If you want to learn more, please visit our website.

Associated Data

Data Availability Statement

The data that support the findings of this study are available from Information Technology Research Center (ITRC) but restrictions apply to the availability of these data, which were used under license for the current study, and so are not publicly available. Data are however available from the authors (Yeong Min Jang, email: yjang@kookmin.ac.kr ) upon reasonable request and with permission of ITRC.

Abstract

Unsafe electrical appliances can be hazardous to humans and can cause electrical fires if not monitored, analyzed, and controlled. The purpose of this study is to monitor the system’s condition, including the electrical properties of the appliances, and to diagnose fault conditions without deploying sensors on individual appliances and analyzing individual sensor data. Using historical data and an acceptable range of normal and leakage currents, we proposed a hybrid model based on multiclass support vector machines (MSVM) integrated with a rule-based classifier (RBC) to determine the changes in leakage currents caused by installed devices at a certain moment. For this, we developed a sensor-based monitoring device with long-range communication to store real-time data in a cloud database. In the modeling process, RBC algorithm is used to diagnose the constructed device fault and overcurrent fault where MSVM is applied for detecting leakage current fault. To conduct an operational field test, the developed device was integrated into some houses. The results demonstrate the effectiveness of the proposed system in terms of electrical safety monitoring and detection. All the collected data were stored in a structured database that could be remotely accessed through the Internet.

Subject terms:

Electrical and electronic engineering, Energy infrastructure

Introduction

In the recent years, incidents of electrical fires have significantly enhanced because of an increasing number of electrical appliances penetrating into electrical distribution systems. In the United States, the third leading cause of fires in homes is cooking and heating equipment, accounting for 10% of the total fire incidents1. Over the last few years, electrical fire incidents caused by the failure, malfunction, or degradation of electrical equipment have caused significant casualties and damages. As the insulation of old or damaged appliances wears off, a higher amount of residual current flows through the appliances which generate a massive amount of heat at a particular point that may result in the insulation getting burned. This causes a short-circuit, which is responsible for most fire incidents involving electrical appliances1. This hidden danger can be effectively eliminated by quickly detecting the causes of faults in appliances through continuous motoring and warning systems. A residual-current device (RCD) that activates depending on a specified threshold is a common and popular device for determining leakage current. Besides the circuit breaker (CB) function, there are no monitoring systems to detect the condition of malfunctioning appliances.

Load monitoring has entered a new era because of the rapid growth of the IoT and cloud computing technologies2. Furthermore, it is a vital technology for assessing appliance usage and consumption, as well as for establishing efficient energy-aware operations and diagnosing any unusual electrical activity in appliances3. Intelligent control, review, and alarm for individual appliances could acquire the appliances’ activities easily, thus offering a viable solution for advanced electrical safety monitoring. Therefore, equipment for monitoring and detecting electrical fires has been developed and used as the most effective tools for preventing and managing electrical fires4. Moreover, as people have become more conscious of electrical safety issues, there has been a growing need for monitoring the health of particular electrical appliances3,5. Hence, the continuous monitoring and analysis of corresponding parameters will be a possible solution to ensure that the equipment is in a safe and serviceable condition.

In6, the ZigBee-based energy monitoring system is deployed in renewable energy and smart home systems, where sensor nodes are developed to perform switching applications and measure power parameters. With the integration of WiFi technology, Martani et al.7 developed time-series energy consumption monitoring systems by considering human activity and occupancy, and ElShafee et al.8 focused on the smart home system.

Their studies did not consider the leakage current monitoring system that is the key parameter for diagnosing an electrical appliance’s health. Furthermore, the authors focused on long-range (LoRa) based data communication systems when considering the monitoring issue in factories9, PV systems, and smart cities. However, in most cases, the behavior of electrical appliances is not monitored and diagnosed with leakage current and insulation resistance. For understanding the behaviors of the appliance, different types of load categorized approaches (such as semi-intrusive, intrusive, and non-intrusive approaches) have been applied by considering the corresponding parameters10–12. Therefore, the appliance’s leakage current depends on different parameters, such as the applied voltage, insulation, and environmental conditions. In13, the appliance’s leakage current properties are analyzed on the basis of the non-intrusive approach, where the device is deployed in the systems without considering communication gateway protocols. In14, the time-domain waveform of the leakage current of the different insulator strings depending on the weather condition has been monitored where they have not focused on any particular communication technology for data acquisition. In high-voltage insulators, an alternative approach (i.e., radio service technology) is used to send data using optoelectronic sensors15. In16, the leakage current monitoring for outdoor insulator and distribution surge arrester has been performed, where the LabVIEWTM platform was used for continuous monitoring and data processing instead of a data server. However, the frequency and time-domain analysis of leakage flux and current are used to develop a non-intrusive approach for identifying and discriminating field winding and damper faults on motor starting time17. Moreover, the event detection-based non-intrusive load monitoring methods3,13 are applied to identify the casualties of the appliances. In the literature, they used some appliances and corresponding active and reactive power profiles for identifying them. However, it is difficult to follow the same procedure for each type of appliance while the penetration of them is more frequent. Therefore, the scheme is no longer important without considering incoming loads (new) in the applied system. To mitigate the discriminative classifier problem of the leakage current, the proposed state detection algorithm is being used in the system.

After years of improvement, several artificial intelligence methods have been developed. Among these numerous methods, support vector machine (SVM)18,19, neural networks20 and K-nearest neighbor21 have become prominent topics in fault detection. SVM could theoretically analyze with the help of learning theory concepts. The advantage of the SVM over other machine learning techniques is that it minimizes the structural classification risk of the training classifier whereas other techniques perform empirical risk minimization. In addition, it has the potential to handle various large classification problems with large feature spaces and can reach feasible performance in practical problems. However, the proposed system could not deal with the unsupervised learning-based method because of the dynamic electrical appliance characteristic.

The SVM is being applied for detecting the faulty condition of the circuit breakers (CB) based on historic vibration measurement data22. Liu et al. proposed a hybrid defect diagnostic model for water quality monitoring devices based on multiclass support vector machines (MSVM)23. For diagnosing the faulty condition of three-phase induction motor with an external rotor-bearing system, Gangsar et al. has applied the MSVM algorithm while the features are obtained from the time-domain current and vibration signals24. By using features from interharmonic voltages, the MSVM identifies the fault positions within the defective zone25. Therefore, Kazemi et al. developed the extended Kalman filter-based SVM model to classify the three-phase residual currents in the primary winding of a transformer, where three residual signals are defined as the discrepancies between the measured and estimated three-phase currents26. ESlami et al. adopted SVM for identifying high impedance arcing failures in a distributed generation integrated microgrid where principal component analysis and the Pearson correlation coefficient technique were used to scale down and select features, respectively27. The Ref28 offers a k-means-based classification algorithm for finding abnormalities in the residual current of a solar system. To identify the residual current defect in low voltage distribution networks, a cooperative training classification model based on an upgraded squirrel search method for a semi-supervised SVM and the k-nearest neighbor is applied in29. A protection strategy based on least squares-SVM is designed and developed for residual current and touch current30. All aforementioned study deal with SVM based different strategies for fault detection in different systems where the proposed system developed rule-based classifiers for detecting sensor fault and load current fault and MSVM is applied for leakage current fault through proper classification in a household environment. All of the aforementioned studies focus on SVM-based fault detection algorithms for various systems. On the contrary, the proposed system developed rule-based classifiers (RBC) for detecting sensor failure and load current fault, while MSVM is used for leakage current fault in a household environment through proper classification.

In this study, we propose a fault detection and monitoring system for electrical appliances based on RBC and MSVM. We design and build a microcontroller-based LoRa-sensor-node for data acquisition because of the low power consumption and long-range features of LoRa-based communication networks. We also integrate an AC-DC buck converter to supply power to the sensor. Following that, the system’s real-time fault is detected by RBC-MSVM model. Moreover, this is the first attempt to integrate RBC and MSVM for electrical system fault detection, which contributes to the advancement of monitoring systems in electrical appliances. Unlike in previous studies, the monitoring systems are no longer limited, specifically, in many electrical appliances. Since electrical characteristics may be easily interpreted, this cloud and classification-based continuous monitoring approach is preferred in many electrical systems. Unlike other existing safety devices, such as RCDs, miniature circuit breaker, and molded case circuit breaker, this will ensure the electrical system’s hazard-free operation. In contrast, the proposed system detects leakage current faults by classifying and differentiating them based on correlation and permissible limits acquired from a large amount of historical data in the corresponding system. The permissible range differed according to the system’s conditions; hence, the proposed scheme recognizance this issue because of higher precision.

The following are the advantages of using the proposed framework: All the possible electrical parameters can be known using a single device. Long-range communication is possible because of the deployed LoRa module. Data server will provide essential storage space for handling massive data from a large number of users. Applying the proposed technique for classifying the normal current and the leakage current will help in identifying the causes of fire in the systems. The real-time detection strategy allows to know the system condition before severe damage occurs due to the implementation of multi-class classification. The user may monitor and recognize the present state of the building owing to the accessibility of the web server. The main contributions of our paper are: an integrated safety monitoring device (SMD) based on LoRa is designed and developed by which the electrical parameters can be measured. A sensitivity-based algorithm is implemented for observing and defining the system’s conditions by providing warning specifications. Smooth coordination is enabled through cloud-based control and management architecture for visualization, monitoring, and storing of real-time data. An RBC-MSVM based classifier is used to examine the system’s conditions where the feature selection method has been applied to obtain higher accuracy.

This manuscript is organized as follows: “Methodology” section covers the proposed system’s modeling such as device construction, mathematical modeling, and detection mechanism. “Results and discussion” section contains the simulation findings as well as the explanation that goes along with them. The conclusion of the proposed system is provided in “Conclusion” section.

Methodology

The proposed system focuses on reducing fires caused by electrical appliances in any location through prompt, dependable monitoring and the use of a control scheme. The proposed system’s framework is depicted in Fig.  ; the process involves collaboration among SMDs, gateway systems, cloud servers, databases, detection algorithms, and visualization. SMDs are used for data acquisition, as shown in Fig.  , and other necessary features are calculated from the data. Each consumer’s data is transmitted via multiple LoRa gateway channels and uploaded to a cloud server at irregular intervals. The proposed algorithm then categorizes the data based on the acceptable range of leakage current and the number of active appliances. The data from different places are stored and analyzed on the cloud platform because of the increasing number of installed SMDs. Afterward, we applied the proposed RBC-MSVM algorithm to identify the system’s abnormalities.

Open in a separate window

Figure illustrates an overview of the proposed methodology, demonstrating the flows of sensing data and information to the cloud database. The system is divided into three parts: the appliance, the database, and the analysis. The appliance section is in charge of acquiring data and transmitting it to the data server via the LoRa module. The database section aims to collect and store sensor data in the database. The relationship between different variables was evaluated in the analysis section to identify the high coloration. Envisaging the households’ appliance specifications, we ascertained the acceptable leakage current to classify the system’s abnormalities. The proposed algorithm will determine the present circumstance regarding the system’s existing issue by investigating the historical data. Furthermore, the analysis section displays the real-time load profiles, leakage current profiles, and the system’s condition. In the following subsection, the detailed methodology is described with other relevant information.

Open in a separate window

Device modeling and specification

The schematic diagram of the electrical safety monitoring device is shown in Fig.  . The device is designed for a single-phase connection rated at 220–380 V (AC) and has the following dimensions: width: 37.5 mm, length: 64.6 mm, and height: 38.2 mm. The LoRa device includes several sensors that measure electrical parameters such as total current, terminal voltage, and leakage currents. From the measured data, we calculated the additional data required for each case, such as total power flow, energy consumption, power factor, resistive and capacitive leakage currents, and insulation resistance. Furthermore, we design in such a way that a multi-step warning signal about the permissible range of total current and residual current concerning the CB’s capacity is provided.

Open in a separate window

The STM32L microcontroller unit (MCU) handles the overall computation and data indexing. Low-Pass filter and Voltage-Divider are being used in the hardware for better analog data acquisition. Moreover, the STM32L MCU is integrated into the LoRa transceiver device in the proposed system to observe and make a difference in normal conditions. The LoRa system is consisted of end devices, gateways, and a network server that form a star topology with the network server at the root, gateways at level one, and end devices as leaves. The sensed and measured information are accumulated into each LoRa packet. One dedicated channel has been assigned for transmitting the LoRa packet in such an interval that the device remains idle for a certain period in normal operation to reduce power consumption. Furthermore, the device transmits data at very short intervals during the transition from normal to critical conditions. The used LoRa module (SX1276), which is connected to the MCU, sends these data packets to the LoRa gateway module via the 902–928 MHz omnidirectional antenna with a maximum gain of 2dBi. The LoRa network operates in the sub-GHz industrial, scientific, and medical band with maximum transmit powers of 21.7 dBm and 14 dBm in the USA and Europe, respectively31. The LoRa modulation (proprietary chirp spread spectrum modulation) uses different types of physical layer packets with different lengths in time, parameterized by the so-called spreading factor (SF), which can take values SF∈Z|7≤SF≤12. The LoRa gateway is used to detect the fault location over a thousand meters because of its proprietary large area coverage32. The SF depends on the communication range’s requirement, where the low value of SF means low coverage and vice versa. To store the transmitted data, the interface between the LoRa gateway and the network server is provided by cellular Internet protocol that uses the standard transmission control protocol (TCP).

Mathematical formulation

Figure shows each possible approach of excessive leakage current flow. We demonstrated three scenarios: an insulation fault between the line and the ground, an insulation fault between the line and the neutral, and an appliance fault with the ground. However, Fig.  depicts the connection diagram and workflow of the proposed constructed device, which is deployed at the entry point of a low voltage power (i.e., 220–380 V) line in an electrical system (i.e., building, factory, and market). We consider the dynamic characteristic of loads in the proposed systems because electrical appliances are either turned on or off based on the consumer’s demand. The total apparent power of the systems can be defined as follows for N loads:

ST(t)=∑ap=1NPap(t)+jQap(t),

1

where Pi and Qi present the active and reactive power of the individual appliance. Therefore, the total currents entering into the loads (IT(t)=I1(t)+I2(t)+⋯) is as follows:

IT(t)=IZr,in(t)+jIXlc,in(t)

2

IXlc,in(t)=IXl,in(t)-IXc,in(t),

3

where IXl,in(t) and IXc,in(t) are the inductive and capacitive currents of the practical load, respectively and IZr,in(t)=IT(t)cosδI,i and IXlc,in(t)=IT(t)sinδI,in are the resistive and inductive current flowing to the circuit, respectively. The δI,in is also known as the power angle at normal conditions. Similarly, the total amount of returning current IL,T of the system can be defined as follows:

IL,T(t)=IZr,ot(t)+jIXlc,ot(t),

4

where IL,T(t) is defined as the total system current returning to the current sensor. IZr,ot(t)=IL,T(t)cosδI,ot and IXlc,o(t)=IL,T(t)sinδI,ot are the resistive and inductive current flowing to the circuit, respectively. Let’s consider a scenario of the system which is explained in Fig.  .

IT(t)=IL,T(t);at normal condition,IT(t)≠IL,T(t);at leakage current condition.

The total leakage current (IL) flowing out of the connected appliance after considering residual current can be formulated as follows:

IL(t)=IT(t)-IL,T(t)

5

IL(t)=Irl(t)+jIcl(t),

6

where the resistive and capacitive leakage currents are defined as Irl=IL(t)cosδL and Icl(t)=IL(t)sinδL, respectively and δL is the angle between Irl and IL(t). Therefore, insulation impedance (ZL) is equal to the LV bus (VLV) voltage divided by the leakage current that flows through the insulation.

ZL=VLV(t)/IL(t).

7

Open in a separate window

Open in a separate window

The quantity of leakage current is quite minimal when compared to the total load current because it only passes via the large insulating impedance of the faulty appliances during the breakdown of insulation. Figure depicts the vector diagram for measuring leakage current wherein the amount of leakage current has considered as large for better visualization. Since the load current is so high in comparison to the IL(t), the total consumed energy does not differ considerably in normal conditions.

Open in a separate window

Data acquisition and classification

Figure shows the SMD device layout. There are two current sensors and one voltage sensor. One current sensor measures the total current of the system and the other sensor measures the leakage current of the system. For measuring the voltage, the terminal of the two wires should be placed as shown in Fig.  . For measuring the current, the current sensor is only placed on the single wire while both of the wires will be entered inside the leakage current sensor. The leakage current sensor actually measures the difference between the two currents which is described in the Mathematical formulation section. For measuring the phase shift between voltage and current, two operational amplifiers are used for zero-cross detection. Thereafter, both outputs are used as input of an XOR gate. The ON-time of XOR output ( i.e. time difference between two phases) is used to determine the phase shift between voltage and current. Finally, the power factor (p.f.) of the system is measured which is used to determine active and reactive components of the current.

δI=f×dtVI×360,

8

p.f.=CosδI,

9

where f and dtVI are defined as frequency and XOR output ON-time, respectively. For measuring the leakage current, we have used a leakage current sensor which is shown in Fig.  . By using the leakage current and voltage sensor data, the phase angle (δL) between leakage current and terminal voltage is calculated, similarly. Thereafter, the resistive and capacitive leakage current are measured for the system, accordingly.

δL=f×dtVIL×360,

10

where f and dtVIL are defined as frequency and XOR output ON-time, respectively.

Open in a separate window

However, to ensure greater system security, three warning types are provided. In this case, the over-current protection warning is designed based on the capacity of the deployed CB, whereas a multi-step warning is designed for leakage current protection by differentiating between resistive and capacitive residual currents. The consecutive state of the system SoS(t) for any consumer is classified by considering the system’s condition.

SoS(t)=SoSN;System runs at normal conditionSoSW;System runs at warning conditionSoSC;System runs at abnormal condition.

11

In the proposed scheme, we account for the two factors for classifying state and the other two factors for determining the type of appliance. Depending on the different threshold value ranges, the status is defined as SoS∈SoSIT,SoSIL,SoSIrl,SoSIcl. The dynamic states of the appliances in terms of total current and leakage currents are defined as SoSIT∈SoSITN,SoSITW,SoSITC, SoSIL∈SoSILN,SoSILW,SoSILC because of the envisaging three-level warning. For tracing the type of devices, the vulnerability of resistive SoSIrl∈SoSIrlN,SoSIrlW,SoSIrlC and capacitive leakage currents SoSIcl∈SoSIclN,SoSIclW,SoSIclC will be taken into consideration. Since the amount of current flow is controlled by the number of contracted appliances and their power rating, the threshold range will be determined accordingly. For additional convenience, we have recommended the opportunity of providing different threshold values. The cut off value of the uninterruptible and healthy system can be defined as ThN∈ThITN,ThILN,ThIrlN,ThIclN. In the proposed system, we have considered the intermediate state between the secured and interrupting conditions. The set of range of the interim circumstance of the system is expressed as ThW∈ThITW,ThILW,ThIrlW,ThIclW. The excessive current flow causes vulnerable state in the system that is known as critical condition ThC∈ThITC,ThILC,ThIrlC,ThIclC. Therefore, the sanctioned constraints of distinguishable apprehension for the IT is as follows:

IT,sN≤IT(t)≤IT,eN,IT,sN,IT,eN∈ThITN,

12

IT,sW<IT(t)≤IT,eW,IT,sW,IT,eW∈ThITW,

13

IT,sC<IT(t)≤IT,eC,IT,sC,IT,eC∈ThITC,

14

where ∀IT,sN≈0, ∀IT,eN≈∀IT,sW and IT,eW≈∀IT,sC.

However, the problem associated with leakage current may not remain in the overcurrent flowing system. Consequently, it is mandatory to comprise the leakage current detection to describe whether the system is secured or not. Similarly, the apprehensive state for leakage current will be ascertained based on the following constraints:

IL,sN≤IL(t)≤IL,eN,IL,sN,IL,eN∈ThILN,

15

IL,sW<IL(t)≤IL,eW,IL,sW,IL,eW∈ThILW,

16

IL,sC<IL(t)≤IL,eC,IL,sC,IL,eC∈ThILC,

17

where ∀IL,sN≈0, ∀IL,eN≈∀IL,sW and IL,eW≈∀IL,sC. The probability of having a leakage issue in multiple devices at the same time is relatively high because of a complete electrical environment inspection. Hence, differentiating resistive and capacitive leakage currents accelerates the process of finding the corresponding appliances. For this reason, we introduced the acceptable range of leakage current using the conditional statement for investigating hazardous circumstances. Furthermore, the permissible limit of the leakage current varies with appliance type, application, and condition. Therefore, the constraints for a reliable and healthy system are defined as follows:

Irl,sN≤Irl(t)≤Irl,eN,Irl,sN,Irl,eN∈ThIrlN,

18

Icl,sN≤Icl(t)≤Icl,eN,Icl,sN,Icl,eN∈ThIclN,

19

Irl,sW<Irl(t)≤Irl,eW,Irl,sW,Irl,eW∈ThIrlW,

20

Icl,sW≤Icl(t)<Icl,eW,Icl,sW,Icl,eW∈ThIclW,

21

Irl,sC<Irl(t)≤Irl,eC,Irl,sC,Irl,eC∈ThIrlC,

22

Icl,sC≤Icl<Icl,eC,Icl,sC,Icl,eC∈ThIclC,

23

where ∀Irl,sN,∀Icl,sN∈0, ∀Irl,eN≈∀Irl,sW, ∀Icl,eN≈I∀cl,sW ∀Irl,eW≈∀Irl,sC, and ∀Icl,eW≈∀Icl,sC. By applying the given condition in Algorithm 1, we have determined the state of total and leakage currents. Therefore, we have applied Algorithm 2 to identify the current status of resistive leakage in the system. The procedure of finding the capacitive leakage current state is identical to that of determining the resistive leakage current condition; we only provide Algorithm 2 here. Since the boundary of the clusters is very close to each other, the classification algorithm may provide less accuracy. By considering this, we have scaled and re-scaled the features based on the following equations.

Ek(Ck,xi)=(1+Ck2)∗xi,

24

Fk(Ck,xi)=Ek(Ck,xi)∗max(xi)max(Ek(Ck,xi)),

25

Ck

,

where

xi, Fk are presented as kth cluster, ith data of the raw feature, and scaled feature which are selected to make up the cluster’s boundary.

Database and monitoring

The real-time data storing and monitoring added more value to the electrical safety analysis for understanding the system’s circumstances. Since the leakage current problem and the deterioration of the appliance’s insulation occurred over time, a large amount of data is required to accurately determine the condition of the installed equipment as well as the entire system. As a consequence, the cloud database33 is the best option for storing large amounts of data. Cloud computing is a model for providing convenient, on-demand network access to a shared pool of configurable computing resources that can be rapidly provisioned and released with minimal management effort and interaction from service providers. Cloud computing can also help to reduce the administrative burden of program management. The cloud environment enables very diverse data sources to gather information, store it in the cloud database, and feed distinct applications.

In the proposed system, the real-time data packets from the LoRa gateway are sent to the cloud database. On a Windows 10 PC, MySQL version 8.0.19 (Oracle, Co., Austin, TX, USA)34 was used as a database management system in the cloud (Microsoft, Redmond, WA, USA). MySQL is a multi-threaded, robust, and scalable open-source service, the platform used under either Oracle’s GNU General Public License or a standard business permit. However, the sensor data collected by the gateway is not uniform and contains noise. Following that, the database server begins intensive computational processing (such as summation, statistics, and data conversion). Finally, the data from several users are stored in the database, which will be used for further processing (such as feature extraction, training, and prediction).

Fault classification and detection

In the proposed system, RBC has been applied to determine the device and over-current fault. And MSVM has been used as a discriminative classifier of the system conditions. The flow chart of detecting faults is shown in Fig.  . In our cases, four rules are generated to diagnose the faults describes as follows:

• Rule1: IF (Sensing data = yes) AND (Current level = normal) THEN the system goes normal

• Rule2: IF (Sensing data = yes) AND (Current level = abnormal) THEN the system goes over-current fault

• Rule3: IF (Sensing data = no) AND (Current level = normal) THEN the system goes device fault

• Rule4: IF (Sensing data = no) AND (Current level = abnormal) THEN the system goes both device and over-current faults

For better classification accuracy, data cleaning, including duplicate and missing data, is conducted prior to categorizing the faulty condition. We have used Pearson’s correlation coefficient-based technique35 to remove unnecessary and redundant information and minimize complexity and dimensionality in the proposed system. The density of correlation depends on the Pearson correlation coefficient known as Pearson’s r. Let’s consider two variable matrix ST=[ST1,ST2,⋯,STq] and IL=[IL1,IL2,⋯,ILq], where q and q are represented as samples: γST¯=1q∑aqSTa and γIL¯=1q∑bqILb. The Pearson correlation co-efficient can be defined as follows:

rST,IL=∑a=1,b=1q,q(STa-γ¯ST)(ILb-γ¯IL)∑a=1q(STa-γ¯ST)2∑b=1q(ILb-γ¯IL)2.

Hengfeng contains other products and information you need, so please check it out.

26

Similarly, the value of r is calculated by taking into account the other variables, with the feature being selected depending on the greater value of r.

Open in a separate window

To classify datasets, it tries to create an optimal hyperplane between two classes of the data set19. The hyperplane acts as a decision boundary to categorize the data into different classes. The points nearer to the hyperplane called support vector, are used to determine the optimized hyperplane. For a given training sample (xi,yi),∀i∈1,2,3,....,n, where yi∈+1,-1 represents class labels, optimal hyperplane is determined by the following mathematical expression:

θTxi+b=0,

27

where θ=θ1,....,θn is n-dimensional vector of weights and xi=x1,x2,....,xn is an n-dimensional input vector, and b is termed as the biasing unit. Here, n represents number of features. The optimization problem associated with finding the hyperplane can be expressed as follows:

min(θ)12∑i=1n(θ)2=12θ2=12θTθ,

28

which is subjected to,

θTxi+b≥+1ifyi=+1,

29

θTxi+b≤+1ifyi=-1.

30

The final nonlinear decision function can be obtained as follows:

f(x)=sign∑i=1nαiθTxi+b.

31

To come up with a set of complex features, SVM uses a technique called Kernel k(xi,x). The value k(xi,x) corresponds to φ(xi).φ(x) which maps linearly non-separable patterns into a higher dimension feature space. Finally, the decision function can be modified as follows:

f(x)=sign∑i=1nαik(xi,x)+b=sign∑i=1nαi(φ(xi).φ(x))+b.

32

In this study, we have performed the classification experiment taking account into four kernel functions (linear, polynomial, radial basis function (RBF), sigmoid) described in Table . Moreover, we have used one versus rest manner multiclass approach. According to this approach, for a mth class classification problem mth class are trained as positive samples while the rest are treated as negative samples21,36.

Table 1

Type of Kernel functionKernel functionLinear

xTxi+c

RBF

exp-x-xi22σ2

Poly

xTxi+cp

Sigmoid

tanhxTxi+c

Open in a separate window

Conclusion

This paper has presented a cloud-based electrical appliance’s health status monitoring system using LoRa connectivity. In this study, starting from designing the sensor until detecting the leakage current fault is elucidated. The scheme aims at developing a data-driven method to learn the permissible range of leakage current in finding the possible features by analyzing the relationship among different variables and detecting the fault by classifying the real-time data. The real-time data is successfully collected and stored in the cloud server through SMD and LoRa gateway. To assess the feasibility and performance of the proposed system, the RBC-MSVM based classification method is implemented on five buildings, yielding the highest accuracy (98.23%) and the F1 score (97.64%) when the system’s circumstances are appropriately distinguished. Furthermore, its fault detection capabilities and rapid detection time (on average 6.67 ms) suggest that it is commercially feasible. The MSVM classifier combined with the Linear/RBF kernel functions and RBC is a promising option for fault diagnosis of electrical safety monitoring equipment, based on the preceding results. In the future, the implementation of fault detection scheme on edge server will enable more accurate analysis of electrical appliance conditions and eliminates the sudden destructive incidents in the electrical system.

Acknowledgements

“This research was supported by the MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center) support program (IITP-2022-2018-0-01396) supervised by the IITP (Institute for Information & Communications Technology Planning & Evaluation)”.

Functions

f(·)

Decision function

k(·)

Kernel function

Parameters

δI

Angle between terminal voltage and current

δL

Angle between terminal voltage and leakage current

N

Number of appliances

θ

Weight vector

b

Biasing unit

Ck

kth

cluster

dtVIL

XOR output ON-time for leakage current

dtVI

XOR output ON-time for total entering current

f

Frequency

Fk

Scaled feature

Icl

Capacitive leakage current

IL,T

Total returning current

IL

Total leakage current

Irl

Resistive leakage current

IT

Total enterning current

IXc

Capacitive current

IXlc

Sum inductive and capacitive current

IXl

Inductive current

IZr

Resistive current

n

Number of features

p.f.

Power factor

P

Total active power

Q

Total reactive power

r

Pearson correlation coefficient

ST

Total apparent power

VLV

Terminal voltage

x

Input vector

ZL

Insulation impedence

Sets, index and subscripts

ap

Index of appliances

e

Index of end

i

Index of data sample

in

Entering moment

j

Complex number

k

Index of cluster

ot

Returning moment

s

Index of start

SoS

Set of state of system

t

Index of time

ThC

Set of threshold for critical condition

ThN

Set of threshold for normal condition

ThW

Set of threshold for warning condition

Author contributions

Conceptualization, M.M.A.; methodology, M.M.A., M.S., and M.H.R.; software, M.M.A. and M.H.R.; resources, H.N., A.T.P., and Y.K.; writing—original draft preparation, M.M.A., M.S., and M.H.R.; supervision, Y.M.J.; project administration, Y.M.J.; funding acquisition, Y.M.J. All authors have read and agreed to the published version of the manuscript.

Data availability

The data that support the findings of this study are available from Information Technology Research Center (ITRC) but restrictions apply to the availability of these data, which were used under license for the current study, and so are not publicly available. Data are however available from the authors (Yeong Min Jang, email: yjang@kookmin.ac.kr ) upon reasonable request and with permission of ITRC.

Competing interests

The authors declare no competing interests.

Footnotes

Publisher's note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

How do I use a leakage current clamp meter?

SINODA

·

Follow

3 min read

·

Dec 28, 2023

--

Leakage Current Clamp Meters are indispensable tools in the realm of electrical maintenance. These devices play a crucial role in ensuring the safety of both individuals and equipment by precisely measuring current leakage. In this article, we delve into the intricacies of Leakage Current Clamp Meters, shedding light on their importance, working principles, applications, and more.

Definition of Leakage Current Clamp Meters

Leakage Current Clamp Meters, often referred to as clamp-on meters, are instruments designed to measure the current flowing in a conductor without the need for physical contact. Their unique design allows for non-invasive measurements, making them ideal for various applications in the field of electrical engineering.

Importance of Measurement

Electrical safety is paramount, and Super Large Leakage Current Clamp Meter play a pivotal role in upholding it. By promptly identifying and measuring leakage currents, these meters prevent potential equipment damage and, more importantly, safeguard against electrical hazards.

Working Principle

Magnetic Field Sensing

One of the key features of Leakage Current Clamp Meters is their reliance on magnetic field sensing. This innovative method enables users to measure current without interrupting the circuit, ensuring efficient and safe operation.

Non-Invasive Current Measurement

Unlike traditional meters that require direct contact with conductors, clamp meters offer a non-invasive solution. This not only enhances user safety but also makes it feasible to measure current in hard-to-reach places.

Applications

Leakage Current Clamp Meters find extensive use in various industries, contributing to both preventive maintenance and quality control. In industrial settings, these meters aid in identifying potential issues before they escalate, minimizing downtime and repair costs.

Types of Leakage Current

Understanding the different types of leakage currents is crucial for effective measurements. Differentiating between conductive and capacitive leakage provides valuable insights into the source of the issue, allowing for targeted solutions.

Choosing the Right Meter

Selecting the appropriate Leakage Current Clamp Meter involves considering several factors, including the type of work, measurement range, and additional features. Professionals must assess their specific needs to make an informed decision.

How to Use a Leakage Current Clamp Meter

Mastering the use of these meters requires a step-by-step approach. This section provides a comprehensive guide, emphasizing safety precautions to ensure accurate measurements without compromising personal well-being.

Calibration and Maintenance

Regular calibration is paramount for the reliability of Leakage Current Clamp Meters. Users will benefit from insights into the importance of calibration and practical tips for ensuring the longevity of their equipment.

Advancements in Technology

The landscape of current measurement is evolving, with smart clamp meters leading the way. Wireless connectivity and advanced features provide unparalleled convenience, enhancing efficiency in various applications.

Case Studies

Real-life examples highlight the practical applications of Leakage Current Clamp Meters. Explore instances where these meters played a decisive role in detecting and resolving electrical issues, showcasing their real-world impact.

Benefits and Challenges

Examining the advantages and potential limitations of Leakage Current Clamp Meters provides a balanced perspective. Professionals can weigh the benefits against challenges to make informed decisions.

Industry Standards

Adherence to industry standards and certifications is crucial for ensuring the accuracy and reliability of measurements. This section delves into the compliance requirements that users should be aware of.

Comparison with Traditional Methods

Leakage Current Clamp Meters offer distinct advantages over traditional current measurement methods. Understanding these differences empowers users to choose the most effective tools for their specific needs.

Troubleshooting Guide

Identifying and resolving common issues with Leakage Current Clamp Meters is essential for maintaining optimal performance. This troubleshooting guide equips users with the knowledge needed to address potential challenges.

Future Trends

Explore the future of current measurement technology with insights into emerging trends. Stay ahead of the curve by understanding the innovations that will shape the landscape of Leakage Current Clamp Meters.

Expert Recommendations

Benefit from expert recommendations on best practices for efficient measurements. Learn from experienced professionals who share valuable insights to optimize the use of Leakage Current Clamp Meters.

Cost Considerations

Balancing budget constraints with the need for reliable equipment is a common challenge. This section provides guidance on choosing cost-effective options without compromising on performance.

Conclusion

In conclusion, mastering the use of Electric instruments and meters​ is a crucial step toward maintaining electrical safety and equipment reliability. Professionals across various industries can leverage the information provided in this article to make informed decisions and enhance their electrical maintenance practices.

An energy and leakage current monitorleakage current monitoring system for ...

How do I use a leakage current clamp meter? | by SINODA