Electric energy meter and acquisition terminal detection system and method

Abstract

The invention discloses an electric energy meter and acquisition terminal detection system and method, and relates to the technical field of electric energy meter and acquisition terminal detection. The system comprises a monitoring terminal, a central control station, a communication network and a CORBA architecture communication interface. The monitoring terminal comprises a high-precision sensor for collecting electric energy meter data, and the electric energy meter data is preprocessed and then transmitted to the central control station through a wired Ethernet network. The central control station diagnoses faults by using an SVM (Support Vector Machine) and a neural network algorithm, judges the fault degree, generates a debugging instruction and feeds back and evaluates the debugging instruction so as to remotely debug the equipment; and the central control station is also provided with a data storage unit and a user interaction interface. The detection system and method can collect data at high frequency and high precision, monitor the equipment state in real time, accurately diagnose the fault type and degree, realize efficient remote debugging, improve the detection efficiency, accuracy and remote detection and control capability, enhance the stability and safety of the system, reduce the operation and maintenance cost, provide powerful guarantee for stable operation of the power system, and improve the safety of the power system. And intelligent development of the power industry is promoted.

Description

Technical Field

[0001] The present invention belongs to the technical field of electric energy meter and data acquisition terminal detection, and in particular relates to an electric energy meter and data acquisition terminal detection system and method. Background Art

[0002] With the continuous development and increasing intelligence of the power system, the performance and reliability of energy meters and data collection terminals as key equipment for power data collection and monitoring are crucial. Traditional detection methods have many problems, such as low detection efficiency, often requiring manual on-site inspections one by one, consuming a lot of time and manpower costs; inaccurate fault diagnosis, relying on simple threshold judgments or empirical judgments, and difficult to accurately locate complex faults; limited remote control and debugging functions, unable to meet the requirements of modern power systems for real-time, accuracy and intelligence, restricting the efficient operation and management of power systems. Summary of the invention

[0003] The purpose of the present invention is to provide an efficient, accurate and intelligent electric energy meter and acquisition terminal detection system, which realizes comprehensive monitoring, accurate fault diagnosis and remote debugging of electric energy meters and acquisition terminals by integrating multiple advanced technologies, including CORBA architecture, intelligent algorithms and stable communication networks.

[0004] To solve the above technical problems, the present invention is achieved through the following technical solutions:

[0005] The present invention is an electric energy meter and a collection terminal detection system, comprising:

[0006] Multiple monitoring terminals, used to collect operation data and status information of the electric energy meter, the operation data includes voltage, current, power, frequency, harmonic data, the status information includes device temperature, communication status data;

[0007] A central control station is connected to the monitoring terminal via a communication network, and is used to receive, process and analyze data sent by the monitoring terminal, and to diagnose, identify and remotely debug faults of the energy meter and the acquisition terminal;

[0008] A communication network, used to realize data transmission and command interaction between the monitoring terminal and the central control station, the communication network includes a wired network and a wireless network;

[0009] The communication interface based on the CORBA architecture is arranged between the monitoring terminal and the central control station to establish a stable and reliable communication connection between the two and ensure the accuracy and integrity of data transmission.

[0010] As a preferred technical solution of the present invention, the monitoring terminal comprises:

[0011] A sensor module, used to collect the operation data and status information of the electric energy meter, the sensor module includes a voltage sensor, a current sensor, a power sensor, a frequency sensor, a harmonic sensor, a temperature sensor and a communication status detection sensor;

[0012] A data acquisition and preprocessing unit, connected to the sensor module, for converting the collected analog signals into digital signals and performing preprocessing operations on the data;

[0013] The communication unit is connected to the data acquisition and preprocessing unit, and is used to send the preprocessed data to the central control station through the communication network, receive the control instructions and debugging instructions sent by the central control station, and feed back the execution results to the central control station.

[0014] As a preferred technical solution of the present invention,

[0015] The accuracy of the voltage sensor is not less than 0.1%;

[0016] The current sensor adopts a Hall effect sensor with a measurement range of 0-50A and an accuracy of not less than 0.2%;

[0017] The accuracy of the power sensor is not less than 0.5%;

[0018] The frequency sensor uses a quartz crystal oscillator with a measurement accuracy of ±0.01Hz;

[0019] The harmonic sensor can measure harmonics of order 2-20 with an accuracy of not less than 1%.

[0020] As a preferred technical solution of the present invention, the central control station includes:

[0021] A data receiving and processing unit, used to receive data sent by the monitoring terminal, and parse, organize and store the data;

[0022] A fault diagnosis and discrimination unit, used for analyzing the data by using an intelligent algorithm to diagnose the fault type and fault degree of the electric energy meter and the acquisition terminal, wherein the intelligent algorithm includes a support vector machine (SVM) algorithm and a neural network algorithm;

[0023] A debugging instruction generating and sending unit, which generates corresponding debugging instructions according to the result of the fault diagnosis and determination unit, and sends the debugging instructions to the monitoring terminal through the communication network;

[0024] A data storage unit, used to store the collected operation data of the electric energy meter and the collection terminal, fault diagnosis results, debugging instructions and feedback data information, the data storage unit adopts a large-capacity hard disk array or a distributed storage system;

[0025] The user interaction interface is used to display monitoring data, fault information, debugging process and results to users, and receive user operation instructions and query requests.

[0026] As a preferred technical solution of the present invention, the SVM algorithm in the fault diagnosis and discrimination unit realizes fault diagnosis in the following manner:

[0027] Collect a large amount of electric energy meter and acquisition terminal data with known fault types and normal operation as training samples, including parameters such as voltage, current, power, frequency, harmonics, and data such as device temperature and communication status;

[0028] The SVM model is trained using the training samples, so that the SVM model constructs an optimal hyperplane that separates different fault types from normal states;

[0029] When new data is input, the SVM model classifies it into different fault types or normal states according to the hyperplane obtained through training, and outputs the classification result of the fault type and the corresponding probability value.

[0030] As a preferred technical solution of the present invention, the neural network algorithm in the fault diagnosis and discrimination unit realizes fault diagnosis and degree assessment in the following manner:

[0031] Construct a multi-layer neural network, including an input layer, a hidden layer and an output layer, wherein the input layer receives various data features of the electric energy meter and the acquisition terminal, the hidden layer extracts features and performs pattern recognition on the input data through nonlinear transformation of neurons, and the output layer outputs prediction results such as fault type and fault degree;

[0032] The neural network is trained using the back-propagation algorithm, which continuously adjusts the connection weights and biases between neurons to minimize the error function between the predicted results and the actual fault conditions.

[0033] When data is input, the neural network outputs the evaluation results of the fault type and fault degree according to the training results, including dividing the fault degree into three levels: mild, moderate and severe, and giving specific quantitative indicators of the fault degree.

[0034] As a preferred technical solution of the present invention, the debugging instructions in the debugging instruction generating and sending unit include reading and modifying device parameters and test start-up operations on specific functional modules, and the debugging instructions are sent to the faulty device through the communication network.

[0035] The present invention also provides an electric energy meter and a data acquisition terminal detection method, using the above detection system, comprising the following steps:

[0036] Data collection step: The monitoring terminal collects the operation data and status information of the electric energy meter according to the preset time interval and collection frequency, and sends it to the central control station through the communication network after pre-processing. The time interval is 1 minute and the collection frequency is 10Hz;

[0037] Remote monitoring steps: The central control station monitors the operating status of the monitoring terminal in real time, sends control instructions to the monitoring terminal through the communication network to achieve remote control, receives status information sent by the monitoring terminal, promptly detects abnormal conditions, and triggers fault diagnosis procedures based on intelligent algorithms;

[0038] Fault diagnosis steps: The central control station uses data mining technology to conduct in-depth analysis of the collected data, uses SVM and neural network algorithms to establish a fault diagnosis model, diagnoses the fault, and issues early warning information, including filtering and feature extraction of the data, and then uses SVM and neural networks to perform fault diagnosis and degree assessment respectively;

[0039] Fault severity determination step: Combine the fault type classification results of SVM and the quantitative evaluation of fault severity by neural network to make a more accurate determination of fault severity and update the determination results in real time according to new data;

[0040] Fault remote debugging steps: Based on the fault diagnosis and severity determination results, the central control station generates debugging instructions and sends them to the faulty device. After the faulty device performs the operation, it feeds back the results to the central control station. The central control station uses a neural network to evaluate the debugging effect based on the feedback data and intelligently adjusts subsequent debugging instructions until the fault is resolved or it is determined that on-site maintenance is required.

[0041] Data storage steps: The central control station stores the collected power quality data, equipment operation status data, fault diagnosis results, debugging instructions and feedback data in the data storage unit, and backs up the data regularly.

[0042] As a preferred technical solution of the present invention, in the remote fault debugging step, if the neural network evaluates that the first debugging instruction does not achieve the expected effect, the central control station adjusts the debugging parameters or tries other debugging methods according to the suggestions of the neural network, generates new debugging instructions and sends them to the faulty device.

[0043] The present invention has the following beneficial effects:

[0044] Improved detection efficiency: The monitoring terminal collects data at specific time intervals and frequencies, and the central control station quickly processes and analyzes data. The fault diagnosis and debugging process is efficient, which reduces the time for fault detection and repair, improves the overall detection efficiency, and reduces manpower and time costs;

[0045] Improved remote inspection and control accuracy: SVM and neural network algorithms accurately diagnose fault types and degrees, and combined with CORBA architecture communication interfaces to ensure accurate data transmission, reduce misjudgments and missed judgments, and lay a solid foundation for the stable operation of the power system;

[0046] Enhanced system stability: Dual-network backup of the communication network ensures stable and continuous data transmission; fault diagnosis and debugging mechanisms solve problems in a timely manner, reduce the risk of power outages caused by equipment failures, and ensure reliable operation of the power system.

[0047] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0049] Figure 1 It is a schematic diagram of the framework structure of the system in the present invention;

[0050] Figure 2 The figure is a flow chart of the method for using the system of the present invention. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] A specific implementation application of the present invention is as follows:

[0053] Embodiment 1

[0054] like Figure 1 As shown: The present invention provides an electric energy meter and acquisition terminal detection system, the system is specifically deployed as follows:

[0055] In the power distribution area of ​​a small town, the electric energy meter and data collection terminal detection system of the present invention is implemented to improve the monitoring and fault handling efficiency of the power equipment in the area and ensure the stability and reliability of the power supply.

[0056] 1. Monitoring terminal deployment

[0057] Monitoring terminals are installed near the installation locations of various electric energy meters in the area. For example, in the power distribution room of a residential area, monitoring terminals are fixed at appropriate locations for different electric energy meters to ensure that their sensor modules can accurately and stably collect the operation data and status information of the electric energy meters.

[0058] The voltage sensor in the sensor module uses a high-precision model with an accuracy of 0.1%. It can accurately measure the voltage value of the energy meter and monitor the small fluctuations of the voltage in real time. For example, during the peak period of electricity consumption in summer, it can keenly capture the voltage changes caused by load changes, providing accurate data support for subsequent fault diagnosis. The current sensor uses a Hall effect sensor with a measurement range of 0-50A and an accuracy of not less than 0.2%. Whether it is the low current state of daily electricity consumption by residents or the sudden increase in current caused by electrical failure, it can accurately measure and feedback. The power sensor has an accuracy of not less than 0.5%, the frequency sensor uses a quartz crystal oscillator with a measurement accuracy of ±0.01Hz, and the harmonic sensor can measure harmonics from 2 to 20 times with an accuracy of not less than 1%. These high-precision sensors work together to comprehensively and accurately collect various operating data of the energy meter, laying a solid foundation for subsequent data processing and fault diagnosis.

[0059] The data acquisition and preprocessing unit is closely connected with the sensor module, which quickly converts the collected analog signals into digital signals and performs preprocessing operations such as filtering and amplification on the data. For example, filtering can remove high-frequency noise interference in the power grid to avoid the impact of such noise on data accuracy; weak signals can be amplified to enhance the strength and stability of the signals, ensuring the reliable quality of data transmitted to the central control station.

[0060] The communication unit is connected to the data acquisition and preprocessing unit, and sends the preprocessed data to the central control station through the communication network, receives the control instructions and debugging instructions sent by the central control station, and promptly feeds back the execution results to the central control station. During the communication process, the communication unit has good stability and compatibility, can adapt to complex electromagnetic environments, and ensure accurate data transmission.

[0061] (II) Central Control Station Setup

[0062] A central control station is set up in the town’s power dispatching center.

[0063] The data receiving and processing unit is responsible for receiving the data sent by the monitoring terminal, and parsing, sorting and storing the data. For example, when receiving the electric energy meter data from different monitoring terminals, it is classified and stored according to the number of the electric energy meter, the collection time and other information, and a detailed database is established to facilitate subsequent query and analysis.

[0064] The fault diagnosis and discrimination unit uses pre-trained SVM and neural network algorithm models to conduct in-depth analysis of the data to diagnose the fault type and degree of the electric energy meter and the acquisition terminal. For example, when an electric energy meter has abnormal power fluctuations and the communication signal strength is weakened, the data is filtered and feature extracted, and then input into the SVM model and the neural network model respectively. The SVM model judges the possible fault types as power measurement module fault and communication module fault based on the hyperplane obtained through training, and outputs the corresponding probability value; the neural network model further evaluates the fault degree as moderate, and gives a specific fault degree quantitative index, such as 0.65 (assuming that 0-1 indicates that the fault degree ranges from mild to severe), to clarify the severity of the fault and provide a scientific basis for the subsequent debugging strategy formulation.

[0065] The debugging instruction generation and sending unit generates corresponding debugging instructions from the preset debugging strategy library according to the results of the fault diagnosis and discrimination unit, and sends them to the monitoring terminal through the communication network. For example, according to the above fault diagnosis results, the instructions for reading the calibration parameters and recalibrating the power measurement module, as well as the instructions for restarting the communication module and detecting the signal strength are generated, and are accurately sent to the corresponding monitoring terminal through the communication network, so as to realize the remote debugging operation of the faulty equipment.

[0066] The data storage unit uses a large-capacity hard disk array to store the collected operation data of the energy meter and the acquisition terminal, fault diagnosis results, debugging instructions, feedback data and other information. At the same time, the data is backed up regularly, using a combination of redundant storage and off-site backup to ensure data security and integrity, prevent data loss due to hardware failure, human error or natural disasters, and provide reliable data support for subsequent data analysis, algorithm optimization and fault handling.

[0067] The user interaction interface provides an intuitive and convenient operation platform for operators to display monitoring data, fault information, debugging process and results to users, and receive user operation instructions and query requests. For example, operators can use this interface to view the dynamic change curves of the voltage, current, power and other operating data of each electric energy meter in real time. When a fault occurs, they can quickly obtain information such as the fault type, fault degree and current debugging progress. At the same time, operators can also manually trigger certain specific detection programs or view historical data through this interface, which is convenient for comprehensive and in-depth understanding and management of the operating status of the power system.

[0068] (III) Communication network construction

[0069] The communication network is built by combining wired and wireless networks. The wired network is based on the Ethernet network of the TCP / IP protocol, and uses standard Category 5 twisted pair cables for wiring to ensure high-speed and stable data transmission. In the process of urban power infrastructure construction, the Ethernet network wiring is planned and laid together with the power lines to ensure that the network covers the installation locations of various monitoring terminals. For example, in the power distribution rooms of residential and commercial areas, the Ethernet network interface is connected to the communication unit of the monitoring terminal to achieve rapid data transmission. The data transmission speed can reach 100Mbps, which meets the needs of real-time monitoring and ensures that the central control station can obtain the latest electricity meter operation data in a timely manner.

[0070] The wireless network uses the wireless GPRS network as a backup network. When the wired network fails or the signal is unstable, the monitoring terminal can automatically switch to the wireless GPRS network for data transmission. For example, when the wired network is interrupted due to force majeure factors such as line construction and natural disasters, the monitoring terminal quickly switches to the wireless GPRS network and continues to transmit data to the central control station to ensure the real-time and continuity of the data, avoid monitoring interruptions due to network problems, and ensure continuous monitoring and management of the power system. At the same time, the base stations of the wireless GPRS network are reasonably distributed and optimally configured to ensure that the signal coverage can cover the entire town's power monitoring area and improve the reliability and stability of communication.

[0071] like Figure 2 As shown: The present invention also provides an operating method of the system:

[0072] 1. Data collection steps

[0073] The monitoring terminal continuously collects the operation data and status information of the energy meter according to the preset parameter settings of 1 minute time interval and 10Hz collection frequency. For example, within every minute, the voltage, current, power and other data of the energy meter are quickly collected 10 times, and the collected data are transmitted to the data acquisition and preprocessing unit in time. The data acquisition and preprocessing unit quickly processes and converts these data, and then sends the processed data to the central control station through the communication unit. In this process, the sensor module always maintains high-precision data collection to ensure the accuracy and integrity of the data, providing rich and reliable data support for subsequent fault diagnosis and analysis.

[0074] 2. Remote monitoring steps

[0075] The central control station monitors the operating status of the monitoring terminal in real time through the communication network, and sends a control command to the monitoring terminal at regular intervals (such as 5 minutes) to achieve remote control. For example, a command to query the status of the monitoring terminal equipment is sent. After receiving the command, the monitoring terminal will feedback its own equipment operating status information (such as sensor working status, communication module signal strength, etc.) to the central control station. The central control station also receives the status information sent by the monitoring terminal. When it is found that the communication signal strength of a certain monitoring terminal is lower than the preset threshold or the operating data of a certain electric energy meter fluctuates abnormally, the fault diagnosis program based on the intelligent algorithm is immediately triggered to quickly diagnose and analyze possible faults, discover potential problems in time, and take corresponding measures to deal with them, thereby improving the system's response speed and fault prevention capabilities.

[0076] (III) Troubleshooting steps

[0077] When the fault diagnosis program is triggered, the central control station uses data mining technology to conduct in-depth analysis of the collected data, uses SVM and neural network algorithms to establish a fault diagnosis model, diagnoses the fault, and issues early warning information. Specifically, the data is first filtered to remove noise and interference, and a digital filter is used to smooth the data to improve the quality of the data. Then feature extraction is performed to extract useful features from the power data and equipment operation status data, such as the load characteristics, operation mode, and communication signal strength of the power meter. Then, the feature data is input into the SVM model and the neural network model for fault diagnosis and degree assessment. The SVM model classifies the fault type according to the hyperplane obtained through training. For example, the fault is divided into different types such as power meter hardware failure, acquisition terminal communication failure, and data processing abnormality failure, and outputs the classification results of the fault type and the corresponding probability value. The neural network model outputs the evaluation results of the fault type and fault degree, including dividing the fault degree into three levels: mild, moderate and severe, and giving specific quantitative indicators of the fault degree. For example, for a metering error fault of an electric energy meter, it is judged to be a moderate fault, and the fault degree quantitative indicator is 0.7, thereby achieving a comprehensive and accurate diagnosis of the fault and providing a reliable basis for subsequent fault repair.

[0078] (IV) Steps for determining the degree of fault

[0079] Combining the SVM classification results of fault types and the neural network's quantitative evaluation of fault severity, the fault severity can be more accurately judged. For example, when SVM determines that a certain fault is a voltage sampling fault of the electric energy meter, the neural network further analyzes the severity of the fault and gives a specific fault severity index based on the deviation size and duration of the voltage sampling data, such as a fault severity score of 0.68 (assuming that 0-1 indicates that the fault severity ranges from mild to severe). At the same time, as new data is continuously collected and analyzed, the system can adjust the judgment of the fault severity in a timely manner to adapt to changes in the fault situation. For example, if the deviation of the voltage sampling data is found to be gradually reduced in subsequent monitoring, the neural network will update the fault severity judgment results in real time based on the new data, and adjust the fault severity from the original moderate to mild, providing a more accurate basis for the formulation of subsequent debugging strategies and improving the flexibility and accuracy of fault diagnosis.

[0080] (V) Fault remote debugging steps

[0081] According to the fault diagnosis and degree judgment results, the central control station generates a debugging instruction and sends it to the faulty device. For example, for the above-mentioned moderate voltage sampling fault of the energy meter, an instruction is generated to adjust the gain parameter or calibration parameter of the voltage sampling circuit, and sent to the corresponding monitoring terminal through the communication network. After the faulty device executes the operation, the result is fed back to the central control station, and the central control station uses the neural network to evaluate the debugging effect based on the feedback data. If the neural network evaluates that the first debugging instruction does not achieve the expected effect, such as the deviation of the voltage sampling data has not been significantly improved, the central control station adjusts the debugging parameters according to the suggestions of the neural network, such as further increasing the adjustment range of the gain parameter, or trying other debugging methods, such as starting the self-test program of the voltage sampling circuit, etc., generates a new debugging instruction and sends it to the faulty device until the fault is resolved or it is determined that on-site maintenance is required. In this process, the debugging instruction generation and sending unit can quickly generate personalized debugging instructions according to different fault diagnosis results, and realize accurate debugging of the energy meter and the acquisition terminal through remote control, avoiding the cumbersome and inefficient traditional on-site debugging methods, greatly improving the efficiency of fault repair, shortening equipment downtime, reducing operation and maintenance costs, and improving the reliability and stability of the power system.

[0082] (VI) Data storage steps

[0083] The central control station stores the collected power quality data, equipment operation status data, fault diagnosis results, debugging instructions and feedback data in the data storage unit, and backs up the data regularly. For example, at 2 a.m. every day, the system automatically starts the data backup program and backs up the data of the previous day to a storage server in a different location. It uses a combination of incremental backup and full backup to ensure the security and integrity of the data. By storing and managing a large amount of data, it provides rich data resources for subsequent data analysis, algorithm optimization and fault handling, which helps to continuously improve the performance and accuracy of the detection system. For example, by analyzing historical fault data, it can be found that certain types of faults have a high incidence trend in specific seasons or time periods, so as to take preventive measures in advance, optimize fault diagnosis models and debugging strategies, improve the intelligence level and adaptability of the system, and further improve the operation and management efficiency of the power system.

[0084] Through the actual application of this embodiment in the power distribution area of ​​the small town, multiple faults of electric energy meters and acquisition terminals were successfully detected within a period of time, including communication module failures caused by lightning strikes, sensor accuracy degradation failures caused by long-term use, and abnormal data processing failures caused by software vulnerabilities. Through the detection system and method of the present invention, the type and degree of faults are diagnosed in a timely and accurate manner, and most faults are quickly repaired through the remote debugging function. For some faults that cannot be repaired remotely, the problem can also be accurately located, providing detailed and accurate information for on-site maintenance, greatly shortening the fault repair time, improving the reliability and stability of the power system, and reducing the operation and maintenance costs. The effectiveness and practicality of the present invention in the actual power system are verified, and strong support is provided for the intelligent management and efficient operation of the power system, which has a good prospect for promotion and application. .

[0085] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0086] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. An electric energy meter and collection terminal detection system, characterized in that: include: Multiple monitoring terminals, used to collect operation data and status information of the electric energy meter, the operation data includes voltage, current, power, frequency, harmonic data, the status information includes device temperature, communication status data; A central control station is connected to the monitoring terminal via a communication network, and is used to receive, process and analyze data sent by the monitoring terminal, and to diagnose, identify and remotely debug faults of the energy meter and the acquisition terminal; A communication network, used to realize data transmission and command interaction between the monitoring terminal and the central control station, the communication network includes a wired network and a wireless network; The communication interface based on the CORBA architecture is arranged between the monitoring terminal and the central control station to establish a stable and reliable communication connection between the two and ensure the accuracy and integrity of data transmission.

2. The electric energy meter and data collection terminal detection system according to claim 1, characterized in that: The monitoring terminal comprises: A sensor module, used to collect the operation data and status information of the electric energy meter, the sensor module includes a voltage sensor, a current sensor, a power sensor, a frequency sensor, a harmonic sensor, a temperature sensor and a communication status detection sensor; A data acquisition and preprocessing unit, connected to the sensor module, for converting the collected analog signals into digital signals and performing preprocessing operations on the data; The communication unit is connected to the data acquisition and preprocessing unit, and is used to send the preprocessed data to the central control station through the communication network, receive the control instructions and debugging instructions sent by the central control station, and feed back the execution results to the central control station.

3. The electric energy meter and data collection terminal detection system according to claim 2, characterized in that: The accuracy of the voltage sensor is not less than 0.1%; The current sensor adopts a Hall effect sensor with a measurement range of 0-50A and an accuracy of not less than 0.2%; The accuracy of the power sensor is not less than 0.5%; The frequency sensor uses a quartz crystal oscillator with a measurement accuracy of ±0.01Hz; The harmonic sensor can measure harmonics of order 2-20 with an accuracy of not less than 1%.

4. The electric energy meter and data collection terminal detection system according to claim 1, characterized in that: The central control station comprises: A data receiving and processing unit, used to receive data sent by the monitoring terminal, and parse, organize and store the data; A fault diagnosis and discrimination unit, used for analyzing the data by using an intelligent algorithm to diagnose the fault type and fault degree of the electric energy meter and the acquisition terminal, wherein the intelligent algorithm includes a support vector machine (SVM) algorithm and a neural network algorithm; A debugging instruction generating and sending unit, which generates corresponding debugging instructions according to the result of the fault diagnosis and determination unit, and sends the debugging instructions to the monitoring terminal through the communication network; A data storage unit, used to store the collected operation data of the electric energy meter and the collection terminal, fault diagnosis results, debugging instructions and feedback data information, the data storage unit adopts a large-capacity hard disk array or a distributed storage system; The user interaction interface is used to display monitoring data, fault information, debugging process and results to users, and receive user operation instructions and query requests.

5. The electric energy meter and data collection terminal detection system according to claim 4, characterized in that: The SVM algorithm in the fault diagnosis and discrimination unit implements fault diagnosis in the following way: Collect a large amount of electric energy meter and acquisition terminal data with known fault types and normal operation as training samples, including parameters such as voltage, current, power, frequency, harmonics, and data such as device temperature and communication status; The SVM model is trained using the training samples, so that the SVM model constructs an optimal hyperplane that separates different fault types from normal states; When new data is input, the SVM model classifies it into different fault types or normal states according to the hyperplane obtained through training, and outputs the classification result of the fault type and the corresponding probability value.

6. The electric energy meter and data collection terminal detection system according to claim 4, characterized in that: The neural network algorithm in the fault diagnosis and discrimination unit realizes fault diagnosis and degree assessment in the following ways: Construct a multi-layer neural network, including an input layer, a hidden layer and an output layer, wherein the input layer receives various data features of the electric energy meter and the acquisition terminal, the hidden layer extracts features and performs pattern recognition on the input data through nonlinear transformation of neurons, and the output layer outputs prediction results such as fault type and fault degree; The neural network is trained using the back-propagation algorithm, which continuously adjusts the connection weights and biases between neurons to minimize the error function between the predicted results and the actual fault conditions. When data is input, the neural network outputs the evaluation results of the fault type and fault degree according to the training results, including dividing the fault degree into three levels: mild, moderate and severe, and giving specific quantitative indicators of the fault degree.

7. The electric energy meter and data collection terminal detection system according to claim 4, characterized in that: The debugging instructions in the debugging instruction generating and sending unit include reading and modifying device parameters and test start-up operations on specific functional modules, and the debugging instructions are sent to the faulty device through the communication network.

8. A method for detecting an electric energy meter and a data collection terminal, using the detection system according to any one of claims 1 to 7, characterized in that: The following steps are involved: Data collection steps: The monitoring terminal collects the operation data and status information of the electric energy meter according to the preset time interval and collection frequency, and sends it to the central control station through the communication network after pre-processing; Remote monitoring steps: The central control station monitors the operating status of the monitoring terminal in real time, sends control instructions to the monitoring terminal through the communication network to achieve remote control, receives status information sent by the monitoring terminal, promptly detects abnormal conditions, and triggers fault diagnosis procedures based on intelligent algorithms; Fault diagnosis steps: The central control station uses data mining technology to conduct in-depth analysis of the collected data, uses SVM and neural network algorithms to establish a fault diagnosis model, diagnoses the fault, and issues early warning information, including filtering and feature extraction of the data, and then uses SVM and neural networks to perform fault diagnosis and degree assessment respectively; Fault severity determination step: Combine the fault type classification results of SVM and the quantitative evaluation of fault severity by neural network to make a more accurate determination of fault severity and update the determination results in real time according to new data; Fault remote debugging steps: Based on the fault diagnosis and severity determination results, the central control station generates debugging instructions and sends them to the faulty device. After the faulty device performs the operation, it feeds back the results to the central control station. The central control station uses a neural network to evaluate the debugging effect based on the feedback data and intelligently adjusts subsequent debugging instructions until the fault is resolved or it is determined that on-site maintenance is required. Data storage steps: The central control station stores the collected power quality data, equipment operation status data, fault diagnosis results, debugging instructions and feedback data in the data storage unit, and backs up the data regularly.

9. The method for detecting an electric energy meter and a data collection terminal according to claim 8, characterized in that: In the remote fault debugging step, if the neural network evaluates that the first debugging instruction does not achieve the expected effect, the central control station adjusts the debugging parameters or tries other debugging methods according to the neural network's suggestions, generates new debugging instructions and sends them to the faulty device.

Images