Electric energy meter fault self-detection method and device

Abstract

The invention discloses an electric energy meter fault self-detection method and device, and relates to the technical field of electric power detection, and the method comprises the steps: obtaining a core part of an electric energy meter; performing equipment self-monitoring on the core component to obtain a self-monitoring data set, and inputting the self-monitoring data set into a working condition monitoring module for working condition judgment to obtain a working condition judgment result; based on historical fault monitoring records, a fault expert knowledge base is established, and a fault prediction model and a fault diagnosis model are trained and embedded into a comprehensive diagnosis unit; and receiving the self-monitoring data set and the working condition judgment result through a comprehensive diagnosis unit, carrying out fault detection, and carrying out operation and maintenance on the electric energy meter based on a fault detection result. The electric energy meter fault self-detection method solves the technical problem that an existing detection method has hysteresis quality and affects the accuracy of electric energy meter fault detection and the operation and maintenance response speed, and achieves the technical effect of improving the accuracy of detection and the operation and maintenance response speed through electric energy meter fault self-detection.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power detection, and in particular to a method and device for self-detecting faults of an electric energy meter. Background Art

[0002] The energy meter is an indispensable device in the power system, used to measure, record and report the consumption of electric energy. Therefore, the accuracy and reliability of the energy meter are crucial to the stable operation of the power system. However, most of the current energy meter devices do not have fault self-detection and fault diagnosis functions, and cannot accurately locate and quickly handle faults. Relying on the technical capabilities of service personnel cannot meet the rapid operation and maintenance response of the energy meter calibration device. Summary of the invention

[0003] The present application provides a method and device for self-detection of electric energy meter faults, which are used to solve the technical problem of improving the detection accuracy and operation and maintenance response speed through self-detection of electric energy meter faults in the prior art.

[0004] The first aspect of the present application provides a method for self-detection of electric energy meter faults, the method comprising: obtaining multiple core components of the electric energy meter, the multiple core components comprising a standard electric energy meter, a signal source, an error calculator and a power source; performing equipment self-monitoring on the multiple core components to obtain multiple self-monitoring data sets, the multiple self-monitoring data sets comprising operating parameter sequences and environmental data sequences of the multiple core components; inputting the multiple self-monitoring data sets into a working condition monitoring module to perform working condition determination and obtain working condition determination results; establishing a fault expert knowledge base based on historical fault monitoring records, and based on the fault expert knowledge base, training a fault prediction model and a fault diagnosis model and embedding them into a comprehensive diagnosis unit; receiving the multiple self-monitoring data sets and the working condition determination results through the comprehensive diagnosis unit, performing fault detection and obtaining fault detection results; and performing operation and maintenance of the electric energy meter based on the fault detection results. Specifically comprising the following steps:

[0005] P10: Obtain the core components of the energy meter, including the standard energy meter, signal source, error calculator and power source.

[0006] P20: Perform equipment self-monitoring on the core component to obtain multiple self-monitoring data sets, wherein the self-monitoring data sets include an operating parameter sequence and an environmental data sequence of the core component.

[0007] P30: Input the self-monitoring data set into the working condition monitoring module to perform working condition determination and obtain the working condition determination result.

[0008] P40: Based on the historical fault monitoring records, a fault expert knowledge base is established, and based on the fault expert knowledge base, the fault prediction model and fault diagnosis model are trained and embedded into the comprehensive diagnosis unit.

[0009] P50: Receive the self-monitoring data set and the operating condition determination result through the comprehensive diagnosis unit, perform fault detection, and obtain the fault detection result.

[0010] P60: Perform operation and maintenance of the electric energy meter based on the fault detection result to ensure normal operation and metering of the electric energy meter.

[0011] The second aspect of the present application provides an electric energy meter fault self-detection device, which includes: a core component acquisition module, a self-monitoring data set acquisition module, an operating condition determination module, a comprehensive diagnosis unit construction module, a fault detection module and an electric energy meter operation and maintenance module.

[0012] The core component acquisition module is used to acquire multiple core components of the electric energy meter, and the multiple core components include a standard electric energy meter, a signal source, an error calculator and a power source; the self-monitoring data set acquisition module is used to perform equipment self-monitoring on the multiple core components and obtain multiple self-monitoring data sets, and the multiple self-monitoring data sets include operating parameter sequences and environmental data sequences of multiple core components; the working condition determination module is used to input the multiple self-monitoring data sets into the working condition monitoring module to perform working condition determination and obtain working condition determination results; the comprehensive diagnosis unit construction module is used to establish a fault expert knowledge base based on historical fault monitoring records, and based on the fault expert knowledge base, train a fault prediction model and a fault diagnosis model to be embedded in the comprehensive diagnosis unit; the fault detection module is used to receive the multiple self-monitoring data sets and the working condition determination results through the comprehensive diagnosis unit, perform fault detection, and obtain fault detection results; the electric energy meter operation and maintenance module is used to perform electric energy meter operation and maintenance based on the fault detection results.

[0013] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0014] The present application provides a method for self-detection of electric energy meter faults, which relates to the field of electric power detection technology. The method performs equipment self-monitoring on multiple core components of the electric energy meter to obtain multiple self-monitoring data sets, perform working condition judgment, establish a fault expert knowledge base based on historical fault monitoring records, construct a comprehensive diagnosis unit, receive multiple self-monitoring data sets and working condition judgment results, perform fault detection, and perform operation and maintenance of the electric energy meter based on the fault detection results. The method solves the technical problem of improving the detection accuracy and operation and maintenance response speed through self-detection of electric energy meter faults in the prior art, and achieves the technical effect of improving the detection accuracy and operation and maintenance response speed through self-detection of electric energy meter faults. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0016] Figure 1 A schematic diagram of a method for self-detecting faults in an electric energy meter provided in an embodiment of the present application;

[0017] Figure 2 A schematic diagram of a flow chart of constructing a comprehensive diagnosis unit in a method for self-detecting faults of an electric energy meter provided in an embodiment of the present application;

[0018] Figure 3 A schematic diagram of a flow chart of performing fault detection according to multiple self-monitoring data sets and working condition determination results in a method for self-detecting faults of an electric energy meter provided in an embodiment of the present application;

[0019] Figure 4 A schematic diagram of the structure of an electric energy meter fault self-detection device provided in an embodiment of the present application;

[0020] Explanation of the reference numerals: core component acquisition module 11, self-monitoring data set acquisition module 12, working condition determination module 13, comprehensive diagnosis unit construction module 14, fault detection module 15, electric energy meter operation and maintenance module 16. DETAILED DESCRIPTION

[0021] The present application provides a method for self-detection of electric energy meter faults, which is used to solve the technical problem of improving the detection accuracy and operation and maintenance response speed through self-detection of electric energy meter faults in the prior art.

[0022] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0023] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, device, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices.

[0024] Embodiment 1

[0025] like Figure 1 As shown, the present application provides a method for self-detection of electric energy meter faults, the method comprising:

[0026] P10: Acquire multiple core components of the electric energy meter, wherein the multiple core components include a standard electric energy meter, a signal source, an error calculator, and a power source;

[0027] Specifically, multiple core components of the target electric energy meter are obtained, and the multiple core components include a standard electric energy meter, a signal source, an error calculator and a power source, wherein the standard electric energy meter is used as a reference benchmark to calibrate and verify the measurement accuracy of the target electric energy meter. The standard electric energy meter usually has high precision and stability and can provide reliable electric energy metering data. The signal source can provide various input signals required by the target electric energy meter, such as voltage, current, etc. The quality and stability of the signal source directly affect the measurement accuracy and performance of the target electric energy meter. The error calculator is used to calculate the measurement error of the electric energy meter. The error of the target electric energy meter can be calculated by comparing the measurement data of the standard electric energy meter with the measurement data of the target electric energy meter, and it can be determined whether it is within the allowable error range. The power source can provide the required electric energy supply for the electric energy meter. By obtaining multiple core components of the electric energy meter, targeted fault detection can be performed to improve the reliability of the ammeter.

[0028] P20: Perform equipment self-monitoring on the multiple core components to obtain multiple self-monitoring data sets, where the multiple self-monitoring data sets include operating parameter sequences and environmental data sequences of the multiple core components;

[0029] Furthermore, step P20 of the embodiment of the present application further includes:

[0030] P21: Preset the self-monitoring cycle and determine the key monitoring parameters, which include component operation parameters and environmental parameters;

[0031] P22: Deploy sensors based on the key monitoring parameters and configure sensor modules;

[0032] P23: Based on the self-monitoring period, the operating parameters and environmental parameters of the multiple core components are collected in real time by the sensor module and serialized to obtain multiple operating parameter sequences and multiple environmental data sequences;

[0033] P24: Construct the multiple self-monitoring data sets from the multiple operating parameter sequences and the multiple environmental data sequences.

[0034] Optionally, perform equipment self-monitoring for the multiple core components, collect the operating status information and operating environment information of the multiple core components in real time, and form multiple self-monitoring data sets. Specifically, according to the actual usage and performance requirements of the target electric energy meter, preset the self-monitoring cycle, that is, the frequency or time interval for self-monitoring. For example, you can choose to perform self-monitoring once a day, every hour, or every minute. Further, determine key monitoring parameters, the key monitoring parameters include component operating parameters and environmental parameters, wherein the component operating parameters include voltage, current, power, temperature, etc., which can reflect the working status of the electric energy meter and its core components, and the environmental parameters include temperature, humidity, air pressure, etc., which are environmental parameters that may affect the performance and measurement accuracy of the electric energy meter.

[0035] Furthermore, according to the determined key monitoring parameters, corresponding types and quantities of sensors are selected for deployment, and according to the layout and structure of the electric energy meter, the sensor module is reasonably configured to ensure that the components and parameters that need to be monitored can be fully covered. During the self-monitoring period, the operating parameters and environmental parameters of the core components of the electric energy meter are collected in real time through the sensor module, and serialized according to the time sequence of data collection to obtain multiple operating parameter sequences and multiple environmental data sequences.

[0036] Furthermore, the multiple operating parameter sequences and multiple environmental data sequences are combined to construct the multiple self-monitoring data sets, each of which contains an operating parameter sequence and an environmental data sequence of a core component over a period of time, which can provide data support for subsequent fault detection and analysis.

[0037] P30: Inputting the plurality of self-monitoring data sets into the working condition monitoring module to perform working condition determination and obtain working condition determination results;

[0038] Furthermore, step P30 of the embodiment of the present application further includes:

[0039] P31: Obtaining design operating condition information, wherein the design operating condition information includes a plurality of standard operating performance indicators, wherein the plurality of standard operating performance indicators include but are not limited to the accuracy, stability and response time of the electric energy meter;

[0040] P32: constructing the working condition monitoring module based on the plurality of standard working performance indicators as constraints;

[0041] P33: Based on the multiple self-monitoring data sets, multiple real-time working performance values ​​are calculated and input into the working condition monitoring module to perform working condition determination to obtain working condition determination results, wherein the working condition determination results are normal or abnormal.

[0042] In a possible embodiment of the present application, the multiple self-monitoring data sets are input into the working condition monitoring module for working condition determination. First, the design working condition information of the target electric energy meter is obtained. The design working condition information generally includes multiple standard working performance indicators, that is, the performance requirements that the target electric energy meter should meet under normal working conditions, and the multiple standard working performance indicators include but are not limited to the accuracy threshold, stability threshold and response time threshold of the target electric energy meter.

[0043] Further, the working condition monitoring module is constructed with the plurality of standard working performance indicators as constraints. The working condition monitoring module can calculate the actual working performance through the self-monitoring data, and compare it with the plurality of standard working performance indicators to judge the current operating condition of the electric energy meter. Exemplarily, based on the plurality of self-monitoring data sets, relevant parameters are extracted to calculate the real-time working performance, and the real-time accuracy, real-time stability and real-time response time of the electric energy meter are obtained, and these are used as a plurality of real-time working performance values ​​to input the working condition monitoring module for working condition determination, and the real-time accuracy, real-time stability and real-time response time are respectively compared with the accuracy threshold, stability threshold and response time threshold to obtain the working condition determination result. When any real-time working performance does not meet the standard performance threshold, it indicates that the current target electric energy meter has a fault, and the working condition determination result is abnormal. When all real-time working performances meet the standard performance threshold, the working condition determination result is normal. Different working condition determination results can be used to respectively perform pre-fault prediction and post-fault analysis, thereby improving the effectiveness and reliability of electric energy meter fault detection.

[0044] P40: Based on the historical fault monitoring records, a fault expert knowledge base is established, and based on the fault expert knowledge base, the fault prediction model and fault diagnosis model are trained and embedded into the comprehensive diagnosis unit;

[0045] Further, such as Figure 2 As shown, step P40 of the embodiment of the present application also includes:

[0046] P41: Collect historical fault monitoring records, sort out the data, extract several fault types, and the corresponding fault characteristics, fault causes, and solutions, and organize them into a fault expert knowledge base;

[0047] P42: Based on the fault expert knowledge base, multiple prior fault feature sequences of different fault types are extracted, and supervised training is performed based on a support vector machine to obtain a fault prediction model;

[0048] P43: Based on the fault expert knowledge base, extract multiple post-fault features of different fault types, as well as corresponding multiple fault causes and multiple solutions, and train them in combination with a neural network model to obtain a fault diagnosis model;

[0049] P44: Embed the fault prediction model and the fault diagnosis model into the comprehensive diagnosis unit.

[0050] It should be understood that by collecting historical fault monitoring records, a fault expert knowledge base is established, and the fault prediction model and the fault diagnosis model are trained by using the fault expert knowledge base to construct a comprehensive diagnosis unit.

[0051] Specifically, the historical fault monitoring records of the target electric energy meter or the historical fault monitoring records of the same model of electric energy meter are collected, and the data of these records are sorted to identify and extract different fault types. For each fault type, the corresponding fault characteristics, fault causes and solutions are extracted, and then this information is organized into a structured fault expert knowledge base.

[0052] Furthermore, based on the fault expert knowledge base, pre-fault feature sequences of different fault types are extracted, and the pre-fault feature sequences include the operating status data of the equipment within a period of time before the fault occurs. The pre-fault feature sequences are supervised trained based on a support vector machine until the output data converges, and a fault prediction model is obtained, which can be used to predict possible future faults.

[0053] At the same time, based on the fault expert knowledge base, multiple post-fault features of different fault types are extracted, and the post-fault features include specific state data of the equipment after the fault occurs. Multiple fault causes and multiple solutions corresponding to the multiple post-fault features are extracted and used as training data. These data are trained using a neural network model, such as a convolutional neural network CNN, a recurrent neural network RNN, etc., to obtain a fault diagnosis model that can diagnose specific fault types and causes based on the current state data of the equipment.

[0054] Furthermore, the fault prediction model and the fault diagnosis model are integrated into the comprehensive diagnosis unit, which can monitor the operating status of the equipment or system in real time, and use the fault prediction model and the fault diagnosis model to predict and diagnose potential faults. When a possible fault is predicted, the comprehensive diagnosis unit can issue a warning signal and prompt possible causes and solutions of the fault. After an actual fault occurs, the comprehensive diagnosis unit can quickly diagnose the type and cause of the fault and give corresponding solutions or maintenance suggestions.

[0055] Furthermore, step P42 of the embodiment of the present application also includes:

[0056] P42-1: The multiple pre-fault feature sequences include pre-fault operating parameter sequences and pre-fault environmental data sequences of multiple core components;

[0057] P42-2: Perform correlation impact analysis on the multiple core components to generate multiple correlation impact factors;

[0058] P42-3: According to the pre-fault operating parameter sequences and pre-fault environmental data sequences of the multiple core components, and multiple fault types, supervised training is performed based on a support vector machine to obtain an initial fault prediction model;

[0059] P42-4: Based on the multiple correlated influencing factors, the initial fault prediction model is corrected to obtain a fault prediction model.

[0060] Optionally, the multiple pre-fault feature sequences include pre-fault operating parameter sequences and pre-fault environmental data sequences of multiple core components, which can reflect changes in operating parameters and environmental conditions of each core component of the device or system for a period of time before the failure. Use statistical analysis, causal analysis, or expert experience to perform correlation impact analysis on multiple core components and generate multiple correlation impact factors, which can reflect the degree of mutual influence between different components or environmental factors.

[0061] Furthermore, using pre-fault operating parameter sequences of multiple core components, pre-fault environmental data sequences, and known fault types as input data, a support vector machine algorithm is applied for supervised training to obtain an initial fault prediction model. The support vector machine algorithm is a machine learning method based on statistical learning theory, which classifies data by finding an optimal hyperplane.

[0062] Furthermore, the associated influencing factors are used as additional input features or weight factors to adjust the initial fault prediction model, for example, by modifying the kernel function of the support vector machine, adjusting parameters or combining other machine learning techniques to obtain a revised fault prediction model. The revised model will be able to better consider the mutual influence relationship between different components, thereby improving the accuracy of the prediction.

[0063] P50: receiving the plurality of self-monitoring data sets and the operating condition determination result through the comprehensive diagnosis unit, performing fault detection, and obtaining a fault detection result;

[0064] Further, such as Figure 3 As shown, step P50 of the embodiment of the present application also includes:

[0065] P51: When the working condition determination result is normal, a pre-warning is performed, and a fault prediction is performed through the fault prediction model in combination with the multiple self-monitoring data sets to obtain a fault prediction result;

[0066] P52: When the working condition determination result is abnormal, a post-event warning is performed, and the fault diagnosis model is used to analyze and locate the fault and obtain a fault diagnosis result in combination with the plurality of self-monitoring data sets;

[0067] P53: Output the fault prediction result or the fault diagnosis result as a fault detection result.

[0068] It should be understood that the integrated diagnostic unit receives the multiple self-monitoring data sets and the working condition determination results to perform fault detection. Specifically, when the working condition determination result is normal, the system enters the pre-warning mode, and performs fault prediction by combining the trained fault prediction model with multiple self-monitoring data sets to obtain the possible fault types, probabilities and possible time points of the equipment in the future as the fault prediction results. When the equipment or system has not yet failed but there is a potential risk, an early warning can be issued to prevent possible failures from occurring.

[0069] Similarly, when the operating condition is determined to be abnormal, the system enters post-warning mode. Through the trained fault diagnosis model, combined with multiple self-monitoring data sets, using existing fault cases, expert knowledge and machine learning algorithms, the current fault phenomenon is analyzed, and the specific location, type and cause of the fault are determined to obtain the fault diagnosis result. After the equipment or system has failed, the fault analysis and location can be quickly carried out to repair and restore the normal operation of the equipment in time.

[0070] Finally, the fault prediction result or the fault diagnosis result is output as a fault detection result, which can serve as an important basis for subsequent repair, maintenance and decision-making, helping relevant personnel to quickly locate problems, develop repair plans, and prevent similar faults from happening again.

[0071] P60: Perform operation and maintenance of the electric energy meter based on the fault detection result.

[0072] Specifically, referring to the fault detection results, the electric energy meter is operated and maintained to ensure the normal operation and accurate measurement of the electric energy meter, thus providing a strong guarantee for the stable operation of the power system.

[0073] Furthermore, the embodiment of the present application further includes step P70, and step P70 further includes:

[0074] P71: Monitor the fault detection results and actual operation and maintenance results in real time to obtain fault self-detection data and actual operation and maintenance data;

[0075] P72: Perform self-detection error analysis based on the fault self-detection data and actual operation and maintenance data to obtain a self-detection error;

[0076] P73: Based on the self-detection error, the fault expert knowledge base, the fault prediction model and the fault diagnosis model are dynamically updated.

[0077] In a possible embodiment of the present application, in daily equipment use, the fault detection results and actual operation and maintenance results are monitored in real time, including collecting the fault self-detection data and actual operation and maintenance data generated by the electric energy meter during the operation and maintenance process. The fault self-detection data is the fault information automatically detected by the electric energy meter, and the actual operation and maintenance data is the actual operation data recorded by the operation and maintenance personnel when handling the fault.

[0078] Furthermore, the fault self-detection data is compared and analyzed with the actual operation and maintenance data to find out the difference between the two, that is, the self-detection error. The self-detection error may be caused by misjudgment of the fault detection algorithm, error in sensor data or other reasons, which can reflect the accuracy and reliability of the fault detection algorithm.

[0079] Furthermore, based on the self-detection error, according to actual operation and maintenance experience and new fault cases, the rules and cases in the fault expert knowledge base are updated to improve the accuracy and completeness of the knowledge base. In addition, according to the self-detection error and new operation and maintenance data, the fault prediction model and fault diagnosis model are retrained or parameter adjusted. By introducing new data and information, the prediction ability and accuracy of the model can be improved. By dynamically updating the model, it is ensured that the model can adapt to the ever-changing equipment and system environment, improve the accuracy and reliability of fault detection, and at the same time, it is also helpful to improve the efficiency and quality of operation and maintenance and reduce the cost of operation and maintenance.

[0080] In summary, the embodiments of the present application have at least the following technical effects:

[0081] The present application performs equipment self-monitoring on multiple core components of the electric energy meter, obtains multiple self-monitoring data sets, makes working condition judgments, establishes a fault expert knowledge base based on historical fault monitoring records, constructs a comprehensive diagnostic unit, receives multiple self-monitoring data sets and working condition judgment results, performs fault detection, and performs operation and maintenance of the electric energy meter based on the fault detection results.

[0082] The technical effect of improving the accuracy of detection and the speed of operation and maintenance response through self-detection of electric energy meter faults has been achieved.

[0083] Embodiment 2

[0084] Based on the same inventive concept as the electric energy meter fault self-detection method in the above embodiment, Figure 4 As shown, the present application provides an electric energy meter fault self-detection device, and the device and method embodiments in the present application are based on the same inventive concept. The device includes:

[0085] A core component acquisition module 11, wherein the core component acquisition module 11 is used to acquire multiple core components of the electric energy meter, wherein the multiple core components include a standard electric energy meter, a signal source, an error calculator, and a power source;

[0086] A self-monitoring data set acquisition module 12, wherein the self-monitoring data set acquisition module 12 is used to perform equipment self-monitoring on the multiple core components to obtain multiple self-monitoring data sets, wherein the multiple self-monitoring data sets include operation parameter sequences and environmental data sequences of the multiple core components;

[0087] A working condition determination module 13, wherein the working condition determination module 13 is used to input the plurality of self-monitoring data sets into a working condition monitoring module to perform working condition determination and obtain a working condition determination result;

[0088] A comprehensive diagnosis unit construction module 14, wherein the comprehensive diagnosis unit construction module 14 is used to establish a fault expert knowledge base based on historical fault monitoring records, and to train a fault prediction model and a fault diagnosis model based on the fault expert knowledge base and embed them into the comprehensive diagnosis unit;

[0089] A fault detection module 15, the fault detection module 15 is used to receive the multiple self-monitoring data sets and the operating condition determination results through the comprehensive diagnosis unit, perform fault detection, and obtain a fault detection result;

[0090] The electric energy meter operation and maintenance module 16 is used to perform electric energy meter operation and maintenance based on the fault detection result.

[0091] Furthermore, the self-monitoring data set acquisition module 12 is further configured to perform the following steps:

[0092] Preset a self-monitoring cycle and determine key monitoring parameters, wherein the key monitoring parameters include component operation parameters and environmental parameters;

[0093] Deploy sensors based on the key monitoring parameters and configure sensor modules;

[0094] By means of the sensor module, based on the self-monitoring cycle, the operating parameters and environmental parameters of the multiple core components are collected in real time and serialized to obtain multiple operating parameter sequences and multiple environmental data sequences;

[0095] The plurality of self-monitoring data sets are constructed from the plurality of operating parameter sequences and the plurality of environmental data sequences.

[0096] Furthermore, the operating condition determination module 13 is further configured to perform the following steps:

[0097] Acquiring design operating condition information, wherein the design operating condition information includes a plurality of standard operating performance indicators, wherein the plurality of standard operating performance indicators include but are not limited to accuracy, stability and response time of the electric energy meter;

[0098] Constructing the working condition monitoring module based on the plurality of standard working performance indicators as constraints;

[0099] Based on the multiple self-monitoring data sets, multiple real-time working performance values ​​are calculated and input into the working condition monitoring module to perform working condition determination to obtain working condition determination results, wherein the working condition determination results are normal or abnormal.

[0100] Furthermore, the comprehensive diagnosis unit construction module 14 is also used to perform the following steps:

[0101] Collect historical fault monitoring records, sort out the data, extract multiple fault types, and the corresponding fault characteristics, fault causes, and solutions, and organize them into a fault expert knowledge base;

[0102] Based on the fault expert knowledge base, multiple prior fault feature sequences of different fault types are extracted, and supervised training is performed based on a support vector machine to obtain a fault prediction model;

[0103] Based on the fault expert knowledge base, multiple post-fault features of different fault types, as well as corresponding multiple fault causes and multiple solutions are extracted, and the fault diagnosis model is obtained by training in combination with a neural network model;

[0104] The fault prediction model and the fault diagnosis model are embedded in the comprehensive diagnosis unit.

[0105] Furthermore, the comprehensive diagnosis unit construction module 14 is also used to perform the following steps:

[0106] The multiple pre-fault feature sequences include pre-fault operating parameter sequences and pre-fault environmental data sequences of multiple core components;

[0107] Performing correlation impact analysis on the multiple core components to generate multiple correlation impact factors;

[0108] According to the pre-fault operating parameter sequences and pre-fault environmental data sequences of the multiple core components, and multiple fault types, supervised training is performed based on a support vector machine to obtain an initial fault prediction model;

[0109] Based on the multiple associated influencing factors, the initial fault prediction model is corrected to obtain a fault prediction model.

[0110] Furthermore, the fault detection module 15 is further configured to perform the following steps:

[0111] When the working condition determination result is normal, a pre-warning is performed, and a fault prediction is performed through the fault prediction model in combination with the multiple self-monitoring data sets to obtain a fault prediction result;

[0112] When the working condition determination result is abnormal, a post-event warning is performed, and the fault diagnosis model is used to analyze and locate the fault and obtain a fault diagnosis result in combination with the multiple self-monitoring data sets;

[0113] The fault prediction result or the fault diagnosis result is output as a fault detection result.

[0114] Furthermore, the device also includes:

[0115] A real-time monitoring module, which is used to monitor the fault detection results and actual operation and maintenance results in real time, and obtain fault self-detection data and actual operation and maintenance data;

[0116] A self-detection error analysis module, the self-detection error analysis module is used to perform self-detection error analysis based on the fault self-detection data and actual operation and maintenance data to obtain a self-detection error;

[0117] A dynamic update module is used to dynamically update the fault expert knowledge base, the fault prediction model and the fault diagnosis model based on the self-detection error.

[0118] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0119] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0120] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A method for self-detecting faults of an electric energy meter, characterized in that: The following steps are involved: P10: Obtain the core components of the energy meter, including the standard energy meter, signal source, error calculator and power source; P20: Performing equipment self-monitoring on the core component to obtain a plurality of self-monitoring data sets, wherein the self-monitoring data sets include an operating parameter sequence and an environmental data sequence of the core component; P30: Input the self-monitoring data set into the working condition monitoring module to determine the working condition and obtain the working condition determination result; P40: Based on the historical fault monitoring records, a fault expert knowledge base is established, and based on the fault expert knowledge base, the fault prediction model and fault diagnosis model are trained and embedded into the comprehensive diagnosis unit; P50: receiving the self-monitoring data set and the working condition determination result through the comprehensive diagnosis unit, performing fault detection, and obtaining a fault detection result; P60: Perform operation and maintenance of the electric energy meter based on the fault detection result to ensure normal operation and metering of the electric energy meter.

2. The method for self-detecting faults of an electric energy meter according to claim 1, characterized in that: In step P10, the standard electric energy meter is used as a reference to calibrate and verify the measurement accuracy of the target electric energy meter; the signal source provides various input signals required by the target electric energy meter; the error calculator calculates the measurement error of the electric energy meter; and the power source provides the required electric energy supply to the electric energy meter.

3. A method for self-detecting faults of an electric energy meter according to claim 2, characterized in that: The specific implementation process of step P20 is as follows: P21: Preset the self-monitoring cycle and determine the key monitoring parameters, which include component operation parameters and environmental parameters; P22: Deploy sensors based on the key monitoring parameters and configure sensor modules; P23: Through the sensor module, based on the self-monitoring cycle, the operating parameters and environmental parameters of the core components are collected in real time and serialized to obtain the operating parameter sequence and the environmental data sequence; P24: Construct a self-monitoring data set from the operating parameter sequence and the environmental data sequence.

4. The method for self-detecting fault of an electric energy meter according to claim 3, characterized in that: The specific implementation process of step P30 is as follows: P31: Obtain design operating condition information, including standard working performance indicators; P32: Construct the working condition monitoring module based on the standard working performance index; P33: Based on the self-monitoring data set, the real-time working performance value is calculated and input into the working condition monitoring module for working condition determination. The working condition determination result is normal or abnormal, as follows: When any real-time working performance does not meet the standard performance threshold, it indicates that the current target electric energy meter has a fault, and the working condition determination result is abnormal. When all real-time working performances meet the standard performance threshold, the working condition determination result is normal.

5. A method for self-detecting faults of an electric energy meter according to claim 4, characterized in that: The specific implementation process of step P40 is as follows: P41: Collect historical fault monitoring records, extract several fault types, and the corresponding fault characteristics, fault causes, and solutions, and organize them into a fault expert knowledge base; P42: Based on the fault expert knowledge base, multiple prior fault feature sequences of different fault types are extracted, and supervised training is performed based on a support vector machine to obtain a fault prediction model; P43: Based on the fault expert knowledge base, extract multiple post-fault features of different fault types, as well as corresponding multiple fault causes and multiple solutions, and train them in combination with a neural network model to obtain a fault diagnosis model; P44: The fault prediction model and fault diagnosis model are embedded into the comprehensive diagnosis unit.

6. A method for self-detecting faults of an electric energy meter according to claim 5, characterized in that: The step P42 is specifically implemented as follows: P42-1: The pre-fault feature sequence includes the pre-fault operating parameter sequence of the core components and the pre-fault environmental data sequence; P42-2: Conduct correlation impact analysis of core components and generate multiple correlation impact factors; P42-3: Based on the pre-fault operating parameter sequence of the core components, the pre-fault environmental data sequence, and multiple fault types, supervised training is performed based on the support vector machine to obtain the initial fault prediction model; P42-4: Based on multiple correlated influencing factors, the initial fault prediction model is modified to obtain a fault prediction model.

7. A method for self-detecting faults of an electric energy meter according to claim 6, characterized in that: The correcting of the initial fault prediction model based on the multiple associated influencing factors specifically includes: using the associated influencing factors as additional input features or weight factors, adjusting the initial fault prediction model, and obtaining a corrected fault prediction model.

8. The electric energy meter fault self-detection method according to claim 7, characterized in that: The specific implementation process of step P50 is as follows: P51: When the working condition is determined to be normal, a pre-warning is performed, and a fault prediction is performed through a fault prediction model combined with a self-monitoring data set to obtain a fault prediction result; P52: When the working condition is determined to be abnormal, a post-event warning is performed, and the fault diagnosis model is used in combination with the self-monitoring data set to perform fault analysis and location to obtain the fault diagnosis result; P53: Output the fault prediction result or fault diagnosis result as a fault detection result.

9. The electric energy meter fault self-detection method according to claim 8, characterized in that: The electric energy meter fault self-detection method further includes: P71: Monitor the fault detection results and actual operation and maintenance results in real time to obtain fault self-detection data and actual operation and maintenance data; P72: Perform self-detection error analysis based on the fault self-detection data and actual operation and maintenance data to obtain a self-detection error; P73: Based on the self-detection error, the fault expert knowledge base, fault prediction model and fault diagnosis model are dynamically updated.

10. A fault self-detection device for an electric energy meter, used to implement the fault self-detection method according to any one of claims 1 to 9, characterized in that: It includes core component acquisition module, self-monitoring data set acquisition module, working condition determination module, comprehensive diagnosis unit construction module, fault detection module and electric energy meter operation and maintenance module; The core component acquisition module is used to acquire the core components of the electric energy meter, including a standard electric energy meter, a signal source, an error calculator and a power source; The self-monitoring data set acquisition module is used to perform equipment self-monitoring on core components to obtain a self-monitoring data set, which includes an operating parameter sequence and an environmental data sequence of the core components; The working condition determination module is used to input the self-monitoring data set into the working condition monitoring module to perform working condition determination and obtain the working condition determination result; The comprehensive diagnosis unit construction module is used to establish a fault expert knowledge base based on historical fault monitoring records, and to train a fault prediction model and a fault diagnosis model based on the fault expert knowledge base and embed them into the comprehensive diagnosis unit; The fault detection module is used to receive the self-monitoring data set and the working condition determination result through the comprehensive diagnosis unit, perform fault detection, and obtain the fault detection result; The electric energy meter operation and maintenance module is used to perform electric energy meter operation and maintenance based on the fault detection result.

Images