Electric valve data exception identification method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides an electric valve data exception recognition method and device, electronic equipment and a storage medium, and belongs to the technical field of electric valves. The method comprises the steps that in response to a target electric valve, the electric valve is triggered to execute actions, and valve control current and valve control voltage of the target electric valve corresponding to the electric valve execution actions are collected; wherein the action type of the action executed by the electric valve is the target action type of the electric valve; active power calculation is carried out based on the valve control current and the valve control voltage, and the valve active power of the target electric valve is obtained; determining a target power evaluation baseline from a plurality of pre-configured candidate power evaluation baselines according to a target electric valve action type corresponding to the electric valve execution action; and performing anomaly recognition based on the valve active power and the target power evaluation baseline to obtain anomaly recognition information. According to the embodiment of the invention, the data generated by the electrically operated valve can be processed so as to carry out abnormity identification, and a basis is provided for subsequent valve fault diagnosis.

Description

Technical Field

[0001] The present application relates to the technical field of electric valves, and in particular to a method, device, electronic equipment and storage medium for identifying abnormal data of electric valves. Background Art

[0002] Electric valves are commonly used equipment in modern industry and are also commonly used equipment in nuclear power plants. Common fault phenomena of electric valves include valve failure, stuck action, valve vibration, increased leakage, etc. In the related art, in the fault diagnosis of electric valves, the conventional method is to shut down the valve when the electric valve fails, dismantle it and then disassemble it for inspection. Conventional means often occur after the valve fails, which will have a certain impact on the safety and economy of the operation of the nuclear power plant. Therefore, online valve status monitoring and fault diagnosis technology are needed. Online valve status monitoring and fault diagnosis will not affect the normal operation of the valve, and have good real-time performance, which is conducive to early detection of abnormal status of the valve, and avoid the valve from deteriorating from abnormal status to fault status, affecting the operation of the power plant.

[0003] However, the data generated by the electric valve is discrete and has unclear periodic characteristics, which makes it inconvenient for fault diagnosis and abnormality identification. Therefore, how to process the data generated by the electric valve for abnormality identification and provide a basis for subsequent valve fault diagnosis has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to propose a method, device, electronic device and storage medium for identifying anomaly in electric valve data, aiming to process the data generated by the electric valve to identify anomalies and provide a basis for subsequent valve fault diagnosis.

[0005] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present application proposes a method for identifying abnormal data of an electric valve, the method comprising: in response to a target electric valve triggering an electric valve to perform an action, collecting a valve control current and a valve control voltage of the target electric valve corresponding to the electric valve performing the action; wherein the action type of the electric valve performing the action is the action type of the target electric valve;

[0006] Performing active power calculation based on the valve control current and the valve control voltage to obtain the valve active power of the target electric valve;

[0007] Determining a target power evaluation baseline from a plurality of pre-configured candidate power evaluation baselines according to the target electric valve action type corresponding to the electric valve execution action;

[0008] Abnormality identification is performed based on the valve active power and the target power evaluation baseline to obtain abnormality identification information.

[0009] In some embodiments, before determining the target power assessment baseline from a plurality of pre-configured candidate power assessment baselines according to the target electric valve action type corresponding to the electric valve execution action, the method further includes pre-configuring the candidate power assessment baselines, specifically including:

[0010] Acquire healthy active power data of the target electric valve corresponding to the action performed by the electric valve under normal operating conditions;

[0011] Performing data cleaning processing based on the healthy active power data to obtain pure power data;

[0012] Perform sliding window processing on the pure power data to obtain multiple valve power data groups;

[0013] A multi-segment fitting process is performed based on the plurality of valve power data groups to obtain the candidate power evaluation baseline corresponding to the execution action of the electric valve.

[0014] In some embodiments, performing data cleaning based on the healthy active power data to obtain pure power data includes:

[0015] Perform Laida's law calculation based on the healthy active power data to obtain a power abnormality value, and obtain a power abnormality time point corresponding to the power abnormality value;

[0016] For each of the abnormal power values ​​in the healthy active power data, the valve active power of the target electric valve before and after the abnormal power time point is obtained based on a preset time wide range value to obtain first processed power data;

[0017] The pure power data is obtained by performing mean calculation based on the first processed power data and replacing the corresponding power abnormal value in the healthy active power data.

[0018] In some embodiments, the sliding window processing is performed on the pure power data to obtain multiple valve power data groups, including:

[0019] The pure power data is divided and processed based on a preset start-stop cut-off interval to obtain power data in a non-start-stop phase;

[0020] Based on a preset window size value and a preset step movement value, sliding window processing is performed on the non-start-stop phase power data to obtain a plurality of valve power data groups.

[0021] In some embodiments, performing multi-segment fitting processing based on the plurality of valve power data groups to obtain the candidate power evaluation baseline corresponding to the electric valve execution action includes:

[0022] Performing connection point fitting processing on the plurality of valve power data groups based on a differential evolution algorithm to obtain a power change inflection point;

[0023] Based on the power change inflection point, a continuous function is fitted to the corresponding plurality of valve power data groups to obtain the candidate power evaluation baseline corresponding to the electric valve execution action.

[0024] In some embodiments, the abnormality identification based on the valve active power and the target power evaluation baseline to obtain abnormality identification information includes:

[0025] The active power of the valve is divided and processed based on the preset start-stop cut-off interval to obtain the target non-start-stop stage power data;

[0026] Performing abnormal data frequency assessment based on the target non-start-stop phase power data and the target power assessment baseline to obtain first assessment information;

[0027] Performing a power change trend assessment based on the target non-start / stop phase power data and the target power assessment baseline to obtain second assessment information;

[0028] The abnormality identification information is obtained based on the first evaluation information and the second evaluation information.

[0029] In some embodiments, the abnormal data frequency assessment is performed based on the target non-start-stop phase power data and the target power assessment baseline to obtain the first assessment information, including:

[0030] Determine the time point at which the target non-start-stop phase power data deviates from the target power evaluation baseline and exceeds the power fluctuation range as a power abnormal point;

[0031] The first evaluation information is obtained according to a preset power anomaly number threshold and the number of power anomaly points within a preset power determination time.

[0032] In some embodiments, the performing power change trend assessment based on the target non-start-stop phase power data and the target power assessment baseline to obtain the second assessment information includes:

[0033] Performing an overall change trend evaluation based on the target non-start-stop phase power data and the target power evaluation baseline to obtain overall evaluation information;

[0034] Performing segmented change trend evaluation based on the target non-start-stop phase power data and the target power evaluation baseline to obtain local evaluation information;

[0035] The second evaluation information is obtained based on the overall evaluation information and the local evaluation information.

[0036] In some embodiments, the performing abnormality identification based on the valve active power and the target power evaluation baseline to obtain abnormality identification information further includes:

[0037] The power anomaly assessment model is used to identify the power anomaly of the valve active power based on a pre-trained power anomaly assessment model to obtain the anomaly identification information; wherein the power anomaly assessment model is pre-trained based on the target power assessment baseline.

[0038] In some embodiments, before performing power anomaly identification on the valve active power based on the pre-trained power anomaly assessment model to obtain the anomaly identification information, the power anomaly assessment model is pre-trained, including:

[0039] Acquire a model training set; wherein the model training set includes valve power training data corresponding to the action performed by the electric valve, and each valve power training data is configured with a corresponding power sample label;

[0040] Inputting the target power assessment baseline and the valve power training data into the original power abnormality assessment model for abnormality recognition training to obtain a sample recognition result;

[0041] Comparing the sample recognition result corresponding to the valve power training data with the power sample label to obtain comparison deviation data;

[0042] Based on the comparison deviation data, the model parameters of the power anomaly assessment model are updated, and the sound training sample is input into the power anomaly assessment model for sample recognition training until the power anomaly assessment model meets the preset training termination condition, thereby obtaining the pre-trained power anomaly assessment model.

[0043] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application provides a device for identifying abnormal data of an electric valve, the device comprising:

[0044] An electric valve parameter acquisition module, for collecting a valve control current and a valve control voltage of the target electric valve corresponding to the electric valve execution action in response to the target electric valve triggering the electric valve execution action; wherein the action type of the electric valve execution action is the target electric valve action type;

[0045] An electric valve power calculation module, used for performing active power calculation based on the valve control current and the valve control voltage to obtain the valve active power of the target electric valve;

[0046] A power baseline screening module, configured to determine a target power evaluation baseline from a plurality of pre-configured candidate power evaluation baselines according to the target electric valve action type corresponding to the electric valve execution action;

[0047] The electric valve abnormality identification module is used to perform abnormality identification based on the valve active power and the target power evaluation baseline to obtain abnormality identification information.

[0048] To achieve the above-mentioned purpose, the third aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the electric valve data abnormality identification method described in the first aspect is implemented.

[0049] To achieve the above objectives, the fourth aspect of an embodiment of the present application proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the electric valve data abnormality identification method described in the first aspect is implemented.

[0050] The electric valve data anomaly identification method, device, electronic device and storage medium proposed in the present application, which triggers the electric valve to perform an action in response to the target electric valve, collects the valve control current and valve control voltage of the target electric valve corresponding to the electric valve execution action, wherein the action type of the electric valve execution action is the target electric valve action type, and then performs active power calculation based on the valve control current and valve control voltage to obtain the valve active power of the target electric valve, and then determines the target power evaluation baseline from multiple pre-configured candidate power evaluation baselines according to the target electric valve action type corresponding to the electric valve execution action, and performs anomaly identification based on the valve active power and the target power evaluation baseline to obtain anomaly identification information. It can be seen that the present application determines the matching target power evaluation baseline from the pre-configured candidate power evaluation baselines through the target electric valve action type, and then performs anomaly evaluation on the valve active power corresponding to the target electric valve triggering the electric valve execution action based on the target power evaluation baseline, and obtains anomaly identification information, so that the data generated by the electric valve can be processed to perform anomaly identification, providing a basis for subsequent valve fault diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 is a flow chart of a method for identifying abnormal electric valve data provided by an embodiment of the present application;

[0052] Figure 2 yes Figure 1 The flowchart before step S103 in FIG.

[0053] Figure 3 yes Figure 2 Flow chart of step S202 in FIG.

[0054] Figure 4 yes Figure 2 Flow chart of step S203 in FIG.

[0055] Figure 5 yes Figure 2 Flow chart of step S204 in FIG.

[0056] Figure 6 yes Figure 1 Flow chart of step S104 in FIG.

[0057] Figure 7 yes Figure 6 Flowchart of step S602 in FIG.

[0058] Figure 8 yes Figure 6 Flow chart of step S603 in FIG.

[0059] Fig. 9 yes Figure 1 Another flowchart of step S104 in;

[0060] Fig.10 yes Fig. 9 The flowchart before step S901 in FIG.

[0061] Fig.11 It is a structural schematic diagram of the electric valve data abnormality identification device provided in an embodiment of the present application;

[0062] Fig.12 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0064] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0065] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0066] The embodiments of the present application provide a method, device, electronic device and storage medium for identifying anomaly in electric valve data, which are intended to process data generated by the electric valve to identify anomalies and provide a basis for subsequent valve fault diagnosis.

[0067] The electric valve data anomaly identification method, device, electronic device and storage medium provided in the embodiments of the present application are specifically described through the following embodiments. First, the electric valve data anomaly identification method in the embodiments of the present application is described.

[0068] The electric valve data anomaly identification method provided in the embodiment of the present application relates to the field of electric valve technology. The electric valve data anomaly identification method provided in the embodiment of the present application can be applied to a terminal, can also be applied to a server side, and can also be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or a server cluster or distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the electric valve data anomaly identification method, etc., but is not limited to the above forms.

[0069] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0070] Figure 1 is an optional flow chart of the method for identifying abnormal electric valve data provided by an embodiment of the present application. Figure 1 The method may include but is not limited to steps S101 to S104.

[0071] Step S101, in response to the target electric valve triggering the electric valve to perform an action, collecting the valve control current and valve control voltage of the target electric valve corresponding to the electric valve performing the action; wherein the action type of the electric valve performing the action is the action type of the target electric valve;

[0072] Step S102, performing active power calculation based on the valve control current and the valve control voltage to obtain the valve active power of the target electric valve;

[0073] Step S103, determining a target power evaluation baseline from a plurality of pre-configured candidate power evaluation baselines according to a target electric valve action type corresponding to the electric valve execution action;

[0074] Step S104, performing abnormality identification based on the valve active power and the target power evaluation baseline to obtain abnormality identification information.

[0075] Steps S101 to S104 shown in the embodiment of the present application, in response to the target electric valve triggering the electric valve to perform an action, collect the valve control current and valve control voltage of the target electric valve corresponding to the electric valve execution action, wherein the action type of the electric valve execution action is the target electric valve action type, then perform active power calculation based on the valve control current and valve control voltage to obtain the valve active power of the target electric valve, and then determine the target power evaluation baseline from multiple pre-configured candidate power evaluation baselines according to the target electric valve action type corresponding to the electric valve execution action, perform abnormal identification based on the valve active power and the target power evaluation baseline, and obtain abnormal identification information. It can be seen that the present application determines the matching target power evaluation baseline from the pre-configured candidate power evaluation baselines through the target electric valve action type, and then performs abnormal evaluation on the valve active power corresponding to the target electric valve triggering the electric valve execution action based on the target power evaluation baseline, and obtains abnormal identification information, so that the data generated by the electric valve can be processed to perform abnormal identification, providing a basis for subsequent valve fault diagnosis.

[0076] In step S101 of some embodiments, when the target electric valve triggers the electric valve execution action, the valve control current and valve control voltage corresponding to the electric valve execution action are collected in real time. The electric valve execution action represents the action performed by the target electric valve, and there are multiple action types of electric valve execution actions, including valve closing type and valve opening type. The type of action being performed by the target electric valve is the target electric valve action type. The valve control current represents the current when the target electric valve is controlled to perform the electric valve execution action, and the valve control voltage represents the voltage when the target electric valve is controlled to perform the electric valve execution action. It should be noted that the electric switch valve represented by the target electric valve in the present application only includes two switching states, namely the valve opening state and the valve closing state, and the electric switch valve is, for example, an electric isolation valve or an electric stop valve.

[0077] In step S102 of some embodiments, the valve active power of the target electric valve is calculated based on the collected valve control current and valve control voltage. The valve active power is an indicator to measure the actual energy consumed by the electric valve when performing the electric valve execution action, which can reflect the workload of the electric valve. The valve active power is proportional to the torque applied to the electric valve, and can characterize the torque on the electric valve to a certain extent. The torque describes the ability of a force to produce a rotational effect on an object, so the valve active power can characterize the opening and closing effect of the electric valve to a certain extent.

[0078] In step S103 of some embodiments, a target power assessment baseline is determined from multiple pre-configured candidate power assessment baselines according to the target electric valve action type corresponding to the electric valve execution action. The candidate power assessment baseline is configured according to the different action types of the target electric valve to ensure that the target electric valve has a matching target power assessment baseline for abnormality identification under different action types.

[0079] See also Figure 2 In some embodiments, before step S103, multiple candidate power evaluation baselines need to be pre-configured, which may include but are not limited to steps S201 to S204:

[0080] Step S201, obtaining healthy active power data of the target electric valve corresponding to the electric valve executing action under normal operating conditions;

[0081] Step S202, performing data cleaning processing based on the healthy active power data to obtain pure power data;

[0082] Step S203, performing sliding window processing according to the pure power data to obtain multiple valve power data groups;

[0083] Step S204 , performing multi-segment fitting processing based on the multiple valve power data groups to obtain a candidate power evaluation baseline corresponding to the electric valve execution action.

[0084] In step S201 of some embodiments, the valve active power of the target electric valve corresponding to the electric valve performing an action under normal operating conditions is obtained and determined as healthy active power data, so as to be used to generate a candidate power evaluation baseline for evaluating whether the target electric valve has an abnormality. The healthy active power data contains a large amount of data on the valve active power of the target electric valve triggering the electric valve to perform an action under normal operating conditions.

[0085] In step S202 of some embodiments, data cleaning is performed based on the collected healthy active power data. The purpose of data cleaning is to remove abnormal values, noise and incomplete data to obtain pure power data.

[0086] In step S203 of some embodiments, sliding window processing is performed based on the pure power data. Sliding window processing is a time series analysis technology that can capture the local characteristics of pure power data and obtain multiple valve power data groups, each of which represents the operating power information of the target electric valve in a specific time period. In addition, the healthy active power data is essentially calculated based on the valve current data and valve voltage data collected at a certain time interval, so the pure power data obtained is discrete. By dividing the pure power data into multiple continuous data groups, the discrete pure power data can be made continuous locally, which is conducive to the subsequent multi-segment fitting processing to obtain a continuous candidate power evaluation baseline.

[0087] In step S204 of some embodiments, a multi-segment fitting process is performed based on multiple valve power data groups. Multi-segment fitting process refers to fitting according to the power change trend of each valve power data group, so as to obtain a candidate power evaluation baseline for the corresponding electric valve execution action. It is equivalent to fitting multiple small continuous data groups based on the power change trend to form a continuous candidate power evaluation baseline. The candidate power evaluation baseline reflects the normal power change trend and normal power change range of the electric valve in different operation stages, and provides a reference standard for subsequent abnormality identification.

[0088] Through steps S201 to S204, multiple candidate power evaluation baselines can be constructed, and the candidate power evaluation baselines can characterize the power change of the target electric valve under normal operating conditions. Therefore, in step S103, according to the action type of the target electric valve, the most suitable one can be selected from multiple candidate power evaluation baselines as the target power evaluation baseline for subsequent abnormality identification, which not only improves the accuracy of abnormality identification, but also can cope with different electric valve execution actions.

[0089] See also Figure 3 In some embodiments, step S202 may include but is not limited to steps S301 to S303:

[0090] Step S301, performing Laida's law calculation based on healthy active power data to obtain a power abnormality value, and obtaining a power abnormality time point corresponding to the power abnormality value;

[0091] Step S302, for each abnormal power value in the healthy active power data, the valve active power of the target electric valve before and after the power abnormal time point is obtained based on a preset time wide range value to obtain the first processed power data;

[0092] Step S303, performing mean calculation based on the first processed power data and replacing the corresponding power abnormal value in the healthy active power data to obtain pure power data.

[0093] In step S301 of some embodiments, the healthy active power data is subjected to an outlier detection using the Laida rule to obtain power outliers. The Laida rule is a statistical method that can find out those power outliers in the healthy active power data that are significantly different from the majority of data, and record the power outlier time points corresponding to these power outliers.

[0094] In step S302 of some embodiments, for each detected power abnormality value, the valve active power of the target electric valve before and after the power abnormality time point is obtained based on the preset time wide range value. The time wide range value is used to represent the range of the valve active power before and after the power abnormality time point of the power abnormality value, that is, to control the amount of the first processed power data to a certain extent. By collecting the valve active power near the power abnormality value, the first processed power data is obtained, so as to facilitate the subsequent processing of the power abnormality value according to the first processed power data. Those skilled in the art can set the time wide range value according to actual needs. For example, if the frequency of collecting the valve active power is very high, a larger time wide range value can be set, and the first processed power data can be obtained by collecting more valve active power, so that when replacing the power abnormality value in step S303, the power replacement value can be obtained more accurately. However, if the frequency of collecting the valve active power is low, the valve active power collected is separated by a large time dimension, so the time wide range value cannot be too large, otherwise the power replacement value obtained by the first processed power data cannot represent the actual power at the power abnormality time point.

[0095] In step S303 of some embodiments, mean calculation is a commonly used data smoothing technology. The power replacement value is obtained by performing mean calculation on the first processed power data to replace the power abnormality value at the corresponding power abnormality time point, thereby reducing the impact of the power abnormality value on subsequent steps. By calculating the mean of the power data adjacent to the power abnormality value and replacing the power abnormality value, smoother and more reliable pure power data can be obtained, so that the pure power data can more accurately reflect the normal operating status of the electric valve.

[0096] Through step S301 to step S303, pure data can be cleaned from the original healthy active power data, providing a high-quality data foundation for subsequent data fitting to construct a candidate power evaluation baseline, thereby improving the accuracy of the data.

[0097] See also Figure 4 In some embodiments, step S203 may include but is not limited to steps S401 to S402:

[0098] Step S401, dividing and processing the pure power data based on the preset start-stop cut-off interval to obtain the non-start-stop stage power data;

[0099] Step S402, performing sliding window processing on the non-start-stop phase power data based on a preset window size value and a preset step movement value to obtain a plurality of valve power data groups.

[0100] In step S401 of some embodiments, the target electric valve can be divided into different operation stages under the operation state, namely, the start-up stage, the non-start-stop stage and the stop stage, wherein the start-up stage represents the process of the target electric valve changing from the static state to the working state. In the start-up stage, the target electric valve needs to overcome the static friction to operate, and the valve active power will suddenly increase sharply from a lower state, and quickly fall back to a stable state as the target electric valve starts to operate, so the valve active power will fluctuate greatly in this stage. The non-start-stop stage represents the state of normal operation of the target electric valve. In this stage, the target electric valve has been fully started and operates stably, and the valve active power is relatively stable, reflecting the performance of the target electric valve under normal working conditions. By monitoring the non-start-stop stage, it is possible to evaluate whether the electric valve is operating in the best state and whether there are signs of performance degradation. The stop stage represents the process of the target electric valve changing from the working state to the static state. In this stage, the valve active power will gradually decrease until it stops. The valve active power at this stage can reflect whether there are any abnormalities when the target electric valve stops, such as whether it can stop smoothly or whether there are delays.

[0101] The start-stop cut-off interval is used to divide the start-up phase and the stop phase of the target electric valve in the operating state, and may include a start-up cut-off interval and a stop-stop cut-off interval, which are respectively used to divide the start-up phase and the stop phase of the target electric valve. The start-stop cut-off interval can be set according to the actual operation of the target electric valve, and different electric valves have different start-stop cut-off intervals.

[0102] The pure power data is divided and processed based on the start-stop cut-off interval to obtain the power data in the non-start-stop stage, that is, the valve active power of the target electric valve in the non-start-stop stage, by identifying and separating the valve active power generated in the start-up and stop stages of the target electric valve, because the valve active power in these stages contains transient behavior under abnormal operating conditions, which will interfere with the analysis of the normal operating state of the target electric valve. In this way, the power data in the non-start-stop stage can be obtained, which can better represent the performance of the target electric valve under normal operating conditions.

[0103] In step S402 of some embodiments, sliding window processing is performed on the non-start-stop phase power data to obtain multiple valve power data groups. Sliding window processing is a commonly used time series analysis technology, which extracts data from the non-start-stop phase power data through a window size value, and moves the window for extracting data on the non-start-stop phase power data according to a step moving value, thereby obtaining multiple valve power data groups. Each valve power data group contains pure power data within a certain time range, so that the discrete pure power data is combined to make the pure power data locally continuous, which is convenient for subsequent processing to generate a candidate power evaluation baseline.

[0104] Through step S401 to step S402, a representative valve power data group is extracted from the pure power data. The valve power data group not only contains the information of the target electric valve under normal operating conditions, but is also organized in a form suitable for further analysis, providing a basis for subsequent multi-segment fitting processing and abnormality identification.

[0105] See also Figure 5 In some embodiments, step S204 may include but is not limited to steps S501 to S502:

[0106] Step S501, performing connection point fitting processing on multiple valve power data groups based on a differential evolution algorithm to obtain a power change inflection point;

[0107] Step S502 : performing continuous function fitting on the corresponding multiple valve power data groups based on the power change inflection point to obtain a candidate power evaluation baseline for the corresponding electric valve execution action.

[0108] In steps S501 to S502 of some embodiments, a differential evolution algorithm is used to process multiple valve continuous data groups, so as to find the power change inflection point that fits multiple valve continuous data. The differential evolution algorithm is a global optimization algorithm that can handle complex nonlinear problems and find the optimal solution in the data. In this process, multiple valve power data groups are processed by the differential evolution algorithm to find the breakpoint position that can minimize the fitting error of multiple valve power data groups, that is, the power change inflection point. Based on the power change inflection point, a continuous function can be constructed to simulate the valve active power of the target electric valve in the actual operating state, so as to serve as a candidate power evaluation baseline. In this process, the approximate fluctuation range of the valve active power deviating from the candidate power evaluation baseline can also be determined, so as to obtain the power fluctuation range corresponding to the candidate power evaluation baseline, so as to facilitate subsequent abnormal evaluation. It should be noted that the valve power data group contains data on the valve active power produced by multiple different electric valve execution actions, so it is based on the power change inflection point obtained by the valve power data group generated by a large number of different electric valve execution actions.

[0109] Through steps S501 to S502, a series of valve power data groups are fitted to construct a candidate power assessment baseline that can accurately reflect the operating status of the target electric valve, providing a reference standard for the normal operating state of the target electric valve, and providing an effective and powerful tool for achieving effective online abnormality identification and subsequent fault diagnosis.

[0110] In step S104 of some embodiments, abnormality identification is performed based on the valve active power and the target power evaluation baseline to obtain abnormality identification information. After obtaining the matched target power evaluation baseline, the valve active power generated by the target electric valve during the current electric valve execution process can be identified based on the target power evaluation baseline to obtain abnormality identification information. The abnormality identification information is used to reflect whether the target electric valve has an abnormality.

[0111] See also Figure 6 In some embodiments, step S104 may include but is not limited to steps S601 to S604:

[0112] Step S601, dividing the valve active power based on the preset start-stop cut-off interval to obtain target non-start-stop stage power data;

[0113] Step S602, performing abnormal data frequency assessment based on the target non-start-stop phase power data and the target power assessment baseline to obtain first assessment information;

[0114] Step S603, performing power change trend evaluation based on the target non-start-stop phase power data and the target power evaluation baseline to obtain second evaluation information;

[0115] Step S604: Obtain abnormality identification information based on the first evaluation information and the second evaluation information.

[0116] In step S601 of some embodiments, the valve active power is divided and processed based on the preset start-stop cut-off interval to obtain the valve active power corresponding to the target electric valve in the non-start-stop stage, that is, the target non-start-stop stage power data. The target non-start-stop stage power data can better represent the performance of the target electric valve in normal operation.

[0117] In step S602 of some embodiments, an abnormal data frequency assessment is performed based on the target non-start-stop phase power data and the target power assessment baseline to obtain first assessment information. Based on the frequency of the target non-start-stop phase power data deviating from the target power assessment baseline, it is determined whether the target electric valve has an abnormality to obtain the first assessment information.

[0118] See also Figure 7In some embodiments, step S602 may include but is not limited to steps S701 to S702:

[0119] Step S701, determining the time point at which the target non-start-stop phase power data deviates from the target power evaluation baseline and exceeds the power fluctuation range as a power abnormal point;

[0120] Step S702: Obtain first evaluation information according to a preset power anomaly number threshold and the number of power anomaly points within a preset power determination time.

[0121] In step S701 of some embodiments, when the target non-start-stop phase power data deviates from the target power evaluation baseline by more than a certain range, the power abnormal point is determined at this instant, and the power fluctuation range is used to limit the maximum range of the target non-start-stop phase power data deviating from the corresponding target power evaluation baseline at any time point, which is related to the power fluctuation range mentioned in step S502. When the target non-start-stop phase power data deviates from the target power evaluation baseline beyond the power fluctuation range, this time point is considered to be a power abnormal point.

[0122] In step S702 of some embodiments, the first evaluation information is obtained according to a preset power abnormality times threshold and the number of power abnormal points within a preset power judgment time. The power abnormality times threshold is used to limit the maximum allowable number of power abnormal points. When the number of power abnormal points exceeds the power abnormality times threshold, it is considered that the target electric valve has an abnormality. The power judgment time is used to monitor the frequency of occurrence of power abnormal points. If the number of power abnormal points that appear within the power judgment time exceeds the power abnormality times threshold, it is considered that the target electric valve has an abnormality.

[0123] Those skilled in the art can set the power abnormality times threshold and power determination time according to actual needs. The power determination time allows to directly cover the entire target non-start-stop stage power data. In this case, it is considered that the target electric valve is abnormal based on the number of power abnormal points in the target non-start-stop stage power data and the power abnormality times threshold.

[0124] It should be noted that when the target electric valve is in operation, it is inevitable that due to external factors or the omission of abnormal values ​​during data cleaning, the target non-start-stop phase power data of the target electric valve deviates from the target power evaluation baseline and exceeds the range specified by the abnormal judgment condition. In this case, the target electric valve may not be abnormal. Therefore, in order not to be affected by such accidental factors, the power abnormality number threshold and power judgment time are set to further determine whether the target electric valve is really abnormal. In addition, in the actual application process, abnormalities can also be identified according to the degree to which the target non-start-stop phase power data deviates from the target power evaluation baseline, that is, at a certain time point, the valve active power of the target non-start-stop phase power data deviates from the target power evaluation baseline, not only exceeding the range specified by the abnormal judgment condition, but also exceeding the value by a very large amount. At this time, it is also considered that the target electric valve may also be abnormal, and the target electric valve needs to be checked.

[0125] Through step S701 to step S702, a power abnormal point is obtained, and the power abnormal point is evaluated based on the power abnormal number threshold and the power determination time, so as to more accurately identify the abnormality.

[0126] In step S603 of some embodiments, a power change trend assessment is performed based on the target non-start-stop phase power data and the target power assessment baseline, and the power change trends of the target non-start-stop phase power data and the target power assessment baseline are compared to determine whether an abnormality occurs in the target electric valve to obtain second evaluation information.

[0127] See also Figure 8 In some embodiments, step S603 may include but is not limited to steps S801 to S803:

[0128] Step S801, performing an overall change trend assessment based on the target non-start-stop phase power data and the target power assessment baseline to obtain overall assessment information;

[0129] Step S802, performing segmented change trend evaluation based on the target non-start-stop phase power data and the target power evaluation baseline to obtain local evaluation information;

[0130] Step S803: obtaining second evaluation information based on the overall evaluation information and the local evaluation information.

[0131] In step S801 of some embodiments, an overall change trend assessment is performed based on the target non-start-stop phase power data and the target power assessment baseline, focusing on whether the overall change trend of the target non-start-stop phase power data and the target power assessment baseline is the same, and overall assessment information is obtained. The overall assessment information provides a macro perspective, comparing the change trend of the target non-start-stop phase power data and the target power assessment baseline in a long-term dimension.

[0132] In step S802 of some embodiments, a segmented change trend assessment is performed based on the target non-start-stop phase power data and the target power assessment baseline, and attention is paid to whether the local power change trends of the target non-start-stop phase power data and the target power assessment baseline are the same, so as to obtain local assessment information. The target non-start-stop phase power data and the target power assessment baseline can be divided into multiple small segments, and the power change trend of each segment is evaluated to obtain the local power change trend. This helps to identify short-term fluctuations or anomalies in the target non-start-stop phase power data, which may be caused by specific events or conditions, such as instantaneous load changes or operational errors.

[0133] In step S803 of some embodiments, second evaluation information is obtained based on the overall evaluation information and the local evaluation information, taking into account both macro trends and micro changes, so as to provide a more comprehensive power change trend evaluation, thereby more accurately identifying which changes are normal operating fluctuations and which may be potential abnormalities or signs of failure.

[0134] In step S604 of some embodiments, the first evaluation information and the second evaluation information are combined to obtain abnormal identification information. The frequency of occurrence of abnormal data and the power change trend are comprehensively evaluated to determine whether the target electric valve is abnormal. When either the first evaluation information or the second evaluation information indicates that the target electric valve is abnormal, it is considered that a subsequent inspection of the target electric valve is required.

[0135] Through steps S601 to S604, not only the power abnormality point of the target electric valve at a specific moment can be identified, but also the abnormality of the power change trend of the target electric valve can be identified, thereby enabling accurate and reliable abnormality identification of the target electric valve, which helps to timely discover and deal with potential problems and ensure the stable operation of the target electric valve.

[0136] See also Fig. 9 In some embodiments, step S104 may include but is not limited to step S901: identifying power anomalies of valve active power based on a pre-trained power anomaly assessment model to obtain anomaly identification information, wherein the power anomaly assessment model is pre-trained based on a target power assessment baseline.

[0137] In step S901 of some embodiments, the power abnormality assessment model trained in advance is used to identify the power abnormality of the valve active power to obtain abnormality identification information. Some potential abnormalities of the target electric valve are difficult to detect by effective means, and the target electric valve can only be identified by the power abnormality assessment model.

[0138] By using the pre-trained power anomaly assessment model to identify power anomalies in valve active power, real-time anomaly detection of the valve active power of the target electric valve can be achieved. The method based on the neural network model not only improves the accuracy of anomaly identification, but also can quickly respond to potential problems, thereby improving the reliability and safety of the target electric valve.

[0139] Before the power anomaly assessment model is used to identify the power anomaly of the valve active power, the original power anomaly assessment model needs to be pre-trained based on the target power assessment baseline to obtain a pre-trained power anomaly assessment model.

[0140] See also Fig.10 In some embodiments, before step S901, the following steps may be included but not limited to steps S1001 to S1004:

[0141] Step S1001, obtaining a model training set; wherein the model training set includes valve power training data corresponding to the electric valve execution action, and each valve power training data is configured with a corresponding power sample label;

[0142] Step S1002, inputting the target power assessment baseline and valve power training data into the original power abnormality assessment model for abnormality recognition training to obtain a sample recognition result;

[0143] Step S1003, comparing the sample recognition result corresponding to the valve power training data with the power sample label to obtain comparison deviation data;

[0144] Step S1004, based on the comparison deviation data, the model parameters of the power anomaly assessment model are updated, and the execution returns to input the sound training sample into the power anomaly assessment model for sample recognition training until the power anomaly assessment model meets the preset training termination condition, thereby obtaining a pre-trained power anomaly assessment model.

[0145] In step S1001 of some embodiments, the model training set includes valve power training data corresponding to the electric valve execution action, and the corresponding valve power training data can be selected for training according to the electric valve execution action triggered by the corresponding target electric valve, so as to obtain a power abnormality assessment model specifically for the valve opening action and the valve closing action. Each valve power training data is configured with a corresponding power sample label, which is used to indicate whether the corresponding valve power training data corresponds to the valve active power of the target electric valve under abnormal conditions.

[0146] In step S1002 of some embodiments, the target power assessment baseline and valve power training data are input into the original power abnormality assessment model for abnormality recognition training, so that the power abnormality assessment model determines whether the valve power training data corresponds to the valve active power of the target electric valve under abnormal conditions, and obtains a sample recognition result.

[0147] In step S1003 of some embodiments, the sample recognition result of the valve power training data obtained by the pass rate anomaly assessment model is compared with the power sample label of the corresponding valve power training data to obtain comparison deviation data, that is, the loss value of the power anomaly assessment model.

[0148] In step S1004 of some embodiments, the model parameters of the power anomaly assessment model are updated according to the comparison deviation data, and the valve power training data of the model training set is repeatedly input to train the power anomaly assessment model until the accuracy of the power anomaly assessment model can meet the preset training termination conditions, and finally a pre-trained power anomaly assessment model is obtained.

[0149] Through step S1001 to step S1004, a powerful power anomaly assessment model is constructed, and the accuracy and reliability of anomaly identification are improved through continuous training and optimization. The power anomaly assessment model is crucial for real-time monitoring of the operating status of the electric valve and preventing potential failures.

[0150] See also Fig.11 The embodiment of the present application further provides a device for identifying abnormal data of an electric valve, which can implement the above-mentioned method for identifying abnormal data of an electric valve, and the device includes:

[0151] The electric valve parameter acquisition module is used to respond to the target electric valve triggering the electric valve to perform an action, and to collect the valve control current and valve control voltage of the target electric valve corresponding to the electric valve execution action; wherein the action type of the electric valve execution action is the action type of the target electric valve;

[0152] The electric valve power calculation module is used to calculate the active power based on the valve control current and the valve control voltage to obtain the valve active power of the target electric valve;

[0153] A power baseline screening module, used to determine a target power evaluation baseline from a plurality of pre-configured candidate power evaluation baselines according to a target electric valve action type corresponding to an electric valve execution action;

[0154] The electric valve abnormality identification module is used to identify abnormalities based on the valve active power and target power evaluation baseline to obtain abnormality identification information.

[0155] The specific implementation of the electric valve data anomaly identification device is basically the same as the specific implementation of the electric valve data anomaly identification method described above, and will not be repeated here.

[0156] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned electric valve data abnormality identification method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0157] See also Fig.12 , Fig.12 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0158] The processor 1201 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application.

[0159] The memory 1202 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1202 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 1202, and the processor 1201 calls and executes the electric valve data abnormality identification method of the embodiment of this application;

[0160] Input / output interface 1203, used to implement information input and output;

[0161] The communication interface 1204 is used to realize the communication interaction between the device and other devices. The communication can be realized through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WI FI, Bluetooth, etc.);

[0162] A bus 1205 that transmits information between the various components of the device (e.g., the processor 1201, the memory 1202, the input / output interface 1203, and the communication interface 1204);

[0163] The processor 1201 , the memory 1202 , the input / output interface 1203 and the communication interface 1204 are connected to each other in communication within the device via the bus 1205 .

[0164] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned electric valve data abnormality identification method is implemented.

[0165] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0166] The electric valve data anomaly identification method, device, electronic device and storage medium provided in the embodiment of the present application, which triggers the electric valve to perform an action in response to the target electric valve, collects the valve control current and valve control voltage of the target electric valve corresponding to the electric valve execution action, wherein the action type of the electric valve execution action is the target electric valve action type, and then performs active power calculation based on the valve control current and valve control voltage to obtain the valve active power of the target electric valve, and then determines the target power evaluation baseline from multiple pre-configured candidate power evaluation baselines according to the target electric valve action type corresponding to the electric valve execution action, and performs anomaly identification based on the valve active power and the target power evaluation baseline to obtain anomaly identification information. It can be seen that the present application determines the matching target power evaluation baseline from the pre-configured candidate power evaluation baselines through the target electric valve action type, and then performs anomaly evaluation on the valve active power corresponding to the target electric valve triggering the electric valve execution action based on the target power evaluation baseline to obtain anomaly identification information, so that the data generated by the electric valve can be processed to perform anomaly identification, providing a basis for subsequent valve fault diagnosis.

[0167] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0168] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0169] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0170] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0171] The terms "first", "second", "third", "fourth", etc. (if any) 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 of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0172] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0173] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. The mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0174] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0175] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0176] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0177] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A method for identifying abnormal data of an electric valve, characterized in that: The method comprises: In response to the target electric valve triggering the electric valve to perform an action, the valve control current and valve control voltage of the target electric valve corresponding to the electric valve performing the action are collected; wherein the action type of the electric valve performing the action is the action type of the target electric valve; Performing active power calculation based on the valve control current and the valve control voltage to obtain the valve active power of the target electric valve; Determining a target power evaluation baseline from a plurality of pre-configured candidate power evaluation baselines according to the target electric valve action type corresponding to the electric valve execution action; Abnormality identification is performed based on the valve active power and the target power evaluation baseline to obtain abnormality identification information.

2. The method according to claim 1, characterized in that Before determining a target power assessment baseline from a plurality of pre-configured candidate power assessment baselines according to the target electric valve action type corresponding to the electric valve execution action, the method further includes pre-configuring the candidate power assessment baselines, specifically including: Acquire healthy active power data of the target electric valve corresponding to the action performed by the electric valve under normal operating conditions; Performing data cleaning processing based on the healthy active power data to obtain pure power data; Perform sliding window processing on the pure power data to obtain multiple valve power data groups; A multi-segment fitting process is performed based on the plurality of valve power data groups to obtain the candidate power evaluation baseline corresponding to the execution action of the electric valve.

3. The method according to claim 2, characterized in that The data cleaning process is performed based on the healthy active power data to obtain pure power data, including: Perform Laida's law calculation based on the healthy active power data to obtain a power abnormality value, and obtain a power abnormality time point corresponding to the power abnormality value; For each of the abnormal power values ​​in the healthy active power data, the valve active power of the target electric valve before and after the abnormal power time point is obtained based on a preset time wide range value to obtain first processed power data; The pure power data is obtained by performing mean calculation based on the first processed power data and replacing the corresponding power abnormal value in the healthy active power data.

4. The method according to claim 2, characterized in that: The sliding window processing is performed on the pure power data to obtain multiple valve power data groups, including: The pure power data is divided and processed based on a preset start-stop cut-off interval to obtain non-start-stop stage power data; Based on a preset window size value and a preset step movement value, sliding window processing is performed on the non-start-stop phase power data to obtain a plurality of valve power data groups.

5. The method according to claim 2, characterized in that: The performing of multi-segment fitting processing based on the plurality of valve power data groups to obtain the candidate power evaluation baseline corresponding to the electric valve execution action includes: Performing connection point fitting processing on the plurality of valve power data groups based on a differential evolution algorithm to obtain a power change inflection point; Based on the power change inflection point, a continuous function is fitted to the corresponding plurality of valve power data groups to obtain the candidate power evaluation baseline corresponding to the electric valve execution action.

6. The method according to claim 1, characterized in that The abnormality identification based on the valve active power and the target power evaluation baseline to obtain abnormality identification information includes: The active power of the valve is divided and processed based on the preset start-stop cut-off interval to obtain the target non-start-stop stage power data; Performing abnormal data frequency assessment based on the target non-start-stop phase power data and the target power assessment baseline to obtain first assessment information; Performing a power change trend assessment based on the target non-start / stop phase power data and the target power assessment baseline to obtain second assessment information; The abnormality identification information is obtained based on the first evaluation information and the second evaluation information.

7. The method according to claim 6, characterized in that The abnormal data frequency assessment is performed based on the target non-start-stop phase power data and the target power assessment baseline to obtain first assessment information, including: Determine the time point at which the target non-start-stop phase power data deviates from the target power evaluation baseline and exceeds the power fluctuation range as a power abnormal point; The first evaluation information is obtained according to a preset power anomaly number threshold and the number of power anomaly points within a preset power determination time.

8. The method according to claim 6, characterized in that The power change trend evaluation is performed based on the target non-start-stop phase power data and the target power evaluation baseline to obtain second evaluation information, including: Performing an overall change trend evaluation based on the target non-start-stop phase power data and the target power evaluation baseline to obtain overall evaluation information; Performing segmented change trend evaluation based on the target non-start-stop phase power data and the target power evaluation baseline to obtain local evaluation information; The second evaluation information is obtained based on the overall evaluation information and the local evaluation information.

9. The method according to claim 1, characterized in that: The abnormality identification based on the valve active power and the target power evaluation baseline to obtain abnormality identification information also includes: The power anomaly assessment model is used to identify the power anomaly of the valve active power based on a pre-trained power anomaly assessment model to obtain the anomaly identification information; wherein the power anomaly assessment model is pre-trained based on the target power assessment baseline.

10. The method according to claim 1, characterized in that Before performing power anomaly identification on the valve active power based on the pre-trained power anomaly assessment model to obtain the anomaly identification information, the power anomaly assessment model is pre-trained, including: Obtain a model training set; wherein the model training set includes valve power training data corresponding to the action performed by the electric valve, and each valve power training data is configured with a corresponding power sample label; Inputting the target power assessment baseline and the valve power training data into the original power abnormality assessment model for abnormality recognition training to obtain a sample recognition result; Comparing the sample recognition result corresponding to the valve power training data with the power sample label to obtain comparison deviation data; Based on the comparison deviation data, the model parameters of the power anomaly assessment model are updated, and the sound training sample is input into the power anomaly assessment model for sample recognition training until the power anomaly assessment model meets the preset training termination condition, thereby obtaining the pre-trained power anomaly assessment model.

11. An electric valve data abnormality identification device, characterized in that: The device comprises: An electric valve parameter acquisition module, for collecting a valve control current and a valve control voltage of the target electric valve corresponding to the electric valve execution action in response to the target electric valve triggering the electric valve execution action; wherein the action type of the electric valve execution action is the target electric valve action type; An electric valve power calculation module, used for performing active power calculation based on the valve control current and the valve control voltage to obtain the valve active power of the target electric valve; A power baseline screening module, configured to determine a target power evaluation baseline from a plurality of pre-configured candidate power evaluation baselines according to the target electric valve action type corresponding to the electric valve execution action; The electric valve abnormality identification module is used to perform abnormality identification based on the valve active power and the target power evaluation baseline to obtain abnormality identification information.

12. An electronic device, characterized in that: The electronic device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the method for identifying abnormal electric valve data according to any one of claims 1 to 10 when executing the computer program.

13. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the electric valve data abnormality identification method according to any one of claims 1 to 10 is implemented.

Images