Electric valve life prediction method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides an electric valve service life prediction 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; 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 prediction model from a plurality of pre-trained candidate power prediction models according to a target electric valve action type corresponding to the electric valve execution action; inputting the active power of the valve into a corresponding target power prediction model for power prediction, and obtaining the number of executable times of the target electric valve; and analyzing the service life of the electric valve according to the executable times corresponding to different action types to obtain target service life information. According to the embodiment of the invention, electric valve service life prediction information with more reference value can be obtained.

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 predicting the life of an electric valve. Background Art

[0002] The target electric valve is a commonly used equipment in modern industry and also in nuclear power plants. Common fault phenomena of the target electric valve include valve failure, stuck action, valve vibration, increased leakage, etc.

[0003] In the related art, in the life prediction of the target electric valve, more attention is paid to the remaining usable time of the target electric valve. However, in the actual use of the target electric valve, the remaining usable time is easily affected, and the target electric valve may even fail during the operation. Therefore, how to obtain electric valve life prediction information with more reference value 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 an electric valve life prediction method, device, electronic device and storage medium, aiming to obtain electric valve life prediction information with more reference value.

[0005] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present application provides a method for predicting the life 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 prediction model from a plurality of pre-trained candidate power prediction models according to the target electric valve action type corresponding to the electric valve execution action;

[0008] Inputting the valve active power into the corresponding target power prediction model to perform power prediction, and obtaining the executable times of the target electric valve;

[0009] The life of the electric valve is analyzed according to the executable times corresponding to different action types to obtain target life information.

[0010] In some embodiments, the step of inputting the valve active power into the corresponding target power prediction model to perform power prediction and obtain the executable times of the target electric valve includes:

[0011] Inputting the valve active power into the target power prediction model to obtain power prediction data of the electric valve execution action corresponding to the target electric valve action type when the target electric valve executes the action next time;

[0012] Performing a health status analysis on the target electric valve based on the power prediction data to obtain health prediction information of the electric valve;

[0013] In response to the electric valve health prediction information reflecting that the power prediction data meets a preset normal execution condition of the electric valve, updating the executable times according to the power prediction data;

[0014] The power prediction data is used as the new valve active power, and the process of inputting the valve active power into the target power prediction model is returned to execute until the electric valve health prediction information reflects that the power prediction data does not meet the normal execution conditions of the electric valve, thereby obtaining the updated executable times.

[0015] In some embodiments, the target electric valve is configured with a torque threshold corresponding to the target electric valve action type, and the health status analysis of the target electric valve based on the power prediction data to obtain the electric valve health prediction information includes:

[0016] Performing power value conversion based on the torque threshold to obtain power threshold information corresponding to the target electric valve action type;

[0017] Obtaining an operating power baseline based on the valve active power of the target electric valve;

[0018] The power prediction data corresponding to the target electric valve in the start-stop stage and the power threshold information are used to perform a start-stop stage power abnormality assessment to obtain first assessment information;

[0019] Performing an operation phase power abnormality assessment on the power prediction data corresponding to the target electric valve in the non-start / stop phase and the operation power baseline to obtain second assessment information;

[0020] The electric valve health prediction information is obtained based on the first evaluation information and the second evaluation information.

[0021] In some embodiments, the power threshold information includes a start power threshold and a stop power threshold, and the power prediction data corresponding to the target electric valve in the start-stop stage and the power threshold information are used to perform a start-stop power abnormality assessment to obtain first assessment information, including:

[0022] Perform power abnormality evaluation on the power prediction data corresponding to the target electric valve in the startup phase and the startup power threshold corresponding to the action type of the target electric valve to obtain startup power evaluation information;

[0023] Perform power abnormality evaluation on the power prediction data corresponding to the target electric valve in the stop phase and the stop power threshold corresponding to the action type of the target electric valve to obtain stop power evaluation information;

[0024] The first evaluation information is obtained according to the start power evaluation information and the stop power evaluation information.

[0025] In some embodiments, the operating power baseline is configured with a corresponding power fluctuation range, and the power prediction data corresponding to the target electric valve in the non-start-stop stage is compared with the operating power baseline to perform operating power abnormality evaluation to obtain second evaluation information, including:

[0026] Determine the time point at which the power prediction data corresponding to the target electric valve in the non-start-stop stage deviates from the operating power baseline and exceeds the power fluctuation range as a power abnormal point;

[0027] The second evaluation information is obtained according to a preset power anomaly number threshold and the number of the power anomaly points within a preset power determination time.

[0028] In some embodiments, the action types of the electric valve execution action include a valve opening type and a valve closing type, and the electric valve life analysis is performed according to the executable times corresponding to different action types to obtain target life information, including:

[0029] Determine the executable times corresponding to the valve opening type as the valve opening action times, and determine the executable times corresponding to the valve closing type as the valve closing action times;

[0030] Acquire a first loss weight coefficient corresponding to the valve opening type and a second loss weight coefficient corresponding to the valve closing type;

[0031] Performing equivalent conversion processing on the number of valve-openable actions based on the first loss weight coefficient to obtain a first equivalent number;

[0032] Performing equivalent conversion processing on the number of closable valve actions based on the second loss weight coefficient to obtain a second equivalent number;

[0033] The target lifetime information is determined based on the first equivalent number of times and the second equivalent number of times.

[0034] In some embodiments, determining the target life information based on the first equivalent number of times and the second equivalent number of times further includes:

[0035] Obtaining an operating environment coefficient corresponding to the target electric valve; wherein the operating environment coefficient includes content type and ambient temperature factors;

[0036] Performing environmental factor correction processing on the first equivalent number and the second equivalent number based on the operating environment coefficient to obtain a first corrected number and a second corrected number;

[0037] The target life information is determined based on the first correction number and the second correction number.

[0038] In some embodiments, the candidate power prediction model includes a valve opening action power prediction model. Before determining the target power prediction model from a plurality of pre-trained candidate power prediction models according to the target electric valve action type corresponding to the electric valve execution action, the valve opening action power prediction model is pre-trained, specifically including:

[0039] Acquire a valve opening action training data set, wherein the valve opening action training data set includes valve opening action training power and valve opening action sample power of the electric valve execution action corresponding to the target electric valve action type to be executed next time;

[0040] Inputting the valve opening action training power into the original valve opening action power prediction model for power prediction, and obtaining the valve opening action prediction power corresponding to the next time the target electric valve executes the action corresponding to the target electric valve action type;

[0041] Based on the comparison between the valve opening action prediction power and the valve opening action sample power, first comparison deviation data is obtained;

[0042] Based on the first comparison deviation data, the model parameters of the valve opening action power prediction model are updated, and the valve opening action training power is returned to be input into the original valve opening action power prediction model for power prediction until the valve opening action power prediction model meets the preset first training termination condition, so as to obtain the pre-trained valve opening action power prediction model.

[0043] In some embodiments, the candidate power prediction model includes a valve closing action power prediction model. Before determining the target power prediction model from a plurality of pre-trained candidate power prediction models according to the target electric valve action type corresponding to the electric valve execution action, the valve closing action power prediction model is pre-trained, specifically including:

[0044] Acquire a valve closing action training data set, wherein the valve closing action training data set includes a valve closing action training power and a valve closing action sample power of the electric valve execution action corresponding to the target electric valve action type to be executed next time;

[0045] Inputting the valve closing action training power into the original valve closing action power prediction model for power prediction, and obtaining the valve closing action prediction power corresponding to the next time the target electric valve executes the action corresponding to the target electric valve action type;

[0046] Comparing the valve closing action predicted power with the valve closing action sample power to obtain second comparison deviation data;

[0047] Based on the second comparison deviation data, the model parameters of the valve closing action power prediction model are updated, and the valve closing action training power is returned to be input into the original valve closing action power prediction model for power prediction until the valve closing action power prediction model meets the preset second training termination condition, so as to obtain the pre-trained valve closing action power prediction model.

[0048] In some embodiments, the electric valve execution action includes an electric valve opening action and an electric valve closing action, and the step of responding to the target electric valve triggering the electric valve execution action and collecting the valve control current and valve control voltage of the target electric valve corresponding to the electric valve execution action includes:

[0049] In response to the target electric valve triggering the electric valve opening action, collecting the valve opening action current and valve opening action voltage of the target electric valve;

[0050] In response to the target electric valve triggering the electric valve closing action, collecting the valve closing action current and valve closing action voltage of the target electric valve;

[0051] The active power calculation based on the valve control current and the valve control voltage is performed to obtain the valve active power of the target electric valve, including:

[0052] Performing active power calculation based on the valve opening action current and the valve opening action voltage to obtain the valve opening action power of the target electric valve;

[0053] Active power calculation is performed based on the valve closing action current and the valve closing action voltage to obtain the valve closing action power of the target electric valve.

[0054] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application provides a device for predicting the life of an electric valve, the device comprising:

[0055] 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;

[0056] 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;

[0057] A power model screening module, used to determine a target power prediction model from a plurality of pre-trained candidate power prediction models according to the target electric valve action type corresponding to the electric valve execution action;

[0058] An operation times prediction module, used for inputting the valve active power into the corresponding target power prediction model to perform power prediction and obtain the executable times of the target electric valve;

[0059] The electric valve life assessment module is used to analyze the electric valve life according to the executable times corresponding to different action types to obtain the target life information.

[0060] 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 life prediction method described in the first aspect is implemented.

[0061] 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, it implements the electric valve life prediction method described in the first aspect.

[0062] The electric valve life prediction method, device, electronic device and storage medium proposed in the present application trigger the electric valve execution action in response to the target electric valve, collect the valve control current and valve control voltage of the target electric valve corresponding to the electric valve execution action, and calculate the active power 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 prediction model from multiple pre-trained candidate power prediction models according to the target electric valve action type corresponding to the electric valve execution action, and then input the valve active power into the corresponding target power prediction model for power prediction to obtain the number of executable times of the target electric valve, and finally analyze the life of the electric valve according to the number of executable times corresponding to different action types to obtain the target life information. It can be seen from this that the present application obtains the valve active power of the electric valve execution action by calculation, and selects the matching target power prediction model according to the target electric valve action type to predict the number of executable times of the target electric valve after the target electric valve is executed, and obtains the target life information of the target electric valve according to the executable times, and the target life information is related to the number of executable times of various electric valve execution actions of the target electric valve, which is more valuable for reference in the actual application of the electric valve. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 is a flow chart of a method for predicting the life of an electric valve provided in an embodiment of the present application;

[0064] Figure 2 yes Figure 1 Flow chart of steps S101 to S102 in FIG.

[0065] Figure 3 yes Figure 1 Another flowchart of steps S101 to S102 in FIG. 1 ;

[0066] Figure 4 yes Figure 1 The flowchart before step S103 in FIG.

[0067] Figure 5 yes Figure 1 Another flowchart before step S103 in ;

[0068] Figure 6 yes Figure 1 Flow chart of step S104 in FIG.

[0069] Figure 7 yes Figure 6 Flowchart of step S602 in FIG.

[0070] Figure 8 yes Figure 7 Flow chart of step S703 in FIG.

[0071] Fig. 9 yes Figure 7 Flow chart of step S704 in FIG.

[0072] Fig.10 yes Figure 1 Flow chart of step S105 in FIG.

[0073] Fig.11 yes Fig.10 Flow chart of step S1005 in FIG.

[0074] Fig.12 is a schematic diagram of the structure of the electric valve life prediction device provided in an embodiment of the present application;

[0075] Fig.13 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0076] 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.

[0077] 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.

[0078] 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.

[0079] The embodiments of the present application provide a method, device, electronic device and storage medium for predicting the life of an electric valve, aiming to obtain more valuable reference information on the life of an electric valve.

[0080] The electric valve life prediction 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 life prediction method in the embodiments of the present application is described.

[0081] The electric valve life prediction method provided in the embodiment of the present application relates to the field of electric valve technology. The electric valve life prediction 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 life prediction method, etc., but is not limited to the above forms.

[0082] 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.

[0083] Figure 1 is an optional flow chart of the electric valve life prediction method provided in the embodiment of the present application, Figure 1 The method may include but is not limited to steps S101 to S105.

[0084] 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;

[0085] 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;

[0086] Step S103, determining a target power prediction model from a plurality of pre-trained candidate power prediction models according to a target electric valve action type corresponding to the electric valve execution action;

[0087] Step S104, inputting the valve active power into the corresponding target power prediction model to perform power prediction, and obtaining the number of executable times of the target electric valve;

[0088] Step S105 , analyzing the life of the electric valve according to the executable times corresponding to different action types to obtain target life information.

[0089] Steps S101 to S105 shown in the embodiment of the present application, by responding to the target electric valve triggering the electric valve execution action, collecting the valve control current and valve control voltage of the target electric valve corresponding to the electric valve execution action, and performing 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 according to the target electric valve action type corresponding to the electric valve execution action, determine the target power prediction model from multiple pre-trained candidate power prediction models, and then input the valve active power into the corresponding target power prediction model for power prediction to obtain the number of executable times of the target electric valve, and finally perform electric valve life analysis according to the number of executable times corresponding to different action types to obtain target life information. It can be seen from this that the present application obtains the valve active power of the electric valve execution action by calculation, and selects the matching target power prediction model according to the target electric valve action type to predict the number of executable times of the target electric valve after the target electric valve is executed, and obtains the target life information of the target electric valve according to the executable times, and the target life information is related to the number of executable times of various electric valve execution actions of the target electric valve, and has more reference value in the actual application process of the electric valve.

[0090] 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.

[0091] 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.

[0092] See also Figure 2 In some embodiments, the electric valve execution action includes an electric valve opening action, and steps S101 to S102 may include but are not limited to steps S201 to S202:

[0093] Step S201, in response to the target electric valve triggering the electric valve opening action, collecting the valve opening action current and valve opening action voltage of the target electric valve;

[0094] Step S202, performing active power calculation based on the valve opening action current and the valve opening action voltage to obtain the valve opening action power of the target electric valve;

[0095] See also Figure 3 In some embodiments, the electric valve execution action includes the electric valve closing action, and steps S101 to S102 may include but are not limited to steps S301 to S302:

[0096] Step S301, in response to the target electric valve triggering the electric valve closing action, collecting the valve closing action current and valve closing action voltage of the target electric valve;

[0097] Step S302 , performing active power calculation based on the valve closing action current and the valve closing action voltage to obtain the valve closing action power of the target electric valve.

[0098] In steps S201 to S202 of some embodiments, the target electric valve performs an electric valve opening action, and the valve opening action current and valve opening action voltage corresponding to this process are collected. The valve opening action current and valve opening action voltage are respectively the valve control current and valve control voltage when the target electric valve performs the electric valve opening action. Active power is calculated based on the valve opening action current and valve opening action voltage to obtain the valve active power corresponding to the target electric valve performing the electric valve opening action, that is, the valve opening action power.

[0099] It should be noted that the collected valve opening action current and valve opening action voltage are the current data and voltage data within a period of time when the target electric valve triggers the electric valve opening action, and the calculated valve opening action power is also the active power of the valve corresponding to this time.

[0100] In some embodiments, the processing process in steps S301 to S302 is the same as that in steps S201 to S202, except that the valve closing action current and valve closing action voltage when the target electric valve performs the electric valve closing action are processed here. In order to save space, it will not be repeated here.

[0101] Corresponding data collection is performed for different action types of the target electric valve to ensure that the current and voltage data of the target electric valve under different working conditions are collected, providing the necessary basic data for subsequent active power calculation and life prediction.

[0102] In step S103 of some embodiments, a target power prediction model is determined from multiple pre-trained candidate power prediction models according to the target electric valve action type corresponding to the electric valve execution action. The candidate power prediction model is trained based on data collected by the target electric valve under different action types to ensure the accuracy and reliability of power prediction.

[0103] See also Figure 4 In some embodiments, the candidate power prediction model includes a valve opening action power prediction model, and before step S103, the valve opening action power prediction model is pre-trained, which may include but is not limited to steps S401 to S404:

[0104] Step S401, obtaining a valve opening action training data set, wherein the valve opening action training data set includes a valve opening action training power and a valve opening action sample power of an electric valve execution action corresponding to a target electric valve action type to be executed next time;

[0105] Step S402, inputting the valve opening action training power into the original valve opening action power prediction model for power prediction, and obtaining the valve opening action prediction power of the electric valve execution action corresponding to the target electric valve action type when the target electric valve executes the action next time;

[0106] Step S403, comparing the valve opening action prediction power with the valve opening action sample power to obtain first comparison deviation data;

[0107] Step S404, based on the first comparison deviation data, updates the model parameters of the valve opening action power prediction model, returns to execute the input of the valve opening action training power into the original valve opening action power prediction model for power prediction, until the valve opening action power prediction model meets the preset first training termination condition, and obtains the pre-trained valve opening action power prediction model.

[0108] In step S401 of some embodiments, a valve opening action training data set is obtained, and the valve opening action training data set includes power data of the target electric valve when performing the electric valve opening action, that is, the valve opening action training power, which can be calculated by the valve control voltage and valve control current of the target electric valve when performing the electric valve opening action. The valve opening action training data set also includes the valve opening action sample power of the electric valve execution action corresponding to the target electric valve action type when the target electric valve performs the next time, which is used to compare the prediction results of the valve opening action prediction evaluation model. It should be noted that the valve opening action training power here is not an instantaneous single power value, but a power value of the target electric valve within a period of time when the electric valve is performing the electric valve opening action, so that the valve opening action power prediction model can learn the power change trend characteristics of the target electric valve when performing the electric valve opening action. It should be noted that in order to better simulate the valve active power of the target electric valve under the real state, the valve opening action training data set does not only include the valve opening action training power under the normal operating condition of the target electric valve.

[0109] In step S402 of some embodiments, the valve opening action training power is input into the original valve opening action power prediction model for power prediction to obtain the valve opening action prediction power of the electric valve execution action corresponding to the target electric valve action type when the target electric valve executes the action next time.

[0110] In step S403 of some embodiments, the predicted power of the valve opening action is compared with the corresponding sample power of the valve opening action in the valve opening action training data set to obtain first comparison deviation data, that is, the loss value is obtained by means of a loss function to update the valve opening action power prediction model.

[0111] In step S404 of some embodiments, the model parameters of the valve opening action power prediction model are updated through the first comparison deviation data, and this process is repeated until the valve opening action power prediction model meets the preset first training termination condition, that is, the deviation value between the obtained valve opening action prediction power and the valve opening action sample power is within the preset allowable fluctuation range, and the power curve composed of the valve opening action prediction power and the power curve composed of the valve opening action sample power are the same in overall trend characteristics. Finally, a pre-trained valve opening action power prediction model is obtained.

[0112] It should be noted that the valve opening action power prediction model can be a long short-term memory network model (Long Short-Term Memory, LSTM), and in the training process, a large number of different electric valve opening action training powers are used to construct a training set. When the target electric valve performs the electric valve opening action, the power curve composed of the valve active power has a certain regularity. Therefore, the overall trend characteristics of the power curve composed of the valve opening action prediction power can reflect the health status of the target electric valve when it performs the electric valve opening action next time.

[0113] Through steps S401 to S404, the valve opening action power prediction model is trained using the valve opening action training data set, which can ensure that the valve opening action power prediction model of the electric valve has high prediction accuracy in practical applications, and provide a solid foundation for the life prediction and health management of the electric valve.

[0114] See also Figure 5 In some embodiments, the candidate power prediction model includes a valve closing action power prediction model, and before step S103, the step further includes pre-training the valve opening action power prediction model, which may include but is not limited to steps S501 to S504:

[0115] Step S501, obtaining a valve closing action training data set, wherein the valve closing action training data set includes the valve closing action training power and the valve closing action sample power of the electric valve execution action corresponding to the target electric valve action type to be executed next time;

[0116] Step S502, inputting the valve closing action training power into the original valve closing action power prediction model for power prediction, and obtaining the valve closing action prediction power of the electric valve execution action corresponding to the target electric valve action type when the target electric valve executes the action next time;

[0117] Step S503, comparing the predicted power of the valve closing action with the sample power of the valve closing action to obtain second comparison deviation data;

[0118] Step S504, based on the second comparison deviation data, the model parameters of the valve closing action power prediction model are updated, and the execution returns to input the valve closing action training power into the original valve closing action power prediction model for power prediction, until the valve closing action power prediction model meets the preset second training termination condition, and the pre-trained valve closing action power prediction model is obtained.

[0119] In some embodiments, in steps S501 to 504, the training process of the valve closing action power prediction model is similar to the training process of the valve opening action power prediction model in steps S401 to S404, except that the valve closing action training data set is used here, and the valve closing action power prediction model learns the power change trend characteristics of the target electric valve when performing the electric valve closing action. In order to save space, it will not be repeated here.

[0120] In step S104 of some embodiments, the calculated valve active power is input into a target power prediction model of a corresponding action type to perform power prediction, thereby obtaining the number of executable actions of the target electric valve.

[0121] See also Figure 6 In some embodiments, step S104 may include but is not limited to steps S601 to S604:

[0122] Step S601, inputting the valve active power into the target power prediction model to obtain the power prediction data of the target electric valve performing the electric valve execution action corresponding to the target electric valve action type next time;

[0123] Step S602, analyzing the health status of the target electric valve based on the power prediction data to obtain the electric valve health prediction information;

[0124] Step S603, in response to the electric valve health prediction information reflecting that the power prediction data meets the preset normal execution condition of the electric valve, the executable times are updated according to the power prediction data;

[0125] Step S604, using the power prediction data as the new valve active power, returning to execute inputting the valve active power into the target power prediction model until the electric valve health prediction information reflects that the power prediction data does not meet the normal execution conditions of the electric valve, and obtaining the updated executable times.

[0126] In step S601 of some embodiments, the valve active power is input into the target power prediction model to obtain power prediction data of the electric valve execution action corresponding to the target electric valve action type when the target electric valve executes the next time. If it is an opening valve type electric valve execution action, the valve active power is input into the opening valve action power prediction model. If it is a closing valve type electric valve execution action, the valve active power is input into the closing valve action power prediction model.

[0127] In step S602 of some embodiments, the power prediction data is analyzed to obtain health prediction information of the target electric valve, that is, to evaluate whether the target electric valve is in a good working condition when the target electric valve performs the electric valve execution action corresponding to the target electric valve action type next time, and whether there are any potential performance problems or failure risks.

[0128] In step S603 of some embodiments, if the electric valve health prediction information obtained through the health status analysis reflects that there is no potential abnormality when the target electric valve executes the electric valve execution action corresponding to the target electric valve action type next time, and the preset electric valve normal execution conditions are met, then it means that the target electric valve can normally perform the next electric valve execution action corresponding to the target electric valve action type, and this electric valve execution action can be recorded in the number of executable times.

[0129] In step S604 of some embodiments, the power prediction data is regarded as the valve active power corresponding to the completed electric valve execution action, and the valve active power is returned and input into the target power prediction model to continuously perform power prediction of the subsequent electric valve execution action corresponding to the target electric valve action type, and update the executable times until the predicted power prediction data does not meet the normal execution conditions of the electric valve. The final executable times, that is, the maximum number of times the target electric valve can perform the electric valve execution action corresponding to the target electric valve action type, can reflect the expected remaining life of the target electric valve in the current healthy state to a certain extent.

[0130] In some embodiments, the normal execution condition of the electric valve also includes setting a prediction limit value for the number of times, which is used to predict a certain number of executable times, and then stop the power prediction of the electric valve execution action corresponding to the subsequent target electric valve action type. This is because in the actual application process, when the service life of the target electric valve is still very sufficient, the target electric valve still has a lot of executable times. In order not to waste computing resources on calculating how many specific executable times there are, the prediction limit value for the number of times is set, that is, after predicting a certain number of executable times, it can be stopped, and it is considered that the service life of the current target electric valve is still very sufficient. For example, if the prediction limit value for the number of times is set to 20, it is predicted whether the 20 electric valve execution actions corresponding to the subsequent target electric valve action type will be abnormal, and the subsequent electric valve execution actions can be predicted. This value is only for explanation and is not used to limit the specific number of the prediction limit value. Those skilled in the art can reasonably set it according to actual needs and system computing power resources. In the field of nuclear power, in order to ensure safety and reliability, a higher prediction limit value for the number of times can be set to obtain more known executable times.

[0131] Through steps S601 to S604, the health status of the target electric valve can be evaluated and the executable number of the target electric valve corresponding to the target electric valve action type can be updated according to the power prediction data. The executable number is a life prediction information with higher reference value. In the related art, the life prediction information of the target electric valve is displayed in the form of the remaining operable time. However, in actual application, the executable number is directly related to the actual working cycle of the target electric valve, directly reflects the performance degradation and wear of the target electric valve after a certain number of operation cycles, and can more intuitively indicate the life information of the target electric valve. The remaining operable time is an evaluation dimension that is difficult to accurately achieve, and it is also more complicated when predicting the life. In addition, the executable number is easier to combine with the maintenance plan and replacement strategy. The operator can arrange regular inspections and maintenance according to the executable number of the target electric valve to ensure that necessary measures are taken before the predetermined number of operations is reached, so that the maintenance and management of the target electric valve is more refined and reliable, which helps to identify and prevent potential failures in advance. In the field of nuclear power, this reliability and accuracy are particularly important.

[0132] See also Figure 7 In some embodiments, the target electric valve is configured with a torque threshold corresponding to the target electric valve action type, and step S602 may include but is not limited to steps S701 to S705:

[0133] Step S701, performing power value conversion based on the torque threshold to obtain power threshold information corresponding to the target electric valve action type;

[0134] Step S702, obtaining an operating power baseline based on the valve active power of the target electric valve;

[0135] Step S703, performing a power abnormality evaluation on the start-stop stage using the power prediction data and power threshold information corresponding to the target electric valve in the start-stop stage to obtain first evaluation information;

[0136] Step S704, performing an operation phase power abnormality assessment on the power prediction data corresponding to the target electric valve in the non-start-stop phase and the operation power baseline to obtain second assessment information;

[0137] Step S705 , obtaining electric valve health prediction information based on the first evaluation information and the second evaluation information.

[0138] In step S701 of some embodiments, the target electric valve is configured with a torque threshold corresponding to the target electric valve action type, and a power value conversion is performed according to the torque threshold to obtain power threshold information corresponding to the target electric valve action type, thereby associating the torque information of the target electric valve with the power information. The torque of the target electric valve describes the ability of the force to produce a rotational effect on an object, and can directly reflect the ability of the target electric valve when performing an electric valve execution action. The torque threshold is the expected torque value within the normal working range of the target electric valve, and the power threshold information is the value of the valve active power of the target electric valve corresponding to the torque threshold.

[0139] In step S702 of some embodiments, an operating power baseline is obtained based on the valve active power of the target electric valve. The operating power baseline represents the average power consumption of the target electric valve under normal operating conditions, which is equivalent to providing a reference line for evaluating the difference between the actual power consumption and the expected power consumption of the target electric valve during operation, so as to identify whether the target electric valve is abnormal.

[0140] The operating power baseline can be obtained through the valve active power of the target electric valve when multiple electric valves corresponding to the target electric valve action type perform actions, can be obtained through neural network model training, and can also be obtained through algorithm processing. The operating power baseline can reflect the average power consumption of the target electric valve at each time point when the electric valve performs an action. The operating power baseline also has the power change trend characteristics of the target electric valve when the electric valve performs an action to a certain extent, and can be used to evaluate whether the power change trend characteristics of the power prediction data are abnormal.

[0141] In step S703 of some embodiments, the power prediction data corresponding to the target electric valve in the start-stop stage and the power threshold information are used to perform a start-stop stage power abnormality assessment to obtain first assessment information. This is because in general, the valve active power of the target electric valve will exceed the threshold in the power threshold information only in the start-stop stage.

[0142] The target electric valve can be divided into different operation stages under the operating state, namely the start-up stage, the non-start-stop stage and the stop stage. The start-up stage refers to 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. The valve active power will suddenly increase sharply from a low state, and quickly fall back to a stable state as the target electric valve starts to operate. Therefore, the valve active power will fluctuate greatly in this stage. The non-start-stop stage refers to the state of normal operation of the target electric valve. In this stage, the target electric valve has been fully started and operates stably. 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 refers to 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. The start-stop stage includes the start-up stage and the stop stage.

[0143] See also Figure 8 In some embodiments, step S703 may include but is not limited to steps S801 to S803:

[0144] Step S801, performing power abnormality evaluation on the power prediction data corresponding to the target electric valve in the startup phase and the startup power threshold corresponding to the action type of the target electric valve to obtain startup power evaluation information;

[0145] Step S802, performing power abnormality evaluation on the power prediction data corresponding to the target electric valve in the stop phase and the stop power threshold corresponding to the action type of the target electric valve to obtain stop power evaluation information;

[0146] Step S803: obtaining first evaluation information according to the start power evaluation information and the stop power evaluation information.

[0147] In step S801 of some embodiments, the power prediction data corresponding to the target electric valve in the startup phase is compared with the startup power threshold of the corresponding target electric valve action type. The startup power threshold sets the expected power consumption range when the target electric valve is started. In order to transform the target electric valve from a static state to a working state, a large amount of energy needs to be consumed. The power prediction data of the target electric valve at this stage is relatively high. By evaluating the power prediction data in the startup phase, the startup power evaluation information is obtained, so as to evaluate whether there is power abnormality in the target electric valve in the startup phase. For example, if the power consumption is too high, it indicates that the target electric valve is difficult to start and there may be mechanical blockage.

[0148] It should be noted that when electric valves of different action types are executed, the starting power threshold and stopping power threshold used are also different. The electric valve opening action has a corresponding starting power threshold and stopping power threshold, while the electric valve closing action has another corresponding starting power threshold and stopping power threshold, thereby realizing the execution of actions on electric valves of different action types and performing corresponding power abnormality assessment on the power prediction data corresponding to the start and stop stages.

[0149] In step S802 of some embodiments, the power prediction data corresponding to the target electric valve in the stop phase is compared with the stop power threshold corresponding to the target electric valve action type. The stop power threshold sets the expected power consumption range of the target electric valve when completing the electric valve execution action. The power consumption in this process is usually different from that in the start phase. By evaluating the power prediction data in the stop phase, the stop power evaluation information can be obtained, so that it can be identified whether there is power abnormality in the stop process of the target electric valve. For example, too low power consumption may mean that the target electric valve has not stopped completely or has a leakage problem.

[0150] In step S803 of some embodiments, first evaluation information is obtained based on the starting power evaluation information and the stopping power evaluation information, so as to evaluate the power performance of the target electric valve in the starting phase and the stopping phase when the electric valve executes the action. If the power prediction data indicates that the power consumption of the target electric valve in the starting phase and the stopping phase are within the normal range, then it can be considered that the start-stop phase performance of the target electric valve is healthy. If an abnormality occurs in any stage, further diagnosis and maintenance may be required.

[0151] Through step S801 to step S803, through the staged power anomaly evaluation, possible problems of the target electric valve in the start-stop stage can be discovered in time, thereby improving the reliability and safety of the target electric valve life prediction.

[0152] In step S704 of some embodiments, power prediction data corresponding to the target electric valve in the non-start-stop phase is compared with the operating power baseline to perform an operating phase power anomaly assessment to obtain second assessment information.

[0153] See also Fig. 9 In some embodiments, the operating power baseline is configured with a corresponding power fluctuation range, and step S704 may include but is not limited to steps S901 to S902:

[0154] Step S901, determining the time point at which the power prediction data corresponding to the target electric valve in the non-start-stop stage deviates from the operating power baseline and exceeds the power fluctuation range as a power abnormal point;

[0155] Step S902: obtaining second evaluation information according to a preset power anomaly number threshold and the number of power anomaly points within a preset power determination time.

[0156] In step S901 of some embodiments, during the normal operation of the target electric valve, that is, the non-start-stop stage, the power prediction data deviates from the operating power baseline by more than the power fluctuation range, that is, the power prediction data deviates from the operating power baseline by more than a certain range, then the time point beyond the range is considered to be a power abnormal point. The power fluctuation range is used to limit the range of the power prediction data deviation from the operating power baseline. Those skilled in the art can set it according to the performance parameters of the target electric valve, or obtain an approximate fluctuation range through experiments.

[0157] In step S902 of some embodiments, it should be noted that the power abnormal point does not necessarily indicate that there is a problem with the target electric valve. The valve active power of the target electric valve in the actual operation process will inevitably fluctuate and just exceed the power fluctuation range. There may also be problems with data collection, and the power prediction data predicted by the target power prediction model may also be slightly biased. Therefore, it is necessary to comprehensively evaluate the preset power abnormality number threshold and the number of power abnormal points within the preset power judgment time to obtain the second evaluation information. If the number of power abnormal points exceeds the power abnormality number threshold within the power judgment time, it is considered that the target electric valve does have a power abnormality during this process, and the second evaluation information reflects that the power prediction data of the target electric valve in the non-start-stop stage is abnormal.

[0158] Through step S901 to step S902, the power consumption of the target electric valve in the non-start-stop stage is monitored and analyzed in detail through stage-by-stage power anomaly evaluation, so that possible problems of the target electric valve in the non-start-stop stage can be discovered in time, thereby improving the reliability and safety of the target electric valve life prediction.

[0159] In step S705 of some embodiments, the electric valve health prediction information is obtained based on the first evaluation information and the second evaluation information, and the health evaluation information of the target electric valve in the start-stop stage and the non-start-stop stage is integrated. If the first evaluation information and the second evaluation information both show that the power consumption of the target electric valve is normal, then it can be predicted that the target electric valve is in a healthy state. If the evaluation results of either the first evaluation information or the second evaluation information show abnormality, then it may be necessary to further inspect or maintain the target electric valve.

[0160] Through steps S701 to S705, the power prediction data obtained by the target electric valve can be analyzed in stages, that is, whether the target electric valve is in a good working state and whether there are any potential performance problems or failure risks when the target electric valve performs the electric valve execution action corresponding to the target electric valve action type next time, so as to more accurately obtain the number of times the target electric valve can execute the electric valve execution action corresponding to the target electric valve action type. Through the staged health status analysis, the performance of the target electric valve under different operating conditions can be analyzed more accurately.

[0161] In step S105 of some embodiments, the life of the electric valve is analyzed according to the executable times corresponding to different action types to obtain target life information.

[0162] See also Fig.10 In some embodiments, the action types of the electric valve include valve opening type and valve closing type, and step S105 may include but is not limited to steps S1001 to S1005:

[0163] Step S1001, determining the executable times corresponding to the valve opening type as the valve opening action times, and determining the executable times corresponding to the valve closing type as the valve closing action times;

[0164] Step S1002, obtaining a first loss weight coefficient corresponding to the valve opening type and a second loss weight coefficient corresponding to the valve closing type;

[0165] Step S1003, performing equivalent conversion processing on the number of valve-openable actions based on the first loss weight coefficient to obtain a first equivalent number;

[0166] Step S1004, performing equivalent conversion processing on the number of closable valve actions based on the second loss weight coefficient to obtain a second equivalent number;

[0167] Step S1005 , determining target life information based on the first equivalent number of times and the second equivalent number of times.

[0168] In steps S1001 to S1002 of some embodiments, the executable number corresponding to the valve opening type is determined as the number of valve opening actions, and the executable number corresponding to the valve closing type is determined as the number of valve closing actions. The electric valve execution actions of the valve opening type and the valve closing type have different effects on the wear and loss of the target electric valve. Therefore, the first loss weight coefficient corresponding to the valve opening type and the second loss weight coefficient corresponding to the valve closing type are obtained. The first loss weight coefficient and the second loss weight coefficient reflect the relative importance of the impact of different action types on the life of the target electric valve, which can be determined based on historical data, expert experience and experimental results.

[0169] In steps S1003 to S1005 of some embodiments, the number of valve-openable actions is equivalently converted based on the first loss weight coefficient to obtain the first equivalent number. The first loss weight coefficient is used to obtain the actual impact of the valve-opening type electric valve execution action on the target electric valve, and the first equivalent number of the target electric valve is adjusted. Similarly, the number of valve-closable actions is equivalently converted using the second loss weight coefficient to obtain the second equivalent number. This step is also to reflect the actual impact of the valve-closing action on the life of the electric valve, and the number of valve-closable actions is adjusted using the second loss weight coefficient. Finally, the target life information is determined based on the first equivalent number and the second equivalent number, and the impact of different action types on the target electric valve is combined to obtain the actual remaining execution times of the target electric valve, which is determined as the target life information.

[0170] In some embodiments, when it is known from the remaining execution times that the service life of the target electric valve is running out, an early warning can be issued to notify relevant staff to repair or replace the target electric valve. A credibility limit can also be set. In the field of nuclear power, in order to ensure the safe and reliable operation of nuclear power plants, after obtaining the remaining execution times, only the first certain number of the remaining execution times is considered credible, and the subsequent values ​​are only used as reference information, so as to more rigorously handle the life information such as the remaining execution times.

[0171] It should be noted that, although the present application predicts the target life information of the target electric valve, it does not mean that the online detection system of the target electric valve is not in operation.

[0172] Through steps S1001 to S1005, not only the actual number of actions of the target electric valve is taken into consideration, but also the different effects of electric valve execution actions of different action types on the life of the target electric valve are taken into consideration. The number of valve-openable actions and the number of valve-closable actions are equivalently converted to obtain the remaining number of executions of the target electric valve, thereby providing more reliable data support for the health management of the electric valve.

[0173] See also Fig.11 In some embodiments, step S1005 may also include but is not limited to steps S1101 to S1103:

[0174] Step S1101, obtaining an operating environment coefficient corresponding to a target electric valve; wherein the operating environment coefficient includes factors such as content type and ambient temperature;

[0175] Step S1102, performing environmental factor correction processing on the first equivalent number and the second equivalent number based on the operating environment coefficient to obtain a first corrected number and a second corrected number;

[0176] Step S1103, determining target life information based on the first correction number and the second correction number.

[0177] In step S1101 of some embodiments, the operating environment coefficient of the target electric valve is obtained. Different target electric valves are in different environments and perform different tasks, and may suffer different degrees of loss. Therefore, it is necessary to obtain information about the working environment of the target electric valve to obtain the operating environment coefficient of the target electric valve. The operating environment coefficient includes the content type and the ambient temperature factor. The content type is the conveyed material passing through the target electric valve, including gas, liquid, etc., and the ambient temperature factor includes the temperature of the conveyed material itself and the temperature of the environment in which the target electric valve is located. The content type and the ambient temperature factor may affect the wear rate and corrosion degree of the target electric valve, and also include other factors, such as the electric valve pressure, conveying flow rate, etc.

[0178] In steps S1102 to S1103 of some embodiments, the first equivalent number and the second equivalent number are corrected using the obtained operating environment coefficient, so that when determining the target life information, the environmental impact of the target electric valve is taken into consideration to obtain the first corrected number and the second corrected number. Finally, the target life information of the target electric valve is determined based on the first corrected number and the second corrected number. The comprehensive life prediction that comprehensively considers the action type, loss weight coefficient and operating environment coefficient of the action performed by the electric valve can obtain a more authentic and reliable target life information.

[0179] In some embodiments, if conditions permit, a power prediction model can be constructed for each target electric valve, and trained based on the historical operating data of each target electric valve. This allows the impact of environmental factors on the target electric valve to be taken into account when evaluating the power prediction data, thereby obtaining more accurate life prediction information, which can be used separately for some particularly important target electric valves.

[0180] See also Fig.12 The embodiment of the present application further provides an electric valve life prediction device, which can implement the above-mentioned electric valve life prediction method, and the device includes:

[0181] The electric valve parameter acquisition module is used to respond to the target electric valve triggering the electric valve execution action, and to acquire 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;

[0182] 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;

[0183] A power model screening module, used to determine a target power prediction model from a plurality of pre-trained candidate power prediction models according to a target electric valve action type corresponding to an electric valve execution action;

[0184] An operation times prediction module is used to input the valve active power into the corresponding target power prediction model to perform power prediction and obtain the executable times of the target electric valve;

[0185] The electric valve life assessment module is used to analyze the electric valve life according to the executable times corresponding to different action types to obtain target life information.

[0186] The specific implementation of the electric valve life prediction device is basically the same as the specific implementation of the electric valve life prediction method described above, and will not be repeated here.

[0187] 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 life prediction method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0188] See also Fig.13 , Fig.13 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0189] The processor 1301 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.

[0190] The memory 1302 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 1302 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 1302, and the processor 1301 calls and executes the electric valve life prediction method of the embodiment of this application;

[0191] Input / output interface 1303, used to implement information input and output;

[0192] The communication interface 1304 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.);

[0193] A bus 1305 that transmits information between the various components of the device (e.g., the processor 1301, the memory 1302, the input / output interface 1303, and the communication interface 1304);

[0194] The processor 1301 , the memory 1302 , the input / output interface 1303 and the communication interface 1304 are connected to each other in communication within the device via a bus 1305 .

[0195] 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 life prediction method is implemented.

[0196] 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.

[0197] The electric valve life prediction method, device, electronic device and storage medium provided in the embodiment of the present application trigger the electric valve execution action in response to the target electric valve, collect the valve control current and valve control voltage of the target electric valve corresponding to the electric valve execution action, and calculate the active power 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 prediction model from multiple pre-trained candidate power prediction models according to the target electric valve action type corresponding to the electric valve execution action, and then input the valve active power into the corresponding target power prediction model for power prediction to obtain the number of executable times of the target electric valve, and finally analyze the life of the electric valve according to the number of executable times corresponding to different action types to obtain the target life information. It can be seen from this that the present application obtains the valve active power of the electric valve execution action by calculation, and selects the matching target power prediction model according to the target electric valve action type to predict the number of executable times of the target electric valve after the target electric valve is executed, and obtains the target life information of the target electric valve according to the executable times, and the target life information is related to the number of executable times of various electric valve execution actions of the target electric valve, which is more valuable for reference in the actual application of the electric valve.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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 predicting the life 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 prediction model from a plurality of pre-trained candidate power prediction models according to the target electric valve action type corresponding to the electric valve execution action; Inputting the valve active power into the corresponding target power prediction model to perform power prediction, and obtaining the executable times of the target electric valve; The life of the electric valve is analyzed according to the executable times corresponding to different action types to obtain target life information.

2. The method according to claim 1, characterized in that The step of inputting the valve active power into the corresponding target power prediction model to perform power prediction and obtain the executable times of the target electric valve includes: Inputting the valve active power into the target power prediction model to obtain power prediction data of the electric valve execution action corresponding to the target electric valve action type when the target electric valve executes the action next time; Performing a health status analysis on the target electric valve based on the power prediction data to obtain health prediction information of the electric valve; In response to the electric valve health prediction information reflecting that the power prediction data meets a preset normal execution condition of the electric valve, updating the executable times according to the power prediction data; The power prediction data is used as the new valve active power, and the process of inputting the valve active power into the target power prediction model is returned to execute until the electric valve health prediction information reflects that the power prediction data does not meet the normal execution conditions of the electric valve, thereby obtaining the updated executable times.

3. The method according to claim 2, characterized in that The target electric valve is configured with a torque threshold corresponding to the target electric valve action type, and the health status analysis of the target electric valve based on the power prediction data is performed to obtain the electric valve health prediction information, including: Performing power value conversion based on the torque threshold to obtain power threshold information corresponding to the target electric valve action type; Obtaining an operating power baseline based on the valve active power of the target electric valve; The power prediction data corresponding to the target electric valve in the start-stop stage and the power threshold information are used to perform a start-stop stage power abnormality assessment to obtain first assessment information; Performing an operation phase power abnormality assessment on the power prediction data corresponding to the target electric valve in the non-start / stop phase and the operation power baseline to obtain second assessment information; The electric valve health prediction information is obtained based on the first evaluation information and the second evaluation information.

4. The method according to claim 3, characterized in that The power threshold information includes a start power threshold and a stop power threshold. The power prediction data corresponding to the target electric valve in the start and stop phase is evaluated for start and stop power abnormality with the power threshold information to obtain first evaluation information, including: Perform power abnormality evaluation on the power prediction data corresponding to the target electric valve in the startup phase and the startup power threshold corresponding to the action type of the target electric valve to obtain startup power evaluation information; Perform power abnormality evaluation on the power prediction data corresponding to the target electric valve in the stop phase and the stop power threshold corresponding to the action type of the target electric valve to obtain stop power evaluation information; The first evaluation information is obtained according to the start power evaluation information and the stop power evaluation information.

5. The method according to claim 3, characterized in that: The operating power baseline is configured with a corresponding power fluctuation range, and the power prediction data corresponding to the target electric valve in the non-start-stop stage is compared with the operating power baseline to perform operating power abnormality evaluation to obtain second evaluation information, including: Determine the time point at which the power prediction data corresponding to the target electric valve in the non-start-stop stage deviates from the operating power baseline and exceeds the power fluctuation range as a power abnormal point; The second evaluation information is obtained according to a preset power anomaly number threshold and the number of the power anomaly points within a preset power determination time.

6. The method according to claim 1, characterized in that The action types of the electric valve execution action include valve opening type and valve closing type, and the electric valve life analysis is performed according to the executable times corresponding to different action types to obtain target life information, including: Determine the executable times corresponding to the valve opening type as the valve opening action times, and determine the executable times corresponding to the valve closing type as the valve closing action times; Acquire a first loss weight coefficient corresponding to the valve opening type and a second loss weight coefficient corresponding to the valve closing type; Performing equivalent conversion processing on the number of valve-openable actions based on the first loss weight coefficient to obtain a first equivalent number; Performing equivalent conversion processing on the number of closable valve actions based on the second loss weight coefficient to obtain a second equivalent number; The target lifetime information is determined based on the first equivalent number of times and the second equivalent number of times.

7. The method according to claim 6, characterized in that The determining the target life information based on the first equivalent number of times and the second equivalent number of times further includes: Obtaining an operating environment coefficient corresponding to the target electric valve; wherein the operating environment coefficient includes content type and ambient temperature factors; Performing environmental factor correction processing on the first equivalent number and the second equivalent number based on the operating environment coefficient to obtain a first corrected number and a second corrected number; The target life information is determined based on the first correction number and the second correction number.

8. The method according to claim 1, characterized in that The candidate power prediction model includes a valve opening action power prediction model. Before determining the target power prediction model from a plurality of pre-trained candidate power prediction models according to the target electric valve action type corresponding to the electric valve execution action, the method further includes pre-training the valve opening action power prediction model, specifically including: Acquire a valve opening action training data set, wherein the valve opening action training data set includes valve opening action training power and valve opening action sample power of the electric valve execution action corresponding to the target electric valve action type to be executed next time; Inputting the valve opening action training power into the original valve opening action power prediction model for power prediction, and obtaining the valve opening action prediction power corresponding to the next time the target electric valve executes the action corresponding to the target electric valve action type; Based on the comparison between the valve opening action prediction power and the valve opening action sample power, first comparison deviation data is obtained; Based on the first comparison deviation data, the model parameters of the valve opening action power prediction model are updated, and the valve opening action training power is returned to be input into the original valve opening action power prediction model for power prediction until the valve opening action power prediction model meets the preset first training termination condition, so as to obtain the pre-trained valve opening action power prediction model.

9. The method according to claim 1, characterized in that: The candidate power prediction model includes a valve closing action power prediction model. Before determining a target power prediction model from a plurality of pre-trained candidate power prediction models according to the target electric valve action type corresponding to the electric valve execution action, the method further includes pre-training the valve closing action power prediction model, specifically including: Acquire a valve closing action training data set, wherein the valve closing action training data set includes a valve closing action training power and a valve closing action sample power of the electric valve execution action corresponding to the target electric valve action type to be executed next time; Inputting the valve closing action training power into the original valve closing action power prediction model for power prediction, and obtaining the valve closing action prediction power corresponding to the next time the target electric valve executes the action corresponding to the target electric valve action type; Comparing the valve closing action predicted power with the valve closing action sample power to obtain second comparison deviation data; Based on the second comparison deviation data, the model parameters of the valve closing action power prediction model are updated, and the valve closing action training power is returned to be input into the original valve closing action power prediction model for power prediction until the valve closing action power prediction model meets the preset second training termination condition, so as to obtain the pre-trained valve closing action power prediction model.

10. The method according to claim 1, characterized in that The electric valve execution action includes an electric valve opening action and an electric valve closing action. The electric valve execution action is triggered in response to the target electric valve, and the valve control current and valve control voltage of the target electric valve corresponding to the electric valve execution action are collected, including: In response to the target electric valve triggering the electric valve opening action, collecting the valve opening action current and valve opening action voltage of the target electric valve; In response to the target electric valve triggering the electric valve closing action, collecting the valve closing action current and valve closing action voltage of the target electric valve; The active power calculation based on the valve control current and the valve control voltage is performed to obtain the valve active power of the target electric valve, including: Performing active power calculation based on the valve opening action current and the valve opening action voltage to obtain the valve opening action power of the target electric valve; Active power calculation is performed based on the valve closing action current and the valve closing action voltage to obtain the valve closing action power of the target electric valve.

11. An electric valve life prediction 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 model screening module, used to determine a target power prediction model from a plurality of pre-trained candidate power prediction models according to the target electric valve action type corresponding to the electric valve execution action; An operation times prediction module, used for inputting the valve active power into the corresponding target power prediction model to perform power prediction and obtain the executable times of the target electric valve; The electric valve life assessment module is used to analyze the electric valve life according to the executable times corresponding to different action types to obtain the target life 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 electric valve life prediction method 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 life prediction method according to any one of claims 1 to 10 is implemented.

Images