Tap switch operating mechanism working condition prediction method and device based on working condition prediction model, computer equipment and storage medium

Abstract

The invention relates to a tap switch operating mechanism working condition prediction method and device based on a working condition prediction model, computer equipment, a storage medium and a computer program product. The method comprises the following steps: inputting sample image information of a sample tap switch operating mechanism into a to-be-trained working condition prediction model to obtain predicted motion information of the sample tap switch operating mechanism; determining predicted working condition information of the sample tap switch operating mechanism based on the predicted motion information through a to-be-trained working condition prediction model; performing iterative training on a to-be-trained working condition prediction model according to the predicted motion information and the predicted working condition information to obtain a trained working condition prediction model; and obtaining to-be-analyzed image information of the to-be-analyzed tap switch operating mechanism, and inputting the to-be-analyzed image information into the trained working condition prediction model to obtain target working condition information of the to-be-analyzed tap switch operating mechanism. By adopting the method, the working condition prediction accuracy of the tap switch operating mechanism can be improved.

Description

Technical Field

[0001] The present application relates to the field of power grid technology, and in particular to a method, device, computer equipment, computer-readable storage medium and computer program product for predicting the operating condition of a tap changer operating mechanism based on an operating condition prediction model. Background Art

[0002] At present, in order to ensure the safe operation of the power system, it is very important to predict the working condition of the tap changer operating mechanism in the high-voltage circuit breaker.

[0003] In traditional technology, manual judgment is generally used in the process of predicting the working condition of the tap changer operating mechanism; however, this manual judgment method has subjective factors and is prone to errors, resulting in low accuracy in predicting the working condition of the tap changer operating mechanism. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for predicting the operating condition of a tap changer operating mechanism based on a working condition prediction model, which can improve the accuracy of the working condition prediction of the tap changer operating mechanism in order to solve the above technical problems.

[0005] In a first aspect, the present application provides a method for predicting the operating condition of a tap changer operating mechanism based on an operating condition prediction model, comprising:

[0006] Acquiring sample image information of a sample tap changer operating mechanism;

[0007] Inputting the sample image information into the working condition prediction model to be trained to obtain the predicted motion information of the sample tap changer operating mechanism;

[0008] Determining predicted operating condition information of the sample tap changer operating mechanism based on the predicted motion information by using the operating condition prediction model to be trained;

[0009] Acquiring actual motion information and actual operating condition information of the sample tap changer operating mechanism, and iteratively training the operating condition prediction model to be trained according to the difference between the predicted motion information and the actual motion information, and the difference between the predicted operating condition information and the actual operating condition information, to obtain a trained operating condition prediction model;

[0010] The image information to be analyzed of the tap changer operating mechanism to be analyzed is obtained, and the image information to be analyzed is input into the trained working condition prediction model to obtain the target working condition information of the tap changer operating mechanism to be analyzed.

[0011] In one embodiment, the step of inputting the sample image information into a working condition prediction model to be trained to obtain the predicted motion information of the sample tap changer operating mechanism includes:

[0012] Inputting the sample image information into the working condition prediction model to be trained to obtain the predicted displacement information, predicted speed information and predicted acceleration information of the sample tap changer operating mechanism;

[0013] The predicted displacement information, the predicted speed information and the predicted acceleration information are all used as the predicted motion information.

[0014] In one embodiment, determining the predicted operating condition information of the sample tap changer operating mechanism based on the predicted motion information includes:

[0015] Preprocessing the predicted motion information to obtain preprocessed predicted motion information;

[0016] According to the preprocessed predicted motion information, the correspondence between the motion information and the operating condition information is queried to obtain the operating condition information corresponding to the preprocessed predicted motion information as the predicted operating condition information.

[0017] In one embodiment, the iterative training of the working condition prediction model to be trained based on the difference between the predicted motion information and the actual motion information, and the difference between the predicted working condition information and the actual working condition information, to obtain a trained working condition prediction model, includes:

[0018] Obtaining a first loss value according to a difference between the predicted motion information and the actual motion information, and obtaining a second loss value according to a difference between the predicted operating condition information and the actual operating condition information;

[0019] fusing the first loss value and the second loss value to obtain a target loss value;

[0020] According to the target loss value, the operating condition prediction model to be trained is iteratively trained to obtain the trained operating condition prediction model.

[0021] In one embodiment, the step of inputting the image information to be analyzed into the trained working condition prediction model to obtain the target working condition information of the tap changer operating mechanism to be analyzed includes:

[0022] Extracting key image information from the image information to be analyzed;

[0023] Inputting the key image information into the trained working condition prediction model to obtain a plurality of predicted working condition information of the tap changer operating mechanism to be analyzed and a predicted probability of each predicted working condition information;

[0024] From each of the predicted operating condition information, the predicted operating condition information with the highest predicted probability is screened out as the target operating condition information.

[0025] In one embodiment, after obtaining the image information to be analyzed of the tap changer operating mechanism to be analyzed, inputting the image information to be analyzed into the trained working condition prediction model, and obtaining the target working condition information of the tap changer operating mechanism to be analyzed, the method further includes:

[0026] When the target operating condition information indicates that the tap changer operating mechanism to be analyzed is in an abnormal operating condition, determining a target circuit breaker corresponding to the tap changer operating mechanism to be analyzed;

[0027] Generate warning information corresponding to the target circuit breaker;

[0028] The warning information is sent to a target terminal associated with the target circuit breaker.

[0029] In a second aspect, the present application further provides a device for predicting operating conditions of a tap changer operating mechanism based on an operating condition prediction model, comprising:

[0030] An information acquisition module, used to acquire sample image information of a sample tap changer operating mechanism;

[0031] An information prediction module, used for inputting the sample image information into a working condition prediction model to be trained to obtain predicted motion information of the sample tap changer operating mechanism;

[0032] A working condition prediction module, used to determine the predicted working condition information of the sample tap changer operating mechanism based on the predicted motion information by using the working condition prediction model to be trained;

[0033] A model training module, used for obtaining actual motion information and actual working condition information of the sample tap changer operating mechanism, and iteratively training the working condition prediction model to be trained according to the difference between the predicted motion information and the actual motion information, and the difference between the predicted working condition information and the actual working condition information, to obtain a trained working condition prediction model;

[0034] The target prediction module is used to obtain the image information to be analyzed of the tap switch operating mechanism to be analyzed, input the image information to be analyzed into the trained working condition prediction model, and obtain the target working condition information of the tap switch operating mechanism to be analyzed.

[0035] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0036] Acquiring sample image information of a sample tap changer operating mechanism;

[0037] Inputting the sample image information into the working condition prediction model to be trained to obtain the predicted motion information of the sample tap changer operating mechanism;

[0038] Determining predicted operating condition information of the sample tap changer operating mechanism based on the predicted motion information by using the operating condition prediction model to be trained;

[0039] Acquiring actual motion information and actual operating condition information of the sample tap changer operating mechanism, and iteratively training the operating condition prediction model to be trained according to the difference between the predicted motion information and the actual motion information, and the difference between the predicted operating condition information and the actual operating condition information, to obtain a trained operating condition prediction model;

[0040] The image information to be analyzed of the tap changer operating mechanism to be analyzed is obtained, and the image information to be analyzed is input into the trained working condition prediction model to obtain the target working condition information of the tap changer operating mechanism to be analyzed.

[0041] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0042] Acquiring sample image information of a sample tap changer operating mechanism;

[0043] Inputting the sample image information into the working condition prediction model to be trained to obtain the predicted motion information of the sample tap changer operating mechanism;

[0044] Determining predicted operating condition information of the sample tap changer operating mechanism based on the predicted motion information by using the operating condition prediction model to be trained;

[0045] Acquiring actual motion information and actual operating condition information of the sample tap changer operating mechanism, and iteratively training the operating condition prediction model to be trained according to the difference between the predicted motion information and the actual motion information, and the difference between the predicted operating condition information and the actual operating condition information, to obtain a trained operating condition prediction model;

[0046] The image information to be analyzed of the tap changer operating mechanism to be analyzed is obtained, and the image information to be analyzed is input into the trained working condition prediction model to obtain the target working condition information of the tap changer operating mechanism to be analyzed.

[0047] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0048] Acquiring sample image information of a sample tap changer operating mechanism;

[0049] Inputting the sample image information into the working condition prediction model to be trained to obtain the predicted motion information of the sample tap changer operating mechanism;

[0050] Determining predicted operating condition information of the sample tap changer operating mechanism based on the predicted motion information by using the operating condition prediction model to be trained;

[0051] Acquiring actual motion information and actual operating condition information of the sample tap changer operating mechanism, and iteratively training the operating condition prediction model to be trained according to the difference between the predicted motion information and the actual motion information, and the difference between the predicted operating condition information and the actual operating condition information, to obtain a trained operating condition prediction model;

[0052] The image information to be analyzed of the tap changer operating mechanism to be analyzed is obtained, and the image information to be analyzed is input into the trained working condition prediction model to obtain the target working condition information of the tap changer operating mechanism to be analyzed.

[0053] The above-mentioned method, device, computer equipment, storage medium and computer program product for predicting the working condition of the tap changer operating mechanism based on the working condition prediction model first obtains sample image information of the sample tap changer operating mechanism, and then inputs the sample image information into the working condition prediction model to be trained to obtain predicted motion information of the sample tap changer operating mechanism. Then, the predicted working condition information of the sample tap changer operating mechanism is determined based on the predicted motion information through the working condition prediction model to be trained. Then, the actual motion information and actual working condition information of the sample tap changer operating mechanism are obtained. According to the difference between the predicted motion information and the actual motion information, and the difference between the predicted working condition information and the actual working condition information, the working condition prediction model to be trained is iteratively trained to obtain a trained working condition prediction model. Finally, the image information to be analyzed of the tap changer operating mechanism to be analyzed is obtained, and the image information to be analyzed is input into the trained working condition prediction model to obtain the target working condition information of the tap changer operating mechanism to be analyzed. In this way, in the process of predicting the working condition of the tap changer operating mechanism, by pre-training the working condition prediction model, it is convenient to predict the target working condition information of the tap changer operating mechanism to be analyzed after the image information to be analyzed of the tap changer operating mechanism to be analyzed in actual application; secondly, the working condition prediction model receives new data in each round of iteration, and improves and optimizes the internal model, so that it can be predicted more effectively, which is beneficial to improve the prediction accuracy of the working condition prediction model, thereby improving the working condition prediction accuracy of the tap changer operating mechanism; moreover, the entire process does not require human intervention, avoiding the subjective factors in the manual judgment method, which is prone to errors and leads to the defect of low working condition prediction accuracy of the tap changer operating mechanism, and further improves the working condition prediction accuracy of the tap changer operating mechanism. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0055] Figure 1 1 is a flow chart of a method for predicting the operating condition of a tap changer operating mechanism based on an operating condition prediction model in one embodiment;

[0056] Figure 2 is a schematic flow chart of a method for predicting the operating condition of a tap changer operating mechanism based on an operating condition prediction model in another embodiment;

[0057] Figure 3 A schematic structural diagram of the opening process of the tap changer operating mechanism in one embodiment;

[0058] Figure 4 A schematic diagram of the constraints and force relationships between the components of the tap changer operating mechanism in one embodiment;

[0059] Figure 5 A schematic diagram of a collision between an axle pin and a joint in one embodiment;

[0060] Figure 6 is a schematic diagram of a cross section of an oil damper in one embodiment;

[0061] Figure 7 is a schematic diagram of an oil circuit of an oil damper in one embodiment;

[0062] Figure 8 is a schematic diagram of an oil damper model in one embodiment;

[0063] Fig. 9 is a schematic diagram of a test platform in one embodiment;

[0064] Fig.10 A schematic diagram of a high-speed camera shooting position in one embodiment;

[0065] Fig.11 A schematic diagram of a displacement curve comparison and an error curve in one embodiment;

[0066] Fig.12 A schematic diagram of a speed curve comparison and an error curve in one embodiment;

[0067] Fig.13 is a schematic diagram of acceleration curve comparison in one embodiment;

[0068] Fig.14 A schematic diagram of a comparison of fault condition curves in an embodiment;

[0069] Fig.15 is a structural block diagram of a tap changer operating mechanism operating condition prediction device based on an operating condition prediction model in one embodiment;

[0070] Fig.16 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0071] 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.

[0072] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0073] In an exemplary embodiment, Figure 1 As shown, a method for predicting the operating condition of a tap changer operating mechanism based on an operating condition prediction model is provided. This embodiment uses the method applied to a server as an example for illustration; it can be understood that the method can also be applied to a terminal, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. Among them, the terminal can be but is not limited to various personal computers, laptops, smart phones and tablet computers; the server can be implemented with an independent server or a server cluster composed of multiple servers. In this embodiment, the method includes the following steps:

[0074] Step S101, obtaining sample image information of a sample tap changer operating mechanism.

[0075] The sample tap changer operating mechanism refers to a tap changer operating mechanism used to train the working condition prediction model to be trained.

[0076] The sample image information refers to the image information of the sample tap changer operating mechanism.

[0077] Exemplarily, in response to a model training instruction for the operating condition prediction model to be trained, the server obtains, through a high-speed camera, photographs of the sample tap switch operating mechanism during the opening process as sample image information of the sample tap switch operating mechanism.

[0078] Step S102: inputting sample image information into the working condition prediction model to be trained to obtain predicted motion information of the sample tap changer operating mechanism.

[0079] Among them, the operating condition prediction model refers to a network model that can predict the operating condition information corresponding to the tap changer operating mechanism, such as a convolutional neural network model.

[0080] The predicted motion information refers to the predicted value corresponding to the motion information of the sample tap changer operating mechanism.

[0081] Exemplarily, the server preprocesses the sample image information to obtain preprocessed sample image information; then, the server inputs the preprocessed sample image information into the working condition prediction model to be trained, and obtains the predicted value corresponding to the motion information of the sample tap switch operating mechanism through the working condition prediction model to be trained, as the predicted motion information of the sample tap switch operating mechanism.

[0082] Step S103 : determining predicted operating condition information of the sample tap changer operating mechanism based on the predicted motion information by using the operating condition prediction model to be trained.

[0083] The predicted operating condition information refers to the predicted value corresponding to the operating condition information of the sample tap changer operating mechanism.

[0084] Exemplarily, the server preprocesses the predicted motion information to obtain preprocessed predicted motion information; then, the server inputs the preprocessed predicted motion information into the operating condition prediction model to be trained to obtain the predicted value corresponding to the operating condition information of the sample tap changer operating mechanism as the predicted operating condition information of the sample tap changer operating mechanism.

[0085] Step S104, obtaining actual motion information and actual operating condition information of the sample tap changer operating mechanism, and iteratively training the operating condition prediction model to be trained according to the difference between the predicted motion information and the actual motion information, and the difference between the predicted operating condition information and the actual operating condition information, to obtain a trained operating condition prediction model.

[0086] The actual motion information refers to the actual value corresponding to the motion information of the sample tap changer operating mechanism.

[0087] The actual operating condition information refers to the actual value corresponding to the operating condition information of the sample tap changer operating mechanism.

[0088] Exemplarily, the server obtains the actual value corresponding to the motion information of the sample tap switch operating mechanism as the actual motion information of the sample tap switch operating mechanism, and obtains the actual value corresponding to the working condition information of the sample tap switch operating mechanism as the actual working condition information of the sample tap switch operating mechanism; then, the server iteratively trains the working condition prediction model to be trained according to the difference between the predicted motion information and the actual motion information, and the difference between the predicted working condition information and the actual working condition information, to obtain a trained working condition prediction model.

[0089] Step S105 , obtaining the image information to be analyzed of the tap changer operating mechanism to be analyzed, inputting the image information to be analyzed into the trained working condition prediction model, and obtaining the target working condition information of the tap changer operating mechanism to be analyzed.

[0090] The tap changer operating mechanism to be analyzed refers to the tap changer operating mechanism for which operating condition prediction is required.

[0091] The image information to be analyzed refers to the image information of the tap changer operating mechanism to be analyzed.

[0092] The target operating condition information refers to the comprehensive operating condition information corresponding to the tap changer operating mechanism to be analyzed.

[0093] Exemplarily, in response to an operating condition prediction instruction for a tap changer operating mechanism to be analyzed, the server obtains image information to be analyzed of the tap changer operating mechanism to be analyzed from a database; then, the server inputs the image information to be analyzed into a trained operating condition prediction model, and obtains a predicted value corresponding to the operating condition information of the tap changer operating mechanism to be analyzed through the trained operating condition prediction model as the target operating condition information of the tap changer operating mechanism to be analyzed.

[0094] In the above-mentioned method for predicting the working condition of the tap changer operating mechanism based on the working condition prediction model, the sample image information of the sample tap changer operating mechanism is first obtained, and then the sample image information is input into the working condition prediction model to be trained to obtain the predicted motion information of the sample tap changer operating mechanism. Then, the predicted working condition information of the sample tap changer operating mechanism is determined based on the predicted motion information through the working condition prediction model to be trained. Then, the actual motion information and actual working condition information of the sample tap changer operating mechanism are obtained. According to the difference between the predicted motion information and the actual motion information, and the difference between the predicted working condition information and the actual working condition information, the working condition prediction model to be trained is iteratively trained to obtain a trained working condition prediction model. Finally, the image information to be analyzed of the tap changer operating mechanism to be analyzed is obtained, and the image information to be analyzed is input into the trained working condition prediction model to obtain the target working condition information of the tap changer operating mechanism to be analyzed. In this way, in the process of predicting the working condition of the tap changer operating mechanism, by pre-training the working condition prediction model, it is convenient to predict the target working condition information of the tap changer operating mechanism to be analyzed after the image information to be analyzed of the tap changer operating mechanism to be analyzed in actual application; secondly, the working condition prediction model receives new data in each round of iteration, and improves and optimizes the internal model, so that it can be predicted more effectively, which is beneficial to improve the prediction accuracy of the working condition prediction model, thereby improving the working condition prediction accuracy of the tap changer operating mechanism; moreover, the entire process does not require human intervention, avoiding the subjective factors in the manual judgment method, which is prone to errors and leads to the defect of low working condition prediction accuracy of the tap changer operating mechanism, and further improves the working condition prediction accuracy of the tap changer operating mechanism.

[0095] In an exemplary embodiment, the above step S102, inputting the sample image information into the working condition prediction model to be trained to obtain the predicted motion information of the sample tap switch operating mechanism, specifically includes the following contents: inputting the sample image information into the working condition prediction model to be trained to obtain the predicted displacement information, predicted speed information and predicted acceleration information of the sample tap switch operating mechanism; using the predicted displacement information, predicted speed information and predicted acceleration information as predicted motion information.

[0096] The predicted displacement information refers to the predicted value corresponding to the displacement information of the sample tap changer operating mechanism.

[0097] The predicted speed information refers to the predicted value corresponding to the speed information of the sample tap changer operating mechanism.

[0098] The predicted acceleration information refers to the predicted value corresponding to the acceleration information of the sample tap changer operating mechanism.

[0099] Exemplarily, the server inputs the sample image information into the working condition prediction model to be trained, and obtains the displacement curve, velocity curve and acceleration curve corresponding to the sample tap switch operating mechanism through the working condition prediction model to be trained; then, the server extracts the predicted values ​​corresponding to the displacement information, velocity information and acceleration information of the sample tap switch operating mechanism from the displacement curve, velocity curve and acceleration curve corresponding to the sample tap switch operating mechanism, respectively, as the predicted displacement information, predicted velocity information and predicted acceleration information of the sample tap switch operating mechanism; then, the server combines the predicted displacement information, predicted velocity information and predicted acceleration information to obtain the predicted motion information of the sample tap switch operating mechanism.

[0100] In this embodiment, the predicted displacement information, predicted velocity information and predicted acceleration information of the sample tap changer operating mechanism are output through the working condition prediction model, and they are integrated into predicted motion information to describe the state of the operating mechanism from multiple key kinematic dimensions, thereby avoiding the defect of low accuracy in determining the predicted motion information due to evaluation based only on single-dimensional information.

[0101] In an exemplary embodiment, the above step S103 determines the predicted operating condition information of the sample tap changer operating mechanism based on the predicted motion information, and specifically includes the following contents: preprocessing the predicted motion information to obtain the preprocessed predicted motion information; according to the preprocessed predicted motion information, querying the correspondence between the motion information and the operating condition information to obtain the operating condition information corresponding to the preprocessed predicted motion information as the predicted operating condition information.

[0102] The pre-processed predicted motion information refers to the predicted motion information after pre-processing.

[0103] The corresponding relationship between the motion information and the working condition information is used to indicate the association information between the motion information and the working condition information. For example, motion information A corresponds to working condition information a, motion information B corresponds to working condition information b, and motion information C corresponds to working condition information c.

[0104] Exemplarily, the server uses data processing technology to clean, fuse, and convert the predicted motion information to obtain pre-processed predicted motion information; then, the server queries the correspondence between the motion information and the operating condition information based on the pre-processed predicted motion information, obtains the operating condition information corresponding to the pre-processed predicted motion information, and uses the operating condition information as the predicted operating condition information.

[0105] In this embodiment, the predicted motion information is preprocessed to remove noise, outliers and other interference factors that may exist in the original data; moreover, by pre-establishing the correspondence between the motion information and the operating condition information, the predicted operating condition information can be quickly obtained by querying according to the established correspondence, which is conducive to improving the efficiency of determining the predicted operating condition information.

[0106] In an exemplary embodiment, the above-mentioned step S104 iteratively trains the working condition prediction model to be trained according to the difference between the predicted motion information and the actual motion information, and the difference between the predicted working condition information and the actual working condition information to obtain a trained working condition prediction model, which specifically includes the following contents: obtaining a first loss value according to the difference between the predicted motion information and the actual motion information, and obtaining a second loss value according to the difference between the predicted working condition information and the actual working condition information; fusing the first loss value and the second loss value to obtain a target loss value; and iteratively training the working condition prediction model to be trained according to the target loss value to obtain a trained working condition prediction model.

[0107] The first loss value refers to a loss value obtained according to the difference between the predicted motion information and the actual motion information.

[0108] The second loss value refers to a loss value obtained according to the difference between the predicted operating condition information and the actual operating condition information.

[0109] The target loss value refers to the loss value obtained by fusing the first loss value and the second loss value.

[0110] Exemplarily, the server obtains a first loss value based on the difference between the predicted motion information and the actual motion information, and obtains a second loss value based on the difference between the predicted operating condition information and the actual operating condition information; then, the server obtains a first weight corresponding to the first loss value, and a second weight corresponding to the second loss value; then, the server fuses the first loss value and the second loss value according to the first weight and the second weight to obtain a target loss value; then, the server adjusts the model parameters of the operating condition prediction model to be trained according to the target loss value; then, the server re-trains the operating condition prediction model after the model parameters are adjusted until the target loss value obtained by the trained operating condition prediction model is less than the loss value threshold, then stops training, and uses the trained operating condition prediction model as the trained operating condition prediction model.

[0111] In this embodiment, the operating condition prediction model is trained by utilizing the target loss value obtained by fusing the first loss value and the second loss value, thereby making the adjustment direction of the model parameters of the operating condition prediction model clearer, and thus being able to optimize in a direction closer to the actual situation, which is beneficial to improving the model training effect of the operating condition prediction model.

[0112] In an exemplary embodiment, the above step S105, inputting the image information to be analyzed into a trained operating condition prediction model to obtain target operating condition information of the tap changer operating mechanism to be analyzed, specifically includes the following contents: extracting key image information from the image information to be analyzed; inputting the key image information into the trained operating condition prediction model to obtain multiple predicted operating condition information of the tap changer operating mechanism to be analyzed, and the predicted probability of each predicted operating condition information; from each predicted operating condition information, screening out the predicted operating condition information with the largest predicted probability as the target operating condition information.

[0113] The key image information is used to represent the sub-image information whose corresponding importance is greater than the preset importance among the multiple sub-image information of the image information to be analyzed.

[0114] The predicted operating condition information refers to the predicted value corresponding to the operating condition information of the tap changer operating mechanism to be analyzed.

[0115] The prediction probability refers to the possibility that the operating condition prediction model determines that the predicted operating condition information is correct.

[0116] Exemplarily, the server segments the image information to be analyzed to obtain multiple sub-image information corresponding to the image information to be analyzed; then, the server determines the importance corresponding to each sub-image information, and filters out the sub-image information whose corresponding importance is greater than the preset importance from each sub-image information as the key image information in the image information to be analyzed; then, the server inputs the key image information into the trained operating condition prediction model, and obtains multiple predicted operating condition information of the tap changer operating mechanism to be analyzed and the predicted probability of each predicted operating condition information through the trained operating condition prediction model; then, the server filters out the predicted operating condition information with the largest predicted probability from each predicted operating condition information, and uses the predicted operating condition information as the target operating condition information.

[0117] In this embodiment, the key image information obtained after screening and refinement is input into the trained operating condition prediction model, so that the model can perform accurate pattern matching and analysis based on these representative features, and then accurately obtain the target operating condition information of the tap changer operating mechanism to be analyzed, which is beneficial to improving the accuracy of determining the target operating condition information.

[0118] In an exemplary embodiment, the above step S105, after acquiring the image information to be analyzed of the tap changer operating mechanism to be analyzed, inputting the image information to be analyzed into the trained operating condition prediction model, and obtaining the target operating condition information of the tap changer operating mechanism to be analyzed, specifically includes the following contents: when the target operating condition information indicates that the tap changer operating mechanism to be analyzed is in an abnormal operating condition, determining the target circuit breaker corresponding to the tap changer operating mechanism to be analyzed; generating early warning information corresponding to the target circuit breaker; and sending the early warning information to a target terminal associated with the target circuit breaker.

[0119] Among them, the abnormal operating condition is also called a fault condition.

[0120] The target circuit breaker is used to represent the high-voltage circuit breaker corresponding to the tap changer operating mechanism to be analyzed. It should be noted that the high-voltage circuit breaker is mainly composed of four parts: a breaking element, an insulating support, a tap changer operating mechanism and a base.

[0121] The warning information is used to indicate the alarm information corresponding to the target circuit breaker.

[0122] The target terminal refers to the terminal associated with the target circuit breaker.

[0123] Exemplarily, the server judges the target operating condition information; when the target operating condition information indicates that the tap changer operating mechanism to be analyzed is in an abnormal operating condition, the server determines the high-voltage circuit breaker corresponding to the tap changer operating mechanism to be analyzed as the target circuit breaker; then, the server generates early warning information corresponding to the target circuit breaker, and determines the target terminal associated with the target circuit breaker; then, the server sends the early warning information to the target terminal.

[0124] In this embodiment, the early warning information of the target circuit breaker corresponding to the tap changer operating mechanism to be analyzed is generated and sent to the associated target terminal, thereby ensuring that the early warning information can be conveyed to the relevant responsible personnel in a timely manner, and then the corresponding inspection, maintenance or emergency treatment measures can be quickly taken to avoid further expansion of the impact scope due to the failure not being discovered in time, which is conducive to ensuring the safe and stable operation of the equipment and the entire system.

[0125] In an exemplary embodiment, Figure 2 As shown, another method for predicting the operating condition of a tap changer operating mechanism based on an operating condition prediction model is provided. The method is applied to a server as an example for explanation, and includes the following steps:

[0126] Step S201, obtaining sample image information of a sample tap changer operating mechanism.

[0127] Step S202: input the sample image information into the working condition prediction model to be trained to obtain the predicted displacement information, predicted speed information and predicted acceleration information of the sample tap changer operating mechanism.

[0128] In step S203, the predicted displacement information, the predicted velocity information and the predicted acceleration information are all used as predicted motion information.

[0129] Step S204, preprocessing the predicted motion information through the working condition prediction model to be trained to obtain the preprocessed predicted motion information; based on the preprocessed predicted motion information, querying the correspondence between the motion information and the working condition information, obtaining the working condition information corresponding to the preprocessed predicted motion information as the predicted working condition information.

[0130] Step S205, obtaining actual movement information and actual working condition information of the sample tap changer operating mechanism.

[0131] Step S206, obtaining a first loss value according to the difference between the predicted motion information and the actual motion information, and obtaining a second loss value according to the difference between the predicted operating condition information and the actual operating condition information.

[0132] Step S207: fusing the first loss value and the second loss value to obtain a target loss value.

[0133] Step S208, iteratively training the operating condition prediction model to be trained according to the target loss value to obtain a trained operating condition prediction model.

[0134] Step S209, obtaining the image information to be analyzed of the tap changer operating mechanism to be analyzed.

[0135] Step S210, extract key image information from the image information to be analyzed; input the key image information into the trained working condition prediction model to obtain multiple predicted working condition information of the tap changer operating mechanism to be analyzed, and the predicted probability of each predicted working condition information.

[0136] Step S211, from each predicted operating condition information, the predicted operating condition information with the highest prediction probability is selected as the target operating condition information.

[0137] In the above-mentioned method for predicting the working condition of the tap switch operating mechanism based on the working condition prediction model, in the process of predicting the working condition of the tap switch operating mechanism, by pre-training the working condition prediction model, it is convenient in practical applications to predict the target working condition information of the tap switch operating mechanism to be analyzed after the image information to be analyzed of the tap switch operating mechanism to be analyzed; secondly, the working condition prediction model receives new data in each round of iteration, and improves and optimizes the internal model, so that it is convenient to predict more effectively, which is conducive to improving the prediction accuracy of the working condition prediction model, thereby improving the working condition prediction accuracy of the tap switch operating mechanism; moreover, the whole process does not require human intervention, avoiding the defect of low working condition prediction accuracy of the tap switch operating mechanism due to subjective factors and prone to errors in the method of manual judgment, thereby further improving the working condition prediction accuracy of the tap switch operating mechanism.

[0138] In an exemplary embodiment, in order to more clearly illustrate the tap changer operating mechanism operating condition prediction method based on the operating condition prediction model provided in the embodiment of the present application, the tap changer operating mechanism operating condition prediction method based on the operating condition prediction model is specifically described below with a specific embodiment. In one embodiment, the present application also provides a tap switch operating mechanism collision model optimization. In the process of predicting the working condition of the tap switch operating mechanism, the sample image information of the sample tap switch operating mechanism is first obtained, and then the sample image information is input into the working condition prediction model to be trained to obtain the predicted motion information of the sample tap switch operating mechanism. Then, the predicted working condition information of the sample tap switch operating mechanism is determined based on the predicted motion information through the working condition prediction model to be trained. Then, the actual motion information and actual working condition information of the sample tap switch operating mechanism are obtained. According to the difference between the predicted motion information and the actual motion information, and the difference between the predicted working condition information and the actual working condition information, the working condition prediction model to be trained is iteratively trained to obtain a trained working condition prediction model. Finally, the image information to be analyzed of the tap switch operating mechanism to be analyzed is obtained, and the image information to be analyzed is input into the trained working condition prediction model to obtain the target working condition information of the tap switch operating mechanism to be analyzed. Specifically, it includes the following contents:

[0139] This embodiment provides a method for optimizing a collision model of a tap changer operating mechanism, including:

[0140] S1, establish a multi-body dynamics model of the tap changer operating mechanism to simulate the movement and collision phenomena during the opening process.

[0141] It should be noted that the opening process of the tap changer operating mechanism is simpler than the closing process and the moving parts are mainly concentrated in one plane, which makes it easy for a high-speed camera to capture its opening process. Therefore, the simulation model of this scheme only simulates the opening process of the tap changer operating mechanism. The schematic diagram of the operating mechanism opening process is shown in the figure. Figure 3 shown.

[0142] Among them, 1- opening spring; 2- opening disc; 3- driving connecting rod; 4- driving connecting rod joint; 5- shaft pin 21; 6- load; 7- output crank arm 8- shaft pin 2; 9- piston rod joint; 10- oil damper piston rod; 11- oil damper end cover 12- operating mechanism base; 13- oil damper base; 14- output shaft; 15- operating mechanism housing.

[0143] During the opening process of the tap switch operating mechanism, the compressed opening spring releases energy to push the opening disc in contact with its surface downward. The opening disc is fixed to the driving connecting rod by fastening bolts, so that the downward movement of the opening disc will drive the driving connecting rod to move together. The driving connecting rod and the driving connecting rod joint are fixed by welding, and the two move in an integrated manner, so the driving connecting rod will drive the driving connecting rod joint to move downward as well. The driving connecting rod joint is connected to the load through the shaft pin 21, and the load is driven to move downward through the shaft pin 21. The two ends of the output crank arm are respectively connected to the shaft pin 21 and the shaft pin 2 in a rolling manner, and the center is fixedly connected to the output shaft. Therefore, the downward movement of the shaft pin 21 will drive the output crank arm to rotate clockwise around the output shaft. The clockwise rotation of the output crank arm will cause the shaft pin 2 to move upward and hit the oil damper piston rod joint, and drive the oil damper piston rod to move upward. The upward movement of the oil damper piston rod will be subject to the damping force brought by the oil damper, converting its own kinetic energy into the internal energy of the oil damper, thereby completing the entire opening movement process.

[0144] The main motion structure of the tap changer operating mechanism during the opening process is a multi-link structure. This embodiment uses multi-body dynamics simulation software ADAMS (Automatic Dynamic Analysis of Mechanical Systems) to simulate its opening process.

[0145] Furthermore, the opening model structure of the operating mechanism is mathematically modeled according to the Lagrangian method in multi-body dynamics, and the corresponding Lagrangian equation is established.

[0146] The multi-body dynamics model of the tap changer operating mechanism includes:

[0147] According to the Lagrangian method in multi-body dynamics, the opening model structure of the operating mechanism is mathematically modeled, and the corresponding Lagrangian equation is established, which is expressed as:

[0148]

[0149] Where M is the system mass matrix; q(x, y, z, ψ, θ, φ) is the system generalized coordinate; Q is the generalized external force on the system; T is the system kinetic energy; Φ is the system constraint equation;

[0150] By adding motion constraints between rigid body parts, the corresponding constraint equations are generated:

[0151] Φ(q,t)=0,Equation (2)

[0152] The system kinetic energy Substituting into the above formula (1), we can get the system dynamics equation:

[0153]

[0154] Furthermore, according to the opening movement process of the tap changer operating mechanism, and considering the movement relationship between the shaft pin 2 and the piston rod joint of the oil damper, the movement constraint between the two is weakened to a collision contact relationship, and the movement constraint relationship and force relationship between the various components of the tap changer operating mechanism during the opening movement are established as follows: Figure 4 In addition, the material parameters of each component are shown in Table 1. The housing and base of the mechanism are made of aluminum, the large components of the mechanism are made of 45 steel, and the remaining small components are made of Q235 steel.

[0155] Table 1 Component material parameters

[0156] Material Type <![CDATA[Density / kg·mm -3 > Young's modulus / Gpa Poisson's ratio Aluminum <![CDATA[2.74×10 -6 ]]> 71.7 0.330 45 steel <![CDATA[7.85×10 -6 ]]> 210.0 0.322 Q235 Steel <![CDATA[7.85×10 -6 ]]> 193.0 0.196

[0157] S2, the external force of the tap changer operating mechanism is modeled. The external force includes the elastic force of the opening spring, the damping force of the oil damper, and the contact force between the shaft pin 2 and the piston rod joint of the oil damper.

[0158] Formula (3) shows that in order to reasonably and accurately describe the dynamic equation of the system, in addition to the constraints within the system, it is also necessary to analyze the external forces of the system. Figure 4 It can be seen that the external forces acting on the system mainly come from the elastic force of the opening spring, the damping force of the oil damper, and the contact force between the shaft pin 2 and the piston rod joint of the oil damper.

[0159] Furthermore, the external force modeling of the tap changer operating mechanism includes:

[0160] The opening spring model, contact collision model and oil damper model are established respectively.

[0161] Furthermore, the trip spring model includes,

[0162] Elastic force F of the opening spring T The expression is:

[0163] F T =F0-K T x, Formula (4)

[0164]

[0165] F0=K T (Ll), Formula (6)

[0166] Among them, F0 is the initial elastic force of the opening spring; K T is the spring stiffness coefficient of the opening brake; x is the compression of the opening brake spring. The relevant parameter values ​​are shown in Table 2 below.

[0167] Table 2 Parameters of opening spring

[0168] parameter unit Numeric Spring length L mm 535 Spring wire diameter d mm 25 Spring diameter D mm 135 Effective number of turns H - 10 Length of opening spring when preloaded l mm 347 Elastic modulus G <![CDATA[N·mm -3 ]]> 79200

[0169] Furthermore, the contact collision model includes,

[0170] Based on the Hertz theory, a continuous contact force model is established for the contact force in the collision process, which is expressed as:

[0171]

[0172] Among them, K is the contact stiffness coefficient; C is the contact damping coefficient; δ is the contact deformation; is the relative collision velocity; and n is the energy index.

[0173] From formula (7), we can see that the continuous contact force model characterizes the contact force in the collision process as an elastic part and a damping part. The elastic part indicates that the kinetic energy is converted into elastic potential energy in the collision process, and the damping part indicates the energy dissipation in the collision process.

[0174] The simplified diagram of the collision between the axle pin 2 of the operating mechanism and the piston rod joint of the oil damper is shown in Figure 5 As shown, the process is divided into three states: before collision, during collision, and after collision. Before collision, the oil damper piston rod joint is approximately in a static state, and the shaft pin 2 collides with the oil damper piston rod joint at a certain speed; during collision, the shaft pin 2 invades the oil damper piston rod joint, and contact deformation occurs between the two, and the deformation amount is that part of the kinetic energy of the shaft pin 2 is converted into elastic potential energy, and part is converted into the kinetic energy of the piston rod joint; after collision, the deformation of the two is restored, and the contact force between the oil damper piston rod joint and the shaft pin 2 is negligible, and the two are in a separated state.

[0175] The contact stiffness coefficient in the continuous contact force model is independent of the contact deformation. The contact stiffness coefficient is only related to the geometric properties and material properties of the contact objects:

[0176]

[0177] in, μ 1, μ 2 is the Poisson's ratio of the joint between the shaft pin 2 and the oil damper piston rod; E1, E2 are the elastic moduli of the joint between the shaft pin 2 and the oil damper piston rod; R1, R2 are the contact radii of the joint between the shaft pin 2 and the oil damper piston rod.

[0178] The damping part in the continuous contact force model is a representation of energy dissipation during the collision process. Its contact damping coefficient is closely related to the contact deformation. It can be determined that the contact damping coefficient C is a function related to the contact deformation δ, that is, C = αδa, α is the damping factor, and a is the contact parameter. Based on the above functional expression, this embodiment analyzes the collision phenomenon between the shaft pin 2 and the oil damper piston rod joint during the opening process from the perspective of energy change, and derives the expression of the damping factor α.

[0179] In the process of collision, compression and recovery of the above two objects, according to the continuous contact force model, it can be considered that the kinetic energy loss in the collision process is caused by the energy dissipation of the damping part, that is:

[0180]

[0181] According to the law of conservation of energy, the kinetic energy loss equation of two objects before and after collision is:

[0182] ΔE=T1-T2, Formula (12)

[0183]

[0184] m1v 11 +m2v 12 =m1v 21 +m2v 22 , Formula (15)

[0185] Wherein, m1 and m2 are the masses of the joint between the shaft pin 2 and the piston rod of the oil damper; v 11 、v 12 are the velocities of the axle pin 2 before and after the collision; v 21 、v 22 are the velocities of the oil damper piston rod joint before and after the collision; T1 and T2 are the kinetic energies before and after the collision.

[0186] Combining equations (12) to (15), we can obtain:

[0187]

[0188] in,

[0189] in, is the relative velocity before collision.

[0190] When the contact deformation between the two objects is δ, let the speed of the shaft pin 2 and the speed of the oil damper piston rod joint be v respectively. δ1 , v δ2 , then we can get:

[0191]

[0192] Among them, E δ represents the strain energy from when the deformation is δ to the end of the compression process; E p Represents the strain energy of the compression process.

[0193] When the collision and compression process ends, the velocities of the two colliding objects become consistent:

[0194]

[0195] (m1+m2)v t =m1v 11 +m2v 12 , Formula (19)

[0196] Among them, v t Represents the common velocity of the two colliding objects after compression ends.

[0197] Combining equations (18) and (19), we can obtain:

[0198]

[0199] The strain energy during compression can also be obtained by integrating the elastic part of the continuum contact force model:

[0200]

[0201] Among them, δmax is the maximum contact deformation.

[0202] Combining equation (20) and equation (21), we can get:

[0203]

[0204] According to the derivation process of formula (20), we can get:

[0205]

[0206] Combining equations (17), (20) and (23), we can obtain:

[0207]

[0208] Since the paths of the compression process and the recovery process of the object are consistent, it is assumed that the energy dissipation of the collision compression process and the recovery process of the object is basically the same, that is:

[0209]

[0210] The simultaneous equations (9), (16), and (25) can be solved as follows:

[0211]

[0212] Among them, the unit of α is N·s / m2.5. According to the continuous contact force model equation, the dimensions on both sides are consistent, and it is deduced that a=1.5.

[0213] Further, refer to Figure 6 , wherein, 16-damper base; 17-external cavity; 18-piston rod: the buffer cylinder is divided into two parts 19 and 20 by the piston rod; 21-lower part of the inner cavity: 22-upper part of the inner cavity; 23-damper end cover: 24-throttle hole.

[0214] The tap switch operating mechanism uses an oil damper to buffer the opening and closing movement process to reduce the collision impact during the opening and closing movement. The oil damper is a porous hydraulic system, and the state of the hydraulic oil in it cannot be described by multi-body dynamics. Therefore, this embodiment models and simulates the opening movement process of the oil damper based on fluid mechanics.

[0215] Oil damper models include,

[0216] Model and simulate the opening movement process of the oil damper based on fluid mechanics;

[0217] According to Newton's laws of motion and related theories of fluid mechanics, a model of the opening motion process of the oil damper of the operating mechanism is established, and the dynamic equation of the piston rod of the oil damper is expressed as:

[0218]

[0219] Among them, Mg is the mass of the oil damper piston rod; v is the movement speed of the piston rod; P1 is the upper pressure of the inner cavity; S1 is the effective area on the upper side of the inner cavity, P2 is the lower pressure of the inner cavity; S2 is the effective area on the lower side of the inner cavity; F3 is the damping force between the hydraulic oil and the tie rod base.

[0220] The liquid flow equation at the throttle hole between the inner cavity and the outer cavity is expressed as:

[0221]

[0222] Among them, vol is the flow rate flowing through the throttle hole; Cq is the flow coefficient; A is the throttle hole area; ρ is the liquid density; p1 is the pressure at the inflow throttle hole; p2 is the pressure at the outflow throttle hole.

[0223] During the opening movement of the operating mechanism, the hydraulic oil in the upper part of the inner cavity flows to the outer cavity through the throttle hole on the buffer cylinder, and the hydraulic oil in the outer cavity flows to the lower part of the inner cavity through the throttle hole on the buffer cylinder. When the piston rod is forced to move from the base side to the end cover side, the throttle hole between the lower part of the inner cavity and the outer cavity gradually opens, and the number of holes increases with the movement of the piston rod, and the area of ​​the throttle hole increases; while the throttle hole between the upper part of the inner cavity and the outer cavity gradually closes, and the number of holes decreases with the movement of the piston rod, and the area of ​​the throttle hole decreases, thereby changing the pressure difference between the upper and lower parts of the inner cavity, and achieving the purpose of adjusting the damping force on the piston rod. Its simplified schematic diagram is shown as follows: Figure 7 shown.

[0224] Where r is the radius of the throttle hole, X is the distance between the bottom of the piston rod and the bottom of the throttle hole; S is the area of ​​the piston rod that does not cover the throttle hole,

[0225]

[0226] During the opening process, the per unit value of the throttle hole area between the lower part of the inner cavity and the outer cavity of the oil damper changes with the piston rod displacement x:

[0227]

[0228] Among them, Ai is the per unit value of the area of ​​the i-th throttle hole; hi is the vertical distance between the bottom of the i-th throttle hole and the damper base; ri is the radius of the i-th throttle hole. The relevant parameters are shown in Table 3.

[0229] Table 3 Related parameters of the throttle hole between the lower part of the inner cavity and the outer cavity

[0230] i <![CDATA[h i / mm]]> <![CDATA[r i / mm]]> 1 7.0 4.0 2 15.5 2.0 3 36.0 7.5 4 38.5 5.0 5 42.0 1.5 6 58.0 4.5 7 58.0 4.5

[0231] It should be noted that during the opening process, the per unit value of the area of ​​each throttle hole between the upper part of the inner cavity and the outer cavity of the oil damper changes with the displacement of the piston rod:

[0232]

[0233] Among them, Aj is the per unit value of the jth throttle hole area; hj is the vertical distance between the bottom of the jth throttle hole and the damper base; rj is the radius of the jth throttle hole. The relevant parameters are shown in Table 4.

[0234] Table 4 Related parameters of the throttle hole between the upper part of the inner cavity and the outer cavity

[0235] j <![CDATA[h j / mm]]> <![CDATA[r j / mm <!-- 15 -->]]> 1 16.5 7.5 2 19.0 5.0 3 22.5 1.5 4 38.5 4.5 5 38.5 4.5 6 58.0 2.0 7 69.5 1.0

[0236] In Amesim (Advanced Modeling Environment for Simulation of engineering systems), a simulation model is established. Figure 8 shown.

[0237] In summary, by analyzing the opening movement process of the tap changer operating mechanism, understanding the movement relationship between its components, using software to establish a simplified opening model of the high-voltage circuit breaker tap changer operating mechanism, and importing the simplified model into the ADAMS simulation software. Based on the movement relationship described above, the constraint relationship between the various components in the opening movement process of the tap changer operating mechanism is added in the ADAMS simulation software, the relevant parameters of its force model are derived and calculated, the material parameters and size parameters are set, and the operating mechanism dynamics model is established. In addition, since ADAMS cannot simulate the movement process of the oil damper in the operating mechanism, this embodiment uses Amesim and ADAMS for joint simulation to simulate the opening movement process of the tap changer operating mechanism. Among them, the external force on the damper piston rod is transmitted to Amesim by ADAMS, the oil damper movement simulation process is completed in the Amesim simulation software, and the damper piston rod movement data-displacement, velocity and acceleration are transmitted back to ADAMS, thereby completing the simulation of the complete opening movement process.

[0238] In order to verify the fidelity of the established tap changer operating mechanism model, a circuit breaker operating mechanism test platform was built with a tap changer operating mechanism simulator as the main body. Fig. 9 As shown. The opening and closing movement process of the tap changer operating mechanism is characterized by fast speed, short time, and large impact, which leads to strong vibration during the movement process. Therefore, the contact sensor cannot be installed on the moving parts of the operating mechanism to measure the motion data during the opening process. This embodiment uses a non-contact measurement method-a high-speed camera to measure the motion data of the tap changer operating mechanism during the opening process. The frame rate of the high-speed camera is set to 50,000 frames / s, and the shooting time for each time is 1s, that is, 50,000 photos of the operating mechanism movement can be obtained each time the camera is shot. In addition, to facilitate data collection, this embodiment uses a high-speed camera to vertically shoot the movement process of the opening connecting rod joint as shown Fig.10 shown.

[0239] The time from the triggering of the secondary side control switch to the basic stable movement of the operating mechanism during the opening process of the tap changer operating mechanism does not exceed 40ms. Therefore, in this embodiment, the measurement time is selected as 40ms, that is, 2000 photos recording the opening action process need to be selected from the 50000 photos taken, and the displacement curve, velocity curve and acceleration curve of the opening connecting rod joint are calculated based on the selected series of photos, and the motion displacement, velocity and acceleration curves obtained by the experiment and the motion displacement, velocity and acceleration curves obtained by simulation are compared and analyzed.

[0240] Motion displacement comparison and analysis:

[0241] Comparison of experimental displacement curve and simulation curve of opening movement of tap changer operating mechanism Fig.11 (a) As shown in the experimental displacement curve, it can be seen that the displacement of the driving connecting rod joint reaches 115mm at 25ms, and the displacement remains basically unchanged afterwards. The total displacement reaches 115.992mm within the measurement time period of 40ms. Fig.11 From the simulation displacement curve results in (a), the total displacement of the simulation is 115.867mm, and the error between the total displacement of the simulation and the experimental one is 0.125mm. Compared with the total displacement of the experiment, the relative error is less than 0.11%. Fig.11 (b) shows that the displacement curves of the experiment and simulation have the largest error at 8.80ms, with a maximum error of 1.627mm and a relative error of 1.4%. The root mean square of the error curve during the entire opening process is 0.847mm, with a relative error of 0.7%.

[0242] Movement speed comparison and analysis:

[0243] Comparison of experimental speed curve and simulation curve of opening movement of tap changer operating mechanism Fig.12(a) is shown. From the experimental speed curve, the overall speed of the driving connecting rod joint shows a trend of first increasing and then decreasing. Before the shaft pin 2 collides with the oil damper piston rod joint, the speed of the driving connecting rod joint shows a rapid increase trend. At around 10.50ms, the speed in the experimental curve reaches 6.376m / s, and the speed in the simulation curve reaches 6.440m / s. The speed curve of the driving connecting rod joint jitters. The reason is that the shaft pin 2 collides with the oil damper piston rod joint for the first time, causing the speed of the driving connecting rod joint to jitter, and causing the speed of the piston rod joint to be greater than the speed of the shaft pin 2. During the period of 10.60-14.50ms, the opening spring is still releasing elastic potential energy, the speed of the shaft pin 2 gradually increases, and exceeds the speed of the piston rod joint; around 14.55ms, the speed in the experimental curve reaches a maximum value of 8.731m / s, and the speed in the simulation curve reaches a maximum value of 8.548m / s, and the shaft pin 2 collides with the piston rod joint for the second time, and the two move together after the collision; during 17.10-25.00ms, the oil damper piston rod moves rapidly toward the damper end cover, and the pressure difference between the upper and lower parts of the damper cavity increases rapidly, that is, the damping force on the piston rod increases rapidly, causing the speed of the driving connecting rod joint to gradually decrease, and the opening process gradually ends.

[0244] from Fig.12 It can be seen that the overall development trend of the experimental speed curve is very consistent with that of the simulation speed curve. The root mean square error of the two curves in the opening process is 0.439m / s, and the relative error with the maximum value of the experimental curve is 5.0%. The areas with large errors between the two curves are mainly concentrated in the two time ranges of 10.60-14.50ms and 25.30-35.84ms. In the first time period, between the first and second collisions between the shaft pin 2 and the piston rod joint of the oil damper, the experimental speed curve changes greatly, while the simulation speed curve tends to be a straight line. The peak error in this time period is 1.020m / s, and the experimental speed at the peak error time point is 7.450m / s, with a relative error of 13.7%. The second time period is the end stage of the opening process, and the movement gradually tends to be stable. In this time period, the experimental speed curve has the phenomenon of increasing speed and then decreasing speed, while the simulation speed curve remains stable. This is due to the shaking of the operating mechanism itself during the opening process caused by the inability of the test platform to be stably fixed on the ground.

[0245] Motion acceleration comparison and analysis:

[0246] Comparison of experimental acceleration curve and simulation acceleration of the opening motion of the tap changer operating mechanism Fig.13As shown. It can be seen from the experimental acceleration curve that during the opening process of the tap changer operating mechanism, its acceleration curve has a maximum peak near 10.50ms, with an amplitude of 1.39×107mm / s2, which corresponds to the first collision between the shaft pin 2 and the oil damper piston rod joint. The second peak appears near 15.02ms, with an amplitude of 7.71×106mm / s2, and the shaft pin 2 collides with the piston rod joint for the second time. The simulated acceleration curve of the opening movement of the tap changer operating mechanism also has peaks near 11.14ms and 15.36ms, with amplitudes of 1.40×107mm / s2 and 7.23×106mm / s2, respectively. The relative errors with the experimental acceleration are 0.7% and 6.2%, respectively. From Fig.11 It can be seen that the collision characteristics of the experimental acceleration curve and the simulation acceleration curve are quite consistent. The two collisions between the shaft pin 2 and the piston rod joint of the oil damper have obvious peaks in both the experimental acceleration curve and the simulation acceleration curve.

[0247] Fault condition simulation:

[0248] The opening spring is the source of power for the spring operating mechanism during the opening movement. The relaxation of the opening spring has a significant impact on the motion characteristics of the spring operating mechanism. This embodiment uses the established high-fidelity tap changer operating mechanism model to simulate the fault condition of the opening spring relaxation. By simulating the three conditions of opening spring relaxation of 5%, 10%, and 15%, the displacement, velocity, and acceleration curves under these three conditions are compared to analyze the influence of the opening spring relaxation on the motion characteristics of the operating mechanism.

[0249] Fig.14 The following are the displacement, velocity and acceleration curve comparisons when the opening spring is relaxed by 5%, 10% and 15%. Fig.14 (a) It can be seen that as the degree of relaxation of the opening spring increases, the displacement curve of the driving connecting rod joint rises more slowly within 9.10-21.90ms, and the phenomenon of the overall displacement curve shifting backward becomes more obvious. Fig.14 (b) It can be seen that the greater the degree of relaxation of the opening spring, the slower the rise of the driving connecting rod speed curve and the slower the speed at the time of collision, and the time of collision is also delayed. Fig.14 (c) It can be seen that the increase in the relaxation degree of the opening spring causes the peak value of the acceleration curve of the driving connecting rod joint to decrease, and the time of the corresponding peak value also shifts backward.

[0250] In summary, the greater the degree of relaxation of the opening spring, the smaller the compression of the opening spring, which makes the opening spring force smaller. As the power source of the opening movement, the smaller the opening spring force, the slower the overall movement speed of the mechanism, and the longer the movement time (the more obvious the time shift of the displacement, velocity and acceleration curves). In addition, the smaller the compression of the opening spring, the smaller the energy it provides, and the smaller the acceleration peak during the collision.

[0251] In summary, this embodiment aims at the collision phenomenon in the opening motion process of the operating mechanism, derives the collision parameters of its continuous contact force model from the perspective of energy change, and establishes the opening motion model of the tap changer operating mechanism.

[0252] In this embodiment, a comparative analysis is conducted on the experimental and simulated motion curves. The results show that the root mean square error of the displacement comparison curve is 0.847 mm, and its relative error is 0.7%; the root mean square error of the velocity comparison curve is 0.439 m / s, and its relative error is 5.2%; the two key peaks of the experimental acceleration curve are 1.39×107 mm / s2 and 7.71×106 mm / s2, and the two key peaks of the simulated acceleration curve are 1.40×107 mm / s2 and 7.23×106 mm / s2, and their relative errors are 0.7% and 6.2%, respectively, which verifies the validity and fidelity of the tap changer operating mechanism model.

[0253] The simulation model constructed using this embodiment simulates the opening spring under different relaxation conditions. The simulation results show that relaxation of the opening spring will reduce the movement speed of the spring operating mechanism and prolong the movement time, and the greater the relaxation degree of the opening spring, the smaller the movement speed of the spring operating mechanism, the longer the movement time, and the smaller the collision acceleration peak.

[0254] In the above embodiment, in the process of predicting the working condition of the tap switch operating mechanism, the working condition prediction model is pre-trained, so that in practical application, after the image information to be analyzed of the tap switch operating mechanism is analyzed, the target working condition information of the tap switch operating mechanism to be analyzed can be predicted; secondly, the working condition prediction model receives new data in each round of iteration, and improves and optimizes the model internally, so that the prediction can be performed more effectively, which is beneficial to improving the prediction accuracy of the working condition prediction model, and further improves the working condition prediction accuracy of the tap switch operating mechanism; moreover, the whole process does not require manual intervention, avoiding the defect of low working condition prediction accuracy of the tap switch operating mechanism due to subjective factors and prone to errors in the manual judgment method, thereby further improving the working condition prediction accuracy of the tap switch operating mechanism.

[0255] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in the present embodiment, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0256] Based on the same inventive concept, the embodiment of the present application also provides a device for predicting the working condition of a tap changer operating mechanism based on a working condition prediction model for realizing the method for predicting the working condition of a tap changer operating mechanism based on a working condition prediction model. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations of one or more embodiments of the device for predicting the working condition of a tap changer operating mechanism based on a working condition prediction model provided below can refer to the limitations of the method for predicting the working condition of a tap changer operating mechanism based on a working condition prediction model above, and will not be repeated here.

[0257] In an exemplary embodiment, Fig.15 As shown, a device for predicting the operating condition of a tap changer operating mechanism based on an operating condition prediction model is provided, comprising: an information acquisition module 1501, an information prediction module 1502, an operating condition prediction module 1503, a model training module 1504 and a target prediction module 1505, wherein:

[0258] The information acquisition module 1501 is used to acquire sample image information of a sample tap changer operating mechanism.

[0259] The information prediction module 1502 is used to input the sample image information into the working condition prediction model to be trained to obtain the predicted motion information of the sample tap changer operating mechanism.

[0260] The operating condition prediction module 1503 is used to determine the predicted operating condition information of the sample tap changer operating mechanism based on the predicted motion information by using the operating condition prediction model to be trained.

[0261] The model training module 1504 is used to obtain the actual motion information and actual working condition information of the sample tap changer operating mechanism, and iteratively train the working condition prediction model to be trained according to the difference between the predicted motion information and the actual motion information, and the difference between the predicted working condition information and the actual working condition information, to obtain a trained working condition prediction model.

[0262] The target prediction module 1505 is used to obtain the image information to be analyzed of the tap changer operating mechanism to be analyzed, input the image information to be analyzed into the trained working condition prediction model, and obtain the target working condition information of the tap changer operating mechanism to be analyzed.

[0263] In an exemplary embodiment, the information prediction module 1502 is also used to input the sample image information into the working condition prediction model to be trained to obtain the predicted displacement information, predicted speed information and predicted acceleration information of the sample tap changer operating mechanism; the predicted displacement information, predicted speed information and predicted acceleration information are all used as predicted motion information.

[0264] In an exemplary embodiment, the operating condition prediction module 1503 is also used to preprocess the predicted motion information to obtain preprocessed predicted motion information; based on the preprocessed predicted motion information, query the correspondence between the motion information and the operating condition information to obtain the operating condition information corresponding to the preprocessed predicted motion information as the predicted operating condition information.

[0265] In an exemplary embodiment, the model training module 1504 is also used to obtain a first loss value based on the difference between the predicted motion information and the actual motion information, and to obtain a second loss value based on the difference between the predicted operating condition information and the actual operating condition information; to fuse the first loss value and the second loss value to obtain a target loss value; and to iteratively train the operating condition prediction model to be trained based on the target loss value to obtain a trained operating condition prediction model.

[0266] In an exemplary embodiment, the target prediction module 1505 is also used to extract key image information from the image information to be analyzed; input the key image information into the trained operating condition prediction model to obtain multiple predicted operating condition information of the tap changer operating mechanism to be analyzed, and the predicted probability of each predicted operating condition information; from each predicted operating condition information, the predicted operating condition information with the largest predicted probability is screened out as the target operating condition information.

[0267] In an exemplary embodiment, the operating condition prediction device for the tap changer operating mechanism based on the operating condition prediction model also includes an information sending module, which is used to determine the target circuit breaker corresponding to the tap changer operating mechanism to be analyzed when the target operating condition information indicates that the tap changer operating mechanism to be analyzed is in an abnormal operating condition; generate early warning information corresponding to the target circuit breaker; and send the early warning information to a target terminal associated with the target circuit breaker.

[0268] Each module in the above-mentioned device for predicting the working condition of the tap changer operating mechanism based on the working condition prediction model can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0269] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Fig.16 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as sample image information and predicted motion information. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for predicting the operating condition of a tap changer operating mechanism based on an operating condition prediction model is implemented.

[0270] Those skilled in the art will understand that Fig.16 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0271] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0272] In an exemplary embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0273] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0274] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0275] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0276] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for predicting the operating condition of a tap changer operating mechanism based on an operating condition prediction model, characterized in that: The method comprises: Acquiring sample image information of a sample tap changer operating mechanism; Inputting the sample image information into the working condition prediction model to be trained to obtain the predicted motion information of the sample tap changer operating mechanism; Determining predicted operating condition information of the sample tap changer operating mechanism based on the predicted motion information by using the operating condition prediction model to be trained; Acquiring actual motion information and actual operating condition information of the sample tap changer operating mechanism, and iteratively training the operating condition prediction model to be trained according to the difference between the predicted motion information and the actual motion information, and the difference between the predicted operating condition information and the actual operating condition information, to obtain a trained operating condition prediction model; The image information to be analyzed of the tap changer operating mechanism to be analyzed is obtained, and the image information to be analyzed is input into the trained working condition prediction model to obtain the target working condition information of the tap changer operating mechanism to be analyzed.

2. The method according to claim 1, characterized in that The step of inputting the sample image information into the working condition prediction model to be trained to obtain the predicted motion information of the sample tap changer operating mechanism includes: Inputting the sample image information into the working condition prediction model to be trained to obtain the predicted displacement information, predicted speed information and predicted acceleration information of the sample tap changer operating mechanism; The predicted displacement information, the predicted speed information and the predicted acceleration information are all used as the predicted motion information.

3. The method according to claim 1, characterized in that The step of determining the predicted operating condition information of the sample tap changer operating mechanism based on the predicted motion information includes: Preprocessing the predicted motion information to obtain preprocessed predicted motion information; According to the preprocessed predicted motion information, the correspondence between the motion information and the operating condition information is queried to obtain the operating condition information corresponding to the preprocessed predicted motion information as the predicted operating condition information.

4. The method according to claim 1, characterized in that The iterative training of the working condition prediction model to be trained according to the difference between the predicted motion information and the actual motion information, and the difference between the predicted working condition information and the actual working condition information, to obtain a trained working condition prediction model, includes: Obtaining a first loss value according to a difference between the predicted motion information and the actual motion information, and obtaining a second loss value according to a difference between the predicted operating condition information and the actual operating condition information; fusing the first loss value and the second loss value to obtain a target loss value; According to the target loss value, the operating condition prediction model to be trained is iteratively trained to obtain the trained operating condition prediction model.

5. The method according to claim 1, characterized in that The step of inputting the image information to be analyzed into the trained working condition prediction model to obtain the target working condition information of the tap changer operating mechanism to be analyzed includes: Extracting key image information from the image information to be analyzed; Inputting the key image information into the trained working condition prediction model to obtain a plurality of predicted working condition information of the tap changer operating mechanism to be analyzed and a predicted probability of each predicted working condition information; From each of the predicted operating condition information, the predicted operating condition information with the highest predicted probability is screened out as the target operating condition information.

6. The method according to any one of claims 1 to 5, characterized in that: After acquiring the image information to be analyzed of the tap changer operating mechanism to be analyzed, inputting the image information to be analyzed into the trained working condition prediction model, and obtaining the target working condition information of the tap changer operating mechanism to be analyzed, the method further includes: When the target operating condition information indicates that the tap changer operating mechanism to be analyzed is in an abnormal operating condition, determining a target circuit breaker corresponding to the tap changer operating mechanism to be analyzed; Generate warning information corresponding to the target circuit breaker; The warning information is sent to a target terminal associated with the target circuit breaker.

7. A device for predicting the operating condition of a tap changer operating mechanism based on an operating condition prediction model, characterized in that: The device comprises: An information acquisition module, used to acquire sample image information of a sample tap changer operating mechanism; An information prediction module, used for inputting the sample image information into a working condition prediction model to be trained to obtain predicted motion information of the sample tap changer operating mechanism; A working condition prediction module, used to determine the predicted working condition information of the sample tap changer operating mechanism based on the predicted motion information by using the working condition prediction model to be trained; A model training module, used for obtaining actual motion information and actual working condition information of the sample tap changer operating mechanism, and iteratively training the working condition prediction model to be trained according to the difference between the predicted motion information and the actual motion information, and the difference between the predicted working condition information and the actual working condition information, to obtain a trained working condition prediction model; The target prediction module is used to obtain the image information to be analyzed of the tap switch operating mechanism to be analyzed, input the image information to be analyzed into the trained working condition prediction model, and obtain the target working condition information of the tap switch operating mechanism to be analyzed.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images