A redundant speed regulation system speed regulation switching control method, device, equipment and medium

Abstract

The present invention relates to a redundant speed control system speed switching control method, device, equipment and medium. The method combines the actual state parameter index of the diesel engine corresponding to each sampling moment under the historical sampling moment and the working mode of the controller under control, predicts the state parameter index of the current i-th sampling moment, compares the error between the predicted result and the actual result to determine whether there is an abnormality at the previous moment, that is, the i-1-th sampling moment, and switches the controller at the i-th sampling moment to a standby controller with the same working mode as the previous moment when the abnormality occurs, observes whether there is still an obvious error between the predicted value and the actual value of the state parameter index of the diesel engine at the next moment, that is, the i+1-th sampling moment, to determine whether the previous abnormality is a diesel engine failure or a previous controller failure and perform corresponding processing. The present invention can significantly improve the switching control efficiency in the scenario of one main controller and multiple standby controllers, thereby improving the working efficiency of the diesel engine.

Description

Technical Field

[0001] The present invention is applicable to the field of system control technology, and in particular relates to a redundant speed regulation system speed regulation switching control method, device, equipment and medium. Background Art

[0002] As a high-power power output device, the diesel engine plays an important role in many scenarios such as nuclear power plant emergency and ship drive. The diesel engine controller is a supporting equipment for the diesel engine or diesel generator set to achieve self-starting, automatic control and automatic protection functions. It is a necessary part for the normal operation of the diesel engine.

[0003] In the prior art, in order to ensure reliable control of the diesel engine and thus ensure reliable operation of the diesel engine, an additional backup controller is configured on the basis of a main controller for the diesel engine, and the main and backup controllers serve as backups for each other and switch to the other controller to perform control when one fails. However, with the significant increase in diesel engine power and the increasing complexity of its structure, the impact of unexpected diesel engine shutdown is also increasing. Therefore, in order to more effectively ensure the normal operation of the diesel engine, the need and necessity to configure multiple backup controllers for the diesel engine are becoming increasingly apparent.

[0004] However, the controller switching control methods in the prior art are mostly designed for scenarios with only two controllers, one main and one backup. They cannot achieve efficient and accurate control of controller speed regulation redundant switching in a scenario with one main and multiple backup controllers, which will significantly affect the working efficiency of the diesel engine.

[0005] Therefore, the existing controller speed regulation redundant switching control method has the defect of low redundant switching control efficiency in the scenario where the controller has one master and multiple backups, which significantly affects the working efficiency of the diesel engine. Summary of the invention

[0006] In view of this, an embodiment of the present invention provides a redundant speed control system speed switching control method, device, equipment and medium to solve the problem that the current controller speed control redundant switching control method has low redundant switching control efficiency when facing a one-master and multiple-standby controller scenario, resulting in low diesel engine operating efficiency.

[0007] In a first aspect, a redundant speed regulation system speed regulation switching control method is provided, the method comprising:

[0008] Acquire various state parameter indicators of the diesel engine at a set sampling interval, use various state parameter indicators of the diesel engine at any sampling moment to form an actual parameter vector corresponding to the sampling moment, and use the working mode of the controller whose reference identifier is the control right identifier at any sampling moment as the working mode corresponding to the sampling moment;

[0009] Input the actual parameter vectors and working modes corresponding to a set number of sampling moments before the i-th sampling moment into the trained state parameter prediction model, obtain the prediction parameter vector corresponding to the i-th sampling moment, calculate the first similarity between the prediction parameter vector corresponding to the i-th sampling moment and the actual parameter vector corresponding to the i-th sampling moment, and determine the magnitude relationship between the first similarity and the similarity threshold;

[0010] If the first similarity is less than the similarity threshold, a controller whose working mode is the same as the working mode corresponding to the i-1th sampling moment and whose reference identifier is a standby identifier is selected as the first target controller, and after the reference identifier of the controller corresponding to the i-1th sampling moment is switched to a no-control right identifier, the reference identifier of the first target controller is switched to a control right identifier as the controller corresponding to the i-th sampling moment;

[0011] Obtain the predicted parameter vector corresponding to the i+1th sampling moment, calculate the second similarity between the predicted parameter vector corresponding to the i+1th sampling moment and the actual parameter vector corresponding to the i+1th sampling moment, if the second similarity is not less than the similarity threshold, switch the reference identifier of the controller corresponding to the i-1th sampling moment to a fault identifier; if the second similarity is less than the similarity threshold, input the actual parameter vector corresponding to the i+1th sampling moment into the trained working mode determination model to determine the target working mode, select any controller whose working mode is the target working mode as the second target controller, switch the reference identifier of the controller corresponding to the i-th sampling moment to a no-control right identifier, and then switch the reference identifier of the second target controller to a control right identifier.

[0012] In a second aspect, a redundant speed regulation system speed regulation switching control device is provided, the device comprising:

[0013] A definition module is used to obtain various state parameter indicators of the diesel engine at a set sampling interval, form the actual parameter vector corresponding to the sampling moment with the various state parameter indicators of the diesel engine at any sampling moment, and use the working mode of the controller whose reference identifier is the control right identifier at any sampling moment as the working mode corresponding to the sampling moment;

[0014] An operation status monitoring module is used to input the actual parameter vectors and working modes corresponding to a set number of sampling moments before the i-th sampling moment into a trained state parameter prediction model, obtain the prediction parameter vector corresponding to the i-th sampling moment, calculate the first similarity between the prediction parameter vector corresponding to the i-th sampling moment and the actual parameter vector corresponding to the i-th sampling moment, and determine the size relationship between the first similarity and the similarity threshold;

[0015] A standby controller switching module, used for, if the first similarity is less than the similarity threshold, selecting a controller whose working mode is the same as the working mode corresponding to the i-1th sampling moment and whose reference identifier is a standby identifier as the first target controller, switching the reference identifier of the controller corresponding to the i-1th sampling moment to a no-control right identifier, and then switching the reference identifier of the first target controller to a control right identifier as the controller corresponding to the i-th sampling moment;

[0016] A fault subdivision processing module is used to obtain the prediction parameter vector corresponding to the i+1th sampling moment, calculate the second similarity between the prediction parameter vector corresponding to the i+1th sampling moment and the actual parameter vector corresponding to the i+1th sampling moment, and if the second similarity is not less than the similarity threshold, the reference identifier of the controller corresponding to the i-1th sampling moment is switched to a fault identifier; if the second similarity is less than the similarity threshold, the actual parameter vector corresponding to the i+1th sampling moment is input into the trained working mode determination model to determine the target working mode, and any controller whose working mode is the target working mode is selected as the second target controller. After the reference identifier of the controller corresponding to the i-th sampling moment is switched to a no-control identifier, the reference identifier of the second target controller is switched to a control identifier.

[0017] In a third aspect, an embodiment of the present invention provides a computer device, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the redundant speed regulation system speed switching control method as described in the first aspect is implemented.

[0018] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the operation as described in the first aspect is implemented.

[0019] In a fifth aspect, an embodiment of the present invention provides a computer program product. When the computer program product is run on a computer device, the computer device executes the redundant speed regulation system speed regulation switching control method described in the first aspect above.

[0020] Compared with the prior art, the present invention has the following beneficial effects:

[0021] The present invention predicts the state parameter index of the current i-th sampling moment by combining the actual state parameter index of the diesel engine corresponding to each sampling moment under the historical sampling moment and the working mode of the controller under the control right corresponding to each sampling moment, and compares the error between the predicted result and the actual result to judge whether there is an abnormality at the previous moment, that is, the i-1th sampling moment, and switches the controller at the i-th sampling moment to a standby controller with the same working mode as the previous moment when an abnormality exists, and observes whether there is still an obvious error between the predicted value and the actual value of the state parameter index of the diesel engine at the next moment, that is, the i+1th sampling moment, to determine whether the previous abnormality is specifically a fault of the diesel engine itself or a fault of the previous controller, and performs corresponding processing. The present invention can significantly improve the switching control efficiency in the scenario of one main controller and multiple standby controllers, thereby improving the working efficiency of the diesel engine. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0023] Figure 1 This is a schematic diagram of an application environment of a redundant speed regulation system speed regulation switching control method provided by the first embodiment of the present invention;

[0024] Figure 2 It is a flow chart of a speed regulation switching control method of a redundant speed regulation system provided in Embodiment 1 of the present invention;

[0025] Figure 3 It is a flow chart of a method for resetting the operating state of a diesel engine when there is no available standby controller after the first similarity is less than the similarity threshold provided by the second embodiment of the present invention;

[0026] Figure 4 It is a structural schematic diagram of a redundant speed regulation system speed regulation switching control device provided in Embodiment 3 of the present invention;

[0027] Figure 5 It is a structural diagram of a computer device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0028] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0029] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0030] It should also be understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0031] As used in the present specification and the appended claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]", depending on the context.

[0032] In addition, in the description of the present specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0033] References to "one embodiment" or "some embodiments" etc. described in the present specification mean that one or more embodiments of the present invention include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0034] The embodiments of the present invention can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0035] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0036] It should be understood that the order of execution of the steps in the following embodiments does not imply a precedence of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0037] In order to illustrate the technical solution of the present invention, specific embodiments are provided below for illustration.

[0038] A redundant speed regulation system speed regulation switching control method provided in the first embodiment of the present invention can be applied in the following aspects: Figure 1 In the application environment, the client communicates with the server to obtain the specific controller and control details of the diesel engine at the current and historical moments from the server. The client includes but is not limited to PDAs, desktop computers, laptops, ultra-mobile personal computers (UMPC), netbooks, cloud terminal devices, personal digital assistants (PDA) and other terminal devices. The server can be implemented with an independent server or a server cluster composed of multiple servers. The sensing device may include a diesel engine-related state parameter indicator acquisition device, such as a sensor device for completing the detection of diesel engine speed, gear position, actuator drive status, cooling water temperature, intake pressure, and oil temperature.

[0039] See also Figure 2 , is a flow chart of a redundant speed regulation system speed regulation switching control method provided in the first embodiment of the present invention. The redundant speed regulation system speed regulation switching control method can be applied to the server in FIG1 , and the computer device corresponding to the server is connected to the corresponding database, rule base, etc. to obtain the corresponding data in the database. The computer device can also be connected to the client to collect the query instructions sent by the client user and return the corresponding speed regulation switching control information to the client.

[0040] like Figure 2 As shown, the redundant speed regulation system speed regulation switching control method may include the following steps:

[0041] Step S101, obtain various state parameter indicators of the diesel engine at a set sampling interval, and use the various state parameter indicators of the diesel engine at any sampling moment to form an actual parameter vector corresponding to the sampling moment, and use the working mode of the controller with the reference identifier as the control right identifier at any sampling moment as the working mode corresponding to the sampling moment.

[0042] The present invention aims to achieve speed switching control in a diesel engine controller with one main and multiple backups, and complete the selection of the optimal backup controller and the determination of the corresponding working mode when there are multiple backup controllers, thereby improving the speed switching control efficiency in the scenario of one main and multiple backup controllers, and ultimately improving the operating efficiency of the diesel engine.

[0043] In order to complete the speed switching control, it is necessary to obtain the diesel engine operating state and the relevant identification states and working modes of each controller. Various relevant state parameter indicators during the operation of the diesel engine are continuously changing, but in order to facilitate statistical implementation, this embodiment preferably obtains various relevant state parameter indicators during the operation of the diesel engine according to the set sampling interval. It is easy to understand that the size of the set sampling interval is related to the corresponding sensitivity of the redundant switching of the diesel engine controller, so the specific size of the set sampling interval can be set according to the strictness of the diesel engine operation stability requirements, and this embodiment does not specifically limit its value.

[0044] There are various status parameter indicators related to the operating status of the diesel engine, such as diesel engine speed, gear position, actuator drive status, etc., and may also include cooling water temperature, intake pressure, oil temperature, etc. The selection of specific status parameter indicators can be specifically selected by the implementer, and this embodiment also does not specifically limit them.

[0045] After clarifying the sampling interval and state parameter indicators, different values ​​of each state parameter indicator can be corresponding to each sampling moment. Therefore, by constructing a vector of each state parameter indicator at each sampling moment, the actual parameter vector corresponding to the current sampling moment can be obtained. The actual parameter vector is in the form of a 1*M vector, where M is the number of state parameter indicators. Each column in the actual parameter vector corresponds to a different state parameter indicator, and the specific value of the element under each column is the size of the corresponding state parameter indicator.

[0046] The diesel engine controller corresponds to the working mode, reference identifier, device ID, etc. The reference identifier can be used to indicate the use status of the controller. The reference identifier can include the control authority identifier, the no control authority identifier, the standby identifier and the fault identifier. The device ID is used as the unique identifier of the controller. The working mode can include idle control, fixed signal control, shutdown control and other working modes. The implementer can determine the specific type of working mode according to the actual control strategy.

[0047] To facilitate the implementation of subsequent speed switching control, the various state parameter indicators of the diesel engine at a certain sampling moment constitute the actual parameter vector corresponding to the sampling moment, and the working mode of the controller with the reference identifier as the control right identifier at the sampling moment is taken as the working mode corresponding to the sampling moment.

[0048] Step S102, input the actual parameter vector and working mode corresponding to a set number of sampling moments before the i-th sampling moment into the trained state parameter prediction model, obtain the prediction parameter vector corresponding to the i-th sampling moment, calculate the first similarity between the prediction parameter vector corresponding to the i-th sampling moment and the actual parameter vector corresponding to the i-th sampling moment, and determine the size relationship between the first similarity and the similarity threshold.

[0049] If the state parameter index of the diesel engine deviates significantly from the normal expectation during operation, it means that the diesel engine or the controller that controls it is likely to have a fault or abnormality. Therefore, this embodiment selects the actual parameter vector and working mode corresponding to each sampling moment within a certain period of time before the current moment to obtain the predicted parameter index state at the current moment, that is, the predicted parameter vector, and compares the obtained predicted parameter vector with the actual parameter vector corresponding to the current moment to determine whether the actual operating state has a significant deviation from the predicted operating state at the current moment based on historical data.

[0050] Among them, it should be emphasized that since it takes a certain amount of time for the controller to control the diesel engine and produce a control result, it is easy to understand that the actual parameter vector corresponding to the current moment is obtained by the controller at the moment before the current moment, that is, the previous moment, controlling the diesel engine at the previous moment according to its working mode, rather than the controller at the current moment controlling the diesel engine at the current moment according to its working mode.

[0051] And, regarding the state parameter prediction model, it includes an encoder and a decoder. The state parameter prediction model corresponds to a preset sliding window. The length of the preset sliding window is set to k in this embodiment. The sliding step of the preset sliding window is 1. Then the sliding result of the preset sliding window is an input to the state parameter prediction model. Since the length of the preset sliding window is k, the single input of the state parameter prediction model is the data corresponding to k sampling moments, so k is also the set number of sampling moments of the input state parameter prediction model. For example, the input of the state parameter prediction model is the actual parameter vector of the diesel engine corresponding to the continuous set number of k sampling moments and the working mode of the controller whose reference identifier is the control right identifier. The actual parameter vector and the working mode corresponding to any moment in the set number of k sampling moments are jointly input into the encoder for feature extraction to obtain the feature information corresponding to the moment, traverse the set number of k sampling moments, fuse the feature information corresponding to the k sampling moments, input the fusion result into the decoder, and output the predicted parameter vector of the next sampling moment of the last sampling moment in the set number of k sampling moments.

[0052] In the above state parameter prediction model, one encoder can also be replaced by k+1 weight-sharing encoders to improve the inference efficiency. The encoder uses one or more encoder weight sharing to effectively reduce the number of model parameters, making the training process easier to converge and ultimately improving the training efficiency.

[0053] When training the state parameter prediction model, the actual parameter vectors and working modes corresponding to each historical sampling moment in the historical time period are used as initial samples. The actual parameter vectors and working modes corresponding to a set number k of historical sampling moments are taken from the initial samples as training samples. The actual parameter vector corresponding to the next historical sampling moment of the last historical sampling moment among the k historical sampling moments is used as the label of the training sample. According to the above method, several training samples and corresponding labels can be constructed to form data pairs. According to multiple groups of data pairs, the state parameter prediction model is trained. The mean square error loss function is used during training, and finally the trained state parameter prediction model can be obtained.

[0054] It should be noted that when preparing the initial samples, there should be initial samples with switching of the working mode, that is, the initial samples should include each working mode of the controller as much as possible, so as to improve the comprehensiveness of the obtained training samples and ensure the accuracy of the prediction parameter vector obtained by the subsequent prediction based on the state parameter prediction model.

[0055] Step S103, if the first similarity is less than the similarity threshold, select any controller whose working mode is the same as the working mode corresponding to the i-1th sampling moment and whose reference identifier is a backup identifier as the first target controller, switch the reference identifier of the controller corresponding to the i-1th sampling moment to a no-control authority identifier, and then switch the reference identifier of the first target controller to a control authority identifier as the controller corresponding to the i-th sampling moment.

[0056] After performing a first similarity calculation on the actual parameter vector and the predicted parameter vector corresponding to the i-th sampling moment, if the first similarity is less than the preset similarity threshold, it means that at the i-1th sampling moment, the diesel engine or the controller that controls it is likely to have a fault or abnormality. At this time, in order to ensure the stable operation of the diesel engine, minimize losses and maximize profits, a controller with a reference identifier as a backup identifier and a working mode that is the same as the working mode corresponding to the i-1th sampling moment is selected as the switching controller to replace the controller corresponding to the i-1th sampling moment.

[0057] The first similarity can be determined by the cosine similarity of the vectors, that is, the cosine similarity between the actual parameter vector and the predicted parameter vector corresponding to the i-th sampling moment is calculated as the first similarity.

[0058] The role of the similarity threshold is to determine whether the diesel engine has an abnormal operation, that is, its role is to identify the possible abnormal operating conditions of the diesel engine so as to accurately select and switch the controller and the corresponding working mode of the controller. The stability of each state parameter index under the normal operating conditions of different diesel engines is also different, or the so-called normal operating stability of different diesel engines is different. Therefore, the size of the similarity threshold applicable to the current diesel engine to be analyzed can be determined according to the inconsistency of the actual parameter vectors corresponding to the current diesel engine to be analyzed at different times under normal operating conditions in the historical data. The greater the inconsistency of the actual parameter vectors corresponding to the current diesel engine to be analyzed at different times under normal operating conditions in the historical data, the worse the stability of the current diesel engine to be analyzed under normal operating conditions, and the smaller the similarity threshold applicable to it should be set accordingly. In this embodiment, the similarity threshold is preferably set to 0.8.

[0059] It is easy to understand that there is still a situation where the first similarity is not less than the similarity threshold. At this time, it indicates that neither the diesel engine nor the controller in the control authority mark has failed, so this round of controller switching control can be ended, that is, the overall judgment process of whether controller switching control is needed for the i-th sampling moment is ended.

[0060] Step S104, obtain the predicted parameter vector corresponding to the i+1th sampling moment, calculate the second similarity between the predicted parameter vector corresponding to the i+1th sampling moment and the actual parameter vector corresponding to the i+1th sampling moment, if the second similarity is not less than the similarity threshold, switch the reference identifier of the controller corresponding to the i-1th sampling moment to a fault identifier; if the second similarity is less than the similarity threshold, input the actual parameter vector corresponding to the i+1th sampling moment into the trained working mode determination model to determine the target working mode, select any controller whose working mode is the target working mode as the second target controller, switch the reference identifier of the controller corresponding to the i-th sampling moment to a no-control identifier, and then switch the reference identifier of the second target controller to a control identifier.

[0061] In step S103, the situation that the first similarity is less than the similarity threshold value may be that the diesel engine itself has a fault, or that the controller controlling the diesel engine at the i-1th sampling moment has a fault. Therefore, after the controller corresponding to the i-1th sampling moment is replaced with a standby controller with the same working mode in step S103, the standby controller controls the diesel engine in exactly the same working mode at the i-1th sampling moment. Then, by observing the second similarity between the predicted parameter vector corresponding to the i+1th sampling moment and the actual parameter vector corresponding to the i+1th sampling moment, if the second similarity is also less than the similarity threshold value like the first similarity, it can be determined that the diesel engine itself has a fault. If the second similarity is not less than the similarity threshold value like the first similarity, but the second similarity is not less than the similarity threshold value, it means that the controller corresponding to the i-1th sampling moment has a fault.

[0062] Therefore, if the second similarity is not less than the similarity threshold, the reference identifier of the controller corresponding to the i-1th sampling moment is switched to the fault identifier; and if the second similarity is less than the similarity threshold, it is necessary to determine the various state parameter index values ​​under the specific fault condition of the diesel engine based on the actual parameter vector corresponding to the i+1th sampling moment, and give the corresponding target working mode of the controller.

[0063] The target working mode can be determined based on a trained working mode determination model. The working mode determination model needs to use the actual parameter vector when a diesel engine fails as a training sample, and the controller working mode annotated by an expert as a label of the training sample. The working mode determination model is trained with a cross entropy loss function to obtain the trained working mode determination model. Then, in specific use, the actual parameter vector corresponding to the i+1th sampling moment is directly input into the trained working mode determination model to obtain the target working mode of the controller required at the i+1th sampling moment. A controller whose working mode is the target working mode is selected as the second target controller. After the reference identifier of the controller corresponding to the i-th sampling moment is switched to a no-control right identifier, the reference identifier of the second target controller is switched to a control right identifier as the controller corresponding to the i+1th sampling moment.

[0064] Of course, there may be a controller that does not have the target working mode. In this case, it means that there is no immediately available controller to perform corresponding control processing on the diesel engine failure. In this case, the diesel engine needs to be shut down. The shutdown control can be achieved through a reserved shutdown control controller, or any backup controller can be selected to complete it.

[0065] This embodiment predicts the state parameter index of the current i-th sampling moment by combining the actual state parameter index of the diesel engine corresponding to each sampling moment under the historical sampling moment and the working mode of the controller under control corresponding to each sampling moment, and compares the error between the predicted result and the actual result to determine whether there is an abnormality at the previous moment, that is, the i-1th sampling moment, and switches the controller at the i-th sampling moment to a standby controller with the same working mode as the previous moment when an abnormality exists, and observes whether there is still an obvious error between the predicted value and the actual value of the state parameter index of the diesel engine at the next moment, that is, the i+1th sampling moment, to determine whether the previous abnormality is a fault of the diesel engine itself or a fault of the previous controller, and performs corresponding processing. This embodiment can significantly improve the switching control efficiency in the scenario of one main controller and multiple standby controllers, thereby improving the working efficiency of the diesel engine.

[0066] like Figure 3 As shown, it is a flow chart of a method for resetting the operating state of a diesel engine when there is no available standby controller after the first similarity is less than the similarity threshold provided by the second embodiment of the present invention, the method comprising:

[0067] Step S201, after the first similarity is less than the similarity threshold, if there is no working mode of the controller with the reference identifier as the backup identifier that is the same as the working mode corresponding to the i-1th sampling moment, a self-inspection operation with a self-inspection duration of T is performed on all controllers with the reference identifier as the no-control authority identifier, and the reference identifier of the controller that passes the self-inspection is modified to a backup identifier, and the various working modes in the working mode corresponding to the controller with the reference identifier as the backup identifier at the i-th sampling moment are respectively recorded as different temporary working modes.

[0068] When the first similarity is less than the similarity threshold, it indicates that an abnormality exists at this time. Under normal circumstances, as in the above embodiment, a backup controller with the same working mode as the previous controller needs to be used to replace the previous controller, and it is verified whether the abnormality occurs specifically in the previous controller or the diesel engine, and further targeted processing is performed.

[0069] However, when the first similarity is less than the similarity threshold, and there is no controller with the reference identifier as the backup identifier whose working mode is the same as the working mode corresponding to the i-1th sampling moment, it indicates that there is no available backup controller, or more accurately, there is no backup controller that can be used directly.

[0070] Then, since the first similarity is less than the similarity threshold, it indicates that an abnormality exists at this time. Regardless of whether the abnormality is caused by the diesel engine itself or by the previous controller, the final result is that the operating state of the diesel engine, that is, the actual parameter vector corresponding to the i-th sampling moment, has an abnormal deviation compared to the predicted normal situation. Then, in the absence of an available backup controller, in order to maximize the normal operation of the diesel engine and thus improve the operating efficiency of the diesel engine, it is necessary to reset the operating state of the diesel engine as soon as possible in the absence of an available backup controller, and restore its operating state to the normal operating state at the i-1-th sampling moment.

[0071] To this end, the idea of ​​this embodiment is to first perform a self-test for a duration of T on all controllers whose reference identifier is represented by no control authority, increase the number of subsequent standby controllers to increase the possibility of recovering the diesel engine's operating state in the future, and at the same time perform a preview estimate of which type of working mode of the current standby controllers will take over the diesel engine during the self-test process to be more conducive to the diesel engine's rapid return to normal operating state after the self-test, so that ultimately during the self-test duration T from the i-th sampling moment to the i+T-th sampling moment, the optimal controller is selected from the controllers whose reference identifier is the standby identifier at the i-th sampling moment to complete the control for this period of time, and after the i+T-th sampling moment, the optimal controller is selected from all standby controllers when the self-test is completed to complete the control for this period of time, so that the diesel engine can finally recover to normal operating state at the fastest speed.

[0072] Therefore, this step performs a self-inspection operation for a self-inspection time of T on all controllers without control authority and modifies the reference identifier of the controller that passes the self-inspection to a backup identifier. Then, various working modes in the working mode corresponding to the controller whose reference identifier is the backup identifier at the i-th sampling moment are recorded as different temporary working modes, so as to facilitate the subsequent analysis of which backup controller in different categories of working modes in the controller whose reference identifier is the backup identifier at the i-th sampling moment is more conducive to the diesel engine to resume normal operation.

[0073] Step S202, randomly select one of the temporary working modes as the working mode corresponding to the i-th sampling moment to the i+T-th sampling moment, and use the working mode corresponding to the i-1-th sampling moment as the working mode corresponding to each sampling moment after the i+T-th sampling moment, and start from the i+T+1-th sampling moment to obtain the prediction parameter vector corresponding to each sampling moment in turn and calculate the third similarity between the prediction parameter vector corresponding to the i-th sampling moment, and use the duration between the sampling moment corresponding to the first third similarity that is not less than the similarity threshold and the i+T-th sampling moment as the temporary duration corresponding to the current temporary working mode.

[0074] The method for determining which type of working mode of the standby controller in the current standby controller (i.e., the controller with the reference identifier as the standby identifier at the i-th sampling moment) takes over the diesel engine during the self-check process is more conducive to the diesel engine quickly returning to the normal operating state after the self-check. The general process can be:

[0075] Select each type of working mode (that is, temporary working mode) to perform a state preview of the diesel engine from the i-th sampling moment through a self-inspection duration of T, that is, perform a state preview from the i-th sampling moment to the i+T-th sampling moment. After the preview, the complete prediction parameter vector corresponding to the i+T+1-th sampling moment can be obtained. The reason why it is called a complete prediction parameter vector is that it is further predicted by the prediction parameter vector corresponding to the i+T-th sampling moment, and is not equivalent to the prediction parameter vector corresponding to the i+T+1-th sampling moment predicted by the actual parameter vector corresponding to the i+T-th sampling moment.

[0076] After obtaining the complete prediction parameter vector corresponding to the i+T+1th sampling moment, starting from the i+T+1th sampling moment, the working mode corresponding to the i-1th sampling moment is used as the working mode corresponding to each sampling moment after the i+Tth sampling moment to continue to preview the diesel engine operation state, and starting from the i+T+1th sampling moment, the prediction parameter vector corresponding to each sampling moment is obtained in turn and the third similarity between the prediction parameter vector corresponding to the i-th sampling moment is calculated. When the third similarity is not less than the similarity threshold, it can be indicated that the operation state of the diesel engine has returned to normal operation. state, then the time length between the sampling moment corresponding to the first third similarity which is not less than the similarity threshold and the i+Tth sampling moment is taken as the temporary time length corresponding to the current temporary working mode, which can characterize the help that the standby controller in the current temporary working mode will provide to the subsequent diesel engine to resume normal operating mode if it takes over the diesel engine during the self-test process. It is easy to understand that the shorter the temporary time length corresponding to the current temporary working mode, the greater the help that the standby controller in the current temporary working mode will provide to the subsequent diesel engine to resume normal operating mode if it takes over the diesel engine during the self-test process.

[0077] Step S203, select the shortest temporary duration from the temporary durations corresponding to each of the temporary working modes, take the temporary working mode corresponding to the shortest temporary duration as the intermediate working mode, select any one of the controllers whose reference identifier is a backup identifier at the i-th sampling moment and whose working mode is the intermediate working mode as the third target controller, and select any one of the controllers whose reference identifier is a backup identifier at the i+T-th sampling moment and whose working mode is the same as the working mode corresponding to the i-1-th sampling moment as the fourth target controller.

[0078] Then, the temporary working mode corresponding to the shortest temporary duration is selected as the intermediate working mode, and a controller with the working mode of the intermediate working mode is selected as the third target controller from the controllers with the reference identifier as the standby identifier at the i-th sampling moment. The third target controller is the controller that is most helpful for the subsequent diesel engine to resume the normal operating mode if the diesel engine is taken over during the self-test process. The principle is that different temporary working modes generate different complete prediction parameter vectors corresponding to the i+T+1 sampling moment after the diesel engine is pre-tested for the self-test duration T, and different complete prediction parameter vectors have different degrees of deviation from the normal operating mode of the diesel engine, that is, the actual parameter vector corresponding to the i-1 sampling moment. The temporary working mode corresponding to the complete prediction parameter vector with the smallest degree of deviation is the most suitable temporary working mode and is recorded as the intermediate working mode.

[0079] Then, after all controllers with reference identifiers as no control authority identifiers have undergone self-inspection operations with a self-inspection duration of T, those controllers that have passed the self-inspection will become new backup controllers. Therefore, the number of controllers with reference identifiers as backup identifiers at the i+Tth sampling moment will be significantly increased compared to the number of controllers with reference identifiers as backup identifiers at the i-th sampling moment. From the controllers with reference identifiers as backup identifiers at the i+Tth sampling moment, a controller with the same working mode as the working mode corresponding to the i-1th sampling moment is selected as the fourth target controller to complete the subsequent recovery process of the diesel engine operating state to the normal operating state after the self-inspection duration.

[0080] Step S204, after switching the reference identifier of the controller corresponding to the i-1th sampling moment to the no-control right identifier at the i-th sampling moment, the reference identifier of the third target controller is switched to the control right identifier as the controller corresponding to the i-th sampling moment to the i+T-th sampling moment, and after switching the reference identifier of the third target controller to the no-control right identifier at the i+T+1-th sampling moment, the reference identifier of the fourth target controller is switched to the control right identifier as the controller corresponding to each sampling moment within the shortest temporary time length after the i+T-th sampling moment.

[0081] After determining the theoretical preview most suitable backup controller during the self-test time T and the theoretical preview most suitable backup controller after the self-test time T, the controller corresponding to the i-1th sampling moment of the current execution control can be replaced, and the controller executing control can be replaced with the third target controller and the fourth target controller in turn to complete the fastest recovery of the diesel engine operating state to the normal operating state.

[0082] This embodiment provides a specific method for how to quickly restore the operating state of a diesel engine to a normal operating state in a scenario with one main controller and multiple backup controllers, when an abnormality occurs during the operation of the diesel engine but there is no directly available backup controller, thereby further improving the operating efficiency of the diesel engine.

[0083] Corresponding to the method of the above embodiment, Figure 4 The structural block diagram of a redundant speed regulation system speed regulation switching control device provided by the third embodiment of the present invention is shown. The speed regulation switching control device is applied to a computer device, and the computer device is connected to a target database through a preset application program interface. When the target database is driven to execute a corresponding task, a corresponding task log is generated, and the task log can be collected through the API. For ease of description, only the part related to the embodiment of the present invention is shown.

[0084] See also Figure 4 , the speed switching control device comprises:

[0085] The operating state acquisition module 31 is used to acquire various state parameter indicators of the diesel engine at a set sampling interval, and use various state parameter indicators of the diesel engine at any sampling moment to form an actual parameter vector corresponding to the sampling moment, and use the working mode of the controller whose reference identifier is the control right identifier at any sampling moment as the working mode corresponding to the sampling moment;

[0086] The operation status monitoring module 32 is used to input the actual parameter vectors and the working mode corresponding to the consecutive set number of sampling moments before the i-th sampling moment into the trained state parameter prediction model, obtain the prediction parameter vector corresponding to the i-th sampling moment, calculate the first similarity between the prediction parameter vector corresponding to the i-th sampling moment and the actual parameter vector corresponding to the i-th sampling moment, and determine the size relationship between the first similarity and the similarity threshold;

[0087] A standby controller switching module 33 is used for, if the first similarity is less than the similarity threshold, selecting a controller whose working mode is the same as the working mode corresponding to the i-1th sampling moment and whose reference identifier is a standby identifier as the first target controller, switching the reference identifier of the controller corresponding to the i-1th sampling moment to a no-control right identifier, and then switching the reference identifier of the first target controller to a control right identifier as the controller corresponding to the i-th sampling moment;

[0088] The fault subdivision processing module 34 is used to obtain the predicted parameter vector corresponding to the i+1th sampling moment, calculate the second similarity between the predicted parameter vector corresponding to the i+1th sampling moment and the actual parameter vector corresponding to the i+1th sampling moment, and if the second similarity is not less than the similarity threshold, the reference identifier of the controller corresponding to the i-1th sampling moment is switched to a fault identifier; if the second similarity is less than the similarity threshold, the actual parameter vector corresponding to the i+1th sampling moment is input into the trained working mode determination model to determine the target working mode, and any controller whose working mode is the target working mode is selected as the second target controller. After the reference identifier of the controller corresponding to the i-th sampling moment is switched to a no-control identifier, the reference identifier of the second target controller is switched to a control identifier.

[0089] Optionally, the speed regulation switching control device further includes:

[0090] The redundant switching stopping module is used to end the current round of controller switching control if the first similarity is not less than the similarity threshold.

[0091] Optionally, the standby controller switching module 33 further includes:

[0092] a reset operation start judgment unit, used for, after the first similarity is less than the similarity threshold, if there is no working mode of the controller with the reference identifier as the spare identifier that is the same as the working mode corresponding to the i-1th sampling moment, performing a self-test operation for a self-test duration of T on all controllers with the reference identifier as the no-control right identifier, and modifying the reference identifier of the controller that passes the self-test to the spare identifier, and recording various working modes in the working mode corresponding to the controller with the reference identifier as the spare identifier at the i-th sampling moment as different temporary working modes;

[0093] A temporary duration acquisition unit, used to select any one of the temporary working modes as the working mode corresponding to the i-th sampling moment to the i+T-th sampling moment, and use the working mode corresponding to the i-1-th sampling moment as the working mode corresponding to each sampling moment after the i+T-th sampling moment, sequentially acquire the prediction parameter vectors corresponding to each sampling moment starting from the i+T+1-th sampling moment and calculate the third similarity between the prediction parameter vectors corresponding to the i-th sampling moment, and use the duration between the sampling moment corresponding to the first third similarity that is not less than the similarity threshold and the i+T-th sampling moment as the temporary duration corresponding to the current temporary working mode;

[0094] a reset process target controller selection unit, configured to select the shortest temporary duration from the temporary durations corresponding to the respective temporary working modes, use the temporary working mode corresponding to the shortest temporary duration as the intermediate working mode, select a controller whose working mode is the intermediate working mode from the controllers whose reference identifier is the standby identifier at the i-th sampling moment as the third target controller, and select a controller whose working mode is the same as the working mode corresponding to the i-1-th sampling moment from the controllers whose reference identifier is the standby identifier at the i+T-th sampling moment as the fourth target controller;

[0095] A reset execution unit is used to switch the reference identifier of the controller corresponding to the i-1th sampling moment to a no-control right identifier at the i-th sampling moment, and then switch the reference identifier of the third target controller to a control right identifier as the controller corresponding to the i-th sampling moment to the i+T-th sampling moment; after switching the reference identifier of the third target controller to a no-control right identifier at the i+T+1-th sampling moment, the reference identifier of the fourth target controller is switched to a control right identifier as the controller corresponding to each sampling moment within the shortest temporary time after the i+T-th sampling moment.

[0096] Optionally, the fault subdivision processing module 34 further includes:

[0097] A shutdown control unit is used to execute shutdown control if there is no controller whose working mode is the target working mode.

[0098] Optionally, the operation status monitoring module 32 further includes:

[0099] The state parameter prediction model training unit is used to continuously select the actual parameter vectors and working modes corresponding to the set number of sampling moments as training samples, and use the actual parameter vector corresponding to a sampling moment after the last sampling moment among the set number of sampling moments as the label of the training sample, construct multiple different training samples and corresponding labels and input them into the state parameter prediction model to train the state parameter prediction model, so as to obtain the trained state parameter prediction model.

[0100] Optionally, the speed regulation switching control device further includes:

[0101] The threshold limiting module 36 is used to limit the size of the similarity threshold to be inversely proportional to the inconsistency of the actual parameter vectors corresponding to different moments under the normal working condition of the diesel engine in the historical data.

[0102] Optionally, the fault subdivision processing module 34 further includes:

[0103] The working mode determination model training unit is used to use the actual parameter vector under the diesel engine fault condition as a training sample, the controller working mode annotated by an expert as a label of the training sample, and train the working mode determination model with a cross entropy loss function to obtain the trained working mode determination model.

[0104] It should be noted that the information interaction, execution process and other contents between the above modules are based on the same concept as the embodiment of the method of the present invention. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0105] Figure 5 This is a schematic diagram of the structure of a computer device provided in Embodiment 4 of the present invention. Figure 5 As shown, the computer device of this embodiment includes: at least one processor ( Figure 5 Only one is shown in the figure), a memory, and a computer program stored in the memory and executable on at least one processor, wherein when the processor executes the computer program, the steps in any of the above-mentioned health prediction method embodiments are implemented.

[0106] The computer device may include, but is not limited to, a processor, a memory, a network interface, a display screen, and an input device. Those skilled in the art will appreciate that Figure 5 This is merely an example of a computer device and does not constitute a limitation on the computer device. The computer device may include more or fewer components than shown in the figure, or a combination of certain components, or different components.

[0107] The processor may be a CPU, or other general-purpose processors, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0108] The memory includes a readable storage medium, an internal memory, etc., wherein the internal memory may be the memory of a computer device, and the internal memory provides an environment for the operation of the operating system and computer-readable instructions in the readable storage medium. The readable storage medium may be a hard disk of a computer device, and in other embodiments, it may also be an external storage device of the computer device, for example, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the computer device. Further, the memory may also include both an internal storage unit of the computer device and an external storage device. The memory is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of a computer program, etc. The memory may also be used to temporarily store data that has been output or is to be output.

[0109] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention. The specific working process of the units and modules in the above-mentioned device can refer to the corresponding process in the above-mentioned method embodiment, which will not be repeated here. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned method embodiment can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device capable of carrying computer program code, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0110] The present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by a computer program product. When the computer program product runs on a computer device, the computer device can implement the steps in the above-mentioned method embodiment when executing.

[0111] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0112] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0113] In the embodiments provided by the present invention, it should be understood that the disclosed devices / computer equipment and methods can be implemented in other ways. For example, the device / computer equipment embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0114] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0115] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A redundant speed control system speed control switching control method, characterized in that: The method comprises: Acquire various state parameter indicators of the diesel engine at a set sampling interval, use various state parameter indicators of the diesel engine at any sampling moment to form an actual parameter vector corresponding to the said any sampling moment, and use the reference identifier at the said any sampling moment as the control right identifier of the controller, and the working mode of the controller as the working mode corresponding to the said any sampling moment; Input the actual parameter vectors and working modes corresponding to a certain number of sampling moments continuously set before the i-th sampling moment into the trained state parameter prediction model, obtain the prediction parameter vector corresponding to the i-th sampling moment, calculate the first similarity between the prediction parameter vector corresponding to the i-th sampling moment and the actual parameter vector corresponding to the i-th sampling moment, and determine the size relationship between the first similarity and the similarity threshold; If the first similarity is less than the similarity threshold, a controller whose working mode is the same as the working mode corresponding to the i-1th sampling moment and whose reference identifier is a standby identifier is selected as the first target controller, and after the reference identifier of the controller corresponding to the i-1th sampling moment is switched to a no-control right identifier, the reference identifier of the first target controller is switched to a control right identifier as the controller corresponding to the i-th sampling moment; Obtain the prediction parameter vector corresponding to the i+1th sampling moment, calculate the second similarity between the prediction parameter vector corresponding to the i+1th sampling moment and the actual parameter vector corresponding to the i+1th sampling moment, if the second similarity is not less than the similarity threshold, switch the reference identifier of the controller corresponding to the i-1th sampling moment to a fault identifier; if the second similarity is less than the similarity threshold, input the actual parameter vector corresponding to the i+1th sampling moment into the trained working mode determination model to determine the target working mode, select any working mode as the target working mode of the controller, use the controller as the second target controller, switch the reference identifier of the controller corresponding to the i-th sampling moment to a no-control right identifier, and then switch the reference identifier of the second target controller to a control right identifier; After determining the magnitude relationship between the first similarity and the similarity threshold, the method further includes: If the first similarity is not less than the similarity threshold, then ending the current round of controller switching control; After the first similarity is less than the similarity threshold, if there is no working mode of the controller whose reference identifier is the backup identifier that is the same as the working mode corresponding to the i-1th sampling moment, a self-test operation with a self-test duration of T is performed on all controllers whose reference identifier is the no-control authority identifier, and the reference identifier of the controller that passes the self-test is modified to a backup identifier, and various working modes in the working mode corresponding to the controller whose reference identifier is the backup identifier at the i-th sampling moment are respectively recorded as different temporary working modes; Select any one of the temporary working modes as the working mode corresponding to the i-th sampling moment to the i+T-th sampling moment, and use the working mode corresponding to the i-1-th sampling moment as the working mode corresponding to each sampling moment after the i+T-th sampling moment, and sequentially obtain the prediction parameter vectors corresponding to each sampling moment starting from the i+T+1-th sampling moment and calculate the third similarity between the prediction parameter vectors corresponding to the i-th sampling moment, and use the duration between the sampling moment corresponding to the first third similarity that is not less than the similarity threshold and the i+T-th sampling moment as the temporary duration corresponding to the current temporary working mode; Select the shortest temporary duration from the temporary durations corresponding to the temporary working modes, use the temporary working mode corresponding to the shortest temporary duration as the intermediate working mode, select a controller whose working mode is the intermediate working mode from the controllers whose reference identifier is the spare identifier at the i-th sampling moment as the third target controller, and select a controller whose working mode is the same as the working mode corresponding to the i-1-th sampling moment from the controllers whose reference identifier is the spare identifier at the i+T-th sampling moment as the fourth target controller; After the reference identifier of the controller corresponding to the i-1th sampling moment is switched to a no-control authority identifier at the i-th sampling moment, the reference identifier of the third target controller is switched to a control authority identifier as the controller corresponding to the i-th sampling moment to the i+T-th sampling moment; after the reference identifier of the third target controller is switched to a no-control authority identifier at the i+T+1-th sampling moment, the reference identifier of the fourth target controller is switched to a control authority identifier as the controller corresponding to each sampling moment within the shortest temporary time length after the i+T-th sampling moment.

2. The redundant speed regulation system speed regulation switching control method according to claim 1, characterized in that: If there is no controller whose working mode is the target working mode, shutdown control is performed.

3. The redundant speed regulation system speed regulation switching control method according to claim 1, characterized in that: The training method of the state parameter prediction model is: Continuously select the actual parameter vectors and working modes corresponding to a certain number of sampling moments as training samples, and use the actual parameter vector corresponding to a sampling moment after the last sampling moment among the set number of sampling moments as the label of the training sample, construct a plurality of different training samples and corresponding labels and input them into the state parameter prediction model to train the state parameter prediction model, and obtain the trained state parameter prediction model.

4. The redundant speed regulation system speed regulation switching control method according to claim 1, characterized in that: The size of the similarity threshold is inversely proportional to the inconsistency of the actual parameter vectors corresponding to different moments under the normal working condition of the diesel engine in the historical data.

5. The redundant speed regulation system speed regulation switching control method according to claim 1, characterized in that: The training method of the working mode determination model is: The actual parameter vector under the diesel engine fault condition is used as a training sample, the controller working mode annotated by an expert is used as a label of the training sample, and the working mode determination model is trained with a cross entropy loss function to obtain the trained working mode determination model.

6. A redundant speed control system speed control switching control device, characterized in that: The device comprises: A definition module is used to obtain various state parameter indicators of the diesel engine at a set sampling interval, and to form an actual parameter vector corresponding to any sampling moment with various state parameter indicators of the diesel engine at any sampling moment, and to use the reference identifier at any sampling moment as the control right identifier of the controller, and the working mode of the controller as the working mode corresponding to any sampling moment; An operation status monitoring module is used to input the actual parameter vector and the working mode corresponding to a certain number of sampling moments set continuously before the i-th sampling moment into the trained state parameter prediction model, obtain the prediction parameter vector corresponding to the i-th sampling moment, calculate the first similarity between the prediction parameter vector corresponding to the i-th sampling moment and the actual parameter vector corresponding to the i-th sampling moment, and determine the size relationship between the first similarity and the similarity threshold; A standby controller switching module, used for, if the first similarity is less than the similarity threshold, selecting a controller whose working mode is the same as the working mode corresponding to the i-1th sampling moment and whose reference identifier is a standby identifier as the first target controller, switching the reference identifier of the controller corresponding to the i-1th sampling moment to a no-control right identifier, and then switching the reference identifier of the first target controller to a control right identifier as the controller corresponding to the i-th sampling moment; A fault subdivision processing module is used to obtain the prediction parameter vector corresponding to the i+1th sampling moment, calculate the second similarity between the prediction parameter vector corresponding to the i+1th sampling moment and the actual parameter vector corresponding to the i+1th sampling moment, and if the second similarity is not less than the similarity threshold, switch the reference identifier of the controller corresponding to the i-1th sampling moment to a fault identifier; if the second similarity is less than the similarity threshold, input the actual parameter vector corresponding to the i+1th sampling moment into the trained working mode determination model to determine the target working mode, select any working mode as the target working mode of the controller, use the controller as the second target controller, switch the reference identifier of the controller corresponding to the i-th sampling moment to a no-control right identifier, and then switch the reference identifier of the second target controller to a control right identifier; A redundant switching stopping module, configured to terminate the current round of controller switching control if the first similarity is not less than the similarity threshold; a reset operation start judgment unit, used for, after the first similarity is less than the similarity threshold, if there is no working mode of the controller with the reference identifier as the spare identifier that is the same as the working mode corresponding to the i-1th sampling moment, performing a self-test operation for a self-test duration of T on all controllers with the reference identifier as the no-control right identifier, and modifying the reference identifier of the controller that passes the self-test to the spare identifier, and recording various working modes in the working mode corresponding to the controller with the reference identifier as the spare identifier at the i-th sampling moment as different temporary working modes; A temporary duration acquisition unit, used to select any one of the temporary working modes as the working mode corresponding to the i-th sampling moment to the i+T-th sampling moment, and use the working mode corresponding to the i-1-th sampling moment as the working mode corresponding to each sampling moment after the i+T-th sampling moment, sequentially acquire the prediction parameter vectors corresponding to each sampling moment starting from the i+T+1-th sampling moment and calculate the third similarity between the prediction parameter vectors corresponding to the i-th sampling moment, and use the duration between the sampling moment corresponding to the first third similarity that is not less than the similarity threshold and the i+T-th sampling moment as the temporary duration corresponding to the current temporary working mode; a reset process target controller selection unit, configured to select the shortest temporary duration from the temporary durations corresponding to the respective temporary working modes, use the temporary working mode corresponding to the shortest temporary duration as the intermediate working mode, select a controller whose working mode is the intermediate working mode from the controllers whose reference identifier is the standby identifier at the i-th sampling moment as the third target controller, and select a controller whose working mode is the same as the working mode corresponding to the i-1-th sampling moment from the controllers whose reference identifier is the standby identifier at the i+T-th sampling moment as the fourth target controller; A reset execution unit is used to switch the reference identifier of the controller corresponding to the i-1th sampling moment to a no-control right identifier at the i-th sampling moment, and then switch the reference identifier of the third target controller to a control right identifier as the controller corresponding to the i-th sampling moment to the i+T-th sampling moment; after switching the reference identifier of the third target controller to a no-control right identifier at the i+T+1-th sampling moment, the reference identifier of the fourth target controller is switched to a control right identifier as the controller corresponding to each sampling moment within the shortest temporary time after the i+T-th sampling moment.

7. A computer device, characterized in that: The computer device includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the redundant speed regulation system speed switching control method according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the redundant speed regulation system speed regulation switching control method according to any one of claims 1 to 5 is implemented.

Images