A control method and control device for large rotating machinery

Abstract

The present application provides a control method and control device for a large rotating machine. The control method includes: obtaining the disturbance state and operating data corresponding to the large rotating machine at the current moment during the operation of the large rotating machine; wherein the disturbance state includes an external disturbance state and a non-external disturbance state; determining whether the accumulated operating data corresponding to the obtained operating data reaches a preset window value, and based on the judgment result, determining a target fuzzy control model corresponding to the disturbance state; inputting the operating data into the target fuzzy control model corresponding to the disturbance state, and using the target fuzzy control model to perform inference calculations based on the operating data to obtain a target mechanical frequency output by the target fuzzy control model; and controlling a motor provided in the large rotating machine to operate according to the target mechanical frequency. Through the above method, the stability and safety of the operation of the large rotating machine are improved.

Description

Technical Field

[0001] The present application relates to the field of mechanical industrial control technology, and in particular to a control method and a control device for large-scale rotating machinery. Background Art

[0002] In the industrial field, large rotating machinery is affected by external disturbances and is prone to losing its stable state, which affects its normal operating performance and work efficiency and even causes operating accidents. Existing control methods lack sufficient robustness and fault tolerance for large rotating machinery in complex disturbance environments.

[0003] At present, the control methods for large rotating machinery usually adopt methods such as PID control and adaptive control. However, these methods will have problems such as poor anti-interference performance and difficulty in coping with rapidly changing disturbances when controlling large rotating machinery in complex disturbance environments, which reduces the stability of large rotating machinery operation and thus reduces the safety of large rotating machinery. Summary of the Invention

[0004] In view of this, the purpose of the present application is to provide a control method and control device for large-scale rotating machinery, which obtains target fuzzy control models under different disturbance states by performing online parameter update and robustness evaluation on fuzzy control models under different disturbance states, and inputs the operating data of the large-scale rotating machinery into the target fuzzy control model under the current disturbance state, and controls the large-scale rotating machinery to operate according to the target mechanical frequency output by the target fuzzy control model, so that the large-scale rotating machinery can better cope with complex external environmental changes, and improve the anti-interference ability in the external disturbance environment, thereby improving the stability of the operation of the large-scale rotating machinery and thus improving the safety of the large-scale rotating machinery.

[0005] The present invention provides a control method for a large rotating machine, the control method comprising:

[0006] During the operation of the large rotating machinery, obtaining the disturbance state and operation data corresponding to the large rotating machinery at the current moment; wherein the disturbance state includes an external disturbance state and a non-external disturbance state;

[0007] Determining whether the accumulated operating data corresponding to the acquired operating data reaches a preset window amount, and determining a target fuzzy control model corresponding to the disturbance state based on the determination result;

[0008] Inputting the operating data into a target fuzzy control model corresponding to the disturbance state, and performing inference calculation based on the operating data using the target fuzzy control model to obtain a target mechanical frequency output by the target fuzzy control model;

[0009] An electric motor provided in the large rotating machine is controlled to operate according to the target machine frequency.

[0010] Furthermore, when the judgment result is that the accumulated operating data corresponding to the acquired operating data does not reach a preset window amount, determining the target fuzzy control model corresponding to the disturbance state based on the judgment result includes:

[0011] A fuzzy control model corresponding to the disturbance state updated online last time is obtained, and the fuzzy control model is determined as a target fuzzy control model corresponding to the disturbance state.

[0012] Furthermore, when the judgment result is that the accumulated operating data corresponding to the acquired operating data reaches a preset window amount, determining the target fuzzy control model corresponding to the disturbance state based on the judgment result includes:

[0013] Obtaining a fuzzy control model corresponding to the disturbance state updated last time online, and using the accumulated operating data to update model parameters in the fuzzy control model online to obtain an updated fuzzy control model corresponding to the disturbance state;

[0014] The updated fuzzy control model is subjected to a robustness evaluation using the target operating data corresponding to the updated fuzzy control model to obtain a robustness evaluation result. Based on the robustness evaluation result, the updated fuzzy control model corresponding to each of the disturbance states is adjusted to obtain a target fuzzy control model corresponding to the disturbance state.

[0015] Furthermore, when the disturbance state is a state without external disturbance, the online updating of the model parameters in the fuzzy control model using the acquired accumulated operating data to obtain an updated fuzzy control model corresponding to the disturbance state includes:

[0016] inputting first accumulated operating data from the accumulated operating data into a first fuzzy control model corresponding to the state without external disturbance to obtain a first mechanical frequency value output by the first fuzzy control model;

[0017] Based on the first mechanical frequency value and the first preset mechanical frequency value, using the preset first objective function corresponding to the state without external disturbance, determine the first target value corresponding to the first accumulated operating data in the state without external disturbance;

[0018] Determining whether the first target value is less than a preset target value;

[0019] If not, then based on the first target value, update the model parameters in the first fuzzy control model to obtain first model parameters corresponding to the first update period, and replace the model parameters in the first fuzzy control model with the first model parameters to obtain the first fuzzy control model corresponding to the first update period;

[0020] Repeatedly inputting the accumulated operating data into the first fuzzy control model corresponding to each update period, calculating a first target value corresponding to each update period, and updating model parameters in the first fuzzy control model when the first target value is greater than or equal to a preset target value, to obtain first model parameters corresponding to each update period, until the first target value is less than the preset target value;

[0021] When the first target value is less than the preset target value, the first target model parameters corresponding to the current update cycle are determined, and the model parameters in the first fuzzy control model are replaced with the first target model parameters to obtain the first updated fuzzy control model corresponding to the state without external disturbance.

[0022] Furthermore, when the disturbance state is an external disturbance state, the online updating of the model parameters in the fuzzy control model using the operating data to obtain an updated fuzzy control model corresponding to the disturbance state includes:

[0023] inputting first accumulated operating data from the accumulated operating data into a second fuzzy control model corresponding to the external disturbance state to obtain a second mechanical frequency value output by the second fuzzy control model;

[0024] Based on the second mechanical frequency value, the second preset mechanical frequency value, the first target model parameters, and the model parameters in the second fuzzy control model, a second target value corresponding to the first accumulated operating data under the external disturbance state is calculated and determined using a second target function preset corresponding to the external disturbance state;

[0025] Determining whether the second target value is less than a preset target value;

[0026] If not, then based on the second target value, update the model parameters in the second fuzzy control model to obtain second model parameters corresponding to the first update period, and replace the model parameters in the second fuzzy control model with the second model parameters to obtain a second fuzzy control model corresponding to the first update period;

[0027] Repeatedly inputting the accumulated operating data into the second fuzzy control model corresponding to each update period, calculating a second target value corresponding to each update period, and updating model parameters in the second fuzzy control model when the second target value is greater than or equal to a preset target value, to obtain second model parameters corresponding to each update period, until the second target value is less than the preset target value;

[0028] When the second target value is less than the preset target value, the second target model parameters corresponding to the current update cycle are determined, and the model parameters in the second fuzzy control model are replaced with the second target model parameters to obtain a second updated fuzzy control model corresponding to the external disturbance state.

[0029] Furthermore, the robustness evaluation of the updated fuzzy control model is performed using the target operating data corresponding to the updated fuzzy control model to obtain a robustness evaluation result, including:

[0030] inputting the target operating data corresponding to the obtained updated fuzzy control model into a first updated fuzzy control model corresponding to the no external disturbance state and a second updated fuzzy control model corresponding to the external disturbance state, respectively, to obtain a first estimated mechanical frequency value output by the first updated fuzzy control model and a second estimated mechanical frequency value output by the second updated fuzzy control model;

[0031] Determining an objective function value by using a preset objective function calculation based on a first objective model parameter in the first updated fuzzy control model, a second objective model parameter in the second updated fuzzy control model, the first evaluated mechanical frequency value, and the second evaluated mechanical frequency value;

[0032] Based on the first evaluated mechanical frequency value, the second evaluated mechanical frequency value, the first target model parameter, the second target model parameter, and the objective function value, a preset response evaluation function is used to calculate and determine a response characteristic result in the robustness evaluation result corresponding to the updated fuzzy control model;

[0033] determining, based on the first evaluated mechanical frequency value, the second evaluated mechanical frequency value, and the target operating data, a first mechanical frequency change rate corresponding to the first evaluated mechanical frequency value and a second mechanical frequency change rate corresponding to the second evaluated mechanical frequency value using the first updated fuzzy control model and the second updated fuzzy control model, respectively;

[0034] Based on the first mechanical frequency change rate, the second mechanical frequency change rate, the first target model parameter, the second target model parameter and the objective function value, a preset fluctuation evaluation function is used to calculate and determine the fluctuation characteristic result in the robustness evaluation result corresponding to the updated fuzzy control model.

[0035] Furthermore, the step of inputting the operating data into a target fuzzy control model corresponding to the disturbance state, and performing inference calculation based on the operating data using the target fuzzy control model to obtain a target mechanical frequency output by the target fuzzy control model includes:

[0036] Inputting the operating data into an input layer of a target fuzzy control model corresponding to the disturbance state to obtain an input vector output by the input layer;

[0037] Inputting the input vector into the radial basis layer set in the target fuzzy control model, performing fuzzy processing on the input vector using the radial basis layer, and obtaining a radial basis output vector output by the radial basis layer;

[0038] Inputting the radial basis output vector into a normalization layer set in the target fuzzy control model, and performing normalization processing on the radial basis output vector by using the normalization layer to obtain a normalized output vector output by the normalization layer;

[0039] Inputting the normalized output vector into the output layer of the target fuzzy control model to obtain the mechanical frequency change output by the output layer;

[0040] A historical target mechanical frequency corresponding to the large rotating machine at a previous moment is obtained, and the sum of the historical target mechanical frequency and the mechanical frequency variation is determined as the target mechanical frequency output by the target fuzzy control model.

[0041] The present application also provides a control device for a large rotating machine, the control device comprising:

[0042] A data acquisition module is used to acquire the disturbance state and operation data corresponding to the large rotating machinery at the current moment during the operation of the large rotating machinery; wherein the disturbance state includes an external disturbance state and a non-external disturbance state;

[0043] a parameter updating module, configured to determine whether the accumulated operating data corresponding to the acquired operating data reaches a preset window amount, and based on the determination result, determine a target fuzzy control model corresponding to the disturbance state;

[0044] a model inference module, configured to input the operating data into a target fuzzy control model corresponding to the disturbance state, and perform inference calculations based on the operating data using the target fuzzy control model to obtain a target mechanical frequency output by the target fuzzy control model;

[0045] The mechanical control module is used to control the motor provided in the large rotating machine to operate according to the target mechanical frequency.

[0046] Furthermore, when the judgment result is that the accumulated operating data corresponding to the acquired operating data does not reach a preset window amount, the parameter updating module is used to determine the target fuzzy control model corresponding to the disturbance state based on the judgment result, and the parameter updating module is used to:

[0047] A fuzzy control model corresponding to the disturbance state updated online last time is obtained, and the fuzzy control model is determined as a target fuzzy control model corresponding to the disturbance state.

[0048] Furthermore, when the judgment result is that the accumulated operating data corresponding to the acquired operating data reaches a preset window amount, the parameter updating module is used to determine the target fuzzy control model corresponding to the disturbance state based on the judgment result, and the parameter updating module is used to:

[0049] Obtaining a fuzzy control model corresponding to the disturbance state updated last time online, and using the accumulated operating data to update model parameters in the fuzzy control model online to obtain an updated fuzzy control model corresponding to the disturbance state;

[0050] The updated fuzzy control model is subjected to a robustness evaluation using the target operating data corresponding to the updated fuzzy control model to obtain a robustness evaluation result. Based on the robustness evaluation result, the updated fuzzy control model corresponding to each of the disturbance states is adjusted to obtain a target fuzzy control model corresponding to the disturbance state.

[0051] Furthermore, when the disturbance state is a state without external disturbance, the parameter updating module is used to update the model parameters in the fuzzy control model online using the acquired accumulated operating data to obtain an updated fuzzy control model corresponding to the disturbance state, and the parameter updating module is used to:

[0052] inputting first accumulated operating data from the accumulated operating data into a first fuzzy control model corresponding to the state without external disturbance to obtain a first mechanical frequency value output by the first fuzzy control model;

[0053] Based on the first mechanical frequency value and the first preset mechanical frequency value, using the preset first objective function corresponding to the state without external disturbance, determine the first target value corresponding to the first accumulated operating data in the state without external disturbance;

[0054] Determining whether the first target value is less than a preset target value;

[0055] If not, then based on the first target value, update the model parameters in the first fuzzy control model to obtain first model parameters corresponding to the first update period, and replace the model parameters in the first fuzzy control model with the first model parameters to obtain the first fuzzy control model corresponding to the first update period;

[0056] Repeatedly inputting the accumulated operating data into the first fuzzy control model corresponding to each update period, calculating a first target value corresponding to each update period, and updating model parameters in the first fuzzy control model when the first target value is greater than or equal to a preset target value, to obtain first model parameters corresponding to each update period, until the first target value is less than the preset target value;

[0057] When the first target value is less than the preset target value, the first target model parameters corresponding to the current update cycle are determined, and the model parameters in the first fuzzy control model are replaced with the first target model parameters to obtain the first updated fuzzy control model corresponding to the state without external disturbance.

[0058] Furthermore, when the disturbance state is an external disturbance state, the parameter updating module is used to update the model parameters in the fuzzy control model online using the operating data to obtain an updated fuzzy control model corresponding to the disturbance state, and the parameter updating module is used to:

[0059] inputting first accumulated operating data from the accumulated operating data into a second fuzzy control model corresponding to the external disturbance state to obtain a second mechanical frequency value output by the second fuzzy control model;

[0060] Based on the second mechanical frequency value, the second preset mechanical frequency value, the first target model parameters, and the model parameters in the second fuzzy control model, a second target value corresponding to the first accumulated operating data under the external disturbance state is calculated and determined using a second target function preset corresponding to the external disturbance state;

[0061] Determining whether the second target value is less than a preset target value;

[0062] If not, then based on the second target value, update the model parameters in the second fuzzy control model to obtain second model parameters corresponding to the first update period, and replace the model parameters in the second fuzzy control model with the second model parameters to obtain a second fuzzy control model corresponding to the first update period;

[0063] Repeatedly inputting the accumulated operating data into the second fuzzy control model corresponding to each update period, calculating a second target value corresponding to each update period, and updating model parameters in the second fuzzy control model when the second target value is greater than or equal to a preset target value, to obtain second model parameters corresponding to each update period, until the second target value is less than the preset target value;

[0064] When the second target value is less than the preset target value, the second target model parameters corresponding to the current update cycle are determined, and the model parameters in the second fuzzy control model are replaced with the second target model parameters to obtain a second updated fuzzy control model corresponding to the external disturbance state.

[0065] Furthermore, the parameter updating module is used to perform a robustness evaluation on the updated fuzzy control model using the target operating data corresponding to the updated fuzzy control model. When the robustness evaluation result is obtained, the parameter updating module is used to:

[0066] inputting the target operating data corresponding to the obtained updated fuzzy control model into a first updated fuzzy control model corresponding to the no external disturbance state and a second updated fuzzy control model corresponding to the external disturbance state, respectively, to obtain a first estimated mechanical frequency value output by the first updated fuzzy control model and a second estimated mechanical frequency value output by the second updated fuzzy control model;

[0067] Determining an objective function value by using a preset objective function calculation based on a first objective model parameter in the first updated fuzzy control model, a second objective model parameter in the second updated fuzzy control model, the first evaluated mechanical frequency value, and the second evaluated mechanical frequency value;

[0068] Based on the first evaluated mechanical frequency value, the second evaluated mechanical frequency value, the first target model parameter, the second target model parameter, and the objective function value, a preset response evaluation function is used to calculate and determine a response characteristic result in the robustness evaluation result corresponding to the updated fuzzy control model;

[0069] determining, based on the first evaluated mechanical frequency value, the second evaluated mechanical frequency value, and the target operating data, a first mechanical frequency change rate corresponding to the first evaluated mechanical frequency value and a second mechanical frequency change rate corresponding to the second evaluated mechanical frequency value using the first updated fuzzy control model and the second updated fuzzy control model, respectively;

[0070] Based on the first mechanical frequency change rate, the second mechanical frequency change rate, the first target model parameter, the second target model parameter and the objective function value, a preset fluctuation evaluation function is used to calculate and determine the fluctuation characteristic result in the robustness evaluation result corresponding to the updated fuzzy control model.

[0071] Furthermore, when the model inference module is used to input the operating data into the target fuzzy control model corresponding to the disturbance state, and use the target fuzzy control model to perform inference calculation based on the operating data to obtain the target mechanical frequency output by the target fuzzy control model, the model inference module is used to:

[0072] Inputting the operating data into an input layer of a target fuzzy control model corresponding to the disturbance state to obtain an input vector output by the input layer;

[0073] Inputting the input vector into the radial basis layer set in the target fuzzy control model, performing fuzzy processing on the input vector using the radial basis layer, and obtaining a radial basis output vector output by the radial basis layer;

[0074] Inputting the radial basis output vector into a normalization layer set in the target fuzzy control model, and performing normalization processing on the radial basis output vector by using the normalization layer to obtain a normalized output vector output by the normalization layer;

[0075] Inputting the normalized output vector into the output layer of the target fuzzy control model to obtain the mechanical frequency change output by the output layer;

[0076] A historical target mechanical frequency corresponding to the large rotating machine at a previous moment is obtained, and the sum of the historical target mechanical frequency and the mechanical frequency variation is determined as the target mechanical frequency output by the target fuzzy control model.

[0077] An embodiment of the present application also provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the steps of the control method for large rotating machinery as described above are performed.

[0078] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the control method for a large rotating machine as described above are executed.

[0079] The embodiments of the present application provide a control method and device for large-scale rotating machinery, the control method comprising: during the operation of the large-scale rotating machinery, obtaining the disturbance state and operation data corresponding to the large-scale rotating machinery at the current moment; wherein the disturbance state includes an external disturbance state and a state without external disturbance; judging whether the accumulated operation data corresponding to the obtained operation data reaches a preset window amount, and determining a target fuzzy control model corresponding to the disturbance state based on the judgment result; inputting the operation data into a target fuzzy control model corresponding to the disturbance state, and using the target fuzzy control model to perform inference calculation based on the operation data to obtain a target mechanical frequency output by the target fuzzy control model; and controlling the motor provided in the large-scale rotating machinery to operate according to the target mechanical frequency.

[0080] Compared with the methods such as PID control and adaptive control in the existing technology, the target fuzzy control model under different disturbance states is obtained by performing online parameter update and robustness evaluation on the fuzzy control model under different disturbance states, and the operation data of the large rotating machinery is input into the target fuzzy control model under the current disturbance state, so that the large rotating machinery is controlled to operate according to the target mechanical frequency output by the target fuzzy control model, so that the large rotating machinery can better cope with complex external environmental changes, improve the anti-interference ability in the external disturbance environment, improve the stability of the operation of the large rotating machinery, and thus improve the safety of the large rotating machinery.

[0081] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0083] Figure 1 A flow chart of a control method for a large rotating machine provided in an embodiment of the present application;

[0084] Figure 2 A schematic structural diagram of a control device for a large rotating machine provided in an embodiment of the present application;

[0085] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0086] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application for which protection is claimed, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, each other embodiment obtained by those skilled in the art without making creative work falls within the scope of protection of the present application.

[0087] Research has found that at present, the control methods for large rotating machinery usually adopt methods such as PID control and adaptive control. However, these methods will have problems such as poor anti-interference performance and difficulty in coping with rapidly changing disturbances when controlling large rotating machinery in complex disturbance environments, which reduces the stability of large rotating machinery operation and thus reduces the safety of large rotating machinery.

[0088] Among them, in the method of controlling large rotating machinery based on PID, the output signal of the large rotating machinery is adjusted by the three control parameters of proportion, integration and differentiation, so as to realize the control of the large rotating machinery. However, due to the limited adaptability of PID control to complex disturbance environments, it may not be able to maintain a stable control state under strong external disturbances. In addition, manual adjustment of parameters may also lead to unstable performance of large rotating machinery.

[0089] In addition, the adaptive control method of large rotating machinery improves the robustness of the system by continuously adjusting the parameters of the controller to adapt to changes in external disturbances. However, when faced with nonlinear and uncertain large rotating machinery systems, the adaptive control method will reduce the stability and convergence of the control.

[0090] Based on this, an embodiment of the present application provides a control method for large rotating machinery. By performing online parameter update and robustness evaluation on the fuzzy control model under different disturbance states, the target fuzzy control model under different disturbance states is obtained, and the operation data of the large rotating machinery is input into the target fuzzy control model under the current disturbance state. The large rotating machinery is controlled to operate according to the target mechanical frequency output by the target fuzzy control model, so that the large rotating machinery can better cope with complex external environmental changes, and improve the anti-interference ability in the external disturbance environment, thereby improving the stability of the operation of the large rotating machinery and thus improving the safety of the large rotating machinery.

[0091] See also Figure 1 , Figure 1 This is a flow chart of a control method for a large rotating machine provided in an embodiment of the present application. Figure 1 As shown in , the control method of a large rotating machinery provided by the embodiment of the present application includes:

[0092] S100 . During the operation of a large rotating machine, obtain a disturbance state and operation data corresponding to the large rotating machine at a current moment.

[0093] It should be noted that large rotating machinery refers to large equipment that plays a key role in industrial applications and contains major rotating parts. It is used in multiple industries, including but not limited to energy, manufacturing, mining and chemical industries. For example, large rotating machinery may include steam turbines, gas turbines, water turbines, wind turbines, rolling mills and centrifuges.

[0094] The disturbance state includes an external disturbance state and a non-external disturbance state.

[0095] Here, the external disturbance state indicates that the environment in which the large rotating machine is located interferes with the operation of the large rotating machine, and the non-external disturbance state indicates that the environment in which the large rotating machine is located does not affect the operation of the large rotating machine.

[0096] In this step, during specific implementation, first, environmental data corresponding to the environment in which the large rotating machinery is located is collected using environmental sensors installed on the large rotating machinery; then, based on the environmental data, the disturbance state corresponding to the large rotating machinery at the current moment is determined; finally, the operating data corresponding to the large rotating machinery at the current moment is obtained.

[0097] In an embodiment of the present application, the environmental data includes at least air flow velocity value, vibration frequency value and ambient temperature value, etc.; the operating data includes at least mechanical rotation wind speed value, actual mechanical frequency value and actual mechanical frequency deviation value, etc.

[0098] The actual mechanical frequency deviation value is the difference between a preset expected frequency value and an actual mechanical frequency value.

[0099] S200: Determine whether the accumulated operating data corresponding to the acquired operating data reaches a preset window amount, and determine a target fuzzy control model corresponding to the disturbance state based on the determination result.

[0100] In this step, the cumulative data volume of the operating data corresponding to the large rotating machinery obtained at the current moment is determined, that is, the data volume corresponding to the cumulative operating data corresponding to the obtained operating data is determined, and it is judged whether the data volume corresponding to the cumulative operating data corresponding to the obtained operating data reaches the preset window volume to obtain a judgment result.

[0101] In the embodiment of the present application, the preset window amount can be specifically calibrated according to the model architecture parameters of the fuzzy control model corresponding to each disturbance state and the actual control requirements.

[0102] Furthermore, based on a determination result of whether the data volume corresponding to the accumulated operating data corresponding to the acquired operating data reaches a preset window volume, a target fuzzy control model corresponding to the disturbance state is determined.

[0103] In an embodiment of the present application, each disturbance state corresponds to a fuzzy control model, and the fuzzy control model can be updated online during the process of controlling large rotating machinery. When the corresponding conditions are met during the update of the fuzzy control model, the target fuzzy control model corresponding to each disturbance state is obtained, so as to use the target fuzzy control model to predict the target mechanical frequency of the large rotating machinery.

[0104] Here, the fuzzy control model may include a neural network model that combines a fuzzy neural network with a radial basis function network. The fuzzy control model combines the computational intelligence technology of the fuzzy logic system and the neural network model, and is intended to utilize the ability of fuzzy logic to process uncertainty and imprecise information, as well as the advantages of neural networks in pattern recognition, learning and adaptation. The fuzzy control model can handle complex, nonlinear mapping problems, and performs well in processing data with uncertainty or ambiguity.

[0105] The state without external disturbance corresponds to the first fuzzy control model and the first target fuzzy control model; the state with external disturbance corresponds to the second fuzzy control model and the second target fuzzy control model.

[0106] In one embodiment of the present application, in a specific implementation, when the judgment result is that the accumulated operating data corresponding to the acquired operating data does not reach a preset window amount, the step of determining the target fuzzy control model corresponding to the disturbance state based on the judgment result in step S200 may include:

[0107] S211 , obtaining a fuzzy control model corresponding to the disturbance state updated online last time, and determining the fuzzy control model as a target fuzzy control model corresponding to the disturbance state.

[0108] In this step, when the judgment result is that the cumulative operating data corresponding to the acquired operating data does not reach the preset window amount, it means that the current cumulative amount of operating data is insufficient to update the fuzzy control model online, and the fuzzy control model corresponding to the disturbance state last updated online is determined as the target fuzzy control model corresponding to the disturbance state, that is, there is no need to update the model parameters of the fuzzy control model online.

[0109] In one embodiment of the present application, in a specific implementation, when the judgment result is that the accumulated operating data corresponding to the acquired operating data reaches a preset window amount, the step of determining the target fuzzy control model corresponding to the disturbance state based on the judgment result in step S200 may include:

[0110] S221. Obtain the fuzzy control model corresponding to the disturbance state updated online last time, and use the accumulated operation data to update the model parameters in the fuzzy control model online to obtain an updated fuzzy control model corresponding to the disturbance state.

[0111] In this step, based on the characteristics of large rotating machinery being susceptible to external interference, an objective function for controlling the robustness of the mechanical frequency in the large rotating machinery is preset, and the model parameters in the fuzzy control model are updated online using the adaptive gradient descent method.

[0112] In an embodiment of the present application, an adaptive gradient descent algorithm is used to dynamically update the model parameters in the fuzzy control model, thereby improving the learning ability and computational efficiency of the fuzzy control model. By optimizing the learning rate of the fuzzy control model, the fuzzy control model can adapt to changes in large rotating machinery more quickly, thereby improving the operational stability of controlling large rotating machinery.

[0113] In one embodiment of the present application, in a specific implementation, when the disturbance state is a state without external disturbance, the step of using the accumulated operating data to update the model parameters in the fuzzy control model online in step S221 to obtain the updated fuzzy control model corresponding to the disturbance state may include:

[0114] S22111. Input first accumulated operating data in the accumulated operating data into a first fuzzy control model corresponding to the state without external disturbance, to obtain a first mechanical frequency value output by the first fuzzy control model.

[0115] In an embodiment of the present application, the fuzzy control model includes an input layer, a radial base layer, a normalization layer and an output layer.

[0116] In this step, the first accumulated operating data corresponding to the first moment in the time sequence is screened out from the accumulated operating data, and the first accumulated operating data is input into the first fuzzy control model corresponding to the state without external disturbance; then, the first mechanical frequency value output by the first fuzzy control model based on the first accumulated operating data is obtained by calculating the input layer, radial base layer, normalization layer and output layer of the first fuzzy control model.

[0117] S22112. Based on the first mechanical frequency value and the first preset mechanical frequency value, a first target value corresponding to the state without external disturbance is calculated using a preset first objective function corresponding to the state without external disturbance.

[0118] In an embodiment of the present application, the expression of the preset first objective function corresponding to the state without external disturbance is as follows.

[0119] .

[0120] in, Indicates the first target value corresponding to the state without external disturbance; Indicates the first mechanical frequency value; Indicates the first preset mechanical frequency value.

[0121] S22113. Determine whether the first target value is less than a preset target value.

[0122] In the embodiment of the present application, the preset target value can generally be specifically calibrated according to the convergence requirements of the objective function of the online update model parameters, and is generally set to 0.01, but can also be set to other values, which are not further limited in this application.

[0123] S22114. If not, then based on the first target value, the model parameters in the first fuzzy control model are updated and calculated to obtain the first model parameters corresponding to the first update period, and the model parameters in the first fuzzy control model are replaced with the first model parameters to obtain the first fuzzy control model corresponding to the first update period.

[0124] In this step, when the first target value is greater than or equal to the preset target value, the model parameters in the first fuzzy control model are updated and calculated using the preset update formula to obtain the first model parameters corresponding to the first update cycle that characterizes this online update; then, the model parameters in the first fuzzy control model are replaced with the first model parameters to obtain the first fuzzy control model corresponding to the first update cycle.

[0125] The model parameters in the fuzzy control model at least include the center value and width value corresponding to the input neuron and the radial basis neuron, and the output weight corresponding to the normalized neuron.

[0126] In an embodiment of the present application, the expression of the update formula for performing update calculation on the model parameters in the first fuzzy control model is as follows.

[0127] .

[0128] .

[0129] .

[0130] in, represents the center value corresponding to the input neuron and the radial basis neuron in the first model parameter; Represents the width values ​​corresponding to the input neurons and radial basis neurons in the first model parameter; represents the output weight corresponding to the normalized neuron in the first model parameter; Represents the central value of the input neuron and the radial basis neuron in the model parameters; Represents the width value corresponding to the input neuron and radial basis neuron in the model parameters; Represents the output weights corresponding to the normalized neurons in the model parameters; Indicates the first target value corresponding to the state without external disturbance; express right The partial derivative of express right The partial derivative of express right The partial derivative of .

[0131] S22115. Repeatedly input the accumulated operating data into the first fuzzy control model corresponding to each update cycle, calculate the first target value corresponding to each update cycle, and when the first target value is greater than or equal to the preset target value, update the model parameters in the first fuzzy control model to obtain the first model parameters corresponding to each update cycle, until the first target value is less than the preset target value.

[0132] In this step, after obtaining the first fuzzy control model corresponding to the first update cycle, the second cumulative operating data corresponding to the second moment in the time sequence in the cumulative operating data is input into the first fuzzy control model corresponding to the first update cycle, and the first target value corresponding to the next update cycle is calculated, and it is determined whether the first target value is less than the preset target value. When the first target value is greater than or equal to the preset target value, the model parameters in the first fuzzy control model are updated.

[0133] Furthermore, when the first target value is greater than or equal to the preset target value, the model parameters in the first fuzzy control model are repeatedly updated and the accumulated operating data is input into the first fuzzy control model corresponding to each update cycle until the first target value is less than the preset target value.

[0134] S22116. When the first target value is less than the preset target value, determine the first target model parameters corresponding to the current update cycle, and replace the model parameters in the first fuzzy control model with the first target model parameters to obtain the first updated fuzzy control model corresponding to the state without external disturbance.

[0135] In this step, when the first target value corresponding to the target update cycle is less than the preset target value, the first target model parameters corresponding to the updated target update cycle (current update cycle) are determined; then, the model parameters in the first fuzzy control model are replaced with the first target model parameters to obtain the first updated fuzzy control model corresponding to the state without external disturbance.

[0136] In one embodiment of the present application, in a specific implementation, when the disturbance state is an external disturbance state, the step of using the accumulated operating data to update the model parameters in the fuzzy control model online in step S221 to obtain an updated fuzzy control model corresponding to the disturbance state may include:

[0137] S22121. Input first accumulated operating data in the accumulated operating data into a second fuzzy control model corresponding to the external disturbance state to obtain a second mechanical frequency value output by the second fuzzy control model.

[0138] In this step, the first accumulated operating data corresponding to the first moment in the time sequence is screened out from the accumulated operating data, and the first accumulated operating data is input into the second fuzzy control model corresponding to the external disturbance state; then, the second mechanical frequency value output by the second fuzzy control model based on the first accumulated operating data is obtained by calculating the input layer, radial base layer, normalization layer and output layer of the second fuzzy control model.

[0139] S22122. Based on the second mechanical frequency value, the second preset mechanical frequency value, the first target model parameters and the model parameters in the second fuzzy control model, the second target value corresponding to the first accumulated operating data under the external disturbance state is determined by calculating the preset second objective function corresponding to the external disturbance state.

[0140] In an embodiment of the present application, the expression of the preset second objective function corresponding to the external disturbance state is as follows.

[0141] .

[0142] in, Indicates the second target value corresponding to the external disturbance state; Indicates the second mechanical frequency value; Indicates the second preset mechanical frequency value; represents the first target model parameter in the first fuzzy control model; represents the model parameters in the second fuzzy control model; Represents the factorial function.

[0143] S22123. Determine whether the second target value is less than a preset target value.

[0144] S22124. If not, then based on the second target value, the model parameters in the second fuzzy control model are updated and calculated to obtain the second model parameters corresponding to the first update period, and the model parameters in the second fuzzy control model are replaced with the second model parameters to obtain the second fuzzy control model corresponding to the first update period.

[0145] S22125. Repeatedly input the accumulated operating data into the second fuzzy control model corresponding to each update cycle, calculate the second target value corresponding to each update cycle, and when the second target value is greater than or equal to the preset target value, update the model parameters in the second fuzzy control model to obtain the second model parameters corresponding to each update cycle, until the second target value is less than the preset target value.

[0146] S22126. When the second target value is less than the preset target value, determine the second target model parameters corresponding to the current update cycle, and replace the model parameters in the second fuzzy control model with the second target model parameters to obtain a second updated fuzzy control model corresponding to the external disturbance state.

[0147] Among them, the description of S22123 to S22126 can refer to the description of S22113 to S22116, and can achieve the same technical effect, so it will not be repeated here.

[0148] S222. Perform a robustness evaluation on the updated fuzzy control model using the target operating data corresponding to the updated fuzzy control model to obtain a robustness evaluation result, and adjust the updated fuzzy control model corresponding to each of the disturbance states based on the robustness evaluation result to obtain a target fuzzy control model corresponding to the disturbance state.

[0149] In an embodiment of the present application, a robustness evaluation strategy is used to analyze and evaluate the dynamic characteristics of the updated fuzzy control model, thereby enhancing the anti-interference ability of large rotating machinery, so that when controlling large rotating machinery, it can better cope with complex external environmental changes and improve the operating stability of large rotating machinery.

[0150] In one embodiment of the present application, in a specific implementation, in step S222, the robustness evaluation of the updated fuzzy control model is performed using the target operating data corresponding to the updated fuzzy control model. The step of obtaining the robustness evaluation result may include:

[0151] S2221. The target operating data corresponding to the updated fuzzy control model is input into the first updated fuzzy control model corresponding to the state without external disturbance and the second updated fuzzy control model corresponding to the state with external disturbance, respectively, to obtain the first evaluated mechanical frequency value output by the first updated fuzzy control model and the second evaluated mechanical frequency value output by the second updated fuzzy control model.

[0152] In this step, during specific implementation, first, when obtaining the updated fuzzy control model, determine the first target operating data input to the first updated fuzzy control model corresponding to the state without external disturbance and making the target value less than the preset target value, and determine the second target operating data input to the second updated fuzzy control model corresponding to the state with external disturbance and making the target value less than the preset target value; then, respectively input the first target operating data and the second target operating data into the first updated fuzzy control model and the second updated fuzzy control model; finally, obtain the first evaluated mechanical frequency value output by the first updated fuzzy control model and the second evaluated mechanical frequency value output by the second updated fuzzy control model.

[0153] S2222. Based on the first target model parameter in the first updated fuzzy control model, the second target model parameter in the second updated fuzzy control model, the first evaluated mechanical frequency value, and the second evaluated mechanical frequency value, determine the target function value using a preset target function calculation.

[0154] In this step, during specific implementation, first, based on the first evaluated mechanical frequency value and the first preset mechanical frequency value, the first objective function value corresponding to the first updated fuzzy control model is determined by using the first objective function calculation; then, based on the second evaluated mechanical frequency value, the second preset mechanical frequency value, the first objective model parameters and the second model parameters, the second objective function value corresponding to the second updated fuzzy control model is determined by using the second objective function calculation; finally, the first objective function value and the second objective function value are integrated into the objective function value.

[0155] In the embodiment of the present application, the expression of the objective function value is as follows.

[0156] ∈( , ).

[0157] in, represents the objective function value; represents the first objective function value; Represents the value of the second objective function.

[0158] S2223. Based on the first evaluated mechanical frequency value, the second evaluated mechanical frequency value, the first target model parameter, the second target model parameter and the objective function value, a preset response evaluation function is used to calculate and determine the response characteristic result in the robustness evaluation result corresponding to the updated fuzzy control model.

[0159] In the embodiment of the present application, the expression of the response evaluation function is as follows.

[0160] .

[0161] in, Indicates the response characteristic results in the robustness evaluation results; represents the first evaluation mechanical frequency value; represents the second evaluation mechanical frequency value; represents the objective function value; represents a parameter matrix consisting of the first target model parameters and the second target model parameters; e is a natural constant.

[0162] S2224. Based on the first evaluated mechanical frequency value, the second evaluated mechanical frequency value and the target operating data, the first updated fuzzy control model and the second updated fuzzy control model are used to respectively determine the first mechanical frequency change rate corresponding to the first evaluated mechanical frequency value and the second mechanical frequency change rate corresponding to the second evaluated mechanical frequency value.

[0163] In this step, based on the first evaluated mechanical frequency value and the target operating data, a first updated fuzzy control model is used to determine the first mechanical frequency change rate corresponding to the first evaluated mechanical frequency value; then, based on the second evaluated mechanical frequency value and the target operating data, a second updated fuzzy control model is used to determine the second mechanical frequency change rate corresponding to the second evaluated mechanical frequency value.

[0164] S2225. Based on the first mechanical frequency change rate, the second mechanical frequency change rate, the first target model parameter, the second target model parameter and the objective function value, a preset fluctuation evaluation function is used to calculate and determine the fluctuation characteristic result in the robustness evaluation result corresponding to the updated fuzzy control model.

[0165] In the embodiment of the application, the expression of the fluctuation evaluation function is as follows.

[0166] .

[0167] in, Indicates the fluctuation characteristics of the robustness evaluation results; Indicates the rate of change of the first mechanical frequency; Indicates the rate of change of the second mechanical frequency; represents the objective function value; Represents a parameter matrix consisting of the first target model parameters and the second target model parameters.

[0168] S300: Input the operating data into a target fuzzy control model corresponding to the disturbance state, and use the target fuzzy control model to perform inference calculation based on the operating data to obtain a target mechanical frequency output by the target fuzzy control model.

[0169] It should be noted that the first target fuzzy control model corresponding to the state without external disturbance and the second target fuzzy control model corresponding to the state with external disturbance both include the same fuzzy control neural network architecture. The training data used by the first target fuzzy control model and the second target fuzzy control model during the training process have differences in representing whether there is external interference, which makes the model parameters of the first target fuzzy control model and the model parameters of the second target fuzzy control model different. The first target fuzzy control model and the second target fuzzy control model perform corresponding inference calculations for the state without external disturbance and the state with external disturbance respectively.

[0170] In an embodiment of the present application, based on the target fuzzy control model corresponding to each disturbance state, the target mechanical frequency is calculated through the variables in the dynamic reasoning model to ensure the safety and stability of the operation of large-scale rotating machinery, so that large-scale rotating machinery can more flexibly cope with unstable working environments and achieve efficient control of large-scale rotating machinery.

[0171] In one embodiment of the present application, during specific implementation, step S300 may include:

[0172] S301 , inputting the operating data into an input layer of a target fuzzy control model corresponding to the disturbance state, and obtaining an input vector output by the input layer.

[0173] In this step, the mechanical rotation wind speed value and the actual mechanical frequency deviation value included in the operating data are input into the input layer of the target fuzzy control model corresponding to the acquired disturbance state to obtain an input vector output by the input layer.

[0174] In an embodiment of the present application, the expression of the input vector output by the input layer in the target fuzzy control model corresponding to the state without external disturbance is as follows.

[0175]

[0176] in, The input vector representing the output of the input layer in the target fuzzy control model corresponding to the state without external disturbance at the current moment; Indicates the mechanical rotation wind speed value corresponding to the state without external disturbance at the current moment; Indicates the actual mechanical frequency deviation value corresponding to the state without external disturbance at the current moment.

[0177] In an embodiment of the present application, the expression of the input vector output by the input layer in the target fuzzy control model corresponding to the external disturbance state is as follows.

[0178] .

[0179] in, The input vector representing the output of the input layer in the target fuzzy control model corresponding to the external disturbance state at the current moment; Indicates the mechanical rotation wind speed value corresponding to the external disturbance state at the current moment; Indicates the actual mechanical frequency deviation value corresponding to the external disturbance state at the current moment.

[0180] S302: Input the input vector into the radial basis layer set in the target fuzzy control model, and use the radial basis layer to perform fuzzy processing on the input vector to obtain a radial basis output vector output by the radial basis layer.

[0181] The radial base layer includes a plurality of radial basis neurons. For example, the number of radial basis neurons can be any positive integer selected from [5, 10].

[0182] In the embodiment of the present application, the expression of the radial basis output vector of the radial basis output in the target fuzzy control model corresponding to the state without external disturbance is as follows.

[0183] 。

[0184] in, The radial basis output value of each radial basis neuron in the radial basis layer in the target fuzzy control model corresponding to the state without external disturbance is represented, and the radial basis output vector of the radial basis layer in the target fuzzy control model corresponding to the state without external disturbance can be determined; Indicates the operating data corresponding to the state without external disturbance at the current moment; Indicates the first target fuzzy control model corresponding to the state without external disturbance input neurons and the The corresponding center value between radial basis neurons; Indicates the first target fuzzy control model corresponding to the state without external disturbance input neurons and the The corresponding width value between radial basis neurons; k It represents the number of input neurons in the input layer of the target fuzzy control model corresponding to the state without external disturbance.

[0185] In the embodiment of the present application, the expression of the radial basis output vector of the radial basis output in the target fuzzy control model corresponding to the external disturbance state is as follows.

[0186]

[0187] in, The radial basis output value of each radial basis neuron in the radial basis layer in the target fuzzy control model corresponding to the external disturbance state can be used to determine the radial basis output vector of the radial basis layer in the target fuzzy control model corresponding to the external disturbance state; Indicates the operating data corresponding to the external disturbance state at the current moment; Indicates the first target fuzzy control model corresponding to the external disturbance state input neurons and the The corresponding center value between radial basis neurons; Indicates the first target fuzzy control model corresponding to the external disturbance state input neurons and the The width value corresponding to each radial basis neuron.

[0188] S303: Input the radial basis output vector into a normalization layer set in the target fuzzy control model, and use the normalization layer to normalize the radial basis output vector to obtain a normalized output vector output by the normalization layer.

[0189] Among them, the normalization layer includes multiple normalization neurons.

[0190] In an embodiment of the present application, the expression of the normalized output vector output by the normalization layer in the target fuzzy control model corresponding to the state without external disturbance is as follows.

[0191] .

[0192] in, The normalized output value of each normalized neuron in the normalized layer in the target fuzzy control model corresponding to the state without external disturbance is represented, and the normalized output vector of the normalized layer in the target fuzzy control model corresponding to the state without external disturbance can be determined; Indicates the operating data corresponding to the state without external disturbance at the current moment; Indicates the first target fuzzy control model corresponding to the state without external disturbance input neurons and the The corresponding center value between radial basis neurons; Indicates the first target fuzzy control model corresponding to the state without external disturbance input neurons and the The corresponding width value between radial basis neurons, l It represents the number of radial basis neurons in the radial basis layer of the target fuzzy control model corresponding to the state without external disturbance.

[0193] In an embodiment of the present application, the expression of the normalized output vector output by the normalization layer in the target fuzzy control model corresponding to the external disturbance state is as follows.

[0194] .

[0195] in, The normalized output value of each normalized neuron in the normalized layer in the target fuzzy control model corresponding to the external disturbance state can be used to determine the normalized output vector of the normalized layer in the target fuzzy control model corresponding to the external disturbance state; Indicates the operating data corresponding to the external disturbance state at the current moment; Indicates the first target fuzzy control model corresponding to the external disturbance state input neurons and the The corresponding center value between radial basis neurons; Indicates the first target fuzzy control model corresponding to the external disturbance state input neurons and the The width value corresponding to each radial basis neuron.

[0196] S304: Input the normalized output vector into the output layer set in the target fuzzy control model to obtain the mechanical frequency variation output by the output layer.

[0197] In the embodiment of the present application, the expression of the mechanical frequency change output by the output layer in the target fuzzy control model corresponding to the state without external disturbance is as follows.

[0198] .

[0199] in, It represents the mechanical frequency change output by the output layer in the target fuzzy control model corresponding to the state without external disturbance; Represents the normalized output vector of the normalization layer output in the target fuzzy control model corresponding to the state without external disturbance; It represents the output weight corresponding to the normalization layer in the target fuzzy control model corresponding to the state without external disturbance.

[0200] In the embodiment of the present application, the expression of the mechanical frequency change output by the output layer in the target fuzzy control model corresponding to the external disturbance state is as follows.

[0201] .

[0202] in, It represents the mechanical frequency change output by the output layer in the target fuzzy control model corresponding to the external disturbance state; Represents the normalized output vector of the normalization layer output in the target fuzzy control model corresponding to the external disturbance state; It represents the output weight corresponding to the normalization layer in the target fuzzy control model corresponding to the external disturbance state.

[0203] S305 , obtaining a historical target mechanical frequency corresponding to the large rotating machinery at a previous moment, and determining the sum of the historical target mechanical frequency and the mechanical frequency variation as the target mechanical frequency output by the target fuzzy control model.

[0204] In the embodiment of the present application, the expression of the target mechanical frequency output by the target fuzzy control model corresponding to the state without external disturbance is as follows.

[0205] .

[0206] in, It represents the target mechanical frequency output by the target fuzzy control model corresponding to the state without external disturbance; Indicates the historical target mechanical frequency corresponding to the state without external disturbance; It represents the mechanical frequency change output by the output layer in the target fuzzy control model corresponding to the state without external disturbance.

[0207] In an embodiment of the present application, the expression of the target mechanical frequency output by the target fuzzy control model corresponding to the external disturbance state is as follows.

[0208] .

[0209] in, The target mechanical frequency output by the target fuzzy control model corresponding to the external disturbance state; Indicates the historical target mechanical frequency corresponding to the external disturbance state; It represents the mechanical frequency change output by the output layer in the target fuzzy control model corresponding to the external disturbance state.

[0210] S400: Control the motor provided in the large rotating machine to operate according to the target mechanical frequency.

[0211] In this step, when the target mechanical frequency corresponding to the disturbance state at the current moment is obtained, the target mechanical frequency is input into the frequency converter in the large rotating machinery, and the frequency converter is controlled to adjust the speed of the motor in the large rotating machinery according to the target mechanical frequency, so that the mechanical frequency of the large rotating machinery reaches the target mechanical frequency, thereby making the large rotating machinery operate at the target mechanical frequency.

[0212] The control method for large rotating machinery provided in the embodiment of the present application obtains target fuzzy control models under different disturbance states by performing online parameter update and robustness evaluation on fuzzy control models under different disturbance states, and inputs the operating data of the large rotating machinery into the target fuzzy control model under the current disturbance state, and controls the large rotating machinery to operate according to the target mechanical frequency output by the target fuzzy control model, so that the large rotating machinery can better cope with complex external environmental changes, improve the anti-interference ability in the external disturbance environment, improve the stability of the operation of the large rotating machinery, and thus improve the safety of the large rotating machinery.

[0213] See also Figure 2 , Figure 2 This is a schematic diagram of the structure of a control device for a large rotating machine provided in an embodiment of the present application. Figure 2 As shown in , the control device 200 includes:

[0214] The data acquisition module 210 is used to acquire the disturbance state and operation data corresponding to the large rotating machinery at the current moment during the operation of the large rotating machinery; wherein the disturbance state includes an external disturbance state and a non-external disturbance state;

[0215] a parameter updating module 220 for determining whether the accumulated operating data corresponding to the acquired operating data reaches a preset window amount, and determining a target fuzzy control model corresponding to the disturbance state based on the determination result;

[0216] a model inference module 230 for inputting the operating data into a target fuzzy control model corresponding to the disturbance state, and performing inference calculations based on the operating data using the target fuzzy control model to obtain a target mechanical frequency output by the target fuzzy control model;

[0217] The mechanical control module 240 is used to control the motor provided in the large rotating machine to operate according to the target mechanical frequency.

[0218] Furthermore, when the judgment result is that the accumulated operating data corresponding to the acquired operating data does not reach the preset window amount, the parameter updating module 220 is used to determine the target fuzzy control model corresponding to the disturbance state based on the judgment result, and the parameter updating module 220 is used to:

[0219] A fuzzy control model corresponding to the disturbance state updated online last time is obtained, and the fuzzy control model is determined as a target fuzzy control model corresponding to the disturbance state.

[0220] Furthermore, when the judgment result is that the accumulated operating data corresponding to the acquired operating data reaches a preset window amount, the parameter updating module 220 is used to determine the target fuzzy control model corresponding to the disturbance state based on the judgment result, and the parameter updating module 220 is used to:

[0221] Obtaining a fuzzy control model corresponding to the disturbance state updated last time online, and using the accumulated operating data to update model parameters in the fuzzy control model online to obtain an updated fuzzy control model corresponding to the disturbance state;

[0222] The updated fuzzy control model is subjected to a robustness evaluation using the target operating data corresponding to the updated fuzzy control model to obtain a robustness evaluation result. Based on the robustness evaluation result, the updated fuzzy control model corresponding to each of the disturbance states is adjusted to obtain a target fuzzy control model corresponding to the disturbance state.

[0223] Furthermore, when the disturbance state is a state without external disturbance, the parameter updating module 220 is used to update the model parameters in the fuzzy control model online using the acquired accumulated operating data to obtain an updated fuzzy control model corresponding to the disturbance state. The parameter updating module 220 is used to:

[0224] inputting first accumulated operating data from the accumulated operating data into a first fuzzy control model corresponding to the state without external disturbance to obtain a first mechanical frequency value output by the first fuzzy control model;

[0225] Based on the first mechanical frequency value and the first preset mechanical frequency value, using the preset first objective function corresponding to the state without external disturbance, determine the first target value corresponding to the first accumulated operating data in the state without external disturbance;

[0226] Determining whether the first target value is less than a preset target value;

[0227] If not, then based on the first target value, update the model parameters in the first fuzzy control model to obtain first model parameters corresponding to the first update period, and replace the model parameters in the first fuzzy control model with the first model parameters to obtain the first fuzzy control model corresponding to the first update period;

[0228] Repeatedly inputting the accumulated operating data into the first fuzzy control model corresponding to each update period, calculating a first target value corresponding to each update period, and updating model parameters in the first fuzzy control model when the first target value is greater than or equal to a preset target value, to obtain first model parameters corresponding to each update period, until the first target value is less than the preset target value;

[0229] When the first target value is less than the preset target value, the first target model parameters corresponding to the current update cycle are determined, and the model parameters in the first fuzzy control model are replaced with the first target model parameters to obtain the first updated fuzzy control model corresponding to the state without external disturbance.

[0230] Furthermore, when the disturbance state is an external disturbance state, the parameter updating module 220 is used to update the model parameters in the fuzzy control model online using the operating data to obtain an updated fuzzy control model corresponding to the disturbance state. The parameter updating module 220 is used to:

[0231] inputting first accumulated operating data from the accumulated operating data into a second fuzzy control model corresponding to the external disturbance state to obtain a second mechanical frequency value output by the second fuzzy control model;

[0232] Based on the second mechanical frequency value, the second preset mechanical frequency value, the first target model parameters, and the model parameters in the second fuzzy control model, a second target value corresponding to the first accumulated operating data under the external disturbance state is calculated and determined using a second target function preset corresponding to the external disturbance state;

[0233] Determining whether the second target value is less than a preset target value;

[0234] If not, then based on the second target value, update the model parameters in the second fuzzy control model to obtain second model parameters corresponding to the first update period, and replace the model parameters in the second fuzzy control model with the second model parameters to obtain a second fuzzy control model corresponding to the first update period;

[0235] Repeatedly inputting the accumulated operating data into the second fuzzy control model corresponding to each update period, calculating a second target value corresponding to each update period, and updating model parameters in the second fuzzy control model when the second target value is greater than or equal to a preset target value, to obtain second model parameters corresponding to each update period, until the second target value is less than the preset target value;

[0236] When the second target value is less than the preset target value, the second target model parameters corresponding to the current update cycle are determined, and the model parameters in the second fuzzy control model are replaced with the second target model parameters to obtain a second updated fuzzy control model corresponding to the external disturbance state.

[0237] Furthermore, the parameter updating module 220 is configured to perform a robustness evaluation on the updated fuzzy control model using the target operating data corresponding to the updated fuzzy control model. When the robustness evaluation result is obtained, the parameter updating module 220 is configured to:

[0238] inputting the target operating data corresponding to the obtained updated fuzzy control model into a first updated fuzzy control model corresponding to the no external disturbance state and a second updated fuzzy control model corresponding to the external disturbance state, respectively, to obtain a first estimated mechanical frequency value output by the first updated fuzzy control model and a second estimated mechanical frequency value output by the second updated fuzzy control model;

[0239] Determining an objective function value by using a preset objective function calculation based on a first objective model parameter in the first updated fuzzy control model, a second objective model parameter in the second updated fuzzy control model, the first evaluated mechanical frequency value, and the second evaluated mechanical frequency value;

[0240] Based on the first evaluated mechanical frequency value, the second evaluated mechanical frequency value, the first target model parameter, the second target model parameter, and the objective function value, a preset response evaluation function is used to calculate and determine a response characteristic result in the robustness evaluation result corresponding to the updated fuzzy control model;

[0241] determining, based on the first evaluated mechanical frequency value, the second evaluated mechanical frequency value, and the target operating data, a first mechanical frequency change rate corresponding to the first evaluated mechanical frequency value and a second mechanical frequency change rate corresponding to the second evaluated mechanical frequency value using the first updated fuzzy control model and the second updated fuzzy control model, respectively;

[0242] Based on the first mechanical frequency change rate, the second mechanical frequency change rate, the first target model parameter, the second target model parameter and the objective function value, a preset fluctuation evaluation function is used to calculate and determine the fluctuation characteristic result in the robustness evaluation result corresponding to the updated fuzzy control model.

[0243] Furthermore, when the model inference module 230 is used to input the operating data into the target fuzzy control model corresponding to the disturbance state, and use the target fuzzy control model to perform inference calculation based on the operating data to obtain the target mechanical frequency output by the target fuzzy control model, the model inference module 230 is used to:

[0244] Inputting the operating data into an input layer of a target fuzzy control model corresponding to the disturbance state to obtain an input vector output by the input layer;

[0245] Inputting the input vector into the radial basis layer set in the target fuzzy control model, performing fuzzy processing on the input vector using the radial basis layer, and obtaining a radial basis output vector output by the radial basis layer;

[0246] Inputting the radial basis output vector into a normalization layer set in the target fuzzy control model, and performing normalization processing on the radial basis output vector by using the normalization layer to obtain a normalized output vector output by the normalization layer;

[0247] Inputting the normalized output vector into the output layer of the target fuzzy control model to obtain the mechanical frequency change output by the output layer;

[0248] A historical target mechanical frequency corresponding to the large rotating machine at a previous moment is obtained, and the sum of the historical target mechanical frequency and the mechanical frequency variation is determined as the target mechanical frequency output by the target fuzzy control model.

[0249] The control device for large-scale rotating machinery provided in the embodiment of the present application obtains target fuzzy control models under different disturbance states by performing online parameter updates and robustness evaluations on fuzzy control models under different disturbance states, and inputs the operating data of the large-scale rotating machinery into the target fuzzy control model under the current disturbance state, thereby controlling the large-scale rotating machinery to operate according to the target mechanical frequency output by the target fuzzy control model, so that the large-scale rotating machinery can better cope with complex external environmental changes, improve the anti-interference ability in the external disturbance environment, improve the stability of the operation of the large-scale rotating machinery, and thus improve the safety of the large-scale rotating machinery.

[0250] See also Figure 3 , Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 3 As shown in FIG, the electronic device 300 includes a processor 310 , a memory 320 and a bus 330 .

[0251] The memory 320 stores machine-readable instructions executable by the processor 310. When the electronic device 300 is running, the processor 310 communicates with the memory 320 via the bus 330. When the machine-readable instructions are executed by the processor 310, the above-mentioned Figure 1 The steps of the control method for large rotating machinery in the method embodiment shown are specifically implemented in accordance with the method embodiment, and will not be described in detail here.

[0252] The embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the computer program can execute the above-mentioned Figure 1 The steps of the control method for large rotating machinery in the method embodiment shown are specifically implemented in accordance with the method embodiment, and will not be described in detail here.

[0253] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0254] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. There may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed may be through some communication interface, indirect coupling or communication connection of devices or units, which may be electrical, mechanical or other forms.

[0255] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0256] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0257] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0258] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The scope of protection of the present application is not limited thereto. Although the present application has been described in detail with reference to the above-mentioned embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-mentioned embodiments within the technical scope disclosed in the present application, or perform equivalent replacements for some of the technical features thereof. These modifications, changes, or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A control method for a large rotating machine, characterized in that: The control method includes: During the operation of the large rotating machinery, obtaining the disturbance state and operation data corresponding to the large rotating machinery at the current moment; wherein the disturbance state includes an external disturbance state and a non-external disturbance state; Determining whether the accumulated operating data corresponding to the acquired operating data reaches a preset window amount, and determining a target fuzzy control model corresponding to the disturbance state based on the determination result; The step of determining a target fuzzy control model corresponding to the disturbance state based on the judgment result includes: When the judgment result is that the accumulated operating data corresponding to the acquired operating data does not reach a preset window amount, obtaining a fuzzy control model corresponding to the disturbance state last updated online, and determining the fuzzy control model as a target fuzzy control model corresponding to the disturbance state; When the judgment result is that the accumulated operating data corresponding to the acquired operating data reaches a preset window amount, the fuzzy control model corresponding to the disturbance state updated last time is obtained, and the model parameters in the fuzzy control model are updated online using the accumulated operating data to obtain an updated fuzzy control model corresponding to the disturbance state; Performing a robustness evaluation on the updated fuzzy control model using the target operating data corresponding to when the updated fuzzy control model is obtained to obtain a robustness evaluation result, and adjusting the updated fuzzy control model corresponding to each of the disturbance states based on the robustness evaluation result to obtain a target fuzzy control model corresponding to the disturbance state; wherein the robustness evaluation result includes a response characteristic result and a fluctuation characteristic result; the state without external disturbance corresponds to a first target fuzzy control model, and the state with external disturbance corresponds to a second target fuzzy control model; Inputting the operating data into a target fuzzy control model corresponding to the disturbance state, and performing inference calculation based on the operating data using the target fuzzy control model to obtain a target mechanical frequency output by the target fuzzy control model; An electric motor provided in the large rotating machine is controlled to operate according to the target machine frequency.

2. The method according to claim 1, characterized in that When the disturbance state is a state without external disturbance, the online updating of the model parameters in the fuzzy control model using the acquired accumulated operation data to obtain an updated fuzzy control model corresponding to the disturbance state includes: inputting first accumulated operating data from the accumulated operating data into a first fuzzy control model corresponding to the state without external disturbance to obtain a first mechanical frequency value output by the first fuzzy control model; Based on the first mechanical frequency value and the first preset mechanical frequency value, using the preset first objective function corresponding to the state without external disturbance, determine the first target value corresponding to the first accumulated operating data in the state without external disturbance; Determining whether the first target value is less than a preset target value; If not, then based on the first target value, update the model parameters in the first fuzzy control model to obtain first model parameters corresponding to the first update period, and replace the model parameters in the first fuzzy control model with the first model parameters to obtain the first fuzzy control model corresponding to the first update period; Repeatedly inputting the accumulated operating data into the first fuzzy control model corresponding to each update period, calculating a first target value corresponding to each update period, and updating model parameters in the first fuzzy control model when the first target value is greater than or equal to a preset target value, to obtain first model parameters corresponding to each update period, until the first target value is less than the preset target value; When the first target value is less than the preset target value, the first target model parameters corresponding to the current update cycle are determined, and the model parameters in the first fuzzy control model are replaced with the first target model parameters to obtain the first updated fuzzy control model corresponding to the state without external disturbance.

3. The method according to claim 2, characterized in that When the disturbance state is an external disturbance state, the online updating of the model parameters in the fuzzy control model using the operating data to obtain an updated fuzzy control model corresponding to the disturbance state includes: inputting first accumulated operating data from the accumulated operating data into a second fuzzy control model corresponding to the external disturbance state to obtain a second mechanical frequency value output by the second fuzzy control model; Based on the second mechanical frequency value, the second preset mechanical frequency value, the first target model parameters, and the model parameters in the second fuzzy control model, a second target value corresponding to the first accumulated operating data under the external disturbance state is calculated and determined using a second target function preset corresponding to the external disturbance state; Determining whether the second target value is less than a preset target value; If not, then based on the second target value, update the model parameters in the second fuzzy control model to obtain second model parameters corresponding to the first update period, and replace the model parameters in the second fuzzy control model with the second model parameters to obtain a second fuzzy control model corresponding to the first update period; Repeatedly inputting the accumulated operating data into the second fuzzy control model corresponding to each update period, calculating a second target value corresponding to each update period, and updating model parameters in the second fuzzy control model when the second target value is greater than or equal to a preset target value, to obtain second model parameters corresponding to each update period, until the second target value is less than the preset target value; When the second target value is less than the preset target value, the second target model parameters corresponding to the current update cycle are determined, and the model parameters in the second fuzzy control model are replaced with the second target model parameters to obtain a second updated fuzzy control model corresponding to the external disturbance state.

4. The method according to claim 1, wherein The step of performing robustness evaluation on the updated fuzzy control model by using the target operation data corresponding to the updated fuzzy control model to obtain a robustness evaluation result includes: inputting the target operating data corresponding to the obtained updated fuzzy control model into a first updated fuzzy control model corresponding to the no external disturbance state and a second updated fuzzy control model corresponding to the external disturbance state, respectively, to obtain a first estimated mechanical frequency value output by the first updated fuzzy control model and a second estimated mechanical frequency value output by the second updated fuzzy control model; Determining an objective function value by using a preset objective function calculation based on a first objective model parameter in the first updated fuzzy control model, a second objective model parameter in the second updated fuzzy control model, the first evaluated mechanical frequency value, and the second evaluated mechanical frequency value; Based on the first evaluated mechanical frequency value, the second evaluated mechanical frequency value, the first target model parameter, the second target model parameter, and the objective function value, a preset response evaluation function is used to calculate and determine a response characteristic result in the robustness evaluation result corresponding to the updated fuzzy control model; determining, based on the first evaluated mechanical frequency value, the second evaluated mechanical frequency value, and the target operating data, a first mechanical frequency change rate corresponding to the first evaluated mechanical frequency value and a second mechanical frequency change rate corresponding to the second evaluated mechanical frequency value using the first updated fuzzy control model and the second updated fuzzy control model, respectively; Based on the first mechanical frequency change rate, the second mechanical frequency change rate, the first target model parameter, the second target model parameter and the objective function value, a preset fluctuation evaluation function is used to calculate and determine the fluctuation characteristic result in the robustness evaluation result corresponding to the updated fuzzy control model.

5. The method according to claim 1, wherein Inputting the operating data into a target fuzzy control model corresponding to the disturbance state, and performing inference calculation based on the operating data using the target fuzzy control model to obtain a target mechanical frequency output by the target fuzzy control model, includes: Inputting the operating data into an input layer of a target fuzzy control model corresponding to the disturbance state to obtain an input vector output by the input layer; Inputting the input vector into the radial basis layer set in the target fuzzy control model, performing fuzzy processing on the input vector using the radial basis layer, and obtaining a radial basis output vector output by the radial basis layer; Inputting the radial basis output vector into a normalization layer set in the target fuzzy control model, and performing normalization processing on the radial basis output vector by using the normalization layer to obtain a normalized output vector output by the normalization layer; Inputting the normalized output vector into the output layer of the target fuzzy control model to obtain the mechanical frequency change output by the output layer; A historical target mechanical frequency corresponding to the large rotating machine at a previous moment is obtained, and the sum of the historical target mechanical frequency and the mechanical frequency variation is determined as the target mechanical frequency output by the target fuzzy control model.

6. A control device for a large rotating machine, characterized in that: The control device comprises: A data acquisition module is used to acquire the disturbance state and operation data corresponding to the large rotating machinery at the current moment during the operation of the large rotating machinery; wherein the disturbance state includes an external disturbance state and a non-external disturbance state; a parameter updating module, configured to determine whether the accumulated operating data corresponding to the acquired operating data reaches a preset window amount, and based on the determination result, determine a target fuzzy control model corresponding to the disturbance state; When the parameter updating module is used to determine the target fuzzy control model corresponding to the disturbance state based on the judgment result, the parameter updating module is used to: When the judgment result is that the accumulated operating data corresponding to the acquired operating data does not reach a preset window amount, obtaining a fuzzy control model corresponding to the disturbance state last updated online, and determining the fuzzy control model as a target fuzzy control model corresponding to the disturbance state; When the judgment result is that the accumulated operating data corresponding to the acquired operating data reaches a preset window amount, the fuzzy control model corresponding to the disturbance state updated last time is obtained, and the model parameters in the fuzzy control model are updated online using the accumulated operating data to obtain an updated fuzzy control model corresponding to the disturbance state; Performing a robustness evaluation on the updated fuzzy control model using the target operating data corresponding to when the updated fuzzy control model is obtained to obtain a robustness evaluation result, and adjusting the updated fuzzy control model corresponding to each of the disturbance states based on the robustness evaluation result to obtain a target fuzzy control model corresponding to the disturbance state; wherein the robustness evaluation result includes a response characteristic result and a fluctuation characteristic result; the state without external disturbance corresponds to a first target fuzzy control model, and the state with external disturbance corresponds to a second target fuzzy control model; a model inference module, configured to input the operating data into a target fuzzy control model corresponding to the disturbance state, and perform inference calculations based on the operating data using the target fuzzy control model to obtain a target mechanical frequency output by the target fuzzy control model; The mechanical control module is used to control the motor provided in the large rotating machine to operate according to the target mechanical frequency.

7. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and the machine-readable instructions are executed by the processor to execute the steps of the control method for large rotating machinery as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the control method for a large rotating machine according to any one of claims 1 to 5 are executed.

Images