Air compressor modeling method, system and equipment based on data fitting driving and medium

Abstract

The invention provides an air compressor modeling method, system and equipment based on data fitting driving and a medium, and belongs to the technical field of computers. The method comprises the steps that an MAP of the air compressor is obtained, the MAP at least records a plurality of performance data sets corresponding to the air compressor under a plurality of rotating speed working conditions, the performance data set corresponding to the air compressor under each rotating speed working condition comprises multiple sets of performance data, and each set of performance data comprises the rotating speed, the flow and the pressure ratio of the air compressor; performing data fitting according to the MAP of the air compressor to obtain a flow constraint function of the air compressor and a plurality of flow-pressure ratio functions corresponding to the air compressor under a plurality of rotating speed working conditions, and training a preset neural network model to obtain a flow prediction model; and integrating the flow prediction model and a preset temperature mechanism model to obtain an air compressor model. The modeling difficulty can be effectively reduced.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an air compressor modeling method, system, device and medium driven by data fitting. Background Art

[0002] In the existing air compressor modeling technology, an interpolation method based on the MAP diagram of the air compressor is usually used to cooperate with the subsequent modeling work. However, this implementation method has relatively strict requirements on the selection of the interpolation algorithm and whether the data points are large and evenly distributed, which will undoubtedly increase the difficulty of modeling. Summary of the invention

[0003] The main purpose of this application is to propose an air compressor modeling method, system, equipment and medium driven by data fitting, which can directly perform multi-class function fitting according to the MAP diagram of the air compressor to train the neural network model, and then combine the temperature mechanism model to model the air compressor, which can effectively reduce the difficulty of modeling.

[0004] To achieve the above objectives, one aspect of the present application proposes an air compressor modeling method based on data fitting drive, the method comprising:

[0005] Acquire a MAP diagram of the air compressor, wherein the MAP diagram of the air compressor records at least a plurality of performance data sets corresponding to the air compressor under a plurality of speed conditions, wherein the performance data set corresponding to each of the speed conditions includes a plurality of groups of performance data, and each group of the performance data includes a speed, a flow rate, and a pressure ratio of the air compressor;

[0006] Performing data fitting according to the MAP diagram of the air compressor to obtain a flow constraint function of the air compressor and a plurality of flow-pressure ratio functions corresponding to the air compressor under the plurality of speed conditions;

[0007] According to the flow constraint function of the air compressor and the several flow-pressure ratio functions corresponding to the air compressor under the several speed working conditions, a preset neural network model is trained to obtain a flow prediction model;

[0008] Integrating the flow prediction model and the preset temperature mechanism model to obtain an air compressor model;

[0009] Among them, the input of the flow prediction model is the pressure ratio and speed of the air compressor, and the output is the flow of the air compressor; the temperature mechanism model is used to characterize the functional relationship between the outlet temperature of the air compressor and the pressure ratio, speed, flow and inlet temperature.

[0010] Furthermore, the data fitting is performed according to the MAP diagram of the air compressor to obtain the flow constraint function of the air compressor and several flow-pressure ratio functions corresponding to the air compressor under the several speed conditions, including:

[0011] Extract data according to the MAP diagram of the air compressor to obtain a plurality of first data groups corresponding to the air compressor under the plurality of speed conditions, wherein the first data group corresponding to the air compressor under each of the speed conditions includes the speed, maximum flow rate and minimum flow rate of the air compressor;

[0012] Performing overall fitting on the plurality of first data groups to obtain a flow constraint function of the air compressor;

[0013] The several performance data sets are fitted respectively to obtain several flow-pressure ratio functions corresponding to the air compressor under the several speed working conditions.

[0014] Furthermore, the flow prediction model is obtained by training the preset neural network model according to the flow constraint function of the air compressor and the several flow-pressure ratio functions corresponding to the air compressor under the several speed conditions, including:

[0015] According to the flow-pressure ratio functions corresponding to the air compressor under the several speed conditions, constructing several training data sets corresponding to the air compressor under the several speed conditions;

[0016] The preset neural network model is trained according to the flow constraint function of the air compressor and the plurality of training data sets to obtain the flow prediction model.

[0017] Further, constructing several training data sets corresponding to the air compressor under the several speed conditions according to the several flow-pressure ratio functions corresponding to the air compressor under the several speed conditions includes:

[0018] For the flow-pressure ratio function corresponding to the air compressor under each speed condition, obtain the reference speed corresponding to the air compressor under the speed condition and the preset first reference pressure ratio and step size, and use the first reference pressure ratio as the current pressure ratio;

[0019] Determining a current flow rate according to the current pressure ratio and the flow rate-pressure ratio function;

[0020] Determine a training data and its corresponding label information according to the reference speed, the current pressure ratio and the current flow rate;

[0021] Determine whether the preset loop end condition is met;

[0022] If yes, then construct a training data set corresponding to the air compressor under the speed condition according to all the determined training data and all the corresponding label information;

[0023] If not, the current pressure ratio is updated according to the step length to obtain a second reference pressure ratio, and the second reference pressure ratio is used as the current pressure ratio, and the process returns to the step of determining the current flow rate according to the current pressure ratio and the flow rate-pressure ratio function.

[0024] Furthermore, the preset neural network model is trained according to the flow constraint function of the air compressor and the plurality of training data sets to obtain the flow prediction model, including:

[0025] Obtaining a total loss function, the total loss function comprising a first loss function and a second loss function, the first loss function being used to measure the prediction deviation of the preset neural network model, the second loss function being determined based on the flow constraint function of the air compressor, and the second loss function being used to measure the prediction rationality of the preset neural network model;

[0026] The preset neural network model is trained according to the total loss function and the several training data sets to obtain the traffic prediction model.

[0027] Furthermore, the method further comprises:

[0028] Performing data fitting according to the MAP diagram of the air compressor to obtain a pressure ratio constraint function of the air compressor;

[0029] Obtaining the actual speed, actual pressure ratio and actual inlet temperature of the air compressor;

[0030] When the actual pressure ratio of the air compressor is determined to be reasonable according to the pressure ratio constraint function of the air compressor, the actual speed, actual pressure ratio and actual inlet temperature of the air compressor are input into the air compressor model for processing to obtain the predicted flow rate and predicted outlet temperature of the air compressor.

[0031] Furthermore, performing data fitting according to the MAP diagram of the air compressor to obtain the pressure ratio constraint function of the air compressor includes:

[0032] Extract data according to the MAP diagram of the air compressor to obtain a plurality of second data groups corresponding to the air compressor under the plurality of speed conditions, wherein the second data group corresponding to the air compressor under each of the speed conditions includes the speed, maximum pressure ratio and minimum pressure ratio of the air compressor;

[0033] The plurality of second data groups are fitted as a whole to obtain a pressure ratio constraint function of the air compressor.

[0034] To achieve the above objectives, another aspect of the present application provides an air compressor modeling system based on data fitting drive, the system comprising:

[0035] an acquisition module, configured to acquire a MAP diagram of an air compressor, wherein the MAP diagram of the air compressor records at least a plurality of performance data sets corresponding to the air compressor under a plurality of speed conditions, wherein the performance data set corresponding to the air compressor under each speed condition includes a plurality of groups of performance data, and each group of the performance data includes a speed, a flow rate, and a pressure ratio of the air compressor;

[0036] A fitting module, used for performing data fitting according to the MAP diagram of the air compressor to obtain a flow constraint function of the air compressor and a plurality of flow-pressure ratio functions corresponding to the air compressor under the plurality of speed conditions;

[0037] A training module, used to train a preset neural network model according to the flow constraint function of the air compressor and a plurality of flow-pressure ratio functions corresponding to the air compressor under the plurality of speed conditions, so as to obtain a flow prediction model;

[0038] An integration module, used to integrate the flow prediction model and the preset temperature mechanism model to obtain an air compressor model;

[0039] Among them, the input of the flow prediction model is the pressure ratio and speed of the air compressor, and the output is the flow of the air compressor; the temperature mechanism model is used to characterize the functional relationship between the outlet temperature of the air compressor and the pressure ratio, speed, flow and inlet temperature.

[0040] To achieve the above objective, another aspect of the present application provides an electronic device, the electronic device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the above method when executing the computer program.

[0041] To achieve the above objective, another aspect of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0042] The present application includes at least the following beneficial effects: by performing data fitting according to the MAP diagram of the air compressor, and then using the fitted flow constraint function of the air compressor and several flow-pressure ratio functions corresponding to the air compressor under several speed conditions to complete the training of the neural network model, the model generalization ability and prediction accuracy can be improved, and finally the temperature mechanism model and the trained flow prediction model are used to complete the construction of the air compressor model, which can achieve a relatively comprehensive prediction of the performance of the air compressor, and the entire implementation method does not require the use of too much additional data, which can effectively reduce the difficulty of modeling. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a flow chart of an air compressor modeling method based on data fitting drive provided in an embodiment of the present application;

[0044] Figure 2 It is a structural schematic diagram of an air compressor modeling system based on data fitting drive provided in an embodiment of the present application;

[0045] Figure 3 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application. They are only examples of systems and methods consistent with some aspects of the embodiments of the present application as detailed in the attached claims.

[0047] It is understood that the terms "first", "second", etc. used in this application can be used to describe various concepts in this article, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another concept. For example, without departing from the scope of the embodiment of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determination".

[0048] The terms "at least one", "multiple", "each", "any", etc. used in this application, at least one includes one, two or more, multiple includes two or more, each refers to each of the corresponding multiple, and any refers to any one of the multiple.

[0049] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0050] In the field of fuel cell technology, how to determine a more accurate supply of hydrogen and oxygen plays a vital role in controlling the fuel cell to achieve maximum efficiency. The air compressor is a key component for controlling the oxygen supply in the fuel cell system. How to achieve accurate control of the air compressor is also a key issue at present.

[0051] In the existing air compressor modeling technology, the MAP diagram based on the air compressor is usually used to interpolate to complete the subsequent modeling work. However, this implementation method has relatively strict requirements on the selection of the interpolation algorithm and whether the data points are large and evenly distributed, which will undoubtedly increase the difficulty of modeling. In addition, another technician proposed a new air compressor modeling technology, that is, a single fitting method based on the MAP diagram of the air compressor is used to complete the subsequent modeling work. However, during the entire implementation process, data fitting will be performed on the areas outside the surge line and the blocking line of the air compressor at the same time, resulting in the air compressor model finally constructed being not accurate and reasonable enough, so that the subsequent actual debugging and control of the air compressor will be adversely affected.

[0052] In view of this, the embodiments of the present application provide an air compressor modeling method, system, equipment and medium driven by data fitting. The scheme performs data fitting according to the MAP diagram of the air compressor, and then uses the fitted flow constraint function of the air compressor and several flow-pressure ratio functions corresponding to the air compressor under several speed conditions to complete the training of the neural network model, which can improve the model generalization ability and prediction accuracy. Finally, the temperature mechanism model and the trained flow prediction model are used to complete the construction of the air compressor model, which can achieve a relatively comprehensive prediction of the performance of the air compressor, and the entire implementation method does not require too much additional data, which can effectively reduce the difficulty of modeling.

[0053] An air compressor modeling method based on data fitting drive provided in an embodiment of the present application relates to the field of computer technology, and can be applied to a terminal, or a server, or can be software running in a terminal or a server. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, and a vehicle-mounted terminal, etc., but is not limited thereto; the server side can be configured as an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network; the software can be an application that implements the above-mentioned air compressor modeling method based on data fitting drive, etc., but is not limited to the above forms.

[0054] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0055] Figure 1 is an optional flow chart of an air compressor modeling method based on data fitting drive provided in an embodiment of the present application, Figure 1 The method may include but is not limited to steps S101 to S104:

[0056] Step S101, obtaining a MAP diagram of an air compressor, wherein the MAP diagram of the air compressor records at least a plurality of performance data sets corresponding to the air compressor under a plurality of speed conditions, wherein the performance data set corresponding to each speed condition of the air compressor includes a plurality of groups of performance data, and each group of performance data includes a speed, a flow rate and a pressure ratio of the air compressor;

[0057] Step S102: performing data fitting according to the MAP diagram of the air compressor to obtain a flow constraint function of the air compressor and a plurality of flow-pressure ratio functions corresponding to the air compressor under a plurality of speed conditions;

[0058] Step S103, training a preset neural network model according to the flow constraint function of the air compressor and a plurality of flow-pressure ratio functions corresponding to the air compressor under a plurality of speed conditions to obtain a flow prediction model;

[0059] Step S104, integrating the flow prediction model and the preset temperature mechanism model to obtain an air compressor model; wherein the input of the flow prediction model is the pressure ratio and speed of the air compressor, and the output is the flow of the air compressor; the temperature mechanism model is used to characterize the functional relationship between the outlet temperature of the air compressor and the pressure ratio, speed, flow and inlet temperature.

[0060] In steps S101 to S104 shown in the embodiment of the present application, the difficulty of modeling can be effectively reduced by directly performing multi-class function fitting according to the MAP diagram of the air compressor to train the neural network model, and then combining the temperature mechanism model to model the air compressor.

[0061] In some embodiments, the above step S102 may include but is not limited to steps S201 to S203:

[0062] Step S201, extracting data according to the MAP diagram of the air compressor to obtain a plurality of first data groups corresponding to the air compressor under a plurality of speed conditions, wherein the first data group corresponding to the air compressor under each speed condition includes the speed, maximum flow rate and minimum flow rate of the air compressor.

[0063] Step S202: performing overall fitting on a plurality of first data groups corresponding to the air compressor under a plurality of speed operating conditions to obtain a flow constraint function of the air compressor.

[0064] In this step, the flow constraint function of the air compressor includes the maximum flow-speed function and the minimum flow-speed function of the air compressor. The fitting methods of these two functions may include but are not limited to the following:

[0065] For the first data group corresponding to the air compressor under each speed condition, the first data group is split to obtain a first sub-data group and a second sub-data group, the first sub-data group includes the speed and maximum flow of the air compressor, and the second sub-data group includes the speed and minimum flow of the air compressor. After splitting the several first data groups according to this implementation method, several first sub-data groups and several second sub-data groups corresponding to the air compressor under several speed conditions can be obtained; the several first sub-data groups corresponding to the air compressor under several speed conditions are fitted as a whole, that is, the several first sub-data groups are fitted as a data set to obtain the maximum flow-speed function of the air compressor; the several second sub-data groups corresponding to the air compressor under several speed conditions are fitted as a whole, that is, the several second sub-data groups are fitted as a data set to obtain the minimum flow-speed function of the air compressor.

[0066] Step S203: fitting several performance data sets corresponding to the air compressor under several speed conditions respectively to obtain several flow-pressure ratio functions corresponding to the air compressor under several speed conditions.

[0067] In this step, for the performance data set corresponding to the air compressor under each speed condition, the multiple speeds contained in the performance data set are the same, and are all reference speeds specified when the air compressor is running under the speed condition. Ignoring the multiple speeds contained in the performance data set, the performance data set is fitted to obtain the flow-pressure ratio function corresponding to the air compressor under the speed condition.

[0068] Steps S201 to S203 shown in the embodiment of the present application, by fitting the flow constraint function of the air compressor and several flow-pressure ratio functions corresponding to the air compressor under several speed conditions according to the relevant data recorded in the MAP diagram of the air compressor, can lay a foundation for the subsequent effective and reliable training of the preset neural network model.

[0069] In some embodiments, the above step S103 may include but is not limited to steps S301 to S302:

[0070] Step S301, constructing a plurality of training data sets corresponding to the air compressor under a plurality of speed conditions according to a plurality of flow-pressure ratio functions corresponding to the air compressor under a plurality of speed conditions;

[0071] In this step, for the flow-pressure ratio function corresponding to the air compressor under each speed condition, it is determined that the reference speed specified when the air compressor is running under the speed condition is unchanged. By setting a reference pressure ratio and a step size, a sufficient number of reference pressure ratios are obtained by gradually updating the reference pressure ratio. For each reference pressure ratio, the corresponding reference flow is determined according to the flow-pressure ratio function and the reference pressure ratio. Then, a training data and its corresponding label information are determined according to the reference speed, the reference pressure ratio and the reference flow. After processing based on a sufficient number of reference pressure ratios, a training data set corresponding to the air compressor under the speed condition can be constructed.

[0072] It should be noted that all speeds contained in the training data set corresponding to the air compressor under any speed condition are the same, but the speeds contained in different training data sets corresponding to the air compressor under different speed conditions are different.

[0073] Step S302: training a preset neural network model according to the flow constraint function of the air compressor and a plurality of training data sets corresponding to the air compressor under a plurality of speed operating conditions to obtain a flow prediction model.

[0074] In this step, the preset neural network model preferably adopts the existing BP (Back Propagation) neural network model, which preferably adopts the MSE (Mean Squared Error) function as the basic loss function during the training process. The present application preferentially formulates the penalty term based on the flow constraint function of the air compressor, and then adds the penalty term to the basic loss function to form a final loss function. Then, based on the final loss function and several training data sets corresponding to the air compressor under several speed conditions, the preset neural network model is trained to update the network parameters, thereby obtaining a flow prediction model.

[0075] Steps S301 to S302 shown in the embodiment of the present application directly generate several training data sets required for model training by utilizing several flow-pressure ratio functions corresponding to the air compressor under several speed conditions, and utilize the flow constraint function of the air compressor to optimize the basic loss function required for model training, which is beneficial to improving the reliability and generalization ability of the flow prediction model finally obtained by training.

[0076] In some embodiments, the above step S301 may include but is not limited to steps S401 to S406:

[0077] Step S401: for the flow-pressure ratio function corresponding to the air compressor under each speed condition, obtain the reference speed corresponding to the air compressor under the speed condition and the preset first reference pressure ratio and step size, and use the first reference pressure ratio as the current pressure ratio.

[0078] In this step, the first reference pressure ratio can be selected within the pressure ratio constraint range. When the first reference pressure ratio selects the minimum pressure ratio within the pressure ratio constraint range, the step length is set to a positive value. When the first reference pressure ratio selects the maximum pressure ratio within the pressure ratio constraint range, the step length is set to a negative value. The pressure ratio constraint range can be set by a technician based on experience, or it can be determined by the pressure ratio constraint function of the air compressor obtained by fitting the MAP diagram of the air compressor mentioned below, that is, the reference speed is substituted into the pressure ratio constraint function of the air compressor to solve the minimum pressure ratio and the maximum pressure ratio to construct the pressure ratio constraint range.

[0079] Step S402: Determine the current flow rate according to the current pressure ratio and the flow rate-pressure ratio function.

[0080] In this step, the current flow rate is obtained by substituting the current pressure ratio into the flow rate-pressure ratio function for solution.

[0081] Step S403: Determine a training data and its corresponding label information according to the reference speed, the current pressure ratio and the current flow rate.

[0082] In this step, the reference speed and the current pressure ratio are combined to form a training data, and the current flow rate is used as label information corresponding to the training data. The label information is used to assist in the prediction deviation of the evaluation model after training.

[0083] Step S404, determine whether the preset loop end condition is met; if so, execute step S406; if not, execute step S405.

[0084] In this step, the cycle end condition can be set to at least one of the following: the current pressure ratio exceeds the first preset pressure ratio, the current number of cycles reaches the preset maximum number of cycles, etc., or can be set to at least one of the following: the current pressure ratio is less than the second preset pressure ratio, the current number of cycles reaches the preset maximum number of cycles, etc. This application does not make any limitation on this.

[0085] It should be noted that, when the first reference pressure ratio selects the minimum pressure ratio within the pressure ratio constraint range, the current pressure ratio exceeding the first preset pressure ratio can be selected as the cycle end condition, and the first preset pressure is set as the difference between the maximum pressure ratio within the pressure ratio constraint range and the step length; and when the first reference pressure ratio selects the maximum pressure ratio within the pressure ratio constraint range, the current pressure ratio less than the second preset pressure ratio can be selected as the cycle end condition, and the second preset pressure ratio is set as the difference between the minimum pressure ratio within the pressure ratio constraint range and the step length. In addition, regarding the condition that the current number of cycles reaches the preset maximum number of cycles, it can be understood that the number of updates to the current pressure ratio reaches the preset maximum number of updates.

[0086] Step S405: update the current pressure ratio according to the step length to obtain a second reference pressure ratio, and then use the second reference pressure ratio as the current pressure ratio, and return to execute the above step S402.

[0087] In this step, the second reference pressure ratio is obtained by adding the current pressure ratio to the step length.

[0088] Step S406: construct a training data set corresponding to the air compressor under the speed condition according to all the training data and all the corresponding label information determined after the cycle operation is completed.

[0089] Steps S401 to S406 shown in the embodiment of the present application update the current pressure ratio by utilizing the step size and solve the flow-pressure ratio function corresponding to the air compressor under each speed condition, thereby quickly and reliably constructing the corresponding training data set, so that subsequent model training tasks can be executed normally.

[0090] Optionally, the implementation method of the above-mentioned step S301 includes: for the flow-pressure ratio function corresponding to the air compressor under each speed condition, obtaining the reference speed and pressure ratio constraint range corresponding to the air compressor under the speed condition, the pressure ratio constraint range can be set by the technician based on experience, or can be determined by the pressure ratio constraint function of the air compressor obtained by fitting according to the MAP diagram of the air compressor mentioned below; by randomly selecting a number of different reference pressure ratios within the pressure ratio constraint range, and then substituting the selected several reference pressure ratios into the flow-pressure ratio function for solving, to obtain a number of reference flow rates corresponding to the several reference pressure ratios; according to the reference speed, the several reference pressure ratios and their corresponding several reference flow rates, construct a training data set corresponding to the air compressor under the speed condition.

[0091] Among them, according to the reference speed, several reference pressure ratios and their corresponding several reference flow rates, a training data set corresponding to the air compressor under the speed operating condition is constructed, specifically including: for each reference pressure ratio, the reference speed and the reference pressure ratio are combined to form a training data, and the reference flow rate corresponding to the reference pressure ratio is used as the label information corresponding to the training data; after the reference speed, several reference pressure ratios and several reference flow rates are sorted according to this implementation method, the training data set corresponding to the air compressor under the speed operating condition can be constructed.

[0092] In some embodiments, the above step S302 may include but is not limited to steps S501 to S502:

[0093] Step S501, obtain a total loss function, which includes a first loss function and a second loss function. The first loss function is used to measure the prediction deviation of the preset neural network model. The second loss function is determined based on the flow constraint function of the air compressor. The second loss function is used to measure the prediction rationality of the preset neural network model.

[0094] In this step, the expression of the total loss function is as follows:

[0095]

[0096] In the formula, Loss t is the total loss function, Loss 1 is the first loss function, Loss 2 is the second loss function, PenaltyFactor is the penalty factor, N is the number of all training data required for a simple training model, which can be understood as the number of all training data contained in the first sub-training data set mentioned below, mse(·) represents the mean square error function, M ic_tis the label information corresponding to the i-th training data, which can be understood as the actual flow rate of the air compressor. ic_p The predicted flow rate of the air compressor obtained by inputting the i-th training data into the preset neural network model for analysis and processing, M ic_max Substituting the speed of the air compressor contained in the i-th training data into the maximum flow-speed function of the air compressor to solve the maximum allowable flow of the air compressor, M ic_mmin The minimum allowable flow rate of the air compressor is obtained by substituting the rotation speed of the air compressor contained in the i-th training data into the minimum flow rate-rotation speed function of the air compressor and solving it.

[0097] Step S502: training the preset neural network model according to the total loss function and a plurality of training data sets corresponding to the air compressor under a plurality of speed operating conditions to obtain a flow prediction model.

[0098] In this step, several training data sets corresponding to the air compressor under several speed conditions are merged to form a total training data set, and the total training data set is divided into a first sub-training data set and a second sub-training data set according to a preset ratio, and the preset ratio is preferably set to 8:2; in the forward propagation stage, all the training data contained in the first sub-training data set are input into the preset neural network model for analysis and processing to obtain all corresponding predicted flows, and then the training loss is determined according to the total loss function, all the training data contained in the first sub-training data set and all the corresponding label information and all the predicted flows; then in the back propagation stage, according to the training loss, the weights, biases and other parameters contained in the preset neural network model are updated using an optimization algorithm, and the optimization algorithm can be an existing SGD (Stochastic Gradient Descent) algorithm or Adam (Adaptive moment estimation) algorithm; by iteratively executing the above-mentioned forward propagation stage, loss calculation stage and back propagation stage until the preset maximum number of iterations is reached or the total loss function reaches a convergence state, a flow prediction model can be obtained; finally, the second sub-training data set is used to evaluate the performance of the flow prediction model obtained by the current training.

[0099] Steps S501 to S502 shown in the embodiment of the present application, by combining the flow constraint function of the air compressor to formulate the loss function required for the preset neural network model training, can ensure that each flow of the air compressor predicted by the preset neural network model after the training is completed and officially put into use can fall within the surge line and the blocking line of the air compressor, thereby improving the accuracy of model prediction.

[0100] In step S104 of some embodiments, the expression of the preset temperature mechanism model is specifically as follows:

[0101]

[0102] Where, T out is the outlet temperature of the air compressor, C P is the specific heat capacity at constant pressure, w cp is the speed of the air compressor, T in is the inlet temperature of the air compressor, η cp is the efficiency of the air compressor, P r is the pressure ratio of the air compressor, r is the adiabatic index and is generally set to 1.4, W cp is the flow rate of the air compressor.

[0103] In some embodiments, after the air compressor model is constructed by executing the above steps S101 to S104, when the air compressor is limited to operate only under the above-mentioned several speed conditions, the air compressor model can be formally put into the monitoring and management application of the air compressor, specifically including the following steps S601 to S603:

[0104] Step S601, performing data fitting according to the MAP diagram of the air compressor to obtain a pressure ratio constraint function of the air compressor;

[0105] Step S602, obtaining the actual speed, actual pressure ratio and actual inlet temperature of the air compressor;

[0106] Step S603: When it is determined that the actual pressure ratio of the air compressor is reasonable according to the pressure ratio constraint function of the air compressor, the actual speed, actual pressure ratio and actual inlet temperature of the air compressor are input into the air compressor model for processing to obtain the predicted flow rate and predicted outlet temperature of the air compressor.

[0107] Steps S601 to S603 shown in the embodiment of the present application can achieve a comprehensive prediction of the performance of the air compressor by analyzing some actual operating parameter values ​​of the air compressor with the help of an air compressor model to predict other related operating parameter values, thereby providing reasonable and effective data support for subsequent technical personnel to control and debug the air compressor.

[0108] In some embodiments, the above step S601 may include but is not limited to steps S701 to S702:

[0109] Step S701, extracting data according to the MAP diagram of the air compressor to obtain a plurality of second data groups corresponding to the air compressor under a plurality of speed conditions, wherein the second data group corresponding to the air compressor under each speed condition includes the speed, maximum pressure ratio and minimum pressure ratio of the air compressor, and the pressure ratio of the air compressor can be obtained by dividing the outlet pressure and the inlet pressure of the air compressor.

[0110] Step S702: performing overall fitting on a plurality of second data groups corresponding to the air compressor under a plurality of speed operating conditions to obtain a pressure ratio constraint function of the air compressor.

[0111] In this step, the flow constraint function of the air compressor includes the maximum pressure ratio-speed function and the minimum pressure ratio-speed function of the air compressor. The fitting methods of these two functions may include but are not limited to the following:

[0112] For the second data group corresponding to the air compressor under each speed condition, the second data group is split to obtain a third sub-data group and a fourth sub-data group, the third sub-data group includes the speed and maximum pressure ratio of the air compressor, and the fourth sub-data group includes the speed and minimum pressure ratio of the air compressor. After splitting the plurality of second data groups according to this implementation mode, a plurality of third sub-data groups and a plurality of fourth sub-data groups corresponding to the air compressor under the plurality of speed conditions can be obtained; the plurality of third sub-data groups corresponding to the air compressor under the plurality of speed conditions are fitted as a whole, that is, the plurality of third sub-data groups are fitted as a data set to obtain the maximum pressure ratio-speed function of the air compressor; the plurality of fourth sub-data groups corresponding to the air compressor under the plurality of speed conditions are fitted as a whole, that is, the plurality of fourth sub-data groups are fitted as a data set to obtain the minimum pressure ratio-speed function of the air compressor.

[0113] Steps S701 to S702 shown in the embodiment of the present application fit the pressure ratio constraint function of the air compressor according to the relevant data recorded in the MAP diagram of the air compressor, which is conducive to the subsequent smooth implementation of rationality judgment on all pressure ratios input into the air compressor model.

[0114] It should be noted that in the above step S202, the above step S203 and the above step S702, at least one of the linear fitting method, the polynomial fitting method, the nonlinear fitting method, etc. can be arbitrarily used to complete the data fitting task, and the present application does not limit this; of course, for each data fitting task, multiple fitting methods can also be used simultaneously to generate corresponding multiple fitting functions, and then use indicators such as mean square error, root mean square error, mean absolute error and determination coefficient to select the best fitting function.

[0115] In step S603 of some embodiments, regarding the rationality judgment of the actual pressure ratio of the air compressor according to the pressure ratio constraint function of the air compressor, the corresponding implementation methods may include but are not limited to the following:

[0116] The actual speed of the air compressor is substituted into the maximum pressure ratio-speed function of the air compressor for solving, and the maximum allowable pressure ratio of the air compressor is obtained; the actual speed of the air compressor is substituted into the minimum pressure ratio-speed function of the air compressor for solving, and the minimum allowable pressure ratio of the air compressor is obtained; according to the maximum allowable pressure ratio and the minimum allowable pressure ratio of the air compressor, the allowable range of the pressure ratio of the air compressor is determined; when the pressure ratio of the air compressor falls within the allowable range of the pressure ratio of the air compressor, the actual pressure ratio of the air compressor is determined to be a reasonable value; when the pressure ratio of the air compressor does not fall within the allowable range of the pressure ratio of the air compressor, the actual pressure ratio of the air compressor is determined to be an unreasonable value, and the air compressor model cannot be used for performance prediction at this time.

[0117] Based on the pressure ratio constraint function of the air compressor, the rationality of each actual pressure ratio input to the air compressor model is judged to ensure that it falls within the surge line and the blocking line of the air compressor, so that the air compressor model can make reasonable performance predictions.

[0118] In step S603 of some embodiments, the actual speed, actual pressure ratio and actual inlet temperature of the air compressor are input into the air compressor model for processing to obtain the predicted flow rate and predicted outlet temperature of the air compressor. The corresponding implementation methods include the following:

[0119] The actual speed and actual pressure ratio of the air compressor are input into the flow prediction model for analysis and processing to obtain the predicted flow of the air compressor; then the actual speed, actual pressure ratio, actual inlet temperature and predicted flow of the air compressor are input into the temperature mechanism model for calculation to obtain the predicted outlet temperature of the air compressor.

[0120] The air compressor modeling method based on data fitting drive provided in the embodiment of the present application can effectively reduce the difficulty of modeling by directly fitting multiple types of functions according to the MAP diagram of the air compressor to train the neural network model, and then combine the temperature mechanism model to model the air compressor, and reliably achieve a relatively comprehensive prediction of the performance of the air compressor. In addition, the surge line and blockage line of the air compressor are taken into account in the data fitting process, which is conducive to accurately setting the operating boundary of the air compressor model and avoiding overfitting in the modeling process.

[0121] See also Figure 2 The embodiment of the present application further provides an air compressor modeling system based on data fitting drive, which can implement the above-mentioned air compressor modeling method based on data fitting drive, and the system includes:

[0122] The acquisition module 801 is used to acquire a MAP diagram of the air compressor, wherein the MAP diagram of the air compressor at least records a plurality of performance data sets corresponding to the air compressor under a plurality of speed conditions, wherein the performance data set corresponding to the air compressor under each speed condition includes a plurality of groups of performance data, and each group of performance data includes a speed, a flow rate and a pressure ratio of the air compressor;

[0123] A fitting module 802 is used to perform data fitting according to the MAP diagram of the air compressor to obtain a flow constraint function of the air compressor and a plurality of flow-pressure ratio functions corresponding to the air compressor under a plurality of speed conditions;

[0124] The training module 803 is used to train the preset neural network model according to the flow constraint function of the air compressor and the corresponding flow-pressure ratio functions of the air compressor under the several speed conditions to obtain a flow prediction model;

[0125] Integration module 804 is used to integrate the flow prediction model and the preset temperature mechanism model to obtain an air compressor model; wherein the input of the flow prediction model is the pressure ratio and speed of the air compressor, and the output is the flow of the air compressor; the temperature mechanism model is used to characterize the functional relationship between the outlet temperature of the air compressor and the pressure ratio, speed, flow and inlet temperature.

[0126] In some embodiments, the system further comprises:

[0127] A first fitting module is used to perform data fitting according to the MAP diagram of the air compressor to obtain a pressure ratio constraint function of the air compressor;

[0128] The first acquisition module is used to obtain the actual speed, actual pressure ratio and actual inlet temperature of the air compressor;

[0129] The processing module is used to input the actual speed, actual pressure ratio and actual inlet temperature of the air compressor into the air compressor model for processing when the actual pressure ratio of the air compressor is determined to be reasonable according to the pressure ratio constraint function of the air compressor, so as to obtain the predicted flow rate and predicted outlet temperature of the air compressor.

[0130] It can be understood that the contents of the above method embodiments are all applicable to the present system embodiments, the functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0131] The embodiment of the present application also provides an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the above-mentioned air compressor modeling method based on data fitting drive when executing the computer program. The electronic device may include any intelligent terminal such as a tablet computer and a vehicle-mounted computer.

[0132] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0133] See also Figure 3 , Figure 3 The hardware structure of an electronic device according to another embodiment is shown. The electronic device includes:

[0134] The processor 901 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0135] The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store an operating system and other application programs. When the technical solution provided in the embodiment of the present application is implemented by software or firmware, the relevant program code is stored in the memory 902, and the processor 901 calls and executes the technical solution provided in the embodiment of the present application;

[0136] Input / output interface 903, used to implement information input and output;

[0137] Communication interface 904, used to realize communication interaction between the device and other devices, which can be realized by wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);

[0138] A bus 905 that transmits information between the various components of the device (e.g., the processor 901, the memory 902, the input / output interface 903, and the communication interface 904);

[0139] The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .

[0140] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned air compressor modeling method based on data fitting drive is implemented.

[0141] It can be understood that the contents of the above method embodiments are all applicable to the present storage medium embodiments, the functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0142] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0143] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0144] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0145] The system embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment.

[0146] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0147] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0148] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0149] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of systems or units, which can be electrical, mechanical or other forms.

[0150] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0151] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0152] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0153] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A method for modeling an air compressor based on data fitting, characterized in that: The method comprises: Acquire a MAP diagram of the air compressor, wherein the MAP diagram of the air compressor records at least a plurality of performance data sets corresponding to the air compressor under a plurality of speed conditions, wherein the performance data set corresponding to each of the speed conditions includes a plurality of groups of performance data, and each group of the performance data includes a speed, a flow rate, and a pressure ratio of the air compressor; Performing data fitting according to the MAP diagram of the air compressor to obtain a flow constraint function of the air compressor and a plurality of flow-pressure ratio functions corresponding to the air compressor under the plurality of speed conditions; According to the flow constraint function of the air compressor and the several flow-pressure ratio functions corresponding to the air compressor under the several speed working conditions, a preset neural network model is trained to obtain a flow prediction model; Integrating the flow prediction model and the preset temperature mechanism model to obtain an air compressor model; Among them, the input of the flow prediction model is the pressure ratio and speed of the air compressor, and the output is the flow of the air compressor; the temperature mechanism model is used to characterize the functional relationship between the outlet temperature of the air compressor and the pressure ratio, speed, flow and inlet temperature.

2. The air compressor modeling method based on data fitting drive according to claim 1 is characterized in that: The data fitting is performed according to the MAP diagram of the air compressor to obtain the flow constraint function of the air compressor and several flow-pressure ratio functions corresponding to the air compressor under the several speed conditions, including: Extract data according to the MAP diagram of the air compressor to obtain a plurality of first data groups corresponding to the air compressor under the plurality of speed conditions, wherein the first data group corresponding to the air compressor under each of the speed conditions includes the speed, maximum flow rate and minimum flow rate of the air compressor; Performing overall fitting on the plurality of first data groups to obtain a flow constraint function of the air compressor; The several performance data sets are fitted respectively to obtain several flow-pressure ratio functions corresponding to the air compressor under the several speed working conditions.

3. The air compressor modeling method based on data fitting drive according to claim 1 is characterized in that: The flow prediction model is obtained by training a preset neural network model according to the flow constraint function of the air compressor and the several flow-pressure ratio functions corresponding to the air compressor under the several speed conditions, including: According to the flow-pressure ratio functions corresponding to the air compressor under the several speed conditions, constructing several training data sets corresponding to the air compressor under the several speed conditions; The preset neural network model is trained according to the flow constraint function of the air compressor and the plurality of training data sets to obtain the flow prediction model.

4. The air compressor modeling method based on data fitting drive according to claim 3 is characterized in that: The step of constructing a plurality of training data sets corresponding to the air compressor under the plurality of speed conditions according to the plurality of flow-pressure ratio functions corresponding to the air compressor under the plurality of speed conditions comprises: For the flow-pressure ratio function corresponding to the air compressor under each speed condition, obtain the reference speed corresponding to the air compressor under the speed condition and the preset first reference pressure ratio and step size, and use the first reference pressure ratio as the current pressure ratio; Determining a current flow rate according to the current pressure ratio and the flow rate-pressure ratio function; Determine a training data and its corresponding label information according to the reference speed, the current pressure ratio and the current flow rate; Determine whether the preset loop end condition is met; If yes, then construct a training data set corresponding to the air compressor under the speed condition according to all the determined training data and all the corresponding label information; If not, the current pressure ratio is updated according to the step length to obtain a second reference pressure ratio, and the second reference pressure ratio is used as the current pressure ratio, and the process returns to the step of determining the current flow rate according to the current pressure ratio and the flow rate-pressure ratio function.

5. The air compressor modeling method based on data fitting drive according to claim 3 is characterized in that: The method of training the preset neural network model according to the flow constraint function of the air compressor and the plurality of training data sets to obtain the flow prediction model includes: Obtaining a total loss function, the total loss function comprising a first loss function and a second loss function, the first loss function being used to measure the prediction deviation of the preset neural network model, the second loss function being determined based on the flow constraint function of the air compressor, and the second loss function being used to measure the prediction rationality of the preset neural network model; The preset neural network model is trained according to the total loss function and the several training data sets to obtain the traffic prediction model.

6. The air compressor modeling method based on data fitting drive according to claim 1 is characterized in that: The method further comprises: Performing data fitting according to the MAP diagram of the air compressor to obtain a pressure ratio constraint function of the air compressor; Obtaining the actual speed, actual pressure ratio and actual inlet temperature of the air compressor; When the actual pressure ratio of the air compressor is determined to be reasonable according to the pressure ratio constraint function of the air compressor, the actual speed, actual pressure ratio and actual inlet temperature of the air compressor are input into the air compressor model for processing to obtain the predicted flow rate and predicted outlet temperature of the air compressor.

7. The air compressor modeling method based on data fitting drive according to claim 6 is characterized in that: The step of performing data fitting according to the MAP diagram of the air compressor to obtain the pressure ratio constraint function of the air compressor includes: Extract data according to the MAP diagram of the air compressor to obtain a plurality of second data groups corresponding to the air compressor under the plurality of speed conditions, wherein the second data group corresponding to the air compressor under each of the speed conditions includes the speed, maximum pressure ratio and minimum pressure ratio of the air compressor; The plurality of second data groups are fitted as a whole to obtain a pressure ratio constraint function of the air compressor.

8. An air compressor modeling system based on data fitting drive, characterized in that: The system comprises: an acquisition module, configured to acquire a MAP diagram of an air compressor, wherein the MAP diagram of the air compressor records at least a plurality of performance data sets corresponding to the air compressor under a plurality of speed conditions, wherein the performance data set corresponding to the air compressor under each speed condition includes a plurality of groups of performance data, and each group of the performance data includes a speed, a flow rate, and a pressure ratio of the air compressor; A fitting module, used for performing data fitting according to the MAP diagram of the air compressor to obtain a flow constraint function of the air compressor and a plurality of flow-pressure ratio functions corresponding to the air compressor under the plurality of speed conditions; A training module, used to train a preset neural network model according to the flow constraint function of the air compressor and a plurality of flow-pressure ratio functions corresponding to the air compressor under the plurality of speed conditions, so as to obtain a flow prediction model; An integration module, used to integrate the flow prediction model and the preset temperature mechanism model to obtain an air compressor model; Among them, the input of the flow prediction model is the pressure ratio and speed of the air compressor, and the output is the flow of the air compressor; the temperature mechanism model is used to characterize the functional relationship between the outlet temperature of the air compressor and the pressure ratio, speed, flow and inlet temperature.

9. An electronic device, characterized in that: The electronic device comprises a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images