Thermistor temperature prediction method, permanent magnet synchronous motor monitoring method and system

Abstract

The invention provides a thermistor temperature prediction method and a permanent magnet synchronous motor monitoring method and system, and belongs to the technical field of computers. The thermistor temperature prediction method comprises the following steps: acquiring a terminal voltage sampling value of a thermistor; inputting the terminal voltage sampling value of the thermistor into a predetermined temperature prediction mathematical model associated with the thermistor for solving to obtain a temperature value of the thermistor; wherein the temperature prediction mathematical model is obtained by performing weighted summation on a plurality of polynomial models, and each polynomial model is used for representing a function relationship between a temperature value of the thermistor and a terminal voltage sampling value; the weight corresponding to each polynomial model is used for representing the closeness degree between the terminal voltage sampling value of the thermistor and the preset voltage sampling value corresponding to the polynomial model. The method can improve the prediction accuracy of the temperature of the thermistor, and further improves the monitoring accuracy and reliability of the stator temperature of the permanent magnet synchronous motor.

Description

Technical Field

[0001] This application relates to the field of computer technology, and particularly to a method for predicting the temperature of a thermistor, a method and system for monitoring a permanent magnet synchronous motor. Background Art

[0002] In the prior art, generally, the resistance-temperature characteristic table of a thermistor is first fitted by the least squares method to obtain a corresponding temperature characteristic function, and then the resistance value of the thermistor collected in actual application is substituted into the temperature characteristic function for solution to obtain the predicted temperature value of the thermistor. However, due to the relatively low fitting accuracy of the temperature characteristic function, there is a certain temperature prediction error. Summary of the Invention

[0003] The main purpose of this application is to propose a method for predicting the temperature of a thermistor, a method and system for monitoring a permanent magnet synchronous motor, aiming to improve the prediction accuracy of the temperature of the thermistor, and further improve the monitoring accuracy and reliability of the stator temperature of the permanent magnet synchronous motor.

[0004] To achieve the above object, one aspect of this application proposes a method for predicting the temperature of a thermistor, including:

[0005] Obtain the sampled terminal voltage value of the thermistor;

[0006] Input the sampled terminal voltage value of the thermistor into a pre-determined temperature prediction mathematical model associated with the thermistor for solution to obtain the predicted temperature value of the thermistor;

[0007] Wherein, the temperature prediction mathematical model is obtained by weighted summation of multiple polynomial models, each polynomial model is used to characterize the functional relationship between the temperature value of the thermistor and the sampled terminal voltage value, and the weight corresponding to each polynomial model is used to characterize the proximity between the sampled terminal voltage value of the thermistor and the preset sampled voltage value corresponding to the polynomial model.

[0008] Further, the temperature prediction mathematical model is obtained through the following method:

[0009] Obtain the characteristic data set of the thermistor, the characteristic data set includes multiple characteristic data, and each characteristic data includes the true temperature value of the thermistor and its corresponding true sampled terminal voltage value;

[0010] Start the K-th round of fitting, and evenly divide the characteristic data set into K characteristic data subsets;

[0011] According to a preset fitting loss function, perform polynomial fitting on the K characteristic data subsets respectively to obtain corresponding K polynomial models;

[0012] For each of the polynomial models, based on all the true terminal voltage sampling values of the thermistor included in the characteristic data subset corresponding to the polynomial model, determine the preset voltage sampling value corresponding to the polynomial model, and then in combination with the Gaussian kernel function, determine the weight mathematical model corresponding to the polynomial model;

[0013] Based on the K polynomial models and their corresponding K weight mathematical models, determine the initial temperature prediction mathematical model obtained by the K-th round of fitting and denote it as the first mathematical model;

[0014] Obtain the initial temperature prediction mathematical model obtained by the (K - 1)-th round of fitting and denote it as the second mathematical model;

[0015] Based on the characteristic data set, the first mathematical model, and the second mathematical model, determine whether the preset prediction loss function tends to be stable;

[0016] If so, use the second mathematical model as the temperature prediction mathematical model;

[0017] If not, assign K + 1 to K, and then return to the step of evenly dividing the characteristic data set into K characteristic data subsets at the beginning of the K-th round of fitting.

[0018] Further, the fitting loss function includes a first loss function and a second loss function. The first loss function is used to measure the fitting degree of the K polynomial models, and the second loss function is used to measure the sparsity degree of the coefficients of each order of the K polynomial models.

[0019] Further, the determining whether the preset prediction loss function tends to be stable according to the characteristic data set, the first mathematical model, and the second mathematical model includes:

[0020] Based on the characteristic data set and the prediction loss function, determine the first prediction loss value corresponding to the first mathematical model and the second prediction loss value corresponding to the second mathematical model;

[0021] Determine the relative difference value between the first prediction loss value and the second prediction loss value, and then based on the relative difference value, determine whether the prediction loss function tends to be stable.

[0022] To achieve the above object, another aspect of the present application proposes a permanent magnet synchronous motor monitoring method, including:

[0023] Obtain a plurality of current temperature values and a plurality of historical temperature value sets corresponding to a plurality of thermistors, where the plurality of thermistors are respectively arranged at a plurality of key positions of the stator of the permanent magnet synchronous motor, and the current temperature value and the historical temperature value set of each thermistor are obtained by the above thermistor temperature prediction method;

[0024] Determine the multiple historical temperature standard deviations corresponding to the multiple thermistors according to the multiple sets of historical temperature values corresponding to the multiple thermistors;

[0025] Perform outlier rejection processing on the multiple current temperature values corresponding to the multiple thermistors according to a preset abnormal screening condition and the multiple historical temperature standard deviations corresponding to the multiple thermistors, and obtain all the current temperature values corresponding to all the target thermistors;

[0026] Optimize all the preset weights corresponding to all the target thermistors according to all the historical temperature standard deviations corresponding to all the target thermistors, and each preset weight corresponding to each target thermistor is used to characterize the importance of the critical position where the target thermistor is located;

[0027] Determine the current stator temperature value of the permanent magnet synchronous motor according to all the current temperature values corresponding to all the target thermistors and all the optimized preset weights.

[0028] Further, after determining the current stator temperature value of the permanent magnet synchronous motor, it includes:

[0029] Obtain the current operating parameter values of the permanent magnet synchronous motor, where the current operating parameter values of the permanent magnet synchronous motor include the current three-phase voltage value, the current three-phase current value, the current speed value, and the current torque value of the permanent magnet synchronous motor, and then perform visual display together with the current stator temperature value of the permanent magnet synchronous motor;

[0030] When at least one of the multiple thermistors detects an abnormality, generate a thermistor abnormality detection message and perform visual display.

[0031] To achieve the above object, another aspect of the present application proposes a thermistor temperature prediction system, including:

[0032] A first acquisition module, configured to acquire the terminal voltage sampling value of the thermistor;

[0033] A solution module, configured to input the terminal voltage sampling value of the thermistor into a pre-determined temperature prediction mathematical model associated with the thermistor for solution, and obtain the predicted temperature value of the thermistor;

[0034] Wherein, the temperature prediction mathematical model is obtained by weighted summation of multiple polynomial models, each polynomial model is used to characterize the functional relationship between the temperature value of the thermistor and the terminal voltage sampling value, and the weight corresponding to each polynomial model is used to characterize the proximity between the terminal voltage sampling value of the thermistor and the preset voltage sampling value corresponding to the polynomial model.

[0035] To achieve the above object, on the other hand, the present application proposes a permanent magnet synchronous motor monitoring system, including:

[0036] A second acquisition module, configured to acquire a plurality of current temperature values and a plurality of sets of historical temperature values corresponding to a plurality of thermistors, where the plurality of thermistors are respectively arranged at a plurality of key positions of the stator of the permanent magnet synchronous motor, and the current temperature value and the set of historical temperature values of each thermistor are obtained by the above-mentioned thermistor temperature prediction method;

[0037] A first determination module, configured to determine a plurality of historical temperature standard deviations corresponding to the plurality of thermistors according to the plurality of sets of historical temperature values corresponding to the plurality of thermistors;

[0038] A processing module, configured to perform outlier rejection processing on the plurality of current temperature values corresponding to the plurality of thermistors according to a preset abnormal screening condition and the plurality of historical temperature standard deviations corresponding to the plurality of thermistors, so as to obtain all the current temperature values corresponding to all the target thermistors;

[0039] An optimization module, configured to optimize all the preset weights corresponding to all the target thermistors according to all the historical temperature standard deviations corresponding to all the target thermistors, where the preset weight corresponding to each target thermistor is used to characterize the importance of the key position where the target thermistor is located;

[0040] A second determination module, configured to determine the current stator temperature value of the permanent magnet synchronous motor according to all the current temperature values corresponding to all the target thermistors and all the optimized preset weights.

[0041] To achieve the above object, on the other hand, the present application proposes an electronic device, where the electronic device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the above-mentioned thermistor temperature prediction method or the above-mentioned permanent magnet synchronous motor monitoring method is implemented.

[0042] To achieve the above object, on the other hand, the present application proposes a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned thermistor temperature prediction method or the above-mentioned permanent magnet synchronous motor monitoring method is implemented.

[0043] The present application has at least the following beneficial effects: By using the temperature prediction mathematical model determined by polynomial combination fitting to convert the sampled value of the terminal voltage of the thermistor, the temperature value of the thermistor can be predicted more accurately. By arranging a plurality of corresponding thermistors at multiple key positions of the stator of the permanent magnet synchronous motor for comprehensive monitoring, and using the method of quantifying the temperature value fluctuations of each thermistor to assist in screening out all temperature values corresponding to all target thermistors without anomalies, and then using the temperature value fluctuations of each target thermistor to optimize the preset weight corresponding to the target thermistor, it is beneficial to more accurately and reliably determine the stator temperature of the permanent magnet synchronous motor. Description of the Drawings

[0044] Figure 1 is a schematic flowchart of a thermistor temperature prediction method provided by an embodiment of the present application;

[0045] Figure 2 is a schematic diagram of a voltage dividing circuit provided by an embodiment of the present application;

[0046] Figure 3 is a schematic flowchart of a permanent magnet synchronous motor monitoring method provided by an embodiment of the present application;

[0047] Figure 4 is a schematic diagram of the brief distribution of multiple thermistors on the stator of a permanent magnet synchronous motor provided by an embodiment of the present application;

[0048] Figure 5 is a schematic diagram of the structural composition of a thermistor temperature prediction system provided by an embodiment of the present application;

[0049] Figure 6 is a schematic diagram of the structural composition of a permanent magnet synchronous motor monitoring system provided by an embodiment of the present application;

[0050] Figure 7 is a schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present application. Detailed Embodiments

[0051] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application. When the following description refers to the accompanying 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 that are consistent with some aspects of the embodiments of the present application detailed in the appended claims.

[0052] It can be understood that the terms "first", "second", etc. used in this application may be used herein to describe various concepts, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of this 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", "when" as used herein may be interpreted as "when...", "while...", or "in response to determining".

[0053] The terms "at least one", "a plurality of", "each", "any one", etc. used in this application, at least one includes one, two or more than two, a plurality of includes two or more than two, each refers to each of the corresponding plurality, and any one refers to any one of the plurality.

[0054] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field 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.

[0055] In the existing thermistor temperature prediction technology, the method of directly querying the resistance-temperature characteristic table of the thermistor can be used to convert the resistance value of the collected thermistor into a temperature value. However, this implementation method requires collecting a large amount of data information in advance to ensure the accuracy of the table lookup, which will occupy a large amount of storage space of the controller and has certain limitations in actual applications. It is necessary to effectively balance the table lookup accuracy and the controller capacity. In addition, the data of the resistance-temperature characteristic table of the thermistor can be pre-fitted by the least squares method to obtain the corresponding temperature characteristic function, and then the resistance value of the collected thermistor is substituted into the temperature characteristic function for solution to obtain the temperature value of the thermistor in actual applications. However, due to the relatively low fitting accuracy of the temperature characteristic function, there is a certain temperature prediction error.

[0056] In the existing motor stator temperature monitoring technology, although it is proposed that multiple thermistors can be used for comprehensive monitoring, the influencing factors such as the possible abnormal monitoring of some thermistors and the layout positions of each thermistor on the motor stator are not fully considered, which easily leads to inaccurate monitoring of the motor stator temperature and further affects the safety and reliability of motor operation.

[0057] In view of this, the embodiments of this application provide a thermistor temperature prediction method, a permanent magnet synchronous motor monitoring method and system, which can improve the prediction accuracy of the temperature of the thermistor, and further improve the monitoring accuracy and reliability of the stator temperature of the permanent magnet synchronous motor.

[0058] The following will elaborate in detail the specific implementation content of a thermistor temperature prediction method provided by an embodiment of the present application in conjunction with the accompanying drawings. A thermistor temperature prediction method provided by an embodiment of the present application relates to the field of computer technology and can be applied to a terminal, a server, or software running on 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, a vehicle-mounted terminal, etc., but is not limited thereto; the server side can be configured as an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing 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 implementing the above thermistor temperature prediction method, etc., but is not limited to the above forms.

[0059] Please refer to Figure 1 , Figure 1 which is an optional flowchart of a thermistor temperature prediction method provided by an embodiment of the present application. The thermistor temperature prediction method may but is not limited to include the following steps S110 to S120:

[0060] Step S110: Obtain the terminal voltage sampling value of the thermistor;

[0061] Step S120: Input the terminal voltage sampling value of the thermistor into a pre-determined temperature prediction mathematical model associated with the thermistor for solution to obtain the predicted temperature value of the thermistor; wherein, the temperature prediction mathematical model is obtained by weighted summation of multiple polynomial models, each polynomial model is used to represent the functional relationship between the temperature value of the thermistor and the terminal voltage sampling value, and the weight corresponding to each polynomial model is used to represent the proximity between the terminal voltage sampling value of the thermistor and the preset voltage sampling value corresponding to the polynomial model.

[0062] In the present application, by using a temperature prediction mathematical model determined by polynomial combination fitting to convert the terminal voltage sampling value of the thermistor, the temperature value of the thermistor can be predicted more accurately.

[0063] In step S110 of some embodiments, the terminal voltage sampling value of the thermistor can be obtained by setting a voltage dividing circuit for the thermistor, such as Figure 2As shown, the voltage division circuit includes a bus voltage source, a voltage division resistor, and the thermistor. The positive terminal of the bus voltage source is connected to the first end of the voltage division resistor. The second end of the voltage division resistor is connected to the first end of the thermistor. The second end of the thermistor is connected to the negative terminal of the bus voltage source. A sampling point ADC is set on the electrical connection line between the voltage division resistor and the thermistor, and the sampling point ADC is used as the output of the voltage division circuit and connected to the analog input pin of the microcontroller, so that the microcontroller can obtain the sampled value of the terminal voltage of the thermistor, which is specifically determined by the following formula:

[0064]

[0065] By converting the above two formulas, the relationship between the resistance value of the thermistor and the sampled value of the terminal voltage can be obtained as follows:

[0066]

[0067] In the formula, V p is the terminal voltage of the thermistor, U is the bus voltage provided by the bus voltage source, R is the resistance value of the voltage division resistor and is preferably set to 120Ω in this application, R P is the resistance value of the thermistor, and ADC is the sampled value of the terminal voltage of the thermistor.

[0068] In step S120 of some embodiments, the determination process of the temperature prediction mathematical model associated with the thermistor may include, but is not limited to, the following steps S121 to step S126:

[0069] Step S121: Obtain the characteristic data set of the thermistor. The characteristic data set includes multiple characteristic data, and each characteristic data includes the true temperature value of the thermistor and its corresponding true sampled value of the terminal voltage.

[0070] In this step, first obtain the resistance-temperature characteristic table of the given thermistor, as shown in Table 1. Then, through the relationship between the resistance value and the sampled value of the terminal voltage of the above thermistor, perform data conversion on the resistance-temperature characteristic table of the thermistor to obtain the temperature-voltage characteristic table of the thermistor, as shown in Table 2. Finally, summarize all the characteristic data recorded in the temperature-voltage characteristic table of the thermistor to form the characteristic data set of the thermistor.

[0071] Table 1 Resistance-Temperature Characteristic Table of Thermistor

[0072]

[0073]

[0074] Table 2 Temperature-Voltage Characteristic Table of Thermistor

[0075] Sampling value of the terminal voltage of the thermistor Temperature value of the thermistor 1641.8 -50℃ 1646.6 -49℃ 1651.4 -48℃ …… …… 2530.5 250℃

[0076] As can be seen from Table 1 and Table 2, in the present application, by means of a preset value-taking step size, values are incremented step by step within the allowable temperature measurement range of the thermistor to obtain a number of temperature values of the thermistor, and then corresponding resistance values and terminal voltage sampling values are set for each temperature value of the thermistor; wherein, the allowable temperature measurement range of the thermistor is preferably set to [-50°C, 250°C], and the value-taking step size is preferably set to 1°C.

[0077] Step S122: Start the Kth round of fitting, and evenly divide the characteristic data set to obtain K characteristic data subsets.

[0078] In this step, first, all the true temperature values of the thermistor included in the characteristic data set are screened to extract the minimum true temperature value and the maximum true temperature value therefrom; secondly, both the minimum true temperature value and the maximum true temperature value are used as interval endpoints to determine a temperature interval; then, the temperature interval is evenly divided to obtain K temperature sub-intervals; finally, for each temperature sub-interval, all the characteristic data whose true temperature values included in the characteristic data set fall within the temperature sub-interval are screened out, and all the screened characteristic data are summarized to form the characteristic data subset corresponding to the temperature sub-interval. By processing according to this data screening and summarizing method, K characteristic data subsets corresponding to K temperature sub-intervals can be obtained, thereby realizing the even division of the characteristic data set.

[0079] Step S123: According to a preset fitting loss function, perform polynomial fitting on the K characteristic data subsets respectively to obtain corresponding K polynomial models.

[0080] In this step, for the kth characteristic data subset, k = 1, 2,..., K, first, an Nth-order polynomial is used to construct the kth initial polynomial model corresponding to the kth characteristic data subset, secondly, the coefficients of each order of the kth initial polynomial model are randomly initialized, and then, with the goal of minimizing the fitting loss function, the kth initial polynomial model after random initialization is iteratively optimized in combination with the kth characteristic data subset to update its coefficients of each order, thereby obtaining the kth polynomial model corresponding to the kth characteristic data subset. In the present application, this optimization and update process can be realized by using the gradient descent method.

[0081] Among them, the kth polynomial model corresponding to the kth characteristic data subset is specifically as follows:

[0082]

[0083] In the formula, ADC is the terminal voltage sampling value of the thermistor, T pkThe predicted temperature value of the thermistor obtained by inputting the ADC sampled value of the terminal voltage of the thermistor into the k-th polynomial model for solution, N k is the order of the k-th polynomial model, and in this application, it is preferably set that the orders of the K polynomial models are the same, α ki is the i-th order coefficient of the k-th polynomial model, ADC i refers to solving the i-th power of ADC.

[0084] Step S124: For each polynomial model, according to all the true terminal voltage sampled values of the thermistor included in the characteristic data subset corresponding to the polynomial model, determine the preset voltage sampled value corresponding to the polynomial model, and then combine with the Gaussian kernel function to determine the weight mathematical model corresponding to the polynomial model.

[0085] In this step, first, select the median from all the true terminal voltage sampled values of the thermistor included in the characteristic data subset corresponding to the polynomial model, and use the median as the preset voltage sampled value corresponding to the polynomial model; then, according to the Gaussian kernel function and the preset voltage sampled value corresponding to the polynomial model, determine the weight mathematical model corresponding to the polynomial model as follows:

[0086]

[0087] In the formula, ADC is the sampled value of the terminal voltage of the thermistor, c k is the preset voltage sampled value corresponding to the k-th polynomial model, σ is the width parameter of the Gaussian kernel, exp(·) represents the exponential function with the natural constant e as the base, w k is the initial weight corresponding to the k-th polynomial model, K is the number of all polynomial models included in the temperature prediction mathematical model, π k is the weight corresponding to the k-th polynomial model, used to characterize the proximity between the sampled value ADC of the terminal voltage of the thermistor and the preset voltage sampled value c corresponding to the k-th polynomial model k and it is the normalization result of the initial weight w corresponding to the k-th polynomial model k so as to ensure that the sum of all weights corresponding to all polynomial models included in the temperature prediction mathematical model is 1.

[0088] It should be noted that if the number of all true terminal voltage sampled values of the thermistor included in the characteristic data subset corresponding to the polynomial model is even, then arbitrarily select one from the two true terminal voltage sampled values located in the middle position selected as the median.

[0089] Step S125: According to the K polynomial models and their corresponding K weight mathematical models, determine the initial temperature prediction mathematical model obtained by the K-th round of fitting and denote it as the first mathematical model. Modeling can be performed through weighted summation as follows:

[0090]

[0091] In the formula, ADC is the sampled value of the terminal voltage of the thermistor, which is the input parameter of the initial temperature prediction mathematical model. It can be further understood that it is the input parameter of each polynomial model included in the initial temperature prediction mathematical model, and T p is the predicted temperature value of the thermistor obtained by inputting the sampled value ADC of the terminal voltage of the thermistor into the initial temperature prediction mathematical model for solution.

[0092] Step S126: Obtain the initial temperature prediction mathematical model obtained by the (K - 1)-th round of fitting and denote it as the second mathematical model. Then, according to the characteristic data set, the first mathematical model, and the second mathematical model, determine whether the preset prediction loss function tends to be stable. If so, output the second mathematical model as the final required temperature prediction mathematical model. If not, assign K + 1 to K, and then return to execute the above step S122.

[0093] It should be noted that the above step S122 starts from K = 1. And in the first round of fitting, the initial temperature prediction mathematical model can be directly obtained by performing polynomial fitting on the characteristic data set only according to the fitting loss function. Subsequently, since the initial temperature prediction mathematical model obtained by the (K - 1)-th round of fitting is empty data, it is defaultly judged that the prediction loss function cannot tend to be stable at this time.

[0094] In this application, by performing separate fitting on each characteristic data subset evenly divided from the characteristic data set and then performing weighted summation, the local fitting effect can be optimized, thereby reducing the global fitting error and effectively improving the model fitting accuracy. With the constraint that the prediction loss function tends to be stable, by reasonably adjusting the number of all characteristic data subsets evenly divided from the characteristic data set, it can be ensured that a more accurate and reliable temperature prediction mathematical model can be obtained after data fitting and weighted combination, so as to better reflect the mapping relationship between the temperature value of the thermistor and the sampled value of the terminal voltage, and the disadvantages such as the look-up table method occupying a large amount of storage space and the low accuracy of the general fitting method can be avoided. In addition, the entire model fitting process has flexibility and scalability.

[0095] In step S123 of some embodiments, the fitting loss function includes a first loss function and a second loss function. The first loss function is used to measure the fitting degree of K polynomial models, and the second loss function is used to measure the sparsity degree of the coefficients of each order of the K polynomial models. It is specifically expressed by the following formula:

[0096] L f = L1 + L2,

[0097]

[0098] In the formula, L f is the fitting loss function, L1 is the first loss function, L2 is the second loss function, M k is the number of all characteristic data included in the kth characteristic data subset corresponding to the kth polynomial model, T pk,m is the predicted temperature value of the thermistor obtained by inputting the mth true terminal voltage sampling value of the thermistor included in the kth characteristic data subset into the kth polynomial model for solution, T k,m is the true temperature value corresponding to the mth true terminal voltage sampling value of the thermistor included in the kth characteristic data subset, and λ is the regularization strength, which is used to control sparsity.

[0099] In this application, by introducing sparsity constraints, it is possible to avoid the polynomial model obtained by fitting from being too complex, thereby improving the calculation efficiency. That is, the L1 regularization algorithm is used to make some coefficients in the initial polynomial model as close to zero as possible, so as to remove redundant features and avoid overfitting of the model.

[0100] In step S126 of some embodiments, the prediction loss function is used to measure the prediction loss generated by the initial mathematical model of temperature prediction obtained by any round of fitting for the characteristic data set. The corresponding expression is as follows:

[0101]

[0102] In the formula, RSS is the sum of squared total errors, M is the number of all characteristic data included in the characteristic data set, T m is the true temperature value corresponding to the mth true terminal voltage sampling value of the thermistor included in the characteristic data set, T p,m is the predicted temperature value of the thermistor obtained by inputting the mth true terminal voltage sampling value of the thermistor included in the characteristic data set into the initial mathematical model of temperature prediction for solution.

[0103] In step S126 of some embodiments, based on the characteristic data set, the first mathematical model, and the second mathematical model, it is determined whether a preset prediction loss function tends to be stable. The corresponding implementation process may but is not limited to including the following steps S126.1 to step S126.3:

[0104] Step S126.1: Based on the characteristic data set and the prediction loss function, determine a first prediction loss value corresponding to the first mathematical model and a second prediction loss value corresponding to the second mathematical model;

[0105] In this step, use the first mathematical model to solve all the true terminal voltage sampling values of the thermistor included in the characteristic data set to obtain all the first predicted temperature values of the corresponding thermistor. Then, use the prediction loss function to solve all the true temperature values and all the first predicted temperature values corresponding to all the true terminal voltage sampling values of the thermistor included in the characteristic data set to obtain the first prediction loss value corresponding to the first mathematical model. Similarly, use the second mathematical model to solve all the true terminal voltage sampling values of the thermistor included in the characteristic data set to obtain all the second predicted temperature values of the corresponding thermistor. Then, use the prediction loss function to solve all the true temperature values and all the second predicted temperature values corresponding to all the true terminal voltage sampling values of the thermistor included in the characteristic data set to obtain the second prediction loss value corresponding to the second mathematical model.

[0106] Step S126.2: Determine the relative difference value between the first prediction loss value and the second prediction loss value, which can be calculated using the following expression:

[0107]

[0108] In the formula, RSS k is the first prediction loss value, RSS k-1 is the second prediction loss value, and W is the relative difference value.

[0109] Step S126.3: Based on the relative difference value, determine whether the prediction loss function tends to be stable;

[0110] In this step, compare the relative difference value with a preset relative difference value, and then determine whether the prediction loss function tends to be stable according to the comparison result. In this application, it is preferably set that the preset relative difference value is 20%. Specifically, when the relative difference value is less than or equal to the preset relative difference value, it is determined that the prediction loss function tends to be stable; when the relative difference value is greater than the preset relative difference value, it is determined that the prediction loss function does not tend to be stable.

[0111] In this application, by analyzing the relative prediction loss differences between the initially obtained temperature prediction mathematical models fitted in two adjacent rounds, it can be ensured that the finally determined temperature prediction mathematical model has a high degree of fitting and will not overfit.

[0112] As an improved implementation, by presetting the maximum number of rounds K max , when iteratively executing the above steps S122 to S126 until reaching this maximum number of rounds K max After that, if the prediction loss function still cannot tend to be stable, directly select the initially obtained temperature prediction mathematical model with the smallest corresponding prediction loss value from the K max initially obtained temperature prediction mathematical models as the finally required temperature prediction mathematical model for output. Or considering that the prediction loss values corresponding to the initially obtained temperature prediction mathematical models fitted when gradually increasing K will gradually decrease, then directly use the initially obtained temperature prediction mathematical model fitted in the (K max -1)th round as the finally required temperature prediction mathematical model for output. By limiting the maximum number of rounds K max , the complexity of this temperature prediction mathematical model can be effectively reduced.

[0113] The following details the specific implementation content of a permanent magnet synchronous motor monitoring method provided by an embodiment of this application in conjunction with the accompanying drawings. A permanent magnet synchronous motor monitoring method provided by an embodiment of this application relates to the field of computer technology and can be applied to a terminal, a server, or software running on a terminal or a server. In some embodiments, the terminal can be a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, a vehicle-mounted terminal, etc., but is not limited thereto; the server side can be configured as an independent physical server, or as a server cluster or distributed system composed of multiple physical servers, or as a cloud server providing 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 implementing the above permanent magnet synchronous motor monitoring method, etc., but is not limited to the above forms.

[0114] Please refer to Figure 3 , Figure 3 which is an optional flowchart of a permanent magnet synchronous motor monitoring method provided by an embodiment of this application. This permanent magnet synchronous motor monitoring method can but is not limited to include the following steps S210 to S250:

[0115] Step S210: Obtain multiple current temperature values and multiple sets of historical temperature values corresponding to multiple thermistors, where the multiple thermistors are respectively arranged at multiple key positions of the stator of the permanent magnet synchronous motor;

[0116] Step S220: Determine multiple historical temperature standard deviations corresponding to the multiple thermistors according to the multiple sets of historical temperature values corresponding to the multiple thermistors;

[0117] Step S230: Perform outlier rejection processing on the multiple current temperature values corresponding to the multiple thermistors according to a preset abnormal screening condition and the multiple historical temperature standard deviations corresponding to the multiple thermistors, so as to obtain all the current temperature values corresponding to all the target thermistors;

[0118] Step S240: Optimize all the preset weights corresponding to all the target thermistors according to all the historical temperature standard deviations corresponding to all the target thermistors, where the preset weight corresponding to each target thermistor is used to represent the importance of the key position where the target thermistor is located;

[0119] Step S250: Determine the current stator temperature value of the permanent magnet synchronous motor according to all the current temperature values corresponding to all the target thermistors and all the optimized preset weights.

[0120] In the present application, through arranging corresponding multiple thermistors at multiple key positions of the stator of the permanent magnet synchronous motor for comprehensive monitoring, and by quantifying the temperature value fluctuation of each thermistor to assist in screening out all the temperature values corresponding to all the non-abnormal target thermistors, and then using the temperature value fluctuation of each target thermistor to optimize the preset weight corresponding to the target thermistor, it is beneficial to more accurately and reliably determine the stator temperature of the permanent magnet synchronous motor.

[0121] In step S210 of some embodiments, the multiple key positions of the stator of the permanent magnet synchronous motor include the stator winding and the inside of the stator slots of the permanent magnet synchronous motor, and the arrangement of the multiple thermistors at the multiple key positions of the stator of the permanent magnet synchronous motor is as Figure 4 shown. The number of arranged thermistors can be determined according to the structure and size of the permanent magnet synchronous motor. Among them: the left figure is a top view of the stator of the permanent magnet synchronous motor, mainly showing the distribution of some thermistors in the stator winding of the permanent magnet synchronous motor; the right figure is a side view of the stator of the permanent magnet synchronous motor, mainly showing the distribution of some thermistors inside the stator slots of the permanent magnet synchronous motor.

[0122] In step S210 of some embodiments, the current temperature value and the set of historical temperature values of each thermistor are obtained by the above-mentioned thermistor temperature prediction method, and the corresponding implementation manners include the following:

[0123] For each thermistor, obtain the sampled terminal voltage value of the thermistor at the current moment and input it into a pre-determined temperature prediction mathematical model associated with the thermistor for solution, so as to obtain the predicted temperature value of the thermistor at the current moment and record it as the current temperature value of the thermistor; and obtain multiple sampled terminal voltage values corresponding to the thermistor at multiple consecutive historical moments before the current moment and input them into the temperature prediction mathematical model associated with the thermistor for solution, so as to obtain multiple predicted temperature values corresponding to the thermistor at the multiple consecutive historical moments and summarize them to form the historical temperature value set of the thermistor.

[0124] In step S220 of some embodiments, for each thermistor, according to the historical temperature value set of the thermistor, determine the historical temperature standard deviation of the thermistor, which can be calculated by the following formula:

[0125]

[0126] In the formula, s is the historical temperature standard deviation of the thermistor, R is the number of all predicted temperature values included in the historical temperature value set of the thermistor, T gr is the r-th predicted temperature value included in the historical temperature value set of the thermistor, is the average value of all predicted temperature values included in the historical temperature value set of the thermistor.

[0127] In step S230 of some embodiments, considering that when the thermistor is damaged, the measured temperature value may be too high or too low, the temperature value fluctuation range is too large, the temperature value remains unchanged or the temperature value is zero, etc., set the abnormal screening condition to include that the current temperature value of the thermistor does not fall within the preset reasonable temperature range and the historical temperature standard deviation of the thermistor does not fall within the preset reasonable temperature standard deviation range.

[0128] In step S230 of some embodiments, according to the multiple historical temperature standard deviations and multiple current temperature values corresponding to multiple thermistors, eliminate each thermistor that meets the abnormal screening condition from the multiple thermistors, and then use all the remaining thermistors that have not been eliminated as all target thermistors, so as to ensure that the current temperature value of each target thermistor falls within the reasonable temperature range and the historical temperature standard deviation of each target thermistor falls within the reasonable temperature standard deviation range, that is, it is determined that all target thermistors are not damaged.

[0129] In step S240 of some embodiments, first, all historical temperature standard deviations corresponding to all target thermistors are screened to extract the maximum historical temperature standard deviation therefrom; for each target thermistor, the preset weight corresponding to the target thermistor is then optimized according to the maximum historical temperature standard deviation and the historical temperature standard deviation of the target thermistor, and the following formula can be used for the optimization calculation:

[0130]

[0131] In the formula, s tmax is the maximum historical temperature standard deviation, s t is the historical temperature standard deviation of the target thermistor, w tbase is the preset weight corresponding to the target thermistor, and w t is the optimized preset weight corresponding to the target thermistor.

[0132] It should be noted that after arranging corresponding multiple thermistors at multiple key positions of the stator of the permanent magnet synchronous motor, the preset weight corresponding to each thermistor is determined according to the importance of the key position where each thermistor is located. The importance of the key position where the thermistor is located refers to the degree to which the temperature value measured by the thermistor can directly reflect the stator temperature value, and the following formula can be used for calculation:

[0133]

[0134] In the formula, H is the number of multiple thermistors, P h is the importance score of the key position where the h-th thermistor is located, which is mainly set based on engineering experience, and w base,h is the preset weight corresponding to the h-th thermistor.

[0135] In the present application, considering that the measurement data will fluctuate when there is external interference on the thermistor, in order to suppress this interference effect, the weight distribution of the thermistor can be optimized by introducing the historical temperature standard deviation. When the measurement data of the thermistor fluctuates greatly, its corresponding preset weight is decreased, and when the measurement data of the thermistor fluctuates slightly, its corresponding preset weight can be slightly adjusted.

[0136] In step S250 of some embodiments, the sum of all optimized preset weights corresponding to all target thermistors is calculated to obtain the total preset weight; according to all optimized preset weights corresponding to all target thermistors, the weighted sum of all current temperature values corresponding to all target thermistors is calculated; the weighted sum result is divided by the total preset weight to obtain the current stator temperature value of the permanent magnet synchronous motor; the following formula can be used for calculation:

[0137]

[0138] In the formula, T avg is the current stator temperature value of the permanent magnet synchronous motor, and H t is the number of all target thermistors, and w t,h is the optimized preset weight corresponding to the h-th target thermistor, and T tc,h is the current temperature value of the h-th target thermistor.

[0139] In some embodiments, in order to globally monitor the operating conditions of the permanent magnet synchronous motor, after determining the current stator temperature value of the permanent magnet synchronous motor, the following operations may be continued:

[0140] Obtain the current operating parameter values of the permanent magnet synchronous motor. The current operating parameter values of the permanent magnet synchronous motor include the current three-phase voltage value, the current three-phase current value, the current rotational speed value, and the current torque value of the permanent magnet synchronous motor, and then perform visual display together with the current stator temperature value of the permanent magnet synchronous motor.

[0141] Among them, the current three-phase voltage value and the current three-phase current value of the permanent magnet synchronous motor can be obtained by collecting the three-phase power supply lines of the permanent magnet synchronous motor through a three-phase electrical parameter collector, and the current rotational speed value and the current torque value of the permanent magnet synchronous motor can be obtained by collecting through a rotational speed and torque sensor arranged on the connection line between the permanent magnet synchronous motor and the load.

[0142] In this application, the three-phase electrical parameter collector, the rotational speed and torque sensor, and the microcontroller for collecting the terminal voltage sampling values of each thermistor can be connected to the upper computer through a data transmission bus, and the upper computer executes the above-mentioned thermistor temperature prediction method and the above-mentioned permanent magnet synchronous motor monitoring method.

[0143] As an improved implementation manner, obtain multiple consecutive historical stator temperature values corresponding to multiple historical moments before the current moment of the permanent magnet synchronous motor, and then generate a real-time stator temperature change curve image together with the current stator temperature value of the permanent magnet synchronous motor and perform visual display; similarly, for any type of operating parameter of the permanent magnet synchronous motor, denote it as the target operating parameter, obtain multiple historical target operating parameter values corresponding to multiple consecutive historical moments before the current moment of the permanent magnet synchronous motor, and then generate a real-time target operating parameter change curve image together with the current target operating parameter value of the permanent magnet synchronous motor and perform visual display. For example, obtain multiple historical three-phase voltage values corresponding to multiple consecutive historical moments before the current moment of the permanent magnet synchronous motor, and then generate a real-time three-phase voltage change curve image together with the current three-phase voltage value of the permanent magnet synchronous motor and perform visual display.

[0144] Further, a real-time temperature change curve of the thermistor is generated based on the current temperature value and the set of historical temperature values of each thermistor, and then the generated temperature change curves of multiple thermistors are combined and summarized to form an integrated thermistor temperature change curve image for visual display.

[0145] Further, based on the current three-phase voltage value and the current three-phase current value of the permanent magnet synchronous motor, relevant electrical parameter values such as the three-phase active power, total active power, three-phase reactive power, total reactive power, and three-phase power factor of the permanent magnet synchronous motor are calculated and visually displayed.

[0146] In some embodiments, after determining the current stator temperature value of the permanent magnet synchronous motor, the following operations can be continued:

[0147] When at least one of the multiple thermistors has an abnormal detection, thermistor abnormal detection information is generated and visually displayed, enabling technicians to promptly repair or replace the thermistor with an abnormal detection; wherein, the thermistor abnormal detection information includes the number and abnormal type of the thermistor with an abnormal detection, the abnormal type includes abnormal temperature value fluctuation of the thermistor and / or abnormal temperature value of the thermistor, the abnormal temperature value fluctuation of the thermistor means that the historical temperature standard deviation of the thermistor does not fall within the reasonable range of the temperature standard deviation, and the abnormal temperature value of the thermistor means that the current temperature value of the thermistor does not fall within the reasonable range of the temperature, that is, the current temperature value of the thermistor is too high or too low or even zero.

[0148] It should be noted that after technicians deploy corresponding multiple thermistors at multiple key positions of the stator of the permanent magnet synchronous motor, a unique number will be set for each thermistor, as Figure 4 shown.

[0149] In some embodiments, after determining the current stator temperature value of the permanent magnet synchronous motor, the following operations can be continued:

[0150] By setting a display control on the visualization interface in advance, the display control serves as a high-temperature warning light. When it is detected that the current stator temperature value of the permanent magnet synchronous motor exceeds the preset temperature threshold, the display control is controlled to light up, enabling technicians to promptly adjust the operating state of the permanent magnet synchronous motor.

[0151] It should be noted that all types of data and curve images mentioned above for visual display can be simultaneously displayed on the visualization interface, enabling technicians to quickly make monitoring judgments.

[0152] Please refer to Figure 5 ,Figure 5 FIG. Figure 5 is an alternative structural composition schematic diagram of a thermistor temperature prediction system provided by an embodiment of the present application, which can implement the above-mentioned thermistor temperature prediction method. The thermistor temperature prediction system may but is not limited to include the following:

[0153] A first acquisition module 310, configured to acquire the terminal voltage sampling value of the thermistor;

[0154] A solution module 320, configured to input the terminal voltage sampling value of the thermistor into a pre-determined temperature prediction mathematical model associated with the thermistor for solution to obtain the predicted temperature value of the thermistor; wherein, the temperature prediction mathematical model is obtained by weighted summation of a plurality of polynomial models, each polynomial model is used to characterize the functional relationship between the temperature value of the thermistor and the terminal voltage sampling value, and the weight corresponding to each polynomial model is used to characterize the proximity between the terminal voltage sampling value of the thermistor and the preset voltage sampling value corresponding to the polynomial model.

[0155] It can be understood that the content in the above-mentioned thermistor temperature prediction method embodiment is applicable to the thermistor temperature prediction system embodiment. The functions specifically implemented by the thermistor temperature prediction system embodiment are the same as those specifically implemented by the above-mentioned thermistor temperature prediction method embodiment, and the beneficial effects achieved by the thermistor temperature prediction system are also the same as those achieved by the above-mentioned thermistor temperature prediction method embodiment.

[0156] Please refer to Figure 6 , Figure 6 FIG. Figure 6 is an alternative structural composition schematic diagram of a permanent magnet synchronous motor monitoring system provided by an embodiment of the present application, which can implement the above-mentioned permanent magnet synchronous motor monitoring method. The permanent magnet synchronous motor monitoring system may but is not limited to include the following:

[0157] A second acquisition module 410, configured to acquire a plurality of current temperature values and a plurality of historical temperature value sets corresponding to a plurality of thermistors. The plurality of thermistors are respectively arranged at a plurality of key positions of the stator of the permanent magnet synchronous motor, and the current temperature value and the historical temperature value set of each thermistor are obtained by the above-mentioned thermistor temperature prediction method;

[0158] A first determination module 420, configured to determine a plurality of historical temperature standard deviations corresponding to the plurality of thermistors according to the plurality of historical temperature value sets corresponding to the plurality of thermistors;

[0159] A processing module 430, configured to perform outlier rejection processing on the plurality of current temperature values corresponding to the plurality of thermistors according to a preset abnormal screening condition and the plurality of historical temperature standard deviations corresponding to the plurality of thermistors to obtain all the current temperature values corresponding to all the target thermistors;

[0160] An optimization module 440 is configured to optimize all preset weights corresponding to all target thermistors according to all historical temperature standard deviations corresponding to all target thermistors, where the preset weight corresponding to each target thermistor is used to characterize the importance of the critical position where the target thermistor is located.

[0161] A second determination module 450 is configured to determine the current stator temperature value of the permanent magnet synchronous motor according to all current temperature values corresponding to all target thermistors and all optimized preset weights.

[0162] It can be understood that the content in the above embodiments of the permanent magnet synchronous motor monitoring method is applicable to the embodiments of the permanent magnet synchronous motor monitoring system. The functions specifically implemented by the embodiments of the permanent magnet synchronous motor monitoring system are the same as those specifically implemented by the above embodiments of the permanent magnet synchronous motor monitoring method, and the beneficial effects achieved by the embodiments of the permanent magnet synchronous motor monitoring system are also the same as those achieved by the above embodiments of the permanent magnet synchronous motor monitoring method.

[0163] An embodiment of the present application further provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the above-mentioned thermistor temperature prediction method or the above-mentioned permanent magnet synchronous motor monitoring method. The electronic device may include any intelligent terminal such as a tablet computer or an in-vehicle computer.

[0164] It can be understood that for any of the above method embodiments, the content in the method embodiments is applicable to the embodiments of this device. The functions specifically implemented by the embodiments of this device are the same as those specifically implemented by the method embodiments, and the beneficial effects achieved by the embodiments of this device are also the same as those achieved by the method embodiments.

[0165] Please refer to Figure 7 , Figure 7 which shows the hardware structure of an electronic device in another embodiment. The electronic device includes:

[0166] A processor 501, which can be implemented in a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., and is configured to execute relevant programs to implement the technical solutions provided by the embodiments of the present application;

[0167] The memory 502 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), etc. The memory 502 can store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of the present application through software or firmware, the relevant program codes are stored in the memory 502 and are called by the processor 501 to execute the technical solutions provided in the embodiments of the present application;

[0168] The input / output interface 503 is used to implement information input and output;

[0169] The communication interface 504 is used to implement communication interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.);

[0170] The bus 505 transmits information between the various components of the device (such as the processor 501, the memory 502, the input / output interface 503, and the communication interface 504);

[0171] Among them, the processor 501, the memory 502, the input / output interface 503, and the communication interface 504 achieve communication connections with each other inside the device through the bus 505.

[0172] The embodiments of the present application also provide a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the above-mentioned thermistor temperature prediction method or the above-mentioned permanent magnet synchronous motor monitoring method.

[0173] It can be understood that for any of the above method embodiments, the content in the method embodiments is applicable to the storage medium embodiments. The functions specifically implemented by the storage medium embodiments are the same as the functions specifically implemented by the method embodiments, and the beneficial effects achieved by the storage medium embodiments are also the same as the beneficial effects achieved by the method embodiments.

[0174] As a non-transitory computer-readable storage medium, the memory can be used to store non-transitory software programs and non-transitory computer-executable programs. In addition, the memory can include high-speed random access memory, and can also include non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory optionally includes a memory remotely set relative to the processor, and these remote memories can be connected to the processor through a network. Examples of the above network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0175] The embodiments described in the embodiments of the present application are for more clearly illustrating the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. As those skilled in the art know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of the present application are equally applicable to similar technical problems.

[0176] Those skilled in the art can understand 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 those shown in the figures, or combine certain steps, or different steps.

[0177] The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0178] Those of ordinary skill in the art can understand that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, and their appropriate combinations.

[0179] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0180] It should be understood that in this application, "at least one (item)" means one or more, and "a plurality" means two or more. "And / or" is used to describe the association relationship of associated objects and indicates that three relationships may exist. For example, "A and / or B" may mean: only A exists, only B exists, and both A and B exist at the same time. Among them, A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after. "At least one (one)" or its similar expression below refers to any combination of these items, including any combination of single items (one) or plural items (ones). For example, at least one (one) of a, b, or c may 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.

[0181] In several embodiments provided in this 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 merely illustrative. For example, the above-mentioned division of units is only a logical function division. In actual implementation, there may be other division methods. For example, 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 displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of the system or unit can be in an electrical, mechanical or other form.

[0182] The units described above as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0183] In addition, each functional unit in various embodiments of this application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0184] When an integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of various embodiments of this application. The aforementioned storage medium includes: various media that can store programs such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0185] The preferred embodiments of the embodiments of this application have been described above with reference to the accompanying drawings, which does not limit the scope of the rights of the embodiments of this application. Any modifications, equivalent replacements, and improvements made by those skilled in the art without departing from the scope and essence of the embodiments of this application shall be within the scope of the rights of the embodiments of this application.

Claims

1. A thermistor temperature prediction method, characterized in that: include: Get the terminal voltage sampling value of the thermistor; Inputting the terminal voltage sampling value of the thermistor into a predetermined temperature prediction mathematical model associated with the thermistor for solving, to obtain a predicted temperature value of the thermistor; Among them, the temperature prediction mathematical model is obtained by weighted summation of multiple polynomial models, each of the polynomial models is used to characterize the functional relationship between the temperature value of the thermistor and the terminal voltage sampling value, and the weight corresponding to each polynomial model is used to characterize the degree of proximity between the terminal voltage sampling value of the thermistor and the preset voltage sampling value corresponding to the polynomial model.

2. The thermistor temperature prediction method according to claim 1, characterized in that: The temperature prediction mathematical model is obtained by the following method: Acquire a characteristic data set of the thermistor, wherein the characteristic data set includes a plurality of characteristic data, each of which includes a real temperature value of the thermistor and a corresponding real terminal voltage sampling value; Starting the Kth round of fitting, the characteristic data set is evenly divided into K characteristic data subsets; According to a preset fitting loss function, polynomial fitting is performed on the K characteristic data subsets respectively to obtain corresponding K polynomial models; For each of the polynomial models, according to all the real terminal voltage sampling values ​​of the thermistor included in the characteristic data subset corresponding to the polynomial model, the preset voltage sampling value corresponding to the polynomial model is determined, and then the weight mathematical model corresponding to the polynomial model is determined in combination with the Gaussian kernel function; According to the K polynomial models and their corresponding K weight mathematical models, an initial mathematical model for temperature prediction obtained by the K-th round of fitting is determined and recorded as a first mathematical model; Obtain the initial mathematical model for temperature prediction obtained by the K-1th round of fitting and record it as the second mathematical model; According to the characteristic data set, the first mathematical model and the second mathematical model, determining whether a preset prediction loss function tends to be stable; If yes, then use the second mathematical model as the temperature prediction mathematical model; If not, assign K+1 to K, and then return to the step of starting the Kth round of fitting to evenly divide the characteristic data set into K characteristic data subsets.

3. The thermistor temperature prediction method according to claim 2, characterized in that: The fitting loss function includes a first loss function and a second loss function, wherein the first loss function is used to measure the degree of fitting of the K polynomial models, and the second loss function is used to measure the sparsity of coefficients of each order of the K polynomial models.

4. The thermistor temperature prediction method according to claim 2, characterized in that: The step of judging whether a preset prediction loss function tends to be stable according to the characteristic data set, the first mathematical model and the second mathematical model comprises: Determining, according to the characteristic data set and the prediction loss function, a first prediction loss value corresponding to the first mathematical model and a second prediction loss value corresponding to the second mathematical model; Determine a relative difference between the first predicted loss value and the second predicted loss value, and then determine whether the predicted loss function tends to be stable based on the relative difference.

5. A permanent magnet synchronous motor monitoring method, characterized in that: include: Acquire multiple current temperature values ​​and multiple historical temperature value sets corresponding to multiple thermistors, wherein the multiple thermistors are respectively arranged at multiple key positions of the stator of the permanent magnet synchronous motor, and the current temperature value and historical temperature value set of each thermistor are obtained by the thermistor temperature prediction method according to any one of claims 1 to 4; Determining a plurality of historical temperature standard deviations corresponding to the plurality of thermistors according to a plurality of historical temperature value sets corresponding to the plurality of thermistors; According to a preset abnormal screening condition and a plurality of historical temperature standard deviations corresponding to the plurality of thermistors, an abnormal value elimination process is performed on a plurality of current temperature values ​​corresponding to the plurality of thermistors to obtain all current temperature values ​​corresponding to all target thermistors; According to all historical temperature standard deviations corresponding to all target thermistors, all preset weights corresponding to all target thermistors are optimized, wherein the preset weight corresponding to each target thermistor is used to characterize the importance of a key position where the target thermistor is located; The current stator temperature value of the permanent magnet synchronous motor is determined according to all current temperature values ​​corresponding to all target thermistors and all optimized preset weights.

6. The permanent magnet synchronous motor monitoring method according to claim 5, characterized in that: After determining the current stator temperature value of the permanent magnet synchronous motor, the method includes: Obtaining current operating parameter values ​​of the permanent magnet synchronous motor, the current operating parameter values ​​of the permanent magnet synchronous motor including the current three-phase voltage value, the current three-phase current value, the current speed value and the current torque value of the permanent magnet synchronous motor, and then visually displaying them together with the current stator temperature value of the permanent magnet synchronous motor; When at least one of the plurality of thermistors has a detection abnormality, thermistor abnormality detection information is generated and visualized.

7. A thermistor temperature prediction system, characterized in that: include: A first acquisition module is used to acquire a terminal voltage sampling value of the thermistor; A solution module, used for inputting the terminal voltage sampling value of the thermistor into a predetermined temperature prediction mathematical model associated with the thermistor for solution to obtain a predicted temperature value of the thermistor; Among them, the temperature prediction mathematical model is obtained by weighted summation of multiple polynomial models, each of the polynomial models is used to characterize the functional relationship between the temperature value of the thermistor and the terminal voltage sampling value, and the weight corresponding to each polynomial model is used to characterize the degree of proximity between the terminal voltage sampling value of the thermistor and the preset voltage sampling value corresponding to the polynomial model.

8. A permanent magnet synchronous motor monitoring system, characterized in that: include: A second acquisition module is used to acquire a plurality of current temperature values ​​and a plurality of historical temperature value sets corresponding to a plurality of thermistors, wherein the plurality of thermistors are respectively arranged at a plurality of key positions of the stator of the permanent magnet synchronous motor, and the current temperature value and the historical temperature value set of each thermistor are obtained by the thermistor temperature prediction method according to any one of claims 1 to 4; A first determination module, configured to determine a plurality of historical temperature standard deviations corresponding to the plurality of thermistors according to a plurality of historical temperature value sets corresponding to the plurality of thermistors; A processing module, configured to perform abnormal value elimination processing on multiple current temperature values ​​corresponding to the multiple thermistors according to a preset abnormal screening condition and multiple historical temperature standard deviations corresponding to the multiple thermistors, so as to obtain all current temperature values ​​corresponding to all target thermistors; An optimization module, used for optimizing all preset weights corresponding to all target thermistors according to all historical temperature standard deviations corresponding to all target thermistors, wherein the preset weight corresponding to each target thermistor is used to characterize the importance of a key position where the target thermistor is located; The second determination module is used to determine the current stator temperature value of the permanent magnet synchronous motor according to all current temperature values ​​corresponding to all target thermistors and all optimized preset weights.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the thermistor temperature prediction method described in any one of claims 1 to 4 or the permanent magnet synchronous motor monitoring method described in any one of claims 5 to 6 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 thermistor temperature prediction method described in any one of claims 1 to 4 or the permanent magnet synchronous motor monitoring method described in any one of claims 5 to 6 is implemented.

Images