A temperature regulation method for liquid-cooled supercharged power supply module

Abstract

The present application relates to the field of temperature control technology, and specifically to a temperature regulation method for a liquid-cooled supercharged power supply module. The method includes: collecting temperature values ​​and parameter values, obtaining temperature stability based on the difference in temperature values ​​within a cycle and the difference from the standard temperature; classifying the cycles according to temperature stability, clustering the filtered cycles, obtaining the degree of influence of the parameters on temperature stability based on the difference in temperature stability and parameter values ​​between the cycles and the cluster clusters, and obtaining the importance of each parameter based on this, clustering all cycles to select target clusters, obtaining reference weights based on the similarity and temperature stability of the cycles in the target cluster clusters, obtaining proportional coefficient adjustment parameters through proportional coefficient differences and reference weights; obtaining the proportional coefficient of the current cycle based on the proportional coefficient adjustment parameters, and controlling the temperature value based on this. The present application improves the accuracy of temperature control.

Description

Technical Field

[0001] The present application relates to the field of temperature control technology, and in particular to a method for regulating the temperature of a liquid-cooled supercharged power supply module. Background Art

[0002] Modern power supply systems require not only high performance, but also intelligent monitoring and adjustment capabilities to ensure stable and efficient operation of the system. During high-power charging, the power module will generate a lot of heat. If the heat is not dissipated in time, it will seriously affect the performance and life of the power module. Liquid cooling technology can effectively reduce the temperature of the power module and improve its reliability and service life. If the temperature of the power module is too high, the power performance and life will be damaged; if it is too low, the power performance will be reduced. Therefore, a PID control system is used to adjust the temperature of the power module. Since the proportional coefficient will affect the adjustment result, and in general, this coefficient is a fixed value, using a fixed value for different scenarios may result in poor temperature control and affect the power performance. Therefore, it is necessary to analyze and adjust the proportional coefficient to adapt to different scenarios. Summary of the invention

[0003] In order to solve the technical problem of poor temperature control effect, the present application provides a liquid-cooled supercharged power supply module temperature adjustment method, and the technical solution adopted is as follows:

[0004] The present application proposes a method for regulating the temperature of a liquid-cooled supercharged power source module, the method comprising the following steps:

[0005] Take the preset time as a cycle and obtain the proportional coefficient of the cycle; collect the parameter values ​​and temperature values ​​of various parameters of the power module at each moment;

[0006] The temperature stability of each cycle is obtained according to the difference between the mean temperature value in each cycle and the temperature value at each moment in the cycle, and the difference between the temperature value at each moment in the cycle and the preset standard temperature;

[0007] The cycles are classified according to temperature stability, the cycles corresponding to a class with large temperature stability are screened and saved, and the screened cycles are clustered according to the proportional coefficient; the influence of each parameter on the temperature stability is obtained according to the difference between the temperature stability of each parameter in the cycle, the parameter value and the mean of the temperature stability of all cycles of each parameter in the clustering cluster, and the mean of the parameter value; the importance of each parameter is obtained according to the difference between the influence of each parameter on the temperature stability and the influence of all parameters on the temperature stability; all the screened cycles are clustered according to the parameter value difference and the parameter importance weighted as the clustering distance, and the target clustering cluster is screened; the target clustering cluster is a clustering cluster including the target cycle, and the target cycle is the cycle before the current cycle;

[0008] The periods other than the target period in the target cluster are recorded as historical periods, and the reference weight of each historical period is obtained according to the similarity between the historical period and the target period and the temperature stability of the historical period; the difference between the proportional coefficient of the historical period and its previous period is weighted by the reference weight to obtain the proportional coefficient adjustment parameter;

[0009] The temperature stability of the target cycle is used as a weight, and the proportional coefficient of the target cycle and the proportional coefficient adjustment parameter are combined to obtain the adjusted proportional coefficient of the current cycle; the temperature value is controlled according to the adjusted proportional coefficient of the current cycle.

[0010] In the above scheme, the present application obtains the temperature control effect of the proportional coefficient based on the temperature change after adjusting different proportional coefficients, and digitizes the effect of temperature control by the proportional coefficient for subsequent analysis; at the same time, the influence of various parameters on the temperature control effect is analyzed, and the parameters are classified according to the influence of different parameters, which greatly avoids the clustering results affected by the parameters that have little influence on the proportional coefficient, increases the unreliability of the reference historical data, and increases the inaccuracy of the adjustment parameters; further, the proportional coefficient adjustment reference value is obtained according to the historical data obtained by clustering, and the obtained proportional coefficient adjustment value is more valuable for reference based on the similarity between the temperature adjustment results and the adjustment scenes under different historical data; finally, the final proportional coefficient adjustment value is determined in combination with the analysis of the proportional coefficient adjustment effect at the previous moment, and the proportional coefficient is adjusted, which increases the adaptability of the PID control system to changes in different scenes, avoids the situation where the temperature control effect may not be ideal due to the fixed proportional coefficient, improves the accuracy of temperature control, and avoids various losses due to unsatisfactory temperature adjustment.

[0011] In one embodiment, the parameters include liquid supply temperature, cold water tank temperature, hot water tank temperature, ambient temperature, liquid supply pressure and liquid supply flow rate.

[0012] In one embodiment, the method for obtaining the temperature stability of each cycle according to the difference between the mean of the temperature values ​​in each cycle and the temperature value at each moment in the cycle and the difference between the temperature value at each moment in the cycle and the preset standard temperature is:

[0013] Calculate the mean of the temperature values ​​at all times in each cycle and record it as the first mean;

[0014] The temperature stability of each cycle is negatively correlated with the difference between the temperature value at each moment and the first mean value, and the difference between the temperature value at each moment and the standard temperature.

[0015] In one embodiment, the method for obtaining the influence of each parameter on the temperature stability according to the difference between the periodic temperature stability and parameter value of each parameter and the mean value of all periodic temperature stabilities and parameter values ​​of each parameter in the cluster is:

[0016] For each parameter, the mean of all parameter values ​​of the parameter in each cycle is recorded as the parameter value of each cycle; the expression of the influence of each parameter on temperature stability is:

[0017] ,in represents the parameter value of the ath parameter in the uth period, represents the temperature stability of the u-th cycle, represents the mean value of the parameter value of the ath parameter in the kth cluster, represents the mean of the temperature stability of all cycles in the kth cluster, represents the number of cycles in the kth cluster, represents the number of clusters, represents an exponential function with a natural constant as base, Indicates the influence of the ath parameter on temperature stability.

[0018] In one embodiment, the method for obtaining the importance of each parameter according to the difference between the influence degree of each parameter on the temperature stability and the influence degree of all parameters on the temperature stability is:

[0019] The expression for the importance of each parameter is:

[0020] , Indicates the number of parameter types, Indicates the importance of the ath parameter, Indicates the influence of the ath parameter on temperature stability.

[0021] In one embodiment, the method of clustering all post-screening cycles according to the parameter value difference and the parameter importance weight as the clustering distance to screen the target cluster cluster is:

[0022] For all cycles, clustering is performed based on the differences in all parameter values;

[0023] The expression of cluster distance is:

[0024] , Indicates the parameter value of the ath parameter of the cluster center, represents the parameter value of the ath parameter in the uth period, represents the cluster distance between the uth period and the cluster center, represents the number of parameter types, Indicates the importance of the ath parameter.

[0025] In one embodiment, the method for obtaining the reference weight of each historical period according to the similarity between the historical period and the target period and the temperature stability of the historical period is:

[0026] The expression of reference weight is:

[0027] , represents the temperature stability of the s-th historical period, represents the similarity between the sth historical period and the target period, represents the number of historical periods, Represents the reference weight of the historical period.

[0028] In one embodiment, the method of obtaining the proportionality coefficient adjustment parameter by weighting the difference between the proportionality coefficient of the historical period and the previous period by reference weight is:

[0029] The expression of the proportional coefficient adjustment parameter is:

[0030] , It represents the difference between the proportional coefficient of the sth historical period and its next period. represents the proportional coefficient adjustment parameter, represents the reference weight of the historical period, Indicates the number of historical periods.

[0031] In one embodiment, the method of taking the temperature stability of the target cycle as the weight and combining the proportional coefficient of the target cycle and the proportional coefficient adjustment parameter to obtain the adjusted proportional coefficient of the current cycle is:

[0032] The expression of the proportional coefficient after the current cycle adjustment is:

[0033] , represents the temperature stability of the tth cycle, represents the proportional coefficient of the tth period, Represents the proportional coefficient after adjustment of the current cycle; the tth cycle is the target cycle, Represents the proportional coefficient adjustment parameter.

[0034] In one embodiment, the method for controlling the temperature value according to the proportional coefficient adjusted in the current cycle is:

[0035] Input the integral coefficient, differential coefficient and adjusted proportional coefficient of PID control, as well as the collected temperature value and target temperature value, and output the adjusted temperature value at each moment through the PID control system.

[0036] The beneficial effects of this application are:

[0037] This application obtains the temperature control effect of the proportional coefficient based on the temperature change after adjusting different proportional coefficients, and digitizes the effect of temperature control by the proportional coefficient for subsequent analysis; at the same time, the influence of various parameters on the temperature control effect is analyzed, and classification is carried out according to the influence degree of different parameters, which greatly avoids the clustering result affected by the parameters that have little influence on the proportional coefficient, increases the unreliability of the reference historical data, and increases the inaccuracy of the adjustment parameters; further, the proportional coefficient adjustment reference value is obtained according to the historical data obtained by clustering, and the obtained proportional coefficient adjustment value is more valuable for reference according to the similarity between the temperature adjustment results and the adjustment scenes under different historical data; finally, the final proportional coefficient adjustment value is determined in combination with the analysis of the proportional coefficient adjustment effect at the previous moment, and the proportional coefficient is adjusted, which increases the adaptability of the PID control system to changes in different scenes, avoids the situation where the temperature control effect may not be ideal due to the fixed proportional coefficient, improves the accuracy of temperature control, and avoids various losses due to unsatisfactory temperature adjustment. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0039] Figure 1 A flow chart of a method for regulating temperature of a liquid-cooled supercharged power source module provided in one embodiment of the present application;

[0040] Figure 2 Flowchart for obtaining target clusters for screening. DETAILED DESCRIPTION

[0041] In order to further explain the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the following is a detailed description of the temperature adjustment method of a liquid-cooled supercharged power module proposed in the present application, its specific implementation, structure, features and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0042] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0043] A liquid-cooled supercharged power module temperature adjustment method embodiment:

[0044] The specific scheme of the temperature regulation method of a liquid-cooled supercharging power supply module provided by the present application is described in detail below with reference to the accompanying drawings.

[0045] See also Figure 1 , which shows a flow chart of a liquid-cooled supercharged power supply module temperature adjustment method provided by an embodiment of the present application, the method comprising the following steps:

[0046] Step S001, taking a preset time as a cycle, obtaining a proportional coefficient of the cycle; collecting parameter values ​​and temperature values ​​of various parameters of the power module at each moment.

[0047] Various data of the power module are collected by various sensors. In this embodiment, the liquid supply temperature, cold water tank temperature, hot water tank temperature, ambient temperature, liquid supply pressure and liquid supply flow rate are collected. The ambient temperature is the temperature value of the power module. Except for the ambient temperature, which is the data that must be collected, the rest of the data can be selected and collected by the implementer. The temperature sensor uses a three-wire platinum thermal resistance temperature sensor. The collected data of several different types are respectively used as a parameter.

[0048] For all the above parameters, data is collected once every minute, with ten minutes as a cycle. Each cycle has a proportional coefficient. The data collected within the cycle is the data collected after being controlled by the proportional coefficient corresponding to the cycle. When a new cycle is reached, the proportional coefficient of the previous cycle is the proportional coefficient of the current cycle. After the proportional coefficient of the current cycle is adjusted, the parameter values ​​and temperature values ​​of the current cycle are collected again.

[0049] At this point, the temperature value for each minute and the data values ​​of the other parameters as well as the proportional coefficient for each cycle are obtained.

[0050] Step S002, obtaining the temperature stability of each cycle according to the difference between the mean value of the temperature value in each cycle and the temperature value at each moment in the cycle and the difference between the temperature value at each moment in the cycle and the preset standard temperature.

[0051] Since different proportional coefficients have different control degrees for temperature values, different temperature values ​​need to be controlled by different proportional coefficients, so the proportional coefficient needs to be adjusted, where the proportional coefficient of each cycle is the adjusted proportional coefficient, and the adjusted proportional coefficient of each cycle is the proportional coefficient before adjustment of the next cycle.

[0052] When using PID control for regulation, you first need to set the standard temperature for regulation. The standard temperature of the power module is , in this embodiment The value of is 60. The mean temperature value in each cycle is calculated, and the temperature stability is obtained according to the difference between the temperature value at each moment in each cycle and the mean temperature value in the cycle and the difference with the standard temperature. The temperature stability is negatively correlated with the difference between the temperature value and the mean and the difference between the temperature value and the standard temperature.

[0053] It should be noted that negative correlation means that when one variable increases, the other variable decreases accordingly, and the two variables change in opposite directions. When one variable changes from large to small or from small to large, the other variable also changes from small to large or from large to small. The specific relationship is determined by actual application and this application does not impose any special restrictions.

[0054] Preferably, in this embodiment, the temperature stability expression is: ,in, is the temperature value at the i-th moment in the cycle, is the mean temperature value within the period, Indicates standard temperature, represents the number of moments in the period, represents the linear normalization function, Indicates the temperature stability per cycle.

[0055] Preferably, in another embodiment of the present application, the temperature stability expression is: .

[0056] The control ability of the proportional coefficient corresponding to each cycle is analyzed by the change of the temperature value in each cycle. If the difference between the temperature value and the standard temperature is greater, it means that the temperature value is far away from the standard temperature, and the control effect of the current proportional coefficient is worse; if the difference between the temperature value and the average temperature value in the cycle is greater, it means that the temperature value in the cycle changes greatly, indicating that the control effect of the current proportional coefficient is poor. When the temperature value is closer to the standard temperature and the change of the temperature value in the cycle is smaller, it means that the control effect of the current proportional coefficient is better and the temperature stability is greater.

[0057] At this point, the temperature stability of each cycle is obtained.

[0058] Step S003, classify the cycles according to temperature stability, filter and save the cycles corresponding to a category with large temperature stability, and cluster the filtered cycles according to the proportional coefficient; obtain the influence of each parameter on the temperature stability according to the difference between the temperature stability of each parameter in the cycle, the parameter value and the mean of the temperature stability of all cycles of each parameter in the clustering cluster, and the mean of the parameter value; obtain the importance of each parameter according to the difference between the influence of each parameter on the temperature stability and the influence of all parameters on the temperature stability; cluster all filtered cycles according to the clustering distance weighted by the parameter value difference and the parameter importance, and filter the target cluster cluster.

[0059] In the same liquid-cooled supercharged power supply module, under the same parameters, similar adjustment effects can be achieved by using the same adjustment parameters. Therefore, the adjustment of the proportional coefficient can be selected by referring to the proportional coefficient in historical moments. There are also proportional coefficients with good control effects and proportional coefficients with poor control effects in historical data. Therefore, it is necessary to screen out proportional coefficients with good control effects from the history.

[0060] Therefore, the present invention analyzes all the historical data obtained, obtains the temperature stability of each cycle in the historical data, classifies all the cycles according to the temperature stability, excludes the cycle with lower temperature stability, and preserves the cycle with higher temperature stability.

[0061] In this embodiment, the Otsu threshold method is used to divide all cycles into two categories for all temperature stabilities, the mean of the temperature stability of each category of cycles is calculated, and all cycles in the category with the larger mean are screened and saved.

[0062] In another embodiment of the present application, a mean value is calculated for all temperature stabilities, and all cycles with temperature stability greater than the mean value are screened and saved.

[0063] When the temperature value is controlled by the proportional coefficient, the other parameters will also affect the calculation of temperature stability. Therefore, it is necessary to analyze different parameters to obtain the degree of influence of each parameter on temperature stability.

[0064] All the screened cycles are clustered by a clustering algorithm. The clustering algorithm used in this embodiment is a K-means clustering algorithm. In this embodiment, the value of K is 5, and the clustering distance is the difference in proportional coefficients between cycles.

[0065] For each parameter, the mean of all parameter values ​​of the parameter in each cycle is recorded as the parameter value of each cycle; the influence of each parameter on the temperature stability is obtained according to the temperature stability of each parameter in each cycle, the parameter value and the mean of the temperature stability of all cycles of each parameter in the cluster, and the mean of the parameter value.

[0066] Preferably, in this embodiment, the expression for the influence degree of the parameter on the temperature stability is:

[0067] ,in represents the parameter value of the ath parameter in the uth period, represents the temperature stability of the u-th cycle, represents the mean value of the parameter value of the ath parameter in the kth cluster, represents the mean of the temperature stability of all cycles in the kth cluster, represents the number of cycles in the kth cluster, represents the number of clusters, represents an exponential function with a natural constant as base, Indicates the influence of the ath parameter on temperature stability.

[0068] Since the present application has screened out periods with greater temperature stability in the above process, the difference in temperature stability is smaller. For clusters with similar proportional coefficients, the more similar the temperature stability and the closer the proportional coefficient, the greater the difference in the parameter values ​​of the periods, and the smaller the impact on the temperature stability; if the difference in proportional coefficients is smaller, if the difference between the parameter value of each period and the mean parameter value of all periods of the cluster is larger, it means that the current parameter value has less impact on the temperature stability; and if the difference between the parameter value of each period and the mean parameter value of all periods of the cluster is smaller, it means that the current parameter value has a greater impact on the temperature stability.

[0069] The importance of each parameter is analyzed according to the degree of influence of each parameter on temperature stability, and the difference between the degree of influence of each parameter on temperature stability and the degree of influence of all parameters on temperature stability is taken as the importance of each parameter.

[0070] Preferably, in this embodiment, the importance of the parameters is , Indicates the number of parameter types. In this embodiment, E is 6. Indicates the importance of the ath parameter.

[0071] For all the screened periods, clustering is performed based on the parameter values ​​of different parameters of each period, and periods with similar parameter values ​​are clustered.

[0072] In this embodiment, the clustering algorithm used for clustering is the DBSCAN clustering algorithm, wherein the parameters in the DBSCAN clustering algorithm are minpts=3, r=3, and the clustering distance of the clustering algorithm is as follows:

[0073] , Indicates the parameter value of the ath parameter of the cluster center, represents the parameter value of the ath parameter in the uth period, Represents the cluster distance between the u-th period and the cluster center.

[0074] Based on this, clustering of all cycles based on parameter values ​​is obtained. The purpose of clustering in this process is to filter out cycles with similar parameter values. The previous cycle of the current cycle is recorded as the target cycle. The proportional coefficient of the current cycle needs to be adjusted, that is, the proportional coefficient after the target cycle is adjusted. Therefore, the cluster cluster where the target cycle is located is recorded as the target cluster cluster. The flowchart of screening and obtaining the target cluster cluster is as follows: Figure 2 shown.

[0075] At this point, all cycles are screened to obtain the target cluster.

[0076] Step S004, record the periods other than the target period in the target cluster as historical periods, obtain the reference weight of each historical period according to the similarity between the historical period and the target period and the temperature stability of the historical period; weight the difference between the proportional coefficient of the historical period and its previous period by the reference weight to obtain the proportional coefficient adjustment parameter.

[0077] Through the above steps, other cycles with parameters close to the target cycle are obtained, and the adjustment of subsequent cycles of the other cycles is used as a reference value for the adjustment of the current cycle.

[0078] All the cycles except the target cycle in the target cluster are recorded as historical cycles. For each historical cycle, the difference in the proportional coefficient between the historical cycle and the next cycle is calculated. The proportional coefficient of the current cycle is adjusted by the difference in the proportional coefficient between all the historical cycles in the target cluster and the next cycle.

[0079] Since there are multiple historical cycles and different historical cycles have different reference values, it is necessary to first determine the reference weights of different historical cycles.

[0080] First, the similarity between each historical cycle and the target cycle is calculated. The similarity is expressed by the inverse of the clustering distance between the two cycles. The larger the clustering distance, the smaller the similarity between the two cycles. The temperature stability of each cycle represents the control effect of the proportional coefficient corresponding to the cycle. The greater the temperature stability, the better the control effect of the proportional coefficient. The smaller the similarity between the historical cycle and the target cycle, the lower the reliability of the historical cycle, the smaller the temperature stability of the historical cycle, the smaller the ability to control the proportional coefficient, and the lower the reference value of the historical cycle.

[0081] Based on the above steps, the reference weight of each historical period is obtained, where the expression of the reference weight is:

[0082] , represents the temperature stability of the s-th historical period, represents the similarity between the sth historical period and the target period, represents the number of historical periods, Represents the reference weight of the historical period.

[0083] Calculate the difference in proportionality coefficient between the historical period and the period after it, and weight the difference in proportionality coefficient with the reference weight of the historical period to obtain the proportionality coefficient adjustment parameter.

[0084] Preferably, in this embodiment, the difference in proportionality coefficient is the difference between the proportionality coefficient of the historical period and the subsequent period, and the proportionality coefficient adjustment parameter is . It represents the difference between the proportional coefficient of the sth historical period and its next period. Represents the proportional coefficient adjustment parameter.

[0085] At this point, the proportional coefficient adjustment parameter is obtained.

[0086] Step S005, taking the temperature stability of the target cycle as the weight, combining the proportional coefficient of the target cycle and the proportional coefficient adjustment parameter to obtain the adjusted proportional coefficient of the current cycle; and controlling the temperature value according to the adjusted proportional coefficient of the current cycle.

[0087] The proportional coefficient adjustment parameters are obtained through the above historical cycle analysis. If the temperature stability of the target cycle is greater at this time, the adjustment effect is better, which means that the necessity of adjusting the proportional coefficient at the current moment is smaller. Therefore, the temperature stability is used as the adjustment weight to obtain the adjusted proportional coefficient at the current moment. The specific expression is: , represents the temperature stability of the tth cycle, represents the proportional coefficient of the tth period, Indicates the proportional coefficient after adjustment of the current cycle. The tth cycle is the target cycle.

[0088] According to the above steps, a cycle is obtained every 10 minutes, and the proportional coefficient in the next cycle is adjusted. Then, the temperature value PID is controlled according to the adjusted proportional coefficient. The integral coefficient, differential coefficient and adjusted proportional coefficient of the PID control are input, the collected temperature value and the target temperature value are input, and the adjusted temperature value is output, thereby completely controlling the temperature of the liquid-cooled supercharging power supply module.

[0089] It should be noted that the above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

[0090] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for regulating the temperature of a liquid-cooled supercharged power supply module, characterized in that: The method comprises the following steps: Taking the preset time as a cycle, obtaining the proportional coefficient of the cycle; collecting the temperature value of the power module at each moment and the parameter values ​​of other parameters; the other parameters include liquid supply temperature, cold water tank temperature, hot water tank temperature, liquid supply pressure and liquid supply flow rate; The temperature stability of each cycle is obtained according to the difference between the mean temperature value in each cycle and the temperature value at each moment in the cycle, and the difference between the temperature value at each moment in the cycle and the preset standard temperature; The cycles are classified according to temperature stability, the cycles corresponding to a class with large temperature stability are screened and saved, and the screened cycles are clustered according to the proportional coefficient; the influence of each parameter on the temperature stability is obtained according to the difference between the temperature stability of each parameter in the cycle, the parameter value and the mean of the temperature stability of all cycles of each parameter in the clustering cluster, and the mean of the parameter value; the importance of each parameter is obtained according to the difference between the influence of each parameter on the temperature stability and the influence of all parameters on the temperature stability; all the screened cycles are clustered according to the parameter value difference and the parameter importance weighted as the clustering distance, and the target clustering cluster is screened; the target clustering cluster is a clustering cluster including the target cycle, and the target cycle is the cycle before the current cycle; The periods other than the target period in the target cluster are recorded as historical periods, and the reference weight of each historical period is obtained according to the similarity between the historical period and the target period and the temperature stability of the historical period; the difference between the proportional coefficient of the historical period and its previous period is weighted by the reference weight to obtain the proportional coefficient adjustment parameter; Taking the temperature stability of the target cycle as the weight, the proportional coefficient of the target cycle and the proportional coefficient adjustment parameter are combined to obtain the proportional coefficient after adjustment of the current cycle; and controlling the temperature value according to the proportional coefficient after adjustment of the current cycle; The method for obtaining the temperature stability of each cycle according to the difference between the mean value of the temperature value in each cycle and the temperature value at each moment in the cycle and the difference between the temperature value at each moment in the cycle and the preset standard temperature is: Calculate the mean of the temperature values ​​at all times in each cycle and record it as the first mean; The temperature stability of each cycle is negatively correlated with the difference between the temperature value at each moment and the first mean value, and the difference between the temperature value at each moment and the standard temperature; the temperature stability is the normalized value; The method for obtaining the influence of each parameter on the temperature stability according to the difference between the periodic temperature stability of each parameter, the parameter value and the mean value of all periodic temperature stabilities of each parameter in the cluster and the mean value of the parameter value is: For each parameter, the mean of all parameter values ​​of the parameter in each cycle is recorded as the parameter value of each cycle; the expression of the influence of each parameter on temperature stability is: ,in represents the parameter value of the ath parameter in the uth period, represents the temperature stability of the u-th cycle, represents the mean value of the parameter value of the ath parameter in the kth cluster, represents the mean of the temperature stability of all cycles in the kth cluster, represents the number of cycles in the kth cluster, represents the number of clusters, represents an exponential function with a natural constant as base, Indicates the influence of the ath parameter on temperature stability; The method for obtaining the importance of each parameter based on the difference between the influence of each parameter on the temperature stability and the influence of all parameters on the temperature stability is: The expression for the importance of each parameter is: , Indicates the number of parameter types, Indicates the importance of the ath parameter, Indicates the influence of the ath parameter on temperature stability.

2. A liquid-cooled supercharged power source module temperature adjustment method as claimed in claim 1, characterized in that: The method of clustering all post-screening cycles according to the parameter value difference and the parameter importance weight as the clustering distance to screen the target cluster cluster is: For all cycles, clustering is performed based on the differences in all parameter values; The expression of cluster distance is: , Indicates the parameter value of the ath parameter of the cluster center, represents the parameter value of the ath parameter in the uth period, represents the cluster distance between the uth period and the cluster center, represents the number of parameter types, Indicates the importance of the ath parameter.

3. A temperature adjustment method for a liquid-cooled supercharged power source module as claimed in claim 1, characterized in that: The method for obtaining the reference weight of each historical period according to the similarity between the historical period and the target period and the temperature stability of the historical period is: The expression of reference weight is: , represents the temperature stability of the s-th historical period, represents the similarity between the sth historical period and the target period, represents the number of historical periods, Represents the reference weight of the historical period.

4. A temperature adjustment method for a liquid-cooled supercharged power source module as claimed in claim 1, characterized in that: The method of obtaining the proportional coefficient adjustment parameter by weighting the difference between the proportional coefficient of the historical period and the previous period by the reference weight is: The expression of the proportional coefficient adjustment parameter is: , It represents the difference between the proportional coefficient of the sth historical period and its next period. represents the proportional coefficient adjustment parameter, represents the reference weight of the historical period, Indicates the number of historical periods.

5. A liquid-cooled supercharged power source module temperature adjustment method as claimed in claim 1, characterized in that: The method of taking the temperature stability of the target cycle as the weight and combining the proportional coefficient of the target cycle and the proportional coefficient adjustment parameter to obtain the adjusted proportional coefficient of the current cycle is: The expression of the proportional coefficient after the current cycle adjustment is: , represents the temperature stability of the tth cycle, represents the proportional coefficient of the tth period, Represents the proportional coefficient after adjustment of the current cycle; the tth cycle is the target cycle, Represents the proportional coefficient adjustment parameter.

6. A temperature adjustment method for a liquid-cooled supercharged power source module as claimed in claim 1, characterized in that: The method for controlling the temperature value according to the proportional coefficient adjusted in the current cycle is: Input the integral coefficient, differential coefficient and adjusted proportional coefficient of PID control, as well as the collected temperature value and target temperature value, and output the adjusted temperature value at each moment through the PID control system.

Images