Frequency converter water cooling control method and system

Abstract

The present invention relates to a frequency converter water cooling control method and system, and to the field of frequency converter data processing technology, including: a communication frequency converter control terminal and a temperature sensor, obtaining the pre-control parameter timing information, the environmental monitoring temperature and the initial temperature of the frequency converter in a specified time zone, performing temperature prediction based on the above information, and obtaining the temperature timing information of the frequency converter in the specified time zone; obtaining the frequency converter model and the coolant temperature, the coolant flow rate and the coolant type; optimizing the coolant temperature, the coolant flow rate and the coolant type based on the temperature timing information and the frequency converter model, and obtaining the water cooling control optimization result; and performing frequency converter water cooling control based on the water cooling control optimization result. The method solves the technical problem that the traditional frequency converter water cooling control in the prior art has control hysteresis, resulting in untimely temperature cooling.

Description

Technical Field

[0001] The present invention relates to the field of frequency converter data processing, and in particular to a frequency converter water cooling control method and system. Background Art

[0002] The inverter is a power electronic device that converts fixed-frequency AC power into adjustable-frequency AC power. It can achieve precise control of motor speed and torque, improve production efficiency, and save energy and reduce emissions. Since high-power electrical transmission inverters involve automated smelting, electric locomotives, mining machinery and other fields, they are widely used.

[0003] In scenarios where higher cooling effects are required, traditional air cooling and oil cooling can no longer meet the needs. Water cooling has the advantages of good cooling effect, low energy consumption, safety and environmental protection, and has been widely used in the cooling of high-power inverters.

[0004] In the prior art, conventional inverter water cooling is usually controlled based on real-time monitored temperature, which results in a control lag and a technical problem of untimely temperature cooling. Summary of the invention

[0005] The present invention aims to solve the technical problem that traditional inverter water cooling in the prior art usually performs water cooling control based on real-time monitored temperature, which has control lag and leads to untimely temperature cooling, and provides an inverter water cooling control method and system.

[0006] In a first aspect, the present invention provides a frequency converter water cooling control method, including: a communication frequency converter control terminal, to obtain the pre-control parameter timing information of the frequency converter in a specified time zone; a communication temperature sensor, to obtain the environmental monitoring temperature and the initial temperature of the frequency converter; temperature prediction is performed based on the pre-control parameter timing information, the environmental monitoring temperature and the initial temperature of the frequency converter to obtain the temperature timing information of the frequency converter in the specified time zone; water cooling control parameters and a frequency converter model are obtained, wherein the water cooling control parameters include coolant temperature, coolant flow rate and coolant type; based on the temperature timing information and the frequency converter model, the coolant temperature, the coolant flow rate and the coolant type are optimized to obtain a water cooling control optimization result; and frequency converter water cooling control is performed based on the water cooling control optimization result.

[0007] In a second aspect, the present invention provides a frequency converter water cooling control system, comprising: a terminal communication module, used to communicate with the frequency converter control terminal, and obtain the pre-control parameter timing information of the frequency converter in a specified time zone; a sensor communication module, used to communicate with the temperature sensor, and obtain the environmental monitoring temperature and the initial temperature of the frequency converter; a predicted temperature module, used to perform temperature prediction based on the pre-control parameter timing information, the environmental monitoring temperature and the initial temperature of the frequency converter, and obtain the temperature timing information of the frequency converter in the specified time zone; a parameter acquisition module, used to obtain water cooling control parameters and a frequency converter model, wherein the water cooling control parameters include coolant temperature, coolant flow rate and coolant type; a control data optimization module, used to optimize the coolant temperature, the coolant flow rate and the coolant type according to the temperature timing information and the frequency converter model, and obtain a water cooling control optimization result; a water cooling control module, used to perform frequency converter water cooling control based on the water cooling control optimization result.

[0008] In a third aspect, the present invention provides an electronic device, comprising: a memory for storing a computer software program; a processor for reading and executing the computer software program, thereby implementing the inverter water cooling control method described in any one of the first aspects.

[0009] In a fourth aspect, the present invention provides a non-transitory computer-readable storage medium, wherein the storage medium stores a computer software program, and when the computer software program is executed by a processor, the inverter water cooling control method described in any one of the first aspects is implemented.

[0010] The beneficial effects of the present invention are as follows: by predicting the temperature change state of the frequency converter in different time domains of a specified time zone and matching the corresponding cooling control parameters, the predictability of parameter control is improved, thereby achieving the technical effect of timely cooling. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A schematic flow chart of the inverter water cooling control method provided by the present invention;

[0012] Figure 2 A schematic diagram of the structure of the frequency converter water cooling control system provided by the present invention;

[0013] Figure 3 A functional block diagram of the electronic device provided by the present invention;

[0014] Figure 4 A functional block diagram of a computer-readable storage device provided by the present invention.

[0015] In the accompanying drawings, the components represented by the reference numerals are listed as follows:

[0016] 1. Terminal communication module, 2. Sensor communication module, 3. Prediction temperature module, 4. Parameter acquisition module, 5. Control data optimization module, 6. Water cooling control module. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0018] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0019] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0020] Example 1

[0021] like Figure 1 As shown, an embodiment of the present invention provides a frequency converter water cooling control method, comprising:

[0022] S10: communicating with the inverter control terminal to obtain the timing information of the pre-control parameters of the inverter in the specified time zone;

[0023] Further, the communication inverter control terminal obtains the pre-control parameter timing information of the inverter in the specified time zone, and step S10 includes:

[0024] S11: Communicate with the inverter control terminal to obtain initial pre-control parameter timing information of the inverter in the specified time zone;

[0025] S12: performing adjacent time domain distance analysis on the initial pre-control parameter timing information to obtain a plurality of adjacent time domain distance parameters;

[0026] S13: Based on the distance parameter threshold, the initial pre-control parameter timing information is segmented in the time domain in combination with the plurality of adjacent time domain distance parameters to obtain the pre-control parameter timing information.

[0027] Specifically, the inverter control terminal collects various parameter information of the inverter in real time during use, including set value data during pre-control.

[0028] The specified time zone is the interval of the actual water cooling control time. The initial pre-control parameters are the specific parameters of the inverter operation initially set, including but not limited to the output frequency, output voltage and acceleration and deceleration time. Among them, the acceleration time is the time required for the output frequency to rise from 0 to the maximum frequency, and the deceleration time is the time required for the maximum frequency to drop from 0.

[0029] By exchanging information with the inverter control terminal, the initial pre-control parameter timing information of the inverter in the specified time zone is obtained. The initial pre-control parameter timing information is a data set arranged in chronological order around the specified time zone. These data can be observed and collected at any time interval (such as every second, every minute).

[0030] In order to interact with accurate and reliable pre-control parameters, it is first necessary to determine the time series range of the collected data. Therefore, a neighborhood search is performed on the initial pre-control parameter time series information. Specifically, by analyzing the distance between adjacent time domains, by setting a distance function, the distance parameter is calculated by the distance function. Exemplarily, after weights are assigned to different pre-control parameters, characteristic value analysis of different parameters in adjacent time domains is performed, and then the distance parameter is analyzed and calculated in combination with the weight assigned to the parameter.

[0031] A distance parameter threshold is preset, and a judgment is made based on the calculation results of the adjacent time domain distance parameters. If the preset distance parameter threshold is met, that is, the time domain data has a high correlation, it is divided into the same segment, and finally the specified time zone is divided into several time segments, thereby completing the time domain segmentation. After sorting the time domain segmentation results in chronological order, the pre-control parameter timing information is obtained.

[0032] S20: communicate with the temperature sensor to obtain the environmental monitoring temperature and the initial temperature of the inverter;

[0033] Specifically, the temperature sensor is a sensor installed in the inverter device for monitoring the ambient temperature and the inverter temperature. When a high-power inverter is working, it will generate several kilowatts or even tens of kilowatts of waste heat. Through communication and interaction with the temperature sensor, the ambient monitoring temperature and the initial temperature of the inverter are collected. The initial temperature of the inverter is the overall temperature of the inverter at room temperature before working. Collecting the ambient monitoring temperature and the initial temperature of the inverter provides key data for the water cooling control during the operation of the inverter.

[0034] S30: performing temperature prediction according to the pre-control parameter timing information, the environmental monitoring temperature and the inverter initial temperature to obtain the temperature timing information of the inverter in the specified time zone;

[0035] Further, temperature prediction is performed according to the pre-control parameter timing information, the environmental monitoring temperature and the inverter initial temperature to obtain the temperature timing information of the inverter in the specified time zone, and step S30 includes:

[0036] S31: partitioning the designated time zone according to the pre-control parameter timing information, obtaining a first time zone pre-control parameter, a second time zone pre-control parameter, and finally an Nth time zone pre-control parameter, wherein the first time zone, the second time zone, and finally the Nth time zone are arranged in sequence according to the timing;

[0037] S32: According to the first time zone pre-control parameter, the environment monitoring temperature and the inverter initial temperature are processed by a temperature predictor to obtain first time zone temperature time series information;

[0038] S33: According to the pre-control parameter of the second time zone, the environmental monitoring temperature and the temperature at the end time of the first time zone are processed by the temperature predictor to obtain the temperature time series information of the second time zone;

[0039] S34: until the environment monitoring temperature and the temperature at the end time of the N-1th time zone are processed by the temperature predictor according to the pre-control parameter of the Nth time zone to obtain the temperature time series information of the Nth time zone;

[0040] S35: Merge the first time zone temperature timing information, the second time zone temperature timing information, and so on until the Nth time zone temperature timing information to obtain the temperature timing information.

[0041] Specifically, after obtaining the pre-control parameter timing information through adjacent time domain distance analysis, the working time that needs water cooling control, i.e., the designated time zone, is partitioned according to the pre-control parameter timing information. Each area contains the corresponding pre-control parameter, and the partition results are represented as the first time zone pre-control parameter, the second time zone pre-control parameter, and so on until the Nth time zone pre-control parameter. The partition results are arranged in chronological order.

[0042] The temperature predictor is obtained by training based on a long short-term memory neural network. By collecting the water cooling history data of the current inverter, including but not limited to the environmental monitoring temperature data set, the environmental prediction temperature data set, where the ambient temperature is the air temperature inside the inverter, and the inverter temperature data set. Further artificially construct a loss function to constrain the number of model training times and determine whether the model is trained to convergence. When the loss value calculated according to the loss function meets the loss threshold, the temperature predictor training is completed.

[0043] The first time zone temperature time series information is the predicted temperature of the time zone during the operation of the inverter in the first time zone and the water cooling control process in the first time zone. The first time zone pre-control parameter, the environmental monitoring temperature and the inverter initial temperature are input into the temperature predictor for processing to obtain the first time zone temperature time series information.

[0044] The temperature at the end time of the first time zone is collected based on the temperature sensor, and the pre-control parameter of the second time zone, the environmental monitoring temperature and the temperature at the end time of the first time zone are input into the temperature predictor for processing to obtain the temperature time series information of the second time zone. The temperature at the end time of the previous time zone, the pre-control parameter of the current time zone and the environmental monitoring temperature are collected in sequence, and processed by the temperature predictor to obtain the current temperature time series information until all time zones are traversed.

[0045] The temperature time series information of the first time zone, the temperature time series information of the second time zone, and even the temperature time series information of the Nth time zone are merged and processed, and sorted in chronological order to obtain the temperature time series information. The temperature time series information can show the temperature change trend in the specified time zone. By dividing the time zone, the temperature is predicted by time zone, and the temperature time series information obtained by merging the temperature prediction results of each zone is more accurate, providing a data basis for the setting of water cooling control parameters.

[0046] S40: Obtaining water cooling control parameters and a frequency converter model, wherein the water cooling control parameters include coolant temperature, coolant flow rate, and coolant type;

[0047] Specifically, inverters of different models and manufacturers have differences in structure and performance, and the water cooling control solutions are also different accordingly. After understanding the inverter model, you can easily call the data of inverters of the same model and structure for water cooling control solution optimization.

[0048] Furthermore, water cooling control must use water with good insulation strength, generally pure water, which has a lower ion content than ordinary distilled water. Therefore, the selection of a water cooling control scheme requires the control and setting of various parameters of the coolant, namely the water cooling control parameters, which include coolant temperature, coolant flow rate, and coolant type. Coolants with different temperatures, different flow rates, and different ion concentrations have different cooling capacities, so water cooling control needs to comprehensively consider the properties of the above coolants.

[0049] S50: optimizing the coolant temperature, the coolant flow rate and the coolant type according to the temperature time series information and the inverter model to obtain a water cooling control optimization result;

[0050] Further, according to the temperature time series information and the inverter model, the coolant temperature, the coolant flow rate and the coolant type are optimized to obtain a water cooling control optimization result, and step S50 includes:

[0051] S501: Obtaining a first time zone temperature characteristic value, a second time zone temperature characteristic value, and a Pth time zone temperature characteristic value according to the temperature time series information;

[0052] S502: assigning values ​​to the coolant temperature, the coolant flow rate, and the coolant type according to the first time zone temperature characteristic value and the inverter model, to obtain a plurality of groups of assignment results, wherein the plurality of groups of assignment results have a plurality of trigger frequencies and a plurality of energy consumption record values;

[0053] S503: sorting the plurality of groups of value assignment results according to the plurality of trigger frequencies and the plurality of energy consumption record values, and setting the results as the first time zone water cooling control optimization result;

[0054] S504: traversing the temperature characteristic values ​​of the second time zone until the temperature characteristic values ​​of the P-th time zone for loop analysis, and obtaining the optimization result of the water cooling control in the second time zone until the optimization result of the water cooling control in the P-th time zone;

[0055] S505: Add the first time zone water cooling control optimization result, the second time zone water cooling control optimization result, and so on to the P-th time zone water cooling control optimization result into the water cooling control optimization result.

[0056] Specifically, after the inverter model and temperature time series information have been obtained, it is necessary to match the optimal water cooling control parameters based on the above information. According to the temperature time series information, the temperature characteristic value of each time zone is extracted, and the temperature characteristic value reflects the predicted temperature of the inverter in the time zone. After the characteristic value is extracted, the temperature characteristic value of the first time zone, the temperature characteristic value of the second time zone, and the temperature characteristic value of the Pth time zone are obtained.

[0057] A data set is obtained based on the coolant temperature, the coolant flow rate and the coolant type. The data set is obtained based on the temperature characteristic value of the first time zone and the inverter model, and is used to generate different cooling schemes, and continuously assign values ​​to the first time zone based on different cooling schemes. A number of assignment results are obtained, including a number of trigger frequencies and a number of energy consumption record values. Among them, the trigger frequency refers to the number of frequencies selected by a corresponding set of control parameters in the same scenario. The energy consumption record refers to the energy consumption such as the electric energy consumed by the water cooling of a corresponding set of control parameters in the same scenario.

[0058] According to the assignment results, sorting is performed. First, a batch of control parameters with trigger frequencies higher than the trigger frequency threshold are selected, and then the one with the lowest energy consumption is selected from them as the optimization result of water cooling control in the first time zone. This result characterizes that this control parameter is the control parameter with the highest usage frequency and the lowest energy consumption.

[0059] In the same optimization method as the first time zone, the temperature characteristic values ​​of the second time zone are analyzed cyclically until the temperature characteristic values ​​of the Pth time zone, and the optimization results of the water cooling control of the second time zone are obtained until the optimization results of the water cooling control of the Pth time zone. Further, the optimization results of each time zone are added to the water cooling control optimization results to control the water cooling of the inverter.

[0060] S60: performing inverter water cooling control according to the water cooling control optimization result.

[0061] Specifically, the parameters of the water cooling system are set according to the water cooling control optimization results. By predicting the temperature change state of the inverter in different time domains in a specified time zone and matching the corresponding cooling control parameters, the anticipation of parameter control is improved, achieving the technical effect of timely cooling.

[0062] Furthermore, the initial pre-control parameter timing information is subjected to adjacent time domain distance analysis to obtain a plurality of adjacent time domain distance parameters, and step S12 includes:

[0063] S121: configuring pre-control parameter attributes, performing weight distribution on the pre-control parameter attributes, and obtaining parameter attribute weight distribution results, wherein the pre-control parameter attributes include output frequency, output voltage, and acceleration / deceleration time;

[0064] S122: Construct adjacent time domain distance analysis function:

[0065]

[0066] Wherein, Distance(X1,X2) represents the distance between any two adjacent time domains, X1 represents the initial pre-control parameter of the first time domain, X2 represents the initial pre-control parameter of the second time domain, the first time domain and the second time domain are neighbors to each other, W iCharacterizes the weight distribution result of the i-th parameter attribute, X 1,i Characterizes the initial pre-control parameter characteristic value of the i-th attribute in the first time domain, X 2,i Characterizing the characteristic value of the initial pre-control parameter of the i-th attribute in the second time domain;

[0067] S123: performing adjacent time domain distance analysis on the initial pre-control parameter timing information according to the adjacent time domain distance analysis function to obtain the plurality of adjacent time domain distance parameters.

[0068] Specifically, the pre-control parameter attributes include output frequency, output voltage and acceleration / deceleration time. The pre-control parameter attributes are specific parameters for pre-controlling the water cooling control of the frequency converter. Since different parameters have different importance to the water cooling control, the parameter attributes are weighted in advance and can be manually designed according to historical experience. The constructed adjacent time domain distance analytic function is:

[0069]

[0070] In the adjacent time domain distance analysis function, Distance(X1,X2) represents the distance between any two adjacent time domains, and the distance between two neighboring domains is calculated each time. X1 represents the initial pre-control parameter of the first time domain, and X2 represents the initial pre-control parameter of the second time domain. The first time domain and the second time domain are neighbors of each other. There are three pre-control parameter attributes in total, W i Characterizes the weight distribution result of the i-th parameter attribute, X 1,i Characterizes the initial pre-control parameter characteristic value of the i-th attribute in the first time domain, X 2,i Characterizes the initial pre-control parameter characteristic value of the i-th attribute in the second time domain.

[0071] The difference between the values ​​of any parameter attribute in the two neighborhoods is squared, the square of the difference is divided by the sum of the values ​​of the parameter in the two neighborhoods, and then multiplied by the weight of the parameter attribute. The other two parameter attribute results are calculated, and the three parameter attribute calculation values ​​are summed up, and further square root operation is performed to finally obtain the distance between two adjacent time domains.

[0072] Based on the constructed adjacent time domain distance analysis function, the initial pre-control parameter time series information is analyzed in adjacent time domain distance to obtain the several adjacent time domain distance parameters. By calculating the distance of important pre-control parameter attributes in different time domains, a scientific data basis is provided for obtaining the time domain whose correlation meets a certain threshold, which improves the pertinence and scientificity of the time domain division.

[0073] Further, according to the first time zone pre-control parameter, the environmental monitoring temperature and the inverter initial temperature are processed by a temperature predictor to obtain the first time zone temperature timing information, step S32 includes:

[0074] S321: Construct loss evaluation function:

[0075]

[0076] Among them, LOSS1 represents the mean loss function, LOSS2 represents the overall loss function, M represents the total number of predicted moments, T j Represents the predicted value at the jth moment, T j0 represents the true value of supervision at the jth moment, and ΔT represents the temperature deviation threshold;

[0077] S322: Training the temperature predictor according to the loss evaluation function.

[0078] Furthermore, the temperature predictor is trained according to the loss evaluation function, step S322 includes:

[0079] S3221: According to the loss evaluation function, train the long short-term memory neural network to obtain Q mean loss values ​​of Q consecutive groups and Q overall loss values;

[0080] S3222: performing central tendency analysis on the Q mean loss values ​​and the Q overall loss values ​​respectively to obtain a mean loss characteristic value and an overall loss characteristic value;

[0081] S3223: When the mean loss characteristic value is less than or equal to the mean loss threshold, and the overall loss characteristic value is less than or equal to the overall loss threshold, generate the temperature predictor.

[0082] Specifically, the LSTM neural network can solve the problem of gradient vanishing to a certain extent by combining short-term memory with long-term memory. The LSTM neural network solves this problem by introducing a "gate" structure and a "cell state". The gate structure can control the inflow and outflow of information, while the cell state can store the state for a long time. This enables the LSTM neural network to better capture dependencies in long sequences.

[0083] Train a long short-term memory neural network suitable for temperature prediction during the operation of the inverter. Artificially construct a loss evaluation function, which is used to constrain the number of model training times and determine whether the model has been trained to convergence.

[0084] The loss evaluation function is as follows:

[0085]

[0086] Among them, LOSS1 represents the mean loss function, LOSS2 represents the overall loss function, M represents the total number of predicted moments, T j Represents the predicted value at the jth moment, T j0represents the true value of supervision at the jth moment, and ΔT represents the temperature deviation threshold.

[0087] The mean loss function is calculated by taking the predicted value T at the jth moment j and the j-th moment supervision truth value T j0 The square of the difference divided by the predicted value T at the jth moment j and the j-th moment supervision truth value T j0 The sum is calculated and then divided by the total number of predicted moments M. The overall loss function is obtained by comparing the predicted value at the jth moment with the true value of the supervision at the jth moment T j0 The number of differences greater than the temperature deviation threshold ΔT is counted and divided by the total number of predicted moments M to obtain the value.

[0088] Collect the water cooling history data of the current inverter. The history data is the continuous data in the cooling process, including but not limited to the environmental monitoring temperature data set, the environmental prediction temperature data set, where the environmental temperature is the air temperature inside the inverter, and the inverter temperature data set. Calculate the loss evaluation function to obtain Q mean loss values ​​and Q overall loss values ​​of Q consecutive groups.

[0089] The Q mean loss values ​​and the Q overall loss values ​​are subjected to central tendency analysis respectively. Central tendency analysis is an analysis method that uses various measures that serve as representative values ​​to reflect the tendency of variable values ​​toward the central position. Exemplarily, central tendency analysis can be performed by methods such as average, median, and harmonic mean. After the central tendency analysis, representative mean loss characteristic values ​​and overall loss characteristic values ​​are obtained.

[0090] The mean loss threshold and the overall loss threshold are preset to perform feature value judgment. When the mean loss feature value is less than or equal to the mean loss threshold, and the overall loss feature value is less than or equal to the overall loss threshold, the temperature predictor training is completed. The stability of the model output can be guaranteed by the loss function about the mean and the overall. Compared with the traditional training strategy, the model stability and accuracy are stronger, and the temperature prediction results are more accurate.

[0091] Example 2

[0092] like Figure 2 As shown, based on the same inventive concept as the inverter water cooling control method provided in Example 1, the embodiment of the present invention provides an inverter water cooling control system, including:

[0093] Terminal communication module 1, used for communicating with the inverter control terminal to obtain the pre-control parameter timing information of the inverter in the specified time zone;

[0094] Sensor communication module 2, used for communicating with the temperature sensor to obtain the environmental monitoring temperature and the initial temperature of the inverter;

[0095] A temperature prediction module 3 is used to perform temperature prediction based on the pre-control parameter timing information, the environmental monitoring temperature and the inverter initial temperature, and obtain the temperature timing information of the inverter in the specified time zone;

[0096] Parameter acquisition module 4, used to obtain water cooling control parameters and inverter model, wherein the water cooling control parameters include coolant temperature, coolant flow rate and coolant type;

[0097] A control data optimization module 5 is used to optimize the coolant temperature, the coolant flow rate and the coolant type according to the temperature timing information and the inverter model to obtain a water cooling control optimization result;

[0098] The water cooling control module 6 is used to perform inverter water cooling control according to the water cooling control optimization result.

[0099] Furthermore, the system also includes:

[0100] A terminal communication module, used for communicating with the inverter control terminal to obtain the initial pre-control parameter timing information of the inverter in the specified time zone;

[0101] A neighborhood analysis module, used for performing adjacent time domain distance analysis on the initial pre-control parameter timing information to obtain a plurality of adjacent time domain distance parameters;

[0102] The time domain segmentation module is used to perform time domain segmentation on the initial pre-control parameter timing information based on a distance parameter threshold and in combination with the plurality of adjacent time domain distance parameters to obtain the pre-control parameter timing information.

[0103] Furthermore, the system also includes:

[0104] An attribute configuration module, used to configure pre-control parameter attributes, perform weight distribution on the pre-control parameter attributes, and obtain parameter attribute weight distribution results, wherein the pre-control parameter attributes include output frequency, output voltage, and acceleration / deceleration time;

[0105] Distance function building module, used to build adjacent time domain distance analysis function:

[0106]

[0107] Wherein, Distance(X1,X2) represents the distance between any two adjacent time domains, X1 represents the initial pre-control parameter of the first time domain, X2 represents the initial pre-control parameter of the second time domain, the first time domain and the second time domain are neighbors to each other, W i Characterizes the weight distribution result of the i-th parameter attribute, X 1,i Characterizes the initial pre-control parameter characteristic value of the i-th attribute in the first time domain, X 2,iCharacterizing the characteristic value of the initial pre-control parameter of the i-th attribute in the second time domain;

[0108] The distance parameter calculation module is used to perform adjacent time domain distance analysis on the initial pre-control parameter timing information according to the adjacent time domain distance analysis function to obtain the plurality of adjacent time domain distance parameters.

[0109] Furthermore, the system also includes:

[0110] A timing partitioning module, used for partitioning the designated time zone according to the pre-control parameter timing information, obtaining the first time zone pre-control parameter, the second time zone pre-control parameter until the Nth time zone pre-control parameter, wherein the first time zone, the second time zone until the Nth time zone are arranged in sequence according to the timing;

[0111] A first temperature prediction module, configured to obtain temperature time series information of the first time zone by processing the environment monitoring temperature and the inverter initial temperature through a temperature predictor according to the first time zone pre-control parameter;

[0112] A second temperature prediction module, configured to obtain temperature time series information of the second time zone by processing the environment monitoring temperature and the temperature at the end point of the first time zone through the temperature predictor according to the pre-control parameter of the second time zone;

[0113] A third temperature prediction module is used to obtain temperature time series information of the Nth time zone by processing the environmental monitoring temperature and the temperature at the end time of the N-1th time zone through the temperature predictor according to the pre-control parameter of the Nth time zone;

[0114] The information merging module is used to merge the temperature timing information of the first time zone, the temperature timing information of the second time zone, and so on until the temperature timing information of the Nth time zone to obtain the temperature timing information.

[0115] Furthermore, the system also includes:

[0116] Evaluation function building module, used to build loss evaluation function:

[0117]

[0118] Among them, LOSS1 represents the mean loss function, LOSS2 represents the overall loss function, M represents the total number of predicted moments, T j Represents the predicted value at the jth moment, T j0 represents the true value of supervision at the jth moment, and ΔT represents the temperature deviation threshold;

[0119] A predictor training module is used to train the temperature predictor according to the loss evaluation function.

[0120] Furthermore, the system also includes:

[0121] A loss value calculation module, used to train a long short-term memory neural network according to the loss evaluation function to obtain Q mean loss values ​​of consecutive Q groups and Q overall loss values;

[0122] A trend analysis module, used to perform central trend analysis on the Q mean loss values ​​and the Q overall loss values, respectively, to obtain a mean loss characteristic value and an overall loss characteristic value;

[0123] A predictor generation module is used to generate the temperature predictor when the mean loss characteristic value is less than or equal to the mean loss threshold and the overall loss characteristic value is less than or equal to the overall loss threshold.

[0124] Furthermore, the system also includes:

[0125] A characteristic value acquisition module, used for obtaining a first time zone temperature characteristic value, a second time zone temperature characteristic value, and finally a P-th time zone temperature characteristic value according to the temperature time series information;

[0126] A time zone assignment module, used to assign the coolant temperature, the coolant flow rate and the coolant type according to the first time zone temperature characteristic value and the inverter model, to obtain a plurality of groups of assignment results, wherein the plurality of groups of assignment results have a plurality of trigger frequencies and a plurality of energy consumption record values;

[0127] A result sorting module, used for sorting the plurality of groups of assignment results according to the plurality of trigger frequencies and the plurality of energy consumption record values, and setting them as the first time zone water cooling control optimization result;

[0128] A loop assignment module, used for traversing the temperature characteristic value of the second time zone until the temperature characteristic value of the P-th time zone to perform loop analysis, and obtaining the optimization result of the water cooling control in the second time zone until the optimization result of the water cooling control in the P-th time zone;

[0129] A result adding module is used to add the first time zone water cooling control optimization result, the second time zone water cooling control optimization result, and so on to the P-th time zone water cooling control optimization result into the water cooling control optimization result.

[0130] See also Figure 3 , Figure 3 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 3As shown, an embodiment of the present invention provides an electronic device 500, including a memory 510, a processor 520 and a computer program 511 stored in the memory 510 and executable on the processor 520, wherein the processor 520 implements the following steps when executing the computer program 511: communicating with the inverter control terminal to obtain the pre-control parameter timing information of the inverter in the specified time zone; communicating with the temperature sensor to obtain the environmental monitoring temperature and the initial temperature of the inverter; performing temperature prediction based on the pre-control parameter timing information, the environmental monitoring temperature and the initial temperature of the inverter to obtain the temperature timing information of the inverter in the specified time zone; obtaining water cooling control parameters and the inverter model, wherein the water cooling control parameters include coolant temperature, coolant flow rate and coolant type; optimizing the coolant temperature, the coolant flow rate and the coolant type based on the temperature timing information and the inverter model to obtain a water cooling control optimization result; and performing inverter water cooling control based on the water cooling control optimization result.

[0131] See also Figure 4 , Figure 4 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 4 As shown, this embodiment provides a computer-readable storage medium 600, on which a computer program 611 is stored. When the computer program 611 is executed by a processor, the following steps are implemented: communicating with the inverter control terminal to obtain the pre-control parameter timing information of the inverter in the specified time zone; communicating with the temperature sensor to obtain the environmental monitoring temperature and the inverter initial temperature; performing temperature prediction based on the pre-control parameter timing information, the environmental monitoring temperature and the inverter initial temperature to obtain the temperature timing information of the inverter in the specified time zone; obtaining water cooling control parameters and the inverter model, wherein the water cooling control parameters include coolant temperature, coolant flow rate and coolant type; optimizing the coolant temperature, the coolant flow rate and the coolant type according to the temperature timing information and the inverter model to obtain a water cooling control optimization result; and performing inverter water cooling control according to the water cooling control optimization result.

[0132] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0133] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0134] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0135] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0136] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0137] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0138] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A frequency converter water cooling control method, characterized in that: include: Communicate with the inverter control terminal to obtain the timing information of the pre-control parameters of the inverter in the specified time zone; Communication temperature sensor, obtains environmental monitoring temperature and inverter initial temperature; Perform temperature prediction according to the pre-control parameter timing information, the environmental monitoring temperature and the inverter initial temperature to obtain the temperature timing information of the inverter in the specified time zone; Obtaining water cooling control parameters and a frequency converter model, wherein the water cooling control parameters include coolant temperature, coolant flow rate, and coolant type; Optimizing the coolant temperature, the coolant flow rate, and the coolant type according to the temperature time series information and the inverter model to obtain a water cooling control optimization result; Performing inverter water cooling control according to the water cooling control optimization result; Among them, the communication inverter control terminal obtains the pre-control parameter timing information of the inverter in the specified time zone, including: Communicate with the inverter control terminal to obtain initial pre-control parameter timing information of the inverter in the specified time zone; Performing adjacent time domain distance analysis on the initial pre-control parameter timing information to obtain a plurality of adjacent time domain distance parameters; Based on the distance parameter threshold, the initial pre-control parameter timing information is segmented in the time domain in combination with the plurality of adjacent time domain distance parameters to obtain the pre-control parameter timing information; wherein the initial pre-control parameter timing information is parsed in the adjacent time domain distance to obtain the plurality of adjacent time domain distance parameters, including: Configure pre-control parameter attributes, perform weight distribution on the pre-control parameter attributes, and obtain parameter attribute weight distribution results, wherein the pre-control parameter attributes include output frequency, output voltage, and acceleration / deceleration time; Construct the adjacent time domain distance analytic function: Wherein, Distance(X1, X2) represents the distance between any two adjacent time domains, X1 represents the initial pre-control parameter of the first time domain, X2 represents the initial pre-control parameter of the second time domain, the first time domain and the second time domain are neighbors to each other, W i Characterizes the weight distribution result of the i-th parameter attribute, X 1,i Characterizes the initial pre-control parameter characteristic value of the i-th attribute in the first time domain, X 2,i Characterizing the characteristic value of the initial pre-control parameter of the i-th attribute in the second time domain; According to the adjacent time domain distance analysis function, performing adjacent time domain distance analysis on the initial pre-control parameter timing information to obtain the plurality of adjacent time domain distance parameters; The step of performing temperature prediction according to the pre-control parameter timing information, the environmental monitoring temperature and the initial temperature of the inverter to obtain the temperature timing information of the inverter in the specified time zone includes: According to the pre-control parameter timing information, the designated time zone is partitioned to obtain the first time zone pre-control parameter, the second time zone pre-control parameter, and the Nth time zone pre-control parameter, wherein the first time zone, the second time zone, and the Nth time zone are arranged in sequence according to the timing; According to the first time zone pre-control parameter, the environment monitoring temperature and the inverter initial temperature are processed by a temperature predictor to obtain the first time zone temperature time series information; According to the pre-control parameter of the second time zone, the environmental monitoring temperature and the temperature at the end time of the first time zone are processed by the temperature predictor to obtain the temperature time series information of the second time zone; Until the environment monitoring temperature and the temperature at the end point of the N-1 time zone are processed by the temperature predictor according to the pre-control parameter of the N time zone to obtain the temperature time series information of the N time zone; Merging the first time zone temperature time series information, the second time zone temperature time series information, and up to the Nth time zone temperature time series information to obtain the temperature time series information; According to the first time zone pre-control parameter, the environment monitoring temperature and the inverter initial temperature are processed by a temperature predictor to obtain the first time zone temperature time series information, including: Construct a loss evaluation function: Among them, LOSS1 represents the mean loss function, LOSS2 represents the overall loss function, M represents the total number of predicted moments, T j Represents the predicted value at the jth moment, T j0 represents the true value of supervision at the jth moment, and ΔT represents the temperature deviation threshold; The temperature predictor is trained according to the loss evaluation function.

2. The method according to claim 1, characterized in that Training the temperature predictor according to the loss evaluation function includes: According to the loss evaluation function, a long short-term memory neural network is trained to obtain Q mean loss values ​​of Q consecutive groups and Q overall loss values; Performing central tendency analysis on the Q mean loss values ​​and the Q overall loss values ​​respectively to obtain a mean loss characteristic value and an overall loss characteristic value; The temperature predictor is generated when the mean loss characteristic value is less than or equal to a mean loss threshold and the overall loss characteristic value is less than or equal to an overall loss threshold.

3. The method according to claim 1, characterized in that According to the temperature time series information and the inverter model, the coolant temperature, the coolant flow rate and the coolant type are optimized to obtain a water cooling control optimization result, including: according to the temperature time series information, obtaining a first time zone temperature characteristic value, a second time zone temperature characteristic value until a P-th time zone temperature characteristic value; Assigning the coolant temperature, the coolant flow rate, and the coolant type according to the temperature characteristic value of the first time zone and the inverter model to obtain several groups of assignment results, wherein the several groups of assignment results have several trigger frequencies and several energy consumption record values; According to the plurality of trigger frequencies and the plurality of energy consumption record values, sorting is performed from the plurality of groups of assignment results, and setting them as the first time zone water cooling control optimization result; Traversing the temperature characteristic values ​​of the second time zone until the temperature characteristic values ​​of the P-th time zone for loop analysis, obtaining the optimization result of the water cooling control in the second time zone until the optimization result of the water cooling control in the P-th time zone; The first time zone water cooling control optimization result, the second time zone water cooling control optimization result, and so on until the P-th time zone water cooling control optimization result are added into the water cooling control optimization result.

4. The inverter water cooling control system is characterized by: The method for implementing the inverter water cooling control method according to any one of claims 1 to 3 comprises: The terminal communication module is used to communicate with the inverter control terminal to obtain the timing information of the pre-control parameters of the inverter in the specified time zone; The sensor communication module is used to communicate with the temperature sensor to obtain the environmental monitoring temperature and the initial temperature of the inverter; A temperature prediction module, used to perform temperature prediction based on the pre-control parameter timing information, the environmental monitoring temperature and the inverter initial temperature, and obtain the temperature timing information of the inverter in the specified time zone; A parameter acquisition module, used to obtain water cooling control parameters and inverter model, wherein the water cooling control parameters include coolant temperature, coolant flow rate and coolant type; A control data optimization module, used to optimize the coolant temperature, the coolant flow rate and the coolant type according to the temperature timing information and the inverter model, and obtain a water cooling control optimization result; The water cooling control module is used to perform inverter water cooling control according to the water cooling control optimization result.

Images