Phase state monitoring method and device for microchannel heat exchange module

Abstract

The present application relates to the field of heat exchange technology, and provides a phase state monitoring method and device for a microchannel heat exchange module. The method includes obtaining multi-source data information of each data collection point of the microchannel heat exchange module within a preset time period; for each multi-source data information, performing time filtering processing on each parameter information in the multi-source data information to obtain multi-source time-filtered data information corresponding to the multi-source data information; for each parameter information, extracting the time-filtered parameter information corresponding to the parameter information in each multi-source time-filtered data information, and performing spatial filtering processing on each extracted time-filtered parameter information to obtain spatial-filtered parameter information corresponding to the parameter information; each spatial-filtered parameter information constitutes the target multi-source data information; inputting the target multi-source data information into a preset phase state prediction model to obtain the phase state monitoring result of the microchannel heat exchange module. The method helps to improve the accuracy and reliability of phase state monitoring.

Description

Technical Field

[0001] The present application relates to the field of heat exchange technology, and in particular to a phase state monitoring method and device for a microchannel heat exchange module. Background Art

[0002] Microchannel heat exchange modules are widely used in high-precision industrial fields such as chemical industry, pharmaceutical industry, semiconductor manufacturing, and new energy due to their high heat transfer efficiency, compact structure, and energy saving. In these applications, accurate phase state monitoring is essential to ensure the stable operation of the heat exchange system, optimize heat exchange performance, and prevent equipment damage.

[0003] Existing technologies usually install a single type of sensor (such as a temperature sensor or a pressure sensor) in a microchannel to infer the phase state of the fluid by monitoring changes in specific parameters. The advantages of this method are simple system and low cost, but the disadvantage is the lack of multi-dimensional data support, resulting in inaccurate phase state monitoring results. Summary of the invention

[0004] The present application provides a phase state monitoring method and device for a microchannel heat exchange module to solve the problems raised by the above background technology.

[0005] In a first aspect, the present application provides a phase state monitoring method for a microchannel heat exchange module, comprising:

[0006] Acquire multi-source data information of each data collection point of the microchannel heat exchange module within a preset time period; wherein a plurality of data collection points are evenly arranged in the microchannel heat exchange module, and the multi-source data information includes a plurality of parameter information;

[0007] For each of the multi-source data information, time filtering is performed on each of the parameter information in the multi-source data information to obtain multi-source time-filtered data information corresponding to the multi-source data information;

[0008] For each of the parameter information, extract the time filtering parameter information corresponding to the parameter information from each of the multi-source time filtering data information, and perform spatial filtering processing on each of the extracted time filtering parameter information to obtain the spatial filtering parameter information corresponding to the parameter information; each of the spatial filtering parameter information constitutes the target multi-source data information;

[0009] The target multi-source data information is input into a preset phase state prediction model to obtain the phase state monitoring result of the microchannel heat exchange module; the phase state prediction model is a pre-trained neural network model.

[0010] In a possible implementation manner, performing time filtering processing on each parameter information in the multi-source data information respectively includes:

[0011] Generate a time domain corresponding to each parameter value in the parameter information based on a preset time domain generation algorithm; the time domain includes multiple parameter values;

[0012] For each parameter value in the parameter information, a time filtering process is performed on the parameter value based on a time domain corresponding to the parameter value to obtain a time filtered value of the parameter value.

[0013] In a possible implementation, the generating the time domain corresponding to each parameter value in the parameter information based on a preset time domain generation algorithm includes:

[0014] pass Acquire the kurtosis corresponding to the parameter information, and determine the time domain corresponding to the maximum value in the parameter information based on the kurtosis; wherein, is the kurtosis of the parameter information, represents the number of parameter values ​​in the parameter information, is the first parameter values, is the average value between the various parameter values ​​in the parameter information, is the standard deviation between each parameter value in the parameter information;

[0015] Obtaining the standard deviation between each parameter value in the parameter information;

[0016] For each parameter value except the maximum value in the parameter information, obtain the interval standard deviation between the parameter value and its adjacent parameter values, and compare the interval standard deviation with the standard deviation;

[0017] If the interval standard deviation is not greater than the standard deviation, determining a first preset time domain as the time domain corresponding to the parameter value; the first preset time domain includes the parameter value and a first adjacent parameter value, and the first adjacent parameter value is adjacent to the parameter value;

[0018] If the interval standard deviation is greater than the standard deviation, determine the second preset time domain as the time domain corresponding to the parameter value; the second preset time domain includes the parameter value, the first adjacent parameter value and the second adjacent parameter value, the first adjacent parameter value is adjacent to the parameter value, and the second adjacent parameter value is adjacent to the first adjacent parameter value.

[0019] In a possible implementation manner, determining the time domain corresponding to the maximum value in the parameter information based on the kurtosis includes:

[0020] comparing the kurtosis with a preset kurtosis;

[0021] If the kurtosis is less than the preset kurtosis, determining a third preset time domain as the time domain corresponding to the maximum value; the third preset time domain includes the maximum value, a first adjacent parameter value, a second adjacent parameter value and a third adjacent parameter value, the first adjacent parameter value is adjacent to the maximum value, the second adjacent parameter value is adjacent to the first adjacent parameter value, and the third adjacent parameter value is adjacent to the second adjacent parameter value;

[0022] If the kurtosis is not less than the preset kurtosis, determine that the fourth preset time domain is the time domain corresponding to the maximum value; the fourth preset time domain includes the maximum value, the first adjacent parameter value, the second adjacent parameter value, the third adjacent parameter value and the fourth adjacent parameter value, the first adjacent parameter value is adjacent to the maximum value, the second adjacent parameter value is adjacent to the first adjacent parameter value, the third adjacent parameter value is adjacent to the second adjacent parameter value, and the fourth adjacent parameter value is adjacent to the third adjacent parameter value.

[0023] In a possible implementation manner, performing time filtering on the parameter value based on the time domain corresponding to the parameter value to obtain the time filtered value of the parameter value includes:

[0024] pass Obtaining initial weight coefficients corresponding to each parameter value in the time domain; wherein, is the first The initial weight coefficient corresponding to the parameter value is is the parameter value corresponding to the time domain, is the first parameter values, is the standard deviation between the values ​​of each parameter in the time domain;

[0025] pass Get the first The target weight coefficient corresponding to the parameter value; among them, is the first The target weight coefficient corresponding to the parameter value is represents the number of parameter values ​​in the time domain;

[0026] A weighted sum is performed on each parameter value in the time domain based on a target weight coefficient corresponding to each parameter value in the time domain to obtain a time filtered value of the parameter value.

[0027] In a possible implementation manner, performing spatial filtering processing on each of the extracted temporal filtering parameter information to obtain spatial filtering parameter information corresponding to the parameter information includes:

[0028] For each of the time filtering parameter information, obtain the Pearson correlation coefficient between the time filtering parameter information and the other time filtering parameter information respectively, and compare each of the Pearson correlation coefficients with a preset Pearson correlation coefficient. If any of the Pearson correlation coefficients is not less than the preset Pearson correlation coefficient, determine that the time filtering parameter information is the target time filtering parameter information;

[0029] The average value of the time filtering parameter value of each target time filtering parameter information at the same data collection time is calculated in sequence to obtain the spatial filtering parameter information.

[0030] In a second aspect, the present application provides a phase state monitoring device for a microchannel heat exchange module, comprising:

[0031] An acquisition module, used to acquire multi-source data information of each data acquisition point of the microchannel heat exchange module within a preset time period; wherein a plurality of data acquisition points are evenly arranged in the microchannel heat exchange module, and the multi-source data information includes a plurality of parameter information;

[0032] A first filtering processing module is used to perform time filtering processing on each parameter information in the multi-source data information for each multi-source data information, so as to obtain multi-source time-filtered data information corresponding to the multi-source data information;

[0033] A second filtering processing module is used to extract the time filtering parameter information corresponding to each parameter information from each multi-source time filtering data information, and perform spatial filtering processing on each extracted time filtering parameter information to obtain the spatial filtering parameter information corresponding to the parameter information; each of the spatial filtering parameter information constitutes the target multi-source data information;

[0034] An input module is used to input the target multi-source data information into a preset phase state prediction model to obtain the phase state monitoring result of the microchannel heat exchange module; the phase state prediction model is a pre-trained neural network model.

[0035] The present application provides a phase state monitoring method and device for a microchannel heat exchange module, the method comprising: obtaining multi-source data information of each data collection point of the microchannel heat exchange module within a preset time period; wherein a plurality of data collection points are evenly arranged in the microchannel heat exchange module, and the multi-source data information includes a plurality of parameter information; for each of the multi-source data information, performing time filtering processing on each parameter information in the multi-source data information, respectively, to obtain multi-source time-filtered data information corresponding to the multi-source data information;

[0036] For each of the parameter information, the time filtering parameter information corresponding to the parameter information is extracted from each of the multi-source time filtering data information, and the extracted time filtering parameter information is subjected to spatial filtering processing to obtain the spatial filtering parameter information corresponding to the parameter information; each of the spatial filtering parameter information constitutes the target multi-source data information; the target multi-source data information is input into a preset phase state prediction model to obtain the phase state monitoring result of the microchannel heat exchange module; the phase state prediction model is a pre-trained neural network model. On the one hand, the method obtains multi-source data information including temperature, pressure, flow rate, vibration and other parameters by evenly arranging multiple data collection points in the microchannel heat exchange module, which helps to fully reflect the phase change characteristics of the fluid. Compared with the single sensor monitoring method in the prior art, the present invention can provide richer data support and significantly improve the accuracy and reliability of phase state monitoring. On the other hand, by performing time filtering processing and spatial filtering processing on the multi-source data information, the noise and interference in the multi-source data information are reduced, which helps to improve the accuracy and reliability of the phase state monitoring results. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0038] Figure 1 A schematic flow chart of a phase state monitoring method for a microchannel heat exchange module provided in an embodiment of the present application;

[0039] Figure 2 A schematic block diagram of the structure of a phase state monitoring device for a microchannel heat exchange module provided in an embodiment of the present application;

[0040] Figure 3 A schematic block diagram of the structure of a terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0043] It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0044] It should be further understood that the term “and / or” used in the specification and appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0045] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0046] See also Figure 1 , Figure 1 A schematic flow chart of a phase state monitoring method for a microchannel heat exchange module provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the phase state monitoring method of the microchannel heat exchange module provided in the embodiment of the present application includes steps S1 to S4.

[0047] Step S1, obtaining multi-source data information of each data collection point of the microchannel heat exchange module within a preset time period; wherein, a plurality of data collection points are evenly arranged in the microchannel heat exchange module, and the multi-source data information includes a plurality of parameter information.

[0048] Specifically, a sensor module is provided at each of the data collection points. The sensor module includes but is not limited to a temperature sensor, a pressure sensor, a flow rate sensor, a vibration sensor and an acoustic sensor. The multi-source data information is acquired through the sensor module.

[0049] Step S2: for each piece of the multi-source data information, perform time filtering processing on each piece of parameter information in the multi-source data information to obtain multi-source time-filtered data information corresponding to the multi-source data information.

[0050] Specifically, the time filtering process is performed on each parameter information in the multi-source data information, including the following steps:

[0051] Generate a time domain corresponding to each parameter value in the parameter information based on a preset time domain generation algorithm; the time domain includes multiple parameter values;

[0052] For each parameter value in the parameter information, a time filtering process is performed on the parameter value based on a time domain corresponding to the parameter value to obtain a time filtered value of the parameter value.

[0053] The step of generating the time domain corresponding to each parameter value in the parameter information based on a preset time domain generation algorithm includes the following steps:

[0054] pass Acquire the kurtosis corresponding to the parameter information, and determine the time domain corresponding to the maximum value in the parameter information based on the kurtosis; wherein, is the kurtosis of the parameter information, represents the number of parameter values ​​in the parameter information, is the first parameter values, is the average value between the various parameter values ​​in the parameter information, is the standard deviation between each parameter value in the parameter information; wherein the maximum value includes the maximum parameter value and the minimum parameter value in the parameter information;

[0055] Obtaining the standard deviation between each parameter value in the parameter information;

[0056] For each parameter value except the maximum value in the parameter information, obtain the interval standard deviation between the parameter value and its adjacent parameter values, and compare the interval standard deviation with the standard deviation;

[0057] If the interval standard deviation is not greater than the standard deviation, determining a first preset time domain as the time domain corresponding to the parameter value; the first preset time domain includes the parameter value and a first adjacent parameter value, and the first adjacent parameter value is adjacent to the parameter value;

[0058] If the interval standard deviation is greater than the standard deviation, determine the second preset time domain as the time domain corresponding to the parameter value; the second preset time domain includes the parameter value, the first adjacent parameter value and the second adjacent parameter value, the first adjacent parameter value is adjacent to the parameter value, and the second adjacent parameter value is adjacent to the first adjacent parameter value.

[0059] Wherein, determining the time domain corresponding to the maximum value in the parameter information based on the kurtosis comprises the following steps:

[0060] comparing the kurtosis with a preset kurtosis;

[0061] If the kurtosis is less than the preset kurtosis, determining a third preset time domain as the time domain corresponding to the maximum value; the third preset time domain includes the maximum value, a first adjacent parameter value, a second adjacent parameter value and a third adjacent parameter value, the first adjacent parameter value is adjacent to the maximum value, the second adjacent parameter value is adjacent to the first adjacent parameter value, and the third adjacent parameter value is adjacent to the second adjacent parameter value;

[0062] If the kurtosis is not less than the preset kurtosis, determine that the fourth preset time domain is the time domain corresponding to the maximum value; the fourth preset time domain includes the maximum value, the first adjacent parameter value, the second adjacent parameter value, the third adjacent parameter value and the fourth adjacent parameter value, the first adjacent parameter value is adjacent to the maximum value, the second adjacent parameter value is adjacent to the first adjacent parameter value, the third adjacent parameter value is adjacent to the second adjacent parameter value, and the fourth adjacent parameter value is adjacent to the third adjacent parameter value.

[0063] It can be understood that the method described above for generating the time domain corresponding to each parameter value in the parameter information based on a preset time domain generation algorithm, on the one hand, when filtering the maximum parameter value and the minimum parameter value in the parameter information, determines the time domain for the maximum parameter value and the minimum parameter value according to the comparison result of the kurtosis with the preset kurtosis, which helps to achieve effective filtering of the maximum parameter value and the minimum parameter value and prevent the negative impact of the maximum value on the overall data. On the other hand, for each parameter value other than the maximum value, by comparing the interval standard deviation corresponding to the parameter value with the overall standard deviation corresponding to the parameter information, and determining the time domain for the parameter value based on the comparison result, a smaller time domain is used in the part where the data changes steadily, and a larger time domain is used in the part where the data changes dramatically, which helps to ensure that the filtering process can effectively suppress noise without destroying the original characteristics of the data, and further, helps to improve the accuracy of the phase monitoring results.

[0064] The step of performing time filtering on the parameter value based on the time domain corresponding to the parameter value to obtain the time filtered value of the parameter value comprises the following steps:

[0065] pass Obtaining initial weight coefficients corresponding to each parameter value in the time domain; wherein, is the first The initial weight coefficient corresponding to the parameter value is is the parameter value corresponding to the time domain, is the first parameter values, is the standard deviation between the values ​​of each parameter in the time domain;

[0066] pass Get the first The target weight coefficient corresponding to the parameter value; among them, is the first The target weight coefficient corresponding to the parameter value is represents the number of parameter values ​​in the time domain;

[0067] A weighted sum is performed on each parameter value in the time domain based on a target weight coefficient corresponding to each parameter value in the time domain to obtain a time filtered value of the parameter value.

[0068] It can be understood that the method of performing time filtering on the parameter value based on the time domain corresponding to the parameter value to obtain the time filtered value of the parameter value performs weighted summation of each parameter value in the time domain based on the target weight coefficient corresponding to each parameter value in the time domain to obtain the time filtered value of the parameter value. This method can comprehensively consider the contribution of each parameter value in the time domain during the filtering process, effectively suppress noise interference, and retain useful information of the data. Compared with the traditional simple average filtering method, this method significantly improves the filtering effect while maintaining data details.

[0069] Step S3: for each of the parameter information, extract the time filtering parameter information corresponding to the parameter information from each of the multi-source time filtering data information, and perform spatial filtering processing on each of the extracted time filtering parameter information to obtain the spatial filtering parameter information corresponding to the parameter information; each of the spatial filtering parameter information constitutes the target multi-source data information.

[0070] Specifically, performing spatial filtering processing on each of the extracted temporal filtering parameter information to obtain spatial filtering parameter information corresponding to the parameter information includes the following steps:

[0071] For each of the time filtering parameter information, obtain the Pearson correlation coefficient between the time filtering parameter information and the remaining time filtering parameter information, and compare each of the Pearson correlation coefficients with the preset Pearson correlation coefficient. If any of the Pearson correlation coefficients is not less than the preset Pearson correlation coefficient, determine that the time filtering parameter information is the target time filtering parameter information; it can be understood that if each of the Pearson correlation coefficients is less than the preset Pearson correlation coefficient, it means that the time filtering parameter information contains more noise and interference. In order to improve the accuracy of the phase monitoring result, delete the time filtering parameter information containing more noise and interference;

[0072] The average value of the time filtering parameter value of each target time filtering parameter information at the same data collection time is calculated in sequence to obtain the spatial filtering parameter information.

[0073] It can be understood that the above-mentioned method of performing spatial filtering processing on each of the extracted time filter parameter information to obtain the spatial filter parameter information corresponding to the parameter information, and the selected target time filter parameter information is averaged at the same data collection time, which can effectively smooth the random noise and sudden interference in each sensor data. The averaging process reduces the impact of a single sensor abnormal value on the overall monitoring result, ensuring that the filtered data is smoother and more reliable.

[0074] Step S4, inputting the target multi-source data information into a preset phase state prediction model to obtain the phase state monitoring result of the microchannel heat exchange module; the phase state prediction model is a pre-trained neural network model.

[0075] The method provided in this embodiment, on the one hand, obtains multi-source data information including temperature, pressure, flow rate, vibration and other parameters by evenly distributing multiple data collection points in the microchannel heat exchange module, which helps to fully reflect the phase change characteristics of the fluid. Compared with the single sensor monitoring method in the prior art, the present invention can provide richer data support and significantly improve the accuracy and reliability of phase monitoring. On the other hand, by performing time filtering and spatial filtering on the multi-source data information, the noise and interference in the multi-source data information are reduced, which helps to improve the accuracy and reliability of the phase monitoring results.

[0076] See also Figure 2 , Figure 2 A schematic block diagram of the structure of a phase monitoring device 100 for a microchannel heat exchange module provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, the phase monitoring device 100 of the microchannel heat exchange module provided in the embodiment of the present application includes:

[0077] The acquisition module 110 is used to acquire multi-source data information of each data acquisition point of the microchannel heat exchange module within a preset time period; wherein a plurality of data acquisition points are evenly arranged in the microchannel heat exchange module, and the multi-source data information includes a plurality of parameter information.

[0078] The first filtering processing module 120 is used to perform time filtering processing on each parameter information in the multi-source data information respectively, so as to obtain multi-source time-filtered data information corresponding to the multi-source data information.

[0079] The second filtering processing module 130 is used to extract the time filtering parameter information corresponding to each of the parameter information in each of the multi-source time filtering data information, and perform spatial filtering processing on each of the extracted time filtering parameter information to obtain the spatial filtering parameter information corresponding to the parameter information; each of the spatial filtering parameter information constitutes the target multi-source data information.

[0080] The input module 140 is used to input the target multi-source data information into a preset phase state prediction model to obtain the phase state monitoring result of the microchannel heat exchange module; the phase state prediction model is a pre-trained neural network model.

[0081] It should be noted that technicians in the relevant technical field can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described device and each module can refer to the process in the aforementioned microchannel heat exchange module phase monitoring method embodiment, and will not be repeated here.

[0082] The phase state monitoring device 100 of the microchannel heat exchange module provided in the above embodiment can be implemented in the form of a computer program. The computer program can be used in Figure 3 The system is run on the terminal device 200 shown.

[0083] See also Figure 3 , Figure 3 The present invention provides a schematic block diagram of the structure of a terminal device 200 according to an embodiment of the present application. The terminal device 200 includes a processor 201 and a memory 202. The processor 201 and the memory 202 are connected via a device bus 203, wherein the memory 202 may include a non-volatile storage medium and an internal memory.

[0084] The non-volatile storage medium can store a computer program. The computer program includes program instructions, and when the program instructions are executed by the processor 201, the processor 201 can execute any of the above-mentioned phase state monitoring methods for the microchannel heat exchange module.

[0085] The processor 201 is used to provide computing and control capabilities to support the operation of the entire terminal device 200.

[0086] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor 201, the processor 201 can execute any of the above-mentioned phase state monitoring methods for the microchannel heat exchange module.

[0087] Those skilled in the art will understand that Figure 3The structure shown in the figure is only a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the terminal device 200 involved in the scheme of the present application. The specific terminal device 200 may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0088] It should be understood that the processor 201 may be a central processing unit (CPU), and the processor 201 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0089] In some embodiments, the processor 201 is used to run a computer program stored in the memory to implement the following steps:

[0090] Acquire multi-source data information of each data collection point of the microchannel heat exchange module within a preset time period; wherein a plurality of data collection points are evenly arranged in the microchannel heat exchange module, and the multi-source data information includes a plurality of parameter information;

[0091] For each of the multi-source data information, time filtering is performed on each of the parameter information in the multi-source data information to obtain multi-source time-filtered data information corresponding to the multi-source data information;

[0092] For each of the parameter information, extract the time filtering parameter information corresponding to the parameter information from each of the multi-source time filtering data information, and perform spatial filtering processing on each of the extracted time filtering parameter information to obtain the spatial filtering parameter information corresponding to the parameter information; each of the spatial filtering parameter information constitutes the target multi-source data information;

[0093] The target multi-source data information is input into a preset phase state prediction model to obtain the phase state monitoring result of the microchannel heat exchange module; the phase state prediction model is a pre-trained neural network model.

[0094] It should be noted that those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the terminal device 200 described above can refer to the process of the phase state monitoring method of the aforementioned microchannel heat exchange module, which will not be repeated here.

[0095] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by one or more processors, the one or more processors implement the phase state monitoring method of the microchannel heat exchange module provided in the embodiment of the present application.

[0096] The computer-readable storage medium may be an internal storage unit of the terminal device 200 in the aforementioned embodiment, such as a hard disk or memory of the terminal device 200. The computer-readable storage medium may also be an external storage device of the terminal device 200, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped with the terminal device 200.

[0097] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A phase state monitoring method for a microchannel heat exchange module, characterized in that: include: Acquire multi-source data information of each data collection point of the microchannel heat exchange module within a preset time period; wherein a plurality of data collection points are evenly arranged in the microchannel heat exchange module, and the multi-source data information includes a plurality of parameter information; For each of the multi-source data information, time filtering is performed on each of the parameter information in the multi-source data information to obtain multi-source time-filtered data information corresponding to the multi-source data information; For each of the parameter information, extract the time filtering parameter information corresponding to the parameter information from each of the multi-source time filtering data information, and perform spatial filtering processing on each of the extracted time filtering parameter information to obtain the spatial filtering parameter information corresponding to the parameter information; each of the spatial filtering parameter information constitutes the target multi-source data information; Inputting the target multi-source data information into a preset phase state prediction model to obtain a phase state monitoring result of the microchannel heat exchange module; the phase state prediction model is a pre-trained neural network model; The step of performing time filtering on each parameter information in the multi-source data information comprises: Generate a time domain corresponding to each parameter value in the parameter information based on a preset time domain generation algorithm; the time domain includes multiple parameter values; For each parameter value in the parameter information, performing time filtering processing on the parameter value based on a time domain corresponding to the parameter value to obtain a time filtered value of the parameter value; The performing spatial filtering processing on each of the extracted temporal filtering parameter information to obtain spatial filtering parameter information corresponding to the parameter information includes: For each of the time filtering parameter information, obtain the Pearson correlation coefficient between the time filtering parameter information and the other time filtering parameter information respectively, and compare each of the Pearson correlation coefficients with a preset Pearson correlation coefficient. If any of the Pearson correlation coefficients is not less than the preset Pearson correlation coefficient, determine that the time filtering parameter information is the target time filtering parameter information; The average value of the time filtering parameter value of each target time filtering parameter information at the same data collection time is calculated in sequence to obtain the spatial filtering parameter information.

2. The phase state monitoring method of the microchannel heat exchange module according to claim 1, characterized in that: The generating the time domain corresponding to each parameter value in the parameter information based on a preset time domain generating algorithm includes: pass Acquire the kurtosis corresponding to the parameter information, and determine the time domain corresponding to the maximum value in the parameter information based on the kurtosis; wherein, is the kurtosis of the parameter information, represents the number of parameter values ​​in the parameter information, is the first parameter values, is the average value between the various parameter values ​​in the parameter information, is the standard deviation between each parameter value in the parameter information; Obtaining the standard deviation between each parameter value in the parameter information; For each parameter value except the maximum value in the parameter information, obtain the interval standard deviation between the parameter value and its adjacent parameter values, and compare the interval standard deviation with the standard deviation; If the interval standard deviation is not greater than the standard deviation, determining a first preset time domain as the time domain corresponding to the parameter value; the first preset time domain includes the parameter value and a first adjacent parameter value, and the first adjacent parameter value is adjacent to the parameter value; If the interval standard deviation is greater than the standard deviation, determine the second preset time domain as the time domain corresponding to the parameter value; the second preset time domain includes the parameter value, the first adjacent parameter value and the second adjacent parameter value, the first adjacent parameter value is adjacent to the parameter value, and the second adjacent parameter value is adjacent to the first adjacent parameter value.

3. The phase state monitoring method of the microchannel heat exchange module according to claim 2, characterized in that: The determining, based on the kurtosis, a time domain corresponding to a maximum value in the parameter information comprises: comparing the kurtosis with a preset kurtosis; If the kurtosis is less than the preset kurtosis, determining a third preset time domain as the time domain corresponding to the maximum value; the third preset time domain includes the maximum value, a first adjacent parameter value, a second adjacent parameter value and a third adjacent parameter value, the first adjacent parameter value is adjacent to the maximum value, the second adjacent parameter value is adjacent to the first adjacent parameter value, and the third adjacent parameter value is adjacent to the second adjacent parameter value; If the kurtosis is not less than the preset kurtosis, determine that the fourth preset time domain is the time domain corresponding to the maximum value; the fourth preset time domain includes the maximum value, the first adjacent parameter value, the second adjacent parameter value, the third adjacent parameter value and the fourth adjacent parameter value, the first adjacent parameter value is adjacent to the maximum value, the second adjacent parameter value is adjacent to the first adjacent parameter value, the third adjacent parameter value is adjacent to the second adjacent parameter value, and the fourth adjacent parameter value is adjacent to the third adjacent parameter value.

4. The phase state monitoring method of the microchannel heat exchange module according to claim 1, characterized in that: The performing time filtering on the parameter value based on the time domain corresponding to the parameter value to obtain the time filtered value of the parameter value includes: pass Obtaining initial weight coefficients corresponding to each parameter value in the time domain; wherein, is the first The initial weight coefficient corresponding to the parameter value is is the parameter value corresponding to the time domain, is the first parameter values, is the standard deviation between the values ​​of each parameter in the time domain; pass Get the first The target weight coefficient corresponding to the parameter value; among them, is the first The target weight coefficient corresponding to the parameter value is represents the number of parameter values ​​in the time domain; A weighted sum is performed on each parameter value in the time domain based on a target weight coefficient corresponding to each parameter value in the time domain to obtain a time filtered value of the parameter value.

5. A phase state monitoring device for a microchannel heat exchange module, characterized in that: For executing the method according to any one of claims 1 to 4, the device comprises: An acquisition module, used to acquire multi-source data information of each data acquisition point of the microchannel heat exchange module within a preset time period; wherein a plurality of data acquisition points are evenly arranged in the microchannel heat exchange module, and the multi-source data information includes a plurality of parameter information; A first filtering processing module is used to perform time filtering processing on each parameter information in the multi-source data information for each multi-source data information, so as to obtain multi-source time-filtered data information corresponding to the multi-source data information; A second filtering processing module is used to extract the time filtering parameter information corresponding to each parameter information from each multi-source time filtering data information, and perform spatial filtering processing on each extracted time filtering parameter information to obtain the spatial filtering parameter information corresponding to the parameter information; each of the spatial filtering parameter information constitutes the target multi-source data information; An input module, used to input the target multi-source data information into a preset phase state prediction model to obtain a phase state monitoring result of the microchannel heat exchange module; the phase state prediction model is a pre-trained neural network model; The step of performing time filtering on each parameter information in the multi-source data information comprises: Generate a time domain corresponding to each parameter value in the parameter information based on a preset time domain generation algorithm; the time domain includes multiple parameter values; For each parameter value in the parameter information, performing time filtering processing on the parameter value based on a time domain corresponding to the parameter value to obtain a time filtered value of the parameter value; The performing spatial filtering processing on each of the extracted temporal filtering parameter information to obtain spatial filtering parameter information corresponding to the parameter information includes: For each of the time filtering parameter information, obtain the Pearson correlation coefficient between the time filtering parameter information and the other time filtering parameter information respectively, and compare each of the Pearson correlation coefficients with a preset Pearson correlation coefficient. If any of the Pearson correlation coefficients is not less than the preset Pearson correlation coefficient, determine that the time filtering parameter information is the target time filtering parameter information; The average value of the time filtering parameter value of each target time filtering parameter information at the same data collection time is calculated in sequence to obtain the spatial filtering parameter information.

Images