A heater performance comprehensive test optimization control method, system and storage medium

Abstract

The present invention discloses a heater performance comprehensive test optimization control method, system and storage medium, which relates to the field of equipment performance testing. Different test parameter sets of the heater to be tested are obtained as the first parameter set, and the historical standard test parameter set is obtained from the standard parameter retrieval directory as the second parameter set; a comprehensive test model based on a knowledge graph is constructed, and the comprehensive test model includes multiple nodes; the idle state of each node is calculated by an edge computing method, and the parameter information corresponding to the idle node is parsed using a preset computing task to obtain a second parsing result; the first parameter set information is parsed, and a correlation analysis is performed with the second parsing result to determine whether the heater performance is intact; the parameters of each intact heater are again subjected to particle swarm calculation according to the test rules to obtain the optimal control parameters, and the optimal control parameters are used to update the comprehensive test model. The present invention improves the test efficiency and accuracy, intelligence and automation levels.

Description

Technical Field

[0001] The invention relates to the field of equipment performance testing, and more specifically to a heater performance comprehensive testing optimization control method. Background Art

[0002] The main purpose of factory commissioning of heaters is to ensure the performance and safety of the heaters and to meet specific usage requirements. Through factory commissioning, it can be ensured that the heaters can work properly under various conditions and avoid malfunctions or unstable performance during use.

[0003] Among them, the specific contents of the factory debugging of the heater include the following aspects: PID parameter calibration: by adjusting the three parameters of proportion (P), integration (I) and differentiation (D), the heater can respond quickly and stabilize at the set temperature, reduce temperature fluctuations, and improve control accuracy. Safety inspection: check whether the various components of the heater are installed correctly and whether the circuit is intact to avoid safety hazards during use. Functional test: ensure that all functions of the heater are normal, such as temperature display, control switch, etc. can work normally. Through factory debugging, the heater can work stably under various conditions, improving the safety and reliability of use. Users can also be more assured during use to avoid inconvenience and safety hazards caused by equipment problems.

[0004] In summary, the specific content of the factory commissioning of the heater includes multiple aspects, and the commissioning parameters of each aspect are different. Therefore, how to implement comprehensive testing of heater performance and find the optimal control method is urgently needed to be studied by technical personnel in this field. Summary of the invention

[0005] In view of this, the present invention provides a heater performance comprehensive test optimization control method, system and storage medium, which show significant beneficial effects in improving test efficiency and accuracy, intelligence and automation levels, optimizing heater control parameters, improving model updating capabilities and enhancing the comprehensiveness of heater performance evaluation.

[0006] In order to achieve the above object, the present invention adopts the following technical solution:

[0007] A heater performance comprehensive test optimization control method comprises the following steps:

[0008] Obtain different test parameter sets of the heater to be tested as a first parameter set, and obtain a historical standard test parameter set from a standard parameter retrieval directory as a second parameter set;

[0009] A comprehensive test model based on the knowledge graph is constructed using the second parameter set, wherein the comprehensive test model includes a plurality of nodes, and each parameter is distributed in a different node;

[0010] The idle state of each node is calculated by an edge computing method, the nodes are classified according to the idle state, and the parameter information corresponding to the idle nodes is parsed by using a preset computing task to obtain a second parsing result;

[0011] Parsing the first parameter set information to obtain a first parsing result, performing a correlation analysis on the first parsing result and the second parsing result, and if the correlation value is higher than a preset threshold, determining that the heater performance is intact;

[0012] The parameters of each intact heater are again calculated by particle swarm according to the test rules to obtain the optimal control parameters, and the comprehensive test model is updated using the optimal control parameters.

[0013] Optionally, the idle state of each node is calculated by edge computing method. The specific steps are as follows:

[0014] Bind the central node and edge nodes of the knowledge graph, obtain the working status information of the edge nodes, determine the utilization rate of the edge nodes, and sort them according to the utilization rate;

[0015] The central node synchronously obtains the usage ranking structure of the edge nodes and determines the idle state level of the edge nodes.

[0016] Optionally, a correlation analysis is performed on the first analysis result and the second analysis result. The specific steps are as follows:

[0017] Perform entity recognition on the data in the idle nodes to output data text and extract feature values ​​from the text data; extract related knowledge information and intent information by matching in the knowledge graph through entity linking to form a second data set; perform entity extraction on the first parameter set and convert it into knowledge information and intent information to form a first data set; perform association analysis on the first data set and calculate the association value using the covariance function.

[0018] Optionally, nodes are classified according to idle status, specifically: current operating data of idle network nodes in the period to be used is obtained, predicted idle time periods of idle network nodes are obtained according to the operating data of idle network nodes and a historical experience data model, and classification is performed according to the length of the predicted idle time periods.

[0019] Optionally, the historical experience data model is obtained by training a convolutional neural network through historical idle time.

[0020] Optionally, the particle swarm algorithm searches for the global optimal solution through information sharing and collaboration among particles to achieve the acquisition of optimal control parameters.

[0021] A heater performance comprehensive test optimization control system, comprising:

[0022] Parameter set acquisition module: used to acquire different test parameter sets of the heater to be tested as the first parameter set, and to acquire historical standard test parameter sets from the standard parameter retrieval directory as the second parameter set;

[0023] Parameter distribution module: used to construct a comprehensive test model based on the knowledge graph using the second parameter set, wherein the comprehensive test model includes a plurality of nodes, and each parameter is distributed in a different node;

[0024] Knowledge graph parameter parsing module: used to calculate the idle state of each node through the edge computing method, classify the nodes according to the idle state, and use the preset computing task to parse the parameter information corresponding to the idle node to obtain the second parsing result;

[0025] Correlation analysis module: used to analyze the first parameter set information, obtain the first analysis result, and perform correlation analysis on the first analysis result and the second analysis result. If the correlation value is higher than a preset threshold, it is determined that the heater performance is intact;

[0026] Model optimization and updating module: It is used to perform particle swarm calculation on the parameters of the intact heater again according to the test rules to achieve the optimal control parameters, and use the optimal control parameters to update the comprehensive test model.

[0027] A computer storage medium stores a computer program, and when the computer program is executed by a processor, the steps of a heater performance comprehensive test optimization control method are implemented.

[0028] It can be seen from the above technical solutions that, compared with the prior art, the present invention provides a heater performance comprehensive test optimization control method, system and storage medium, which have the following beneficial effects:

[0029] 1. By obtaining the first parameter set of the heater to be tested and comparing it with the second parameter set in the standard parameter retrieval catalog, the performance status of the heater can be quickly located. The comprehensive test model built using the knowledge graph can systematically organize and present various parameters of the heater to facilitate correlation analysis. The use of edge computing methods can calculate the idle state of the node in real time, thereby efficiently parsing parameter information and improving test efficiency.

[0030] 2. By performing particle swarm calculation on the parameters of intact heaters, the optimal control parameters can be obtained. Obtaining the optimal control parameters helps to improve the operating efficiency and performance of the heater and reduce energy consumption and costs. At the same time, by updating the comprehensive test model with the optimal control parameters, the model performance can be continuously optimized to make it more in line with actual operating requirements. The continuous updating of the model helps to maintain the advancement and accuracy of the test method and provide strong support for the long-term monitoring and optimization of heater performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0032] Figure 1 It is a schematic diagram of the process of the present invention;

[0033] Figure 2 It is a schematic diagram of the structure of the present invention. DETAILED DESCRIPTION

[0034] 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 only 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.

[0035] Example 1

[0036] The embodiment of the present invention discloses a heater performance comprehensive test optimization control method, such as Figure 1 As shown, the following steps are included:

[0037] Step 1: obtaining different test parameter sets of the heater to be tested as the first parameter set, and obtaining a historical standard test parameter set from a standard parameter retrieval directory as the second parameter set;

[0038] Step 2: Use the second parameter set to construct a comprehensive test model based on the knowledge graph, wherein the comprehensive test model includes multiple nodes, and each parameter is distributed in a different node;

[0039] Step 3: Calculate the idle state of each node by edge computing method, classify the nodes according to the idle state, and parse the parameter information corresponding to the idle nodes by using the preset computing task to obtain the second parsing result;

[0040] Step 4: parse the first parameter set information to obtain a first parsing result, and perform a correlation analysis on the first parsing result and the second parsing result. If the correlation value is higher than a preset threshold, it is determined that the heater performance is intact.

[0041] Step 5: Perform particle swarm calculation on the parameters of each intact heater again according to the test rules to obtain the optimal control parameters, and use the optimal control parameters to update the comprehensive test model.

[0042] Furthermore, in step three, the idle state of each node is calculated by edge computing method. The specific steps are as follows:

[0043] Step 3.1: Bind the central node and edge nodes of the knowledge graph, obtain the working status information of the edge nodes, determine the utilization rate of the edge nodes, and sort them according to the utilization rate;

[0044] Step 3.2: The central node synchronously obtains the usage ranking structure of the edge nodes and determines the idle state level of the edge nodes.

[0045] Furthermore, in step three, the nodes are classified according to the idle status, specifically: the current operation data of the idle network nodes in the period to be used is obtained, the predicted idle time period of the idle network nodes is obtained according to the operation data of the idle network nodes according to the historical experience data model, and the nodes are classified according to the length of the predicted idle time period.

[0046] Furthermore, in step 4, correlation analysis is performed on the first analysis result and the second analysis result. The specific steps are as follows:

[0047] Perform entity recognition on the data in the idle nodes to output data text and extract feature values ​​from the text data; extract related knowledge information and intent information by matching in the knowledge graph through entity linking to form a second data set; perform entity extraction on the first parameter set and convert it into knowledge information and intent information to form a first data set; perform association analysis on the first data set and calculate the association value using the covariance function.

[0048] Furthermore, the historical experience data model is obtained by training the convolutional neural network through historical idle time.

[0049] Furthermore, the particle swarm algorithm searches for the global optimal solution through information sharing and collaboration among particles to achieve the acquisition of optimal control parameters.

[0050] and Figure 1 Corresponding to the method shown, the present invention also discloses a heater performance comprehensive test optimization control system for Figure 1 The implementation of the method, the specific structure is as follows Figure 2 As shown, including:

[0051] Parameter set acquisition module: used to acquire different test parameter sets of the heater to be tested as the first parameter set, and to acquire historical standard test parameter sets from the standard parameter retrieval directory as the second parameter set;

[0052] Parameter distribution module: used to construct a comprehensive test model based on the knowledge graph using the second parameter set, wherein the comprehensive test model includes a plurality of nodes, and each parameter is distributed in a different node;

[0053] Knowledge graph parameter parsing module: used to calculate the idle state of each node through the edge computing method, classify the nodes according to the idle state, and use the preset computing task to parse the parameter information corresponding to the idle node to obtain the second parsing result;

[0054] Correlation analysis module: used to analyze the first parameter set information, obtain the first analysis result, and perform correlation analysis on the first analysis result and the second analysis result. If the correlation value is higher than a preset threshold, it is determined that the heater performance is intact;

[0055] Model optimization and updating module: It is used to perform particle swarm calculation on the parameters of the intact heater again according to the test rules to achieve the optimal control parameters, and use the optimal control parameters to update the comprehensive test model.

[0056] Finally, this embodiment discloses a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the heater performance comprehensive test optimization control method are implemented.

[0057] Example 2

[0058] The following discloses the specific use of the test bench using the method of the present invention:

[0059] Install the test heater on the test bench, connect the water inlet and outlet pipes of the small water tank and the water inlet and outlet pipes of the heater respectively, connect the wiring harness, connect the oil pipe, insert the inlet and return oil into the oil pipe of the test bench, turn on the heater water pump switch, check that the water circulation is normal, turn on the heater switch, the heater starts to ignite and burn, detect the voltage meter, ammeter, water temperature meter, exhaust temperature meter and other parameters of the test bench, and they are normal and qualified; after the heater water temperature is 81℃ and shut down, the water pump keeps circulating, the temperature drops to 68 degrees, and the second start is performed. After passing the test, turn off the heater, close the small circulation valve, open the heater waterproof plug, and the internal circulating water automatically flows to the circulating large water tank. A small amount of coolant in the disassembly process flows from the waste water pipe to the oil-water separator. After oil-water separation, pure water flows to the large water tank, and the residual oil on the surface flows to the recovery barrel, which is collected and processed uniformly. Realize the debugging of the application of circulating water and test the performance of the heater.

[0060] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0061] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A heater performance comprehensive test optimization control method, characterized in that: The following steps are involved: Obtain different test parameter sets of the heater to be tested as a first parameter set, and obtain a historical standard test parameter set from a standard parameter retrieval directory as a second parameter set; A comprehensive test model based on the knowledge graph is constructed using the second parameter set, wherein the comprehensive test model includes a plurality of nodes, and each parameter is distributed in a different node; The idle state of each node is calculated by an edge computing method, the nodes are classified according to the idle state, and the parameter information corresponding to the idle nodes is parsed by using a preset computing task to obtain a second parsing result; Parsing the first parameter set information to obtain a first parsing result, performing a correlation analysis on the first parsing result and the second parsing result, and if the correlation value is higher than a preset threshold, determining that the heater performance is intact; The parameters of each intact heater are again calculated by particle swarm according to the test rules to obtain the optimal control parameters, and the comprehensive test model is updated using the optimal control parameters.

2. A heater performance comprehensive test optimization control method according to claim 1, characterized in that: The idle state of each node is calculated by edge computing method. The specific steps are as follows: Bind the central node and edge nodes of the knowledge graph, obtain the working status information of the edge nodes, determine the utilization rate of the edge nodes, and sort them according to the utilization rate; The central node synchronously obtains the usage ranking structure of the edge nodes and determines the idle state level of the edge nodes.

3. A heater performance comprehensive test optimization control method according to claim 1, characterized in that: The correlation analysis is performed on the first analysis result and the second analysis result. The specific steps are as follows: Perform entity recognition on the data in the idle nodes to output data text and extract feature values ​​in the text data; extract related knowledge information and intention information in the knowledge graph through entity linking to form a second data set; Extract entities from the first parameter set and convert them into knowledge information and intent information to form a first data set; The first data set and the second data set are subjected to correlation analysis, and the correlation value is calculated using the covariance function.

4. A heater performance comprehensive test optimization control method according to claim 1, characterized in that: Nodes are classified according to idle status, specifically: current operation data of idle network nodes in the period to be used is obtained, predicted idle time periods of idle network nodes are obtained according to the operation data of idle network nodes and historical experience data models, and classification is performed according to the length of the predicted idle time periods.

5. A heater performance comprehensive test optimization control method according to claim 4, characterized in that: The historical experience data model is obtained by training the convolutional neural network through historical idle time.

6. A heater performance comprehensive test optimization control method according to claim 1, characterized in that: The particle swarm algorithm searches for the global optimal solution through information sharing and collaboration among particles to achieve the acquisition of optimal control parameters.

7. A heater performance comprehensive test optimization control system, characterized in that: include: Parameter set acquisition module: used to acquire different test parameter sets of the heater to be tested as the first parameter set, and to acquire historical standard test parameter sets from the standard parameter retrieval directory as the second parameter set; Parameter distribution module: used to construct a comprehensive test model based on the knowledge graph using the second parameter set, wherein the comprehensive test model includes a plurality of nodes, and each parameter is distributed in a different node; Knowledge graph parameter parsing module: used to calculate the idle state of each node through the edge computing method, classify the nodes according to the idle state, and use the preset computing task to parse the parameter information corresponding to the idle node to obtain the second parsing result; Correlation analysis module: used to analyze the first parameter set information, obtain the first analysis result, and perform correlation analysis on the first analysis result and the second analysis result. If the correlation value is higher than a preset threshold, it is determined that the heater performance is intact; Model optimization and updating module: It is used to perform particle swarm calculation on the parameters of the intact heater again according to the test rules to achieve the optimal control parameters, and use the optimal control parameters to update the comprehensive test model.

8. A computer storage medium, characterized in that: The computer storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the heater performance comprehensive test optimization control method as described in any one of claims 1 to 6 are implemented.

Images