Refrigerating machine environment testing method, device and equipment and storage medium
By obtaining refrigerator sample data, performing data preprocessing and DBSCAN clustering algorithm, and automatically formulating environmental test standards, the problem of low refrigerator screening accuracy is solved, efficient screening is achieved, and rework costs are reduced.
Patent Information
- Application Number
- CN202510826474.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-19
- Publication Date
- 2025-10-17
AI Technical Summary
Existing refrigerator environmental testing relies on human judgment, resulting in low accuracy in screening unqualified refrigerators and frequent misscreening or missed screening.
By obtaining refrigerator sample data, performing data preprocessing and calculating statistical parameters, the DBSCAN clustering algorithm is used for unsupervised cluster division, the environmental test standards are revised, the target environmental test standards are formulated, and automated screening is achieved.
It improves the accuracy of refrigerator screening, reduces human error, improves production efficiency and reduces repair costs.
Smart Images
Figure CN120804804A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of refrigerator equipment detection, in particular to a refrigerator environmental test method, device, equipment and storage medium. BACKGROUND
[0002] The whole Stirling rotary refrigerator is mainly used for providing an effective cold source for a low-temperature detector. In order to ensure that each refrigerator can be stably operated, a large number of environmental tests need to be performed on the refrigerator equipment in the production screening stage. However, the current production and test standards are mainly set by experience and rely on human judgment, and unqualified refrigerator screening is often missed. SUMMARY
[0003] Therefore, it is necessary to provide a refrigerator environmental test method, device, equipment and storage medium capable of analyzing and calculating incoming data, refrigerator production data and test experimental data, formulating a target environmental test standard through an unsupervised learning algorithm, and effectively improving the screening accuracy of unqualified refrigerators.
[0004] In a first aspect, the present application provides a refrigerator environmental test method, which comprises: obtaining refrigerator sample data of a plurality of refrigerator equipment, wherein the refrigerator sample data comprises incoming data, production data and historical experimental data, and the historical experimental data comprises normal temperature running-in test characteristic parameters, high and low temperature test characteristic parameters and performance test characteristic parameters; performing data preprocessing on the refrigerator sample data to obtain optimized sample data, wherein the data preprocessing comprises outlier detection processing, missing value filling processing and data standardization processing; calculating statistical parameters of each characteristic in the optimized sample data, and determining a first environmental test standard according to the statistical parameters; performing unsupervised cluster division on the refrigerator sample data based on a DBSCAN clustering algorithm to obtain a clustering result, and determining a second environmental test standard according to the clustering result; modifying the first environmental test standard according to the second environmental test standard to obtain a target environmental test standard, wherein the target environmental test standard comprises a characteristic parameter threshold range for making the refrigerator equipment pass the environmental test; performing environmental test on a refrigerator equipment to be tested according to the target environmental test standard.
[0005] In one of the embodiments, the normal-temperature running-in test characteristic parameters include a normal-temperature running-in test current, a normal-temperature running-in test rotating speed and a normal-temperature running-in test focus temperature; the high-low temperature test characteristic parameters include a high-low temperature test current, a high-low temperature test frequency reduction time length, a high-low temperature test rotating speed and a high-low temperature test focus temperature; and the performance test characteristic parameters include a performance test current, a performance test rotating speed, a performance test focus temperature, a performance test temperature recovery time length and a performance test frequency reduction time length. The data preprocessing of the refrigeration machine sample data comprises: The refrigeration machine sample data are normalized to obtain the optimized sample data; The optimized sample data are subjected to an outlier detection based on an isolated forest algorithm, and the detected outliers are removed as missing values; The missing values are filled according to a k-nearest neighbor interpolation algorithm.
[0006] In one of the embodiments, the statistical parameters include minimum and maximum values of the features; and the determination of the first environmental test standard according to the statistical parameters comprises: determination of a first threshold range corresponding to each feature in the optimized sample data, wherein the boundary points of the first threshold range are the minimum and maximum values of the features; comprehensive determination of the first environmental test standard from the first threshold ranges corresponding to all the features in the refrigeration machine sample data.
[0007] In one of the embodiments, the clustering result includes a plurality of classes, wherein one class corresponds to a data set of refrigeration machine equipment of one category; and the determination of the second environmental test standard according to the clustering result comprises: determination of a target class corresponding to refrigeration machine equipment of a target category; calculation of a second threshold range of features corresponding to the refrigeration machine equipment in the target class; comprehensive determination of the second environmental test standard from the second threshold range.
[0008] In one of the embodiments, the number of features included in the first environmental test standard is greater than or equal to the number of feature data included in the second environmental test standard; and the modification of the first environmental test standard according to the second environmental test standard to obtain a target environmental test standard comprises: modification of a feature parameter threshold range corresponding to a second feature in the first environmental test standard according to a feature parameter threshold range corresponding to a first feature in the second environmental test standard; wherein the first feature and the second feature are the same feature; According to the modified feature parameter threshold range and the feature parameter threshold range in the first environment test standard that has not been modified, the target environment test standard is obtained.
[0009] In one of the embodiments, the environment test on the to-be-tested refrigeration machine equipment according to the target environment test standard comprises: In the case that all parameters of the to-be-tested refrigeration machine equipment during the environment test meet the target environment test standard, the to-be-tested refrigeration machine equipment is determined as a qualified refrigeration machine equipment. In the case that any parameter of the to-be-tested refrigeration machine equipment during the environment test does not meet the target environment test standard, the to-be-tested refrigeration machine equipment is determined as an unqualified refrigeration machine equipment.
[0010] In one of the embodiments, the method further comprises: Performing life test on the qualified refrigeration machine equipment and the unqualified refrigeration machine equipment respectively to obtain a first life test result corresponding to the qualified refrigeration machine equipment and a second life test result corresponding to the unqualified refrigeration machine equipment; In the case that the first life test result is greater than the second life test result, continue to perform environment test on the to-be-tested refrigeration machine equipment using the current target environment test standard; In the case that the first life test result is less than the second life test result, increase the data amount of the refrigeration machine sample data, and reacquire a target environment test standard, and perform environment test on the to-be-tested refrigeration machine equipment according to the target environment test standard until the first life test result is greater than the second life test result.
[0011] In a second aspect, the application further provides a refrigeration machine environment test device, comprising: An acquisition module is configured to acquire refrigeration machine sample data of a plurality of refrigeration machine equipments, wherein the refrigeration machine sample data comprises incoming data, production data and historical experimental data, and the historical experimental data comprises normal temperature running-in test feature parameters, high-low temperature test feature parameters and performance test feature parameters. A preprocessing module is configured to perform data preprocessing on the refrigeration machine sample data to obtain optimized sample data, wherein the data preprocessing comprises outlier detection processing, missing value filling processing and data standardization processing. A calculation module is configured to calculate statistical parameters of each feature in the optimized sample data, and determine a first environment test standard according to the statistical parameters. A clustering module is configured to perform unsupervised cluster division on the refrigeration machine sample data based on a DBSCAN clustering algorithm to obtain a clustering result, and determine a second environment test standard according to the clustering result. a correction module, configured to correct the first environmental test standard according to the second environmental test standard to obtain a target environmental test standard, wherein the target environmental test standard includes a characteristic parameter threshold range for the refrigerator device to pass the environmental test; The test module is used to perform environmental testing on the refrigerator device to be tested according to the target environmental testing standard.
[0012] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the refrigerator environment testing method described in the first aspect are implemented.
[0013] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the refrigerator environment testing method described in the first aspect.
[0014] In a fifth aspect, the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps of the refrigerator environment testing method described in the first aspect are implemented.
[0015] In summary, the present application proposes a refrigerator environmental testing method, apparatus, equipment, and storage medium, including: obtaining refrigerator sample data of multiple refrigerator devices; performing data preprocessing on the refrigerator sample data to obtain optimized sample data; calculating the statistical parameters of each feature in the optimized sample data, and determining a first environmental testing standard based on the statistical parameters; performing unsupervised clustering on the refrigerator sample data based on the DBSCAN clustering algorithm to obtain clustering results, and determining a second environmental testing standard based on the clustering results; correcting the first environmental testing standard according to the second environmental testing standard to obtain a target environmental testing standard; and performing environmental testing on the refrigerator device to be tested according to the target environmental testing standard. The present application automatically formulates refrigerator environmental testing standards through an unsupervised learning algorithm and applies them to environmental testing, which can effectively improve the accuracy of refrigerator quality screening and improve production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] Figure 1 1 is a flow chart of a refrigerator environment testing method according to an embodiment; Figure 2 Schematic diagram of a flow chart of a refrigerator environment testing method according to another embodiment; Figure 3 is a structural block diagram of a refrigerator environment testing device in one embodiment; Figure 4 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION
[0017] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in combination with the drawings and examples. It should be understood that the specific examples described herein are only used to explain the present application and do not limit the present application.
[0018] In the production line of the Stirling refrigerator, in order to ensure that each refrigerator can stably run, a large number of environmental tests will be performed on the refrigerator to screen out qualified Stirling refrigerator products and unqualified Stirling refrigerator products. However, during the environmental test, due to the problem of artificially formulating test standards, the accuracy of the environmental test is low, and the phenomenon of screening out unqualified refrigerator products is wrong or missed.
[0019] In one embodiment, as shown in Figure 1 A refrigerator environmental test method is provided, comprising the following steps: S101, obtaining refrigerator sample data of a plurality of refrigerator devices, wherein the refrigerator sample data includes incoming data, production data and historical experimental data, and the historical experimental data includes normal temperature running-in test characteristic parameters, high and low temperature test characteristic parameters and performance test characteristic parameters.
[0020] In this embodiment, the incoming data includes, for example, incoming size parameters of the refrigerator body, the plunger, the crankshaft and the like. The production data includes, for example, the production quantity, the completion situation and the like on the refrigerator production line of the body assembly, the compression assembly, the expansion assembly, the rotor assembly and the whole machine assembly.
[0021] The normal temperature running-in test characteristic parameters include normal temperature running-in test current, normal temperature running-in test speed and normal temperature running-in test focal temperature; the high and low temperature test characteristic parameters include high and low temperature test current, high and low temperature test frequency reduction time, high and low temperature test speed and high and low temperature test focal temperature; and the performance test characteristic parameters include performance test current, performance test speed, performance test focal temperature, performance test temperature rise time and performance test frequency reduction time.
[0022] In this embodiment, the number of refrigerator devices corresponding to the refrigerator sample data can be determined according to the needs of the actual application scene. For example, the number of refrigerator devices corresponding to the refrigerator sample data can be configured as 500, that is, the refrigerator sample data of 500 refrigerator devices is obtained.
[0023] It should be noted that the acquisition of the refrigerator sample data can be collected by a computer device or a monitoring system on the production line in the relevant application scene, and the specific acquisition method of the refrigerator sample data is not limited in this embodiment.
[0024] S102, data preprocessing is performed on the refrigeration machine sample data to obtain optimized sample data, wherein the data preprocessing includes outlier detection processing, missing value filling processing and data standardization processing.
[0025] In this embodiment, the outlier detection processing is mainly used for detecting and removing outliers in the refrigeration machine sample data. The outliers refer to abnormal parameter values in the refrigeration machine sample data. For example, parameters with sizes that do not conform to standard sizes or preset sizes are abnormal size values. Processes with sequence errors in the whole machine assembly process are abnormal processes. Currents deviating from standard currents in normal temperature running-in test, high and low temperature test or performance test are abnormal current values. It should be noted that the outliers in this embodiment need to be determined according to the actual application scenario and the actual type of the refrigeration machine sample data.
[0026] The missing value filling processing is mainly used for supplementing missing values in the refrigeration machine sample data, so as to facilitate subsequent calculation of statistical characteristics and data standardization processing.
[0027] The data standardization processing is mainly used for unifying dimensions, accelerating the precision of the outlier detection processing and the algorithm sensitivity of the missing value filling algorithm, and improving the algorithm performance of the outlier detection and the missing value filling.
[0028] In one embodiment, the data preprocessing of the refrigeration machine sample data includes: first, standardizing the refrigeration machine sample data to obtain the optimized sample data. Second, detecting outliers in the optimized sample data based on the Isolation Forest algorithm, and removing the detected outliers as missing values. Third, filling the missing values according to the k-Nearest Neighbor Imputation algorithm.
[0029] In actual application problems, different variables often have different dimensions and orders of magnitude. For example, the value range of one variable is 0 to 1, and the value range of another variable is 100 to 10000. If these data are directly used for machine learning, the features with large value ranges will have a greater impact on the model, which may cause the model to fail to correctly learn the information of other features. Through data standardization, the value ranges of all features can be unified to the same scale, so that the model can consider the information of each feature fairly. In this embodiment, the refrigeration machine sample data is transformed by standardization to obtain optimized sample data with a mean of 0 and a variance of 1.
[0030] Specifically, if the refrigeration machine sample data is the refrigeration machine sample data is transformed based on formula 1, formula 1: wherein, represents the i-th sample in the refrigeration machine sample data, represents the i-th sample in the transformed optimization sample data, represents the average value of each sample in the refrigeration machine sample data, and n represents the number of samples in the refrigeration machine sample data. s is calculated based on formula 2, formula 2: Transformed to obtain an optimized experimental data set , represents the n-th sample in the optimization sample data.
[0031] In this embodiment, the isolation forest algorithm can generate multiple trees through its own mechanism. The principle of generating trees is that feature selection is random and a threshold is randomly set. As each tree grows, when a certain height is reached or each leaf node has only one point, those points with relatively shallow depth can be quickly identified as abnormal value points. The specific steps of the isolation forest algorithm are as follows: First, randomly select n sample points from the optimization sample data to form a subset, and build trees on m subsets. Second, randomly select a feature (for example, refrigeration machine incoming size, component production, whole machine assembly, or performance test data) and a threshold for bisection. Third, recursively build trees in the second step until a certain height is reached or each leaf has only one point. Fourth, define the abnormal probability according to the average depth of the m decision trees.
[0032] wherein the abnormal probability is defined according to the average depth of the m decision trees, that is, the abnormal probability is defined according to formula 3, formula 3: wherein, is the abnormal index of the sample data in the iTree trained by data, is the expectation of the path length of the data in all iTrees, represents the path length of each tree, is the path length of the sample . The path length of the sample is calculated by formula 2, formula 2: ; wherein, is the harmonic number, which can be estimated as , is the average value of the path length when the given sample number is n, which is used to standardize the path length of the sample .
[0033] When the anomaly index is close to 1, the sample will be determined as an anomaly, and the outlier will be removed. The specific determination range is determined according to the actual situation, and is not specifically limited here.
[0034] In this embodiment, the specific steps of the k-nearest neighbor interpolation algorithm (K-Nearest Neighbors, KNN) include: First, define the distance metric, for example, define the Gower distance, which can handle continuous and categorical variables at the same time; second, determine the number of neighbors (k value), for example, take k = 6; third, search for the nearest neighbor, for each sample with missing values, calculate the distance between the sample and all complete samples (only based on non-missing features); Sort by distance in ascending order, and select the top k nearest neighbors. Fourth, missing value filling, interpolation according to the information of the nearest neighbor, for continuous variables, use the mean / median for filling, for example, take the mean of the k nearest neighbors corresponding to the feature for filling; for categorical variables, use the mode for filling, for example, take the most frequent category among the k nearest neighbors for filling.
[0035] S103, calculate the statistical parameters of each feature in the optimized sample data, and determine the first environmental test standard according to the statistical parameters.
[0036] In this embodiment, the statistical parameter is a statistical parameter, including but not limited to mean, median, standard deviation, minimum value, maximum value, quantile. By calculating the statistical parameters corresponding to each feature in the optimized sample data, the test standard in the environmental test can be determined according to the statistical parameters.
[0037] In one embodiment, the statistical parameters include the minimum and maximum values of the features; and determining the first environmental test standard according to the statistical parameters includes: determining a first threshold range corresponding to each feature according to the maximum and minimum values of each feature in the optimized sample data, wherein the boundary points of the first threshold range are the minimum and maximum values of the feature; and obtaining the first environmental test standard by comprehensively determining the first threshold range corresponding to all features in the comprehensive refrigerator sample data.
[0038] In this embodiment, the first environmental test standard can be directly calculated according to the optimized sample data obtained by processing steps S101-S102. Based on the above steps, the incoming data, refrigerator production data and test experimental data can be analyzed and calculated, and the production and test data determination standard can be calculated. And in the data preprocessing process, the isolated forest algorithm is used to randomly select features and randomly select threshold values, which can realize the processing of the refrigerator sample data using unsupervised learning algorithm, and then the first environmental test standard can be quickly and efficiently obtained.
[0039] In S104, unsupervised cluster division is performed on the chiller sample data based on the DBSCAN clustering algorithm to obtain a clustering result, and a second environmental test standard is determined according to the clustering result.
[0040] In this embodiment, the clustering result includes a plurality of classes, wherein one class corresponds to a data set of chiller equipment of one category.
[0041] The specific steps of performing unsupervised cluster division on the chiller sample data based on the DBSCAN clustering algorithm are as follows: Suppose the chiller sample set is unsupervised cluster division is performed on the chiller by the DBSCAN clustering algorithm, the given field radius Eps and the minimum number of points in the field radius that become core objects are determined. A sample point is randomly selected from the sample , and is taken as the center, and is taken as the radius, to judge the relationship between the number of samples in the radius range and . When , the center point is , and the samples in the range are core objects, otherwise they are noise points. Then, the core object is taken as the center of the circle, and the above steps are repeated until all sample points are traversed.
[0042] wherein the number of samples is defined as: for , when , the neighborhood contains a sample set whose distance from is less than or equal to , and the number of this sub-sample set is ; the definition of core object is: for any sample , if its neighborhood corresponds to at least contains samples, i.e. if , then is a core object.
[0043] In this embodiment, the second environmental test standard is determined according to the clustering result, including: determining a target class corresponding to the chiller equipment of the target category; calculating a second threshold range of the features corresponding to the chiller equipment in the target class; and obtaining the second environmental test standard by synthesizing the second threshold range.
[0044] In this embodiment, the different cluster refrigerators classified by the DBSCAN model, that is, the refrigerator equipment in the target class, can be calculated to calculate the maximum and minimum values of the high and low temperature speeds, high and low temperature starting currents, high and low temperature stable currents, high and low temperature frequency reduction times, and high and low temperature current fluctuations of the refrigerators in each cluster, and the second threshold range can be calculated using the maximum and minimum parameter values of the cluster refrigerators obtained by classification.
[0045] In this embodiment, the target class can be distinguished based on the similarity with the refrigerator to be tested. For example, refrigerators with an 80% similarity to the refrigerator to be tested are classified into one class, refrigerators with a 60% similarity to the refrigerator to be tested are classified into another class, and refrigerators with a 40% similarity to the refrigerator to be tested are classified into another class. In actual application scenarios, the setting of the target class can be determined according to actual application needs. Preferably, the target class is the class with the closest similarity to the refrigerator to be tested.
[0046] S105 , amending the first environmental test standard according to the second environmental test standard to obtain a target environmental test standard, wherein the target environmental test standard includes a characteristic parameter threshold range that enables the refrigerator device to pass the environmental test.
[0047] In this embodiment, the target environmental test standard is obtained by integrating the first environmental test standard and the second environmental test standard, wherein the second environmental test standard is an environmental test standard that is closer to the sample data of multiple refrigerators of the refrigerator to be tested. Therefore, by correcting the first environmental test standard according to the second environmental test standard, an environmental test standard for more accurately identifying qualified refrigerators can be obtained.
[0048] In one embodiment, the number of features included in the first environmental test standard is greater than or equal to the number of feature data included in the second environmental test standard; and the first environmental test standard is modified according to the second environmental test standard to obtain the target environmental test standard, including: Modifying the characteristic parameter threshold range corresponding to the second characteristic in the first environmental test standard according to the characteristic parameter threshold range corresponding to the first characteristic in the second environmental test standard; wherein the first characteristic and the second characteristic are the same characteristic; The target environmental test standard is obtained according to the corrected characteristic parameter threshold range and the characteristic parameter threshold range in the first environmental test standard that has not been corrected.
[0049] In this embodiment, during the acquisition process of the second environmental test standard, the number of features may be smaller than the number of features in the first environmental test standard. In this case, correction needs to be made based on the same features during the correction process to avoid incorrect setting of the environmental test standard.
[0050] In the embodiment, since the number of the modified feature parameter threshold ranges is less than or equal to the number of the feature parameter threshold ranges in the first environmental test standard, when the target environmental test standard is obtained, the modified feature parameter threshold ranges and the feature parameter threshold ranges in the first environmental test standard that have not been modified are combined to form a complete evaluation standard for each feature of the refrigerator, i.e., the feature parameter threshold range.
[0051] Based on the above steps, a more accurate target environmental test standard can be obtained, thereby improving the accuracy of environmental testing.
[0052] S106, performing environmental testing on the refrigerator device to be tested according to the target environmental test standard.
[0053] In the embodiment, the environmental testing includes various tests, such as normal temperature running-in testing, high-low temperature testing, performance testing, production link testing, incoming size testing, etc. The embodiment does not limit the specific testing steps of the environmental testing, and the environmental testing can be configured according to the needs of the actual application scene.
[0054] In one of the embodiments, when each parameter of the refrigerator device to be tested meets the target environmental test standard during the environmental testing, the refrigerator device to be tested is determined to be a qualified refrigerator device. When any parameter of the refrigerator device to be tested does not meet the target environmental test standard during the environmental testing, the refrigerator device to be tested is determined to be an unqualified refrigerator device.
[0055] To sum up, the embodiment provides a method of analyzing and calculating incoming data, refrigerator production data, and test experimental data based on an unsupervised learning algorithm, calculating production and test data determination standards, and dividing refrigerators by the unsupervised learning algorithm to develop standards, which can more effectively screen refrigerators and reduce the situation of incorrect screening and missed screening of unqualified refrigerators caused by human-set standards.
[0056] In one of the embodiments, as shown in Figure 2 the refrigerator environmental testing method further includes: S201, respectively performing life testing on the qualified refrigerator device and the unqualified refrigerator device to obtain a first life test result corresponding to the qualified refrigerator device and a second life test result corresponding to the unqualified refrigerator device.
[0057] S202, in the case where the first life test result is greater than the second life test result, continuing to perform environmental testing on the refrigerator device to be tested using the current target environmental test standard.
[0058] S203, in a case where the first life test result is less than the second life test result, increasing the data amount of the refrigeration machine sample data, and reacquiring the target environment test standard, performing environment test on the refrigeration machine equipment to be tested according to the target environment test standard until the first life test result is greater than the second life test result.
[0059] In the embodiment, the validity of the target environment test standard can also be verified by performing life test on the qualified refrigeration machine equipment and the unqualified refrigeration machine equipment subjected to the environment test respectively.
[0060] In the embodiment, the increasing of the data amount of the refrigeration machine sample data in step S203 can be adding the sample data of the refrigeration machine equipment subjected to the environment test based on the previous target environment test standard to the original refrigeration machine sample data in step S101. Alternatively, the refrigeration machine sample data can be randomly added to the original refrigeration machine sample data in step S101. The specific steps of increasing the data amount can be operated according to the needs of actual application scenarios.
[0061] To sum up, the embodiment provides a refrigeration machine environment test method, which automatically formulates a target environment test standard, revises the target environment test standard based on an unsupervised learning algorithm, judges subsequent refrigeration machine equipment under the target environment test standard, classifies machines through performance data, and reversely verifies the rationality of the standard formulation through refrigeration machine life, so as to effectively reduce the probability of refrigeration machine misjudgment and greatly save the repair cost of the refrigeration machine. It should be understood that, although each step in the flowchart involved in the above embodiments is displayed in sequence according to the arrow, these steps are not necessarily executed in sequence according to the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other sequences. Moreover, at least part of the steps in the flowchart involved in the above embodiments can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or steps or stages in other steps.
[0062] Based on the same inventive concept, the embodiment of the present application also provides a refrigeration machine environment test device for implementing the refrigeration machine environment test method described above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more refrigeration machine environment test device embodiments provided below can refer to the limitations of the refrigeration machine environment test method described above, and will not be repeated here.
[0063] In one embodiment, Figure 3 As shown, a refrigerator environment testing device 300 is provided, comprising: an acquisition module 310, a pre-processing module 320, a calculation module 330, a clustering module 340, a correction module 350 and a testing module 360, wherein: An acquisition module 310 is configured to acquire refrigerator sample data of a plurality of refrigerator devices, wherein the refrigerator sample data includes incoming material data, production data, and historical experimental data, wherein the historical experimental data includes characteristic parameters of a normal temperature running-in test, characteristic parameters of a high and low temperature test, and characteristic parameters of a performance test; A preprocessing module 320 is used to perform data preprocessing on the refrigerator sample data to obtain optimized sample data, wherein the data preprocessing includes outlier detection processing, missing value filling processing and data normalization processing; A calculation module 330 is configured to calculate statistical parameters of each feature in the optimized sample data and determine a first environmental test standard based on the statistical parameters; A clustering module 340 is configured to perform unsupervised clustering of the refrigerator sample data based on a DBSCAN clustering algorithm to obtain clustering results, and determine a second environmental test standard based on the clustering results; A correction module 350 is configured to correct the first environmental test standard according to the second environmental test standard to obtain a target environmental test standard, wherein the target environmental test standard includes a characteristic parameter threshold range that enables the refrigerator device to pass the environmental test; The testing module 360 is used to perform an environmental test on the refrigerator device to be tested according to a target environmental test standard.
[0064] In one embodiment, the preprocessing module 320 is specifically used to detect outliers on the refrigerator sample data based on the isolation forest algorithm, and eliminate the detected outliers as missing values; fill the missing values according to the k-nearest neighbor interpolation algorithm; and standardize the refrigerator sample data that has completed the missing value filling process to obtain optimized sample data.
[0065] In one embodiment, the calculation module 330 is specifically used to determine the first threshold range corresponding to each feature based on the maximum and minimum values of each feature in the optimized sample data, wherein the boundary points of the first threshold range are the minimum and maximum values of the feature; and the first threshold ranges corresponding to all features in the integrated refrigerator sample data are used to obtain the first environmental test standard.
[0066] In one embodiment, the clustering module 340 is specifically configured to determine a target class corresponding to the target class of refrigerator equipment; calculate a second threshold range of features corresponding to the refrigerator equipment in the target class; and obtain a second environmental test standard by combining the second threshold range.
[0067] In one of the embodiments, the correction module 350 is specifically configured to correct a threshold range of a feature parameter corresponding to a second feature in the first environmental test standard according to a threshold range of the feature parameter corresponding to the first feature in the second environmental test standard; wherein the first feature and the second feature are the same feature; and obtain the target environmental test standard according to the corrected threshold range of the feature parameter and a threshold range of the feature parameter in the first environmental test standard which is not subjected to the correction.
[0068] In one of the embodiments, the test module 360 is specifically configured to determine that the to-be-tested refrigeration machine device is a qualified refrigeration machine device in a case where each parameter of the to-be-tested refrigeration machine device meets the target environmental test standard during the environmental test; and determine that the to-be-tested refrigeration machine device is an unqualified refrigeration machine device in a case where any parameter of the to-be-tested refrigeration machine device does not meet the target environmental test standard during the environmental test.
[0069] In one of the embodiments, the test module 360 is further configured to perform life tests on the qualified refrigeration machine device and the unqualified refrigeration machine device respectively to obtain a first life test result corresponding to the qualified refrigeration machine device and a second life test result corresponding to the unqualified refrigeration machine device; continue to perform the environmental test on the to-be-tested refrigeration machine device using the current target environmental test standard in a case where the first life test result is greater than the second life test result; and increase the data amount of the refrigeration machine sample data and reacquire the target environmental test standard in a case where the first life test result is less than the second life test result, and perform the environmental test on the to-be-tested refrigeration machine device according to the target environmental test standard until the first life test result is greater than the second life test result.
[0070] To sum up, the embodiment provides a refrigeration machine environmental test device, which automatically formulates a target environmental test standard, revises the target environmental test standard based on an unsupervised learning algorithm, determines subsequent refrigeration machine devices under the target environmental test standard, classifies machines through performance data, and reversely verifies rationality of standard formulation through refrigeration machine life, so as to effectively reduce a probability of refrigeration machine misjudgment and greatly save refrigeration machine repair costs.
[0071] The above refrigeration machine environmental test device can be implemented by software, hardware, or a combination thereof. The above modules can be embedded in or independent of a processor in a computer device in a hardware form, or stored in a memory in a computer device in a software form, so as to be called and executed by a processor to perform operations corresponding to the above modules.
[0072] In one of the embodiments, a computer device is provided, which can be a terminal, and an internal structure diagram of the computer device can be as shown in Figure 4The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus. The communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for running the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is configured to exchange information between the processor and external devices. The communication interface of the computer device is configured to perform wired or wireless communication with external terminals. The wireless communication can be achieved through WIFI, mobile cellular network, NFC (Near Field Communication) or other technologies. The computer program is executed by the processor to implement a refrigeration machine environment test method. The display unit of the computer device is configured to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or can be a key, a trackball or a touchpad arranged on the shell of the computer device, or can be an external keyboard, a touchpad or a mouse, etc.
[0073] Those skilled in the art can understand that Figure 4 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0074] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps in the above method embodiments.
[0075] In one embodiment, a computer readable storage medium is provided, storing a computer program, and the computer program is executed by a processor to implement the steps in the above method embodiments.
[0076] In one embodiment, a computer program product is provided, including a computer program, and the computer program is executed by a processor to implement the steps in the above method embodiments.
[0077] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.
[0078] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.
[0079] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.
Claims
1. A refrigerator environmental testing method, characterized in that: The method comprises: Acquire refrigerator sample data of a plurality of refrigerator devices, wherein the refrigerator sample data includes incoming material data, production data, and historical experimental data, and the historical experimental data includes characteristic parameters of a normal temperature running-in test, characteristic parameters of a high and low temperature test, and characteristic parameters of a performance test; Performing data preprocessing on the refrigerator sample data to obtain optimized sample data, wherein the data preprocessing includes outlier detection processing, missing value filling processing and data standardization processing; Calculating statistical parameters of each feature in the optimized sample data, and determining a first environmental test standard based on the statistical parameters; Performing unsupervised clustering on the refrigerator sample data based on the DBSCAN clustering algorithm to obtain a clustering result, and determining a second environmental test standard according to the clustering result; Modifying the first environmental test standard according to the second environmental test standard to obtain a target environmental test standard, wherein the target environmental test standard includes a characteristic parameter threshold range for the refrigerator device to pass the environmental test; An environmental test is performed on the refrigerator equipment to be tested according to the target environmental test standard.
2. The method according to claim 1, characterized in that The characteristic parameters of the normal temperature running-in test include the normal temperature running-in test current, the normal temperature running-in test speed and the normal temperature running-in test coke temperature; the characteristic parameters of the high and low temperature test include the high and low temperature test current, the high and low temperature test frequency reduction time, the high and low temperature test speed and the high and low temperature test coke temperature; The performance test characteristic parameters include performance test current, performance test speed, performance test coke temperature, performance test temperature recovery time and performance test frequency reduction time; The data preprocessing of the refrigerator sample data includes: performing standardization processing on the refrigerator sample data to obtain the optimized sample data; Performing outlier detection on the optimized sample data based on the isolation forest algorithm, and removing the detected outliers as missing values; The missing values are filled in according to the k-nearest neighbor interpolation algorithm.
3. The method according to claim 1, characterized in that The statistical parameters include a minimum value and a maximum value of a characteristic; and determining the first environmental test standard according to the statistical parameters includes: Determine a first threshold range corresponding to each feature according to the maximum value and the minimum value of each feature in the optimized sample data, wherein the boundary points of the first threshold range are the minimum value and the maximum value of the feature; The first environmental test standard is obtained by integrating the first threshold ranges corresponding to all features in the refrigerator sample data.
4. The method according to claim 1, wherein The clustering result includes a plurality of classes, wherein each class corresponds to a data set of refrigerator equipment of a certain category; and determining the second environmental test standard according to the clustering result includes: Determine the target class corresponding to the target category of refrigeration equipment; Calculating a second threshold range of features corresponding to refrigerator devices in the target class; The second environmental test standard is obtained by integrating the second threshold range.
5. The method according to claim 1, wherein The number of features included in the first environmental test standard is greater than or equal to the number of feature data included in the second environmental test standard; and the modifying the first environmental test standard according to the second environmental test standard to obtain the target environmental test standard includes: Modifying the characteristic parameter threshold range corresponding to the second characteristic in the first environmental testing standard according to the characteristic parameter threshold range corresponding to the first characteristic in the second environmental testing standard; wherein the first characteristic and the second characteristic are the same characteristic; The target environmental test standard is obtained according to the corrected characteristic parameter threshold range and the characteristic parameter threshold range in the first environmental test standard that has not been corrected.
6. The method according to claim 1, wherein The environmental test of the refrigerator device to be tested according to the target environmental test standard includes: If all parameters of the refrigerator device to be tested meet the target environmental test standards during the environmental test, determining that the refrigerator device to be tested is a qualified refrigerator device; If any parameter of the refrigerator device to be tested does not meet the target environmental test standard during the environmental test process, the refrigerator device to be tested is determined to be an unqualified refrigerator device.
7. The method according to claim 6, characterized in that The method further comprises: Performing life tests on the qualified refrigerator equipment and the unqualified refrigerator equipment respectively, to obtain a first life test result corresponding to the qualified refrigerator equipment and a second life test result corresponding to the unqualified refrigerator equipment; If the first life test result is greater than the second life test result, continuing to perform environmental testing on the refrigerator device to be tested using the current target environmental testing standard; When the first life test result is smaller than the second life test result, the data volume of the refrigerator sample data is increased, and the target environmental test standard is reacquired, and the environmental test is performed on the refrigerator equipment to be tested according to the target environmental test standard until the first life test result is larger than the second life test result.
8. A refrigerator environmental testing device, characterized in that: The device comprises: An acquisition module is used to acquire refrigerator sample data of multiple refrigerator devices, wherein the refrigerator sample data includes incoming material data, production data, and historical experimental data, and the historical experimental data includes normal temperature running-in test characteristic parameters, high and low temperature test characteristic parameters, and performance test characteristic parameters; A preprocessing module, configured to perform data preprocessing on the refrigerator sample data to obtain optimized sample data, wherein the data preprocessing includes outlier detection processing, missing value filling processing, and data standardization processing; a calculation module, configured to calculate statistical parameters of each feature in the optimized sample data, and determine a first environmental test standard based on the statistical parameters; A clustering module, configured to perform unsupervised clustering of the refrigerator sample data based on a DBSCAN clustering algorithm to obtain clustering results, and determine a second environmental test standard based on the clustering results; a correction module, configured to correct the first environmental test standard according to the second environmental test standard to obtain a target environmental test standard, wherein the target environmental test standard includes a characteristic parameter threshold range for the refrigerator device to pass the environmental test; The test module is used to perform environmental testing on the refrigerator device to be tested according to the target environmental testing standard.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the refrigerator environment testing method according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the refrigerator environment testing method according to any one of claims 1 to 7 are implemented.