Search

CN-115424106-B - Trolley detection method, device, electronic equipment and storage medium

CN115424106BCN 115424106 BCN115424106 BCN 115424106BCN-115424106-B

Abstract

The invention relates to the technical field of manufacturing industry and provides a trolley detection method, a trolley detection device, electronic equipment and a storage medium, wherein the trolley detection method comprises the steps of obtaining original characteristic information of a trolley to be detected, wherein the original characteristic information comprises parameter information collected by the trolley to be detected in the process of detecting a target product; determining target feature information based on the original feature information, wherein the target feature information comprises the residual feature information after the original feature information is subjected to exception processing, and obtaining a target detection result aiming at the trolley to be detected based on the target feature information and a preset detection model. The method can realize the purpose of timely and intelligently detecting whether the trolley is abnormal or not, and is time-saving, labor-saving, efficient and accurate.

Inventors

  • CHEN PENGFEI
  • CHUAN JIANG
  • LIN GANG
  • YU PING

Assignees

  • 美的集团股份有限公司

Dates

Publication Date
20260505
Application Date
20220906

Claims (11)

  1. 1. A trolley detection method, characterized by comprising: the method comprises the steps of obtaining original characteristic information of a trolley to be detected, wherein the original characteristic information comprises parameter information collected by the trolley to be detected in the process of detecting a target product, and the original characteristic information comprises preset equipment part codes, id of the target product, target code information of the trolley to be detected and dynamic parameters in the process of detecting, wherein the dynamic parameters comprise at least one of temperature, current, voltage and power; determining target feature information based on the original feature information, wherein the target feature information comprises the residual feature information after the original feature information is subjected to exception processing; obtaining a target detection result aiming at the trolley to be detected based on the target characteristic information and a preset detection model; The determining target feature information based on the original feature information comprises the following steps: Performing row-column transfer operation on column data of a column field where the parameter information is located in the original characteristic information, and determining characteristic information to be processed of the trolley to be detected; performing exception processing on the feature information to be processed based on a preset exception processing rule; Determining the target characteristic information based on the characteristic information obtained by the exception processing; the preset exception handling rule comprises removing column data with column field deletion rate exceeding a column deletion rate threshold, filling row data with row field deletion rate lower than a row deletion rate threshold, removing column data which does not meet a preset distribution rule, removing column data which does not meet preset temperature correlation, removing column data which does not meet a preset temperature range and removing column data which does not meet preset power correlation according to the feature information to be handled.
  2. 2. The dolly detection method according to claim 1, wherein the performing exception processing on the feature information to be processed further comprises: acquiring the target number of target products belonging to the same preset equipment piece code, wherein the preset equipment piece code is the hardware parameter model of the same target product; and determining that the target quantity is smaller than a preset quantity threshold value, and eliminating data where preset equipment piece codes corresponding to the target quantity are located in the feature information to be processed.
  3. 3. The dolly detection method according to claim 1, wherein the determining the target feature information based on feature information obtained by exception processing comprises: performing characteristic amplification processing on the characteristic information obtained by the exception processing, and determining a plurality of characteristic information after the amplification processing; And screening the plurality of feature information based on the correlation of the preset feature information and the quantity of the preset feature information, and determining the target feature information.
  4. 4. The method for detecting a trolley according to claim 1, wherein the preset detection models include different preset detection sub-models, and the obtaining the target detection result for the trolley to be detected based on the target feature information and the preset detection models includes: inputting the target characteristic information into the preset detection model to obtain preset number of detection results of the trolley to be detected, which are output by the preset detection model, under different preset equipment piece codes and different preset detection sub-models; And obtaining a target detection result aiming at the trolley to be detected based on the abnormal detection result in the preset number of detection results.
  5. 5. The dolly detection method according to claim 4, wherein the obtaining the target detection result for the dolly to be detected based on the abnormality detection result among the preset number of detection results comprises: Determining the duty ratio of abnormal detection results in the preset number of detection results; determining that the duty ratio exceeds a first preset duty ratio, and acquiring a target detection result of the trolley to be detected as an abnormal trolley; determining that the duty ratio is between a second preset duty ratio and the first preset duty ratio, and acquiring a target detection result of the trolley to be detected as a risk trolley; and determining that the duty ratio is lower than the second preset duty ratio, and acquiring a target detection result of the trolley to be detected as a normal trolley.
  6. 6. The dolly detection method according to claim 5, wherein after the obtaining of the target detection result that the dolly to be detected is a risk dolly, the method further comprises: Acquiring target coding information of the risk trolley; And sending early warning information to the user terminal based on the target coding information, wherein the early warning information is used for reminding the user terminal of carrying out field evaluation on the risk trolley by corresponding rechecking personnel.
  7. 7. The dolly detection method according to any one of claims 1 to 6, wherein the training method of the preset detection model comprises: Acquiring a plurality of different initial detection sub-models for carrying out anomaly detection on the trolley to be detected; Training each initial detection sub-model for a preset number of times based on the target characteristic information, and determining a plurality of intermediate detection results of a plurality of intermediate detection sub-models after each training; Transmitting the plurality of intermediate detection results to a user terminal, and receiving a rechecking result for the plurality of intermediate detection results, which is fed back by the user terminal; And determining the preset detection sub-model and the preset detection model corresponding to the preset detection sub-model based on the rechecking result and the intermediate detection sub-model after updating of each model parameter.
  8. 8. A dolly detection apparatus, characterized by comprising: The device comprises an acquisition module, a detection module and a detection module, wherein the acquisition module is used for acquiring original characteristic information of a trolley to be detected, the original characteristic information comprises parameter information collected by the trolley to be detected in the process of detecting a target product, and the original characteristic information comprises preset equipment part codes, id of the target product, target code information of the trolley to be detected and dynamic parameters in the process of detecting, wherein the dynamic parameters comprise at least one of temperature, current, voltage and power; The determining module is used for determining target feature information based on the original feature information, wherein the target feature information comprises the residual feature information after the original feature information is subjected to exception processing; The detection module is used for obtaining a target detection result aiming at the trolley to be detected based on the target characteristic information and a preset detection model; The determining module is further configured to perform a row-column transfer operation on column data of a column field where the parameter information is located in the original feature information, determine feature information to be processed of the trolley to be detected, perform exception processing on the feature information to be processed based on a preset exception processing rule, and determine the target feature information based on feature information obtained by the exception processing, wherein the preset exception processing rule includes, for the feature information to be processed, eliminating column data with a column field deletion rate exceeding a column deletion rate threshold, filling column data with a column field deletion rate lower than a column deletion rate threshold, eliminating column data not meeting a preset distribution rule, eliminating column data not meeting a preset temperature correlation, eliminating column data not meeting a preset temperature range, and eliminating column data not meeting a preset power correlation.
  9. 9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the trolley detection method of any one of claims 1 to 7 when the program is executed by the processor.
  10. 10. A non-transitory computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when executed by a processor, implements the trolley detection method according to any one of claims 1 to 7.
  11. 11. A computer program product comprising a computer program, characterized in that the computer program, when executed by a processor, implements the trolley detection method according to any one of claims 1 to 7.

Description

Trolley detection method, device, electronic equipment and storage medium Technical Field The present invention relates to the field of manufacturing technologies, and in particular, to a method and apparatus for detecting a trolley, an electronic device, and a storage medium. Background In the production process of air conditioner, the assembly line terminal has the operation room, is provided with the platform truck that the inspection air conditioner had the problem in the operation room to the platform truck constantly works in the air conditioner production process, but receives influence such as environment, equipment loss, and the platform truck inspection air conditioner appears the great condition of deviation easily. Therefore, it is important to detect whether the trolley is abnormal. In the related art, in a detection method for a trolley, generally, a worker installs 1 normal air conditioner on a plurality of trolleys respectively, manually collects parameters such as power and pressure in the process of checking the air conditioner by each trolley, calculates average values of corresponding parameters respectively, and finally determines that the trolley with larger deviation degree of the average value compared with a preset average value is an abnormal trolley. However, when the trolley is checked by a worker on site, the air conditioner is required to be manually installed first, data is manually collected in the running process after the installation, and then the air conditioner is manually removed after the running is finished, so that the whole detection process is too dependent on human factors, time and labor are wasted, and the efficiency of detecting the trolley is low and the accuracy is not high. Disclosure of Invention The present invention is directed to solving at least one of the technical problems existing in the related art. Therefore, the invention provides the trolley detection method, which achieves the purpose of timely and intelligently detecting whether the trolley is abnormal or not by means of automatic information acquisition, abnormal processing and model detection, and is time-saving, labor-saving, efficient and accurate. The invention further provides a trolley detection device. The invention further provides electronic equipment. The invention also proposes a non-transitory computer readable storage medium. The invention also proposes a computer program product. The trolley detection method according to the embodiment of the first aspect of the invention comprises the following steps: Acquiring original characteristic information of a trolley to be detected, wherein the original characteristic information comprises parameter information collected by the trolley to be detected in the process of detecting a target product; determining target feature information based on the original feature information, wherein the target feature information comprises the residual feature information after the original feature information is subjected to exception processing; And obtaining a target detection result aiming at the trolley to be detected based on the target characteristic information and a preset detection model. According to the trolley detection method, the original characteristic information of the trolley to be detected is firstly obtained, and the original characteristic information comprises the parameter information collected by the trolley to be detected in the process of detecting the target product, so that the target characteristic information is determined from the original characteristic information in an abnormal processing mode of the original characteristic information, and then the target detection result aiming at the trolley to be detected is obtained further based on the target characteristic information and a preset detection model. According to one embodiment of the present invention, the determining target feature information based on the original feature information includes: Performing row-column transfer operation on column data of a column field where the parameter information is located in the original characteristic information, and determining characteristic information to be processed of the trolley to be detected; performing exception processing on the feature information to be processed based on a preset exception processing rule; Determining the target characteristic information based on the characteristic information obtained by the exception processing; the preset exception handling rule comprises removing column data with column field deletion rate exceeding a column deletion rate threshold, filling row data with row field deletion rate lower than a row deletion rate threshold, removing column data which does not meet a preset distribution rule, removing column data which does not meet preset temperature correlation, removing column data which does not meet a preset temperature range and removing column data which does not meet pr