CN-121052812-B - Production line equipment health prediction and maintenance optimization method based on Hongmon system

Abstract

The invention relates to the technical field of data processing, in particular to a production line equipment health prediction and maintenance optimization method based on a hong and Monte-go system. According to the invention, the change relation between key operation parameters of the production line equipment is collected and comprehensively analyzed in real time, the judgment threshold value is dynamically adjusted or a targeted maintenance management strategy is generated according to different abnormal types and time distribution characteristics of the abnormal types, and the acceleration value, the temperature value, the current value, the rotation speed value, the diameter value, the surface roughness, the response delay value and the voltage value are judged step by step and are comprehensively synthesized into the health prediction index, so that the prediction result is closer to the real operation state of the equipment, and the problems of delay of the production line maintenance decision and low operation and maintenance efficiency caused by single monitoring index and static maintenance suggestion are effectively solved.

Inventors

• GAO LIZHEN

Assignees

• 厦门工学院

Dates

Publication Date

20260508

Application Date

20251105

Claims (6)

1. 1. A method for predicting and maintaining and optimizing the health of production line equipment based on a hong Monte-go system is characterized by comprising the following steps: Acquiring acceleration values and temperature values of spindles of all station equipment in the production line equipment cluster, current values and rotation speed values of a driving unit, diameter values and surface roughness values of workpieces and response delay values and voltage values of a control component in real time according to the hong-Meng distributed bus; judging that an abnormal event occurs according to the acceleration value, the temperature value and a preset abnormal judgment threshold value to obtain an abnormal judgment result; determining the degree of abnormality of the abnormal event according to the current value and the rotation speed value based on the abnormality determination result to obtain a first degree or a second degree; The method comprises the steps of carrying out similarity analysis on a normalization value of current and rotating speed, quantifying the running state of equipment into a degree judgment value, accurately distinguishing different abnormal degrees, reflecting that the relevance between the current and the rotating speed is weakened when the degree judgment value is lower than a preset threshold value, and indicating that the equipment has sudden or unstable abnormality, namely a first degree; Determining an anomaly type of the anomaly event based on the first degree according to the diameter value and the surface roughness value to obtain a first type; Determining an anomaly type of the anomaly event according to the response delay value and the voltage value based on the second degree to obtain a second type or a third type; Correcting the second type or the third type to the first type according to the time distribution characteristics of the first degree and the second degree in a preset correction duration; determining a health prediction index according to the acceleration value and the temperature value corresponding to the first type, the second type and the third type in a preset prediction duration; Adjusting the preset abnormality judgment threshold according to the health prediction index and all the abnormality types, or generating a maintenance management strategy; determining an anomaly type of the anomaly event based on the diameter value and the surface roughness value to obtain a first type of anomaly event comprises: respectively calculating the average value and the variance of all the diameter values in the preset detection time length to obtain a diameter average value and a diameter variance; Calculating the difference between the diameter average value and the diameter variance to obtain a diameter deviation; respectively calculating the average value and variance of all the surface roughness in the preset detection time period to obtain a roughness average value and roughness variance; Calculating the difference between the rough average value and the rough variance to obtain rough deviation; Determining the anomaly type of the anomaly event according to the diameter deviation and the roughness deviation to obtain the first type; determining the anomaly type of the anomaly event from the diameter deviation and the roughness deviation to obtain the first type of anomaly event comprises: When the diameter deviation is larger than a preset diameter deviation threshold and the roughness deviation is larger than a preset roughness deviation threshold, judging that the abnormal type is geometric abrasion so as to obtain the first type; determining an anomaly type of the anomaly event based on the response delay value and the voltage value to obtain a second type or a third type of process includes: Calculating the average value of all the response delay values in the preset detection duration to obtain a delay average value; calculating the average value of all the voltage values in the preset detection duration to obtain a voltage average value; when the delay average value is larger than a preset delay threshold value and the voltage average value is smaller than a preset voltage threshold value, judging that the abnormal type is a control failure so as to obtain the second type; When the delay average value is larger than the preset delay threshold value and the voltage average value is larger than or equal to the preset voltage threshold value, judging that the abnormal type is a power supply fluctuation type so as to obtain the third type; the process of correcting the second type or the third type to the first type according to the time distribution characteristics of the first degree and the second degree in the preset correction duration comprises the following steps: Marking all time stamps corresponding to the first degree and the second degree obtained in the preset correction time length to obtain a first time sequence and a second time sequence; Respectively calculating time differences of adjacent time stamps in the first time sequence to obtain a first time interval sequence; respectively calculating time differences of adjacent time stamps in the second time sequence to obtain a second time interval sequence; respectively calculating the mean value and the variance of the first time interval sequence to obtain a first interval mean value and a first interval variance; Respectively calculating the mean value and the variance of the second time interval sequence to obtain a second interval mean value and a second interval variance; when the second interval variance is larger than a preset interval variance threshold, the second interval mean is smaller than the first interval mean, and the difference between the first interval mean and the second interval mean is larger than a preset mean difference threshold, determining that a corresponding time period in the second time sequence is an irregular distribution time period; The second type or the third type in the irregular distribution period is determined as the first type to be corrected as the first type.
2. 2. The method of optimizing health prediction and maintenance of production line equipment based on a hong-mo system according to claim 1, wherein determining the degree of abnormality of the abnormal event based on the current value and the rotational speed value to obtain the first degree or the second degree comprises: performing Z-score calculation on all the current values in the preset degree determination duration to obtain a plurality of normalization currents; performing Z-score calculation on all the rotating speed values in the preset degree determination duration to obtain a plurality of return rotating speeds; calculating absolute values of cosine similarity of all the normalization currents and all the normalization rotational speeds to obtain a degree judgment value; And determining the degree of abnormality of the abnormal event according to the degree determination value to obtain the first degree or the second degree.
3. 3. A method of optimizing health prediction and maintenance of production line equipment based on a hong-mo system according to claim 2, wherein determining the degree of abnormality of the abnormal event according to the degree determination value to obtain the first degree or the second degree comprises: when the degree judgment value is smaller than a preset degree judgment threshold value, judging that the association deviation occurs so as to determine the degree of abnormality of the abnormal event as the first degree; And when the degree judgment value is larger than or equal to the preset degree judgment threshold value, judging that association and maintenance occur so as to determine the degree of abnormality of the abnormal event to be the second degree.
4. 4. A method for optimizing health prediction and maintenance of production line equipment based on a hong Mongolian system as recited in claim 3, wherein determining a health prediction index according to the acceleration values and the temperature values corresponding to the first type, the second type, and the third type within the preset prediction period comprises: Respectively calculating the average value of all acceleration values and the average value of temperature values corresponding to the first type in the preset prediction time period to obtain a first acceleration average value and a first temperature average value; respectively calculating the average value of all the acceleration values and the average value of the temperature values corresponding to the second type in the preset prediction time period to obtain a second acceleration average value and a second temperature average value; Respectively calculating the average value of the acceleration values and the average value of the temperature values corresponding to all the third types in the preset prediction time period to obtain a third acceleration average value and a third temperature average value; and determining the health prediction index according to the first acceleration average value, the first temperature average value, the second acceleration average value, the second temperature average value, the third acceleration average value and the third temperature average value.
5. 5. The method of claim 4, wherein the process of adjusting the preset anomaly determination threshold according to the health prediction index and all anomaly types or generating a maintenance management strategy comprises: When the health prediction index is larger than a preset prediction index threshold, calculating the ratio of the number of the first type to the number of all the abnormal types to obtain a first duty ratio; calculating the ratio of the number of the second types to the number of all the abnormal types to obtain a second duty ratio; calculating the ratio of the number of the third types to the number of all the abnormal types to obtain a third duty ratio; when the first duty ratio, the second duty ratio and the third duty ratio are all larger than a preset duty ratio threshold, adjusting the preset abnormality judgment threshold according to the first duty ratio, the second duty ratio, the third duty ratio and the preset duty ratio threshold; and when any one or two of the first duty ratio, the second duty ratio and the third duty ratio are larger than the preset duty ratio threshold, generating the maintenance management strategy according to the corresponding abnormal type.
6. 6. The method for optimizing health prediction and maintenance of production line equipment based on a hong-mo system according to claim 5, wherein the process of determining occurrence of an abnormal event according to the acceleration value, the temperature value and a preset abnormality determination threshold value comprises: Recording the duration time that the acceleration value is larger than a preset acceleration threshold value for the first time and the temperature value is larger than a preset temperature threshold value for the first time, so as to obtain an abnormality judgment value; and when the abnormality judgment value is larger than the preset abnormality judgment threshold value, judging that the abnormality event occurs.

Description

Production line equipment health prediction and maintenance optimization method based on Hongmon system Technical Field The invention relates to the technical field of equipment maintenance, in particular to a production line equipment health prediction and maintenance optimization method based on a hong Monte system. Background With the continuous development of industrial automation and intelligent manufacturing, the running stability and reliability of production line equipment have become key factors affecting the production efficiency, running cost and market competitiveness of enterprises. In recent years, with the popularization of the distributed operating system technology, an industrial control and management architecture based on a hong and Monte-like system is gradually applied to the intelligent manufacturing field, and the distributed task scheduling and multi-node data coordination capability of the architecture provides a technical basis for realizing information intercommunication among devices and dynamic coordination among working procedures. Under the existing factory management mode, equipment maintenance generally faces two major problems, namely preventive maintenance based on a fixed period or a single parameter threshold value, lack of accurate insight on the real health state of equipment and easy to cause unreasonable maintenance resource allocation, and serious data island of a traditional equipment monitoring system, and incapability of carrying out collaborative analysis and intelligent prediction on multidimensional operation parameters, so that a production scheduling department is difficult to carry out scientific maintenance decision and production plan adjustment in advance, and the fluency and resource utilization rate of the whole production system are seriously affected. CN113592179A discloses a predictive maintenance method, a system and a storage medium, wherein the method comprises the steps of receiving configuration information of each target monitoring component in at least one target monitoring component by a user through a station management man-machine interaction interface, wherein the configuration information comprises a station, a component name, a data acquisition scheme and a protocol, acquired data characteristic variables, respectively acquiring data of at least one target monitoring component based on the configuration information, uniformly managing the acquired data and storing the acquired data in a first database, when the configuration information further comprises a fault alarm threshold value for a data characteristic variable and a fault code representing the fault information, monitoring data of a real-time acquired target monitoring component based on the fault alarm threshold value, and sending out a fault alarm and providing corresponding fault information according to the fault code when the data of one data characteristic variable reaches the corresponding alarm threshold value in a set time, or analyzing the data of the acquired data characteristic variable based on the self-adaptive threshold value identification and the fault code of one data characteristic variable, obtaining a safety data range of the data characteristic variable, determining the safety data range of the data characteristic variable based on the acquired data characteristic variable, sending out the fault alarm based on the fault alarm threshold value when the fault alarm threshold value reaches the fault alarm threshold value for the data characteristic variable in a set time, or the fault alarm threshold value is continuously monitored based on the fault alarm threshold value and the fault alarm is continuously set in the set to the fault condition data, and the fault alarm threshold value is continuously monitored based on the fault threshold value, the fault information comprises at least one or any combination of a fault name, fault description information and fault resolution suggestions, and the corresponding relation between the fault code and the fault information is provided for a user to learn and inquire through a code information man-machine interaction interface. Therefore, the predictive maintenance method has the following problems that the method only triggers an alarm when a single data characteristic variable continuously exceeds standard, the output fault solution advice is usually static and predefined, so that the maintenance decision lacks priority judgment basis, the threshold self-adaption is only limited to the adjustment of the statistical range of historical data, and the sensitivity of abnormality monitoring cannot be dynamically adjusted according to the evolution trend of an abnormality type and the health degradation rule of the whole equipment. Disclosure of Invention Therefore, the invention provides a production line equipment health prediction and maintenance optimization method based on a hong Mongolian system, which is used for s