CN117689270A - Method, system and storage medium for improving quality management of power equipment production process - Google Patents

Method, system and storage medium for improving quality management of power equipment production process Download PDF

Info

Publication number
CN117689270A
CN117689270A CN202410124616.3A CN202410124616A CN117689270A CN 117689270 A CN117689270 A CN 117689270A CN 202410124616 A CN202410124616 A CN 202410124616A CN 117689270 A CN117689270 A CN 117689270A
Authority
CN
China
Prior art keywords
quality detection
data
production
detection result
operation step
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202410124616.3A
Other languages
Chinese (zh)
Other versions
CN117689270B (en
Inventor
申亚会
赵洁
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shen Yahui
Original Assignee
Lingjun Liaoning Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Lingjun Liaoning Technology Co ltd filed Critical Lingjun Liaoning Technology Co ltd
Priority to CN202410124616.3A priority Critical patent/CN117689270B/en
Publication of CN117689270A publication Critical patent/CN117689270A/en
Application granted granted Critical
Publication of CN117689270B publication Critical patent/CN117689270B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06395—Quality analysis or management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
    • G06Q10/06375—Prediction of business process outcome or impact based on a proposed change
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/067—Enterprise or organisation modelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/04—Manufacturing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Educational Administration (AREA)
  • Physics & Mathematics (AREA)
  • Development Economics (AREA)
  • Quality & Reliability (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • Manufacturing & Machinery (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to the technical field of quality management, in particular to a method, a system and a storage medium for improving quality management in a production process of power equipment. The method comprises the steps of periodically obtaining production data in a first process of the power equipment, generating process control information according to a process execution process, obtaining an operation quality detection result of a j-th operation step based on a detection standard corresponding to the j-th operation step when the j-th operation step of the i-th process of the power equipment is completed, and storing the production data and the operation quality detection result into a storage unit; and constructing a prediction model by using the modeling unit, training the prediction model by using the production data and the operation quality detection result stored in the storage unit, predicting the operation quality detection result of the next period according to the prediction model and the production data of the next period, and adjusting the inspection standard corresponding to the j-th operation step of the i-th procedure. The invention has the beneficial effect of improving the qualification rate of the production of the power equipment.

Description

Method, system and storage medium for improving quality management of power equipment production process
Technical Field
The invention relates to the technical field of quality management, in particular to a method, a system and a storage medium for improving quality management in a production process of power equipment.
Background
The electric power equipment occupies an important role in daily life of people, and at present, the traditional quality management mode is insufficient to meet the production qualification rate of the electric power equipment in the actual production process.
In the prior art, for example, chinese patent No. CN108255142B, a method and apparatus for controlling production quality are provided, which comprise: acquiring and storing power production data and production environment data of a power equipment production system according to a preset time interval; responding to the selection operation of the object to be controlled, and sampling the stored power production data or the data corresponding to the object to be controlled in the production environment data according to a preset sampling strategy; carrying out statistic operation on the sampled data, and drawing a corresponding control chart according to the calculation result; detecting abnormal conditions of data corresponding to an object to be controlled based on the control diagram, and searching a control scheme corresponding to the abnormal conditions when the abnormal conditions are detected; and controlling the power equipment production system to adjust the power equipment production flow according to the control scheme so as to control the production quality of the power equipment. The method has the advantages of low resource consumption and high accuracy, can maintain the production quality of the power equipment in a better state, and improves the production efficiency of the power equipment. Also, for example, chinese patent CN117056688A, discloses a new material production data management system and method based on data analysis, which relates to the technical field of production data management, and includes: s1: real-time monitoring is carried out on the new material production process, and a related data set of automatic production is acquired through a sensor or machine vision; s2: analyzing the production related data set collected by real-time monitoring according to the production history data, and identifying and screening abnormal data in the production related data set; s3: confirming that the abnormal data generates relevant elements by analyzing the generation paths and relevant characteristics of the abnormal data in the production process based on the abnormal data in the production related data set; s4: according to the analysis result of the abnormal data in the production process, a tracing result of the abnormal production state of the new material is obtained, and the production of the new material is correspondingly managed based on the tracing result; the invention improves the monitoring capability of the production process of new materials with different specifications and avoids potential risks.
However, both patents only analyze the production process data, but cannot improve the qualification rate of the power equipment by starting from each production link in the production process, so the invention provides an improved quality management method for the production process of the power equipment to improve the production qualification rate of the power equipment.
Disclosure of Invention
In order to better solve the above problems, the present invention provides a method for improving quality management in a production process of an electrical device, comprising the steps of:
step S1: the method comprises the steps that a data acquisition unit periodically acquires production data in a first process of the power equipment, wherein the production data represent data corresponding to the first process, the first process comprises m working procedures, each working procedure comprises n operation steps, and the production data are divided into m production data segments corresponding to the m working procedures according to a production sequence;
step S2: the production management unit generates process control information including control information C of a j-th operation step in an i-th process according to the process execution process ij Production data S corresponding to the j-th operation step of the i-th process ij The sensor comprises sensing data detected by a plurality of sensors, wherein i is greater than or equal to 1 and less than or equal to m, and j is greater than or equal to 1 and less than or equal to n;
Step S3: upon completion of the j-th operation step of the i-th process of the electric power equipment, the first quality detection unit is used for detecting the operation state of the electric power equipment based on the inspection standard B corresponding to the j-th operation step ij Obtaining an operation quality detection result K of the j-th operation step ij Wherein the operation quality detection result K ij Quality detection results of the j-th operation step of the i-th process, and the production data S ij And the operation quality detection result K ij Saving in a storage unit;
step S4: constructing a predictive model by a modeling unit and using the stored data in the storage unitThe production data S ij And the operation quality detection result K ij Training the predictive model based on the predictive model and the production data S of the next cycle ij Predicting the operation quality detection result K of the next period ij And based on the predicted operation quality detection result K ij Adjusting the inspection standard B corresponding to the j-th operation step of the i-th procedure ij 。
As a preferred embodiment of the present invention, step S4 further includes step S5:
upon completion of the ith process of the power equipment, a second quality detection unit is used to detect the presence of a load on the basis of the inspection standard B of the ith process i Obtaining an ith process quality detection result T i And based on the i-th process quality detection result T i And all the operation quality detection results K ij And determining an abnormal position and adjusting the abnormal position.
As a preferred embodiment of the present invention, step S5 further includes step S6:
the data acquisition unit is used for collecting operation data of the power equipment when faults occur in real time, the analysis unit is used for analyzing the reasons for the faults based on the operation data, when the reasons for the faults are caused in the production process, the fault tracing unit is used for tracing the ith working procedure which causes the faults based on the reasons for the faults and the jth operation step corresponding to the ith working procedure, and the inspection standard B corresponding to the jth operation step of the ith working procedure is adjusted based on the jth operation step of the ith working procedure, the reasons for the faults, the times of occurrence of the faults and the operation time from the delivery of the power equipment to the occurrence of the faults ij Or adjusting the control information C of the jth operation step in the ith step ij 。
As a preferred technical scheme of the present invention, the step S3 includes the following steps:
step S31: based on the predicted quality detection result K of the j-th operation step of the i-th process ij And benchmark test criteria, determining said firstinspection Standard B of the jth operation step of the i procedure ij ；
Step S32: after the j-th operation step of the i-th process is completed, the first quality detection unit performs quality detection on the j-th operation step and acquires quality detection data D ij The quality detection data D ij And the inspection standard B of the j-th operation step ij Comparing, and obtaining a first comparison result, wherein when the first comparison result is smaller than or equal to a first threshold value, the operation quality detection result K ij Qualified, otherwise the operation quality detection result K ij Is unqualified;
step S33: the production data S ij And the operation quality detection result K ij And storing the data into the storage unit.
As a preferred embodiment of the present invention, the step S4 includes the following steps:
step S41: constructing the prediction model based on a random forest algorithm by the modeling unit and based on the production data S stored in the storage unit ij And the operation quality detection result K ij Training the prediction model;
step S42: the production data S of the next period to be acquired ij Inputting the prediction model, and predicting the operation quality detection result K of the next period ij ；
Step S43: in the predicted operation quality detection result K ij When the production data is qualified, the production data S ij Comparing the sensing data detected by each sensor with the standard reference data of each sensor to obtain a plurality of second comparison results, and reducing the inspection standard B of the jth operation step within a first set threshold range when the second comparison results are smaller than or equal to a second threshold ij The first quality detection unit is in accordance with the reduced inspection standard B ij Detecting the j-th operation step of the i-th procedure, otherwise, the first quality detection unit is in accordance with the inspection standard B of the j-th operation step ij For the ith stepThe j-th operation step of (2) is detected;
step S44: in the predicted operation quality detection result K ij If it is not qualified, the production data S ij Comparing the sensing data detected by each sensor with the standard reference data of each sensor to obtain a plurality of third comparison results, and improving the inspection standard B of the j-th operation step within a first set threshold range when at least one of the third comparison results is larger than or equal to a third threshold ij The first quality detection unit is in accordance with the improved inspection standard B ij Detecting the j-th operation step of the i-th procedure, otherwise, the first quality detection unit is in accordance with the inspection standard B of the j-th operation step ij And detecting the j-th operation step of the i-th procedure, wherein the third threshold value is smaller than the second threshold value.
As a preferred embodiment of the present invention, the step S5 includes the following steps:
step S51: detecting the ith process by the second quality detection unit and acquiring the ith process detection data D when all operation steps of the ith process are completed i The ith step detection data D i Detection Standard B with the ith procedure i Comparing to obtain a fourth comparison result, and when the fourth comparison result is smaller than or equal to a fourth threshold value, obtaining an i-th process quality detection result T i If not, the quality detection result T of the ith procedure is qualified i Disqualification;
step S52: at the quality test result T i If the operation quality detection result K is not qualified and corresponds to all the j-th operation steps in the i-th process ij If all are qualified, passing the quality detection result T of the ith working procedure i Determining an abnormality type, determining an abnormality position based on the abnormality type, and improving the control information precision of the operation step related to the abnormality in the ith process control information according to the abnormality position and the operation step related to the abnormality.
As a preferred embodiment of the present invention, the step S6 includes the following steps:
step S61: the data acquisition unit is used for collecting the operation data of the power equipment when the power equipment fails in real time, and the analysis unit is used for analyzing the reason of the failure based on the operation data;
step S62: when the cause of the fault is caused in the production process, tracing the ith working procedure causing the fault and the jth operation step corresponding to the ith working procedure through a fault tracing unit based on the cause of the fault;
step S63: when the running time from delivery to occurrence of the fault of the power equipment is greater than or equal to a preset duration, ignoring the fault; when the running time from delivery to occurrence of the fault of the power equipment is smaller than the preset time, and when the occurrence frequency of the fault is smaller than or equal to the preset frequency, the inspection standard B of the j-th operation step is improved within a second set threshold value range ij The method comprises the steps of carrying out a first treatment on the surface of the When the number of times of occurrence of the fault is greater than the preset number of times, the control information C corresponding to the jth operation step in the ith procedure control information is increased ij Precision;
the operation data comprise voltage, current, frequency, temperature and operation duration of the power equipment.
The invention also provides a system for improving the quality management of the production process of the power equipment, which comprises the following modules:
the data acquisition unit is used for periodically acquiring production data in a first process of the power equipment, wherein the production data represents data corresponding to the first process, the first process comprises m working procedures, each working procedure comprises n operation steps, and the production data is divided into m production data corresponding to the m working procedures according to a production sequence;
a production management unit for generating process control information including control information C of a j-th operation step in an i-th process according to a process execution process ij Production data S corresponding to the j-th operation step of the i-th process ij Comprising sensing data detected by a plurality of sensors, wherein i is greater thanEqual to 1 and less than or equal to m, j is equal to or greater than 1 and less than or equal to n;
a first quality detection unit configured to, upon completion of the j-th operation step of the i-th process of the electric power equipment, based on a verification criterion B corresponding to the j-th operation step ij Obtaining an operation quality detection result K of the j-th operation step ij Wherein the operation quality detection result K ij Quality detection results of the j-th operation step of the i-th process, and the production data S ij And the operation quality detection result K ij Saving in a storage unit;
a modeling unit for constructing a predictive model and using the production data S stored in the storage unit ij And the operation quality detection result K ij Training the predictive model based on the predictive model and the production data S of the next cycle ij Predicting the operation quality detection result K of the next period ij And based on the predicted operation quality detection result K ij Adjusting the inspection standard B corresponding to the j-th operation step of the i-th procedure ij 。
The present invention also provides a storage medium storing computer executable instructions which when executed by a processor implement the above-described power equipment production process quality management improvement method.
Compared with the prior art, the invention has the following beneficial effects:
1. according to the technical scheme, the data acquisition unit periodically acquires the production data in the first process of the power equipment, the continuity and the integrity of the acquired production data are ensured, the production data are divided into m production data corresponding to m working procedures according to the production sequence, and therefore classification and arrangement of the production data are realized, and a foundation is provided for subsequent quality analysis. In the first process of the power equipment, the production management unit generates process control information according to the process execution process, divides the ith process into a plurality of operation steps according to different operation actions, and defines control information C of the jth operation step in the ith process ij Therefore, by monitoring each operation step in real time, problems can be found in time and improved in a targeted manner. By analyzing the sensing data detected by the plurality of sensors corresponding to the j-th operation step of the i-th process, the quality condition of each process can be reflected more accurately, so that a basis is provided for optimizing the production process and improving the production qualification rate of the power equipment.
2. According to the technical scheme, when the j-th operation step of the i-th procedure of the power equipment is completed, the first quality detection unit is used for detecting the quality of the power equipment based on the inspection standard B corresponding to the j-th operation step ij Obtaining an operation quality detection result K of the j-th operation step ij And the production data S ij And the operation quality detection result K ij Saving in a storage unit; the method is convenient for subsequent traceability in analysis, and provides abundant data support for constructing the prediction model. Building a predictive model by a modeling unit and using the production data S stored in the storage unit ij And an operation quality detection result K ij And training a prediction model to realize the prediction of the quality detection result of the j-th operation step of the next period. Meanwhile, based on the predicted operation quality detection result K ij Adjusting the inspection standard B corresponding to the j-th operation step of the i-th procedure ij Dynamic adjustment of the inspection standard is realized. Through the mutual coordination among the schemes, powerful support is provided for quality management of the production process of the power equipment, so that the production qualification rate of the power equipment is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of the steps of a method for improving quality management in a power plant production process according to the present invention;
FIG. 2 is a block diagram of a system for improving quality management in a power plant production process according to the present invention;
FIG. 3 is an exemplary diagram of a power plant production process in accordance with the present invention;
FIG. 4 is a diagram of two-sided tolerance and coincidence of the center of distribution and the center of standardization in a second embodiment of the present invention;
FIG. 5 is a diagram illustrating a systematic error analysis according to a second embodiment of the present invention;
FIG. 6 is a threshold model in a second embodiment of the present invention;
FIG. 7 is a model diagram of an integrated learning process in a second embodiment of the present invention;
FIG. 8 is a diagram of a two-sided tolerance and misalignment of the center of distribution μ and the center of standardization M in a second embodiment of the present invention;
FIG. 9 is a normal distribution diagram of the mass characteristics in the second embodiment of the present invention;
FIG. 10 is a process analysis diagram of a production system according to a second embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
It will be understood that the terms "first," "second," and the like, as used herein, may be used to describe various elements, but these elements are not limited by these terms unless otherwise specified. These terms are only used to distinguish one element from another element. For example, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script, without departing from the scope of the present application.
The electric power equipment occupies an important role in daily life of people, and at present, the traditional quality management mode is insufficient to meet the production qualification rate of the electric power equipment in the actual production process.
Aiming at the technical problems, a method for improving the quality management of the production process of the power equipment shown in fig. 1 is provided, which comprises the following steps:
step S1: the data acquisition unit periodically acquires production data in a first process of the power equipment, the production data represents data corresponding to the first process, the first process comprises m working procedures, each working procedure comprises n operation steps, and the production data is divided into m production data segments corresponding to the m working procedures according to a production sequence;
in the first embodiment, in the conventional power equipment production data management manner, the acquisition of production data is often manual and scattered, and lacks of systematicness and continuity, and cannot effectively support quality management of the production process. According to the scheme, the data acquisition unit periodically acquires production data in the production process of the power equipment, so that continuity and integrity of acquiring the production data are ensured. Meanwhile, the production data are divided into m production data segments corresponding to m working procedures according to the production sequence, so that the production process of the power equipment is conveniently managed in the minimum unit, the classification and arrangement of the production data are realized, and a foundation is provided for subsequent quality analysis. Wherein the production data includes production equipment operation data, sensor data detected by the sensor, process parameters, etc., and the first process may be a production process.
Step S2: the production management unit generates process control information including control information C of a j-th operation step in the i-th process based on the process execution process ij Production data S corresponding to the j-th operation step of the i-th process ij The sensor comprises sensing data detected by a plurality of sensors, wherein i is greater than or equal to 1 and less than or equal to m, and j is greater than or equal to 1 and less than or equal to n;
specifically, as shown in fig. 3, the production of the electric power equipment is a complex process, involving a plurality of processes and operation steps, each process and operation step has its specific production requirements, so that in the production process of the electric power equipment, the production management unit generates process control information according to the process execution process, divides the ith process into a plurality of operation steps according to the operation actions, and defines control information C of the jth operation step in the ith process ij Therefore, by monitoring each operation step in real time, the problems can be found out in time and aimed atImproved in nature. Since the production data in the production process of the electric power equipment is composed of the sensing data detected by the plurality of sensors, the production data S corresponding to the jth operation step of the ith process ij Also comprises a plurality of sensor-detected sensing data, wherein the production data S corresponding to the jth operation step ij The sensing data detected by the plurality of sensors corresponding to the j-th operation step of the i-th process is also obtained from the sensing data detected by the plurality of sensors corresponding to the i-th process, the sensing data detected by the plurality of sensors are divided into m sensing data segments corresponding to m processes according to the production sequence, the sensing data detected by different sensors are different, and temperature data, pressure data and the like. By analyzing the sensing data detected by the plurality of sensors corresponding to the j-th operation step of the i-th process, the quality condition of each process can be reflected more accurately, so that a basis is provided for optimizing the production process and improving the production qualification rate of the power equipment.
Step S3: upon completion of the j-th operation step of the i-th process of the electrical equipment, the first quality detection unit is used for detecting the quality of the electrical equipment based on the inspection standard B corresponding to the j-th operation step ij Obtaining the operation quality detection result K of the j-th operation step ij Wherein the quality of operation detection result K ij Quality detection results of the j-th operation step of the i-th procedure, and the production data S ij And an operation quality detection result K ij Saving in a storage unit;
Specifically, in the production process of the power equipment, each operation step of each procedure obtains detection data of a jth operation step of the power equipment through a first quality detection unit, compares the detection data with a detection standard of the jth operation step, and obtains an operation quality detection result K according to a comparison result ij The quality problem can be found out easily, the production loss of the subsequent operation steps is reduced, and meanwhile, a reference basis is provided for the detection result of the subsequent predicted operation quality. Will produce data S ij And an operation quality detection result K ij Is stored in a storage unit, is convenient for subsequent traceability in analysis and also is used for constructing predictionsThe model provides rich data support.
Step S4: building a predictive model by a modeling unit and using the production data S stored in the storage unit ij And the operation quality detection result K ij Training a predictive model based on the predictive model and the production data S of the next cycle ij Predicting operation quality detection result K of next period ij And based on the predicted operation quality detection result K ij Adjusting the inspection standard B corresponding to the j-th operation step of the i-th procedure ij 。
Specifically, in the conventional production process of the electric power equipment, since each operation step causes a certain tolerance in the production process due to the production equipment or the problem of operation, it is necessary to fine-tune the inspection standard of the operation step in a certain range according to the prediction result of the operation step, thereby improving the production efficiency, and also improving the accuracy of the quality detection result of the operation step, and taking corresponding measures according to the quality detection result, thereby improving the production quality. The technical proposal constructs a prediction model by a modeling unit and uses the production data S stored in a storage unit ij And an operation quality detection result K ij And training a prediction model to realize the prediction of the quality detection result of the j-th operation step of the next period. Meanwhile, based on the predicted operation quality detection result K ij Adjusting the inspection standard B corresponding to the j-th operation step of the i-th procedure ij Dynamic adjustment of the inspection standard is realized. Through the mutual coordination among the schemes, powerful support is provided for quality management of the production process of the power equipment, so that the production qualification rate of the power equipment is improved.
Further, step S5 is further included after step S4:
when the ith procedure of the power equipment is completed, the second quality detection unit is used for detecting the standard B based on the ith procedure i Obtaining an ith process quality detection result T i And based on the i-th process quality detection result T i And the total operation quality detection result K ij And determining the abnormal position and adjusting the abnormal position.
In particular, implementationFor example, in the production process of the electric equipment, since one process includes a plurality of operation steps, when the quality detection result of each operation step is qualified and the quality detection result of the whole process is qualified, the production of the process can be determined to be qualified, but each operation step is qualified, since each operation step has a certain tolerance, when the tolerance between two or more operation steps is accumulated to a certain value, the quality detection result of the whole process can be possibly unqualified, so that by the technical scheme, the quality detection result T of the ith process is obtained i And the total operation quality detection result K ij The abnormal position is determined and adjusted, so that the quality condition of the whole process can be more comprehensively evaluated, and the abnormal problem in the process can be timely found and solved.
Further, step S6 is further included after step S5:
the data acquisition unit is used for collecting operation data of the power equipment in real time when the power equipment fails, the analysis unit is used for analyzing the reason of the failure based on the operation data, when the reason of the failure is caused in the production process, the failure tracing unit is used for tracing the ith working procedure which causes the failure and the jth operation step in the corresponding ith working procedure based on the reason of the failure, and the inspection standard B corresponding to the jth operation step of the ith working procedure is adjusted based on the jth operation step of the ith working procedure, the reason of the failure, the number of times of occurrence of the failure and the operation time from delivery of the power equipment to the failure ij Or adjusting the control information C of the jth operation step in the ith step ij 。
Specifically, although the power equipment may pass the quality detection during the production process, after the power equipment is put into actual operation, the power equipment may fail within a certain period of time during the actual application due to the problem that a certain operation step in a certain working procedure of the production process is at a critical value during the quality detection or is exposed after a certain time period of operation, and the like, and these potential quality problems may not be found during the quality detection during the production process, so that there is a need to continuously optimize and improve the quality management method of the power equipment to reduce the failure risk during the actual operation A method for improving the production qualification rate of power equipment. By collecting the operation data in real time, the equipment faults can be found in time, and corresponding measures are taken for processing. Meanwhile, when determining that the cause of the fault is caused in the production process, the working procedure causing the fault and the corresponding operation step are traced, so that the control information C of the operation step can be conveniently and timely adjusted ij Or corresponding test standard B ij 。
Further, the step S3 includes the following steps:
step S31: quality detection result K of jth operation step of ith process based on prediction ij And a reference inspection standard B for determining the j-th operation step of the i-th process ij ；
Step S32: after the j-th operation step of the i-th process is completed, the first quality detection unit performs quality detection on the j-th operation step and acquires quality detection data D ij Quality inspection data D ij And test criterion B for the j-th operation step ij Comparing, and obtaining a first comparison result, and when the first comparison result is smaller than or equal to a first threshold value, operating the quality detection result K ij If the operation quality is qualified, otherwise, the operation quality detection result K is obtained ij Is unqualified;
step S33: will produce data S ij And an operation quality detection result K ij And storing the data in a storage unit.
Specifically, in the process of producing the power equipment, the reference inspection standard is an international standard, an industry standard or an enterprise standard of the power equipment, and the quality inspection result K is detected through prediction ij Adjusting the reference standard corresponding to the jth operation step part of the ith procedure to obtain the inspection mark B ij . After the j-th operation step of the i-th process is completed, the first quality detection unit performs quality detection on the j-th operation step, and during the quality detection, the detection unit acquires quality detection data D ij For example, the power equipment outputs a specific waveform signal after completing the step, and the quality detection unit can obtain the specific waveform signal, namely the quality detection data D ij Etc. Then, the quality detection data D ij And checkingStandard of test B ij Comparing, if the first comparison result is smaller than or equal to the first threshold value, indicating that the quality of the result produced in the j-th operation step meets the requirement, and thus operating the quality detection result K ij And the product is qualified. Conversely, if the first comparison result is greater than the first threshold value, it is indicated that the quality of the result produced in the j-th operation step is problematic, and thus the quality detection result K is operated ij And is disqualified. After finishing the quality inspection of the j-th operation step of the i-th process, the invention produces the data S ij And the operation quality detection result K ij Stored in a memory unit. Thus, the quality condition of each operation step can be checked and analyzed at any time. At the same time, these data can also be used for subsequent quality prediction and adjustment of the inspection criteria to optimize the production process and improve the product quality.
Further, the step S4 includes the following steps:
step S41: constructing a prediction model based on a random forest algorithm by a modeling unit and based on the production data S stored in a storage unit ij And an operation quality detection result K ij Training a prediction model;
step S42: production data S of the next cycle to be acquired ij Inputting a prediction model to predict an operation quality detection result K of the next period ij ；
Step S43: in the predicted operation quality detection result K ij When the data is qualified, the production data S ij Comparing the sensing data detected by each sensor with the standard reference data of each sensor to obtain a plurality of second comparison results, and reducing the inspection standard B of the j-th operation step within the range of a first set threshold value when the second comparison results are smaller than or equal to a second threshold value ij The first quality detection unit is in accordance with the reduced inspection standard B ij Detecting the j-th operation step of the i-th procedure, otherwise, the first quality detection unit is in accordance with the inspection standard B of the j-th operation step ij Detecting the j operation step of the i procedure;
specifically, the quality detection result K of the j-th operation step is predicted ij Can judge the j-th operation stepIs qualified in the predicted operation quality detection result K ij If the operation is qualified, the qualification rate of the j-th operation step is higher, but the inspection standard B cannot be characterized ij Thus by comparing the production data S of the j-th step ij Comparing the standard reference data corresponding to the j-th step, and when a plurality of second comparison results are smaller than or equal to a second threshold value, describing the production data S ij The standard reference data corresponding to the j-th step is relatively close to each other, so that the quality detection result of the j-th operation step and the inspection standard B are deduced ij More closely, therefore, the inspection criterion of the j-th operation step can be appropriately lowered within the first set threshold range, thereby improving the inspection efficiency, whereas the predicted operation quality inspection result K is, in contrast ij Qualified, but when at least one of the plurality of second comparison results is greater than a second threshold value, the quality inspection result of the j-th operation step and the inspection criterion B cannot be inferred ij Closer, the first quality detection unit also requires a check criterion B according to the j-th operating step ij And detecting the j-th operation step of the i-th procedure, thereby ensuring the accuracy of the quality detection result of the j-th operation step. Random forest algorithms are well known in the art and will not be described in detail herein.
Step S44: in the predicted operation quality detection result K ij If it is not qualified, the production data S ij The sensing data detected by each sensor in the system is compared with standard reference data of each sensor to obtain a plurality of third comparison results, and when at least one of the third comparison results is larger than or equal to a third threshold value, the inspection standard B of the j-th operation step is improved within the range of a first set threshold value ij The first quality detection unit is in accordance with the improved inspection standard B ij Detecting the j-th operation step of the i-th procedure, otherwise, the first quality detection unit is in accordance with the inspection standard B of the j-th operation step ij And detecting the j-th operation step of the i-th procedure, wherein the third threshold value is smaller than the second threshold value.
Specifically, in the predicted operation quality detection result K ij If the quality is not acceptable, the quality detection result K of the j-th operation step is obtained ij The probability of disqualification is larger due to the quality detection standard B ij Can detect the general quality problem, and therefore, in order to prevent the quality detection efficiency from being reduced, it is necessary to further use the production data S ij The difference between the sensing data detected by each sensor and the standard reference data of each sensor is used for judging whether the inspection standard B needs to be improved ij When at least one of the plurality of third comparison results is greater than or equal to a third threshold value, the production data S is described ij The difference between the sensing data detected by at least one sensor and the standard reference data of the sensor is large, and the quality detection result K of the j-th operation step is represented again ij The probability of failure is large, so that the first quality detection unit needs to improve the inspection standard B ij And detecting the j-th operation step of the i-th procedure, otherwise, the j-th operation step is not needed, so that the quality detection efficiency of the j-th operation step is ensured, and the quality detection accuracy of the j-th operation step is ensured.
Further, the step S5 includes the following steps:
step S51: detecting the ith process by the second quality detection unit and acquiring ith process detection data D when all operation steps of the ith process are completed i The ith step detection data D i Detection Standard B with the ith procedure i Comparing to obtain a fourth comparison result, and when the fourth comparison result is smaller than or equal to a fourth threshold value, obtaining an ith procedure quality detection result T i If not, the quality detection result T of the ith procedure is qualified i Disqualification;
specifically, according to the above technical solution, the second quality detection unit detects the quality of the ith process and detects the data D of the ith process i Detection Standard B with the ith procedure i Comparing, and judging whether the ith procedure is qualified according to a fourth comparison result, wherein the detection standard B is i Is an international standard, an industry standard or an enterprise standard.
Step S52: at the quality test result T i If the operation quality detection result K is not qualified and corresponds to all the j-th operation steps in the i-th procedure ij If they are qualified, the quality detection result T is passed through the ith procedure i And determining the abnormality type, determining the abnormality position based on the abnormality type, and improving the control information precision of the operation step related to the abnormality in the ith procedure control information according to the abnormality position and the operation step related to the abnormality.
Specifically, if the quality is detected as the result T i And when the power equipment is qualified, the production requirement of the power equipment is met, and the power equipment is not considered any more. At the quality test result T i If the operation quality detection result K is not qualified and corresponds to all the j-th operation steps in the i-th procedure ij When the control information is qualified, the method is focused on the problem of quality caused by accumulation of tolerance among a plurality of operation steps, and the type and the position of the abnormality are required to be determined first, so that the control information precision of the operation step related to the abnormality in the ith procedure control information is improved through the scheme, and the production requirement of the power equipment is met.
Further, the step S6 includes the following steps:
step S61: the data acquisition unit is used for collecting the operation data of the power equipment when the power equipment fails in real time, and the analysis unit is used for analyzing the failure reason based on the operation data;
specifically, since the quality of the power equipment is finally reflected in the operation process, the power equipment with higher quality has the advantages of good performance and less faults, after the power equipment is put into operation, operation data of the power equipment, especially operation data when faults occur, are also required to be collected, and due to the fact that a certain operation step in a certain working procedure in the production process is in a critical value during quality detection or is exposed after accumulation of factors such as operation for a certain time, faults occur in a certain time period during practical application, and the potential quality problems can not be found in the quality detection in the production process.
Step S62: when the cause of the fault is caused in the production process, tracing the ith working procedure causing the fault and the jth operation step in the corresponding ith working procedure through a fault tracing unit based on the cause of the fault;
Specifically, when the analysis unit analyzes the failure cause to determine the failure cause and causes the production process, the failure position needs to be positioned, the tracing unit traces back to the specific procedure and the corresponding operation step leading to the failure cause, and the optimization adjustment is performed, so that the inspection standard B is adjusted in the subsequent production process ij Or control information C ij The precision improves the production quality of the power equipment.
Step S63: when the running time from delivery to failure of the power equipment is greater than or equal to the preset duration, ignoring the failure; when the running time from delivery to failure of the power equipment is smaller than the preset time, when the number of times of failure is smaller than or equal to the preset number of times, the inspection standard B of the j-th operation step is improved within the second set threshold value range ij The method comprises the steps of carrying out a first treatment on the surface of the When the frequency of faults is greater than the preset frequency, the control information C corresponding to the j-th operation step in the i-th procedure control information is improved ij Precision;
the operation data comprise voltage, current, temperature and operation duration of the power equipment.
Specifically, when tracing the cause of the fault, it is necessary to determine the operation time from delivery to the fault of the power equipment, and if the operation time of the power equipment is longer than (greater than) the preset time (or the design time), it is indicated that the power equipment has reached the scrapping stage, and the problem that is not the problem of the present invention here can be solved by replacing the new power equipment. When the operation time from delivery to failure of the power equipment is less than a preset time period and the number of times of failure is less than or equal to the preset number of times, possibly because the quality of a certain electronic device has individual differences, under the inspection standard of the same operation step, the requirement of the inspection standard can be met, but after inspection, the long-time operation cannot be met, for example: the quality detection is fatigue detection, and thus the inspection standard B of the jth operation step can be increased within the second set threshold value ij To solve, for example: the number of times or the duration of fatigue detection can be increased, thereby reducing the faultsOccurrence of (2); when the running time from delivery to failure of the power equipment is smaller than the preset time and the number of times of failure is larger than the preset number of times, the quality detection of the first quality detection unit and the second quality detection unit is passed when delivery is performed, but the probability of failure is still larger, and the failure is possibly the control information C corresponding to the operation steps ij Due to insufficient accuracy, the control information C corresponding to the jth operation step in the ith procedure control information can be increased ij Accuracy is solved in which the control information C ij Production equipment for controlling the j-th operation step, for example: when welding electronic devices of power equipment, the position alignment precision and the welding temperature are controlled, so that the finishing quality level of the operation step is improved, and the occurrence of the faults is prevented.
In the second embodiment, the quality detection result may further include calculation of a process quality characteristic value and calculation of a process capability index, and the specific implementation manner is as follows: selecting a process quality characteristic value: the key mass characteristics or the main mass characteristics (customizable value μ) that do not stably meet the standard requirements are mainly selected. Process capability index calculation, which represents the magnitude of the degree to which process capability meets process quality criteria, the ratio of process quality requirements to process capability (T is the technical requirement or quality criteria of the product).
Where Cp denotes the process capability index (the magnitude of the degree to which the process capability meets the process quality standard requirement, i.e. the ratio of process quality requirement to process capability), T denotes the technical requirement or quality standard of the product, σ denotes the distribution or degree of dispersion of the mean value of any of the process parameters, 6σ denotes the 6 times standard deviation.
The process capability is the quality level actually achieved by the process itself, and is a relatively stable value; process capability index is also a relative concept, even though the process capability index may vary from one quality standard requirement to another, as shown in table 1. As an index of the degree to which the technical requirements are satisfied, the greater the process capability index,the more the process capability can meet the technical requirements, even a certain technical reserve is provided. Bilateral tolerance and coincidence of the center of distribution and the center of standardization, T, as shown in FIG. 4 U Is the upper limit value of the quality standard, T L Is the lower limit value of the quality standard.
Since the overall standard deviation is typically unknown, the estimate of σ is typically used instead. When the samples are large enough, the standard deviation S of all sample data is often used to estimate the total standard deviation σ, when Cheng Wending is exceeded.
Table 1 risk judgment and countermeasure table.
The first quality detection unit may also measure a systematic error analysis (MSA): the measurement is the basis for making an adjustment decision on the manufacturing process, determining whether there is a significant correlation between two or more variables, if the manner of measurement is not correct, then good results may be measured as bad results, and bad results may be measured as good results, at which time the actual product or process characteristics may not be obtained. In order to analyze the variations present in the measurement results of the various measurement and test equipment systems, appropriate statistical studies must be performed, which requirements must be applicable to the measurement systems proposed in the control program.
The measurement system should be statistically controlled, which means that under repeatable conditions, the deterioration of the measurement system can only be due to common reasons and not to special reasons. This is known as statistical stability and is best evaluated graphically as shown in fig. 5.
For product control, the variability of the measurement system must be smaller than the tolerance-based tolerance evaluation measurement system compared to the tolerance.
For process control, the variability of the measurement system should show an effective resolution and be small compared to process variations. The measurement system was evaluated based on 6σ variation and/or total variation from MSA studies.
Measurement = true value + measurement error (y = x + epsilon), where y represents measurement value, x represents true value, epsilon represents measurement error.
In addition to setting the first threshold in the first embodiment, the second embodiment may also set a threshold model exceeding the standard upper limit and being lower than the standard lower limit, as shown in fig. 6, and taking [ mu ] ±3σ as the upper and lower control limits according to the nature of the normal distribution.
Under the "3σ" principle, the general formula for the control limit is: the upper limit ucl=e (x) +3σ (x), the lower limit lcl=e (x) -3σ (x), cl=e (x), wherein UCL represents the upper limit value of quality characteristic control, LCL represents the lower limit value of quality characteristic control, CL represents the center value of quality characteristic, x represents the product quality characteristic value, and E (x) represents the desired value.
The first embodiment adopts a random forest algorithm to construct the prediction model, and the second embodiment can also add an integrated learning process model, wherein the integrated learning learns a plurality of estimators through training, and when the prediction is needed, the results of the estimators are integrated through a combiner and output as the final result, as shown in fig. 7.
For example, the second threshold in the first embodiment may also be set as a function value in the second embodiment, and the distribution center μ and the standard center M are not coincident due to double-sided tolerance, as shown in fig. 8.
Wherein T is U Upper limit value of the quality standard, T L The lower limit value of the quality standard is represented, and M represents the standard center value.
The absolute offset of the scoreboard center mu to the standard center M is epsilon, then. Let ε to T/2 be the relative offset or relative offset coefficient, denoted K, then: />Wherein M represents a standard center value, mu represents a normal distribution center value, epsilon represents an absolute offset of the distribution center mu from the standard center M, T represents a technical requirement or quality standard of a product, and K represents a relative offset or a relative offset coefficient.
The process capability index on the left side of the distribution center is:wherein C pl Represents the process ability index on the left side of the distribution center, μ represents the normal distribution center value, T L The lower limit value of the quality standard is represented, T represents the technical requirement or the quality standard of the product, epsilon represents the absolute offset of the distribution center mu from the standard center M, and 3 sigma represents three times of standard deviation.
From the above formula, it can be seen that:
(1) when mu is exactly in the center of the standard,i.e., k=0, cpk=cp, where Cpk represents the corrected process capability index, the corrected process capability index is the general process capability index;
(2) when μ happens to be at the standard upper or lower limit, i.e., μ=tu or μ=tl, where k=1, cpk=0;
(3) When μ is outside the standard limits, i.e., ε > T/2, then K > 1, cpk=0.
Therefore, the smaller the K value, the better, k=0 is an ideal state.
The abnormal position is determined based on the abnormal type, and the control information precision of the operation step related to the abnormality in the ith procedure control information is improved according to the abnormal position and the operation step related to the abnormality. The method can also analyze by adding a normal distribution map of the quality variation, for example, the product quality variation rule: in the production process of the product, certain rules can be circulated on the quality condition of the same batch of products.
Probability theory center limit theorem: the distribution of the sum of n mutually independent random variables with the same distribution is asymptotically to the normal distribution.
In the production process, when a plurality of accidental factors independent of each other commonly affect the production object, the mutual interaction and mutual cancellation result in normal distribution of the quality characteristics of the product, as shown in fig. 9.
For example: under normal production conditions, 68.26% of the product has a quality characteristic in the interval mu+ -sigma; products in the interval mu+ -2σ have 95.46%; products within the interval mu+ -3 sigma have 99.73% and all the mass differences within the range mu+ -3 sigma are normal, which is the result of the effect of contingency factors, as shown in figure 10.
The invention also provides a system for improving the quality management of the production process of the electric equipment, which is shown in fig. 2, and comprises the following modules:
the data acquisition unit is used for periodically acquiring production data in a first process of the power equipment, wherein the production data represents data corresponding to the first process, the first process comprises m working procedures, each working procedure comprises n operation steps, and the production data is divided into m production data corresponding to the m working procedures according to a production sequence;
a production management unit for generating process control information including control information C of the j-th operation step in the i-th process according to the process execution process ij Production data S corresponding to the j-th operation step of the i-th process ij The sensor comprises sensing data detected by a plurality of sensors, wherein i is greater than or equal to 1 and less than or equal to m, and j is greater than or equal to 1 and less than or equal to n;
a first quality detection unit for, when the j-th operation step of the i-th process of the power equipment is completed, based on the inspection standard B corresponding to the j-th operation step ij Obtaining the operation quality detection result K of the j-th operation step ij Wherein the quality of operation detection result K ij Quality detection results of the j-th operation step of the i-th procedure, and the production data S ij And an operation quality detection result K ij Saving in a storage unit;
a modeling unit for constructing a predictive model and using the production data S stored in the storage unit ij And the operation quality detection result K ij Training a predictive model based on the predictive model and the production data S of the next cycle ij Predicting operation quality detection result K of next period ij And based on the predicted operation quality detection result K ij Adjusting the inspection standard B corresponding to the j-th operation step of the i-th procedure ij 。
The invention also provides a computer storage medium, wherein the storage medium stores program instructions, and the equipment where the computer storage medium is located is controlled to execute the method for improving the quality management of the production process of the power equipment when the program instructions run.
In summary, the data acquisition unit periodically acquires the production data in the first process of the power equipment, so as to ensure continuity and integrity of acquiring the production data. Meanwhile, the production data are divided into m production data corresponding to m working procedures according to the production sequence, so that the first process of the power equipment is conveniently managed in the minimum unit, the classification and arrangement of the production data are realized, and a foundation is provided for subsequent quality analysis. In the first process of the power equipment, the production management unit generates process control information according to the process execution process, divides the ith process into a plurality of operation steps according to different operation actions, and defines control information C of the jth operation step in the ith process ij Therefore, by monitoring each operation step in real time, problems can be found in time and improved in a targeted manner. Since the production data in the first process of the electric power plant is composed of the sensing data detected by the plurality of sensors, the production data S corresponding to the j-th operation step of the i-th process ij And also includes sensed data sensed by a plurality of sensors. By analyzing the sensing data detected by the plurality of sensors corresponding to the j-th operation step of the i-th process, the quality condition of each process can be reflected more accurately, so that a basis is provided for optimizing the first process and improving the production qualification rate of the power equipment. Upon completion of the j-th operation step of the i-th process of the electrical equipment, the first quality detection unit is used for detecting the quality of the electrical equipment based on the inspection standard B corresponding to the j-th operation step ij Obtaining the operation quality detection result K of the j-th operation step ij Wherein the quality of operation detection result K ij Quality detection results of the j-th operation step of the i-th procedure, and the production data S ij And an operation quality detection result K ij Saving in a storage unit; the method is convenient for subsequent traceability in analysis, and provides abundant data support for constructing the prediction model. Building a predictive model by a modeling unit and using the raw data stored in the storage unit Production data S ij And an operation quality detection result K ij And training a prediction model to realize the prediction of the quality detection result of the j-th operation step of the next period. Meanwhile, based on the predicted operation quality detection result K ij Adjusting the inspection standard B corresponding to the j-th operation step of the i-th procedure ij Dynamic adjustment of the inspection standard is realized. Through the mutual coordination among the schemes, powerful support is provided for quality management of the production process of the power equipment, so that the production qualification rate of the power equipment is improved.
It should be understood that, although the steps in the flowcharts of the embodiments of the present invention are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in various embodiments may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor do the order in which the sub-steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of the sub-steps or stages of other steps or other steps.
Those skilled in the art will appreciate that implementing all or part of the above-described methods may be accomplished by way of computer programs, which may be stored on a non-transitory computer readable storage medium, and which, when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above embodiments may be arbitrarily combined, and for brevity, all of the possible combinations of the technical features of the above embodiments are not described, however, they should be considered as the scope of the description of the present specification as long as there is no contradiction between the combinations of the technical features.
The foregoing examples have been presented to illustrate only a few embodiments of the invention and are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.

Claims (9)

1. A method for improving quality management of an electrical equipment manufacturing process, the method comprising the steps of:
Step S1: the method comprises the steps that a data acquisition unit periodically acquires production data in a first process of the power equipment, wherein the production data represent data corresponding to the first process, the first process comprises m working procedures, each working procedure comprises n operation steps, and the production data are divided into m production data segments corresponding to the m working procedures according to a production sequence;
step S2: the production management unit generates the procedure according to the procedure execution processControl information including control information C of a jth operation step in an ith process ij Production data S corresponding to the j-th operation step of the i-th process ij The sensor comprises sensing data detected by a plurality of sensors, wherein i is greater than or equal to 1 and less than or equal to m, and j is greater than or equal to 1 and less than or equal to n;
step S3: upon completion of the j-th operation step of the i-th process of the electric power equipment, the first quality detection unit is used for detecting the operation state of the electric power equipment based on the inspection standard B corresponding to the j-th operation step ij Obtaining an operation quality detection result K of the j-th operation step ij Wherein the operation quality detection result K ij Quality detection results of the j-th operation step of the i-th process, and the production data S ij And the operation quality detection result K ij Saving in a storage unit;
step S4: constructing a predictive model by a modeling unit and using the production data S stored in the storage unit ij And the operation quality detection result K ij Training the predictive model based on the predictive model and the production data S of the next cycle ij Predicting the operation quality detection result K of the next period ij And based on the predicted operation quality detection result K ij Adjusting the inspection standard B corresponding to the j-th operation step of the i-th procedure ij 。
2. The method for improving the quality management of the production process of the electric equipment according to claim 1, wherein the step S4 further comprises a step S5:
upon completion of the ith process of the power equipment, a second quality detection unit is used to detect the presence of a load on the basis of the inspection standard B of the ith process i Obtaining an ith process quality detection result T i And based on the i-th process quality detection result T i And all the operation quality detection results K ij And determining an abnormal position and adjusting the abnormal position.
3. The method for improving the quality management of the production process of the electric equipment according to claim 2, wherein the step S5 further comprises a step S6 of:
The data acquisition unit is used for collecting operation data of the power equipment when faults occur in real time, the analysis unit is used for analyzing the reasons for the faults based on the operation data, when the reasons for the faults are caused in the production process, the fault tracing unit is used for tracing the ith working procedure which causes the faults based on the reasons for the faults and the jth operation step corresponding to the ith working procedure, and the inspection standard B corresponding to the jth operation step of the ith working procedure is adjusted based on the jth operation step of the ith working procedure, the reasons for the faults, the times of occurrence of the faults and the operation time from the delivery of the power equipment to the occurrence of the faults ij Or adjusting the control information C of the jth operation step in the ith step ij 。
4. The method for improving the quality management of a power plant production process according to claim 1, wherein said step S3 comprises the steps of:
step S31: based on the predicted quality detection result K of the j-th operation step of the i-th process ij And a reference inspection standard B for determining the inspection standard B of the j-th operation step of the i-th process ij ；
Step S32: after the j-th operation step of the i-th process is completed, the first quality detection unit performs quality detection on the j-th operation step and acquires quality detection data D ij The quality detection data D ij And the inspection standard B of the j-th operation step ij Comparing, and obtaining a first comparison result, wherein when the first comparison result is smaller than or equal to a first threshold value, the operation quality detection result K ij Qualified, otherwise the operation quality detection result K ij Is unqualified;
step S33: the production data S ij And the operation quality detection result K ij And storing the data into the storage unit.
5. The method for improving the quality management of a power plant production process according to claim 1, wherein said step S4 comprises the steps of:
step S41: constructing the prediction model based on a random forest algorithm by the modeling unit and based on the production data S stored in the storage unit ij And the operation quality detection result K ij Training the prediction model;
step S42: the production data S of the next period to be acquired ij Inputting the prediction model, and predicting the operation quality detection result K of the next period ij ；
Step S43: in the predicted operation quality detection result K ij When the production data is qualified, the production data S ij Comparing the sensing data detected by each sensor with the standard reference data of each sensor to obtain a plurality of second comparison results, and reducing the inspection standard B of the jth operation step within a first set threshold range when the second comparison results are smaller than or equal to a second threshold ij The first quality detection unit is in accordance with the reduced inspection standard B ij Detecting the j-th operation step of the i-th procedure, otherwise, the first quality detection unit is in accordance with the inspection standard B of the j-th operation step ij Detecting the j-th operation step of the i-th procedure;
step S44: in the predicted operation quality detection result K ij If it is not qualified, the production data S ij Comparing the sensing data detected by each sensor with the standard reference data of each sensor to obtain a plurality of third comparison results, and improving the inspection standard B of the j-th operation step within a first set threshold range when at least one of the third comparison results is larger than or equal to a third threshold ij The first quality detection unit is in accordance with the improved inspection standard B ij Detecting the j-th operation step of the i-th procedure, otherwise, the first quality detection unit detects the j-th operation stepIs the test standard B of (2) ij And detecting the j-th operation step of the i-th procedure, wherein the third threshold value is smaller than the second threshold value.
6. The method for improving the quality management of the production process of the electric power equipment according to claim 2, wherein the step S5 comprises the steps of:
Step S51: detecting the ith process by the second quality detection unit and acquiring the ith process detection data D when all operation steps of the ith process are completed i The ith step detection data D i Detection Standard B with the ith procedure i Comparing to obtain a fourth comparison result, and when the fourth comparison result is smaller than or equal to a fourth threshold value, obtaining an i-th process quality detection result T i If not, the quality detection result T of the ith procedure is qualified i Disqualification;
step S52: at the quality test result T i If the operation quality detection result K is not qualified and corresponds to all the j-th operation steps in the i-th process ij If all are qualified, passing the quality detection result T of the ith working procedure i Determining an abnormality type, determining an abnormality position based on the abnormality type, and improving the control information precision of the operation step related to the abnormality in the ith process control information according to the abnormality position and the operation step related to the abnormality.
7. A method of improving quality management of a power plant production process according to claim 3, wherein said step S6 comprises the steps of:
Step S61: the data acquisition unit is used for collecting the operation data of the power equipment when the power equipment fails in real time, and the analysis unit is used for analyzing the reason of the failure based on the operation data;
step S62: when the cause of the fault is caused in the production process, tracing the ith working procedure causing the fault and the jth operation step corresponding to the ith working procedure through a fault tracing unit based on the cause of the fault;
step S63: when the running time from delivery to occurrence of the fault of the power equipment is greater than or equal to a preset duration, ignoring the fault; when the running time from delivery to occurrence of the fault of the power equipment is smaller than the preset time, and when the occurrence frequency of the fault is smaller than or equal to the preset frequency, the inspection standard B of the j-th operation step is improved within a second set threshold value range ij The method comprises the steps of carrying out a first treatment on the surface of the When the number of times of occurrence of the fault is greater than the preset number of times, the control information C corresponding to the jth operation step in the ith procedure control information is increased ij Precision;
the operation data comprise voltage, current, frequency, temperature and operation duration of the power equipment.
8. A power plant production process quality management improvement system for implementing the method according to any of claims 1-7, characterized in that the system comprises the following modules:
The data acquisition unit is used for periodically acquiring production data in a first process of the power equipment, wherein the production data represents data corresponding to the first process, the first process comprises m working procedures, each working procedure comprises n operation steps, and the production data is divided into m production data corresponding to the m working procedures according to a production sequence;
a production management unit for generating process control information including control information C of a j-th operation step in an i-th process according to a process execution process ij Production data S corresponding to the j-th operation step of the i-th process ij The sensor comprises sensing data detected by a plurality of sensors, wherein i is greater than or equal to 1 and less than or equal to m, and j is greater than or equal to 1 and less than or equal to n;
a first quality detection unit configured to, upon completion of the j-th operation step of the i-th process of the electric power equipment, based on a verification criterion B corresponding to the j-th operation step ij Obtaining an operation quality detection result K of the j-th operation step ij Wherein the operation quality detection result K ij Quality detection results of the j-th operation step of the i-th process, and the production data S ij And the operation quality detection result K ij Saving in a storage unit;
a modeling unit for constructing a predictive model and using the production data S stored in the storage unit ij And the operation quality detection result K ij Training the predictive model based on the predictive model and the production data S of the next cycle ij Predicting the operation quality detection result K of the next period ij And based on the predicted operation quality detection result K ij Adjusting the inspection standard B corresponding to the j-th operation step of the i-th procedure ij 。
9. A computer storage medium, characterized in that the storage medium stores program instructions, wherein the program instructions, when run, control a device in which the storage medium is located to perform the method for improving quality management of a production process of an electrical device according to any one of claims 1-7.
CN202410124616.3A 2024-01-30 2024-01-30 Method, system and storage medium for improving quality management of power equipment production process Active CN117689270B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202410124616.3A CN117689270B (en) 2024-01-30 2024-01-30 Method, system and storage medium for improving quality management of power equipment production process

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202410124616.3A CN117689270B (en) 2024-01-30 2024-01-30 Method, system and storage medium for improving quality management of power equipment production process

Publications (2)

Publication Number Publication Date
CN117689270A true CN117689270A (en) 2024-03-12
CN117689270B CN117689270B (en) 2024-06-18

Family

ID=90132251

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202410124616.3A Active CN117689270B (en) 2024-01-30 2024-01-30 Method, system and storage medium for improving quality management of power equipment production process

Country Status (1)

Country Link
CN (1) CN117689270B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118113010A (en) * 2024-04-30 2024-05-31 成都飞机工业（集团）有限责任公司 Processing quality control method, device, equipment and storage medium

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115204555A (en) * 2021-04-13 2022-10-18 埃森哲环球解决方案有限公司 Anomaly detection method and system for manufacturing process
CN115983532A (en) * 2023-02-10 2023-04-18 杭州艾想科技有限公司 Method, system, electronic device and storage medium for detecting production quality of equipment
CN117193222A (en) * 2023-10-24 2023-12-08 东北林业大学 Intelligent quality control system based on industrial Internet of things and big data and control method thereof

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115204555A (en) * 2021-04-13 2022-10-18 埃森哲环球解决方案有限公司 Anomaly detection method and system for manufacturing process
CN115983532A (en) * 2023-02-10 2023-04-18 杭州艾想科技有限公司 Method, system, electronic device and storage medium for detecting production quality of equipment
CN117193222A (en) * 2023-10-24 2023-12-08 东北林业大学 Intelligent quality control system based on industrial Internet of things and big data and control method thereof

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118113010A (en) * 2024-04-30 2024-05-31 成都飞机工业（集团）有限责任公司 Processing quality control method, device, equipment and storage medium

Also Published As

Publication number Publication date
CN117689270B (en) 2024-06-18

Similar Documents

Publication Publication Date Title
CN109459993B (en) Online adaptive fault monitoring and diagnosing method for process industrial process
Coble et al. Identifying optimal prognostic parameters from data: a genetic algorithms approach
CN117689270B (en) Method, system and storage medium for improving quality management of power equipment production process
JP6811018B2 (en) Quality evaluation system, quality evaluation method and program
KR20190062739A (en) Method, algorithm and device for Data analytics for predictive maintenance using multiple sensors
KR20090001148A (en) Virtual metrology system and virtual metrology method
US20220050023A1 (en) System for predicting anomalies of machining
Vafeiadis et al. Robust malfunction diagnosis in process industry time series
CN117808456A (en) Equipment fault early warning method and device based on intelligent operation management
Baghbanpourasl et al. Failure prediction through a model-driven machine learning method
Kurz et al. Monitoring virtual metrology reliability in a sampling decision system
JP6765769B2 (en) State change detection device and state change detection program
CN115907033A (en) Method and system for predicting hourly power consumption based on machine learning algorithm
KR20220097252A (en) Method and system for managing equipment of smart plant using machine-learning
CN116957120A (en) Device state history trend anomaly prediction method based on data analysis
CN113887990A (en) Electrical equipment maintenance decision optimization method
Klees et al. Building a smart database for predictive maintenance in already implemented manufacturing systems
CN117272844B (en) Method and system for predicting service life of distribution board
CN116990685B (en) Method and system for evaluating quality of retired motor
CN111650444A (en) Regression analysis-based TCU failure early warning method in electromagnetic environment
JP6859381B2 (en) State change detection device and state change detection program
Zhao et al. Equipment Health Assessment Based on AHP-CRITIC Dynamic Weight
Ou et al. An incipient on-line anomaly detection approach for the dynamic rolling process
CN118155779B (en) Ultra-thin wall internal thread copper pipe expansion and contraction rate evaluation method and system
CN117970168B (en) High-efficiency processing method for monitoring data of dual-power conversion device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
TA01 Transfer of patent application right
TA01 Transfer of patent application right

Effective date of registration: 20240514

Address after: No. 100-21 Xingdao Road, Heping District, Shenyang City, Liaoning Province, 110000, 2-10-1

Applicant after: Shen Yahui

Country or region after: China

Address before: Room 606, No. 39-1, Chuangxin Second Road, Shenyang area, China (Liaoning) pilot Free Trade Zone, Shenyang, Liaoning Province

Applicant before: Lingjun (Liaoning) Technology Co.,Ltd.

Country or region before: China

GR01 Patent grant
GR01 Patent grant