CN114219461A - Production control method and device based on multiple production working conditions - Google Patents

Production control method and device based on multiple production working conditions Download PDF

Info

Publication number
CN114219461A
CN114219461A CN202210160309.1A CN202210160309A CN114219461A CN 114219461 A CN114219461 A CN 114219461A CN 202210160309 A CN202210160309 A CN 202210160309A CN 114219461 A CN114219461 A CN 114219461A
Authority
CN
China
Prior art keywords
working condition
version
benchmark
production
versions
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
CN202210160309.1A
Other languages
Chinese (zh)
Other versions
CN114219461B (en
Inventor
郭传亮
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.)
Hope Zhizhou Technology Shenzhen Co ltd
Original Assignee
Hope Zhizhou Technology Shenzhen 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 Hope Zhizhou Technology Shenzhen Co ltd filed Critical Hope Zhizhou Technology Shenzhen Co ltd
Priority to CN202210160309.1A priority Critical patent/CN114219461B/en
Priority to CN202210675216.2A priority patent/CN115130985A/en
Publication of CN114219461A publication Critical patent/CN114219461A/en
Application granted granted Critical
Publication of CN114219461B publication Critical patent/CN114219461B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • G06Q10/10—Office automation; Time management
    • G06Q10/103—Workflow collaboration or project management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/04—Inference or reasoning models
    • 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
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Software Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Mathematical Physics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Business, Economics & Management (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Tourism & Hospitality (AREA)
  • Computing Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Manufacturing & Machinery (AREA)
  • Computational Linguistics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • General Factory Administration (AREA)

Abstract

The invention discloses a production control method and a device based on multiple production working conditions, which comprises the following steps: obtaining at least one working condition version of the benchmark, wherein the at least one working condition version of the benchmark is a working condition version inferred through a machine learning model; generating a working condition benchmark value score sub-card of each benchmark working condition version in at least one benchmark working condition version; performing volume production verification according to each benchmark working condition version in at least one benchmark working condition version, and updating the working condition benchmark value dividing card of each benchmark working condition version according to design parameters of the volume production verification; and evaluating the usability of each benchmark working condition version according to the working condition benchmark value dividing card of each benchmark working condition version, and determining the mass production version in at least one benchmark working condition version. The invention can scientifically judge the mass production quality of each working condition version, determine the optimal production process parameters, and perform quality control on mass-produced products so as to ensure the optimal yield of the products.

Description

Production control method and device based on multiple production working conditions
Technical Field
The invention relates to the field of general data processing, in particular to a production control method and device based on multiple production working conditions.
Background
For a traditional process manufacturing type enterprise to realize optimization of a production process, actual operators are required to reason and summarize experiences in actual production and manufacturing, for example, a traditional chemical plant enterprise, the obtained method cannot be widely verified in mass production, excellent experiences cannot be shared, solidification and popularization cannot be achieved, the experiences of system management of optimal production full-process parameters are lacked, and meanwhile, the traditional experiences lack support of big data and accurate statistical analysis and cannot meet the requirements of current intelligent production.
In the production process of a production manufacturing enterprise, the operation boundary conditions of production equipment are constantly changed: the quality of supplied materials is variable, the climate is variable, the equipment is variable, the load is variable, the operation and application difficulty of excellent experience in the equipment is high, meanwhile, only one set of large and complete production process standard is usually adopted in the production process, the quality index of products produced according to the standard fluctuates greatly, the quality is unstable, engineers are required to adjust process parameters according to own experience, a mechanism for operating the multi-working-condition classification management equipment under the optimal parameter is lacked, and the achievement of the quality, cost and efficiency index targets of the products is guaranteed.
Disclosure of Invention
In order to solve the problems, the embodiment of the application provides a production control method and a device based on multiple production working conditions, and the working condition benchmarking value dividing cards are newly built for a plurality of working condition versions obtained through machine learning model reasoning, so that the refining degree of production is improved, and the product quality is improved. The working condition versions are subjected to volume production verification, a plurality of design parameters obtained by volume production are recorded in a working condition benchmark value dividing card, the versions of the training results corresponding to each working condition are determined, the working condition versions of all the versions are recommended according to the version types, and the production quality has a scientific judgment basis. The optimal mass production working condition version is selected by the method for verifying the mass production of the working condition versions, the production process parameters are guaranteed to be set in the optimal state all the time, the mass production version of the benchmarking working condition is dynamically updated through a sampling filtering algorithm, the product quality control in the mass production stage is achieved, and the optimal yield of the product is guaranteed.
In order to achieve the above object, in a first aspect, an embodiment of the present application provides a production control method based on multiple production conditions, where the method includes:
obtaining at least one working condition version of the benchmark, wherein the at least one working condition version of the benchmark is a working condition version which is inferred by a machine learning model; generating a working condition benchmark value dividing card of each benchmark working condition version in at least one benchmark working condition version, wherein the working condition benchmark value dividing card is used for recording design parameters of each benchmark working condition version; performing volume production verification according to each benchmark working condition version in at least one benchmark working condition version, and updating the working condition benchmark value dividing card of each benchmark working condition version according to design parameters of the volume production verification; and evaluating the usability of each benchmark working condition version according to the working condition benchmark value dividing card of each benchmark working condition version, and determining the mass production version in at least one benchmark working condition version.
With reference to the first aspect, in a possible embodiment, obtaining at least one benchmarking working condition version includes:
acquiring a first working condition version, wherein the first working condition version is one working condition version with the highest priority rank in working condition versions which reach learning targets through machine learning model reasoning; acquiring a second working condition version, wherein the second working condition version is M randomly selected from N working condition versions with the highest priority ranking, except the working condition version with the highest priority ranking, in the working condition versions which reach the learning target through machine learning model reasoning, and N is more than or equal to M; and taking the first working condition version and the second working condition version as at least one benchmark working condition version.
With reference to the first aspect, in a possible embodiment, obtaining at least one benchmarking working condition version includes:
and if the benchmark working condition version does not reach the learning target after being inferred by the machine learning model, taking the first T working condition versions with the highest priority ranking as at least one benchmark working condition version.
With reference to the first aspect, in one possible embodiment, the priorities of the condition versions are determined before and after ranking according to a condition that a design parameter in the condition version reaches a target value.
With reference to the first aspect, in one possible embodiment, the evaluating the availability of each benchmarking condition version according to the benchmarking value score card of each benchmarking condition version includes: updating the batch data of the product parameters of the corresponding benchmark working condition version by the working condition benchmark value dividing card of each benchmark working condition version according to the volume production verification result; acquiring upper and lower limits of product parameter specifications of a dividing card by a working condition benchmark value; calculating the mean value and standard deviation of the product parameters according to the batch data of the product parameters; and calculating to obtain the process capability index CPK of the product parameter of each benchmark working condition version according to the product parameter mean value, the product parameter standard deviation and the product parameter specification upper and lower limits.
With reference to the first aspect, in a possible embodiment, the evaluating the availability of each benchmarking version according to the CPK value of the product parameter includes: if the CPK of the product parameter of the first target working condition version in the at least one benchmark working condition version is not larger than a first preset value, determining that the first target working condition version is a mass production unavailable version; if the CPK of the product parameter of the second target working condition version in the at least one benchmark working condition version is larger than the first preset value, determining that the second target working condition version is a mass production available version; and if the CPK of the product parameter of the third target working condition version in the at least one benchmark working condition version is greater than a second preset value, determining that the current product is the optimal version for mass production.
With reference to the first aspect, in one possible embodiment, determining a mass production version of at least one benchmarking operating condition version includes: if the fact that the at least one benchmark working condition version comprises the only mass production optimal version is determined, the only mass production optimal version is determined to be the mass production version in the at least one benchmark working condition version; and/or if at least one benchmark working condition version is determined to comprise a plurality of mass production optimal versions, determining sequencing according to the parameter priority and parameter value corresponding to each of the plurality of mass production optimal versions in the production data table, and determining the mass production versions according to the sequencing result, wherein the production data table is composed of design parameters in the working condition benchmark value dividing card; and/or if the fact that the at least one benchmarking working condition version does not comprise the only optimal mass production version and comprises at least one available mass production version is determined, determining sequencing according to the parameter priority and the parameter value corresponding to each of the plurality of available mass production versions in the production data table, and determining the mass production versions according to the sequencing result.
In a second aspect, an embodiment of the present application provides a production control device based on multiple production conditions, where the production control device based on multiple production conditions includes:
an acquisition unit: the system comprises a machine learning model and a benchmark version module, wherein the machine learning model is used for obtaining at least one benchmark working condition version;
a recording unit: the working condition benchmark value dividing card is used for recording design parameters of each benchmark working condition version; performing volume production verification according to each benchmark working condition version in at least one benchmark working condition version, and updating the working condition benchmark value dividing card of each benchmark working condition version according to design parameters of the volume production verification;
an evaluation unit: and the system is used for evaluating the usability of each benchmark working condition version according to the working condition benchmark value dividing card of each benchmark working condition version and determining the mass production version in at least one benchmark working condition version.
In a third aspect, embodiments of the present application provide an electronic device, including a processor, a memory, a communication interface, and one or more programs, where the one or more programs are stored in the memory and configured to be executed by the processor, and where the one or more instructions are adapted to be loaded by the processor and to perform the following steps:
obtaining at least one working condition version of the marker post, wherein the at least one working condition version of the marker post is a working condition version which is inferred by a machine learning model;
generating a working condition benchmark value dividing card of each benchmark working condition version in at least one benchmark working condition version, wherein the working condition benchmark value dividing card is used for recording design parameters of each benchmark working condition version;
performing volume production verification according to each benchmark working condition version in at least one benchmark working condition version, and updating the working condition benchmark value dividing card of each benchmark working condition version according to design parameters of the volume production verification;
and evaluating the usability of each benchmark working condition version according to the working condition benchmark value dividing card of each benchmark working condition version, and determining the mass production version in at least one benchmark working condition version.
In a fourth aspect, embodiments of the present application provide a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program causes a computer to perform the method according to the first aspect.
The embodiment of the application has the following beneficial effects:
newly-built operating mode benchmark value minute card for a plurality of operating mode editions that obtain through machine learning model reasoning, the technological parameter that increases the record has improved the degree that becomes more meticulous of production, has promoted product quality. The working condition versions are subjected to volume production verification, a plurality of process parameters obtained by volume production are recorded in a working condition benchmark value dividing card, the versions of the training results corresponding to each working condition are determined, and the working condition versions of each version are recommended according to the version types, so that a scientific judgment basis exists for the production quality. By the method for verifying the working condition versions in mass production, the optimal mass production working condition version is selected, the production process parameters are guaranteed to be set in the optimal state all the time, and the yield of the product is guaranteed to be optimal.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic view of an application scenario of a production control method based on multiple production conditions according to an embodiment of the present application;
fig. 2 is a schematic flow chart of a production control method based on multiple production conditions according to an embodiment of the present application;
FIG. 3A is a schematic view of a product scorecard according to an embodiment of the present application;
FIG. 3B is a schematic view of a component scorecard according to an embodiment of the present application;
FIG. 3C is a schematic view of a process tool scorecard according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a production control device based on multiple production conditions according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The terms "first," "second," and the like in the description and claims of the present application and in the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
First, terms related to embodiments of the present application will be explained.
Multiple working conditions: the definition of the working condition is the combination of the variation intervals of the characteristic values of the input elements of the production process, such as production workers, production machines, production raw materials, production methods, production environments and the like. Different working condition combinations have obvious influence on the control parameters of the production flow. The multiple working conditions mean that the production process is classified and managed according to different working conditions.
The working condition version is as follows: the working condition version in the embodiment of the application comprises various process parameters in a production method of a certain product, such as parameters including a person manufacturing the product, a machine used for manufacturing the product, a raw material used for manufacturing the product, a method used for manufacturing the product, an environment in the process of manufacturing the product, and the like. The working condition versions at different stages in the method can be continuously updated according to various process parameters.
Working condition benchmarking value version scoring card: in the embodiment of the application, the working condition benchmark version scoring card comprises a process equipment scoring card, a component scoring card and a product scoring card, is used for recording the design parameters of the working condition version, and has a numerical value updating function.
Designing parameters: the method comprises the following steps of (1) including product parameters, component parameters and process equipment parameters, wherein the product parameters are various parameters for evaluating the quality of a final product after actual production; the part parameters are characteristic parameters of supplier incoming materials or intermediate products generated in the production process; the process equipment parameters are process indexes (such as operation time and material feeding amount) and equipment parameter indexes (such as temperature, pressure, liquid level and the like) for controlling each production process flow.
Upper Limit of specification (Upper Spec Limit, USL) and Lower Limit of specification (Lower Spec Limit, LSL): refers to the maximum and minimum values that allow the parameter values to float.
Process Capability Index (Capability Index of Process, Cpk): is the degree to which the process capability meets the product quality standard requirements (specification range, etc.).
Embodiments of the present application are described below with reference to the drawings.
Referring to fig. 1, fig. 1 is a schematic view of an application scenario of a production control method based on multiple production conditions according to an embodiment of the present application; the application scenario 100 comprises a machine learning module 101, a working condition benchmark version scoring card 102, an evaluation module 103 and a sampling and filtering module 104, wherein the machine learning module 101 is used for performing machine learning on the benchmark working condition versions to adjust technological equipment parameters of the benchmark working condition versions to obtain theoretically optimal technological equipment parameter combinations and obtain a plurality of benchmark working condition versions which are trained, the working condition benchmark version scoring card 102 is used for recording design parameters of the finished plurality of benchmark working condition versions in each stage, the evaluation module 103 is used for evaluating and classifying the benchmark working condition versions according to data recorded by the working condition benchmark version scoring card 102 to select final mass production versions, and the sampling and filtering module 104 is used for dynamically updating the versions of the benchmark working conditions according to a sampling and filtering algorithm in the mass production stage.
Referring to fig. 2, fig. 2 is a schematic flow chart of a production control method based on multiple production conditions according to an embodiment of the present application, which can be implemented based on the application environment shown in fig. 1, as shown in fig. 2, including steps S201 to S205:
s201: and acquiring at least one working condition version of the marker post, wherein the at least one working condition version of the marker post is a working condition version which is inferred by a machine learning model.
In the embodiment of the application, after a new working condition version of the flagpole is created, a preset learning task target value is set for the new working condition version of the flagpole, and the target value is reached by theoretically optimal combination of process equipment parameters such as production time, raw materials used by a manufactured product, a method used by the manufactured product and the like which are obtained by inference through a machine learning model; at this time, the working condition version reaching the learning target or completing the training times can be called a benchmark working condition version, or part of the working condition versions selected from the working condition versions can be called the benchmark working condition versions. And selecting the working condition version of the marker post to enter a mass production verification stage.
In one possible embodiment, obtaining at least one benchmarking condition version comprises: acquiring a first working condition version, wherein the first working condition version is one working condition version with the highest priority rank in working condition versions which reach learning targets after being inferred by a machine learning model; acquiring a second working condition version, wherein the second working condition version is M working condition versions randomly selected from N working condition versions with the highest priority ranking, except the working condition version with the highest priority ranking, in the working condition versions which reach the learning target after being inferred by the machine learning model, and N is more than or equal to M; and taking the first working condition version and the second working condition version as at least one benchmark working condition version.
Specifically, in a case where a part of the working condition versions that reach the learning target or that have completed training times is selected as a benchmarking working condition version, the process of specifically determining the benchmarking working condition version for the benchmarking working condition version may include: sequencing according to the standard reaching degree of the learning target, and firstly determining a benchmark working condition version with the highest rank as one of the at least one benchmark working condition version; secondly, M benchmarking condition versions which are not the highest ranked but are the top ranked N benchmarking condition versions can be randomly selected and determined as the at least one benchmarking condition version together with the one benchmarking condition version with the highest priority ranking. Where M ≦ N, e.g., N =5, M = 3.
In one possible embodiment, obtaining at least one benchmarking condition version comprises:
and if the benchmark working condition version does not reach the learning target after being inferred by the machine learning model, taking the first T working condition versions with the highest priority ranking as at least one benchmark working condition version.
Specifically, if the benchmarking working condition versions do not reach the preset target values after being inferred by the machine learning model, the benchmarking working condition versions which do not reach the target values cannot be optimized through model training, the benchmarking working condition versions which complete machine learning are directly sorted according to the standard reaching degree of the learning target, after a sorting list is obtained, the former T benchmarking working condition versions with the higher standard reaching degree of the learning target are determined to be at least one benchmarking working condition version, and T can be 3,5 or 2 and the like.
In one possible embodiment, the priority of the working condition version is determined according to the matching degree of the working condition version and the preset working condition version before and after the priority ranking.
Specifically, the method for sorting the multiple benchmarking working condition versions subjected to machine learning according to the standard reaching degree of the learning target includes that the machine learning model adjusts values of other process equipment parameters according to preset target parameters such as production time, finally obtains the matching degree of the actual value and the target value of the benchmarking working condition versions subjected to machine training, and sorts the multiple benchmarking working condition versions subjected to machine learning according to the matching degree.
Possibly, the priority ranking of the benchmark working condition versions can be completed according to single or multiple process parameters in the benchmark working condition versions, the content of the substance A can be determined as a product parameter with the highest priority for measuring the product quality, the content of the substance A carries out the priority ranking on the benchmark working condition versions, the benchmark working condition versions with the highest substance A quantity in all the working condition versions are selected, and the more excellent the design parameters are, the higher the priority ranking of the benchmark working condition versions is.
It can be seen that in the embodiment of the application, the marker post working condition versions completing machine learning are sorted according to different conditions, a plurality of marker post working condition versions which can be used for subsequent steps are screened out, the marker post working condition versions used for subsequent mass production verification steps are added, and the data of each version have parallel comparison objects before the final working condition version is output, so that the number of the working condition versions participating in verification is increased, a large number of process parameters are recorded, the refinement degree of production is improved, and the product quality is further improved.
S202: and generating a working condition benchmark value dividing card of each benchmark working condition version in at least one benchmark working condition version, wherein the working condition benchmark value dividing card is used for recording the design parameters of each benchmark working condition version.
In this embodiment, a corresponding working condition flagpole value scoring card is newly built for each flagpole working condition version, where the working condition flagpole value scoring card includes a product scoring card, a component scoring card, and a process equipment scoring card. As shown in fig. 3A, fig. 3A is a schematic diagram of a product score card provided in an embodiment of the present application, where the product score card is used to record multiple design parameter indexes, and these product indexes will reflect product quality, so as to reflect performance and quality of production process equipment and intermediate steps in actual production, where an upper specification limit USL and a lower specification limit LSL of a product parameter are set and recorded in a working condition target score card when a parameter learning target value is set when a new learning task is created on the target, and a product parameter process capability index CPK is calculated by a parameter mean value, a parameter standard deviation, and upper and lower parameter specification limits; FIG. 3B is a schematic diagram of a component score card for recording a plurality of component parameter indicators, wherein the component is a characteristic parameter of a supplier's incoming material or an intermediate product generated in a production process, which may occur in a benchmarking version, and is used for reflecting the degree of excellence of the supplier's incoming material, the intermediate product and the intermediate step; as shown in fig. 3C, fig. 3C is a schematic diagram of a score card for process equipment according to an embodiment of the present disclosure; the technical equipment scoring card is used for recording parameters such as using equipment of a product, using amount of raw materials, using environment of the raw materials and the like, and the calculating method of the USL of the upper specification limit of the parameters in the component scoring card and the technical equipment scoring card is determined to be the sum of the target value of the parameters and the A-time standard deviation in the learning stage by the technical equipment scoring card; the calculation method of the lower specification limit LSL of the parameter is the difference between the target value of the parameter and A times of standard deviation, wherein A is a positive number which is larger than zero and can be 1, 2.5,4 and the like, and the parameter process capability index CPK is calculated by a parameter mean value, a parameter standard deviation and the upper and lower specification limits of the parameter.
S203: and performing volume production verification according to each benchmark working condition version in at least one benchmark working condition version, and updating the working condition benchmark value dividing card of each benchmark working condition version according to design parameters of the volume production verification.
In this embodiment, the mass production verification according to each of the at least one benchmarking working condition versions here refers to: according to the production method and the actual input generation of the process parameters of the benchmarking working condition version record, batch limitation of mass production verification can be set at the moment, and the preset value of the batch limitation can be adjusted according to the actual mass production verification requirement. For example, after three benchmarking working condition versions which can be used for mass production verification are obtained, 30 batches of actual production are arranged for each benchmarking working condition version, product parameters of a final product are collected after each production is finished, and a product scoring card in a working condition benchmarking value scoring card of each benchmarking working condition version is updated through the collected product parameters.
S204: and evaluating the usability of each benchmark working condition version according to the working condition benchmark value dividing card of each benchmark working condition version, and determining that the mass production version in at least one benchmark working condition version is put into mass production.
In the embodiment of the application, the obtained working condition versions of the marking pole can be theoretically applied to production, but the working condition versions most suitable for mass production are selected from the working condition versions, so that the availability of the scoring condition of the corresponding working condition marking pole value dividing card to each working condition version of the marking pole can be determined according to the usability of the working condition marking pole value dividing card when the working condition versions of the marking pole are applied to mass production verification, and finally the selected mass production version for the mass production stage is determined.
In one possible embodiment, evaluating the availability of each benchmarking job version according to the benchmarking value score card of each benchmarking job version includes: updating the batch data of the product parameters of the corresponding benchmark working condition version by the working condition benchmark value dividing card of each benchmark working condition version according to the volume production verification result; acquiring upper and lower limits of product parameter specifications of a dividing card by a working condition benchmark value; calculating the mean value and standard deviation of the product parameters according to the batch data of the product parameters; calculating to obtain a process capability index CPK of each benchmark working condition version product parameter according to the product parameter mean value, the product parameter standard deviation and the product parameter specification upper and lower limits; and evaluating the usability of each benchmark working condition version according to the CPK value.
Specifically, after each benchmark working condition version completes the actual production of one batch, the product scoring card updates the batch data of the benchmark working condition version, and calculates the parameter mean value and the product parameter standard deviation of the product parameters of the working condition version; calculating the process capability index CPK of the batch of product parameters through the product parameter mean value, the product parameter standard deviation and the product parameter specification upper and lower limits and recording the process capability index CPK in a product score card, wherein the product parameter mean value mu is the mean value of data generated by a certain parameter in all batches produced at present; the standard deviation sigma of the product parameters is the standard deviation of the product parameters of all batches; the upper limit of the product parameter specification is that the benchmark working condition version is set and recorded in the working condition benchmark scorecard when a learning target is set when a new learning target is established, and can be directly called; the method comprises the steps that a process capability index CPK = min { Cpl, Cpu }, wherein Cpl = (mu-LSL)/3 sigma, Cpu = (USL-mu)/3 sigma obtains all the batch CPK mean values recorded as CPK data of the standard staff working condition version after all batches of the standard staff working condition version are produced, the availability of each standard staff working condition version is evaluated according to the CPK values, and the standard staff working condition version in the mass production stage is selected according to the evaluation result and used in actual production. The upper and lower limits of the parameter specification can also be used for eliminating error data according to the upper and lower limits of the parameter specification, the obtained design parameters only fluctuate between the upper and lower limits of the specification in the version which is determined by input elements of production and can be subjected to mass production verification, and the error design parameters which are not in the range of the upper and lower limits of the specification can be generated under the conditions of possible human errors or machine faults, and the like, under the condition, the production batch is marked as an error batch, and the error parameters of the production batch are eliminated.
In a possible embodiment, the method for updating the working condition benchmark value score sub-card according to the design parameters of the benchmark working condition further comprises the following steps: performing cluster analysis on the collected design parameters through a DBSCAN (Density-Based Spatial Clustering of Applications with Noise, Density-Based Clustering method); dividing the same production condition parameter into a plurality of clusters according to a preset parameter; and taking the cluster with the largest number of parameters as a design parameter to be recorded into a working condition benchmark value dividing card, and defining other clusters as noise and eliminating the noise.
Specifically, the production conditions of each production batch cannot be completely consistent in the actual mass production process, the obtained design parameters have slight differences, if unexpected conditions such as operator error, sudden change of production environment, production equipment failure and the like occur, abnormal production conditions can be caused, and the obtained design parameters have larger differences from normal values. The number of production batches for mass production verification is not large, the density of the obtained parameter sample set is uniform, the difference of clustering distances is not large, and the accidental conditions such as equipment faults, intermediate product abnormity and the like can be avoided through a DBSCAN algorithm, so that the design parameters of the working condition version of the benchmarks in the production batch are excluded, and only the normal design parameters are recorded.
In the embodiment of the application, the DBSCAN algorithm is more suitable for processing the working condition version of the benchmark, abnormal data belonging to outliers can be accurately distinguished under the condition that the data needing to be processed is not large, the abnormal data is excluded, the reliability of the data recorded by the working condition benchmark value dividing card is improved, and the problem of inaccurate evaluation result caused by the abnormal data is reduced.
In one possible embodiment, evaluating the availability of each benchmarking job version according to the product parameter CPK value includes: if the product parameter CPK of a first target working condition version in at least one benchmark working condition version is not larger than a first preset value, determining that the first target working condition version is a mass production unavailable version; if the product parameter CPK of a second target working condition version in at least one benchmarking working condition version is larger than a first preset value, determining that the second target working condition version is a mass production available version; and if the product parameter CPK of the third target working condition version in the at least one benchmark working condition version is greater than the second preset value, determining that the current product is the optimal version for mass production.
Specifically, as shown in table 1, the CPK value herein specifically refers to a CPK value of a product parameter, the CPK preset value of the product parameter may be determined according to actual requirements, the first preset value may be set to 1.0, the second preset value may be set to 1.33, the process capability index CPK refers to a degree that the process capability meets the product quality standard requirements (specification range, etc.), and is also called a process capability index, which refers to an actual processing capability of a process in a control state (steady state) within a certain time. When the CPK of at least one product parameter of the benchmarking procedure version is not more than 1.0, the process capability of the benchmarking procedure version needs to be improved, and if the production needs to be stopped and stopped seriously, the benchmarking procedure version is determined as an unavailable version for mass production; when the CPK of all the product parameters of the benchmarking procedure version is greater than 1.0 and at least one product parameter CPK is less than 1.33, the process capability of the benchmarking procedure version belongs to a normal range, and the benchmarking procedure version is a mass production available version; and if the CPK values of all the product parameters of the third target working condition version in the at least one benchmark working condition version are greater than 1.33, the process capability of the benchmark working procedure version is good, and the benchmark working procedure version is determined to be the optimal mass production version.
TABLE 1
CPK value of product parameter Evaluation results
CPK of at least one product parameter<1.0 Mass production unusable edition
All product parameters have a CPK greater than 1.0 and at least one product parameter has a CPK less than 1.33 Mass production of usable versions
The CPK value of all product parameters is more than 1.33 Best version of mass production
In one possible embodiment, determining a mass production version of the at least one benchmarking operating version comprises: if the fact that the at least one benchmark working condition version comprises the only mass production optimal version is determined, the only mass production optimal version is determined to be the mass production version in the at least one benchmark working condition version; and/or if at least one benchmark working condition version is determined to comprise a plurality of mass production optimal versions, determining sequencing according to the parameter priority and parameter value corresponding to each of the plurality of mass production optimal versions in the production data table, and determining the mass production versions according to the sequencing result, wherein the production data table is composed of design parameters in the working condition benchmark value dividing card; and/or if the fact that the at least one benchmarking working condition version does not comprise the only optimal mass production version and comprises at least one available mass production version is determined, determining sequencing according to the parameter priority and the parameter value corresponding to each of the plurality of available mass production versions in the production data table, and determining the mass production versions according to the sequencing result.
Specifically, the CPK calculation results of the product parameters of the multiple benchmarking working condition versions subjected to mass production verification may have different situations, and if the CPK of the product parameter of only one benchmarking working condition version in all the multiple benchmarking working condition versions subjected to mass production verification exceeds 1.33, the benchmarking working condition version can be determined to be the final mass production version; if the CPK of the product parameters of more than one benchmarking working condition version in all the benchmarking working condition versions subjected to mass production verification exceeds 1.3, comparing the CPKs of the product parameters of the benchmarking working condition versions, sequencing the product parameters with high, medium and low priorities, setting the priorities of the product parameters according to actual requirements, sequencing the versions according to the CPK value of the product parameter with the highest priority, and determining the first benchmarking working condition version in the sequence as the final mass production version. If only mass production available versions with all the product parameters of which the CPK is greater than 1.0 and at least one product parameter of which the CPK is less than 1.33 exist in all the benchmarking working condition versions, similarly, the sequencing can be determined according to the priority of the product parameter corresponding to each of the mass production available versions in the production data table and the CPK value of each product parameter, and the final mass production version is determined according to the sequencing result.
It can be seen that in the embodiment of the application, the mass production verification is performed on the multiple working condition versions, multiple design parameters obtained by mass production of multiple mass production batches are recorded in the working condition benchmark value division card, the versions are determined according to the corresponding training results under each working condition, and the working condition version most suitable for mass production is recommended according to the version type, so that the production quality has a scientific judgment basis.
S205: and dynamically updating the mass production version of the working condition of the benchmark to be put into mass production through a sampling filtering algorithm according to the design parameters generated by the working condition version of the benchmark in the mass production stage.
After the mass production version of the benchmark working condition is actually put into production in the embodiment of the application, the mass production version of the benchmark working condition is dynamically updated through a sampling filtering algorithm. The sampling filtering algorithm here includes: acquiring product scoring cards of the volume production versions of the benchmark working conditions of X batches in the actual volume production stage, and calculating the CPK values of the product parameters of the volume production versions of the benchmark working conditions of X batches; when the CPK values of all product parameters are larger than a preset threshold value, determining upper and lower parameter specification limits according to product score cards of mass production versions of benchmarking working conditions of X batches; the specification upper and lower limits are used, if a product parameter obtained from a certain batch of mass production in the equivalent production stage exceeds the specification upper and lower limits, it can be determined that an unexpected situation such as equipment abnormality or intermediate product abnormality may exist in the production process, and the product parameter obtained from the production exceeds the specification upper and lower limits, so that the product of the batch of mass production is excluded, the mass production version of the benchmarking working condition is updated, the specification upper and lower limits of the corresponding process parameter and component parameter are calculated according to the process equipment score card and the component score card corresponding to the filtered sample, and the process quality control is performed by using the specification upper and lower limits of the parameter, where the calculation method of the CPK value may refer to the relevant content of step S204, which is not repeated herein, where X is a positive integer, such as 20,30, and the preset threshold value may be 1.33, 1.0, and the like.
In a possible embodiment, if the CPK values of X batches of the volume production version of the benchmarking working condition do not exceed the preset threshold, the CPK values of the other X batches of the product parameters are calculated, if the CPK values of the other X batches of the product do not exceed the preset threshold, the upper and lower specification limits are calculated according to the product score cards of the volume production versions of all the current benchmarking working conditions, and the volume production version of the benchmarking working condition is updated according to the obtained upper and lower specification limits.
In the embodiment of the application, the product score cards of the volume production versions of the benchmarking working conditions of the X volume production batches with the CPK of the product parameters larger than the preset threshold are collected, the obtained specification upper and lower limits are used as filtering conditions, the process equipment score cards corresponding to the filtered samples and the process equipment parameters and the specification upper and lower limits of the component parameters corresponding to the component score cards are used for process quality control, equipment abnormity and middle product abnormity are timely found, response improvement measures are taken, and the yield of product production is guaranteed.
By implementing the method of the embodiment of the invention, the mass production verification is carried out on a plurality of working condition versions, the working condition benchmark value dividing card is updated according to the design parameters obtained by the mass production verification, the product parameter CPK value of each working condition version is calculated, the version determination is carried out on the corresponding training result under each working condition, the working condition version of the mass production version most suitable for mass production is recommended, and the production quality has a scientific judgment basis. The optimal mass production working condition version is selected by the method for verifying the mass production of the working condition versions, the production process parameters are guaranteed to be set in the optimal state all the time, the mass production versions of the benchmarking working conditions are dynamically updated through a sampling filtering algorithm, the quality of mass-produced products is controlled, and the optimal yield of the products is guaranteed.
Based on the above description of the configuration method embodiment, the present application further provides a multi-production-condition-based production control apparatus 400, and the multi-production-condition-based production control apparatus 400 may be a computer program (including program code) running in a terminal. The multi-production-condition-based production control apparatus 400 may perform the methods shown in fig. 1, 2, 3A, 3B, and 3C. Referring to fig. 4, the apparatus includes:
the acquisition unit 401: the system comprises a machine learning model, a benchmark version module and a benchmark version module, wherein the benchmark version module is used for acquiring at least one benchmark working condition version;
the recording unit 402: the working condition benchmark value dividing card is used for recording design parameters of each benchmark working condition version;
performing volume production verification according to each benchmark working condition version in at least one benchmark working condition version, and updating the working condition benchmark value dividing card of each benchmark working condition version according to design parameters of the volume production verification;
the evaluation unit 403: and the system is used for evaluating the usability of each benchmark working condition version according to the working condition benchmark value dividing card of each benchmark working condition version and determining the mass production version in at least one benchmark working condition version.
In a possible embodiment, in obtaining the benchmarking working condition version, the obtaining unit is further specifically configured to execute the following steps:
acquiring a first working condition version, wherein the first working condition version is one working condition version with the highest priority rank in working condition versions which reach learning targets after being inferred by a machine learning model; acquiring a second working condition version, wherein the second working condition version is M working condition versions randomly selected from N working condition versions with the highest priority ranking, except the working condition version with the highest priority ranking, in the working condition versions which reach the learning target after being inferred by the machine learning model, and N is more than or equal to M; and taking the first working condition version and the second working condition version as at least one benchmark working condition version.
In a possible embodiment, in obtaining the benchmarking working condition version, the obtaining unit is further specifically configured to execute the following steps:
and if the benchmark working condition version does not reach the learning target after being inferred by the machine learning model, taking the first T working condition versions with the highest priority ranking as at least one benchmark working condition version.
In one possible embodiment, the priority ranking of the condition versions is determined according to the condition that the design parameters in the condition versions reach the target values.
In one possible embodiment, the recording unit is further configured to execute instructions for, in evaluating the availability of each benchmarking job version based on the benchmarking value scorecard for each benchmarking job version:
updating the batch data of the product parameters of the corresponding benchmark working condition version by the working condition benchmark value dividing card of each benchmark working condition version according to the volume production verification result; acquiring upper and lower limits of product parameter specifications of a dividing card by a working condition benchmark value; calculating the mean value and standard deviation of the product parameters according to the batch data of the product parameters; calculating to obtain a process capability index CPK of each benchmark working condition version product parameter according to the product parameter mean value, the product parameter standard deviation and the product parameter specification upper and lower limits; and evaluating the usability of each benchmark working condition version according to the CPK value.
In one possible embodiment, the evaluation unit is further configured to execute the following steps in evaluating the availability of each benchmarking version based on the CPK values of the product parameters:
if the CPK of the product parameter of the first target working condition version in the at least one benchmark working condition version is not larger than a first preset value, determining that the first target working condition version is a mass production unavailable version; if the CPK of the product parameter of the second target working condition version in the at least one benchmark working condition version is larger than the first preset value, determining that the second target working condition version is a mass production available version; and if the CPK of the product parameter of the third target working condition version in the at least one benchmark working condition version is greater than a second preset value, determining that the current product is the optimal version for mass production.
In a possible embodiment, the evaluation unit is further configured to execute the following steps in determining a mass production version of the at least one benchmarking operating condition version:
if the fact that the at least one benchmark working condition version comprises the only mass production optimal version is determined, the only mass production optimal version is determined to be the mass production version in the at least one benchmark working condition version; and/or if at least one benchmark working condition version is determined to comprise a plurality of mass production optimal versions, determining sequencing according to the parameter priority and parameter value corresponding to each of the plurality of mass production optimal versions in the production data table, and determining the mass production versions according to the sequencing result, wherein the production data table is composed of design parameters in the working condition benchmark value dividing card; and/or if the fact that the at least one benchmarking working condition version does not comprise the only optimal mass production version and comprises at least one available mass production version is determined, determining sequencing according to the parameter priority and the parameter value corresponding to each of the plurality of available mass production versions in the production data table, and determining the mass production versions according to the sequencing result.
Based on the description of the method embodiment and the apparatus embodiment, please refer to fig. 5, fig. 5 is a schematic structural diagram of an electronic device 500 provided in an embodiment of the present application, where the electronic device 500 described in this embodiment, as shown in fig. 5, the electronic device 500 includes a processor 501, a memory 502, a communication interface 503, and one or more programs, and the one or more programs are stored in the memory in the form of application program codes and configured to be executed by the processor, and in an embodiment of the present application, the programs include instructions for performing the following steps:
obtaining at least one working condition version of the marker post, wherein the at least one working condition version of the marker post is a working condition version which is inferred by a machine learning model;
generating a working condition benchmark value dividing card of each benchmark working condition version in at least one benchmark working condition version, wherein the working condition benchmark value dividing card is used for recording design parameters of each benchmark working condition version;
performing volume production verification according to each benchmark working condition version in at least one benchmark working condition version, and updating the working condition benchmark value dividing card of each benchmark working condition version according to design parameters of the volume production verification;
and evaluating the usability of each benchmark working condition version according to the working condition benchmark value dividing card of each benchmark working condition version, and determining the mass production version in at least one benchmark working condition version.
In one possible embodiment, obtaining at least one benchmarking condition version comprises:
acquiring a first working condition version, wherein the first working condition version is one working condition version with the highest priority rank in working condition versions which reach learning targets after being inferred by a machine learning model; acquiring a second working condition version, wherein the second working condition version is M working condition versions randomly selected from N working condition versions with the highest priority ranking, except the working condition version with the highest priority ranking, in the working condition versions which reach the learning target after being inferred by the machine learning model, and N is more than or equal to M; and taking the first working condition version and the second working condition version as at least one benchmark working condition version.
In one possible embodiment, obtaining at least one benchmarking condition version comprises:
and if the benchmark working condition version does not reach the learning target after being inferred by the machine learning model, taking the first T working condition versions with the highest priority ranking as at least one benchmark working condition version.
In one possible embodiment, the priority ranking of the condition versions is determined according to the condition that the design parameters in the condition versions reach the target values.
In one possible embodiment, evaluating the availability of each benchmarking job version according to the benchmarking value score card of each benchmarking job version includes: updating the batch data of the product parameters of the corresponding benchmark working condition version by the working condition benchmark value dividing card of each benchmark working condition version according to the volume production verification result; acquiring upper and lower limits of product parameter specifications of a dividing card by a working condition benchmark value; calculating the mean value and standard deviation of the product parameters according to the batch data of the product parameters; calculating to obtain a process capability index CPK of each benchmark working condition version product parameter according to the product parameter mean value, the product parameter standard deviation and the product parameter specification upper and lower limits; and evaluating the usability of each benchmark working condition version according to the CPK value.
In one possible embodiment, evaluating the availability of each benchmarking version based on the CPK values of the product parameters includes: if the CPK of the product parameter of the first target working condition version in the at least one benchmark working condition version is not larger than a first preset value, determining that the first target working condition version is a mass production unavailable version; if the CPK of the product parameter of the second target working condition version in the at least one benchmark working condition version is larger than the first preset value, determining that the second target working condition version is a mass production available version; and if the CPK of the product parameter of the third target working condition version in the at least one benchmark working condition version is greater than a second preset value, determining that the current product is the optimal version for mass production.
In one possible embodiment, determining a mass production version of the at least one benchmarking operating version comprises: if the fact that the at least one benchmark working condition version comprises the only mass production optimal version is determined, the only mass production optimal version is determined to be the mass production version in the at least one benchmark working condition version; and/or if at least one benchmark working condition version is determined to comprise a plurality of mass production optimal versions, determining sequencing according to the parameter priority and parameter value corresponding to each of the plurality of mass production optimal versions in the production data table, and determining the mass production versions according to the sequencing result, wherein the production data table is composed of design parameters in the working condition benchmark value dividing card; and/or if the fact that the at least one benchmarking working condition version does not comprise the only optimal mass production version and comprises at least one available mass production version is determined, determining sequencing according to the parameter priority and the parameter value corresponding to each of the plurality of available mass production versions in the production data table, and determining the mass production versions according to the sequencing result.
Illustratively, the electronic device may include, but is not limited to, a processor, a memory, a communication interface, and one or more programs, and may further include a memory, a power supply, an application client module, and the like. It will be appreciated by those skilled in the art that the schematic diagrams are merely examples of an electronic device and are not limiting of an electronic device and may include more or fewer components than those shown, or some components in combination, or different components.
An embodiment of the present application further provides a computer storage medium (Memory), which is a Memory device in an information processing device or an information transmitting device or an information receiving device, and is used to store programs and data. It is understood that the computer storage medium herein may include a built-in storage medium in the terminal, and may also include an extended storage medium supported by the terminal. The computer storage medium provides a storage space that stores an operating system of the terminal. Also stored in the memory space are one or more instructions, which may be one or more computer programs (including program code), suitable for loading and execution by the processor. The computer storage medium may be a high-speed RAM Memory, or may be a Non-volatile Memory (Non-volatile Memory), such as at least one disk Memory; and optionally at least one computer storage medium located remotely from the processor. In one embodiment, one or more instructions stored in a computer storage medium may be loaded and executed by a processor to perform the corresponding steps of the above-described multi-production condition based production control method.
The foregoing detailed description of the embodiments of the present application has been presented to illustrate the principles and implementations of the present application, and the above description of the embodiments is only provided to help understand the method and the core concept of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims (10)

1. A production control method based on multiple production working conditions is characterized by comprising the following steps:
obtaining at least one working condition version of the benchmark, wherein the at least one working condition version of the benchmark is a working condition version which is inferred by a machine learning model;
generating a working condition benchmark value score dividing card of each benchmark working condition version in the at least one benchmark working condition version, wherein the working condition benchmark value score dividing card is used for recording design parameters of each benchmark working condition version;
performing volume production verification according to each benchmark working condition version in the at least one benchmark working condition version, and updating the working condition benchmark value dividing card of each benchmark working condition version according to design parameters of the volume production verification;
and evaluating the usability of each benchmark working condition version according to the working condition benchmark value dividing card of each benchmark working condition version, and determining the mass production version in at least one benchmark working condition version.
2. The method of claim 1, wherein said obtaining at least one benchmarking version comprises:
acquiring a first working condition version, wherein the first working condition version is one working condition version with the highest priority rank in the working condition versions which reach the learning target through the machine learning model inference;
acquiring a second working condition version, wherein the second working condition version is M working condition versions randomly selected from N working condition versions with the highest priority ranking, except the working condition version with the highest priority ranking, in the working condition versions which reach the learning target through the machine learning model inference, and N is more than or equal to M;
and taking the first working condition version and the second working condition version as the at least one benchmark working condition version.
3. The method of claim 1, wherein said obtaining at least one benchmarking version comprises:
and if the benchmark working condition version does not reach the learning target after being inferred by the machine learning model, taking the T working condition versions with the highest priority ranking as the at least one benchmark working condition version.
4. The method according to claim 2 or 3, wherein the priority ranking of the condition versions is determined according to the condition that the design parameters in the condition versions reach the target values.
5. The method of claim 1, wherein evaluating the availability of each benchmarking version according to the benchmarking value scorecard for each benchmarking version comprises:
the working condition benchmark value dividing card of each benchmark working condition version updates the batch data of the product parameters of the corresponding benchmark working condition version according to the volume production verification result;
acquiring upper and lower limits of product parameter specifications of the dividing card of the working condition benchmark value;
calculating a product parameter mean value and a product parameter standard deviation according to the batch data of the product parameters;
calculating to obtain a process capability index CPK of the product parameter of each benchmark working condition version according to the product parameter mean value, the product parameter standard deviation and the upper and lower limits of the product parameter specification;
and evaluating the usability of each benchmarking working condition version according to the CPK value of the product parameter.
6. The method of claim 5, wherein evaluating the availability of each benchmarking version according to the CPK value of the product parameter comprises:
if the CPK of the product parameter of a first target working condition version in the at least one benchmark working condition version is not larger than a first preset value, determining that the first target working condition version is a mass production unavailable version;
if the CPK of the product parameter of a second target working condition version in the at least one benchmarking working condition version is larger than a first preset value, determining that the second target working condition version is a mass production available version;
and if the CPK of the product parameter of the third target working condition version in the at least one benchmark working condition version is greater than a second preset value, determining that the current product is the optimal version for mass production.
7. The method of claim 6, wherein said determining a production version of said at least one benchmarking operating version comprises:
if the fact that the at least one benchmark working condition version comprises the only optimal mass production version is determined, determining the only optimal mass production version as the mass production version in the at least one benchmark working condition version; and/or
If the fact that the at least one benchmark working condition version comprises a plurality of mass production optimal versions is determined, determining sequencing according to the parameter priority and the parameter value corresponding to each of the plurality of mass production optimal versions in a production data table, and determining the mass production versions according to sequencing results, wherein the production data table is composed of design parameters in the working condition benchmark value dividing card; and/or
And if the at least one benchmarking working condition version does not comprise the unique optimal mass production version and comprises at least one available mass production version, determining a sequence according to the parameter priority and the parameter value corresponding to each of the plurality of available mass production versions in the production data table, and determining the mass production versions according to the sequencing result.
8. A production control apparatus based on multiple production conditions, the apparatus being configured to execute the production control method based on multiple production conditions, characterized by comprising:
an acquisition unit: the system comprises a machine learning model, a benchmark working condition version acquisition module and a benchmark working condition version acquisition module, wherein the benchmark working condition version acquisition module is used for acquiring at least one benchmark working condition version which is a working condition version subjected to inference adjustment by the machine learning model and ending a learning stage;
a recording unit: the working condition benchmark score dividing card is used for generating a working condition benchmark score dividing card of each benchmark working condition version in the at least one benchmark working condition version, and the working condition benchmark score dividing card is used for recording design parameters of each benchmark working condition version;
performing volume production verification according to each benchmark working condition version in the at least one benchmark working condition version, and updating the working condition benchmark value dividing card of each benchmark working condition version according to design parameters of the volume production verification;
an evaluation unit: and the system is used for evaluating the usability of each benchmark working condition version according to the working condition benchmark value dividing card of each benchmark working condition version and determining the mass production version in at least one benchmark working condition version.
9. An electronic device comprising a processor, a memory, a communication interface, and one or more programs stored in the memory and configured to be executed by the processor, the programs comprising instructions for performing the steps in the method of any of claims 1-7.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program causes a computer to perform the method according to any one of claims 1-7.
CN202210160309.1A 2022-02-22 2022-02-22 Production control method and device based on multiple production working conditions Active CN114219461B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202210160309.1A CN114219461B (en) 2022-02-22 2022-02-22 Production control method and device based on multiple production working conditions
CN202210675216.2A CN115130985A (en) 2022-02-22 2022-02-22 Production control method and related apparatus, storage medium, and program product

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210160309.1A CN114219461B (en) 2022-02-22 2022-02-22 Production control method and device based on multiple production working conditions

Related Child Applications (1)

Application Number Title Priority Date Filing Date
CN202210675216.2A Division CN115130985A (en) 2022-02-22 2022-02-22 Production control method and related apparatus, storage medium, and program product

Publications (2)

Publication Number Publication Date
CN114219461A true CN114219461A (en) 2022-03-22
CN114219461B CN114219461B (en) 2022-05-06

Family

ID=80709228

Family Applications (2)

Application Number Title Priority Date Filing Date
CN202210160309.1A Active CN114219461B (en) 2022-02-22 2022-02-22 Production control method and device based on multiple production working conditions
CN202210675216.2A Pending CN115130985A (en) 2022-02-22 2022-02-22 Production control method and related apparatus, storage medium, and program product

Family Applications After (1)

Application Number Title Priority Date Filing Date
CN202210675216.2A Pending CN115130985A (en) 2022-02-22 2022-02-22 Production control method and related apparatus, storage medium, and program product

Country Status (1)

Country Link
CN (2) CN114219461B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114384885A (en) * 2022-03-23 2022-04-22 希望知舟技术(深圳)有限公司 Process parameter adjusting method, device, equipment and medium based on abnormal working conditions

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004206955A (en) * 2002-12-24 2004-07-22 Matsushita Electric Ind Co Ltd Production line and its construction method
CN111027744A (en) * 2019-11-06 2020-04-17 上海长庚信息技术股份有限公司 Real-time benchmarking optimization method for multi-level power plant
CN113780287A (en) * 2021-07-30 2021-12-10 武汉中海庭数据技术有限公司 Optimal selection method and system for multi-depth learning model
CN114067350A (en) * 2020-07-31 2022-02-18 伊姆西Ip控股有限责任公司 Model updating method, device and computer program product

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004206955A (en) * 2002-12-24 2004-07-22 Matsushita Electric Ind Co Ltd Production line and its construction method
CN111027744A (en) * 2019-11-06 2020-04-17 上海长庚信息技术股份有限公司 Real-time benchmarking optimization method for multi-level power plant
CN114067350A (en) * 2020-07-31 2022-02-18 伊姆西Ip控股有限责任公司 Model updating method, device and computer program product
CN113780287A (en) * 2021-07-30 2021-12-10 武汉中海庭数据技术有限公司 Optimal selection method and system for multi-depth learning model

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
傅骏等: "数值模拟技术在熔模铸造生产中的应用实践", 《铸造技术》 *
张磊等: "翻转臂支架的结构优化与铸造工艺开发", 《铸造设备与工艺》 *
温兴化等: "基于聚类分析的墨量预置优化方法", 《数码世界》 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114384885A (en) * 2022-03-23 2022-04-22 希望知舟技术(深圳)有限公司 Process parameter adjusting method, device, equipment and medium based on abnormal working conditions

Also Published As

Publication number Publication date
CN114219461B (en) 2022-05-06
CN115130985A (en) 2022-09-30

Similar Documents

Publication Publication Date Title
US11170332B2 (en) Data analysis system and apparatus for analyzing manufacturing defects based on key performance indicators
CN113655768B (en) Assembly yield control method, equipment and computer readable storage medium
CN114219461B (en) Production control method and device based on multiple production working conditions
US20090234482A1 (en) System, program and method for calculating equipment load factor
US11625029B2 (en) Manufacturing condition setting automating apparatus and method
CN115373370A (en) Method and system for monitoring running state of programmable controller
CN115268406A (en) Single chip microcomputer chip testing method and system, computer equipment and storage medium
CN114140034B (en) Quality monitoring method based on working conditions and related device
US8768499B2 (en) Production index information generating device, program therefore, and production information generating method
CN115130737A (en) Machine learning method based on working condition, related device and medium program product
CN117171896A (en) Method and system for optimizing machining of input shaft of automobile steering gear
CN101142559A (en) Monitoring computer-controlled processes
CN114781948B (en) Data processing method and related device for determining working quality of staff
CN112527610A (en) Method and device for monitoring operation state of equipment
CN111243647B (en) Flash memory programming parameter determination method and device, electronic equipment and storage medium
CN113836826A (en) Key parameter determination method and device, electronic device and storage medium
CN115147236A (en) Processing method, processing device and electronic equipment
CN109492913B (en) Modular risk prediction method and device for power distribution terminal and storable medium
CN102902838A (en) Trend-based target setting method and system for process control
CN113627755A (en) Test method, device, equipment and storage medium for intelligent terminal factory
JP2017059016A (en) Component manufacturing lot selecting device, manufacturing plan formulation system, component manufacturing lot selecting method, and program
Wang et al. Requirements management for the incremental development model
CN114742332B (en) Productivity analysis method and productivity analysis system
CN114298561B (en) Method and device for generating equipment production conditions, electronic equipment and storage medium
CN117236682B (en) Industrial automation control method and system

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
GR01 Patent grant
GR01 Patent grant