CN116307526B - Intelligent factory productivity analysis system based on mathematical model - Google Patents
Intelligent factory productivity analysis system based on mathematical model Download PDFInfo
- Publication number
- CN116307526B CN116307526B CN202310128617.0A CN202310128617A CN116307526B CN 116307526 B CN116307526 B CN 116307526B CN 202310128617 A CN202310128617 A CN 202310128617A CN 116307526 B CN116307526 B CN 116307526B
- Authority
- CN
- China
- Prior art keywords
- production
- capacity
- type
- function
- feature
- 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.)
- Active
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 107
- 238000013178 mathematical model Methods 0.000 title claims abstract description 18
- 238000004519 manufacturing process Methods 0.000 claims abstract description 249
- 238000000034 method Methods 0.000 claims abstract description 11
- 238000012937 correction Methods 0.000 claims description 21
- 230000008569 process Effects 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 abstract description 2
- 230000008901 benefit Effects 0.000 abstract description 2
- 238000010438 heat treatment Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000009776 industrial production Methods 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Manufacturing & Machinery (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a mathematical model-based intelligent factory productivity analysis system, which comprises a local service subsystem, an inter-factory service subsystem, an element foundation subsystem, a productivity analysis subsystem and a plurality of production terminals, wherein the local service subsystem is used for providing a factory to a factory; the method has the advantages that the relation between each production element and the productivity can be analyzed in a targeted manner, so that a producer can conveniently acquire the information corresponding to the production element, the abnormal situation or the shortage situation of the production element under the productivity task can be found in time, the producer is reminded of taking precautions or preparing in advance, the analysis of the production situation of lack of historical data introduces two dimensions of reference macroscopic dimension and actual inter-factory relation data, and the production element is analyzed, and by the analysis mode, the accurate result can still be obtained under the condition of insufficient local data.
Description
Technical Field
The application relates to the field of intelligent factories, in particular to an intelligent factory productivity analysis system based on a mathematical model.
Background
At present, along with the popularization of information technology, data, network, communication, analysis and processing technologies are increasingly applied to industrial production processes, multi-dimension, large amount of data in the industrial production processes are assisted to be collected, processed and analyzed, meanwhile, intelligent equipment is matched, an intelligent factory production system based on industrial Internet of things is disclosed for completing the production processes, for example, patent with publication No. CN113867302A, production data are collected through Internet of things and are implanted into various application modules to process the collected production data, and auxiliary data and information support for data analysis, processing and decision making are provided for each link of the production through storage of the production data, analysis, processing and decision making of factories are released from the data level, but in the application level, as the intelligent factory belongs to the emerging field, the PLARD system of the intelligent factory is disclosed by the patent with the publication number of CN108038605B, the optimal production scheduling strategy is obtained by calculating according to the process data of the production process, and the production equipment in the production process is scheduled, so that the intelligent management of the intelligent factory is truly realized, the production benefit of the intelligent factory can be improved, the production schedule is scheduled according to the production process through the optimal production scheduling strategy, thus, the configuration of the production elements under different production tasks is realized, while the optimal configuration of the production resources can be realized in the current mode, the estimated quantity depends on local historical data, and the following two cases can be faced with deviation: 1. and (2) estimating the effectiveness of the new production element, and estimating the estimated change of the influence of time on the production element, wherein the equipment is taken as an example, if no history data exists in the new equipment, the corresponding production function cannot be judged, or the history data of the old equipment is insufficient to judge the new situation.
Disclosure of Invention
In view of the above, it is an object of the present application to provide a mathematical model-based intelligent plant capacity analysis system.
In order to solve the technical problems, the technical scheme of the application is as follows: an intelligent factory productivity analysis system based on a mathematical model is characterized in that: the system comprises a local service subsystem, an inter-plant service subsystem, an element foundation subsystem, a productivity analysis subsystem and a plurality of production terminals;
the production terminal is provided with a plurality of acquisition units, and the acquisition units are used for acquiring production element data in the production process and generating capacity acquisition information according to the production element data and corresponding capacity;
the local service subsystem comprises a local configuration module, wherein the local configuration module is used for generating a corresponding local configuration model corresponding to each local terminal, the local configuration module acquires and processes the production element data to generate capacity history information, and the capacity history information is input into the local configuration model so that corresponding element values and capacity values are associated under each production element in the local configuration model;
the inter-plant service subsystem comprises an inter-plant association module, wherein the inter-plant association module is used for generating an element feature model corresponding to each production element feature, extracting corresponding element association data from capacity acquisition information according to the production element feature, and inputting the element association data into the element feature model so that corresponding element values and capacity values are associated under each production parameter in the element feature model;
the element foundation subsystem comprises a foundation configuration module, wherein the foundation configuration module is used for generating an element type model corresponding to each production element type, acquiring reference type data corresponding to the production element type from an external foundation database, and inputting the reference type data into the element type model so that corresponding element values and productivity values are associated with each production parameter in the element type model;
the capacity analysis subsystem comprises a request analysis module, a function calling module and an information analysis module; the request analysis module responds to the capacity analysis request of the corresponding production terminal and generates a plurality of capacity analysis tasks according to production elements in the capacity analysis request, and the function calling module calls a local capacity function, a characteristic capacity function and a type capacity function from the local configuration model, the element characteristic model and the element type model respectively according to the capacity analysis tasks; the information analysis module is configured with a capacity analysis algorithm, and the capacity analysis algorithm is thatThe method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Is the comprehensive productivity function corresponding to the production element with the number of n,local energy production function corresponding to production element with number nCount (n)/(l)>A feature capacity function corresponding to the element capacity feature with the number of m1, wherein the element capacity feature with the number of m1 corresponds to the production element with the number of n; />A type capacity function corresponding to an element capacity type with the number of m2, wherein the element capacity type with the number of m2 corresponds to a production element with the number of n; />Historical weight corresponding to production element with number n,/->Is the characteristic weight corresponding to the production element with the number of n>For the type weight corresponding to the production element with the number n, there is +.>。
Further, the local configuration module is provided with a local configuration policy, and the local configuration policy comprises
A1, establishing a historical capacity coordinate graph corresponding to each production element;
a2, extracting element values and productivity values corresponding to production elements from the productivity acquisition information, and determining corresponding production relation points in a historical productivity coordinate graph;
a3, fitting production relation points to generate a local productivity function if the corresponding historical productivity coordinate graph meets a first constraint condition; otherwise, waiting for the historical capacity coordinate graph to meet a first constraint condition;
and A4, constructing the local configuration model by taking the production elements as nodes and through each obtained local energy function.
Further, the inter-plant association module is provided with an inter-plant association policy, and the inter-plant association policy comprises
Step B1, establishing a characteristic capacity coordinate graph corresponding to each production element;
step B2, extracting element values and yield values from the element association data, determining corresponding element characteristic points in the characteristic yield coordinate graph, and establishing terminal stamp according to the production terminal to which the element characteristic points belong;
step B3, connecting element feature points with the same terminal marks to obtain element feature subfunctions;
step B4, dividing the element characteristic subfunctions into a plurality of element characteristic groups according to the shape similarity among the element characteristic subfunctions;
step B5, comparing production parameter items in the element feature groups, and endowing feature coefficients of each feature sub-function according to different production parameter items so as to obtain feature reference functions of the corresponding element feature groups;
step B6, constructing an element feature model by taking the element feature group as a node and through each feature reference function;
the function retrieval module comprises determining characteristic coefficients according to production parameters and bringing the characteristic coefficients into the characteristic reference function to obtain a characteristic energy production function.
Further, the basic configuration module is provided with a basic configuration strategy, and the basic configuration strategy comprises the following steps of
Step C1, constructing a type reference function according to the reference type data, wherein the type reference function has type coefficients with production parameters as indexes;
step C2, associating each type of reference function with a production element type, associating each type of reference function with at least one production element type, and dividing the production element types associated with the same type of reference function into the same element type group;
step C3, constructing an element type model by taking an element type group as a node through each type of reference function;
the function invoking module comprises determining a type coefficient according to the production parameters, and bringing the type coefficient into the type reference function to obtain the type productivity function.
Further, the production terminal is configured with an element analysis unit, the element analysis unit is configured with a load analysis table corresponding to each production element, the load analysis table comprises a plurality of element load ranges and corresponding load analysis information, and when the productivity value corresponding to the production element falls into the element load range, the corresponding load analysis information is output.
Further, the load analysis information includes element association functions, and when the corresponding load analysis information is output, the corresponding comprehensive capacity function is updated through the element association functions, and the load analysis information includesWherein->And reflecting the variation of the nth production element in the e-th load analysis information as an element association function corresponding to the e-th load analysis information.
Further, the capacity analysis algorithm corresponds to a weight constraint condition, wherein the weight constraint condition is as follows;
whereinFor the number of production relations corresponding to the production element, < >>For the number of element feature points corresponding to the production element, < >>Is->Element values corresponding to the respective production relationship points, < ->Is->Capacity corresponding to each production relationship point, < ->Is->Element values corresponding to the individual element feature points, < >>Is->Capacity value corresponding to each element feature point, < +.>Is->Production feature similarity between production terminal and target terminal corresponding to each element feature point>Is->Time of generation of each production relation point, +.>Is->Time of generation of individual element feature points, +.>For the current moment +.>Is a preset reference weight value, +.>The variables are corrected for locally.
Further, the production terminal is provided with an offset correction unit, the offset correction unit comprises an offset correction algorithm, and the offset correction algorithm is thatWherein->For local correction value, ++>For the actual capacity, +.>For the actual element value, +.>For the preset correction parameters, the local correction variables are updated by the deviation correction unit, and the method comprises the following steps of。
Further, the production elements correspond to different element parameter items, each element parameter item corresponds to different similarity weight values, the similarity sub-values of each element parameter item of the production terminal and the target terminal are compared through the production parameters, and the similarity sub-values are weighted according to the similarity weight values to calculate and obtain the production feature similarity.
Further, the reference weight value is determined in advance according to the data volume, the reliability value and the discrete degree corresponding to the type productivity function.
The technical effects of the application are mainly as follows: through the arrangement, the relation between each production element and the productivity can be analyzed in a targeted manner, so that a producer can conveniently acquire information corresponding to the production element, an abnormal condition or a shortage condition of the production element under the productivity task can be found in time, the producer is reminded of preventing or preparing in advance, the analysis of the production condition of lack of historical data introduces two dimensions of reference macroscopic dimension and actual inter-factory relation data, and the production element is analyzed, and in the analysis mode, a more accurate result can be still obtained under the condition of insufficient local data.
Drawings
Fig. 1: the application relates to a mathematical model-based intelligent factory productivity analysis system architecture schematic diagram;
fig. 2: the application relates to a local configuration strategy flow chart of an intelligent factory productivity analysis system based on a mathematical model;
fig. 3: the application relates to an inter-plant association strategy flow chart based on a mathematical model intelligent factory capacity analysis system;
fig. 4: the application discloses a basic configuration strategy flow chart of an intelligent factory capacity analysis system based on a mathematical model.
Reference numerals: 111. an acquisition unit; 110. a production terminal; 210. a local service subsystem; 211. a local configuration module; 220. an inter-plant service subsystem; 221. an inter-plant association module; 230. an element base subsystem; 231. a base configuration module; 240. a capacity analysis subsystem; 241. a request analysis module; 242. a function calling module; 243. and an information analysis module.
Detailed Description
The following detailed description of the application is provided in connection with the accompanying drawings to facilitate understanding and grasping of the technical scheme of the application.
For a clearer understanding of the design intent of the present application, firstly, for the case of the conventional intelligent factory, the intelligent factory applicable to data analysis generally includes factors such as equipment, labor force, raw materials, energy, funds and the like, all factors related to production results belong to production factors, as the productivity increases, generally, the investment of the production factors increases, but obviously, different production factors have different corresponding investment characteristics, such as equipment, the continuous operation of which may affect the service life and may be damaged, so that the actual loss is generated, such as labor force, if the labor force needs to increase under the condition of increasing the productivity, one aspect may be an increase in labor time, and the other aspect is an increase in labor force quantity, so that the factors generated by the two aspects are different, as for the factory supported by data, if the analysis of the content is required, the problem of the present application is encountered, the productivity is not expected, and the corresponding investment of the productivity is not expected, for example, the continuous operation of the equipment is not easy to take into consideration, the new production history of the equipment is not considered, and the working history of the new production is not likely to be considered, and the working history of the equipment is not likely to be in consideration, and the working history is not likely to be in terms of the working history is not longer than the working time is not likely to be taken into consideration, and the working history is not likely to be in terms of the working history of the equipment is not longer.
Based on the above situation, the present application proposes a mathematical model-based intelligent factory capacity analysis system, which includes a local service subsystem 210, an inter-factory service subsystem 220, an element foundation subsystem 230, a capacity analysis subsystem 240, and a plurality of production terminals 110;
the production terminal 110 is configured with a plurality of acquisition units 111, wherein the acquisition units 111 are used for acquiring production element data in a production process and generating the capacity acquisition information according to the production element data and corresponding capacity; the production terminal 110 is a data center in which the intelligent factory is responsible for processing, storing and analyzing all data, the data acquisition unit 111 of the production terminal 110 comprises various sensors and collectors not limited to be arranged on equipment, and a product production counter or an equipment state monitoring interface, corresponding data can be acquired from data which cannot be acquired, the acquisition unit 111 of the intelligent factory can acquire information such as working time and electricity consumption of each worker every day, and the information is acquired to the production terminal 110 in an input or information acquisition mode, the production terminal 110 can generate the relationship between the capacity and the corresponding production element at the moment in real time, and each production element data reflects the relationship between the element use condition of a specific production element and the corresponding production capacity. Since the local service subsystem 210, the inter-plant service subsystem 220, and the element base subsystem 230 are all determined according to the element values and the capacity values, the production terminal 110 reflects the input conditions of the production elements according to the element values configured corresponding to each production element when processing the information, and the input of the production elements can be quantified by the numerical values although the measurement units of the different production elements are different, and the capacity values are determined according to the number of the product output results.
The local service subsystem 210 includes a local configuration module 211, where the local configuration module 211 is configured to generate a corresponding local configuration model corresponding to each local terminal, and the local configuration module 211 acquires and processes the production element data to generate capacity history information, and inputs the capacity history information into the local configuration model so that under each production element in the local configuration model, a corresponding element value and a capacity value are associated; the local configuration module 211 is provided with local configuration policies, which include
A1, establishing a historical capacity coordinate graph corresponding to each production element;
a2, extracting element values and productivity values corresponding to production elements from the productivity acquisition information, and determining corresponding production relation points in a historical productivity coordinate graph;
a3, fitting production relation points to generate a local productivity function if the corresponding historical productivity coordinate graph meets a first constraint condition; otherwise, waiting for the historical capacity coordinate graph to meet a first constraint condition;
and A4, constructing the local configuration model by taking the production elements as nodes and through each obtained local energy function. The local configuration module 211 specifically analyzes data in such a way that the node using the production element as a model can determine the function used by the number of the production element, and it needs to be described that, because the historical productivity value and the historical element value in the present application are both concepts of point values, but if the point value is predicted, the point value cannot directly affect the result, and cannot achieve the predicted effect, the local configuration policy is that the production relationship point is input into the historical productivity coordinate graph, then the point is fitted, for example, the number of the production relationship points exceeds the preset value by the first constraint condition, if the first constraint condition is not satisfied, the function is marked as 0, and the fitting relationship point is a corresponding function formed by connecting the point as the local property function, and the local property function uses the production element as the node in the model, and because the production element has different relativity, the production element as the node can be quickly indexed to the corresponding local property function during analysis.
The inter-plant service subsystem 220 includes an inter-plant association module 221, where the inter-plant association module 221 is configured to generate an element feature model corresponding to each production element feature, and the inter-plant association module 221 extracts corresponding element association data from the capacity collection information according to the production element feature, and inputs the element association data into the element feature model so that corresponding element values and capacity values are associated with each production parameter in the element feature model; the inter-plant association module 221 is provided with inter-plant association strategies, which comprise
Step B1, establishing a characteristic capacity coordinate graph corresponding to each production element;
step B2, extracting element values and yield values from the element association data, determining corresponding element feature points in the feature yield coordinate graph, and establishing terminal stamp according to the production terminal 110 to which the element feature points belong;
step B3, connecting element feature points with the same terminal marks to obtain element feature subfunctions;
step B4, dividing the element characteristic subfunctions into a plurality of element characteristic groups according to the shape similarity among the element characteristic subfunctions;
step B5, comparing production parameter items in the element feature groups, and endowing feature coefficients of each feature sub-function according to different production parameter items so as to obtain feature reference functions of the corresponding element feature groups;
step B6, constructing an element feature model by taking the element feature group as a node and through each feature reference function;
the function retrieval module 242 includes determining characteristic coefficients based on production parameters and bringing the characteristic coefficients into the characteristic reference function to obtain a characteristic energy production function. The factory association module 221 is connected to different production terminals 110, so that corresponding data can be obtained from different production terminals 110, and the strategy of obtaining the data is to establish a graph as well, then mark corresponding element feature points according to the relation between productivity and elements, theoretically, since different production elements have the same production features, waveforms of connecting lines corresponding to the element feature points should be approximately the same, for example, element features corresponding to the production elements are heating devices, and heating power is different, so that the efficiency of the heating devices is different, but for the same production, the use efficiency of the heating devices is the same, and cooling needs to be performed at intervals, so that the data with the same element features are divided into a productivity graph by utilizing the element features of the production elements, and then connecting the element feature points from the same production terminal 110, and determining corresponding element characteristic sub-functions, dividing the element characteristic sub-functions into a plurality of element characteristic groups according to the corresponding shape similarity, dividing the element characteristic sub-functions into a plurality of element characteristic groups more easily according to the higher similarity, calculating only the similarity of functions, not calculating the difference value of the functions, wherein the similarity of functions reflects the change characteristics of production elements, dividing the change characteristics of the production elements into the same group indicates similar element characteristics, distinguishing the differences of different element characteristics according to different production parameter items, taking the previous heating equipment as an example, for example, the element characteristics are different in power, knowing that when a new request is generated, looking at the power of the corresponding request is closer to which value, the specific characteristic reference function is more prone to be selected, constructing an element characteristic model through the characteristic reference function, taking the element characteristic group as a node, the corresponding element feature function can be determined by analyzing the element feature of the corresponding production element, for example, the element feature can be different from the labor of the manual manufacturing industry, the labor of the semi-automatic manufacturing industry and the labor of the full-automatic manufacturing industry, and the corresponding function shape can be different according to the corresponding production parameter, for example, the labor input density of the specifically manufactured product, for example, how much time the labor can be used for producing the product, and determining the different element feature sub-functions.
The element base subsystem 230 includes a base configuration module 231, where the base configuration module 231 is configured to generate an element type model corresponding to each production element type, and the base configuration module 231 obtains reference type data corresponding to the production element type from an external base database and inputs the reference type data into the element type model so that corresponding element values and productivity values are associated with each production parameter in the element type model; the basic configuration module 231 is provided with basic configuration strategies, and the basic configuration strategies comprise
Step C1, constructing a type reference function according to the reference type data, wherein the type reference function has type coefficients with production parameters as indexes;
step C2, associating each type of reference function with a production element type, associating each type of reference function with at least one production element type, and dividing the production element types associated with the same type of reference function into the same element type group;
step C3, constructing an element type model by taking an element type group as a node through each type of reference function;
the function retrieval module 242 includes determining a type coefficient based on the production parameters and bringing the type coefficient into the type reference function to obtain the type capacity function. The element-based subsystem 230 is simpler, and by analyzing elements and manually setting functions, such as analyzing the relationship between the use standard and risk of a common production device by a certain research, the possible changes of the investment of the production elements when the production device is overloaded for use can be calculated according to the analysis stage, for example, the analysis of labor force and productivity is performed, when the labor force is increased at first, the labor force is increased, the productivity is promoted due to the cooperation of the labor force, more management cost is required to maintain the efficiency if the labor force is increased again, or the average efficiency is reduced, and the functions are the processes of accelerating, decelerating, accelerating and decelerating again. The type reference function is constructed by editing or calling data of an external database in advance, the unknown number in the type reference function is more, the corresponding coefficient can be directly converted according to different production parameters and is input into the type reference function to generate the type productivity function, and the element type is relatively wider than the element characteristic, for example, the heating equipment can be of the element type, but the specific heating power or the heating mode belongs to the element characteristic.
The capacity analysis subsystem 240 includes a request analysis module 241, a function invoking module 242, and an information analysis module 243; the request analysis module responds to the capacity analysis request of the corresponding production terminal and generates a plurality of capacity analysis tasks according to production elements in the capacity analysis request, and the function calling module calls a local capacity function, a characteristic capacity function and a type capacity function from the local configuration model, the element characteristic model and the element type model respectively according to the capacity analysis tasks; the information analysis module is configured with a capacity analysis algorithm, and the capacity analysis algorithm is thatThe method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Is the comprehensive productivity function corresponding to the production element with the number of n,for the local energy function corresponding to the n numbered production element->A feature capacity function corresponding to the element capacity feature with the number of m1, wherein the element capacity feature with the number of m1 corresponds to the production element with the number of n; />A type capacity function corresponding to an element capacity type with the number of m2, wherein the element capacity type with the number of m2 corresponds to a production element with the number of n; />Historical weight corresponding to production element with number n,/->Is the characteristic weight corresponding to the production element with the number of n>For the type weight corresponding to the production element with the number n, there is +.>. The capacity analysis red copper weights the three functions with different weights through request analysis, function calling and information analysis, so that the predicted value of the element value under different capacity value requirements can be obtained, and a producer can be assisted to make a production decision. The capacity analysis algorithm corresponds to a weight constraint condition, wherein the weight constraint condition is as follows;
whereinFor the number of production relations corresponding to the production element, < >>For the number of element feature points corresponding to the production element, < >>Is->Element values corresponding to the respective production relationship points, < ->Is->Capacity corresponding to each production relationship point, < ->Is->Element values corresponding to the individual element feature points, < >>Is->Capacity value corresponding to each element feature point, < +.>Is->Production feature similarity between production terminal and target terminal corresponding to each element feature point>Is->Time of generation of each production relation point, +.>Is->Time of generation of individual element feature points, +.>For the current moment +.>Is a preset reference weight value, +.>The variables are corrected for locally. The production element corresponds to different element parameter items, each element parameter item corresponds to different similarity weight values,and comparing the similarity sub-values of each element parameter item of the production terminal and the target terminal through the production parameters, and weighting the similarity sub-values according to the similarity weight to calculate and obtain the production feature similarity. The reference weight value is determined in advance according to the data volume, the reliability value and the discrete degree corresponding to the type productivity function. Since the larger the data amount is, the higher the data reliability is, the lower the data discrete degree is, the higher the data reliability is, the shorter the time span is, the higher the data reliability is, and the higher the similarity is, the weight constraint condition is configured according to the correlation of the reliability, that is, if the reliability of a function is higher, the corresponding weight is larger. The reliable value of the reference weight value is the authenticity of the data, such as the data source and the repeated occurrence of the data, and the data is referenced, so that the authenticity of the corresponding data can be reflected, and the basis is made for prediction. The production terminal is provided with a deviation correcting unit, and the deviation correcting unit comprises a deviation correcting algorithm, wherein the deviation correcting algorithm is +.>Wherein->For local correction value, ++>For the actual capacity, +.>For the actual element value, +.>For the preset correction parameters, the local correction variables are updated by means of the deviation correction unit, with +.>. The actual measured result and the predicted result are compared, and the data can be continuously perfected through the deviation correction, so that the predicted reliability and novelty can be improved.
The production terminal is provided withThe element analysis unit is configured with a load analysis table corresponding to each production element, the load analysis table comprises a plurality of element load ranges and corresponding load analysis information, and when the capacity value corresponding to the production element falls into the element load range, the corresponding load analysis information is output. The load analysis information comprises element association functions, and when the corresponding load analysis information is output, the corresponding comprehensive capacity function is updated through the element association functions, and the load analysis information comprisesWherein->And reflecting the variation of the nth production element in the e-th load analysis information as an element association function corresponding to the e-th load analysis information. After the comprehensive capacity function is determined, it is also possible to determine, through the load analysis table, information that needs to be output by each production function, for example, when the element value of the labor force exceeds a certain value, an additional introduction of the labor force unit is required, and at this time, corresponding information is output to remind that if the capacity is increased, the labor force unit needs to be increased, or when the labor force is increased to a certain value, a new management element needs to be increased, and the other element is edited through the element association function, and the editing is limited to specific information that may occur to the production terminal, because the common information can be found and identified. In summary, the above manner provides basis for production element analysis from three dimensions, providing data support for producer decision-making.
Of course, the above is only a typical example of the application, and other embodiments of the application are also possible, and all technical solutions formed by equivalent substitution or equivalent transformation fall within the scope of the application claimed.
Claims (7)
1. An intelligent factory productivity analysis system based on a mathematical model is characterized in that: the system comprises a local service subsystem, an inter-plant service subsystem, an element foundation subsystem, a productivity analysis subsystem and a plurality of production terminals;
the production terminal is provided with a plurality of acquisition units, and the acquisition units are used for acquiring production element data in the production process and generating capacity acquisition information according to the production element data and corresponding capacity;
the local service subsystem comprises a local configuration module, wherein the local configuration module is used for generating a corresponding local configuration model corresponding to each local terminal, the local configuration module acquires and processes the production element data to generate capacity history information, and the capacity history information is input into the local configuration model so that corresponding element values and capacity values are associated under each production element in the local configuration model;
the inter-plant service subsystem comprises an inter-plant association module, wherein the inter-plant association module is used for generating an element feature model corresponding to each production element feature, extracting corresponding element association data from capacity acquisition information according to the production element feature, and inputting the element association data into the element feature model so that corresponding element values and capacity values are associated under each production parameter in the element feature model;
the element foundation subsystem comprises a foundation configuration module, wherein the foundation configuration module is used for generating an element type model corresponding to each production element type, acquiring reference type data corresponding to the production element type from an external foundation database, and inputting the reference type data into the element type model so that corresponding element values and productivity values are associated with each production parameter in the element type model;
the capacity analysis subsystem comprises a request analysis module, a function calling module and an information analysis module; the request analysis module responds to the capacity analysis request of the corresponding production terminal and generates a plurality of capacity analysis tasks according to production elements in the capacity analysis request, and the function calling module calls a local capacity function, a characteristic capacity function and a type capacity function from the local configuration model, the element characteristic model and the element type model respectively according to the capacity analysis tasks; the information analysisThe module is configured with a capacity analysis algorithm, wherein the capacity analysis algorithm is thatThe method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>For the production element with the number n, the comprehensive productivity function +.>For the local energy function corresponding to the n numbered production element->A feature capacity function corresponding to the element capacity feature with the number of m1, wherein the element capacity feature with the number of m1 corresponds to the production element with the number of n; />A type capacity function corresponding to an element capacity type with the number of m2, wherein the element capacity type with the number of m2 corresponds to a production element with the number of n; />Historical weight corresponding to production element with number n,/->Is the characteristic weight corresponding to the production element with the number of n>For the type weight corresponding to the production element with the number n, there is +.>；
The local configuration module is provided with a local configuration strategy, and the local configuration strategy comprises:
a1, establishing a historical capacity coordinate graph corresponding to each production element;
a2, extracting element values and productivity values corresponding to production elements from the productivity acquisition information, and determining corresponding production relation points in a historical productivity coordinate graph;
a3, fitting production relation points to generate a local productivity function if the corresponding historical productivity coordinate graph meets a first constraint condition; otherwise, waiting for the historical capacity coordinate graph to meet a first constraint condition;
step A4, constructing the local configuration model by taking the production elements as nodes and through each obtained local energy function;
the inter-plant association module is provided with an inter-plant association strategy, and the inter-plant association strategy comprises:
step B1, establishing a characteristic capacity coordinate graph corresponding to each production element;
step B2, extracting element values and yield values from the element association data, determining corresponding element characteristic points in the characteristic yield coordinate graph, and establishing terminal stamp according to the production terminal to which the element characteristic points belong;
step B3, connecting element feature points with the same terminal marks to obtain element feature subfunctions;
step B4, dividing the element characteristic subfunctions into a plurality of element characteristic groups according to the shape similarity among the element characteristic subfunctions;
step B5, comparing production parameter items in the element feature groups, and endowing feature coefficients of each feature sub-function according to different production parameter items so as to obtain feature reference functions of the corresponding element feature groups;
step B6, constructing an element feature model by taking the element feature group as a node and through each feature reference function;
the function retrieval module comprises a step of determining characteristic coefficients according to production parameters and a step of bringing the characteristic coefficients into the characteristic reference function to obtain a characteristic energy production function;
the basic configuration module is provided with a basic configuration strategy, and the basic configuration strategy comprises:
step C1, constructing a type reference function according to the reference type data, wherein the type reference function has type coefficients with production parameters as indexes;
step C2, associating each type of reference function with a production element type, associating each type of reference function with at least one production element type, and dividing the production element types associated with the same type of reference function into the same element type group;
step C3, constructing an element type model by taking an element type group as a node through each type of reference function;
the function invoking module comprises determining a type coefficient according to the production parameters, and bringing the type coefficient into the type reference function to obtain the type productivity function.
2. The mathematical model-based intelligent plant capacity analysis system of claim 1, wherein: the production terminal is provided with an element analysis unit, the element analysis unit is provided with a load analysis table corresponding to each production element, the load analysis table comprises a plurality of element load ranges and corresponding load analysis information, and when the productivity value corresponding to the production element falls into the element load range, the corresponding load analysis information is output.
3. The mathematical model-based intelligent plant capacity analysis system of claim 2, wherein: the load analysis information comprises element association functions, and when the corresponding load analysis information is output, the corresponding comprehensive capacity function is updated through the element association functions, and the load analysis information comprisesWherein->And reflecting the variation of the nth production element in the e-th load analysis information as an element association function corresponding to the e-th load analysis information.
4. The mathematical model-based intelligent plant capacity analysis system of claim 1, wherein: the capacity analysis algorithm corresponds to a weight constraint condition, wherein the weight constraint condition is as follows;
wherein->For the number of production relations corresponding to the production element, < >>For the number of element feature points corresponding to the production element, < >>Is->Element values corresponding to the respective production relationship points, < ->Is->Capacity corresponding to each production relationship point, < ->Is->Element values corresponding to the individual element feature points, < >>Is->Capacity value corresponding to each element feature point, < +.>Is->Production feature similarity between production terminal and target terminal corresponding to each element feature point>Is->Time of generation of each production relation point, +.>Is->Time of generation of individual element feature points, +.>For the current moment +.>Is a preset reference weight value, +.>The variables are corrected for locally.
5. The mathematical model-based intelligent plant capacity analysis system of claim 4, wherein: the production terminal is provided with an offset correction unit, the offset correction unit comprises an offset correction algorithm, and the offset correction algorithm is thatWherein->For local correction value, ++>For the actual capacity, +.>As the actual value of the element,for the preset correction parameters, the local correction variables are updated by means of the deviation correction unit, with +.>。
6. The mathematical model-based intelligent plant capacity analysis system of claim 5, wherein: the production elements correspond to different element parameter items, each element parameter item corresponds to different similarity weight values, the similarity sub-values of each element parameter item of the production terminal and the target terminal are compared through the production parameters, and the similarity sub-values are weighted according to the similarity weight values to calculate and obtain the production feature similarity.
7. The mathematical model-based intelligent plant capacity analysis system of claim 6, wherein: the reference weight value is determined in advance according to the data volume, the reliability value and the discrete degree corresponding to the type productivity function.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310128617.0A CN116307526B (en) | 2023-02-06 | 2023-02-06 | Intelligent factory productivity analysis system based on mathematical model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310128617.0A CN116307526B (en) | 2023-02-06 | 2023-02-06 | Intelligent factory productivity analysis system based on mathematical model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116307526A CN116307526A (en) | 2023-06-23 |
| CN116307526B true CN116307526B (en) | 2023-11-07 |
Family
ID=86835182
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310128617.0A Active CN116307526B (en) | 2023-02-06 | 2023-02-06 | Intelligent factory productivity analysis system based on mathematical model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116307526B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117829547A (en) * | 2024-01-29 | 2024-04-05 | 山东创未空间互联网科技有限公司 | Factory equipment intelligent upgrading and reforming method and system based on Internet of things technology |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110969304A (en) * | 2019-12-04 | 2020-04-07 | 汇鼎数据科技(上海)有限公司 | Method, system and device for predicting production capacity of digital factory |
| CN111027799A (en) * | 2019-10-24 | 2020-04-17 | 山西云时代技术有限公司 | National enterprise productivity analysis system |
| CN114926051A (en) * | 2022-05-27 | 2022-08-19 | 上海哥瑞利软件股份有限公司 | Analysis system for evaluating manufacturing capacity of semiconductor equipment |
| CN115186910A (en) * | 2022-07-18 | 2022-10-14 | 南京致景信息科技有限公司 | Grey fabric factory productivity prediction method based on LSTM and XGboost mixed model |
-
2023
- 2023-02-06 CN CN202310128617.0A patent/CN116307526B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111027799A (en) * | 2019-10-24 | 2020-04-17 | 山西云时代技术有限公司 | National enterprise productivity analysis system |
| CN110969304A (en) * | 2019-12-04 | 2020-04-07 | 汇鼎数据科技(上海)有限公司 | Method, system and device for predicting production capacity of digital factory |
| CN114926051A (en) * | 2022-05-27 | 2022-08-19 | 上海哥瑞利软件股份有限公司 | Analysis system for evaluating manufacturing capacity of semiconductor equipment |
| CN115186910A (en) * | 2022-07-18 | 2022-10-14 | 南京致景信息科技有限公司 | Grey fabric factory productivity prediction method based on LSTM and XGboost mixed model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116307526A (en) | 2023-06-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116307526B (en) | Intelligent factory productivity analysis system based on mathematical model | |
| CN107679715A (en) | A kind of electric energy meter comprehensive error process merit rating method and evaluation system based on SPC | |
| CN104794535B (en) | A kind of method of electric power demand forecasting and early warning based on Dominant Industry | |
| CN113675863B (en) | Digital twin-based micro-grid frequency secondary cooperative control method | |
| CN110909958A (en) | Short-term load prediction method considering photovoltaic grid-connected power | |
| CN116227637A (en) | Active power distribution network oriented refined load prediction method and system | |
| CN103136895A (en) | Furnace group energy consumption system and method in fused magnesia smelting process | |
| CN116722605B (en) | Power distribution network scheduling optimization method based on Internet of things | |
| CN111275582B (en) | Method and device for automatically processing data | |
| CN112036634A (en) | Photovoltaic power generation power determination method, prediction system and readable storage medium | |
| CN114819391B (en) | Photovoltaic power generation power prediction method and system based on historical data set time span optimization | |
| CN105573269B (en) | The parameter monitoring system and method for semiconductor manufacturing board | |
| CN114912700A (en) | Factory workshop electric power energy consumption assessment method and system | |
| CN110705866B (en) | Method for evaluating matching degree of energy production equipment configuration and load of comprehensive energy system | |
| CN114415040A (en) | Energy storage power station energy management method and device based on SOC real-time estimation | |
| CN113485280A (en) | New energy stamping workshop scheduling system and method based on information physical model conversion | |
| CN107272611A (en) | A kind of algorithm for weighing manufacture procedure quality ability | |
| CN116307406B (en) | Energy efficiency management method and system based on Internet of things | |
| CN112785142A (en) | Intelligent work order early warning method and system for sewage treatment equipment based on Internet of things | |
| CN117539169B (en) | Management method and system based on digital twin | |
| CN114047372B (en) | Voltage characteristic-based platform region topology identification system | |
| CN117595231B (en) | Intelligent power grid distribution management system and method thereof | |
| CN112564100B (en) | Method and system for evaluating maximum output of thermal power generating unit in real time based on differential pressure of air preheater | |
| CN110555220A (en) | Calibration method and system of photoelectric conversion model | |
| CN115357002B (en) | Energy efficiency monitoring and management method and system for electromechanical equipment of factory |
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 |