CN116307664A - Intelligent manufacturing process management system based on big data - Google Patents

Abstract

The invention discloses an intelligent manufacturing flow management system based on big data, which belongs to the technical field of production and manufacturing management and comprises a marking module, a scheme module, a recommending module and a server; the marking module is used for marking flow steps to be improved in the intelligent manufacturing flow; the scheme module is used for setting an improvement scheme corresponding to the step to be improved, obtaining corresponding step information to be improved, setting a corresponding retrieval formula based on the obtained step information to be improved, and carrying out corresponding retrieval in the Internet according to the obtained retrieval formula to obtain a to-be-selected improvement scheme; carrying out adaptability calculation on the obtained to-be-selected improved scheme to obtain a corresponding suitable value, and marking the to-be-selected improved scheme corresponding to the suitable value being greater than a threshold value X3 as a target improved scheme; the recommending module is used for recommending the target improvement scheme to a corresponding manager, acquiring the target improvement scheme, setting the corresponding manager and sending the acquired target improvement scheme to the corresponding manager.

Description

Intelligent manufacturing process management system based on big data

technical field

The invention belongs to the technical field of production and manufacturing management, in particular to an intelligent manufacturing process management system based on big data.

Background technique

With the rapid development of manufacturing technology, more and more manufacturing enterprises adopt intelligent production technology to improve the automation and intelligence of production, and then increase the production efficiency of enterprises; but with the rapid development of related technologies, production equipment The upgrading of the production process has brought new challenges to the management of the manufacturing process. For example, when the management personnel of the enterprise find an efficient production equipment, but do not consider the actual situation of the production process of the enterprise, the replacement of the production equipment does not work. The expected target has increased the cost of the enterprise; or because the enterprise management personnel cannot timely understand the real-time technological development information, the enterprise cannot update the production equipment in time, and the production efficiency cannot wait for the corresponding improvement; therefore, in order to improve the manufacturing The process is intelligently managed, and the invention provides an intelligent manufacturing process management system based on big data.

Contents of the invention

In order to solve the problems in the above solution, the present invention provides an intelligent manufacturing process management system based on big data.

The purpose of the present invention can be achieved through the following technical solutions:

Intelligent manufacturing process management system based on big data, including marking module, scheme module, recommendation module and server;

The marking module is used to mark the process steps to be improved in the intelligent manufacturing process;

The scheme module is used to set the improvement scheme corresponding to the step to be improved, obtain the corresponding step information to be improved, set the corresponding search formula based on the obtained step information to be improved, perform corresponding search on the Internet according to the obtained search formula, and obtain The improvement plan to be selected; perform adaptive calculation on the obtained improvement plan to be selected, obtain the corresponding fitness value, and mark the improvement solution to be selected with the fitness value greater than the threshold value X3 as the target improvement solution;

The recommendation module is used for recommending the target improvement plan to the corresponding management personnel, obtaining the target improvement plan, setting the corresponding management personnel, and sending the obtained target improvement plan to the corresponding management personnel.

Further, the working method of the marking module includes:

Obtain the currently adopted intelligent manufacturing process, divide the intelligent manufacturing process into several production steps according to the production nodes, establish the corresponding step data record table according to the obtained production steps, collect the suggested data corresponding to the production steps in real time, and input the obtained suggested data into Go to the step data recording table; analyze the data in the step data recording table to obtain the steps to be improved, and make corresponding marks in the intelligent manufacturing process according to the obtained steps to be improved.

Further, the method for analyzing the data in the step data recording table includes:

计算对应的建议值，当建议值超过阈值X1时，将对应的生产步骤标记为待改进步骤，并标记对应的侧重分类；当建议值不大于阈值X1时，不进行操作。Identify the suggested data in the step data record table, classify the identified suggested data, obtain several classified data, obtain the number of suggested items in the classified data, match the corresponding quantity value according to the obtained suggested number, and classify the corresponding classified data Mark as i, where i=1, 2, ..., n, n is a positive integer; mark the obtained quantity value as PLi, analyze the suggested content corresponding to each classification data, obtain the corresponding content value, and obtain the obtained The content value is marked as NRi, according to the formula

Calculate the corresponding suggested value, when the suggested value exceeds the threshold X1, mark the corresponding production step as the step to be improved, and mark the corresponding emphasis classification; when the suggested value is not greater than the threshold X1, no operation is performed.

Further, the classification-focused methods corresponding to the marking include:

According to the formula b1×PLi+b2×NRi, the emphasis value corresponding to each classification data is calculated, and the classification data whose emphasis value is greater than the threshold X2 is listed as the emphasis classification. When no emphasis value is greater than the threshold X2, there is no emphasis classification.

Further, the method for adaptive calculation of the obtained improvement plan includes:

Obtain the process data of the current step to be improved, integrate the obtained process data and the improvement plan to be selected into comprehensive analysis data, establish a comprehensive value analysis model, input the comprehensive analysis data into the comprehensive value analysis model, and obtain the corresponding implementation value and efficiency The improvement value, process connection value and operation change value are marked as SZ, GZ, LX and BZ respectively, and the corresponding fitness value is calculated according to the fitness calculation formula SYZ=β1×SZ+β2×GZ+β3×LX+β4×BZ, Among them, β1, β2, β3, and β4 are the weight coefficients of implementation value, efficiency improvement value, process connection value and operation change value respectively.

Furthermore, the comprehensive value analysis model is established based on a CNN network or a DNN network.

Compared with prior art, the beneficial effect of the present invention is:

Through the setting of the marking module, the intuitive understanding of the current production process problems in the enterprise can be realized, and the most real problems of the production process and the corresponding improvement directions can be understood from the production line, so as to point out the direction for the subsequent industrial upgrading; through the marking module, program module and The mutual cooperation between the recommended modules realizes the intelligent management of the manufacturing process, and realizes closed-loop management from problem discovery to problem-solving solutions. Based on the retrieval and analysis of big data, when there is an improvement plan suitable for the enterprise, it can be recommended to the management personnel in a timely manner.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. Those skilled in the art can also obtain other drawings based on these drawings without creative work.

Fig. 1 is a schematic block diagram of the present invention.

Detailed ways

The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Apparently, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

As shown in Figure 1, the intelligent manufacturing process management system based on big data includes a marking module, a solution module, a recommendation module and a server;

The marking module is used to mark the process steps to be improved in the intelligent manufacturing process, and the specific methods include:

Obtain the currently adopted intelligent manufacturing process, and divide the intelligent manufacturing process into several production steps according to the production nodes. Specifically, the corresponding segmentation can be carried out according to the common sense of the current production steps, such as cleaning, drying, grinding and other processes, which can be divided into cleaning Production steps, drying production steps and grinding production steps; establish a corresponding step data record table according to the obtained production steps, collect suggested data corresponding to the production steps in real time, and input the obtained suggested data into the step data record table;

Analyze the data in the step data recording table to obtain the steps to be improved, and make corresponding marks in the intelligent manufacturing process according to the obtained steps to be improved.

The step data recording table is used to record relevant data such as problems in the corresponding production steps and areas that need to be improved during the production and manufacturing process. Specifically, the corresponding staff will make supplementary suggestions based on their own operating experience in the daily production and manufacturing process.

In one embodiment, the method for collecting suggested data corresponding to a production step in real time includes:

Set the corresponding suggested collection unit. When the staff has suggestions, they can directly use the suggested collection unit to make suggestions. Manual input, document transmission, voice input, etc. can be used for collection, and then through docking with the suggested collection unit. When a suggestion is received, the corresponding suggestion is entered into the corresponding step data record form.

In another embodiment, in the actual operation process, it often happens that the corresponding workers will not include the suggestions even if there are relevant suggestions because they are afraid of trouble, etc., which will affect the data collection work, so in this In the embodiment, a manager is set up, and through contact with the staff in the corresponding production steps during the work process, the manager can learn the corresponding suggestions during the work, and the manager will summarize them and enter them into the suggestion collection unit , and in order to further stimulate the enthusiasm of the corresponding staff to put forward suggestions, relevant incentive measures can also be set, which are specifically set according to actual production needs.

The methods for analyzing the data in the step data record table include:

计算对应的建议值，当建议值超过阈值X1时，将对应的生产步骤标记为待改进步骤，并标记对应的侧重分类；当建议值不大于阈值X1时，不进行操作。Identify the suggested data in the step data record table, classify the identified suggested data, obtain several classified data, obtain the number of suggested items in the classified data, match the corresponding quantity value according to the obtained suggested number, and classify the corresponding classified data Mark as i, where i=1, 2, ..., n, n is a positive integer; mark the obtained quantity value as PLi, analyze the suggested content corresponding to each classification data, obtain the corresponding content value, and obtain the obtained The content value is marked as NRi, according to the formula

Calculate the corresponding suggested value, when the suggested value exceeds the threshold X1, mark the corresponding production step as the step to be improved, and mark the corresponding emphasis classification; when the suggested value is not greater than the threshold X1, no operation is performed.

Match the corresponding quantity value according to the number of suggestions obtained. The data value is analyzed and set according to the proposer, the number of suggestions, and the total number of suggestions. Because the number of times proposed by the same person and the number of times proposed by different people are different, so Comprehensive analysis is required. Specifically, a corresponding numerical value analysis model can be established based on a CNN network or a DNN network, and the corresponding training set can be manually set for training. After successful training, the numerical value analysis model can be analyzed to obtain the corresponding quantity. value.

The analysis of the suggestion content corresponding to each classification data is mainly to analyze the suggestion content and the corresponding proposer and the number of suggestions, and can set different weights for different proposers according to the acceptance degree of historical suggestions Coefficients, to carry out corresponding analysis, specifically based on the CNN network or DNN network to establish the corresponding content value analysis model, manually set the corresponding training set for training, analyze the content value analysis model after the training is successful, and obtain the corresponding content value.

Tags correspond to category-focused methods including:

According to the formula b1×PLi+b2×NRi, the emphasis value corresponding to each classification data is calculated, and the classification data whose emphasis value is greater than the threshold X2 is listed as the emphasis classification. When no emphasis value is greater than the threshold X2, there is no emphasis classification.

The program module is used to set an improvement program corresponding to the steps to be improved, and the specific methods include:

Obtain the corresponding step information to be improved. The step information to be improved includes the operation method of the step to be improved, and the emphasis on classification. If there is no emphasis on classification, it does not include the emphasis on classification; According to the corresponding search in the Internet, obtain the improvement plan to be selected;

Perform adaptive calculations on the obtained candidate improvement schemes to obtain corresponding fitness values, and mark the candidate improvement schemes whose fitness values are greater than the threshold X3 as target improvement schemes.

Based on the obtained step information to be improved, the corresponding retrieval formula is set, and the corresponding retrieval formula of the target retrieval data can be set through the existing retrieval technology, so no detailed description is given.

According to the obtained search formula, carry out the corresponding search on the Internet to obtain the improvement plan to be selected. The improvement plan to be selected is the existing improvement measure provided according to the current technology, because the technology is constantly developing and moving forward. When a new technology appears or a certain technology application is mature, there will always be different improved technologies for the current production steps. Therefore, based on the set search formula, real-time search is performed to obtain the corresponding improvement plan to be selected. Specifically, through the existing Retrieval techniques can be implemented accordingly.

The methods for adaptive calculation of the obtained candidate improvement schemes include:

Obtain the process data of the current step to be improved, integrate the obtained process data and the improvement plan to be selected into comprehensive analysis data, establish a comprehensive value analysis model, input the comprehensive analysis data into the comprehensive value analysis model, and obtain the corresponding implementation value and efficiency The improvement value, process connection value and operation change value are marked as SZ, GZ, LX and BZ respectively, and the corresponding fitness value is calculated according to the fitness calculation formula SYZ=β1×SZ+β2×GZ+β3×LX+β4×BZ, Among them, β1, β2, β3, and β4 are the weight coefficients of the implementation value, efficiency improvement value, process connection value and operation change value respectively, and the specific ones are set by the expert group through discussion.

The comprehensive value analysis model is established based on the CNN network or DNN network, and the corresponding training set is manually established for training. The implementation fee is set according to the cost required to modify the existing process, and the efficiency improvement value refers to It is the improvement value of the beneficial effect of the improvement plan to be selected relative to the efficiency of the current step to be improved. The process connection value is set according to the degree of connection between the improvement plan to be selected and the previous and subsequent production steps. Whether the staff of the step can operate the level of the improvement plan to be selected can be set, and the training set is manually set for training.

The recommendation module is used to recommend the target improvement plan to the corresponding management personnel, and obtain the target improvement plan, which can be one or more; set the corresponding management personnel, discuss and set it within the enterprise, and send the obtained target improvement plan to The corresponding management personnel; that is, the final manual review method is used to determine whether the target improvement plan is implemented.

The above formulas are calculated by removing the dimension and taking its numerical value. The formula is a formula that is closest to the real situation obtained by collecting a large amount of data for software simulation. The preset parameters and preset thresholds in the formula are set by those skilled in the art according to the actual situation Or obtain a large amount of data simulation.

The above embodiments are only used to illustrate the technical method of the present invention without limitation. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present invention can be modified or equivalently replaced. Without departing from the spirit and scope of the technical method of the present invention.

Claims (6)

1. The intelligent manufacturing process management system based on big data is characterized in that it includes a marking module, a scheme module, a recommendation module and a server; The marking module is used to mark the process steps to be improved in the intelligent manufacturing process; The scheme module is used to set the improvement scheme corresponding to the step to be improved, obtain the corresponding step information to be improved, set the corresponding search formula based on the obtained step information to be improved, perform corresponding search on the Internet according to the obtained search formula, and obtain The improvement plan to be selected; perform adaptive calculation on the obtained improvement plan to be selected, obtain the corresponding fitness value, and mark the improvement solution to be selected with the fitness value greater than the threshold value X3 as the target improvement solution; The recommendation module is used for recommending the target improvement plan to the corresponding management personnel, obtaining the target improvement plan, setting the corresponding management personnel, and sending the obtained target improvement plan to the corresponding management personnel. 2. The intelligent manufacturing process management system based on big data according to claim 1, wherein the working method of the marking module comprises: Obtain the currently adopted intelligent manufacturing process, divide the intelligent manufacturing process into several production steps according to the production nodes, establish the corresponding step data record table according to the obtained production steps, collect the suggested data corresponding to the production steps in real time, and input the obtained suggested data into Go to the step data recording table; analyze the data in the step data recording table to obtain the steps to be improved, and make corresponding marks in the intelligent manufacturing process according to the obtained steps to be improved. 3. The intelligent manufacturing process management system based on big data according to claim 2, wherein the method for analyzing the data in the step data recording table comprises: Identify the suggested data in the step data record table, classify the identified suggested data, obtain several classified data, obtain the number of suggested items in the classified data, match the corresponding quantity value according to the obtained suggested number, and classify the corresponding classified data Mark as i, where i=1, 2, ..., n, n is a positive integer; mark the obtained quantity value as PLi, analyze the suggested content corresponding to each classification data, obtain the corresponding content value, and obtain the obtained The content value is marked as NRi, according to the formula

Calculate the corresponding suggested value, when the suggested value exceeds the threshold X1, mark the corresponding production step as the step to be improved, and mark the corresponding emphasis classification; when the suggested value is not greater than the threshold X1, no operation is performed. 4. The big data-based intelligent manufacturing process management system according to claim 3, characterized in that, the methods corresponding to the marking and focusing on classification include: According to the formula b1×PLi+b2×NRi, the emphasis value corresponding to each classification data is calculated, and the classification data whose emphasis value is greater than the threshold X2 is listed as the emphasis classification. When no emphasis value is greater than the threshold X2, there is no emphasis classification. 5. The intelligent manufacturing process management system based on big data according to claim 1, wherein the method for performing adaptive calculation of the obtained improvement plan comprises: Obtain the process data of the current step to be improved, integrate the obtained process data and the improvement plan to be selected into comprehensive analysis data, establish a comprehensive value analysis model, input the comprehensive analysis data into the comprehensive value analysis model, and obtain the corresponding implementation value and efficiency The improvement value, process connection value and operation change value are marked as SZ, GZ, LX and BZ respectively, and the corresponding fitness value is calculated according to the fitness calculation formula SYZ=β1×SZ+β2×GZ+β3×LX+β4×BZ, Among them, β1, β2, β3, and β4 are the weight coefficients of implementation value, efficiency improvement value, process connection value and operation change value respectively. 6. The big data-based intelligent manufacturing process management system according to claim 5, wherein the comprehensive value analysis model is established based on a CNN network or a DNN network.

Images