A digital management method and system for mold workshop based on artificial intelligence

Abstract

The present invention discloses a digital management method and system for a mold workshop based on artificial intelligence, comprising a mold resource data acquisition module, a mold information digital analysis module, and a mold workshop digital management module, wherein the mold resource data acquisition module is used to collect and process mold resource data information in a mold production process; the mold information digital analysis module is used to perform multi-dimensional feature analysis on the collected mold data; and the mold workshop digital management module is used to optimize and control the production scheduling and maintenance of the mold digital workshop. The present invention manages the production scheduling of the mold workshop, maintains and controls the production of the mold, and achieves the technical effect of improving the digital management efficiency of the mold workshop and reducing the operation and maintenance cost of the mold by collecting and processing the mold resource data information, constructing a multi-dimensional analysis model, and classifying the data features into a process-feature system.

Description

Technical Field

[0001] The present invention relates to the technical field of workshop digital management, and in particular to a mold workshop digital management method and system based on artificial intelligence. Background Art

[0002] In various links of the use of molds in industrial production, it is often the case that the use status of molds is not recorded after use, resulting in many molds still being put into production after the use period has expired, resulting in an increase in the defective rate. In the existing digital mold management system, various data during the use of molds are collected and recorded in real time, and various parameters during the use process are analyzed. According to the various data collected during the production of the mold, it is judged whether the mold needs maintenance and whether it is damaged, and the yield rate of the product is evaluated. However, based on the large accumulation of mold data, the management of storage structures in different ways has formed a large number of heterogeneous data resources. The speed and efficiency of enterprises in the existing production scheduling management and maintenance control process are greatly reduced. Conventional processing methods are prone to cause a large amount of redundancy of invalid data and increased maintenance costs. Therefore, it is necessary to design a digital management method and system for mold workshops based on artificial intelligence to improve the digital management efficiency of mold workshops and reduce the operation and maintenance costs of molds. Summary of the invention

[0003] The purpose of the present invention is to provide a digital management method and system for a mold workshop based on artificial intelligence to solve the problems raised in the above background technology.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions: a digital management system for a mold workshop based on artificial intelligence, comprising a mold resource data acquisition module, a mold information digital analysis module, and a mold workshop digital management module, characterized in that: the mold resource data acquisition module is used to collect and process mold resource data information in the mold production process; the mold information digital analysis module is used to perform multi-dimensional feature analysis on the collected mold data; the mold workshop digital management module is used to optimize and control the production scheduling and maintenance of the mold digital workshop.

[0005] According to the above technical solution, the acquisition grid division module, the sensor equipment acquisition module, and the data information processing module, the acquisition grid division module is used to divide the mold processing area into multiple acquisition grids of the same size; the sensor equipment acquisition module is used to use the sensor equipment to detect and collect various production status data during the mold processing process; the data information processing module is used to process the mold data that needs to be modeled.

[0006] According to the above technical solution, the data type division module, the data statistical analysis model construction module, the feature system modeling module, and the relationship link construction module, the data type division module is used to divide the data types of all collected data; the data statistical analysis model construction module is used to construct a data statistical analysis model of three dimensions of mold production status data, operation behavior data, and trigger behavior data through artificial intelligence; the feature system modeling module is used to model the feature system according to the mold resource data after system classification; the relationship link construction module is used to construct a relationship link based on the correlation between the production status data and the operation behavior data.

[0007] According to the above technical solution, the mold workshop digital management module includes: a production scheduling data processing module, a production scheduling constraint analysis module, a production scheduling operation module, and a production scheduling maintenance module. The production scheduling data processing module is used to integrate the associated production scheduling templates and plan node data to form production scheduling data; the production scheduling constraint analysis module is used to select parameter information that meets the current processing scheduling constraints from the sorting results; the production scheduling operation module is used to perform a cyclic operation of the production scheduling list based on the production scheduling plan; the production scheduling maintenance module is used to use digitization and big data to perform maintenance and management of mold differentiation.

[0008] According to the above technical solution, a digital management method for a mold workshop based on artificial intelligence is provided, the method comprising:

[0009] Step 1: Collect and process the mold resource data information during the mold production process;

[0010] Step 2: Use the collected resource data to mark the operation behavior data of the operator and build a multi-dimensional analysis model;

[0011] Step 3: Classify the process-feature system according to the data characteristics of the mold resource data at the operation end of different processes;

[0012] Step 4: Build a production scheduling model for the mold shop based on the production volume data of each processing step and mold;

[0013] Step 5: Maintain and control the production inspection of the mold according to the set operation behaviors of the mold resources in different processes.

[0014] According to the above technical solution, the step 1 includes the following steps:

[0015] Step 11: Divide the mold processing area into multiple collection grids of the same size. According to the number of tags defined in the actual collection range, arrange multiple sensor devices within the grid range. Mark each small grid as an area, and select one of them as the collection reference node.

[0016] Step 12: Use sensor equipment to detect and collect various production status data during the mold processing process, including monitoring the initial temperature, processing temperature, and shutdown temperature of the mold processing through a temperature sensor, monitoring the real-time production pressure through a pressure sensor, and the system generates a pressure production curve. The weight sensor is installed in the weight detection end to measure the weight data of the finished product;

[0017] Step 13: All sample data of the collected measurement records are stored in the database, and valid data is screened out for location matching modeling of the data and the process. According to the positioning algorithm of the data corresponding to the process, the data to be modeled is processed to obtain the results to determine the specific location of the label.

[0018] According to the above technical solution, the step 2 includes the following steps:

[0019] Step 21: Complete the classification of all collected data, determine the operations of mold business and each process management requirement through the production volume data of each mold production line, abstract it into objects, summarize and integrate the objects, draw the top-level class diagram, organize the connections between classes based on the top-level class diagram, and obtain the relationship diagram;

[0020] Step 22: Use image acquisition equipment to collect and mark the operation behavior data of the user at the operation end of each process. When the operation behavior that affects the mold processing production is determined according to the set threshold, the system automatically marks the operation behavior and records the triggering behavior data including alarm behavior and production stop behavior triggered by the corresponding operation behavior;

[0021] Step 23: Upload the collected and marked mold resource data, operation behavior data and trigger behavior data to the cloud through the industrial network of the mold production workshop, and build a data statistical analysis model with three dimensions of mold production status data, operation behavior data and trigger behavior data through artificial intelligence.

[0022] According to the above technical solution, step three includes the following steps:

[0023] Step 31: Classify the domain knowledge of the mold digital workshop into classes, relationships, and attributes, divide all mold categories according to mold material attributes, and perform feature system modeling based on the mold resource data after system classification;

[0024] Step 32: Structuring the mold resource data based on data features, and using the classified structured data to classify the process-feature system according to the data features of the mold resource data at the operation end of different processes;

[0025] Step 33: During the mold production process, the operator performs process operations and marks each process. If the operation is qualified, it will enter the next process. If the operation is unqualified, the operation behavior will be marked. Based on each process, the correlation between the production status data in the mold production process and the operation behavior data of the operator end user is extracted to build a relationship link.

[0026] According to the above technical solution, the step 4 includes the following steps:

[0027] Step 41: According to the actual production data volume of the mold workshop and the master production plan, the associated production scheduling template and planning node data are integrated to form the production scheduling data, and the processing time required for each mold in each process is calculated. The production scheduling data is processed by using the relationship between the production capacity of each process and the planned demand;

[0028] Step 42: Initialize the basic parameter information of the mold and production scheduling, initialize the scheduling constraints, sort the processes from the largest to the smallest according to the processing time of each process, and select the process that meets the current processing scheduling constraints from the sorting results;

[0029] Step 43: add the production data with the production status of being processed to the running list, subtract the planned start time of each production data in the running list from the current system time, obtain the remaining working hours of each production data in processing, change the planned start time of each production data in the running list to the current system time, and the planned end time is the current system time plus the remaining working hours, output the production data in the running list and enter the result list for operation;

[0030] Step 44: Synchronously remove the production data with the status of being processed, determine the production order of the production data based on the production process flow chart, obtain a new production data running list, loop the data in the new production data running list, mark the first data of the run, calculate the reduced start time for the first data of the marked run through the production data preliminary scheduling method, and determine whether the list has been looped.

[0031] According to the above technical solution, the step five includes the following steps:

[0032] Step 51: After the mold production information is saved based on the production schedule, when the mold production schedule is enabled, maintenance plan data is automatically generated, and a maintenance plan is generated according to the rules of life cycle and maintenance frequency;

[0033] Step 52: Setting the maintenance cycle and frequency of the system in the initial operation stage based on experience, setting the maintenance content based on the mold production status data, and using the relationship link between the established production status data and the operation behavior data to identify the mold damage type in the production stage combined with the experience value of the mold production status data failure;

[0034] Step 53: At the same time, according to the production status data of the mold within the set time period and the operation data of the operation end of each process, the differentiated frequency and content are formulated, and the mold differentiation is maintained and managed using digitalization and big data.

[0035] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention, by providing a mold resource data acquisition module, a mold information digital analysis module, and a mold workshop digital management module, collects and processes mold resource data information, constructs a multi-dimensional analysis model, and classifies data features into a process-feature system, manages the production scheduling of the mold workshop, maintains and controls the production process of the mold, and achieves the technical effect of improving the digital management efficiency of the mold workshop and reducing the operation and maintenance costs of the mold. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0037] Figure 1 A schematic diagram of the module composition of a digital management system for a mold workshop based on artificial intelligence provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] Embodiment 1: This embodiment can be applied to the scenario of digital management of mold workshops. The method can be executed by a digital management system for mold workshops based on artificial intelligence provided by this embodiment. The method specifically includes the following steps:

[0040] Step 1: Collect and process the mold resource data information during the mold production process;

[0041] Step 2: Use the collected resource data to mark the operation behavior data of the operator and build a multi-dimensional analysis model;

[0042] Step 3: Classify the process-feature system according to the data characteristics of the mold resource data at the operation end of different processes;

[0043] Step 4: Build a production scheduling model for the mold shop based on the production volume data of each processing step and mold;

[0044] Step 5: Maintain and control the production inspection of the mold according to the set operation behaviors of the mold resources in different processes.

[0045] In the embodiment of the present invention, step one includes the following steps:

[0046] Step 11: Divide the mold processing area into multiple collection grids of the same size. According to the number of tags defined in the actual collection range, arrange multiple sensor devices within the grid range. Mark each small grid as an area, and select one of them as the collection reference node.

[0047] Step 12: Use sensor equipment to detect and collect various production status data during the mold processing process, including monitoring the initial temperature, processing temperature, and shutdown temperature of the mold processing through a temperature sensor, monitoring the real-time production pressure through a pressure sensor, and the system generates a pressure production curve. The weight sensor is installed in the weight detection end to measure the weight data of the finished product;

[0048] Step 13: All sample data of the collected measurement records are stored in the database, and valid data is screened out for location matching modeling of the data and the process. According to the positioning algorithm of the data corresponding to the process, the data to be modeled is processed to obtain the results to determine the specific location of the label.

[0049] In the embodiment of the present invention, step 2 includes the following steps:

[0050] Step 21: Complete the classification of all collected data, determine the operations of mold business and each process management requirement through the production volume data of each mold production line, abstract it into objects, summarize and integrate the objects, draw the top-level class diagram, organize the connections between classes based on the top-level class diagram, and obtain the relationship diagram;

[0051] Step 22: Use image acquisition equipment to collect and mark the operation behavior data of the user at the operation end of each process. When the operation behavior that affects the mold processing production is determined according to the set threshold, the system automatically marks the operation behavior and records the triggering behavior data including alarm behavior and production stop behavior triggered by the corresponding operation behavior;

[0052] Step 23: Upload the collected and marked mold resource data, operation behavior data and trigger behavior data to the cloud through the industrial network of the mold production workshop, and build a data statistical analysis model with three dimensions of mold production status data, operation behavior data and trigger behavior data through artificial intelligence.

[0053] In the embodiment of the present invention, step three includes the following steps:

[0054] Step 31: Classify the domain knowledge of the mold digital workshop into classes, relationships, and attributes, divide all mold categories according to mold material attributes, and perform feature system modeling based on the mold resource data after system classification;

[0055] Step 32: Structuring the mold resource data based on data features, and using the classified structured data to classify the process-feature system according to the data features of the mold resource data at the operation end of different processes;

[0056] Step 33: During the mold production process, the operator performs process operations and marks each process. If the operation is qualified, it will enter the next process. If the operation is unqualified, the operation behavior will be marked. Based on each process, the correlation between the production status data in the mold production process and the operation behavior data of the operator end user is extracted to build a relationship link.

[0057] In the embodiment of the present invention, step 4 includes the following steps:

[0058] Step 41: According to the actual production data volume of the mold workshop and the master production plan, the associated production scheduling template and planning node data are integrated to form the production scheduling data, and the processing time required for each mold in each process is calculated. The production scheduling data is processed by using the relationship between the production capacity of each process and the planned demand;

[0059] Step 42: Initialize the basic parameter information of the mold and production scheduling, initialize the scheduling constraints, sort the processes from the largest to the smallest according to the processing time of each process, and select the process that meets the current processing scheduling constraints from the sorting results;

[0060] Step 43: add the production data with the production status of being processed to the running list, subtract the planned start time of each production data in the running list from the current system time, obtain the remaining working hours of each production data in processing, change the planned start time of each production data in the running list to the current system time, and the planned end time is the current system time plus the remaining working hours, output the production data in the running list and enter the result list for operation;

[0061] Step 44: Synchronously remove the production data with the status of being processed, determine the production order of the production data based on the production process flow chart, obtain a new production data running list, loop the data in the new production data running list, mark the first data of the run, calculate the reduced start time for the first data of the marked run through the production data preliminary scheduling method, and determine whether the list has been looped.

[0062] In the embodiment of the present invention, step five includes the following steps:

[0063] Step 51: After the mold production information is saved based on the production schedule, when the mold production schedule is enabled, maintenance plan data is automatically generated, and a maintenance plan is generated according to the rules of life cycle and maintenance frequency;

[0064] Step 52: Setting the maintenance cycle and frequency of the system in the initial operation stage based on experience, setting the maintenance content based on the mold production status data, and using the relationship link between the established production status data and the operation behavior data to identify the mold damage type in the production stage combined with the experience value of the mold production status data failure;

[0065] Step 53: At the same time, according to the production status data of the mold within the set time period and the operation data of the operation end of each process, the differentiated frequency and content are formulated, and the mold differentiation is maintained and managed using digitalization and big data.

[0066] Embodiment 2: Embodiment 2 of the present invention provides a digital management system for a mold workshop based on artificial intelligence. Figure 1 A schematic diagram of the module composition of a mold workshop digital management system based on artificial intelligence provided in the second embodiment of the present invention, such as Figure 1 As shown, the system includes:

[0067] The mold resource data collection module is used to collect and process the mold resource data information during the mold production process;

[0068] The mold information digital analysis module is used to perform multi-dimensional feature analysis on the collected mold data;

[0069] The mold workshop digital management module is used to optimize the production scheduling and maintenance of the mold digital workshop.

[0070] In some embodiments of the present invention, the mold resource data acquisition module includes:

[0071] A collection grid division module is used to divide the mold processing area into multiple collection grids of the same size;

[0072] The sensor equipment acquisition module is used to detect and collect various production status data during the mold processing process using sensor equipment;

[0073] The data information processing module is used to process the mold data that needs to be modeled.

[0074] In some embodiments of the present invention, the mold information digital analysis module includes:

[0075] Data type classification module, used to classify all collected data into data types;

[0076] Data statistical analysis model building module, used to build data statistical analysis models in three dimensions: mold production status data, operation behavior data, and trigger behavior data through artificial intelligence;

[0077] Feature system modeling module, used to perform feature system modeling based on mold resource data after system classification;

[0078] The relationship link building module is used to build a relationship link based on the association relationship between the production status data and the operation behavior data.

[0079] In some embodiments of the present invention, the mold shop digital management module includes:

[0080] The production scheduling data processing module is used to integrate the associated production scheduling templates and planning node data to form production scheduling data;

[0081] The production scheduling constraint analysis module is used to select parameter information that meets the current processing scheduling constraints from the sorting results;

[0082] The production scheduling module is used to perform cyclic operation of the production schedule based on the production schedule;

[0083] The production scheduling and maintenance module is used to utilize digitalization and big data to perform maintenance management on mold differentiation.

[0084] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0085] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A digital management system for mold workshop based on artificial intelligence, including a mold resource data acquisition module, a mold information digital analysis module, and a mold workshop digital management module, characterized in that: The mold resource data acquisition module is used to collect and process mold resource data information during the mold production process; the mold information digital analysis module is used to perform multi-dimensional feature analysis on the collected mold data; The mold workshop digital management module is used to optimize and control the production scheduling and maintenance of the mold digital workshop; The mold resource data acquisition module includes: an acquisition grid division module, a sensor device acquisition module, and a data information processing module. The acquisition grid division module is used to divide the mold processing area into a plurality of acquisition grids of the same size; the sensor device acquisition module is used to detect and collect various production status data during the mold processing process using sensor equipment; the data information processing module is used to process the mold data that needs to be modeled; The mold information digital analysis module includes: a data type classification module, a data statistical analysis model construction module, a feature system modeling module, and a relationship link construction module. The data type classification module is used to classify the data types of all collected data; the data statistical analysis model construction module is used to construct a data statistical analysis model of three dimensions of mold production status data, operation behavior data, and trigger behavior data through artificial intelligence; the feature system modeling module is used to perform feature system modeling according to the mold resource data after system classification; the relationship link construction module is used to construct a relationship link based on the association between production status data and operation behavior data; The mold workshop digital management module includes: a production scheduling data processing module, a production scheduling constraint analysis module, a production scheduling operation module, and a production scheduling maintenance module. The production scheduling data processing module is used to integrate the associated production scheduling templates and plan node data to form production scheduling data; the production scheduling constraint analysis module is used to select parameter information that meets the current processing production scheduling constraints from the sorting results; the production scheduling operation module is used to perform a cyclic operation of the production scheduling list based on the production scheduling plan; the production scheduling maintenance module is used to use digitization and big data to perform maintenance and management of mold differentiation.

2. A digital management method for mold workshop based on artificial intelligence, characterized by: The method comprises: Step 1: Collect and process the mold resource data information during the mold production process; Step 2: Use the collected resource data to mark the operation behavior data of the operator and build a multi-dimensional analysis model; Step 3: Classify the process-feature system according to the data characteristics of the mold resource data at the operation end of different processes; Step 4: Build a production scheduling model for the mold shop based on the production volume data of each processing step and mold; Step 5: Maintain and control the production inspection of the mold according to the set operation behaviors of the mold resources in different processes; The step 1 comprises the following steps: Step 11: Divide the mold processing area into multiple collection grids of the same size. According to the number of tags defined in the actual collection range, arrange multiple sensor devices within the grid range. Mark each small grid as an area, and select one of them as the collection reference node. Step 12: Use sensor equipment to detect and collect various production status data during the mold processing process, including monitoring the initial temperature, processing temperature, and shutdown temperature of the mold processing through a temperature sensor, monitoring the real-time production pressure through a pressure sensor, and the system generates a pressure production curve. The weight sensor is installed in the weight detection end to measure the weight data of the finished product; Step 13: Store all sample data of collected measurement records into the database, select valid data to match the data with the process location modeling, and process the data to be modeled according to the positioning algorithm of the data corresponding to the process, and obtain the results to determine the specific location of the label; The step 2 comprises the following steps: Step 21: Complete the classification of all collected data, determine the operations of mold business and each process management requirement through the production volume data of each mold production line, abstract it into objects, summarize and integrate the objects, draw the top-level class diagram, organize the connections between classes based on the top-level class diagram, and obtain the relationship diagram; Step 22: Use image acquisition equipment to collect and mark the operation behavior data of the user at the operation end of each process. When the operation behavior that affects the mold processing production is determined according to the set threshold, the system automatically marks the operation behavior and records the triggering behavior data including alarm behavior and production stop behavior triggered by the corresponding operation behavior; Step 23: Upload the collected and marked mold resource data, operation behavior data and trigger behavior data to the cloud through the industrial network of the mold production workshop, and build a data statistical analysis model with three dimensions of mold production status data, operation behavior data and trigger behavior data through artificial intelligence; The step three comprises the following steps: Step 31: Classify the domain knowledge of the mold digital workshop into classes, relationships, and attributes, divide all mold categories according to mold material attributes, and perform feature system modeling based on the mold resource data after system classification; Step 32: Structuring the mold resource data based on data features, and using the classified structured data to classify the process-feature system according to the data features of the mold resource data at the operation end of different processes; Step 33: During the mold production process, the operator performs process operations and marks each process. If the operation is qualified, the next process will be entered. If the operation is unqualified, the operation behavior will be marked. Based on each process, the correlation between the production status data in the mold production process and the operation behavior data of the operator end user is extracted to build a relationship link; The step 4 comprises the following steps: Step 41: According to the actual production data volume of the mold workshop and the master production plan, the associated production scheduling template and planning node data are integrated to form the production scheduling data, and the processing time required for each mold in each process is calculated. The production scheduling data is processed by using the relationship between the production capacity of each process and the planned demand; Step 42: Initialize the basic parameter information of the mold and production scheduling, initialize the scheduling constraints, sort the processes from the largest to the smallest according to the processing time of each process, and select the process that meets the current processing scheduling constraints from the sorting results; Step 43: add the production data with the production status of being processed to the running list, subtract the planned start time of each production data in the running list from the current system time, obtain the remaining working hours of each production data in processing, change the planned start time of each production data in the running list to the current system time, and the planned end time is the current system time plus the remaining working hours, output the production data in the running list and enter the result list for operation; Step 44: synchronously remove the production data with the production status of being processed, determine the production order of the production data based on the production process flow chart, obtain a new production data running list, loop the data in the new production data running list, mark the first data of the running, calculate the reduced start time of the first data of the marked running by the production data preliminary scheduling method, and determine whether the list is completely cycled; The step five comprises the following steps: Step 51: After the mold production information is saved based on the production schedule, when the mold production schedule is enabled, maintenance plan data is automatically generated, and a maintenance plan is generated according to the rules of life cycle and maintenance frequency; Step 52: Setting the maintenance cycle and frequency of the system in the initial operation stage based on experience, setting the maintenance content based on the mold production status data, and using the relationship link between the established production status data and the operation behavior data to identify the mold damage type in the production stage combined with the experience value of the mold production status data failure; Step 53: At the same time, according to the production status data of the mold within the set time period and the operation data of the operation end of each process, the differentiated frequency and content are formulated, and the mold differentiation is maintained and managed using digitalization and big data.

Images