Intelligent manufacturing resource management and control method and system based on industrial interconnection data

Abstract

The present invention discloses an intelligent manufacturing resource management and control method and system based on industrial interconnection data, relates to the field of intelligent manufacturing technology, and realizes comprehensive, real-time and accurate management of production resources through refined data processing; the method first constructs a data collection module for production equipment, equipment components and workshops to provide a basis for data analysis; uses a preset model to analyze layer by layer to obtain status data at all levels from components to workshops; establishes corresponding association relationships between data, delineates feature segments and configures labels to form feature label association groups; constructs a feature segment association library as a basis for subsequent early warning and decision-making; matches the multi-level data groups collected in real time with the association library, screens out the most suitable feature segment association group, and realizes production early warning. The present invention effectively improves the management and control efficiency and accuracy of intelligent manufacturing resources by constructing a complete data processing and analysis system, and provides strong support for the intelligent upgrading of the manufacturing industry.

Description

Technical Field

[0001] The present invention relates to the field of intelligent manufacturing technology, and in particular to an intelligent manufacturing resource management and control method and system based on industrial interconnection data. Background Art

[0002] Driven by the wave of Industry 4.0 and smart manufacturing, the manufacturing industry is accelerating its transformation towards digitalization, networking and intelligence. However, in this transformation process, how to efficiently integrate, deeply analyze and utilize the massive and heterogeneous industrial Internet data generated in industrial production to achieve precise control of smart manufacturing resources has become a key issue that needs to be solved urgently. The traditional production management method that relies on manual experience can no longer meet the rapidly changing production needs and the increasingly complex production environment. Problems such as delayed equipment failure prediction, rigid production scheduling, and inefficient resource allocation frequently occur, which seriously restricts production efficiency, product quality and cost control. Summary of the invention

[0003] The object of the present invention is to provide a manufacturing resource management method and system capable of providing early warning of production anomalies.

[0004] The present invention discloses a method for intelligent manufacturing resource management and control based on industrial interconnection data, including:

[0005] Establish a production equipment collection module for different production equipment in the production workshop, establish an equipment component collection module for several equipment components of each production equipment, and establish a workshop collection module for different production workshops;

[0006] Acquire the sensor status data of different collection nodes, and determine the equipment component to which the collection node belongs based on the equipment component to which it belongs, determine the component status data based on the analysis of the sensor status data by the component status analysis model preset by the equipment component collection module, determine the production equipment status data based on the analysis of the component status data by the equipment status analysis model preset by the production equipment collection module, and determine the workshop status data based on the analysis of the production equipment status data by the workshop status analysis model corresponding to the workshop collection module;

[0007] Establish corresponding association relationships among sensor status data, component status data, production equipment status data and workshop status data, respectively delineate characteristic sections for sensor status data, component status data, production equipment status data and workshop status data, and configure characteristic tags for each characteristic section. Perform relationship analysis for different characteristic tags for several different time periods, determine the association between different characteristic tags on the timeline, and form a characteristic tag association group.

[0008] Based on the feature tag association group, the association relationship between different feature segments is determined to form a feature segment association group, and the combination of several feature segment association groups is recorded as a feature segment association library;

[0009] The sensor status data, component status data, production equipment status data and workshop status data collected in real time are recorded as real-time multi-level data groups. The feature segment association group that best matches the real-time multi-level data group is screened out in the feature segment association library, and production early warning is performed based on the most suitable feature segment association group.

[0010] In some embodiments disclosed in the present invention, a method for analyzing state data based on a state analysis model includes:

[0011] Acquire a number of state factor parameters, and respectively configure the state factor parameters of each category on the time axis to form a number of state factor parameter curves;

[0012] Several levels of parameter boundary intervals are set for each category of state factor parameter curves, and mapping features of each category of state factor parameter curves within the parameter boundary intervals are identified as state data.

[0013] In some embodiments disclosed in the present invention, the mapping characteristics of the state factor parameter curve within the parameter boundary interval include:

[0014] The parameter boundary interval to which the state factor parameter curve belongs, the time retention ratio within the parameter boundary interval, and the fluctuation parameter of the state factor parameter curve;

[0015] The time retention ratio in the parameter boundary interval is the ratio of the retention time in the parameter boundary interval to which the state factor parameter curve belongs within the preset time period;

[0016] Among them, the determination method of the fluctuation parameter of the state factor parameter curve includes:

[0017] Calculate the number of peak points of the state factor parameter curve within a preset time period, determine the state factor parameter difference between adjacent peak points, and calculate the average value of the state factor parameter difference, recorded as the average state parameter difference, and determine the fluctuation parameter of the fluctuation factor parameter curve based on the number of peak points and the average state parameter difference;

[0018] The expression for calculating the fluctuation parameter is: ;

[0019] Among them, F is the fluctuation parameter, L is the fluctuation parameter conversion coefficient, u is the number of peak points, h is the average state parameter difference, R is the fluctuation impact adjustment coefficient, and b is the fluctuation impact adjustment constant.

[0020] In some embodiments disclosed in the present invention, the method for defining characteristic segments of state data includes:

[0021] Establishing a time reference line, and configuring the state data corresponding to different time segments on the time reference line, and analyzing the change of the state data corresponding to the time reference line, including the up and down fluctuation of each state factor data and the up and down fluctuation range;

[0022] The changes in the state data corresponding to adjacent and continuous time segments are analyzed, and the state data whose changes meet the preset standards are correlated to form feature segments. The method for judging whether the changes meet the preset standards includes that the cumulative fluctuation amplitude of the monotonic upward fluctuation or monotonic downward fluctuation of each state factor data within the preset time period meets the preset fluctuation amplitude range, and also includes, within the preset time length, judging the ups and downs fluctuation of each state factor data and whether the ups and downs fluctuation amplitudes are periodic.

[0023] In some embodiments disclosed in the present invention, the feature tag includes the time length of the feature segment mapping, the type of the mapped state data, and the state degree of the mapped state data;

[0024] The method for determining the status degree of the mapped status data includes:

[0025] A factor data interval is set for each state factor data in the state data, the factor data interval to which each state factor data in the state data belongs is determined, and a combination of several factor data intervals corresponding to the state data is recorded as a factor data interval group;

[0026] Corresponding status levels are set for different factor data interval groups, and the status level corresponding to the status data is determined based on the factor data interval group corresponding to the status data.

[0027] In some embodiments disclosed in the present invention, a method for determining the association between different feature tags on a timeline includes:

[0028] A time period is selected as a pre-analysis time period, and within a number of consecutive pre-analysis time periods, the repetition frequency of each feature tag is determined, and the feature tag with the lowest repetition frequency is determined and recorded as the lowest frequency feature tag;

[0029] The time period of the lowest frequency feature tag is gradually expanded until the time period is expanded to a point where all feature tags can appear at least once. The time period at this time is recorded as the locked time period, and the feature tags in the locked time period are associated, and the respective time nodes of the feature tags on the timeline are recorded to form a feature tag association group.

[0030] In some embodiments disclosed in the present invention, a method for selecting a feature segment association group that best matches a real-time multi-level data group from a feature segment association library includes:

[0031] Analyze the real-time multi-level data group, and compare the corresponding state data with different characteristic segment association groups according to the time correspondence, and determine the corresponding sub-parameters of the state data corresponding to different time segments and the characteristic segment association groups;

[0032] Based on the matching sub-parameters corresponding to different time segments, the matching degree between the feature segment association group and the real-time multi-level data group is determined, and based on the matching degree, the most suitable feature segment association group is determined.

[0033] In some embodiments disclosed in the present invention, the method for determining the degree of matching between the feature segment association group and the real-time multi-level data group includes:

[0034] Determine a number of time segments corresponding to the characteristic segment association group, form a time segment corresponding template, and determine the state data corresponding to the real-time multi-level data group based on the time segment corresponding template, which is recorded as the real-time multi-level data group segment;

[0035] Comparing the real-time multi-level data group segment with the corresponding feature segment in the feature segment association group to determine the matching sub-parameter, and determining the matching degree between the feature segment association group and the real-time multi-level data group based on the matching sub-parameter corresponding to each feature segment;

[0036] ;

[0037] Where P is the matching degree between the feature segment association group and the real-time multi-level data group, is the judgment function for the consistency between the t-th feature segment and the real-time multi-level data group segment. If the difference between the t-th feature segment and the real-time multi-level data group segment is less than or equal to the preset value, then Output 1, is the preset weight coefficient of the tth feature segment, T is the total number of feature segments, K is the feature segment matching influence coefficient, and c is the feature segment matching influence constant.

[0038] In some embodiments disclosed in the present invention, an intelligent manufacturing resource management and control system based on industrial Internet data is also disclosed, including:

[0039] The first module is used to establish a production equipment collection module for different production equipment in a production workshop, establish an equipment component collection module for several equipment components of each production equipment, and establish a workshop collection module for different production workshops;

[0040] The second module is used to obtain the sensor status data of different collection nodes, and determine the equipment component collection module to which the collection node belongs based on the equipment component to which the collection node belongs, analyze the sensor status data based on the component status analysis model preset by the equipment component collection module, determine the component status data, analyze the component status data based on the equipment status analysis model preset by the production equipment collection module, determine the production equipment status data, and analyze the production equipment status data based on the workshop status analysis model corresponding to the workshop collection module, determine the workshop status data;

[0041] The third module is used to establish the corresponding association relationship between sensor status data, component status data, production equipment status data and workshop status data, respectively delineate characteristic sections for sensor status data, component status data, production equipment status data and workshop status data, and configure characteristic tags for each characteristic section, perform relationship analysis for different characteristic tags for several different time periods, determine the association between different characteristic tags on the timeline, and form a characteristic tag association group;

[0042] The fourth module is used to determine the association relationship between different feature segments based on the feature tag association group, form a feature segment association group, and record the combination of several feature segment association groups as a feature segment association library;

[0043] The fifth module is used to record the sensor status data, component status data, production equipment status data and workshop status data collected in real time as a real-time multi-level data group, screen out the feature segment association group that best matches the real-time multi-level data group in the feature segment association library, and perform production warning based on the most suitable feature segment association group.

[0044] The present invention discloses an intelligent manufacturing resource management and control method and system based on industrial interconnection data, relates to the field of intelligent manufacturing technology, and realizes comprehensive, real-time and accurate management of production resources through refined data processing; the method first constructs a data collection module for production equipment, equipment components and workshops to provide a basis for data analysis; uses a preset model to analyze layer by layer to obtain status data at all levels from components to workshops; establishes corresponding association relationships between data, delineates feature segments and configures labels to form feature label association groups; constructs a feature segment association library as a basis for subsequent early warning and decision-making; matches the multi-level data groups collected in real time with the association library, screens out the most suitable feature segment association group, and realizes production early warning. The present invention effectively improves the management and control efficiency and accuracy of intelligent manufacturing resources by constructing a complete data processing and analysis system, and provides strong support for the intelligent upgrading of the manufacturing industry.

[0045] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 This is a method step diagram of the intelligent manufacturing resource management and control method based on industrial Internet data disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0047] The technical solution of the present invention is further described below through the accompanying drawings and embodiments.

[0048] The following will be combined with the accompanying drawings and specific embodiments to clearly and completely describe the technical solution of the present invention. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention and cannot be understood as limiting the scope of protection of the present invention. Those skilled in the art in this field can make some non-essential improvements and adjustments based on the content of the present invention described below. In the present invention, unless otherwise clearly specified and limited, the technical terms used in the present invention should be the common meanings understood by the technical personnel described in the present invention.

[0049] Example:

[0050] The present invention discloses a method for intelligent manufacturing resource management and control based on industrial interconnection data. Figure 1 ,include:

[0051] Step S100, establishing a production equipment collection module for different production equipment in a production workshop, establishing an equipment component collection module for several equipment components of each production equipment, and establishing a workshop collection module for different production workshops.

[0052] In the intelligent manufacturing system, the data collection module is the basis for realizing resource control and interoperability. This module effectively integrates various information on the production site by building a three-level data collection system for production equipment, equipment components and workshops. The production equipment collection module focuses on collecting key data such as the operating status and production efficiency of a single device; the equipment component collection module goes deep into the equipment to monitor detailed information such as the wear, temperature, and vibration of each component; the workshop collection module is responsible for integrating macro data such as the production progress, material consumption, and personnel arrangements of the entire workshop. This hierarchical data collection method not only ensures the comprehensiveness and accuracy of the data, but also provides a solid foundation for subsequent data analysis and intelligent decision-making. At the same time, the data collection module also takes into account the resource model in the industrial Internet environment, and includes the industrial manufacturing resource object model of the equipment in the collection scope, providing data support for subsequent resource interoperability.

[0053] Step S200, obtain the sensor status data of different collection nodes, and determine the equipment component collection module to which the collection node belongs based on the equipment component to which the collection node belongs, determine the component status data based on the analysis of the sensor status data by the component status analysis model preset by the equipment component collection module, determine the production equipment status data based on the analysis of the component status data by the equipment status analysis model preset by the production equipment collection module, and determine the workshop status data based on the analysis of the production equipment status data by the workshop status analysis model corresponding to the workshop collection module.

[0054] Based on the data collection module, step S200 further realizes the collection and analysis of production data. Through various sensors and transmission networks deployed at the industrial site, the status data of production equipment, such as temperature, pressure, flow, etc., are collected in real time. At the same time, the collected data is deeply mined and analyzed using the preset component status analysis model, equipment status analysis model and workshop status analysis model. These models are based on advanced technologies such as machine learning, big data analysis or algorithm analysis, and can automatically identify abnormal conditions in the production process, predict equipment failures, evaluate production efficiency, etc. Through the analysis results, problems in the production process can be discovered in a timely manner, providing strong support for subsequent early warning and decision-making. In addition, the data analysis process also takes into account the correlation between resource models to ensure the accuracy and comprehensiveness of the analysis results.

[0055] In some embodiments disclosed in the present invention, a method for analyzing state data based on a state analysis model includes:

[0056] Step S201, obtaining a plurality of state factor parameters, and respectively configuring each category of the state factor parameters on the time axis to form a plurality of categories of state factor parameter curves.

[0057] State factor parameters are key indicators that reflect the current state of a system or device. Their changes over time can reveal the dynamic performance characteristics of the system or device. By configuring these parameters on the timeline, we can intuitively observe their changing trends, thereby providing basic data for subsequent analysis. At the same time, classifying state factor parameters helps us more accurately grasp the performance of different aspects of the system or device, providing strong support for subsequent state evaluation.

[0058] Step S202: a plurality of parameter boundary intervals are set for each category of state factor parameter curves, and mapping features of each category of state factor parameter curves within the parameter boundary intervals are identified as state data.

[0059] The parameter demarcation intervals are carefully set according to the performance requirements and historical data of the system or equipment. They can help us distinguish different status levels, such as normal, warning, danger, etc. By mapping the state factor parameter curve with these intervals, we can extract key features that reflect the state of the system or equipment, such as the maximum value, minimum value, average value, rate of change, etc. of the parameter value. These features, as state data, provide an important basis for us to evaluate the current state of the system or equipment, predict future trends, and discover potential problems. Through the close combination of these two steps, we can achieve comprehensive, real-time, and accurate monitoring and analysis of the system or equipment status, and provide strong support for decision-making in the fields of industrial production, equipment management, fault diagnosis, etc.

[0060] In some embodiments disclosed in the present invention, the mapping characteristics of the state factor parameter curve within the parameter boundary interval include:

[0061] The parameter boundary interval to which the state factor parameter curve belongs, the time retention ratio within the parameter boundary interval, and the fluctuation parameter of the state factor parameter curve.

[0062] The time retention ratio within the parameter boundary interval is the ratio of the retention time within the parameter boundary interval to which the state factor parameter curve belongs within the preset time period.

[0063] Among them, the determination method of the fluctuation parameter of the state factor parameter curve includes:

[0064] Calculate the number of peak points of the state factor parameter curve within the preset time period, determine the state factor parameter difference between adjacent peak points, and calculate the average value of the state factor parameter difference, recorded as the average state parameter difference, and determine the fluctuation parameter of the fluctuation factor parameter curve based on the number of peak points and the average state parameter difference.

[0065] The expression for calculating the fluctuation parameter is: .

[0066] Among them, F is the fluctuation parameter, L is the fluctuation parameter conversion coefficient, u is the number of peak points, h is the average state parameter difference, R is the fluctuation impact adjustment coefficient, and b is the fluctuation impact adjustment constant.

[0067] Step S300, establish corresponding association relationships among sensor status data, component status data, production equipment status data and workshop status data, delineate characteristic segments for the sensor status data, component status data, production equipment status data and workshop status data respectively, configure characteristic tags for each characteristic segment, perform relationship analysis for different characteristic tags for several different time periods, determine the association between different characteristic tags on the timeline, and form a characteristic tag association group.

[0068] Step S300 aims to establish the association relationship between production data and extract representative feature segments and labels. By establishing data associations between equipment components, equipment and workshops, the inherent connections and laws in the production process can be revealed. For example, abnormal wear of a certain component may cause the performance of the entire equipment to decline, thereby affecting the production efficiency of the entire workshop. Through feature extraction technology, key information such as the duration of the abnormal state, the scope of impact, etc. can be screened out from massive data to form feature segments and labels. These feature segments and labels provide important reference for subsequent intelligent early warning and decision-making. At the same time, the feature extraction process also combines the characteristics of the resource model to ensure that the extracted features can accurately reflect the actual status of the resources.

[0069] In some embodiments disclosed in the present invention, the method for defining characteristic segments of state data includes:

[0070] Step S301, establish a time reference line, and configure the state data corresponding to different time segments on the time reference line, and analyze the changes of the state data corresponding to the time reference line, including the up and down fluctuations of each state factor data and the up and down fluctuation range.

[0071] Step S302, analyze the changes in the state data corresponding to adjacent and continuous time segments, and correlate the state data whose changes meet the preset standards to form feature segments. The method for judging whether the changes meet the preset standards includes that the cumulative fluctuation amplitude of the monotonic upward fluctuation or monotonic downward fluctuation of each state factor data within the preset time period meets the preset fluctuation amplitude range, and also includes, within the preset time length, judging the ups and downs fluctuation of each state factor data and whether the ups and downs fluctuation amplitudes are periodic.

[0072] In some embodiments disclosed in the present invention, the feature tag includes the time length of the feature segment mapping, the type of the mapped state data, and the state degree of the mapped state data;

[0073] The method for determining the status degree of the mapped status data includes:

[0074] A factor data interval is set for each state factor data in the state data, the factor data interval to which each state factor data in the state data belongs is determined, and a combination of several factor data intervals corresponding to the state data is recorded as a factor data interval group.

[0075] Corresponding status levels are set for different factor data interval groups, and the status level corresponding to the status data is determined based on the factor data interval group corresponding to the status data.

[0076] In some embodiments disclosed in the present invention, a method for determining the association between different feature tags on a timeline includes:

[0077] Step S303, selecting a time period as a pre-analysis time period, determining the repetition frequency of each feature tag within a number of consecutive pre-analysis time periods, determining the feature tag with the lowest repetition frequency, and recording it as the lowest frequency feature tag.

[0078] Step S304, gradually expand the time period of the lowest frequency feature tag as a benchmark until the time period is expanded to a point where all feature tags can appear at least once, record the time period at this time as the locked time period, associate the feature tags in the locked time period, and record the respective time nodes of the feature tags on the timeline to form a feature tag association group.

[0079] Step S400 , based on the feature tag association group, determining the association relationship between different feature segments to form a feature segment association group, and recording a combination of several feature segment association groups as a feature segment association library.

[0080] Step S400 further constructs a feature segment association library based on step S300. The association library stores the associations between different feature segments and the changes in these associations on the timeline. By monitoring the state changes of the resource model in real time, the content of the association library is dynamically adjusted to ensure the accuracy and timeliness of the associations. For example, when the resource model of a certain device changes, the association between its feature segment and other devices may also change. At this time, the association library needs to update this information in a timely manner to reflect the latest production status. The purpose of building a feature segment association library is to provide comprehensive data support for intelligent early warning and decision-making, to help the system quickly identify abnormal conditions in the production process, and to take corresponding countermeasures.

[0081] Step S500, the sensor status data, component status data, production equipment status data and workshop status data collected in real time are recorded as a real-time multi-level data group, the feature segment association group that best matches the real-time multi-level data group is screened out in the feature segment association library, and production warning is performed based on the most suitable feature segment association group.

[0082] Step S500 is the core link of the entire technical solution, which realizes the real-time warning and decision support functions. In the real-time warning stage, the system combines the status information of the feature segment association library and the resource model to quickly identify and warn production anomalies. When an abnormality is detected in a certain feature segment, the system immediately triggers the early warning mechanism to notify relevant personnel or systems to take countermeasures. In the decision support stage, the system uses the interoperability of resource models to realize cross-system and cross-platform resource scheduling and optimization decisions. For example, when a workshop has a problem of low production efficiency, the system can automatically schedule idle resources in other workshops, or optimize the production process of the current workshop to improve overall production efficiency. This data-driven decision support method not only improves the scientificity and accuracy of decision-making, but also enhances the flexibility and responsiveness of the manufacturing system.

[0083] In some embodiments disclosed in the present invention, a method for selecting a feature segment association group that best matches a real-time multi-level data group from a feature segment association library includes:

[0084] Step S501, analyzing the real-time multi-level data group, and comparing the corresponding state data with different characteristic segment association groups according to the time correspondence, to determine the matching sub-parameters of the state data corresponding to different time segments and the characteristic segment association groups;

[0085] Step S502, based on the matching sub-parameters corresponding to different time segments, the matching degree between the feature segment association group and the real-time multi-level data group is determined, and based on the matching degree, the most suitable feature segment association group is determined.

[0086] In some embodiments disclosed in the present invention, the method for determining the degree of matching between the feature segment association group and the real-time multi-level data group includes:

[0087] Step S5021, determining a number of time segments corresponding to the characteristic segment association group, forming a time segment corresponding template, and determining the state data corresponding to the real-time multi-level data group based on the time segment corresponding template, and recording it as the real-time multi-level data group segment;

[0088] Step S5022, comparing the real-time multi-level data group segment with the corresponding feature segment in the feature segment association group to determine the matching sub-parameter, and based on the matching sub-parameter corresponding to each feature segment, determining the matching degree between the feature segment association group and the real-time multi-level data group;

[0089] ;

[0090] Where P is the matching degree between the feature segment association group and the real-time multi-level data group, is the judgment function for the consistency between the t-th feature segment and the real-time multi-level data group segment. If the difference between the t-th feature segment and the real-time multi-level data group segment is less than or equal to the preset value, then Output 1, is the preset weight coefficient of the tth feature segment, T is the total number of feature segments, K is the feature segment matching influence coefficient, and c is the feature segment matching influence constant.

[0091] In some embodiments disclosed in the present invention, an intelligent manufacturing resource management and control system based on industrial Internet data is also disclosed, including:

[0092] The first module is used to establish a production equipment collection module for different production equipment in a production workshop, establish an equipment component collection module for several equipment components of each production equipment, and establish a workshop collection module for different production workshops;

[0093] The second module is used to obtain the sensor status data of different collection nodes, and determine the equipment component collection module to which the collection node belongs based on the equipment component to which the collection node belongs, analyze the sensor status data based on the component status analysis model preset by the equipment component collection module, determine the component status data, analyze the component status data based on the equipment status analysis model preset by the production equipment collection module, determine the production equipment status data, and analyze the production equipment status data based on the workshop status analysis model corresponding to the workshop collection module, determine the workshop status data;

[0094] The third module is used to establish the corresponding association relationship between sensor status data, component status data, production equipment status data and workshop status data, respectively delineate characteristic sections for sensor status data, component status data, production equipment status data and workshop status data, and configure characteristic tags for each characteristic section, perform relationship analysis for different characteristic tags for several different time periods, determine the association between different characteristic tags on the timeline, and form a characteristic tag association group;

[0095] The fourth module is used to determine the association relationship between different feature segments based on the feature tag association group, form a feature segment association group, and record the combination of several feature segment association groups as a feature segment association library;

[0096] The fifth module is used to record the sensor status data, component status data, production equipment status data and workshop status data collected in real time as a real-time multi-level data group, screen out the feature segment association group that best matches the real-time multi-level data group in the feature segment association library, and perform production warning based on the most suitable feature segment association group.

[0097] The present invention discloses an intelligent manufacturing resource management and control method and system based on industrial interconnection data, relates to the field of intelligent manufacturing technology, and realizes comprehensive, real-time and accurate management of production resources through refined data processing; the method first constructs a data collection module for production equipment, equipment components and workshops to provide a basis for data analysis; uses a preset model to analyze layer by layer to obtain status data at all levels from components to workshops; establishes corresponding association relationships between data, delineates feature segments and configures labels to form feature label association groups; constructs a feature segment association library as a basis for subsequent early warning and decision-making; matches the multi-level data groups collected in real time with the association library, screens out the most suitable feature segment association group, and realizes production early warning. The present invention effectively improves the management and control efficiency and accuracy of intelligent manufacturing resources by constructing a complete data processing and analysis system, and provides strong support for the intelligent upgrading of the manufacturing industry.

[0098] In the process of implementing the above technical solutions, an enhanced modeling solution for heterogeneous manufacturing resources can be applied, namely the industrial manufacturing resource object model and the industrial object metamodel solution; a model-based resource interoperability interaction scenario is designed to determine the functional and non-functional requirements that need to be met by the interoperability solutions of intelligent manufacturing resources and their models; functional requirements include achieving real-time response, state synchronization, method calls, etc.

[0099] Determine the software and hardware configuration of the key physical resources and runtime environment of the manufacturing workshop. Based on the general intelligent implementation plan for underlying processing and manufacturing resources, introduce real-time equipment and technologies such as RTX real-time system, reflective memory card (RMC), fiber optic equipment, and RTTCP / IP protocol. This provides a real-time hardware foundation for key manufacturing equipment and prepares a flexible real-time operating environment for heterogeneous equipment and upper-level scheduling strategies.

[0100] The topology structure of the underlying resources is planned, and a hybrid topology consisting of P2P and centralized topologies is used to avoid the potential risk of single-point failure in the centralized topology and overcome the complexity of the P2P routing strategy. In the resource initialization and management links, a centralized topology structure is used for resource addressing, interaction matching, and data routing operations. When data interactions are frequent, the P2P topology mode is used to disperse the pressure on the central node and avoid line overload.

[0101] A smart manufacturing resource interoperability solution for the industrial Internet environment was constructed; the logical architecture of the solution is divided into five layers: physical layer, runtime environment layer, manufacturing resource model layer, industrial object transmission layer and collaborative optimization application layer; at the physical layer, a hybrid structure of P2P topology and centralized topology is adopted to meet the needs of industrial object transmission technology; at the runtime environment layer, real-time intelligent upgrades are performed on physical nodes; at the manufacturing resource model layer, multi-source heterogeneous resources are scientifically described and encapsulated; at the industrial object transmission layer, a dual-channel communication mechanism is implemented to connect the underlying resources and the upper-level collaborative optimization algorithm services; at the collaborative optimization application layer, real-time analysis of dynamic key manufacturing information models is achieved, optimization decision support is provided, and a complete industrial Internet ecosystem is built; through the implementation of this solution, the real-time response of underlying resources to the upper-level scheduling algorithm and the low-latency perception feedback of the manufacturing status are successfully achieved, providing a solid technical foundation for the further development of smart manufacturing.

[0102] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present invention can be implemented by hardware, or by software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each implementation scenario of the present invention.

[0103] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.

Claims

1. An intelligent manufacturing resource management and control method based on industrial Internet data, characterized in that: include: Establish a production equipment collection module for different production equipment in the production workshop, establish an equipment component collection module for several equipment components of each production equipment, and establish a workshop collection module for different production workshops; Acquire the sensor status data of different collection nodes, and determine the equipment component to which the collection node belongs based on the equipment component to which it belongs, determine the component status data based on the analysis of the sensor status data by the component status analysis model preset by the equipment component collection module, determine the production equipment status data based on the analysis of the component status data by the equipment status analysis model preset by the production equipment collection module, and determine the workshop status data based on the analysis of the production equipment status data by the workshop status analysis model corresponding to the workshop collection module; Establish corresponding association relationships among sensor status data, component status data, production equipment status data and workshop status data, respectively delineate characteristic sections for sensor status data, component status data, production equipment status data and workshop status data, and configure characteristic tags for each characteristic section. Perform relationship analysis for different characteristic tags for several different time periods, determine the association between different characteristic tags on the timeline, and form a characteristic tag association group. Based on the feature tag association group, the association relationship between different feature segments is determined to form a feature segment association group, and the combination of several feature segment association groups is recorded as a feature segment association library; The sensor status data, component status data, production equipment status data and workshop status data collected in real time are recorded as a real-time multi-level data group, and the feature segment association group that best matches the real-time multi-level data group is selected from the feature segment association library, and production early warning is performed based on the most suitable feature segment association group; Based on the state analysis model, the methods for analyzing the state data include: Acquire a number of state factor parameters, and respectively configure the state factor parameters of each category on the time axis to form a number of state factor parameter curves; A number of parameter boundary intervals are set for each category of state factor parameter curves, and mapping features of each category of state factor parameter curves within the parameter boundary intervals are identified as state data; The mapping characteristics of the state factor parameter curve within the parameter boundary range include: The parameter boundary interval to which the state factor parameter curve belongs, the time retention ratio within the parameter boundary interval, and the fluctuation parameter of the state factor parameter curve; The time retention ratio in the parameter boundary interval is the ratio of the retention time in the parameter boundary interval to which the state factor parameter curve belongs within the preset time period; Among them, the determination method of the fluctuation parameter of the state factor parameter curve includes: Calculate the number of peak points of the state factor parameter curve within a preset time period, determine the state factor parameter difference between adjacent peak points, and calculate the average value of the state factor parameter difference, recorded as the average state parameter difference, and determine the fluctuation parameter of the fluctuation factor parameter curve based on the number of peak points and the average state parameter difference; The expression for calculating the fluctuation parameter is: ; Among them, F is the fluctuation parameter, L is the fluctuation parameter conversion coefficient, u is the number of peak points, h is the average state parameter difference, R is the fluctuation impact adjustment coefficient, and b is the fluctuation impact adjustment constant.

2. The intelligent manufacturing resource management and control method based on industrial interconnection data according to claim 1 is characterized in that: Methods for defining characteristic segments of state data include: Establishing a time reference line, and configuring the state data corresponding to different time segments on the time reference line, and analyzing the change of the state data corresponding to the time reference line, including the up and down fluctuation of each state factor data and the up and down fluctuation range; The changes in the state data corresponding to adjacent and continuous time segments are analyzed, and the state data whose changes meet the preset standards are correlated to form feature segments. The method for judging whether the changes meet the preset standards includes that the cumulative fluctuation amplitude of the monotonic upward fluctuation or monotonic downward fluctuation of each state factor data within the preset time period meets the preset fluctuation amplitude range, and also includes, within the preset time length, judging the ups and downs fluctuation of each state factor data and whether the ups and downs fluctuation amplitudes are periodic.

3. The intelligent manufacturing resource management and control method based on industrial interconnection data according to claim 1 is characterized in that: The feature tag includes the time length of the feature segment mapping, the type of the mapped state data, and the state degree of the mapped state data; The method for determining the status degree of the mapped status data includes: A factor data interval is set for each state factor data in the state data, the factor data interval to which each state factor data in the state data belongs is determined, and a combination of several factor data intervals corresponding to the state data is recorded as a factor data interval group; Corresponding status levels are set for different factor data interval groups, and the status level corresponding to the status data is determined based on the factor data interval group corresponding to the status data.

4. The intelligent manufacturing resource management and control method based on industrial interconnection data according to claim 1 is characterized in that: Methods for determining the association between different feature labels on the timeline include: A time period is selected as a pre-analysis time period, and within a number of consecutive pre-analysis time periods, the repetition frequency of each feature tag is determined, and the feature tag with the lowest repetition frequency is determined and recorded as the lowest frequency feature tag; The time period of the lowest frequency feature tag is gradually expanded until the time period is expanded to a point where all feature tags can appear at least once. The time period at this time is recorded as the locked time period, and the feature tags in the locked time period are associated, and the respective time nodes of the feature tags on the timeline are recorded to form a feature tag association group.

5. The intelligent manufacturing resource management and control method based on industrial interconnection data according to claim 1 is characterized in that: The method of selecting the feature segment association group that best matches the real-time multi-level data group from the feature segment association library includes: Analyze the real-time multi-level data group, and compare the corresponding state data with different characteristic segment association groups according to the time correspondence, and determine the corresponding sub-parameters of the state data corresponding to different time segments and the characteristic segment association groups; Based on the matching sub-parameters corresponding to different time segments, the matching degree between the feature segment association group and the real-time multi-level data group is determined, and based on the matching degree, the most suitable feature segment association group is determined.

6. The intelligent manufacturing resource management and control method based on industrial interconnection data according to claim 5 is characterized in that: The method for determining the degree of matching between the feature segment association group and the real-time multi-level data group includes: Determine a number of time segments corresponding to the characteristic segment association group, form a time segment corresponding template, and determine the state data corresponding to the real-time multi-level data group based on the time segment corresponding template, which is recorded as the real-time multi-level data group segment; Comparing the real-time multi-level data group segment with the corresponding feature segment in the feature segment association group to determine the matching sub-parameter, and determining the matching degree between the feature segment association group and the real-time multi-level data group based on the matching sub-parameter corresponding to each feature segment; ; Where P is the matching degree between the feature segment association group and the real-time multi-level data group, is the judgment function for the consistency between the t-th feature segment and the real-time multi-level data group segment. If the difference between the t-th feature segment and the real-time multi-level data group segment is less than or equal to the preset value, then Output 1, is the preset weight coefficient of the tth feature segment, T is the total number of feature segments, K is the feature segment matching influence coefficient, and c is the feature segment matching influence constant.

7. Intelligent manufacturing resource management and control system based on industrial Internet data, characterized by: The method for intelligent manufacturing resource management and control according to any one of claims 1 to 6 comprises: The first module is used to establish a production equipment collection module for different production equipment in a production workshop, establish an equipment component collection module for several equipment components of each production equipment, and establish a workshop collection module for different production workshops; The second module is used to obtain the sensor status data of different collection nodes, and determine the equipment component collection module to which the collection node belongs based on the equipment component to which the collection node belongs, analyze the sensor status data based on the component status analysis model preset by the equipment component collection module, determine the component status data, analyze the component status data based on the equipment status analysis model preset by the production equipment collection module, determine the production equipment status data, and analyze the production equipment status data based on the workshop status analysis model corresponding to the workshop collection module, determine the workshop status data; The third module is used to establish the corresponding association relationship between sensor status data, component status data, production equipment status data and workshop status data, respectively delineate characteristic sections for sensor status data, component status data, production equipment status data and workshop status data, and configure characteristic tags for each characteristic section, perform relationship analysis for different characteristic tags for several different time periods, determine the association between different characteristic tags on the timeline, and form a characteristic tag association group; The fourth module is used to determine the association relationship between different feature segments based on the feature tag association group, form a feature segment association group, and record the combination of several feature segment association groups as a feature segment association library; The fifth module is used to record the sensor status data, component status data, production equipment status data and workshop status data collected in real time as a real-time multi-level data group, screen out the feature segment association group that best matches the real-time multi-level data group in the feature segment association library, and perform production warning based on the most suitable feature segment association group.

Images