Digital factory equipment monitoring system based on big data

Abstract

The invention discloses a digital factory equipment monitoring system based on big data, and relates to the technical field of digital factory equipment monitoring, comprising the following steps: acquiring production and equipment data in a digital factory related to inter-process time intervals, and identifying initial time interval distribution; according to the factory rhythm and the equipment performance, determining an evaluation constraint condition of the time interval between the processes; introducing random changes to the initial time interval distribution to generate different time interval distributions, and randomly permutation and combination different time intervals to generate a plurality of time interval arrays; based on big data analysis, the multiple time interval arrays are applied and monitored, and multi-dimensional quantitative analysis is carried out; according to the multi-dimensional quantitative analysis result and the corresponding process time interval array, a visual analysis model is constructed, data analysis is carried out, a screened process time interval array is obtained, the screened process time interval array is applied to digital factory equipment monitoring, and the problem that the height of the inter-process time interval is lack of precise regulation and control is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of digital factory equipment monitoring, and more specifically, to a digital factory equipment monitoring system based on big data. Background Art

[0002] Digital factory is an intelligent production model based on advanced technologies such as the Internet of Things, big data, artificial intelligence and digital twins, which aims to achieve intelligent monitoring, dynamic adjustment and optimization of the entire production process. In digital factories, factory rhythm control, as an important link to ensure efficient production, is deeply related to a number of technologies, which provide a scientific basis for rhythm control through real-time data collection and analysis.

[0003] Related technologies include the Industrial Internet of Things (IIoT): IIoT collects real-time data (such as equipment operating status, product flow time, etc.) through sensors deployed on equipment and production lines, and transmits the data to the factory management system. Relationship with rhythm control: Through real-time collected production data, the factory management system can understand the current production rhythm and adjust production parameters when necessary.

[0004] Manufacturing Execution System (MES): The MES system integrates various production data in the factory (such as order progress, equipment utilization, production bottlenecks, etc.) to track and optimize the production rhythm in real time. Relationship with rhythm control: MES can dynamically adjust the rhythm of the production line according to order priority and equipment status to ensure maximum resource utilization.

[0005] Big data analysis and prediction: Big data analysis based on historical data and real-time data is used to predict bottlenecks or resource conflicts in the production rhythm. Relationship with rhythm control: Analyze the fluidity of tasks in the production line, predict possible backlogs or resource idleness, and take adjustment measures in advance.

[0006] Digital twin technology: Digital twins use virtual simulation to achieve digital mapping of the factory's physical space, and are used to simulate the operating effects under different production rhythms. Relationship with rhythm control: Before adjusting the factory rhythm, virtual simulation can be used to simulate the impact of different rhythm strategies on overall efficiency, thereby optimizing the control plan.

[0007] Edge computing and adaptive control: Edge computing enables data processing to be completed at edge nodes close to the production site, reducing latency and increasing response speed. Relationship with rhythm control: Edge computing can control the factory rhythm in real time and quickly respond to emergencies (such as equipment failure or order changes).

[0008] For example, the invention patent announcement with announcement number: CN113435773B announces a production progress monitoring method, system and storage medium for a digital factory, including connecting each production equipment in the workshop to a gateway and collecting data in real time to transmit to an equipment monitoring database, using the input contract number to search the contract database according to the contract number to obtain at least one production task number corresponding to the contract, querying the task execution progress data of each production equipment involved in implementing the production task through the production task number, and finally displaying the task execution progress information of each production equipment on a three-dimensional map of the workshop, so that the progress data of each production equipment in the workshop can be specifically displayed in an intuitive way of three-dimensional visualization, whether it is workshop personnel, workshop directors or factory decision makers, they can quickly understand the production equipment involved in each project or contract and their respective completion progress, and realize the status monitoring of the entire workshop on the display terminal.

[0009] For example, the invention patent announcement with announcement number: CN115759698B establishes a method and system for monitoring the production progress data of corrugated base paper based on a digital factory, including making the comparison results of the production monitoring data that needs to be processed and the sample production monitoring data that has been processed be within the configured comparison result interval, thereby improving the problem of unstable noise comparison results between the production monitoring data that needs to be processed and the sample production monitoring data. After projecting the sample production monitoring data that has been processed and the production monitoring data that needs to be processed, one or several sample production monitoring data after projection are used to perform progress monitoring processing on the production monitoring data that needs to be processed, and generate target progress monitoring results corresponding to the production monitoring data that needs to be processed. In this way, the present application can accurately and reliably obtain production monitoring data, ensure the normal operation of production equipment, and thus improve the production efficiency of corrugated base paper.

[0010] The above disclosed technical solutions have at least the following technical problems: In a digital factory, the core of factory rhythm control is to optimize the coordination between various processes, and the time interval between processes, as an important parameter for measuring production continuity, has a direct impact on production efficiency and resource utilization. Too high a time interval between processes may lead to idle resources and a slowdown in production rhythm, which is manifested as idling equipment or workers waiting for the next task to arrive, and overall efficiency declines; while too low a time interval between processes may easily lead to task accumulation or resource conflicts, resulting in equipment overload, confusion between processes, and even bottlenecks or quality problems.

[0011] The existing technology lacks precise control over the time intervals between processes, making it difficult to adapt to the dynamic changes in production rhythm in real time, resulting in frequent idle resources or task backlogs, thereby affecting production efficiency and overall operational stability. In view of the above problems, the present invention proposes a solution. Summary of the invention

[0012] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a digital factory equipment monitoring system based on big data, which evaluates the time intervals between processes to solve the problem of lack of precise regulation of the time intervals between processes, making it difficult to adapt to the dynamic changes in the production rhythm in real time, resulting in frequent idle resources or task backlogs, thereby affecting production efficiency and overall operational stability.

[0013] To achieve the above object, the present invention provides the following technical solutions: The digital factory equipment monitoring system based on big data includes an initial interval distribution identification module, a constraint condition update module, a time interval array generation module, a multidimensional analysis module and a time interval update module: An initial interval distribution identification module is used to obtain production and equipment data in a digital factory related to the time intervals between processes and identify the initial time interval distribution; The constraint updating module is used to determine the evaluation constraints of the time interval between processes according to the factory rhythm and equipment performance; A time interval array generation module is used to introduce random changes to the initial time interval distribution, generate different time interval distributions, randomly arrange and combine different time intervals, and generate multiple time interval arrays; The multi-dimensional analysis module is used to apply and monitor multiple time interval arrays separately based on big data analysis, and conduct multi-dimensional quantitative analysis; The time interval updating module is used to build a visual analysis model based on the multi-dimensional quantitative analysis results and the corresponding process time interval array, and perform data analysis to obtain the screened process time interval array, which is applied to digital factory equipment monitoring.

[0014] It is used to obtain production and equipment data in the digital factory related to the time interval between processes and identify the initial time interval distribution, specifically: Production data includes production process time data, order execution cycle, and production records; Equipment data includes equipment startup and downtime, equipment idle and response time; For each production record, calculate the actual time interval between processes; Calculate basic statistics of time intervals and analyze the distribution characteristics of time intervals through box plots; If the time intervals are concentrated in a certain range and are skewed, choose the gamma distribution; When the time intervals are symmetrically distributed, the normal distribution is selected; The selected distribution model is fitted based on maximum likelihood estimation to obtain the initial time interval distribution.

[0015] According to the factory rhythm and equipment performance, determine the evaluation constraints of the time interval between processes, specifically: According to the overall production goals and process requirements of the factory, the production cycle and rhythm are set, and the time interval between processes must meet the following conditions: ; In the formula, is the execution time of the ith process, is the total number of processes, is the time interval between processes, The maximum total time allowed in the production plan.

[0016] The introduction of random changes to the initial time interval distribution to generate different time interval distributions, and the random arrangement and combination of different time intervals to generate multiple time interval arrays are specifically as follows: A normally distributed random variable is introduced to perturb the time interval, and the change of each time interval follows a normal distribution; After disturbing the time interval between each process, the time intervals are randomly arranged and combined to generate multiple time interval arrays.

[0017] Based on the big data analysis, multiple time interval arrays are applied and monitored respectively, specifically: Each time interval array is directly applied to the production scheduling system of the digital factory as the execution standard of the time interval between processes; The scheduling system adjusts and controls the execution rhythm of each process based on these time interval arrays to ensure that the time intervals between processes meet the predetermined parameters; The monitoring module collects production data, equipment status and actual performance of time intervals in real time, and tracks and records them.

[0018] The multi-dimensional quantitative analysis is specifically as follows: The multidimensional data includes production efficiency data, equipment load utilization data and factory scheduling flexibility data; the production efficiency data includes a production efficiency impact coefficient; the specific method for obtaining the production efficiency impact coefficient is as follows; Obtain the actual processing time and theoretical processing time in the production process at different process time intervals; Calculate the processing time deviation in the production process at different time intervals, and set the data with a deviation less than the preset standard deviation value as an acceptable deviation, and set the data with a deviation greater than the preset standard deviation value as a potential hidden danger deviation; Obtaining processing time deviation values ​​generated at all process time intervals, and comparing these deviation values ​​with preset standard deviation values; All potential hidden danger deviation values ​​are used to establish a hidden danger deviation set, and all acceptable deviation values ​​are used to establish an acceptable deviation set; Data analysis is performed based on the hidden danger deviation set and the acceptable deviation set, and the production efficiency impact coefficient is calculated.

[0019] The equipment load utilization data includes an equipment load utilization influence coefficient; the specific method for obtaining the equipment load utilization influence coefficient is as follows: Obtain the equipment load fluctuations of several equipments at different process time intervals; Calculate the load fluctuation standard deviation and load fluctuation average of several equipment load fluctuations at different process time intervals; Calculate the equipment load fluctuation coefficient of variation based on the load fluctuation standard deviation and load fluctuation average value; The equipment load fluctuation variation coefficient is used to calculate the equipment load utilization impact coefficient based on a preset equipment load utilization impact coefficient calculation formula.

[0020] The factory scheduling flexibility data includes a factory scheduling flexibility influence coefficient; the specific method for obtaining the factory scheduling flexibility influence coefficient is as follows: Based on the production scheduling process under different process time intervals, a set of events of the impact of various scheduling strategies on scheduling flexibility is obtained, wherein the set of events of the impact of various scheduling strategies on scheduling flexibility includes production delays, equipment idleness and resource conflicts caused by various scheduling strategies, and a weighted valuation is performed on the production situation based on historical scheduling data; A regression model is constructed based on the event set and corresponding scores of the impact of various scheduling strategies on scheduling flexibility to generate the impact coefficient of plant scheduling flexibility.

[0021] The visualization analysis model is constructed based on the multi-dimensional quantitative analysis results and the corresponding process time interval array, specifically: Construct a visual analysis model based on a rectangular coordinate system to demonstrate the comprehensive impact of different process time interval arrays in the digital factory application process; The two coordinate systems of the visualization analysis model represent the process time interval evaluation coefficient and the process time interval array respectively; According to the results of multi-dimensional quantitative analysis, the combination of each process time interval array and its corresponding process time interval evaluation coefficient is mapped to a rectangular coordinate system; Each process time interval array corresponds to a point, and the position of the point is determined by the output of multi-dimensional quantitative analysis and the process time interval array; Several points are smoothed by interpolation method to obtain a smooth curve as a visualization analysis model.

[0022] The data analysis is performed to obtain a filtered process time interval array, which is applied to digital factory equipment monitoring, specifically: Filter the process time interval array corresponding to each maximum value of the visual analysis model to obtain a first screening combination; The minimum values ​​of the integrals corresponding to the process time interval arrays in the first screening combination on the visual analysis model are compared, and the process time interval array with the smallest comparison result is used as the screened process time interval array and applied to digital factory equipment monitoring.

[0023] The technical effects and advantages of the digital factory equipment monitoring system based on big data of the present invention are as follows: 1. The present invention can provide data-based decision support for production scheduling by identifying and analyzing the distribution characteristics of time intervals between processes. By introducing random changes and multidimensional analysis, the system can not only optimize production efficiency and improve equipment load balance, but also respond to changes in production rhythm in real time, avoiding idle resources, equipment overload or production delays caused by inaccurate time intervals. Specifically, the production efficiency influence coefficient can ensure the improvement of production process speed, the equipment load utilization influence coefficient ensures the rational use of equipment, and the factory scheduling flexibility influence coefficient optimizes the adjustment and scheduling of production plans. The comprehensive application of these technical means enables digital factories to maintain stable operating efficiency in a dynamically changing production environment, thereby improving the overall operational stability and competitiveness of the factory, reducing resource waste and equipment failure risks, and ensuring the smooth progress of the production process.

[0024] 2. The present invention introduces a time interval update module, combines the multi-dimensional quantitative analysis results and the process time interval array to build a visual analysis model, thereby effectively improving the intelligent level of digital factory equipment monitoring. First, a rectangular coordinate system visualization model is used to intuitively display the relationship between different process time interval arrays and their evaluation coefficients, helping managers to fully understand the comprehensive impact of each process time. The curve is formed by interpolation and smoothing, making the process time interval data more stable and accurate, providing a reliable basis for subsequent data analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a structural schematic diagram of the digital factory equipment monitoring system based on big data of the present invention. DETAILED DESCRIPTION

[0026] 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.

[0027] Embodiment 1, Figure 1 The present invention provides a digital factory equipment monitoring system based on big data, including an initial interval distribution recognition module, a constraint condition update module, a time interval array generation module, a multidimensional analysis module and a time interval update module: The initial interval distribution identification module is used to obtain production and equipment data in a digital factory related to the time intervals between processes and identify the initial time interval distribution.

[0028] The method for acquiring production and equipment data in a digital factory related to the time intervals between processes and identifying the initial time interval distribution is specifically: Production data includes production process time data, order execution cycle, and production records; Equipment data includes equipment startup and downtime, equipment idle and response time; For each production record, calculate the actual time interval between processes; Calculate basic statistics of time intervals and analyze the distribution characteristics of time intervals through box plots; If the time intervals are concentrated in a certain range and are skewed, choose the gamma distribution; When the time intervals are symmetrically distributed, the normal distribution is selected; Fitting the selected distribution model based on maximum likelihood estimation to obtain the initial time interval distribution; It should be noted that the basic statistics include minimum, maximum, mean, standard deviation, skewness and kurtosis; the start time and end time of each process are obtained, and the actual execution time of the process is calculated as the production process time data; the order execution cycle is the start and end time of each order, which can be used to calculate the impact of order execution on the overall process time; Equipment startup and downtime: The startup and downtime of each equipment is used to evaluate whether the equipment has an impact in the intervals between certain processes; Equipment idle and response time: Equipment idle time and response time reflect the role of the equipment in the time intervals between processes.

[0029] The constraint updating module is used to determine the evaluation constraints of the time interval between processes according to the factory rhythm and equipment performance.

[0030] The evaluation constraints for determining the time interval between processes according to the factory rhythm and equipment performance are specifically: According to the overall production goals and process requirements of the factory, the production cycle and rhythm are set, and the time interval between processes must meet the following conditions: ; In the formula, is the execution time of the ith process, is the total number of processes, is the time interval between processes, The maximum total time allowed in the production plan.

[0031] The time interval array generation module is used to introduce random changes to the initial time interval distribution, generate different time interval distributions, randomly arrange and combine different time intervals, and generate multiple time interval arrays.

[0032] The introduction of random changes to the initial time interval distribution to generate different time interval distributions, and the random arrangement and combination of different time intervals to generate multiple time interval arrays are specifically as follows: A normally distributed random variable is introduced to perturb the time interval, and the change of each time interval follows a normal distribution; After disturbing the time interval between each process, the time intervals are randomly arranged and combined to generate multiple time interval arrays.

[0033] The multi-dimensional analysis module is used to apply and monitor multiple time interval arrays separately based on big data analysis, and to perform multi-dimensional quantitative analysis.

[0034] Based on the big data analysis, multiple time interval arrays are applied and monitored respectively, specifically: Each time interval array is directly applied to the production scheduling system of the digital factory as the execution standard of the time interval between processes; The scheduling system adjusts and controls the execution rhythm of each process based on these time interval arrays to ensure that the time intervals between processes meet the predetermined parameters; The monitoring module collects production data, equipment status and actual performance of time intervals in real time, and tracks and records them.

[0035] The multi-dimensional quantitative analysis is specifically as follows: Multi-dimensional data includes production efficiency data, equipment load utilization data, and factory scheduling flexibility data; The production efficiency data includes the production efficiency impact coefficient, the equipment load utilization data includes the equipment load utilization impact coefficient, and the factory scheduling flexibility data includes the factory scheduling flexibility impact coefficient.

[0036] The production efficiency impact coefficient is used to measure the impact of adjusting the time interval between processes on the speed of the production process. Shorter time intervals can improve production efficiency, shorten process waiting time, and increase production output, but they may also cause equipment overload and resource conflicts, thus affecting production stability; while longer time intervals may reduce production efficiency, leading to idleness and delays between processes, thereby reducing overall production progress. This coefficient is used to evaluate the overall effect of the digital factory under different time interval groups, aiming to solve the problem of lack of precise control of the time interval between processes, especially in the dynamically changing production rhythm, to avoid idle resources or task accumulation, and ensure production efficiency and operational stability.

[0037] Analyzing the production efficiency impact coefficient is helpful for evaluating the overall effect of the digital factory under different process time interval groups, solving the problem of lack of precise control of the time interval between processes, difficulty in real-time adaptation to the dynamic changes in the production rhythm, resulting in frequent idle resources or task accumulation, thus affecting production efficiency and overall operational stability. It has the following advantages: Real-time control of production rhythm: The production efficiency impact coefficient can help the system monitor and adjust the time intervals between processes in real time to adapt to dynamic changes in the production process, thereby improving production efficiency.

[0038] Optimize resource utilization: By accurately controlling the time intervals between processes, the utilization of resources such as equipment and workers can be maximized, resource waste or overload can be avoided, and the overall operational efficiency of the factory can be improved.

[0039] Reduce production delays: Reasonable time interval control can effectively reduce the waiting time and equipment idle time that may occur during the production process, and avoid production delays caused by unreasonable time settings.

[0040] Improve factory scheduling flexibility: By evaluating the impact on production efficiency, production plans can be adjusted in a timely manner to improve the factory's scheduling flexibility when dealing with emergencies and changes in market demand.

[0041] Improve overall operational stability: Accurate time interval control helps maintain stable operation of the production line and reduce operational fluctuations caused by inconsistent production rhythms, thereby improving the overall stability and competitiveness of the digital factory.

[0042] The specific method for obtaining the production efficiency influence coefficient is as follows: Obtain the actual processing time and theoretical processing time in the production process at different process time intervals; Calculate the processing time deviation in the production process at different time intervals, and set the data with a deviation less than the preset standard deviation value as an acceptable deviation, and set the data with a deviation greater than the preset standard deviation value as a potential hidden danger deviation; Obtaining processing time deviation values ​​generated at all process time intervals, and comparing these deviation values ​​with preset standard deviation values; All potential hidden danger deviation values ​​are used to establish a hidden danger deviation set, and all acceptable deviation values ​​are used to establish an acceptable deviation set; Data analysis is performed based on the hidden danger deviation set and the acceptable deviation set, and the production efficiency impact coefficient is calculated.

[0043] Calculate the production efficiency impact coefficient. The specific calculation formula is as follows: ; In the formula, is the production efficiency influence coefficient, is the data with a deviation less than the preset standard deviation value, h is the number of the data with a deviation less than the preset standard deviation value, is the data with a deviation greater than the preset standard deviation value, k is the number of the data with a deviation greater than the preset standard deviation value, , is the acceptable deviation time period during the data conversion process, , This is the time period for potential hidden danger deviation values ​​during data conversion.

[0044] The equipment load utilization impact coefficient is used to measure the impact of changes in time intervals between processes on equipment load and utilization. Shorter time intervals may lead to frequent equipment switching, increase the burden on the equipment, and may even cause equipment overload; while longer time intervals may cause the equipment to be idle and unable to fully utilize its performance and resources. This coefficient is used to evaluate the overall effect of the digital factory under different time interval groups, aiming to solve the problem of inaccurate time interval regulation, especially in the dynamically changing production rhythm, to avoid excessive load or idleness of equipment, ensure the optimization of equipment load and utilization, and thus improve production efficiency and operational stability.

[0045] Analyzing the impact coefficient of equipment load utilization is helpful for evaluating the overall effect of the digital factory under different process time interval groups, solving the problem of lack of precise regulation of the time interval between processes, making it difficult to adapt to the dynamic changes of the production rhythm in real time, resulting in frequent idle resources or task accumulation, thus affecting production efficiency and overall operational stability. It has the following advantages: Improve equipment load balance: The equipment load utilization impact coefficient can monitor the changes in equipment load in real time, ensure that the equipment is balanced during the entire production process, avoid overload or long-term idleness caused by frequent equipment switching, and thus improve the overall utilization of the equipment.

[0046] Optimize production efficiency: By analyzing the impact of time intervals on equipment load, reasonable adjustment of time intervals can avoid production bottlenecks caused by equipment overload or idleness, and improve the overall efficiency and capacity of the production line.

[0047] Reduce resource waste: Reasonable distribution of equipment load helps to maximize the utilization of factory resources, reduce unnecessary idle time and excessive load, thereby reducing equipment loss and energy consumption, and reducing production costs.

[0048] Improve system flexibility: During the production process, precise control of time intervals can respond to dynamic changes in production rhythm in real time. By balancing equipment loads, factories can more flexibly adapt to fluctuations in market demand and avoid wasting equipment resources.

[0049] Enhance operational stability: Reasonable time interval settings can avoid production fluctuations and equipment failures caused by uneven equipment loads, improve the stability and continuity of the overall production line, and thus enhance the operational stability and long-term reliability of the digital factory.

[0050] The specific method for obtaining the equipment load utilization influence coefficient is as follows: Obtain the equipment load fluctuations of several equipments at different process time intervals; Calculate the load fluctuation standard deviation and load fluctuation average of several equipment load fluctuations at different process time intervals; Calculate the equipment load fluctuation coefficient of variation based on the load fluctuation standard deviation and load fluctuation average value; The equipment load fluctuation variation coefficient is used to calculate the equipment load utilization impact coefficient based on a preset equipment load utilization impact coefficient calculation formula.

[0051] The specific calculation formula of the equipment load fluctuation coefficient of variation is as follows: ; The specific calculation formula of the equipment load utilization coefficient is as follows: ; In the formula, is the coefficient of variation of equipment load fluctuation, is the load fluctuation of the jth device, is the total amount of data collected at different process time intervals, j is the amount of equipment load fluctuation data; is the equipment load utilization factor.

[0052] The factory scheduling flexibility impact coefficient is used to measure the impact of time intervals on factory rhythm and scheduling flexibility. The time interval setting directly determines the gap between processes. If the time interval between processes is too long, it may lead to scheduling conflicts and waste of resources; while a time interval that is too short may cause uneven resources, which in turn affects the flexibility and adjustment ability of the entire production process. This coefficient is used to evaluate the overall effect of the digital factory under different time interval groups, aiming to solve the problem of lack of precise control of time intervals between processes, especially in the rapidly changing production rhythm, to ensure smooth adjustment of production plans, avoid idle resources or task accumulation, and thus ensure production efficiency and operational stability.

[0053] Analyzing the impact coefficient of factory scheduling flexibility is helpful for evaluating the overall effect of digital factories under different process time interval groups, solving the problem of lack of precise control of the time intervals between processes, making it difficult to adapt to the dynamic changes in the production rhythm in real time, resulting in frequent idle resources or task accumulation, thus affecting production efficiency and overall operational stability. It has the following advantages: Improve scheduling adaptability: The factory scheduling flexibility impact coefficient can promptly reflect the impact of the time interval between processes on production planning and scheduling flexibility, help optimize production scheduling to adapt to changes in production rhythm, and reduce conflicts and delays between processes.

[0054] Improve the response speed of the production line: Reasonable setting of process time intervals can enable the factory to quickly adjust the time intervals between processes according to real-time production needs, avoiding production bottlenecks caused by too long or too short time intervals, thereby speeding up the response speed of the production line and improving production efficiency.

[0055] Enhance the real-time performance of production plans: By dynamically adjusting the time intervals between processes, factories can adjust production plans in real time to avoid task accumulation or idle resources caused by unreasonable time intervals between processes, and ensure the smooth operation of the production line.

[0056] Optimize resource allocation: The scheduling flexibility impact coefficient helps to optimize the dynamic allocation of resources, enabling factories to flexibly allocate manpower, equipment and materials to cope with uncertain changes in the production process, thereby reducing production costs and improving resource utilization efficiency.

[0057] Enhance the stability of the production system: The factory scheduling flexibility influence coefficient can effectively balance the production rhythm, avoid production plan conflicts, resource bottlenecks and equipment idleness, thereby improving the stability of the overall factory operation and reducing possible fluctuations and interference in the production process.

[0058] Support long-term planning: By analyzing and optimizing the impact of time intervals on production scheduling flexibility, factories can achieve continuous optimization during the production cycle, improve overall operational efficiency, and provide data support for future production expansion and equipment investment.

[0059] The specific method for obtaining the factory scheduling flexibility influence coefficient is as follows: Based on the production scheduling process under different process time intervals, a set of events of the impact of various scheduling strategies on scheduling flexibility is obtained, wherein the set of events of the impact of various scheduling strategies on scheduling flexibility includes production delays, equipment idleness and resource conflicts caused by various scheduling strategies, and a weighted valuation is performed on the production situation based on historical scheduling data; A regression model is constructed based on the event set and corresponding scores of the impact of various scheduling strategies on scheduling flexibility to generate the impact coefficient of plant scheduling flexibility.

[0060] The specific calculation formula of the factory scheduling flexibility influence coefficient is as follows: ; In the formula, is the factory scheduling flexibility influence coefficient, … is the weight estimation corresponding to the influencing events of the production scheduling process under different process time intervals, … is the proportion of the influencing events of the production scheduling process at different process time intervals in all the influencing events of the production scheduling process, is the corresponding production delay time of the influencing event of the production scheduling process under different process time intervals, n is the number of the influencing event of the production scheduling process under different process time intervals, and e is a natural number.

[0061] The multidimensional data is used to construct a process time interval evaluation model based on the BP neural network, that is, the obtained production efficiency influence coefficient, equipment load utilization influence coefficient and factory scheduling flexibility influence coefficient are used to construct a process time interval evaluation model to generate a process time interval evaluation coefficient; The specific process time interval evaluation model is as follows: ; In the formula, is the process time interval evaluation coefficient, is the preset proportional coefficient of the production efficiency influence coefficient, is the preset proportional coefficient of the equipment load utilization factor. is the preset proportional coefficient of the factory scheduling flexibility impact coefficient, is the production efficiency influence coefficient, is the equipment load utilization factor, It is the impact coefficient of factory scheduling flexibility.

[0062] This embodiment can provide data-based decision support for production scheduling by identifying and analyzing the distribution characteristics of the time intervals between processes. By introducing random changes and multidimensional analysis, the system can not only optimize production efficiency and improve equipment load balance, but also respond to changes in production rhythm in real time, avoiding idle resources, equipment overload or production delays caused by inaccurate time intervals. Specifically, the production efficiency influence coefficient can ensure the improvement of production process speed, the equipment load utilization influence coefficient ensures the rational use of equipment, and the factory scheduling flexibility influence coefficient optimizes the adjustment and scheduling of production plans. The comprehensive application of these technical means enables digital factories to maintain stable operating efficiency in a dynamically changing production environment, thereby improving the overall operational stability and competitiveness of the factory, reducing resource waste and equipment failure risks, and ensuring the smooth progress of the production process.

[0063] The time interval updating module is used to build a visual analysis model based on the multi-dimensional quantitative analysis results and the corresponding process time interval array, and perform data analysis to obtain the screened process time interval array, which is applied to digital factory equipment monitoring.

[0064] The visualization analysis model is constructed based on the multi-dimensional quantitative analysis results and the corresponding process time interval array, specifically: Construct a visual analysis model based on a rectangular coordinate system to demonstrate the comprehensive impact of different process time interval arrays in the digital factory application process; The two coordinate systems of the visualization analysis model represent the process time interval evaluation coefficient and the process time interval array respectively; According to the results of multi-dimensional quantitative analysis, the combination of each process time interval array and its corresponding process time interval evaluation coefficient is mapped to a rectangular coordinate system; Each process time interval array corresponds to a point, and the position of the point is determined by the output of multi-dimensional quantitative analysis and the process time interval array; Several points are smoothed by interpolation method to obtain a smooth curve as a visualization analysis model.

[0065] The data analysis is performed to obtain a filtered process time interval array, which is applied to digital factory equipment monitoring, specifically: Filter the process time interval array corresponding to each maximum value of the visual analysis model to obtain a first screening combination; The minimum values ​​of the integrals corresponding to the process time interval arrays in the first screening combination on the visual analysis model are compared, and the process time interval array with the smallest comparison result is used as the screened process time interval array and applied to digital factory equipment monitoring.

[0066] This embodiment introduces a time interval update module, combines the multi-dimensional quantitative analysis results and the process time interval array to build a visual analysis model, thereby effectively improving the intelligent level of digital factory equipment monitoring. First, a rectangular coordinate system visualization model is used to intuitively display the relationship between different process time interval arrays and their evaluation coefficients, helping managers to fully understand the comprehensive impact of each process time. The curve is formed by interpolation and smoothing, making the process time interval data more stable and accurate, providing a reliable basis for subsequent data analysis.

[0067] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0068] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0069] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0070] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0071] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0072] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A digital factory equipment monitoring system based on big data, characterized by: It includes initial interval distribution identification module, constraint condition update module, time interval array generation module, multi-dimensional analysis module and time interval update module: An initial interval distribution identification module is used to obtain production and equipment data in a digital factory related to the time intervals between processes and identify the initial time interval distribution; The constraint updating module is used to determine the evaluation constraints of the time interval between processes according to the factory rhythm and equipment performance; A time interval array generation module is used to introduce random changes to the initial time interval distribution, generate different time interval distributions, randomly arrange and combine different time intervals, and generate multiple time interval arrays; The multi-dimensional analysis module is used to apply and monitor multiple time interval arrays separately based on big data analysis, and conduct multi-dimensional quantitative analysis; The time interval updating module is used to build a visual analysis model based on the multi-dimensional quantitative analysis results and the corresponding process time interval array, and perform data analysis to obtain the screened process time interval array, which is applied to digital factory equipment monitoring.

2. The digital factory equipment monitoring system based on big data according to claim 1 is characterized in that: It is used to obtain production and equipment data in the digital factory related to the time interval between processes and identify the initial time interval distribution, specifically: Production data includes production process time data, order execution cycle, and production records; Equipment data includes equipment startup and downtime, equipment idle and response time; For each production record, calculate the actual time interval between processes; Calculate basic statistics of time intervals and analyze the distribution characteristics of time intervals through box plots; If the time intervals are concentrated in a certain range and are skewed, choose the gamma distribution; When the time intervals are symmetrically distributed, the normal distribution is selected; The selected distribution model is fitted based on maximum likelihood estimation to obtain the initial time interval distribution.

3. The digital factory equipment monitoring system based on big data according to claim 2 is characterized in that: According to the factory rhythm and equipment performance, determine the evaluation constraints of the time interval between processes, specifically: According to the overall production goals and process requirements of the factory, the production cycle and rhythm are set, and the time interval between processes must meet the following conditions: ； In the formula, is the execution time of the ith process, is the total number of processes, is the time interval between processes, The maximum total time allowed in the production plan.

4. The digital factory equipment monitoring system based on big data according to claim 3 is characterized in that: The introduction of random changes to the initial time interval distribution to generate different time interval distributions, and the random arrangement and combination of different time intervals to generate multiple time interval arrays are specifically as follows: A normally distributed random variable is introduced to perturb the time interval, and the change of each time interval follows a normal distribution; After disturbing the time interval between each process, the time intervals are randomly arranged and combined to generate multiple time interval arrays.

5. The digital factory equipment monitoring system based on big data according to claim 4 is characterized in that: Based on the big data analysis, multiple time interval arrays are applied and monitored respectively, specifically: Each time interval array is directly applied to the production scheduling system of the digital factory as the execution standard of the time interval between processes; The scheduling system adjusts and controls the execution rhythm of each process based on these time interval arrays to ensure that the time intervals between processes meet the predetermined parameters; The monitoring module collects production data, equipment status and actual performance of time intervals in real time, and tracks and records them.

6. The digital factory equipment monitoring system based on big data according to claim 5 is characterized in that: The multi-dimensional quantitative analysis is specifically as follows: The multidimensional data includes production efficiency data, equipment load utilization data and factory scheduling flexibility data; the production efficiency data includes a production efficiency impact coefficient; the specific method for obtaining the production efficiency impact coefficient is as follows; Obtain the actual processing time and theoretical processing time in the production process at different process time intervals; Calculate the processing time deviation in the production process at different time intervals, and set the data with a deviation less than the preset standard deviation value as an acceptable deviation, and set the data with a deviation greater than the preset standard deviation value as a potential hidden danger deviation; Obtaining processing time deviation values ​​generated at all process time intervals, and comparing these deviation values ​​with preset standard deviation values; All potential hidden danger deviation values ​​are used to establish a hidden danger deviation set, and all acceptable deviation values ​​are used to establish an acceptable deviation set; Data analysis is performed based on the hidden danger deviation set and the acceptable deviation set, and the production efficiency impact coefficient is calculated.

7. The digital factory equipment monitoring system based on big data according to claim 6 is characterized in that: The equipment load utilization data includes an equipment load utilization influence coefficient; the specific method for obtaining the equipment load utilization influence coefficient is as follows: Obtain the equipment load fluctuations of several equipments at different process time intervals; Calculate the load fluctuation standard deviation and load fluctuation average of several equipment load fluctuations at different process time intervals; Calculate the equipment load fluctuation coefficient of variation based on the load fluctuation standard deviation and load fluctuation average value; The equipment load fluctuation variation coefficient is used to calculate the equipment load utilization impact coefficient based on a preset equipment load utilization impact coefficient calculation formula.

8. The digital factory equipment monitoring system based on big data according to claim 7 is characterized in that: The factory scheduling flexibility data includes a factory scheduling flexibility influence coefficient; the specific method for obtaining the factory scheduling flexibility influence coefficient is as follows: Based on the production scheduling process under different process time intervals, a set of events of the impact of various scheduling strategies on scheduling flexibility is obtained, wherein the set of events of the impact of various scheduling strategies on scheduling flexibility includes production delays, equipment idleness and resource conflicts caused by various scheduling strategies, and a weighted valuation is performed on the production situation based on historical scheduling data; A regression model is constructed based on the event set and corresponding scores of the impact of various scheduling strategies on scheduling flexibility to generate the impact coefficient of plant scheduling flexibility.

9. The digital factory equipment monitoring system based on big data according to claim 8 is characterized in that: The visualization analysis model is constructed based on the multi-dimensional quantitative analysis results and the corresponding process time interval array, specifically: Construct a visual analysis model based on a rectangular coordinate system to demonstrate the comprehensive impact of different process time interval arrays in the digital factory application process; The two coordinate systems of the visualization analysis model represent the process time interval evaluation coefficient and the process time interval array respectively; According to the results of multi-dimensional quantitative analysis, the combination of each process time interval array and its corresponding process time interval evaluation coefficient is mapped to a rectangular coordinate system; Each process time interval array corresponds to a point, and the position of the point is determined by the output of multi-dimensional quantitative analysis and the process time interval array; Several points are smoothed by interpolation method to obtain a smooth curve as a visualization analysis model.

10. The digital factory equipment monitoring system based on big data according to claim 9 is characterized in that: The data analysis is performed to obtain a filtered process time interval array, which is applied to digital factory equipment monitoring, specifically: Filter the process time interval array corresponding to each maximum value of the visual analysis model to obtain a first screening combination; The minimum values ​​of the integrals corresponding to the process time interval arrays in the first screening combination on the visual analysis model are compared, and the process time interval array with the smallest comparison result is used as the screened process time interval array and applied to digital factory equipment monitoring.

Images