Data fusion method and intelligent processing system based on industrial Internet of Things
By performing multi-dimensional data fusion and predictive regulation of industrial plants on the industrial Internet of Things platform, the problem of low rationality in industrial plants in the existing technology is solved, and the effect of improving manufacturing efficiency and reducing energy consumption is achieved.
Patent Information
- Application Number
- CN202411112529.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-14
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-08-14
AI Technical Summary
In the prior art, it is impossible to conduct predictive quantitative evaluation of industrial plants based on multi-dimensional manufacturing parameters, resulting in low rationality in industrial plants, poor manufacturing efficiency and quality, and large energy consumption.
Using the data fusion method based on the industrial Internet of Things, multi-dimensional manufacturing feature monitoring and distributed fusion analysis are carried out through block division and distributed fusion device layout to generate manufacturing timing and predictive manufacturing index. If the limit value is not met, predictiveness will be issued. Regulation instructions, obtain the optimal regulation plan for regulation.
It improves the management efficiency of industrial plant areas, reduces risks in the production process, ensures efficient and stable operation of production activities, and reduces energy consumption.
Smart Images

Figure CN118627022B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of intelligent processing technology, and in particular to a data fusion method and an intelligent processing system based on industrial Internet of Things. Background Art
[0002] In the modern industrial production process, improving manufacturing efficiency, ensuring product quality and reducing energy consumption are the core goals pursued by the manufacturing industry. With the advancement of Industry 4.0, intelligent, information-based and automated industrial production models have gradually become mainstream. In this context, it is particularly important to carry out refined management of production activities in industrial plants. Traditional industrial plant management methods often rely on manual monitoring and empirical judgment, which is not only inefficient, but also difficult to achieve real-time monitoring and predictive maintenance of the production process. In order to overcome these limitations, it is necessary to adopt advanced monitoring technology and data analysis methods to improve the management efficiency of industrial plants. Among the existing technical solutions, although there are some systems that can monitor the status of industrial equipment, these systems can often only provide single-dimensional data monitoring and lack a comprehensive evaluation of the overall performance of the equipment. In addition, when these systems process large amounts of data, they often have problems such as slow data processing speed and inaccurate analysis results.
[0003] In summary, when the existing technology integrates the dynamic manufacturing parameters of various equipment in industrial plants based on the industrial Internet, there is a technical problem that it is impossible to perform predictive quantitative evaluation of the dynamic manufacturing of the industrial plant based on multi-dimensional manufacturing parameters, which leads to low rationality of industrial plant regulation and control, and ultimately leads to poor comprehensive manufacturing effects of the industrial plant. Summary of the invention
[0004] The purpose of this application is to provide a data fusion method and intelligent processing system based on the Industrial Internet of Things, so as to solve the technical problems in the prior art that it is impossible to perform predictive and coordinated regulation of various equipment in industrial plants based on the Industrial Internet, resulting in poor manufacturing efficiency and manufacturing quality of industrial plants, and high energy consumption.
[0005] In view of the above problems, the present application provides a data fusion method and an intelligent processing system based on industrial Internet of Things.
[0006] In a first aspect, the present application provides a data fusion method based on the industrial Internet of Things, which is implemented by an intelligent processing system, wherein the data fusion method based on the industrial Internet of Things includes: dividing a target industrial plant area into blocks to obtain a target division result, and deploying a first distributed fuser in a first block in the target division result; reading a predetermined manufacturing feature, and based on the predetermined manufacturing feature, performing multi-dimensional manufacturing feature monitoring on each manufacturing equipment in the first block at a first time to obtain a first manufacturing feature parameter set; performing distributed fusion analysis on a first operating feature parameter in the first manufacturing feature parameter set by the first distributed fuser to obtain a first manufacturing index; generating a first manufacturing timing of the first block based on a first corresponding relationship between the first time and the first manufacturing index; reading a predetermined timing prediction strategy, and performing a predictive analysis on the first manufacturing timing according to the predetermined timing prediction strategy to obtain a first target predicted manufacturing index at the target time; if the first target predicted manufacturing index does not meet a predetermined manufacturing limit, issuing a first predictive control instruction; obtaining a first optimal control plan for each manufacturing equipment in the first block based on the first predictive control instruction; and controlling the target industrial plant area according to the first optimal control plan at the target time.
[0007] In the second aspect, the present application also provides an intelligent processing system for executing the data fusion method based on the industrial Internet of Things as described in the first aspect, wherein the intelligent processing system comprises: a division and layout module, the division and layout module is used to divide the target industrial plant area into blocks to obtain a target division result, and to layout a first distributed fuser in the first block of the target division result; a feature monitoring module, the feature monitoring module is used to read a predetermined manufacturing feature, and based on the predetermined manufacturing feature, perform multi-dimensional manufacturing feature monitoring on each manufacturing equipment in the first block at the first time to obtain a first manufacturing feature parameter set; a distributed fusion module, the distributed fusion module is used to perform distributed fusion analysis on the first operating feature parameter in the first manufacturing feature parameter set through the first distributed fuser to obtain a first manufacturing index; a timing generation module The timing generation module is used to generate the first manufacturing timing of the first block based on the first corresponding relationship between the first time and the first manufacturing index; the timing prediction module is used to read the predetermined timing prediction strategy, and predict and analyze the first manufacturing timing according to the predetermined timing prediction strategy to obtain the first target predicted manufacturing index under the target time; the predictive control module is used to issue a first predictive control instruction if the first target predicted manufacturing index does not meet the predetermined manufacturing limit; the control optimization module is used to obtain the first optimal control plan of each manufacturing equipment in the first block based on the first predictive control instruction; the control execution module is used to control the target industrial plant according to the first optimal control plan under the target time.
[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:
[0009] The target industrial plant is divided into blocks to obtain a target division result, and a first distributed fusion device is arranged in the first block of the target division result; a predetermined manufacturing feature is read, and based on the predetermined manufacturing feature, a multi-dimensional manufacturing feature monitoring is performed on each manufacturing equipment in the first block at a first time to obtain a first manufacturing feature parameter set; a first operating feature parameter in the first manufacturing feature parameter set is distributedly fused and analyzed by the first distributed fusion device to obtain a first manufacturing index; a first manufacturing time sequence of the first block is generated based on a first corresponding relationship between the first time and the first manufacturing index; a predetermined time sequence prediction strategy is read, and a prediction analysis is performed on the first manufacturing time sequence according to the predetermined time sequence prediction strategy to obtain a first target predicted manufacturing index at a target time; if the first target predicted manufacturing index does not meet a predetermined manufacturing limit, a first predictive control instruction is issued; based on the first predictive control instruction, a first optimal control plan of each manufacturing equipment in the first block is obtained; at the target time, the target industrial plant is controlled according to the first optimal control plan. The technical goal of improving the management efficiency of industrial plants is achieved, and the technical effect of reducing risks in the production process, ensuring efficient and stable operation of production activities, and reducing energy consumption is achieved.
[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0011] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.
[0012] Figure 1 This is a flow chart of the data fusion method based on the industrial Internet of Things in this application;
[0013] Figure 2 This is a structural schematic diagram of an intelligent processing system for this application.
[0014] Description of reference numerals:
[0015] Partitioning and layout module 11, feature monitoring module 12, distributed fusion module 13, time series generation module 14, time series prediction module 15, predictive control module 16, control optimization module 17, control execution module 18. DETAILED DESCRIPTION
[0016] This application provides a data fusion method and intelligent processing system based on the industrial Internet of Things, which solves the technical problem that when the dynamic manufacturing parameters of various equipment in the industrial plant are integrated based on the industrial Internet, the dynamic manufacturing of the industrial plant cannot be predicted and quantitatively evaluated based on multi-dimensional manufacturing parameters, which leads to low rationality of industrial plant regulation and control, and ultimately leads to poor comprehensive manufacturing effects of the industrial plant. The technical goal of improving the management efficiency of industrial plants is achieved, and the technical effect of reducing risks in the production process, ensuring the efficient and stable operation of production activities, and reducing energy consumption is achieved.
[0017] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.
[0018] For example, please refer to the attached Figure 1 The present application provides a data fusion method based on the industrial Internet of Things, wherein the data fusion method based on the industrial Internet of Things is applied to an intelligent processing system, and the data fusion method based on the industrial Internet of Things specifically includes the following steps:
[0019] Step 1: Divide the target industrial plant area into blocks to obtain a target division result, and deploy a first distributed fusion device in the first block in the target division result.
[0020] Specifically, first, the target industrial plant is effectively divided into blocks, and distributed fusion devices are deployed in specific blocks. It aims to optimize the management and resource allocation of industrial plants and improve overall operational efficiency. Block division can help to more accurately identify and utilize the characteristics of each area, and the deployment of distributed fusion devices further enhances the functionality and interactivity of these areas. Specifically, first, a detailed block division is carried out, which involves a comprehensive consideration of the plant structure, functional requirements and resource distribution. Then the location and functional requirements of the first block are determined. Among them, the first block is any one of the multiple blocks obtained after dividing the target industrial plant. Next, a suitable type of distributed fusion device is selected, which should be able to meet the specific needs of the first block. In addition, when deploying the distributed fusion device, its compatibility and interactivity with other systems and equipment in the plant need to be considered. Finally, ensure that the distributed fusion device operates stably in the first block, and continuously monitor and maintain it to ensure its long-term and effective operation.
[0021] Through precise block division, resources can be allocated and used more effectively, and the deployment of distributed fusion devices further improves the interaction and collaboration efficiency between blocks. This not only optimizes the overall operation of the factory, but also may bring the dual benefits of cost savings and efficiency improvement.
[0022] Step 2: Reading predetermined manufacturing features, and based on the predetermined manufacturing features, performing multi-dimensional manufacturing feature monitoring on each manufacturing equipment in the first block at a first time to obtain a first manufacturing feature parameter set.
[0023] Further, it includes: the predetermined manufacturing characteristics include operating status characteristics and energy consumption characteristics, wherein the operating status characteristics include multiple operating index characteristics.
[0024] Specifically, the first manufacturing feature parameter set is obtained by reading predetermined manufacturing features and performing multi-dimensional manufacturing feature monitoring on manufacturing equipment in a specific block in an industrial plant. The predetermined manufacturing features include operating state features and energy consumption features, where the operating state features are further subdivided into multiple operating indicator features. The purpose of this is to have a more comprehensive and in-depth understanding of the working conditions of the manufacturing equipment in order to carry out effective performance optimization and fault prevention. First, the predetermined manufacturing features are read, which are pre-set to guide the monitoring process. Then, at the first time, multi-dimensional manufacturing feature monitoring is performed on each manufacturing equipment in the first block. This includes comprehensive monitoring of the operating state features and energy consumption features of the equipment. Next, the first manufacturing feature parameter set is extracted from the monitoring data, which contains the performance indicators of the equipment in various dimensions. In addition, the multiple operating indicator features in the operating state features provide a more detailed perspective for monitoring, which helps to discover subtle changes in equipment performance.
[0025] By obtaining the first manufacturing characteristic parameter set, the working condition of the equipment can be evaluated more accurately, potential problems can be discovered in time, and targeted optimization and adjustment can be carried out. This not only improves the operating efficiency and reliability of the equipment, but also helps to extend the service life of the equipment and reduce maintenance costs.
[0026] Step three: Perform distributed fusion analysis on the first operating characteristic parameter in the first manufacturing characteristic parameter set through the first distributed fuser to obtain a first manufacturing index.
[0027] Specifically, the first distributed fuser is used to perform distributed fusion analysis on the first operating characteristic parameter in the first manufacturing characteristic parameter set to obtain the first manufacturing index. The key lies in the distributed fusion technology, which can effectively integrate and analyze the operating data from multiple manufacturing equipment to provide a comprehensive evaluation of the performance of the entire manufacturing process. First, the first operating characteristic parameters in the first manufacturing characteristic parameter set are determined, which reflect the operating status and performance of the manufacturing equipment. Then, these parameters are subjected to distributed fusion analysis through the first distributed fuser. Distributed fusion analysis involves the collection, processing and analysis of data, and aims to reveal the operating trends and performance characteristics of the equipment from multiple angles and dimensions. Next, based on the results of the distributed fusion analysis, the first manufacturing index is calculated. This index is a comprehensive reflection of the operating status and performance of the equipment, and can provide an important basis for subsequent decision-making.
[0028] Through the First Manufacturing Index, you can quickly understand the overall operating status of the equipment, discover performance deviations and potential problems in a timely manner, and take corresponding optimization measures. This not only improves the transparency and controllability of the manufacturing process, but also helps improve production efficiency and product quality.
[0029] Step 4: Generate a first manufacturing timing of the first block based on a first corresponding relationship between the first time and the first manufacturing index.
[0030] Specifically, a corresponding relationship between the first time and the first manufacturing index is established, and the manufacturing time series of the first block is generated based on this relationship. The key is to understand and use time series data to more accurately analyze and predict trends and changes in the manufacturing process.
[0031] Specifically, first, the correspondence between the first time and the first manufacturing index is determined. This correspondence may be based on historical data analysis and statistical analysis, reflecting the law of change of the manufacturing index over time. Then, using this correspondence, the manufacturing time series of the first block is generated. The manufacturing time series is a chart or data set that reflects the changes of the manufacturing process over time, which can help understand the dynamic changes and trends of the manufacturing process. Next, the generated manufacturing time series is analyzed to identify any abnormal patterns or trends, which may indicate potential problems or improvement opportunities in the manufacturing process. The manufacturing time series can more clearly see the changes of the manufacturing index over time, so as to better predict and plan manufacturing activities. This not only improves the predictability and controllability of the manufacturing process, but also helps to detect problems in a timely manner and take corresponding measures to optimize manufacturing performance and efficiency.
[0032] Step 5: Read the predetermined timing prediction strategy, and perform prediction analysis on the first manufacturing timing according to the predetermined timing prediction strategy to obtain a first target prediction manufacturing index under the target time.
[0033] Specifically, the first manufacturing time series is predicted and analyzed using a predetermined time series prediction strategy to obtain a first target predicted manufacturing index at the target time. The key is that the time series prediction technology can predict the manufacturing index at a specific time point in the future based on historical data, thereby providing an important basis for planning and decision-making in the manufacturing process.
[0034] Specifically, first, the predetermined timing prediction strategies are read. These strategies are based on historical data and statistical analysis and are used to guide the timing prediction process. Then, the first manufacturing timing is predicted and analyzed according to these strategies. Predictive analysis involves processing and modeling manufacturing timing data to predict the manufacturing index at a specific point in time in the future. Next, based on the results of the predictive analysis, the first target predicted manufacturing index at the target time is calculated. This index is a comprehensive prediction of the performance and status of the future manufacturing process, which can provide an important basis for subsequent decision-making. Through the first target predicted manufacturing index, the manufacturing status at a specific point in time in the future can be understood in advance, so that corresponding optimization measures and preventive measures can be taken. This not only improves the predictability and controllability of the manufacturing process, but also helps to improve production efficiency and product quality.
[0035] Step six: If the first target predicted manufacturing index does not meet the predetermined manufacturing limit, a first predictive control instruction is issued.
[0036] Further, it includes: if the first target predicted manufacturing index meets the predetermined manufacturing limit, issuing an integrated fusion instruction; obtaining the second target predicted manufacturing index of the second block at the target time based on the integrated fusion instruction; using the coefficient of variation principle to perform a weighted analysis on the first target predicted manufacturing index and the second target predicted manufacturing index to obtain a target predicted manufacturing index; wherein the target predicted manufacturing index is used to characterize the comprehensive manufacturing status of the target industrial plant at the target time.
[0037] Specifically, according to the relationship between the first target predicted manufacturing index and the predetermined manufacturing limit, a corresponding control instruction is issued. If the first target predicted manufacturing index does not meet the predetermined manufacturing limit, a first predictive control instruction is issued to adjust and optimize the manufacturing process. If the predetermined manufacturing limit is met, an integrated fusion instruction is issued to further analyze and predict the manufacturing status of other blocks to obtain a more comprehensive comprehensive manufacturing status of the industrial plant.
[0038] Specifically, first, it is determined whether the first target predicted manufacturing index meets the predetermined manufacturing limit. If not, a first predictive control instruction is issued to guide the adjustment of the manufacturing process. Then, if the first target predicted manufacturing index meets the predetermined manufacturing limit, an integrated fusion instruction is issued. Next, based on the integrated fusion instruction, the second target predicted manufacturing index of the second block at the target time is obtained. In addition, the first target predicted manufacturing index and the second target predicted manufacturing index are weighted analyzed using the coefficient of variation principle to obtain the target predicted manufacturing index. The target predicted manufacturing index characterizes the comprehensive manufacturing status of the target industrial plant at the target time. Through predictive control instructions and integrated fusion instructions, the manufacturing process can be adjusted and optimized in a timely manner to ensure that the manufacturing performance meets expectations. At the same time, the target predicted manufacturing index obtained through weighted analysis provides an important basis for the overall management and decision-making of the industrial plant. This not only improves the flexibility and response speed of the manufacturing process, but also helps to improve the production efficiency and product quality of the entire industrial plant.
[0039] Step seven: obtaining a first optimal control plan for each manufacturing equipment in the first block based on the first predictive control instruction.
[0040] Specifically, based on the first predictive control instruction, the first optimal control plan for each manufacturing equipment in the first block is obtained. The key to this process is to formulate an optimal control strategy for each manufacturing equipment based on the predictive control instruction to optimize the operating performance and overall manufacturing efficiency of the equipment.
[0041] Specifically, first, according to the first predictive control instruction, the current operating status and performance of each manufacturing equipment in the first block are analyzed. Then, based on these analysis results, the first optimal control plan is generated for each device. These plans include the optimal operating parameters, maintenance plans or adjustment measures for each device. Next, these control plans are applied to the corresponding manufacturing equipment to achieve optimal operating performance and efficiency. Through the first optimal control plan, it can be ensured that each device can operate in the best state, thereby improving the overall manufacturing efficiency and production quality. This not only optimizes the performance of the manufacturing process, but also helps to extend the service life of the equipment and reduce maintenance costs.
[0042] Step 8: Under the target time, control the target industrial plant according to the first optimal control plan.
[0043] Specifically, at the target time, the target industrial plant is regulated according to the first optimal regulation plan. The key to this process is to implement the regulation plan in a timely and accurate manner to optimize the overall operating performance and efficiency of the industrial plant. First, at the target time, the regulation process is started. Then, according to the first optimal regulation plan, each manufacturing equipment in the target industrial plant is regulated. This includes adjusting the operating parameters of the equipment, executing maintenance plans, or taking other adjustment measures. Next, the regulation effect is monitored to ensure that each equipment operates according to the plan to achieve the expected performance goals. By executing the first optimal regulation plan at the target time, it is possible to ensure that the industrial plant operates in the best condition, thereby improving production efficiency and quality. This not only optimizes the performance of the manufacturing process, but also helps to reduce operating costs and improve the competitiveness of the industrial plant.
[0044] Further, it includes: extracting the first manufacturing equipment and the second manufacturing equipment in the first block in sequence, wherein the first manufacturing equipment and the second manufacturing equipment are the same type of equipment; traversing the first manufacturing feature parameter set in sequence to obtain the first parameter set of the first manufacturing equipment and the second parameter set of the second manufacturing equipment; obtaining the first indicator among the multiple operating indicator characteristics, and traversing the first parameter set and the second parameter set in sequence to obtain the first indicator parameter and the second indicator parameter respectively; introducing a monitoring support function to perform support analysis on the first indicator parameter and the second indicator parameter to obtain support; if the support does not reach the predetermined support limit, issuing a retest instruction, and repeating the monitoring of the first indicator based on the retest instruction.
[0045] Further, including: the expression of the monitoring support function is as follows: ;in, Refers to the second indicator parameter The first indicator parameter The support of , k refers to the magnitude of the monitoring support function, and , is the attenuation factor, and .
[0046] Specifically, detailed parameter analysis and monitoring support evaluation are performed on the first manufacturing equipment and the second manufacturing equipment in the first block. The accuracy and reliability of the monitoring data are ensured by comparing the parameter sets and support analysis of similar equipment.
[0047] First, extract the first manufacturing equipment and the second manufacturing equipment from the first block in turn, and these two equipment are of the same type. Then, traverse the first manufacturing feature parameter set to obtain the first parameter set of the first manufacturing equipment and the second parameter set of the second manufacturing equipment respectively. Next, obtain the first indicator from multiple operating indicator features, and traverse the first parameter set and the second parameter set to obtain the first indicator parameter and the second indicator parameter respectively. In addition, introduce the monitoring support function, perform support analysis on the first indicator parameter and the second indicator parameter, and obtain the support. The expression of the monitoring support function is as follows: ;in, Refers to the second indicator parameter The first indicator parameter The support of , k refers to the magnitude of the monitoring support function, and , is the attenuation factor, and If the support does not reach the predetermined support limit, a retest instruction is issued, and the first indicator is repeatedly monitored based on the retest instruction.
[0048] Through monitoring support analysis, potential problems and deviations in monitoring data can be discovered in a timely manner, and the accuracy of data can be ensured through retest instructions. This not only improves the credibility of monitoring data, but also helps to more accurately evaluate the operating status and performance of the equipment, so as to take effective optimization measures.
[0049] Further, it includes: collecting multi-domain features of the first manufacturing timing according to the predetermined timing prediction strategy to obtain first multi-domain feature information; using the first multi-domain feature information and the target time as input information of the manufacturing prediction model to obtain the first target prediction manufacturing index; wherein the construction process of the manufacturing prediction model is as follows: obtaining the historical manufacturing timing; obtaining the first historical time, and matching the first historical manufacturing index corresponding to the first historical time in the historical manufacturing timing; taking the first historical time as a constraint to perform segment interception on the historical manufacturing timing to obtain the first historical manufacturing timing; collecting multi-domain features of the first historical manufacturing timing according to the predetermined timing prediction strategy to obtain the first historical multi-domain feature information; based on the principle of neural network, supervised learning is performed on the first historical data set composed of the first historical multi-domain feature information and the first historical manufacturing index to obtain the manufacturing prediction model.
[0050] Specifically, a predetermined time series prediction strategy is used to collect multi-domain features of the first manufacturing time series, and a manufacturing prediction model is constructed based on these feature information to predict the first target prediction manufacturing index at the target time. The key lies in the multi-domain feature collection and supervised learning of the neural network, which ensures the accuracy and reliability of the prediction model.
[0051] First, according to a predetermined timing prediction strategy, multi-domain features are collected for the first manufacturing timing to obtain first multi-domain feature information. Then, the first multi-domain feature information and the target time are used as input information, and the first target prediction manufacturing index is calculated using the manufacturing prediction model. Next, the construction process of the manufacturing prediction model includes obtaining the historical manufacturing timing and obtaining the first historical manufacturing index corresponding to the first historical time. Then, with the first historical time as a constraint, the historical manufacturing timing is segmented to obtain the first historical manufacturing timing. In addition, according to the predetermined timing prediction strategy, multi-domain features are collected for the first historical manufacturing timing to obtain the first historical multi-domain feature information. Finally, based on the principle of neural network, supervised learning is performed on the first historical data set composed of the first historical multi-domain feature information and the first historical manufacturing index, so as to construct a manufacturing prediction model.
[0052] Through the manufacturing prediction model, the manufacturing index at a specific point in the future can be predicted based on historical data and real-time feature information, providing an important basis for planning and decision-making in the manufacturing process. This not only improves the predictability and controllability of the manufacturing process, but also helps to improve production efficiency and product quality.
[0053] Further, it includes: performing polynomial regression fitting on a first manufacturing scatter plot drawn based on the first manufacturing timing to obtain a first fitting polynomial; inputting the target time into the first fitting polynomial to obtain a second target predicted manufacturing index; wherein the second target predicted manufacturing index is used to verify the first target predicted manufacturing index.
[0054] Specifically, a first fitting polynomial is obtained by performing polynomial regression fitting on the first manufacturing scatter plot drawn by the first manufacturing sequence, and the polynomial is used to predict the second target predicted manufacturing index at the target time. Polynomial regression fitting can predict the manufacturing index at a specific time point in the future based on historical data, and provide verification of the first target predicted manufacturing index. First, based on the first manufacturing sequence, a first manufacturing scatter plot is drawn. Then, a polynomial regression fitting is performed on the first manufacturing scatter plot to obtain a first fitting polynomial. Next, the target time is input into the first fitting polynomial to calculate the second target predicted manufacturing index. In addition, the second target predicted manufacturing index is used to verify the first target predicted manufacturing index to ensure the accuracy and reliability of the prediction result. Through polynomial regression fitting and verification of the second target predicted manufacturing index, the manufacturing index at a specific time point in the future can be predicted more accurately, and an important basis for the planning and decision-making of the manufacturing process can be provided. This not only improves the predictability and controllability of the manufacturing process, but also helps to improve production efficiency and product quality.
[0055] Further, it includes: normalizing the first energy consumption characteristic parameter in the first manufacturing characteristic parameter set, and weighting it with the first manufacturing index to obtain a first fitness; arbitrarily obtaining a first regulation plan for the first block; obtaining first simulation information of the first regulation plan, the first simulation information including a first simulation manufacturing index and a first simulation energy consumption index; weighting and normalizing the first simulation manufacturing index and the first simulation energy consumption index to obtain a first simulation fitness; if the first simulation fitness is greater than the first fitness, taking the first regulation plan as the first optimal regulation plan.
[0056] Specifically, through normalization and weighted analysis, the first energy consumption characteristic parameter and the first manufacturing index in the first manufacturing characteristic parameter set are evaluated to obtain the first fitness. Then, by comparing with the simulation information of the first block control plan obtained arbitrarily, it is determined whether to use this plan as the first optimal control plan. First, the first energy consumption characteristic parameter in the first manufacturing characteristic parameter set is normalized. Then, the normalized first energy consumption characteristic parameter and the first manufacturing index are weighted to obtain the first fitness. Next, the first control plan of the first block is arbitrarily obtained, and the first simulation information of the plan is obtained, including the first simulated manufacturing index and the first simulated energy consumption index. Then, these simulation information are weighted and normalized to obtain the first simulation fitness. Finally, if the first simulation fitness is greater than the first fitness, the first control plan is used as the first optimal control plan.
[0057] By comparing fitness evaluation and simulation information, the best control plan can be determined to optimize the performance and efficiency of the manufacturing process. This not only improves the flexibility and response speed of the manufacturing process, but also helps to improve the production efficiency and product quality of the entire industrial plant.
[0058] In summary, the data fusion method based on industrial Internet of Things provided by this application has the following technical effects:
[0059] The target industrial plant is divided into blocks to obtain a target division result, and a first distributed fusion device is arranged in the first block of the target division result; a predetermined manufacturing feature is read, and based on the predetermined manufacturing feature, a multi-dimensional manufacturing feature monitoring is performed on each manufacturing equipment in the first block at a first time to obtain a first manufacturing feature parameter set; a first operating feature parameter in the first manufacturing feature parameter set is distributedly fused and analyzed by the first distributed fusion device to obtain a first manufacturing index; a first manufacturing time sequence of the first block is generated based on a first corresponding relationship between the first time and the first manufacturing index; a predetermined time sequence prediction strategy is read, and a prediction analysis is performed on the first manufacturing time sequence according to the predetermined time sequence prediction strategy to obtain a first target predicted manufacturing index at a target time; if the first target predicted manufacturing index does not meet a predetermined manufacturing limit, a first predictive control instruction is issued; based on the first predictive control instruction, a first optimal control plan of each manufacturing equipment in the first block is obtained; at the target time, the target industrial plant is controlled according to the first optimal control plan. The technical goal of improving the management efficiency of industrial plants is achieved, and the technical effect of reducing risks in the production process, ensuring efficient and stable operation of production activities, and reducing energy consumption is achieved.
[0060] Embodiment 2: Based on the same inventive concept as the data fusion method based on industrial Internet of Things in the above embodiment, this application also provides an intelligent processing system, please refer to the attached Figure 2 , the intelligent processing system comprises:
[0061] The partitioning and layout module 11 is used to divide the target industrial plant into blocks to obtain a target partitioning result, and to layout a first distributed fusion device in the first block of the target partitioning result.
[0062] The feature monitoring module 12 is used to read predetermined manufacturing features, and based on the predetermined manufacturing features, perform multi-dimensional manufacturing feature monitoring on each manufacturing equipment in the first block at a first time to obtain a first manufacturing feature parameter set.
[0063] The distributed fusion module 13 is used to perform distributed fusion analysis on the first operating characteristic parameter in the first manufacturing characteristic parameter set through the first distributed fuser to obtain a first manufacturing index.
[0064] The timing generation module 14 is configured to generate a first manufacturing timing of the first block based on a first corresponding relationship between the first time and the first manufacturing index.
[0065] The timing prediction module 15 is used to read a predetermined timing prediction strategy, and perform prediction analysis on the first manufacturing timing according to the predetermined timing prediction strategy to obtain a first target prediction manufacturing index under a target time.
[0066] The predictive control module 16 is configured to issue a first predictive control instruction if the first target predicted manufacturing index does not meet a predetermined manufacturing limit.
[0067] The control optimization module 17 is used to obtain a first optimal control plan for each manufacturing equipment in the first block based on the first predictive control instruction.
[0068] The control execution module 18 is used to control the target industrial plant according to the first optimal control plan at the target time.
[0069] Furthermore, the intelligent processing system also includes a comprehensive manufacturing status evaluation module, wherein the comprehensive manufacturing status evaluation module is used to: issue an integrated fusion instruction if the first target predicted manufacturing index meets the predetermined manufacturing limit; obtain a second target predicted manufacturing index of the second block at the target time based on the integrated fusion instruction; use the coefficient of variation principle to perform a weighted analysis on the first target predicted manufacturing index and the second target predicted manufacturing index to obtain a target predicted manufacturing index; wherein the target predicted manufacturing index is used to characterize the comprehensive manufacturing status of the target industrial plant at the target time.
[0070] Furthermore, the feature monitoring module 12 in the intelligent processing system is also used for: the predetermined manufacturing feature includes an operation status feature and an energy consumption feature, wherein the operation status feature includes a plurality of operation index features.
[0071] Furthermore, the feature monitoring module 12 in the intelligent processing system is also used to: extract the first manufacturing equipment and the second manufacturing equipment in the first block in sequence, wherein the first manufacturing equipment and the second manufacturing equipment are the same type of equipment; traverse the first manufacturing feature parameter set in sequence to obtain the first parameter set of the first manufacturing equipment and the second parameter set of the second manufacturing equipment; obtain the first indicator among the multiple operating indicator characteristics, and traverse the first parameter set and the second parameter set in sequence to obtain the first indicator parameter and the second indicator parameter respectively; introduce a monitoring support function to perform support analysis on the first indicator parameter and the second indicator parameter to obtain support; if the support does not reach the predetermined support limit, issue a retest instruction, and repeat the monitoring of the first indicator based on the retest instruction.
[0072] Furthermore, the feature monitoring module 12 in the intelligent processing system is also used for: the expression of the monitoring support function is as follows: ;in, Refers to the second indicator parameter The first indicator parameter The support of , k refers to the magnitude of the monitoring support function, and , is the attenuation factor, and .
[0073] Furthermore, the timing prediction module 15 in the intelligent processing system is also used to: collect multi-domain features of the first manufacturing timing according to the predetermined timing prediction strategy to obtain first multi-domain feature information; use the first multi-domain feature information and the target time as input information of the manufacturing prediction model to obtain the first target prediction manufacturing index; wherein, the construction process of the manufacturing prediction model is as follows: obtain the historical manufacturing timing; obtain the first historical time, and match the first historical manufacturing index corresponding to the first historical time in the historical manufacturing timing; segment the historical manufacturing timing with the first historical time as a constraint to obtain the first historical manufacturing timing; collect multi-domain features of the first historical manufacturing timing according to the predetermined timing prediction strategy to obtain the first historical multi-domain feature information; and perform supervised learning on the first historical data set composed of the first historical multi-domain feature information and the first historical manufacturing index based on the principle of neural network to obtain the manufacturing prediction model.
[0074] Furthermore, the distributed fusion module 13 in the intelligent processing system is also used to: perform polynomial regression fitting on the first manufacturing scatter plot drawn based on the first manufacturing timing to obtain a first fitting polynomial; input the target time into the first fitting polynomial to obtain a second target predicted manufacturing index; wherein the second target predicted manufacturing index is used to verify the first target predicted manufacturing index.
[0075] Furthermore, the control optimization module 17 in the intelligent processing system is also used to: normalize the first energy consumption characteristic parameter in the first manufacturing characteristic parameter set, and weight it with the first manufacturing index to obtain a first fitness; arbitrarily obtain the first control plan of the first block; obtain the first simulation information of the first control plan, the first simulation information includes a first simulation manufacturing index and a first simulation energy consumption index; weighted and normalized the first simulation manufacturing index and the first simulation energy consumption index to obtain a first simulation fitness; if the first simulation fitness is greater than the first fitness, use the first control plan as the first optimal control plan.
[0076] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. Figure 1The data fusion method based on the industrial Internet of Things and the specific examples in the first embodiment are also applicable to an intelligent processing system in this embodiment. Through the above detailed description of the data fusion method based on the industrial Internet of Things, those skilled in the art can clearly understand an intelligent processing system in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.
[0077] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
[0078] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.
Claims
1. The data fusion method based on industrial Internet of Things is characterized by: include: Divide the target industrial plant area into blocks to obtain a target division result, and deploy a first distributed fusion device in the first block in the target division result; Reading predetermined manufacturing features, and based on the predetermined manufacturing features, performing multi-dimensional manufacturing feature monitoring on each manufacturing equipment in the first block at a first time to obtain a first manufacturing feature parameter set, wherein the predetermined manufacturing features include operating state features and energy consumption features, wherein the operating state features include multiple operating indicator features; Performing distributed fusion analysis on the first operating characteristic parameter in the first manufacturing characteristic parameter set by the first distributed fuser to obtain a first manufacturing index; generating a first manufacturing timing of the first block based on a first corresponding relationship between the first time and the first manufacturing index; Reading a predetermined timing prediction strategy, and performing a prediction analysis on the first manufacturing timing according to the predetermined timing prediction strategy to obtain a first target prediction manufacturing index under the target time, including: collecting multi-domain features of the first manufacturing timing according to the predetermined timing prediction strategy to obtain first multi-domain feature information; using the first multi-domain feature information and the target time as input information of a manufacturing prediction model to obtain the first target prediction manufacturing index; wherein the construction process of the manufacturing prediction model is as follows: obtaining a historical manufacturing timing; obtaining a first historical time, and matching the first historical manufacturing index corresponding to the first historical time in the historical manufacturing timing; taking the first historical time as a constraint to perform segment interception on the historical manufacturing timing to obtain the first historical manufacturing timing; collecting multi-domain features of the first historical manufacturing timing according to the predetermined timing prediction strategy to obtain the first historical multi-domain feature information; performing supervised learning on the first historical data set composed of the first historical multi-domain feature information and the first historical manufacturing index based on the principle of neural network to obtain the manufacturing prediction model; If the first target predicted manufacturing index does not meet the predetermined manufacturing limit, issuing a first predictive control instruction; Based on the first predictive control instruction, the first optimal control plan of each manufacturing equipment in the first block is obtained, including: normalizing the first energy consumption characteristic parameter in the first manufacturing characteristic parameter set, and weighting it with the first manufacturing index to obtain a first fitness; arbitrarily obtaining the first control plan of the first block; obtaining first simulation information of the first control plan, the first simulation information including a first simulation manufacturing index and a first simulation energy consumption index; weighting and normalizing the first simulation manufacturing index and the first simulation energy consumption index to obtain a first simulation fitness; if the first simulation fitness is greater than the first fitness, taking the first control plan as the first optimal control plan; Under the target time, regulating the target industrial plant according to the first optimal regulation plan; If the first target predicted manufacturing index meets the predetermined manufacturing limit, issuing an integrated fusion instruction; Acquire a second target predicted manufacturing index of the second block at the target time based on the integrated fusion instruction; Performing a weighted analysis on the first target forecast manufacturing index and the second target forecast manufacturing index using the coefficient of variation principle to obtain a target forecast manufacturing index; The target predicted manufacturing index is used to characterize the comprehensive manufacturing status of the target industrial plant at the target time.
2. The data fusion method based on industrial Internet of Things according to claim 1 is characterized in that: include: Sequentially extracting a first manufacturing device and a second manufacturing device in the first block, wherein the first manufacturing device and the second manufacturing device are the same type of devices; In the first manufacturing feature parameter set, sequentially traverse to obtain a first parameter set of the first manufacturing equipment and a second parameter set of the second manufacturing equipment; Obtaining a first indicator from the plurality of operating indicator features, and traversing the first parameter set and the second parameter set in turn to obtain a first indicator parameter and a second indicator parameter respectively; Introducing a monitoring support function to perform support analysis on the first indicator parameter and the second indicator parameter to obtain support; If the support does not reach a predetermined support limit, a retest instruction is issued, and the first indicator is repeatedly monitored based on the retest instruction.
3. The data fusion method based on industrial Internet of Things according to claim 2 is characterized in that: The expression of the monitoring support function is as follows: ; in, Refers to the second indicator parameter The first indicator parameter The support of , k refers to the magnitude of the monitoring support function, and , is the attenuation factor, and .
4. An intelligent processing system, characterized in that: The intelligent processing system is used to execute the data fusion method based on the industrial Internet of Things as described in any one of claims 1 to 3, and the intelligent processing system includes: A partitioning and deployment module, the partitioning and deployment module is used to partition the target industrial plant area into blocks to obtain a target partitioning result, and to deploy a first distributed fusion device in a first block in the target partitioning result; A feature monitoring module, the feature monitoring module is used to read a predetermined manufacturing feature, and based on the predetermined manufacturing feature, perform multi-dimensional manufacturing feature monitoring on each manufacturing device in the first block at a first time to obtain a first manufacturing feature parameter set, wherein the predetermined manufacturing feature includes an operation status feature and an energy consumption feature, wherein the operation status feature includes a plurality of operation index features; a distributed fusion module, the distributed fusion module being used to perform distributed fusion analysis on the first operation characteristic parameter in the first manufacturing characteristic parameter set through the first distributed fuser to obtain a first manufacturing index; a timing generation module, the timing generation module being configured to generate a first manufacturing timing of the first block based on a first corresponding relationship between the first time and the first manufacturing index; A timing prediction module, the timing prediction module is used to read a predetermined timing prediction strategy, and perform a prediction analysis on the first manufacturing timing according to the predetermined timing prediction strategy to obtain a first target prediction manufacturing index under the target time. The timing prediction module is also used to: collect multi-domain features of the first manufacturing timing according to the predetermined timing prediction strategy to obtain first multi-domain feature information; use the first multi-domain feature information and the target time as input information of a manufacturing prediction model to obtain the first target prediction manufacturing index; wherein the construction process of the manufacturing prediction model is as follows: obtain a historical manufacturing timing; obtain a first historical time, and match the first historical manufacturing index corresponding to the first historical time in the historical manufacturing timing; take the first historical time as a constraint to perform segment interception on the historical manufacturing timing to obtain the first historical manufacturing timing; collect multi-domain features of the first historical manufacturing timing according to the predetermined timing prediction strategy to obtain the first historical multi-domain feature information; perform supervised learning on the first historical data set composed of the first historical multi-domain feature information and the first historical manufacturing index based on the principle of neural network to obtain the manufacturing prediction model; a predictive control module, the predictive control module being configured to issue a first predictive control instruction if the first target predicted manufacturing index does not meet a predetermined manufacturing limit; A control optimization module, the control optimization module is used to obtain the first optimal control plan for each manufacturing equipment in the first block based on the first predictive control instruction, and the control optimization module is also used to: normalize the first energy consumption characteristic parameter in the first manufacturing characteristic parameter set, and weight it with the first manufacturing index to obtain a first fitness; arbitrarily obtain the first control plan for the first block; obtain the first simulation information of the first control plan, the first simulation information includes a first simulation manufacturing index and a first simulation energy consumption index; obtain the first simulation fitness after weighted normalization of the first simulation manufacturing index and the first simulation energy consumption index; if the first simulation fitness is greater than the first fitness, use the first control plan as the first optimal control plan; a control execution module, the control execution module is used to control the target industrial plant according to the first optimal control plan at the target time; A comprehensive manufacturing status evaluation module, wherein the comprehensive manufacturing status evaluation module is used to issue an integrated fusion instruction if the first target predicted manufacturing index meets the predetermined manufacturing limit; obtain the second target predicted manufacturing index of the second block at the target time based on the integrated fusion instruction; use the coefficient of variation principle to perform a weighted analysis on the first target predicted manufacturing index and the second target predicted manufacturing index to obtain a target predicted manufacturing index; wherein the target predicted manufacturing index is used to characterize the comprehensive manufacturing status of the target industrial plant at the target time.
Citation Information
Patent Citations
Wireless sensor node and RFID (Radio Frequency Identification) data fusion method
CN103281805A
Distributed optical network terminal fault monitoring method and system
CN118054845A
