Industrial production process optimization management system based on Internet of Things

Abstract

The invention provides an industrial production process optimization management system based on the Internet of Things, and relates to the technical field of production management. The system comprises a data acquisition module, a data preprocessing module, a data analysis module, an evaluation index acquisition module, a production improvement module and a feedback optimization module. The data acquisition module is used for acquiring production data; the data preprocessing module is used for acquiring preprocessed data, and the data analysis module is used for constructing a linear evaluation model, inputting the preprocessed data and outputting production parameters; the evaluation index acquisition module is used for acquiring optimal production parameters; the production improvement module is used for formulating a production improvement strategy; and the feedback optimization module is used for continuously optimizing the linear evaluation model and the production improvement strategy. Through cooperative work of all the modules, data-driven production optimization decision making is achieved, product quality and production efficiency are improved, cost and resource consumption are reduced, and innovative revolution and sustainable development power are brought to the field of industrial production.

Description

Technical Field

[0001] The present invention relates to the technical field of production management, and in particular to an industrial production process optimization management system based on the Internet of Things. Background Art

[0002] In today's society, industrial production is an important pillar of economic development. With the continuous advancement of science and technology and the increasing diversification of market demand, the industrial production process has undergone a long and profound transformation. Early industrial production mainly relied on manual labor and simple mechanical tools, with low production efficiency and uneven product quality. With the invention and widespread application of steam engines, the first industrial revolution began, mechanized production gradually replaced manual labor, the factory system was established, and large-scale production became possible. This greatly improved production efficiency, reduced product costs, and provided society with abundant goods. In the second industrial revolution, the widespread use of electricity and the invention of the internal combustion engine further promoted the development of industrial production. The emergence of production lines made the production process more standardized and specialized, and the division of labor more refined. Major breakthroughs have been made in the chemical industry, steel industry and other fields, new materials and processes have continued to emerge, the product variety has become richer, and the quality has also been significantly improved. Entering the modern era, the rapid development of information technology has brought new opportunities and challenges to industrial production. The application of computer technology, automation control technology and sensor technology has made industrial production automated and intelligent. Production equipment can self-monitor, self-diagnose and self-adjust, and the accuracy and stability of the production process are greatly guaranteed. At the same time, the popularization of the Internet enables enterprises to achieve global resource allocation and supply chain management, improving production flexibility and responsiveness.

[0003] Although the industrial production process optimization management system based on the Internet of Things has brought many advantages, it also has some technical defects that cannot be ignored. The control of product quality often relies on manual sampling and limited testing equipment, which makes it difficult to achieve comprehensive and real-time monitoring of the production process. This leads to a lag in the discovery of quality problems and the inability to adjust production parameters in a timely manner, thus affecting the stability and consistency of product quality. Moreover, due to the lack of accurate data analysis, it is difficult to accurately trace the root cause of quality problems, making quality improvement work lack of pertinence and effectiveness. Traditional production processes usually lack effective coordination and optimization. The information flow between various production links is not smooth, which is prone to overproduction or insufficient supply, resulting in waste of resources and extended production cycles. Summary of the invention

[0004] The present invention provides an industrial production process optimization management system based on the Internet of Things to solve the defects in the prior art.

[0005] The present invention provides an industrial production process optimization management system based on the Internet of Things, comprising: The data acquisition module is used to collect production data in the industrial production process in real time. The production data includes equipment parameters and product quality parameters.

[0006] The data preprocessing module is used to preprocess the collected production data to obtain preprocessed data.

[0007] The data analysis module is used to establish a linear evaluation model between equipment parameters and product quality parameters based on the linear regression algorithm, input preprocessed data, and output production parameters.

[0008] The evaluation index acquisition module is used to analyze the equipment parameters and product quality parameters in the historical production process, and obtain the optimal production parameters in the historical production process based on the linear evaluation model.

[0009] The production improvement module is used to compare the production management data in the current production process with the optimal production parameters, obtain production differences, and formulate production improvement strategies based on the production differences.

[0010] The feedback optimization module is used to establish a real-time monitoring feedback mechanism, evaluate the implementation effect of the production improvement strategy, and continuously optimize the linear evaluation model and production improvement strategy based on the evaluation results.

[0011] According to the industrial production process optimization management system based on the Internet of Things provided by the present invention, the data acquisition module includes a sensor unit and a data acquisition unit. The sensor unit is used to obtain production data in the industrial production process and convert the production data into an electrical signal. The data acquisition unit is used to receive the electrical signal and convert the electrical signal into a digital signal using an analog-to-digital converter.

[0012] According to the industrial production process optimization management system based on the Internet of Things provided by the present invention, the data preprocessing module includes a data cleaning unit, a data conversion unit and a data compression unit. The data cleaning unit is used to screen and filter the production data to remove invalid, erroneous or duplicated data in the production data. The data conversion unit is used to convert the production data into the same format and unit. The data compression unit is used to compress the production data using the Huffman coding algorithm to reduce the storage space of the production data.

[0013] According to the industrial production process optimization management system based on the Internet of Things provided by the present invention, the data analysis module includes a data modeling unit, and the data modeling unit is used to construct a linear evaluation model based on a linear regression algorithm. The process includes: Divide the preprocessed data into training and testing sets.

[0014] Use the training set to build a linear evaluation model based on the linear regression algorithm. The formula is expressed as:

[0015] In the formula, y represents the product quality parameter, , , …, Indicates device parameters. represents the intercept, , , …, represents the regression coefficient, represents the error term.

[0016] Add to the loss function Constrain the regression coefficients to prevent overfitting.

[0017] The mean square error is used as the evaluation indicator, the linear evaluation model is evaluated using the test set, and the model parameters are adjusted according to the evaluation results until the preset model performance is met.

[0018] According to the industrial production process optimization management system based on the Internet of Things provided by the present invention, the data analysis module also includes a coefficient and intercept calculation unit and a goodness of fit evaluation unit. The coefficient and intercept calculation unit is used to calculate the coefficient and intercept in the linear evaluation model. The goodness of fit evaluation unit is used to evaluate the goodness of fit of the linear evaluation model and judge the degree of fit of the linear evaluation model to the production data.

[0019] According to the Internet of Things-based industrial production process optimization management system provided by the present invention, the evaluation index acquisition module includes a historical data acquisition unit, an optimal production parameter calculation unit and an index storage and retrieval unit. The historical data acquisition unit is used to collect historical production data in the industrial production process, and the historical production data includes historical equipment parameters and corresponding historical product quality parameters. The optimal production parameter calculation unit is used to obtain the optimal production parameters in the historical production process through a linear evaluation model based on the historical production data. The index storage and retrieval unit is used to store the optimal production parameters and provide retrieval and query functions.

[0020] According to the industrial production process optimization management system based on the Internet of Things provided by the present invention, the process of obtaining the optimal production parameters includes: Input historical production data into the linear evaluation model and output historical production parameters.

[0021] The historical production parameters are encoded and expressed in the form of gene strings.

[0022] Genetic optimization of gene strings, including: A set of initial gene strings is randomly generated to form an initial population.

[0023] For each gene string in the initial population, it is decoded into the corresponding production parameter value and substituted into the objective function to calculate the fitness value.

[0024] According to the fitness value, a roulette wheel selection strategy is used to select a part of individuals from the current population as parent individuals to reproduce the next generation.

[0025] Perform a crossover operation on the selected parent individuals to generate new offspring individuals.

[0026] Perform mutation operations on offspring individuals to increase the diversity of the population.

[0027] The genetic optimization process is repeated until the preset number of iterations is reached, and the individual with the highest fitness value is selected and decoded as the optimal production parameter.

[0028] According to the industrial production process optimization management system based on the Internet of Things provided by the present invention, the production improvement module includes a difference comparison unit, a strategy customization unit and a strategy implementation unit. The difference comparison unit is used to compare the production parameters with the optimal production parameters, and the difference value between the production parameters and the optimal production parameters is used as the production difference. The strategy customization unit is used to formulate corresponding production improvement strategies based on the production differences using the rule engine method. The strategy implementation unit is used to convert the production improvement strategy into a production control instruction, and send the production control instruction to the production equipment through the communication interface.

[0029] According to the industrial production process optimization management system based on the Internet of Things provided by the present invention, the feedback optimization module includes a real-time monitoring unit and an effect evaluation unit. The real-time monitoring unit is used to monitor the implementation process of the production improvement strategy in real time and obtain monitoring data, and the monitoring data includes improved parameters and improved product quality. The effect evaluation unit is used to evaluate the implementation effect of the production improvement strategy based on the monitoring data.

[0030] According to the Internet of Things-based industrial production process optimization management system provided by the present invention, the feedback optimization module also includes a model and strategy optimization unit, which is used to continuously optimize the linear evaluation model and production improvement strategy according to the evaluation results of the effect evaluation unit.

[0031] The industrial production process optimization management system based on the Internet of Things provided by the present invention collects equipment parameters and product quality parameters in the industrial production process in real time through a data acquisition module, ensuring the timeliness and comprehensiveness of the data. Various key information in the production process can be accurately acquired, providing a solid data foundation for subsequent analysis and optimization, and avoiding decision-making errors caused by data loss or lag. The data preprocessing module preprocesses the collected data to improve the quality and availability of the data. Noise and outliers are removed to make the data more accurate and reliable, providing a pure data environment for subsequent analysis and modeling, and enhancing the accuracy and stability of the model. The data analysis module uses a linear regression algorithm to establish a linear evaluation model between equipment parameters and product quality parameters, which can clearly reveal the inherent relationship between the two. It helps to deeply understand the cause-and-effect relationship in the production process, so as to adjust the production parameters more targetedly, achieve accurate production control, and improve the consistency and stability of product quality. The evaluation index acquisition module can analyze historical production data and obtain optimal production parameters, providing a valuable reference for current production. Enterprises can learn from past successful experiences, avoid repeating mistakes, quickly find the direction of optimizing production, significantly improve production efficiency and resource utilization, and reduce production costs. The production improvement module compares the current production management data with the optimal production parameters, clarifies the production differences and formulates improvement strategies. The production process can be dynamically adjusted according to the actual situation, and the deficiencies can be made up in time to ensure that the production is always developing in the optimal direction and enhance the market competitiveness of the enterprise. The real-time monitoring feedback mechanism established by the feedback optimization module can timely evaluate the implementation effect of the production improvement strategy. According to the evaluation results, the linear evaluation model and production improvement strategy are continuously optimized to form a closed-loop system that is constantly improving and evolving. The entire production management system can adapt to the ever-changing production environment and market demand, and has strong self-adjustment and optimization capabilities to ensure that the enterprise maintains a leading position in long-term production operations. In summary, the industrial production process optimization management system realizes data-driven production optimization decisions through the collaborative work of various modules. It not only improves product quality and production efficiency, reduces costs and resource consumption, but also enhances the market adaptability and competitiveness of enterprises, bringing innovative changes and sustainable development momentum to the field of industrial production. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0033] Figure 1It is a structural diagram of an industrial production process optimization management system based on the Internet of Things provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are 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.

[0035] Combine the following Figure 1 The present invention describes an industrial production process optimization management system based on the Internet of Things.

[0036] Figure 1 It is a flow chart of an industrial production process optimization management system based on the Internet of Things provided by an embodiment of the present invention.

[0037] like Figure 1 As shown, the industrial production process optimization management system based on the Internet of Things provided by the embodiment of the present invention includes a data acquisition module, a data preprocessing module, a data analysis module, an evaluation index acquisition module, a production improvement module and a feedback optimization module.

[0038] The data acquisition module is used to collect production data in the industrial production process in real time. The production data includes equipment parameters and product quality parameters.

[0039] The data acquisition module includes a sensor unit and a data acquisition unit. The sensor unit is used to obtain production data in the industrial production process and convert the production data into electrical signals. The data acquisition unit is used to receive electrical signals and convert the electrical signals into digital signals using an analog-to-digital converter.

[0040] In this embodiment, the sensor unit plays a key role. First, according to the characteristics of the industrial production process and the type of parameters to be monitored, a suitable sensor is selected. For example, for temperature monitoring, a thermistor sensor can be selected; for pressure monitoring, a pressure sensor may be used. These sensors are installed at key positions of production equipment to accurately obtain equipment parameters and product quality parameters. When the production process is in progress, the sensor senses the corresponding physical quantity changes and converts them into electrical signals. The strength of the electrical signal is proportional to the size of the monitored physical quantity. Then, the data acquisition unit starts working. It receives electrical signals from the sensor unit and converts these analog electrical signals into digital signals through an analog-to-digital converter (ADC). The working principle of the analog-to-digital converter is to sample and quantize the input analog electrical signals according to a certain sampling frequency. During the sampling process, it obtains the instantaneous value of the electrical signal at a fixed time interval. Then, these sampled values ​​are converted into discrete digital quantities through quantization. The accuracy of quantization depends on the number of bits of the ADC. The higher the number of bits, the higher the accuracy of quantization, and the more accurately the original analog signal can be represented. The converted digital signal is transmitted to the subsequent data processing and analysis module. During the transmission process, in order to ensure the accuracy and integrity of the data, some data verification and error correction mechanisms may be used. In addition, the data acquisition unit also needs to have a certain anti-interference ability to cope with factors such as electromagnetic interference that may exist in the industrial production environment to ensure that the collected data is true and reliable. Through the collaborative work of the sensor unit and the data acquisition unit, the real-time and accurate collection of production data in the industrial production process is realized, providing a basis for subsequent analysis and optimization.

[0041] The data preprocessing module is used to preprocess the collected production data to obtain preprocessed data.

[0042] The data preprocessing module includes a data cleaning unit, a data conversion unit and a data compression unit. The data cleaning unit is used to screen and filter the production data to remove invalid, erroneous or duplicated data in the production data. The data conversion unit is used to convert the production data into the same format and unit. The data compression unit is used to compress the production data using the Huffman coding algorithm to reduce the storage space of the production data.

[0043] In this embodiment, when the production data is collected, the data cleaning unit will immediately screen and filter it. It will identify invalid data through a series of rules and algorithms. For example, if the value of a certain equipment parameter exceeds its reasonable range, or if the product quality parameter has an extreme value that is obviously inconsistent with the actual situation, these data will be marked as invalid data. At the same time, for repeated data records, the cleaning unit will only retain one copy to avoid data redundancy. For erroneous data, it may be corrected by comparing with other related data and logical judgment, or directly deleted. Next is the data conversion unit. Since different equipment and sensors may generate production data in different formats and units, the data conversion unit will convert these data into the same standard format and unit. For example, convert temperature data from Fahrenheit to Celsius, and convert pressure data from pounds per square inch to Pascal. The conversion unit will refer to the preset conversion rules and standards and complete the conversion process through mathematical operations and data mapping. This enables subsequent data analysis and processing to be carried out on a unified data basis, avoiding confusion and errors caused by inconsistent data formats and units. Then there is the data compression unit. The cleaned and converted data will enter the data compression unit. Huffman coding is a commonly used lossless compression algorithm. The compression unit will first count the frequency of occurrence of characters or values ​​in the data. Characters or values ​​with high frequency will be assigned shorter codes, while those with low frequency will be assigned longer codes. For example, if the value "0" appears frequently in the production data, it may be assigned a shorter code, such as "00"; while the value "999" with low frequency may be assigned a longer code, such as "1101". In this way, the space occupied by the data during storage and transmission will be greatly reduced, thereby improving the efficiency of data storage and transmission. During the entire preprocessing process, each unit will continuously optimize and adjust its own parameters and rules to adapt to production data of different types and characteristics. At the same time, the preprocessing module will also perform quality assessment and verification on the processed data to ensure that the preprocessed data is accurate, complete, valid, and meets the requirements of subsequent analysis and processing. Through the careful processing of the data preprocessing module, a high-quality, easy-to-process and store data foundation is provided for subsequent data analysis and decision-making.

[0044] The data analysis module is used to establish a linear evaluation model between equipment parameters and product quality parameters based on the linear regression algorithm, input preprocessed data, and output production parameters.

[0045] The data analysis module includes a data modeling unit, which is used to build a linear evaluation model based on a linear regression algorithm. The process includes: Divide the preprocessed data into training and testing sets.

[0046] Use the training set to build a linear evaluation model based on the linear regression algorithm. The formula is expressed as:

[0047] In the formula, y represents the product quality parameter, , , …, Indicates device parameters. represents the intercept, , , …, represents the regression coefficient, represents the error term.

[0048] Add to the loss function Constrain the regression coefficients to prevent overfitting.

[0049] The mean square error is used as the evaluation indicator, the linear evaluation model is evaluated using the test set, and the model parameters are adjusted according to the evaluation results until the preset model performance is met.

[0050] The data analysis module also includes a coefficient and intercept calculation unit and a goodness of fit evaluation unit. The coefficient and intercept calculation unit is used to calculate the coefficient and intercept in the linear evaluation model. The goodness of fit evaluation unit is used to evaluate the goodness of fit of the linear evaluation model and determine the degree of fit of the linear evaluation model to the production data.

[0051] The evaluation index acquisition module is used to analyze the equipment parameters and product quality parameters in the historical production process, and obtain the optimal production parameters in the historical production process based on the linear evaluation model.

[0052] The evaluation index acquisition module includes a historical data acquisition unit, an optimal production parameter calculation unit and an index storage and retrieval unit. The historical data acquisition unit is used to collect historical production data in the industrial production process, and the historical production data includes historical equipment parameters and corresponding historical product quality parameters. The optimal production parameter calculation unit is used to obtain the optimal production parameters in the historical production process based on the historical production data through a linear evaluation model. The index storage and retrieval unit is used to store the optimal production parameters and provide retrieval and query functions.

[0053] The process of obtaining the optimal production parameters includes: Input historical production data into the linear evaluation model and output historical production parameters.

[0054] The historical production parameters are encoded and expressed in the form of gene strings.

[0055] A set of initial gene strings is randomly generated to form an initial population.

[0056] Genetic optimization of gene strings, including: For each gene string in the initial population, it is decoded into the corresponding production parameter value and substituted into the objective function to calculate the fitness value.

[0057] According to the fitness value, a roulette wheel selection strategy is used to select a part of individuals from the current population as parent individuals to reproduce the next generation.

[0058] Perform a crossover operation on the selected parent individuals to generate new offspring individuals.

[0059] Perform mutation operations on offspring individuals to increase the diversity of the population.

[0060] The genetic optimization process is repeated until the preset number of iterations is reached, and the individual with the highest fitness value is selected and decoded as the optimal production parameter.

[0061] In this embodiment, in the evaluation index acquisition module, each unit works closely together to obtain the optimal production parameters in the historical production process. First, the historical data acquisition unit plays a role. It collects historical production data in the industrial production process from a database or data storage system, which covers historical equipment parameters and corresponding historical product quality parameters. During the collection process, the integrity and accuracy of the data are ensured, and missing or abnormal data are marked and processed. Then, the optimal production parameter calculation unit starts working. It inputs the collected historical production data into the linear evaluation model. In the linear evaluation model, the historical production data is used as an input variable, and after calculation and processing inside the model, the historical production parameters are output. Then enter the core step of obtaining the optimal production parameters. The historical production parameters are encoded and expressed in the form of gene strings. This encoding method enables the production parameters to exist in a form suitable for genetic algorithm processing. A set of initial gene strings is randomly generated to form an initial population. This initial population represents the possibility of potential production parameter combinations. For each gene string in the initial population, it is decoded into a corresponding production parameter value and substituted into the objective function to calculate the fitness value. The fitness value reflects the degree of superiority or inferiority of the production parameter combination represented by the gene string in achieving the production goal. According to the fitness value, a roulette wheel selection strategy is used to select a part of individuals from the current population as parent individuals to reproduce the next generation. In the roulette wheel selection, the individuals with higher fitness values ​​have a greater probability of being selected, so that excellent gene combinations have more opportunities to be passed on to the next generation. The selected parent individuals are crossover operated. The crossover operation randomly selects the gene fragments of the parent individuals for exchange to generate new offspring individuals, thereby creating a gene combination with new characteristics. The offspring individuals are mutated. Mutation randomly changes the gene values ​​of offspring individuals with a smaller probability, increases the diversity of the population, and avoids the algorithm from falling into a local optimal solution. The genetic optimization process is repeated continuously, that is, new populations are continuously generated, fitness is evaluated, and selection, crossover and mutation operations are performed. Until the preset number of iterations is reached. In each iteration, the overall fitness of the population gradually increases and gradually approaches the optimal solution. Finally, the individual with the highest fitness value is selected and decoded as the optimal production parameter. The indicator storage and retrieval unit is responsible for storing the obtained optimal production parameters. Efficient data structures and database management technologies are used during storage to ensure fast writing and reading. At the same time, it provides retrieval and query functions so that these optimal production parameters can be quickly obtained and used when needed. Through the above detailed steps and the collaborative work of the units, the evaluation index acquisition module can accurately and efficiently obtain the optimal production parameters in the historical production process, providing strong support for the optimization and improvement of industrial production.

[0062] The production improvement module is used to compare the production management data in the current production process with the optimal production parameters, obtain production differences, and formulate production improvement strategies based on the production differences.

[0063] The production improvement module includes a difference comparison unit, a strategy customization unit and a strategy implementation unit. The difference comparison unit is used to compare the production parameters with the optimal production parameters, and the difference between the production parameters and the optimal production parameters is used as the production difference. The strategy customization unit is used to formulate corresponding production improvement strategies based on the production difference using the rule engine method. The strategy implementation unit is used to convert the production improvement strategy into a production control instruction and send the production control instruction to the production equipment through the communication interface.

[0064] In this embodiment, the work of the production improvement module is first started by the difference comparison unit. This unit obtains the production parameters contained in the production management data in the current production process, and extracts the optimal production parameters that have been obtained. Then, the two sets of parameters are compared one by one, the numerical difference between each parameter is calculated, and these difference values ​​are combined as the production difference. Next, the strategy customization unit starts working according to the production difference obtained by the difference comparison unit. The rule engine method comes into play at this time, and it has a series of rules preset inside that are formulated according to different production difference situations. For example, if the difference of a key equipment parameter exceeds a certain threshold, it may correspond to a strategy that requires adjusting the equipment running speed or replacing parts; if the difference of product quality parameters is large, it may mean that the process needs to be improved or the quality inspection link needs to be strengthened. By matching the production difference with the preset rules, the strategy customization unit generates the corresponding production improvement strategy. After that, the strategy implementation unit takes over. It converts the formulated production improvement strategy into a production control instruction that the production equipment can understand and execute. This conversion process needs to consider the communication protocol and control interface requirements of the production equipment. After the conversion is completed, the production control instruction is accurately and timely sent to the production equipment through a communication interface, such as industrial Ethernet, wireless network, etc. Throughout the entire process, each unit works closely together to monitor changes in production parameters in real time, and quickly formulates and implements improvement strategies based on comparison results to ensure that the production process can continuously approach the optimal state, improve production efficiency and product quality, and reduce production costs and resource consumption.

[0065] The feedback optimization module is used to establish a real-time monitoring feedback mechanism, evaluate the implementation effect of the production improvement strategy, and continuously optimize the linear evaluation model and production improvement strategy based on the evaluation results.

[0066] The feedback optimization module includes a real-time monitoring unit and an effect evaluation unit. The real-time monitoring unit is used to monitor the implementation process of the production improvement strategy and obtain monitoring data, which includes improvement parameters and improved product quality. The effect evaluation unit is used to evaluate the implementation effect of the production improvement strategy based on the monitoring data.

[0067] The feedback optimization module also includes a model and strategy optimization unit, which is used to continuously optimize the linear evaluation model and the production improvement strategy according to the evaluation results of the effect evaluation unit.

[0068] In this embodiment, the work of the feedback optimization module is first started by the real-time monitoring unit. The real-time monitoring unit monitors the implementation process of the production improvement strategy in real time by connecting with the production equipment and the quality inspection system. It continuously collects various data in the improvement process, including key information such as the improved equipment parameters and product quality, to form detailed monitoring data. The effect evaluation unit then analyzes and processes these monitoring data. It compares the monitored improvement parameters and the improved product quality with the expected goals. For example, it compares whether the parameters such as the improved equipment running speed and temperature have reached the optimization expectations, and whether the quality indicators of the product have been significantly improved. Through a series of evaluation indicators and algorithms, the implementation effect of the production improvement strategy is comprehensively evaluated, and a quantitative evaluation result is given. The model and strategy optimization unit takes action based on the evaluation results of the effect evaluation unit. If the evaluation results show that the production improvement strategy has achieved good results, it will further strengthen and consolidate the relevant strategies and apply them to similar production scenarios where appropriate. If the evaluation results are unsatisfactory, it will analyze the reasons in depth, which may be that the parameters of the linear evaluation model are inaccurate or the production improvement strategy has defects. For the linear evaluation model, the model and strategy optimization unit will adjust the model's coefficients, variable weights and other parameters to improve the model's accuracy and predictive ability. For the production improvement strategy, it will re-examine the strategy formulation logic and steps, and may modify certain aspects of the strategy, add new control variables or adjust the optimization direction, so as to achieve continuous optimization of the linear evaluation model and production improvement strategy, ensure that they can better adapt to the actual production situation, and continuously improve production efficiency and product quality.

[0069] In summary, this embodiment provides an industrial production process optimization management system based on the Internet of Things, which collects equipment parameters and product quality parameters in the industrial production process in real time through the data acquisition module, ensuring the timeliness and comprehensiveness of the data. Various key information in the production process can be accurately acquired, providing a solid data foundation for subsequent analysis and optimization, and avoiding decision-making errors caused by data loss or lag. The data preprocessing module preprocesses the collected data to improve the quality and availability of the data. Noise and outliers are removed to make the data more accurate and reliable, providing a pure data environment for subsequent analysis and modeling, and enhancing the accuracy and stability of the model. The data analysis module uses a linear regression algorithm to establish a linear evaluation model between equipment parameters and product quality parameters, which can clearly reveal the intrinsic relationship between the two. It helps to deeply understand the cause-and-effect relationship in the production process, so as to adjust the production parameters more targetedly, achieve precise production control, and improve the consistency and stability of product quality. The evaluation index acquisition module can analyze historical production data and obtain optimal production parameters, providing a valuable reference for current production. Enterprises can learn from past successful experiences, avoid repeating mistakes, quickly find the direction of optimizing production, significantly improve production efficiency and resource utilization, and reduce production costs. The production improvement module compares the current production management data with the optimal production parameters, clarifies the production differences and formulates improvement strategies. The production process can be dynamically adjusted according to the actual situation, and the deficiencies can be made up in time to ensure that production always develops in the optimal direction and enhance the market competitiveness of the enterprise. The real-time monitoring feedback mechanism established by the feedback optimization module can timely evaluate the implementation effect of the production improvement strategy. According to the evaluation results, the linear evaluation model and production improvement strategy are continuously optimized to form a closed-loop system that is constantly improving and evolving. The entire production management system can adapt to the ever-changing production environment and market demand, and has strong self-adjustment and optimization capabilities, ensuring that the enterprise maintains a leading position in long-term production operations. In summary, the industrial production process optimization management system realizes data-driven production optimization decisions through the collaborative work of various modules. It not only improves product quality and production efficiency, reduces costs and resource consumption, but also enhances the market adaptability and competitiveness of enterprises, bringing innovative changes and sustainable development momentum to the field of industrial production.

[0070] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0071] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. The industrial production process optimization management system based on the Internet of Things is characterized by: include: A data acquisition module, used to collect production data in the industrial production process in real time, wherein the production data includes equipment parameters and product quality parameters; A data preprocessing module, used to preprocess the collected production data to obtain preprocessed data; A data analysis module, used to establish a linear evaluation model between the equipment parameters and the product quality parameters according to a linear regression algorithm, input the preprocessed data, and output the production parameters; An evaluation index acquisition module is used to analyze the equipment parameters and product quality parameters in the historical production process, and obtain the optimal production parameters in the historical production process according to the linear evaluation model; A production improvement module, used to compare the production management data in the current production process with the optimal production parameters, obtain production differences, and formulate a production improvement strategy based on the production differences; The feedback optimization module is used to establish a real-time monitoring feedback mechanism, evaluate the implementation effect of the production improvement strategy, and continuously optimize the linear evaluation model and the production improvement strategy based on the evaluation results.

2. The industrial production process optimization management system based on the Internet of Things according to claim 1 is characterized in that: The data acquisition module includes a sensor unit and a data acquisition unit; the sensor unit is used to obtain production data in an industrial production process and convert the production data into an electrical signal; the data acquisition unit is used to receive the electrical signal and convert the electrical signal into a digital signal using an analog-to-digital converter.

3. The industrial production process optimization management system based on the Internet of Things according to claim 1 is characterized in that: The data preprocessing module includes a data cleaning unit, a data conversion unit and a data compression unit; the data cleaning unit is used to screen and filter the production data to remove invalid, erroneous or duplicate data in the production data; the data conversion unit is used to convert the production data into the same format and unit; the data compression unit is used to compress the production data using a Huffman coding algorithm to reduce the storage space of the production data.

4. The industrial production process optimization management system based on the Internet of Things according to claim 1 is characterized in that: The data analysis module includes a data modeling unit, and the data modeling unit is used to construct a linear evaluation model based on a linear regression algorithm. The process includes: Dividing the preprocessed data into a training set and a test set; The training set is used to construct a linear evaluation model based on a linear regression algorithm, and the formula is expressed as follows: In the formula, y represents the product quality parameter, , , …, Indicates device parameters. represents the intercept, , , …, represents the regression coefficient, represents the error term; Add to the loss function constraining the regression coefficients to prevent overfitting; The mean square error is used as an evaluation indicator, the linear evaluation model is evaluated using a test set, and the model parameters are adjusted according to the evaluation results until the preset model performance is met.

5. The industrial production process optimization management system based on the Internet of Things according to claim 1 is characterized in that: The data analysis module also includes a coefficient and intercept calculation unit and a goodness of fit evaluation unit; the coefficient and intercept calculation unit is used to calculate the coefficients and intercept in the linear evaluation model; the goodness of fit evaluation unit is used to evaluate the goodness of fit of the linear evaluation model and determine the degree of fit of the linear evaluation model to the production data.

6. The industrial production process optimization management system based on the Internet of Things according to claim 1 is characterized in that: The evaluation index acquisition module includes a historical data acquisition unit, an optimal production parameter calculation unit and an index storage and retrieval unit; the historical data acquisition unit is used to collect historical production data in the industrial production process, and the historical production data includes historical equipment parameters and corresponding historical product quality parameters; the optimal production parameter calculation unit is used to obtain the optimal production parameters in the historical production process based on the historical production data through the linear evaluation model; the index storage and retrieval unit is used to store the optimal production parameters and provide retrieval and query functions.

7. The industrial production process optimization management system based on the Internet of Things according to claim 6 is characterized in that: The process of obtaining the optimal production parameters includes: Inputting the historical production data into the linear evaluation model and outputting historical production parameters; Encoding the historical production parameters in the form of gene strings; The gene string is genetically optimized, comprising: Randomly generate a set of initial gene strings to form an initial population; For each gene string in the initial population, decode it into a corresponding production parameter value, and substitute it into the objective function to calculate the fitness value; According to the fitness value, a roulette wheel selection strategy is used to select a part of individuals from the current population to serve as parent individuals to reproduce the next generation; Perform crossover operation on the selected parent individuals to generate new offspring individuals; Perform mutation operations on offspring individuals to increase the diversity of the population; The genetic optimization process is repeated until a preset number of iterations is reached, and the individual with the highest fitness value is selected and decoded as the optimal production parameter.

8. The industrial production process optimization management system based on the Internet of Things according to claim 1 is characterized in that: The production improvement module includes a difference comparison unit, a strategy customization unit and a strategy implementation unit; the difference comparison unit is used to compare the production parameters with the optimal production parameters, and use the difference value between the production parameters and the optimal production parameters as the production difference; the strategy customization unit is used to formulate corresponding production improvement strategies based on the production difference using a rule engine method; the strategy implementation unit is used to convert the production improvement strategy into a production control instruction, and send the production control instruction to the production equipment through a communication interface.

9. The industrial production process optimization management system based on the Internet of Things according to claim 1 is characterized in that: The feedback optimization module includes a real-time monitoring unit and an effect evaluation unit; the real-time monitoring unit is used to monitor the implementation process of the production improvement strategy and obtain monitoring data, wherein the monitoring data includes improvement parameters and improved product quality; the effect evaluation unit is used to evaluate the implementation effect of the production improvement strategy based on the monitoring data.

10. The industrial production process optimization management system based on the Internet of Things according to claim 9 is characterized in that: The feedback optimization module also includes a model and strategy optimization unit, which is used to continuously optimize the linear evaluation model and the production improvement strategy according to the evaluation result of the effect evaluation unit.

Images