A method for optimizing energy efficiency of PET bottle production line

Abstract

The present invention relates to the technical field of energy efficiency optimization, specifically to a method for optimizing the energy efficiency of a PET bottle production line, comprising the following steps: based on the process parameters of the PET bottle production line, analyzing the energy consumption characteristics of the heating, blow molding, and cooling links, identifying key links with low energy efficiency, including heating time exceeding a threshold value and unstable blow molding pressure, and obtaining key link energy efficiency analysis results. The present invention, by analyzing the process parameters of the production line, can accurately identify the key links with low energy efficiency, and adjust the parameters in a targeted manner to optimize energy consumption, and adopt a multivariate linear regression method to evaluate the impact of different parameter settings on energy efficiency, so that the optimization measures are more scientific and accurate, and by refining the operation priority and adjusting the production parameters using a deep deterministic policy gradient model, the energy utilization rate is optimized, and the cost and product quality are balanced, so that the entire production process is more efficient and sustainable, product quality is guaranteed, and the market competitiveness of the enterprise is significantly enhanced.

Description

Technical Field

[0001] The invention relates to the technical field of energy efficiency optimization, and in particular to an energy efficiency optimization method for a PET bottle production line. Background Art

[0002] The field of energy efficiency optimization technology focuses on improving energy efficiency in industrial production processes, reducing energy consumption while maintaining or improving product quality and production efficiency. This field covers a wide range of technologies and methods, including improving equipment design, optimizing production processes, implementing energy-saving measures, and adopting efficient energy conversion and utilization technologies. It aims to reduce the impact of industrial activities on the environment, reduce energy costs, and meet the requirements of sustainable development.

[0003] Among them, the energy efficiency optimization method of PET bottle production line aims to improve the energy efficiency of PET bottle manufacturing process by optimizing production line operation, equipment configuration and process flow. The purpose of this method is to reduce energy consumption in the production process and reduce production costs while ensuring or improving product quality, including improving energy utilization in heating, blowing and cooling processes, and optimizing production processes to reduce energy consumption and material waste. By achieving energy efficiency optimization, enterprises can reduce their environmental footprint and enhance their market competitiveness.

[0004] Traditional energy efficiency optimization methods lack analysis and precise adjustment of the complex relationship between energy efficiency and production parameters in each link of the production process. They only rely on experience to adjust equipment or optimize processes. They are unable to accurately identify the root causes of energy efficiency loss, resulting in energy waste and insufficient production efficiency. They fail to fully consider the comprehensive impact of production parameter adjustments on cost and product quality, which will lead to increased costs or reduced product quality while optimizing energy efficiency. This limits the effectiveness of traditional methods in improving production line energy efficiency, reducing environmental footprint and reducing production costs, and affects the overall competitiveness of enterprises. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings in the prior art and to propose a method for optimizing the energy efficiency of a PET bottle production line.

[0006] In order to achieve the above object, the present invention adopts the following technical scheme: a method for optimizing the energy efficiency of a PET bottle production line, comprising the following steps:

[0007] S1: Based on the process parameters of the PET bottle production line, the energy consumption characteristics of the heating, blowing and cooling links are analyzed to identify the key links with low energy efficiency, including heating time exceeding the threshold and unstable blowing pressure, and obtain the energy efficiency analysis results of the key links;

[0008] S2: According to the energy efficiency analysis results of the key links, analyze the energy efficiency influencing factors of multiple links, identify the correlation between energy consumption and production efficiency, and obtain the energy efficiency influencing factor identification results;

[0009] S3: Based on the identification results of the energy efficiency influencing factors, a multivariate linear regression method is used to evaluate the impact of differentiated parameter settings on energy efficiency, and corresponding optimization measures are implemented, including adjusting the heating temperature, optimizing the pressure setting, optimizing the energy efficiency of key links, and obtaining a matching optimization measure plan;

[0010] S4: According to the matching optimization measure plan, the operation priorities of multiple production links are refined, the energy utilization rate is optimized, and the operation priority adjustment strategy is obtained;

[0011] S5: Based on the operation priority adjustment strategy, combined with the real-time monitoring data of the production line, the deep deterministic policy gradient model is used to adjust the production parameters, optimize the balance between energy efficiency, cost and production quality, and obtain the production parameter adjustment plan;

[0012] S6: Using the production parameter adjustment plan, implement energy consumption adjustment and monitoring of production line equipment, respond to changes in the production process, optimize the production line operation status, and obtain dynamic optimization results of the production line;

[0013] S7: Based on the dynamic optimization results of the production line, the energy efficiency of the production line and the quality of the PET bottle products are tracked and evaluated, the effects of the optimization measures are analyzed, the energy efficiency improvement, cost reduction, and product quality are identified, and the energy efficiency optimization evaluation results are obtained.

[0014] The present invention has improvements in that the energy efficiency analysis results of the key links include overtime energy consumption in the heating link, pressure fluctuation in the blow molding link, and inconsistent cooling speed; the energy efficiency influencing factor identification results include energy consumption associated with production speed, the impact of heating temperature on energy efficiency, and the impact of pressure setting on product quality; the matching optimization measures include heating temperature adjustment, blow molding pressure stability improvement, and cooling speed regulation; the operation priority adjustment strategy specifically includes adjusting the heating parameters, optimizing the blow molding pressure, and adjusting the cooling speed priority; the production parameter adjustment plan includes adjusting the heating temperature range, the blow molding pressure setting value, and the cooling speed setting value; the production line dynamic optimization results include improved production line energy efficiency, reduced production costs, and enhanced product quality stability; the energy efficiency optimization evaluation results include the trend of energy efficiency improvement, the cumulative effect of cost savings, and the continuous improvement of product quality.

[0015] The present invention is improved in that, based on the process parameters of the PET bottle production line, the energy consumption characteristics of the heating, blow molding and cooling links are analyzed, and the key links with low energy efficiency are identified, including heating time exceeding the threshold and blow molding pressure being unstable. The specific steps for obtaining the energy efficiency analysis results of the key links are as follows:

[0016] S101: Based on the process parameters of the PET bottle production line, the energy consumption data of the heating, blow molding and cooling links are collected, including the energy consumption, operation time, temperature and pressure parameters of each link, and the data are integrated and processed to obtain an energy consumption data set;

[0017] S102: Analyze the heating time, blowing pressure and cooling speed parameters according to the energy consumption data set, identify the heating time exceeding the industry standard threshold and the blowing pressure fluctuation, and obtain a list of exceeding parameters;

[0018] S103: Based on the list of parameters exceeding the standard, evaluate the links with low energy efficiency, identify the heating time exceeding the threshold and the parameters of unstable blowing pressure as key energy inefficiency factors, and obtain the energy efficiency analysis results of the key links.

[0019] The present invention is improved in that, based on the energy efficiency analysis results of the key links, the energy efficiency influencing factors of multiple links are analyzed, the correlation between energy consumption and production efficiency is identified, and the specific steps of obtaining the energy efficiency influencing factor identification results are as follows:

[0020] S201: Based on the energy efficiency analysis results of the key links, parameters related to energy consumption and production efficiency are collected, including actual energy consumption, output rate and scrap rate, to generate an energy efficiency related parameter data set;

[0021] S202: using the energy efficiency related parameter data set, analyzing the influence of multiple links on energy consumption, identifying the correlation between production efficiency and energy consumption, identifying links with high energy consumption, low output rate and high scrap rate, and obtaining an energy efficiency correlation analysis table;

[0022] S203: Based on the energy efficiency correlation analysis table, identify the correlation between energy consumption and production efficiency, mark the influence of heating temperature and blow molding pressure on output rate and scrap rate, and obtain the energy efficiency influencing factor identification result.

[0023] The present invention is improved in that, based on the energy efficiency influencing factor identification result, a multivariate linear regression method is used to evaluate the influence of differentiated parameter settings on energy efficiency, and corresponding optimization measures are implemented, including adjusting the heating temperature, optimizing the pressure setting, and optimizing the energy efficiency of key links. The specific steps of obtaining a matching optimization measure scheme are as follows:

[0024] S301: According to the energy efficiency influencing factor identification result, the energy consumption data of the heating link is subdivided, the relationship between the heating time and the temperature setting and the energy consumption is identified, and the energy consumption value of each temperature point is recorded to obtain the energy consumption analysis result of the heating link;

[0025] S302: Based on the energy consumption analysis result of the heating link, analyze the pressure data of the blow molding link, record the energy consumption change and product quality data under the differentiated pressure settings, identify the impact of pressure fluctuations on energy consumption and product quality, and obtain the blow molding pressure analysis result;

[0026] S303: Based on the blow molding pressure analysis results and the heating link energy consumption analysis results, a multivariate linear regression method is used to evaluate the impact of differentiated parameter settings on energy efficiency, formulate measures to adjust the heating temperature and stabilize the blow molding pressure, and obtain a matching optimization measure plan;

[0027] The multivariate linear regression method is according to the formula:

[0028]

[0029] Calculate the energy efficiency value and evaluate the impact of differentiated parameter settings on energy efficiency, where: For energy efficiency, is the heating temperature, is the blowing pressure, is the cooling rate, is the intercept term, , and is the influence coefficient, is the error term.

[0030] The present invention is improved in that, based on the matching optimization measure scheme, the operation priorities of multiple production links are refined, the energy utilization rate is optimized, and the specific steps of obtaining the operation priority adjustment strategy are as follows:

[0031] S401: Based on the matching optimization measure plan, sort out the production flow chart, mark the operation priorities of various current production links, record energy consumption data and production efficiency data, and obtain a production link energy efficiency and priority record table;

[0032] S402: According to the production link energy efficiency and priority record table, by simulating the effects of differentiated operation priority adjustment plans, the balance point between energy utilization and production efficiency is captured and a priority adjustment simulation optimization result is generated;

[0033] S403: Based on the priority adjustment simulation optimization result, refine the operation priority adjustment plan, plan the optimization steps and operation guidance of multiple links, and obtain the operation priority adjustment strategy.

[0034] The present invention is improved in that, based on the operation priority adjustment strategy, combined with the real-time monitoring data of the production line, the deep deterministic policy gradient model is used to adjust the production parameters, optimize the balance between energy efficiency, cost and production quality, and obtain the specific steps of the production parameter adjustment plan as follows:

[0035] S501: Based on the operation priority adjustment strategy, combined with the real-time monitoring data of the production line, the deep deterministic policy gradient model is used to adjust the heating temperature, blowing pressure and cooling speed parameters, optimize the energy efficiency, cost and product quality balance in the production process, and obtain a parameter optimization plan;

[0036] The deep deterministic policy gradient model is based on the formula:

[0037]

[0038] Calculate the improved action value function, where is the improved action value function, is the action value function, is the current state, For current actions, is the parameter of the current action value function, For instant rewards, is the discount factor, For the next state, The action to be taken in the next state, is the parameter of the next action value function, is the environmental factor adjustment coefficient, is the heating temperature parameter, is the blowing pressure parameter, is the cooling rate parameter, The weights of the adjustment coefficients for environmental factors;

[0039] S502: Based on the parameter optimization scheme, adjust the material flow and energy allocation strategy of the production line, optimize cost and production efficiency and reduce environmental impact, and obtain a cost-effectiveness optimization strategy;

[0040] S503: According to the cost-effectiveness optimization strategy, the production line operation is adjusted to match the market demand changes and raw material price fluctuations, the flexibility and response speed of the production line are optimized, and a production parameter adjustment plan is obtained.

[0041] The present invention is improved in that, based on the production parameter adjustment scheme, the energy consumption adjustment and monitoring of the production line equipment are implemented to cope with the changes and challenges in the production process, optimize the operation status of the production line, and obtain the specific steps of the dynamic optimization result of the production line as follows:

[0042] S601: Based on the production parameter adjustment plan, implement energy consumption adjustment of production line equipment, monitor the energy consumption of equipment in multiple links of the production line after adjustment, record energy consumption data before and after equipment adjustment, and obtain equipment energy consumption comparison data;

[0043] S602: using the equipment energy consumption comparison data, identifying equipment adjustment measures that reduce energy consumption and do not affect production efficiency, refining adjustment strategies, optimizing the production line operation status, and obtaining optimized production line status data;

[0044] S603: Perform data analysis based on the optimized production line status data to identify situations where production line equipment energy consumption is reduced, production costs are reduced, and product quality stability is enhanced, thereby obtaining a dynamic optimization result for the production line.

[0045] The present invention is improved in that, based on the dynamic optimization result of the production line, the energy efficiency of the production line and the quality of the PET bottle products are tracked and evaluated, the effects of the optimization measures are analyzed, and the energy efficiency improvement, cost reduction, and product quality are identified. The specific steps of obtaining the energy efficiency optimization evaluation result are as follows:

[0046] S701: Based on the dynamic optimization result of the production line, collect the energy consumption data of the optimized production line and the quality record of the PET bottle products, analyze the links of energy consumption reduction and product quality improvement points, and obtain the energy consumption and quality improvement analysis record;

[0047] S702: using the energy consumption and quality improvement analysis records, comparing the cost data before and after the optimization measures, evaluating the extent of cost reduction and the corresponding links, and obtaining cost saving evaluation results;

[0048] S703: Based on the energy consumption and quality improvement analysis records and cost savings evaluation results, evaluate the effectiveness of the optimization measures, identify the comprehensive energy efficiency improvement, cost reduction and product quality improvement, and obtain energy efficiency optimization evaluation results.

[0049] Compared with the prior art, the advantages and positive effects of the present invention are:

[0050] In the present invention, by analyzing the process parameters of the production line, the key links of low energy efficiency can be accurately identified, including problems such as too long heating time or unstable blow molding pressure, and the parameters can be adjusted in a targeted manner to optimize energy consumption. The multivariate linear regression method is used to evaluate the impact of different parameter settings on energy efficiency, making the optimization measures more scientific and precise. By refining the operation priority and adjusting the production parameters using the deep deterministic policy gradient model, the energy utilization rate is optimized, and the cost and product quality are balanced, making the entire production process more efficient and sustainable, ensuring product quality, and significantly enhancing the market competitiveness of the enterprise. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 A flow chart of a method for optimizing energy efficiency of a PET bottle production line is proposed for the present invention;

[0052] Figure 2The present invention proposes a detailed flow chart of step S1 in a method for optimizing energy efficiency of a PET bottle production line;

[0053] Figure 3 The present invention proposes a detailed flow chart of step S2 in a method for optimizing energy efficiency of a PET bottle production line;

[0054] Figure 4 The present invention proposes a detailed flow chart of step S3 in a method for optimizing the energy efficiency of a PET bottle production line;

[0055] Figure 5 The present invention proposes a detailed flow chart of step S4 in a method for optimizing energy efficiency of a PET bottle production line;

[0056] Figure 6 The present invention proposes a detailed flow chart of step S5 in a method for optimizing energy efficiency of a PET bottle production line;

[0057] Figure 7 The present invention proposes a detailed flow chart of step S6 in a method for optimizing energy efficiency of a PET bottle production line;

[0058] Figure 8 The present invention proposes a detailed flow chart of step S7 in a method for optimizing the energy efficiency of a PET bottle production line. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0060] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined. Example

[0061] See also Figure 1 The present invention provides a technical solution: a method for optimizing the energy efficiency of a PET bottle production line, comprising the following steps:

[0062] S1: Based on the process parameters of the PET bottle production line, the energy consumption characteristics of the heating, blowing and cooling links are analyzed to identify the key links with low energy efficiency, including heating time exceeding the threshold and unstable blowing pressure, and obtain the energy efficiency analysis results of the key links;

[0063] S2: Based on the results of energy efficiency analysis of key links, analyze the factors affecting energy efficiency in multiple links, identify the correlation between energy consumption and production efficiency, and obtain the results of identifying factors affecting energy efficiency;

[0064] S3: Based on the results of energy efficiency influencing factor identification, the multivariate linear regression method is used to evaluate the impact of differentiated parameter settings on energy efficiency, and corresponding optimization measures are implemented, including adjusting the heating temperature, optimizing the pressure setting, optimizing the energy efficiency of key links, and obtaining matching optimization measures.

[0065] S4: According to the matching optimization measure plan, the operation priorities of multiple production links are refined, the energy utilization rate is optimized, and the operation priority adjustment strategy is obtained;

[0066] S5: Based on the operation priority adjustment strategy, combined with the real-time monitoring data of the production line, the deep deterministic policy gradient model is used to adjust the production parameters, optimize the balance between energy efficiency, cost and production quality, and obtain the production parameter adjustment plan;

[0067] S6: Use the production parameter adjustment plan to implement production line equipment energy consumption adjustment and monitoring, respond to changes in the production process, optimize the production line operation status, and obtain dynamic optimization results of the production line;

[0068] S7: Based on the dynamic optimization results of the production line, conduct production line energy efficiency and PET bottle product quality tracking and evaluation, analyze the effects of optimization measures, identify energy efficiency improvement, cost reduction, and product quality, and obtain energy efficiency optimization evaluation results.

[0069] The results of energy efficiency analysis of key links include overtime energy consumption in the heating link, pressure fluctuation in the blow molding link, and inconsistent cooling speed. The results of identification of factors affecting energy efficiency include energy consumption related to production speed, the impact of heating temperature on energy efficiency, and the impact of pressure setting on product quality. The matching optimization measures include heating temperature adjustment, blow molding pressure stability improvement, and cooling speed adjustment. The operation priority adjustment strategy specifically includes adjusting heating parameters, optimizing blow molding pressure, and adjusting the priority of cooling speed. The production parameter adjustment plan includes adjusting the heating temperature range, blow molding pressure setting value, and cooling speed setting value. The results of dynamic optimization of the production line include improved energy efficiency of the production line, reduced production costs, and enhanced product quality stability. The results of energy efficiency optimization evaluation include the trend of energy efficiency improvement, the cumulative effect of cost savings, and the continuous improvement of product quality.

[0070] See also Figure 2Based on the process parameters of the PET bottle production line, the energy consumption characteristics of the heating, blowing and cooling links are analyzed to identify the key links with low energy efficiency, including heating time exceeding the threshold and unstable blowing pressure. The specific steps to obtain the energy efficiency analysis results of the key links are as follows:

[0071] S101: Based on the process parameters of the PET bottle production line, the energy consumption data of the heating, blow molding and cooling links are collected, including the energy consumption, operation time, temperature and pressure parameters of each link, and the data are integrated and processed to obtain the specific process of the energy consumption data set as follows;

[0072] In sub-step S101, based on the process parameters of the PET bottle production line, data aggregation technology is used to integrate the energy consumption data of the heating, blow molding, and cooling links using Python's Pandas library, including using groupby and merge functions to aggregate data by link, and summarizing the energy consumption, operation time, temperature, and pressure parameters of each link to form a unified data framework and generate an energy consumption data set.

[0073] S102: Analyze the heating time, blowing pressure and cooling speed parameters according to the energy consumption data set, identify the heating time exceeding the industry standard threshold and the blowing pressure fluctuation, and obtain the list of exceeding parameters. The specific process is as follows;

[0074] In sub-step S102, based on the energy consumption data set, a statistical analysis method is adopted, and the SciPy library is used to perform a volatility analysis of the heating time and blow molding pressure, including applying the describe function to obtain a statistical summary, using the zscore function to identify heating time and pressure fluctuations that deviate from the industry standard threshold, and generating a list of parameters that exceed the standard.

[0075] S103: Based on the list of parameters exceeding the standard, evaluate the links with low energy efficiency, identify the heating time exceeding the threshold and the parameters of unstable blow molding pressure as key energy inefficiency factors, and obtain the specific process of energy efficiency analysis results of key links as follows;

[0076] In sub-step S103, based on the list of parameters exceeding the standard, a decision tree classification method is adopted, and a decision tree model is constructed using the sklearn library, including setting the criteria to gini to evaluate data purity, using the fit function to train the model, classifying the heating time exceeding the threshold and the unstable blowing pressure, identifying them as key energy-inefficient factors, and generating energy efficiency analysis results for key links.

[0077] See also Figure 3 Based on the results of energy efficiency analysis of key links, the energy efficiency influencing factors of multiple links are analyzed to identify the correlation between energy consumption and production efficiency. The specific steps to obtain the results of energy efficiency influencing factor identification are as follows:

[0078] S201: Based on the results of energy efficiency analysis of key links, collect parameters related to energy consumption and production efficiency, including actual energy consumption, output rate and scrap rate, and generate energy efficiency related parameter data sets. The specific process is as follows;

[0079] In sub-step S201, based on the results of energy efficiency analysis of key links, a data integration and processing method is adopted. The Python programming language is combined with the Pandas library to create a data frame. The energy consumption data of the heating, blow molding, and cooling links, such as energy consumption, operation time, temperature, and pressure parameters, are merged and sorted. The data cleaning function is used to remove missing values ​​and outliers to ensure the integrity and accuracy of the data and generate a data set of energy efficiency-related parameters.

[0080] S202: Analyze the influence of multiple links on energy consumption using the energy efficiency related parameter data set, identify the correlation between production efficiency and energy consumption, identify links with high energy consumption, low output rate and high scrap rate, and obtain the energy efficiency correlation analysis table. The specific process is as follows;

[0081] In sub-step S202, based on the energy efficiency related parameter data set, a statistical analysis method is used to perform Pearson correlation coefficient calculation through the SciPy library in Python, and the correlation between the heating time, blowing pressure and cooling speed parameters and the energy consumption is analyzed. The conditional filtering function is used to filter out data points where the heating time exceeds the industry standard threshold and the blowing pressure fluctuates greatly. Cluster analysis is performed to determine the production links with high energy consumption, low output and high scrap rate, and an energy efficiency correlation analysis table is generated.

[0082] S203: Based on the energy efficiency correlation analysis table, identify the correlation between energy consumption and production efficiency, mark the influence of heating temperature and blow molding pressure on output rate and scrap rate, and obtain the specific process of energy efficiency influencing factor identification results as follows;

[0083] In sub-step S203, based on the energy efficiency correlation analysis table, a decision tree classification method is adopted to build a decision tree model through the Scikit-learn library in Python, and the heating temperature and blow molding pressure parameters are input as features, and the output rate and scrap rate are used as target variables. Model training and validation are performed, and the accuracy and generalization ability of the model are evaluated using the cross-validation method. The heating temperature and blow molding pressure parameters that have a significant impact on the output rate and scrap rate are identified, and the energy efficiency influencing factor identification results are generated.

[0084] See also Figure 4 , Based on the results of energy efficiency influencing factors identification, the multivariate linear regression method is used to evaluate the impact of differentiated parameter settings on energy efficiency, and corresponding optimization measures are implemented, including adjusting the heating temperature, optimizing the pressure setting, and optimizing the energy efficiency of key links. The specific steps for obtaining the matching optimization measures are as follows:

[0085] S301: According to the identification result of the energy efficiency influencing factors, the energy consumption data of the heating link is subdivided, the relationship between the heating time and the temperature setting and the energy consumption is identified, and the energy consumption value of each temperature point is recorded. The specific process of obtaining the energy consumption analysis result of the heating link is as follows;

[0086] In sub-step S301, based on the results of identifying factors affecting energy efficiency, a time series analysis method is used to perform time series modeling on the energy consumption data of the heating link through the Statsmodels library in Python. The heating time and temperature setting are used as independent variables, and the energy consumption is used as the dependent variable. A linear regression analysis is performed, and the model parameters are optimized through the least squares method. The mathematical relationship between the heating time and temperature setting and the energy consumption is identified, the energy consumption value of each temperature point is recorded, and the energy consumption analysis results of the heating link are generated.

[0087] S302: Based on the energy consumption analysis results of the heating link, analyze the pressure data of the blow molding link, record the energy consumption changes and product quality data under the differentiated pressure settings, identify the impact of pressure fluctuations on energy consumption and product quality, and obtain the blow molding pressure analysis results. The specific process is as follows;

[0088] In sub-step S302, based on the energy consumption analysis results of the heating stage, the variance analysis method is used to perform variance analysis on the pressure data of the blow molding stage through the SciPy library in Python. The differentiated pressure settings are used as independent variables, and the energy consumption changes and product quality data are used as dependent variables. The statistical impact of pressure setting changes on energy consumption and product quality is identified, and the significance level of each factor is determined through the F test to obtain the blow molding pressure analysis results.

[0089] S303: Based on the blow molding pressure analysis results and the heating link energy consumption analysis results, a multivariate linear regression method is used to evaluate the impact of differentiated parameter settings on energy efficiency, and measures are formulated to adjust the heating temperature and stabilize the blow molding pressure. The specific process of obtaining the matching optimization measures is as follows;

[0090] In sub-step S303, based on the analysis results of blowing pressure and energy consumption in heating stage, a multivariate linear regression model is constructed by using the Scikit-learn library in Python. The heating temperature and blowing pressure are used as independent variables, and energy efficiency is used as the dependent variable. Model training and cross-validation are performed, and the model is optimized by adjusting the regression coefficient. The mathematical influence of differentiated parameter settings on energy efficiency is evaluated, and specific numerical measures for adjusting the heating temperature and stabilizing the blowing pressure are formulated to generate a matching optimization measure plan.

[0091] The multiple linear regression method is based on the formula:

[0092]

[0093] Calculate the energy efficiency value and evaluate the impact of differentiated parameter settings on energy efficiency, where: For energy efficiency, is the heating temperature, is the blowing pressure, is the cooling rate, is the intercept term, , and is the influence coefficient, is the error term.

[0094] The specific implementation process of the improved formula is as follows:

[0095] Import the multivariate linear regression model through Python's Scikit-learn library, and then set the heating temperature , Blowing pressure and cooling rate As an independent variable, energy efficiency The model will learn and optimize the coefficients by fitting the historical data set. , , and , so that the energy efficiency value predicted by the model is as close as possible to the actual observed value. And the cooling rate is introduced After the model training is completed, the cross-validation method is used to evaluate the generalization ability of the model to ensure that the energy efficiency can be accurately predicted on new data. , and The value of can be used to evaluate the specific impact of heating temperature, blow molding pressure and cooling speed on energy efficiency, and accordingly formulate specific parameter adjustment measures to optimize the energy efficiency performance of the production line.

[0096] See also Figure 5 ,Based on the matching optimization measures, the operation priorities of multiple production links are refined, the energy utilization rate is optimized, and the specific steps of the operation priority adjustment strategy are as follows:

[0097] S401: Based on the matching optimization measure plan, sort out the production flow chart, mark the operation priorities of various current production links, record energy consumption data and production efficiency data, and obtain the production link energy efficiency and priority record table. The specific process is as follows;

[0098] In sub-step S401, based on the matching optimization measures plan, a flowchart drawing method is adopted to draw a production flow chart through Microsoft Visio software, and various production links such as heating, blow molding, cooling, etc. are displayed in a graphical way. The annotation function is used to indicate the operation priority of each link. At the same time, Excel software is used to record the energy consumption data and production efficiency data of each link. The data summary function is used to integrate the information to generate a production link energy efficiency and priority record table.

[0099] S402: According to the production link energy efficiency and priority record table, by simulating the effects of differentiated operation priority adjustment plans, the balance point between energy utilization and production efficiency is captured, and the specific process of generating priority adjustment simulation optimization results is as follows;

[0100] In sub-step S402, according to the energy efficiency and priority record table of the production links, the particle swarm optimization algorithm is adopted and implemented through Python programming. The initial position and speed of the particle swarm are set, and the operation priority is used as the position of the particle. The balance point between energy utilization and production efficiency is used as the optimization goal. The particle position and speed are iteratively updated to find the optimal solution. In the process, a dynamically adjusted weight update strategy is used to improve the search efficiency and generate priority adjustment simulation optimization results.

[0101] S403: Based on the priority adjustment simulation optimization result, refine the operation priority adjustment plan, plan the optimization steps and operation guidance of multiple links, and obtain the specific process of the operation priority adjustment strategy as follows;

[0102] In sub-step S403, based on the priority adjustment simulation optimization results, a detailed strategy formulation method is adopted, and the optimization steps and specific operation instructions for multiple links such as heating, blow molding, and cooling are planned through Microsoft Project software, including setting new operation priorities, adjusting production line rhythm and resource allocation, and using the Gantt chart function to display the optimized time plan and resource allocation of each link, and generate an operation priority adjustment strategy.

[0103] See also Figure 6 Based on the operation priority adjustment strategy, combined with the real-time monitoring data of the production line, the deep deterministic policy gradient model is used to adjust the production parameters to optimize the balance between energy efficiency, cost and production quality. The specific steps of the production parameter adjustment plan are as follows:

[0104] S501: Based on the operation priority adjustment strategy, combined with the real-time monitoring data of the production line, the deep deterministic policy gradient model is used to adjust the heating temperature, blowing pressure and cooling speed parameters to optimize the energy efficiency, cost and product quality balance in the production process. The specific process of obtaining the parameter optimization solution is as follows;

[0105] In sub-step S501, based on the operation priority adjustment strategy and real-time monitoring data of the production line, a deep deterministic policy gradient method is adopted to build a deep learning model through Python and TensorFlow library. By inputting the heating temperature, blowing pressure and cooling speed parameters, a neural network is used to learn how to adjust the parameters to optimize the balance between energy efficiency, cost and product quality. The model training adopts back propagation and gradient descent algorithms to find the optimal strategy through iterative training and generate a parameter optimization plan.

[0106] Deep deterministic policy gradient model, according to the formula:

[0107]

[0108] Calculate the improved action value function, where is the improved action value function, is the action value function, which is used to evaluate the expected utility of taking a specific action in a given state, The current status represents the current operating conditions of the production line, including machine status, raw material status, etc. The current action represents the specific operation of the production line, such as adjusting the heating temperature, blowing pressure and cooling speed. is the parameter of the current action value function, which determines the shape and evaluation criteria of the action value function. It is an immediate reward, which means the reward value obtained immediately after taking an action. It is used to evaluate the immediate effect of the action. is a discount factor used to adjust the current value of future rewards to reflect the importance of future rewards to current decisions. is the next state, which represents the new state of the production line after the action is taken. The action to be taken in the next state represents the operation to be taken in the new state. is the parameter of the next action value function, which is used to evaluate the value of different actions in the next state. Adjustment coefficient for environmental factors, according to the heating temperature , Blowing pressure and cooling rate to adjust value to refine the control of production process optimization, The heating temperature parameter directly affects the molding quality and energy consumption of the product. It is the blow molding pressure parameter, which has a key influence on the molding speed and quality of the product. It is a cooling speed parameter, which affects the cooling cycle and quality stability of the product. The weight of the environmental factor adjustment coefficient is used to adjust Contribution to the update of the action value function.

[0109] The specific implementation process of the improved formula is as follows:

[0110] By initializing the model parameters , the parameters define the action value function The current status of the production line is collected through real-time monitoring data , including heating temperature , Blowing pressure and cooling rate And other key parameters, according to the current state , and model parameters , using deep learning models to predict the best current action Through the forward propagation process of the neural network, the environmental factor adjustment coefficient is added , specifically, is a product based on current production parameters , , The function adjusts the action value function by the influence of the weighted parameters The output of the production process takes into account the comprehensive impact of production parameters on energy efficiency, cost and product quality balance. It is determined in advance through data analysis and measures the impact of each parameter on the production optimization goal. Take action , and observe the new state And the instant rewards . Simulate the results of adjusting parameters on the actual production line, such as the change in energy consumption and product quality caused by adjusting the heating temperature or blowing pressure, and then use the improved formula to calculate the improved action value function. Through the back propagation and gradient descent algorithms of the neural network, adjust the , so that The value more accurately reflects the expected utility after taking a specific action. Through multiple iterations of training, the model learns how to adjust parameters such as heating temperature, blowing pressure and cooling speed to find the best balance between improving energy efficiency, reducing costs and ensuring product quality. The improved formula introduces , which enables the model to consider the actual impact of production parameters more carefully when making decisions, thereby improving the accuracy and practicality of the optimization strategy.

[0111] S502: Based on the parameter optimization scheme, the material flow and energy allocation strategy of the production line are adjusted to optimize the cost and production efficiency and reduce the environmental impact. The specific process of obtaining the cost-effectiveness optimization strategy is as follows;

[0112] In sub-step S502, based on the parameter optimization scheme, the system dynamic simulation method was adopted to simulate the material flow and energy distribution of the production line through AnyLogic software, adjust the material input rate and energy distribution strategy of each production link, use the flowchart function in the software to define the logic and conditions of each link, observe the changes in cost and production efficiency through simulation operation, and fine-tune the optimization strategy based on the simulation results to achieve the goal of reducing costs and environmental impact, thus generating a cost-effective optimization strategy.

[0113] S503: According to the cost-effectiveness optimization strategy, the production line operation is adjusted to match the market demand changes and raw material price fluctuations, and the flexibility and response speed of the production line are optimized. The specific process of obtaining the production parameter adjustment plan is as follows;

[0114] In sub-step S503, based on the cost-benefit optimization strategy, a flexibility analysis method is adopted, and a macro program is written through Excel software and VBA programming to simulate the impact of changes in market demand and fluctuations in raw material prices on the production line, and production parameters such as heating temperature, blow molding pressure and cooling speed are adjusted to adapt to the changes. The program automatically adjusts the production line parameters by reading external market data and raw material price information to improve the flexibility and response speed of the production line and generate a production parameter adjustment plan.

[0115] See also Figure 7 Based on the production parameter adjustment plan, the energy consumption adjustment and monitoring of production line equipment are implemented to cope with changes and challenges in the production process, optimize the operation status of the production line, and obtain the specific steps of the dynamic optimization results of the production line as follows:

[0116] S601: Based on the production parameter adjustment plan, implement the energy consumption adjustment of the production line equipment, monitor the energy consumption of the equipment in multiple links of the production line after the adjustment, record the energy consumption data before and after the equipment adjustment, and obtain the specific process of the equipment energy consumption comparison data as follows;

[0117] In sub-step S601, based on the production parameter adjustment plan, an energy consumption monitoring method is adopted. The energy consumption data of equipment in each link is collected in real time through energy consumption monitoring instruments installed on the production line equipment. The energy consumption values ​​before and after the equipment adjustment are automatically recorded using the data acquisition system. The data is sorted and compared using Excel software, energy consumption changes are identified, and equipment energy consumption comparison data is generated.

[0118] S602: Using the equipment energy consumption comparison data, identify equipment adjustment measures that reduce energy consumption and do not affect production efficiency, refine the adjustment strategy, optimize the production line operation status, and obtain the optimized production line status data. The specific process is as follows;

[0119] In sub-step S602, the energy consumption data is compared using equipment energy consumption comparison data and data analysis methods. The Python programming language is combined with the Pandas library and the Matplotlib library to perform statistical analysis and visualization on the energy consumption data. By drawing energy consumption change charts, equipment adjustment measures that reduce energy consumption without affecting production efficiency are identified, and the measures are strategically refined to optimize the production line operation status and obtain the optimized production line status data.

[0120] S603: According to the optimized production line status data, data analysis is performed to identify the reduction in production line equipment energy consumption, the reduction in production costs, and the enhancement in product quality stability. The specific process of obtaining the dynamic optimization result of the production line is as follows;

[0121] In sub-step S603, based on the optimized production line status data, a comprehensive evaluation method is adopted to perform statistical analysis through the Python programming language combined with the SciPy library to evaluate the specific circumstances of reduced energy consumption of production line equipment, reduced production costs, and enhanced product quality stability. By calculating the equipment operating efficiency and cost-effectiveness ratio, the comprehensive effects of the optimization measures are identified and the dynamic optimization results of the production line are generated.

[0122] See also Figure 8 Based on the dynamic optimization results of the production line, the energy efficiency of the production line and the quality of PET bottle products are tracked and evaluated, the effects of the optimization measures are analyzed, and the energy efficiency improvement, cost reduction, and product quality are identified. The specific steps to obtain the energy efficiency optimization evaluation results are as follows:

[0123] S701: Based on the dynamic optimization results of the production line, collect the energy consumption data of the optimized production line and the quality records of PET bottles, analyze the links of energy consumption reduction and product quality improvement points, and obtain the specific process of energy consumption and quality improvement analysis records as follows;

[0124] In sub-step S701, based on the dynamic optimization results of the production line, a data collection and analysis method is used to collect the optimized energy consumption data and PET bottle product quality records in real time through sensors installed on the production line. The Python programming language is combined with the Pandas library to summarize and preliminarily process the collected data, identify the production links with reduced energy consumption and product quality improvement points, and use data visualization tools such as Matplotlib to draw charts of energy consumption and product quality improvement, and generate energy consumption and quality improvement analysis records.

[0125] S702: Using the energy consumption and quality improvement analysis records, comparing the cost data before and after the optimization measures, evaluating the extent of cost reduction and the corresponding links, and obtaining the specific process of cost saving evaluation results are as follows;

[0126] In sub-step S702, energy consumption and quality improvement analysis records are used, and cost analysis methods are adopted. Through the advanced data analysis function of Excel software, the cost data before and after the optimization measures are compared, including raw material consumption costs, energy consumption costs, and labor costs. By calculating the cost differences and total cost savings of each link, the extent of cost reduction and the specific performance of the corresponding links are evaluated, and the cost savings evaluation results are generated.

[0127] S703: Based on the energy consumption and quality improvement analysis records and cost savings evaluation results, evaluate the effectiveness of optimization measures, identify comprehensive energy efficiency improvement, cost reduction and product quality improvement, and obtain the specific process of energy efficiency optimization evaluation results as follows;

[0128] In sub-step S703, based on the energy consumption and quality improvement analysis records and cost savings evaluation results, a comprehensive evaluation method is adopted to conduct multi-dimensional data analysis through the Python programming language combined with the SciPy library, including quantitative evaluation of energy efficiency improvement, cost reduction and product quality improvement. Statistical methods such as correlation analysis and regression analysis are used to determine the contribution rate of different optimization measures to production efficiency and cost savings, as well as the impact on product quality stability, to generate energy efficiency optimization evaluation results.

[0129] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A method for optimizing energy efficiency of a PET bottle production line, characterized in that: The following steps are involved: Based on the process parameters of the PET bottle production line, the energy consumption characteristics of the heating, blow molding and cooling links are analyzed, the key links with low energy efficiency are identified, and the energy efficiency analysis results of the key links are obtained; According to the energy efficiency analysis results of the key links, the correlation between energy consumption and production efficiency is identified, and the results of identifying factors affecting energy efficiency are obtained; Based on the identification results of the energy efficiency influencing factors, a multivariate linear regression method is used to evaluate the impact of differentiated parameter settings on energy efficiency, and corresponding optimization measures are implemented to obtain a matching optimization measure plan; According to the matching optimization measure plan, the operation priorities of multiple production links are refined, the energy utilization rate is optimized, and the operation priority adjustment strategy is obtained; Based on the operation priority adjustment strategy, combined with the real-time monitoring data of the production line, the deep deterministic policy gradient model is used to adjust the production parameters to obtain the production parameter adjustment plan; Using the production parameter adjustment scheme, implement production line equipment energy consumption adjustment and monitoring, respond to changes in the production process, and obtain dynamic optimization results of the production line; Based on the dynamic optimization results of the production line, the energy efficiency of the production line and the quality tracking of PET bottle products are evaluated to obtain energy efficiency optimization evaluation results.

2. The method for optimizing the energy efficiency of a PET bottle production line according to claim 1, characterized in that: The energy efficiency analysis results of the key links include overtime energy consumption in the heating link, pressure fluctuation in the blow molding link, and inconsistent cooling speed. The identification results of the energy efficiency influencing factors include energy consumption related to production speed, the impact of heating temperature on energy efficiency, and the impact of pressure setting on product quality. The matching optimization measures include heating temperature adjustment, blow molding pressure stability improvement, and cooling speed adjustment. The operation priority adjustment strategy specifically includes adjusting the heating parameters, optimizing the blow molding pressure, and adjusting the cooling speed priority. The production parameter adjustment plan includes adjusting the heating temperature range, blow molding pressure setting value, and cooling speed setting value. The dynamic optimization results of the production line include improved production line energy efficiency, reduced production costs, and enhanced product quality stability. The energy efficiency optimization evaluation results include the trend of energy efficiency improvement, the cumulative effect of cost savings, and the continuous improvement of product quality.

3. The method for optimizing the energy efficiency of a PET bottle production line according to claim 1, characterized in that: Based on the process parameters of the PET bottle production line, the energy consumption characteristics of the heating, blowing and cooling links are analyzed, and the key links with low energy efficiency are identified. The specific steps to obtain the energy efficiency analysis results of the key links are as follows: Based on the process parameters of the PET bottle production line, the energy consumption data of the heating, blow molding and cooling links are collected, including the energy consumption, operation time, temperature and pressure parameters of each link, and the data are integrated and processed to obtain the energy consumption data set; Analyze the heating time, blowing pressure and cooling speed parameters according to the energy consumption data set, identify the heating time exceeding the industry standard threshold and the blowing pressure fluctuation, and obtain a list of exceeding parameters; Based on the list of parameters exceeding the standard, the links with low energy efficiency are evaluated, and the parameters of heating time exceeding the threshold and unstable blowing pressure are identified as key energy-inefficient factors, so as to obtain the energy efficiency analysis results of the key links.

4. The method for optimizing the energy efficiency of a PET bottle production line according to claim 1, characterized in that: According to the energy efficiency analysis results of the key links, the specific steps to identify the correlation between energy consumption and production efficiency and obtain the results of energy efficiency influencing factors are as follows: Based on the energy efficiency analysis results of the key links, parameters related to energy consumption and production efficiency are collected, including actual energy consumption, output rate and scrap rate, to generate a data set of energy efficiency related parameters; Utilizing the energy efficiency related parameter data set, analyzing the influence of multiple links on energy consumption, identifying the correlation between production efficiency and energy consumption, identifying links with high energy consumption, low output rate and high scrap rate, and obtaining an energy efficiency correlation analysis table; Based on the energy efficiency correlation analysis table, the correlation between energy consumption and production efficiency is identified, the influence of heating temperature and blow molding pressure on output rate and scrap rate is marked, and the energy efficiency influencing factor identification result is obtained.

5. The method for optimizing the energy efficiency of a PET bottle production line according to claim 1, characterized in that: Based on the identification results of the energy efficiency influencing factors, the multivariate linear regression method is used to evaluate the impact of differentiated parameter settings on energy efficiency, and corresponding optimization measures are implemented. The specific steps for obtaining the matching optimization measures are as follows: According to the energy efficiency influencing factor identification results, the energy consumption data of the heating link is subdivided, the relationship between the heating time and the temperature setting and the energy consumption is identified, and the energy consumption value of each temperature point is recorded to obtain the energy consumption analysis results of the heating link; Based on the energy consumption analysis results of the heating link, the pressure data of the blow molding link is analyzed, the energy consumption changes and product quality data under the differentiated pressure settings are recorded, the influence of pressure fluctuations on energy consumption and product quality is identified, and the blow molding pressure analysis results are obtained; Based on the blow molding pressure analysis results and the heating link energy consumption analysis results, a multivariate linear regression method is used to evaluate the impact of differentiated parameter settings on energy efficiency, formulate measures to adjust the heating temperature and stabilize the blow molding pressure, and obtain a matching optimization measure plan; The multivariate linear regression method is according to the formula: ； Calculate the energy efficiency value and evaluate the impact of differentiated parameter settings on energy efficiency, where: For energy efficiency, is the heating temperature, is the blowing pressure, is the cooling rate, is the intercept term, , and is the influence coefficient, is the error term.

6. The method for optimizing the energy efficiency of a PET bottle production line according to claim 1, characterized in that: According to the matching optimization measure scheme, the operation priorities of multiple production links are refined, the energy utilization rate is optimized, and the specific steps of the operation priority adjustment strategy are as follows: Based on the matching optimization measures, the production flow chart is sorted out, the operation priorities of various current production links are marked, the energy consumption data and production efficiency data are recorded, and the energy efficiency and priority record table of the production links is obtained; According to the energy efficiency and priority record table of the production links, by simulating the effects of differentiated operation priority adjustment plans, the balance point between optimizing energy utilization and production efficiency is captured, and a priority adjustment simulation optimization result is generated; Based on the priority adjustment simulation optimization results, the operation priority adjustment plan is refined, the optimization steps and operation guidance of multiple links are planned, and the operation priority adjustment strategy is obtained.

7. The method for optimizing the energy efficiency of a PET bottle production line according to claim 1, characterized in that: Based on the operation priority adjustment strategy, combined with the real-time monitoring data of the production line, the deep deterministic policy gradient model is used to adjust the production parameters. The specific steps of the production parameter adjustment plan are as follows: Based on the operation priority adjustment strategy, combined with the real-time monitoring data of the production line, the deep deterministic policy gradient model is used to adjust the heating temperature, blowing pressure and cooling speed parameters, optimize the energy efficiency, cost and product quality balance in the production process, and obtain the parameter optimization plan; The deep deterministic policy gradient model is based on the formula: ； Calculate the improved action value function, where is the improved action value function, is the action value function, is the current state, For current actions, is the parameter of the current action value function, For instant rewards, is the discount factor, For the next state, The action to be taken in the next state, is the parameter of the next action value function, is the environmental factor adjustment coefficient, is the heating temperature parameter, is the blowing pressure parameter, is the cooling rate parameter, weights for adjusting coefficients for environmental factors; Based on the parameter optimization scheme, the material flow and energy allocation strategy of the production line is adjusted to optimize cost and production efficiency and reduce environmental impact, thereby obtaining a cost-effectiveness optimization strategy; According to the cost-effectiveness optimization strategy, the production line operation is adjusted to match the changes in market demand and the fluctuations in raw material prices, the flexibility and response speed of the production line are optimized, and a production parameter adjustment plan is obtained.

8. The method for optimizing the energy efficiency of a PET bottle production line according to claim 1, characterized in that: The specific steps for using the production parameter adjustment scheme to implement production line equipment energy consumption adjustment and monitoring to cope with changes in the production process and obtain dynamic optimization results of the production line are as follows: Based on the production parameter adjustment plan, implement energy consumption adjustment of production line equipment, monitor the energy consumption of equipment in multiple links of the production line after adjustment, record energy consumption data before and after equipment adjustment, and obtain equipment energy consumption comparison data; Using the equipment energy consumption comparison data, identify equipment adjustment measures that reduce energy consumption and do not affect production efficiency, refine the adjustment strategy, optimize the production line operation status, and obtain optimized production line status data; According to the optimized production line status data, data analysis is performed to identify the reduction in energy consumption of production line equipment, reduction in production costs, and enhancement in product quality stability, thereby obtaining dynamic optimization results of the production line.

9. The method for optimizing the energy efficiency of a PET bottle production line according to claim 1, characterized in that: The specific steps for using the production parameter adjustment scheme to implement production line equipment energy consumption adjustment and monitoring to cope with changes in the production process and obtain dynamic optimization results of the production line are as follows: Based on the dynamic optimization results of the production line, the energy consumption data of the optimized production line and the quality records of PET bottle products are collected, the energy consumption reduction links and product quality improvement points are analyzed, and the energy consumption and quality improvement analysis records are obtained; By using the energy consumption and quality improvement analysis records, the cost data before and after the optimization measures are compared, the extent of cost reduction and the corresponding links are evaluated, and the cost saving evaluation results are obtained; Based on the energy consumption and quality improvement analysis records and cost savings assessment results, the effectiveness of the optimization measures is evaluated, the comprehensive energy efficiency improvement, cost reduction and product quality improvement are identified, and the energy efficiency optimization evaluation results are obtained.

Images