A method for monitoring the production process of CNC machine tool castings

Abstract

The present invention relates to the technical field of production process monitoring, and specifically to a method for monitoring the production process of CNC machine tool castings, comprising the following steps: deploying various types of sensors based on the CNC machine tool casting production line, capturing key production parameters, and obtaining a production parameter set. The present invention, by constructing a nonlinear dynamic model of the CNC machine tool casting production process, adopting a polynomial regression method to analyze the complex relationship between production parameters and casting quality, can identify potential deviations and defects in the production process in real time, optimize casting quality by dynamically adjusting production parameters, adopt a multi-objective optimization algorithm to balance and optimize energy consumption and production efficiency, and verify the effectiveness of the optimization scheme through simulation evaluation, thereby significantly improving production efficiency and product quality, reducing waste, enhancing the transparency and controllability of the production process, and quickly responding to changes and demands in the production process, ensuring that castings meet higher quality standards.

Description

Technical Field

[0001] The invention relates to the technical field of production process monitoring, and in particular to a method for monitoring the production process of a CNC machine tool casting. Background Art

[0002] The field of production process monitoring technology focuses on implementing systems and methods to monitor, control, and optimize various processes on the production line. This technology has a wide range of applications, covering all aspects of traditional manufacturing to high-tech industries, aiming to maximize production efficiency while maintaining or improving product quality. In a manufacturing environment, production process monitoring uses real-time data collection and analysis to carefully control and adjust the production process, reduce waste, improve production transparency, and quickly respond to problems that arise in the production process.

[0003] Among them, the CNC machine tool casting production process monitoring method focuses on real-time tracking of key parameters of CNC machine tools in the casting production process through monitoring technology and systems. Its purpose is to optimize the quality of castings, reduce scrap rates, and improve production efficiency by accurately controlling variables in the production process, such as temperature, pressure, and speed. It is committed to achieving high-precision and high-repeatability production output to ensure that castings meet strict quality standards.

[0004] Traditional CNC machine tool casting production process monitoring methods have limited capabilities in dealing with nonlinear complex relationships and real-time response changes in the production process. Traditional methods rely on static control strategies and later quality inspections, and it is difficult to capture key parameters that change instantaneously during the production process, resulting in the inability to adjust production conditions in real time to prevent defects. For example, failure to adjust temperature or pressure in a timely manner will cause cracks or other defects in castings, increase scrap rates, reduce production efficiency, and also show obvious deficiencies in energy consumption management and optimization. This static monitoring method lacks flexibility and predictability, limiting the optimization potential of the production line and the improvement of product quality. 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 monitoring the production process of a CNC machine tool casting.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a method for monitoring the production process of CNC machine tool castings, comprising the following steps:

[0007] S1: Based on the CNC machine tool casting production line, deploy various types of sensors to capture key production parameters and obtain the production parameter set;

[0008] S2: constructing a nonlinear dynamic model of the CNC machine tool casting production process according to the production parameter set, using a polynomial regression method to analyze the relationship between key production parameters and casting quality, and obtaining a parameter relationship identification result;

[0009] S3: According to the parameter relationship identification result, potential deviations and defects in the production process are identified, production parameters are dynamically adjusted, and an adjustment decision plan is obtained;

[0010] S4: Based on the adjustment decision plan, automatically adjust the production parameters of the CNC machine tool casting production line, optimize the casting quality, and obtain the quality control result;

[0011] S5: Based on the production parameter set and the quality control result, a multi-objective optimization algorithm is used to perform multi-objective optimization on the energy consumption and production efficiency in the production process, and a balance plan for optimizing energy consumption and production efficiency is formulated to obtain an optimized production plan set;

[0012] S6: Perform simulation evaluation based on the optimized production plan set, verify the effectiveness of the plans in the optimized production plan set, analyze and identify production plans that meet current production needs and resource utilization efficiency, and obtain a production implementation plan.

[0013] The present invention has improvements in that the production parameter set includes temperature values, pressure readings, and vibration frequencies; the parameter relationship identification results include the impact of temperature adjustment on casting quality, the impact of pressure changes on yield, and the impact of vibration levels on product precision; the adjustment decision plan includes adjusting the heating program, optimizing pressure application, and adjusting anti-vibration measures; the quality control results include the reduction ratio of casting defect rate, quality consistency improvement indicators, and production efficiency improvement data; the optimized production plan set includes energy consumption optimization strategy, production efficiency optimization strategy, and cost-benefit analysis results; the production implementation plan includes target casting temperature setting, optimized injection speed, and adjusted pressure control parameters.

[0014] The present invention is improved in that, according to the production parameter set, a nonlinear dynamic model of the CNC machine tool casting production process is constructed, and a polynomial regression method is used to analyze the relationship between key production parameters and casting quality. The specific steps of obtaining the parameter relationship identification result are as follows:

[0015] S201: Based on the production parameter set, analyzing the influence of temperature, pressure and vibration parameters individually and mutually on the casting quality, and generating single parameter analysis results;

[0016] S202: Based on the single parameter analysis results, a sensitivity analysis is performed to identify key production parameters that affect casting quality, and obtain key parameter identification results;

[0017] S203: Based on the key parameter identification results, a nonlinear relationship model between the parameters and the casting quality is constructed, and a polynomial regression method is used to analyze the impact of key parameter changes on the casting quality, and a parameter relationship identification result is generated.

[0018] The present invention is improved in that the polynomial regression method is according to the formula:

[0019] ;

[0020] Calculate the casting quality and generate parameter relationship identification results, where: is the predicted value of casting quality, is the temperature value, is the pressure value, is the vibration value, is the temperature change rate, is the pressure stability index, is the vibration frequency distribution skewness, to is the regression coefficient.

[0021] The present invention is improved in that, according to the parameter relationship identification result, potential deviations and defects in the production process are identified, and the production parameters are dynamically adjusted. The specific steps of obtaining the adjustment decision plan are as follows:

[0022] S301: Based on the parameter relationship identification result, analyzing the data in the production process, including temperature, pressure, and speed data, comparing the data with the preset quality standards, identifying the production parameters that deviate from the standards, and obtaining the deviation identification record;

[0023] S302: Based on the deviation identification record, analyzing multiple deviation data, identifying the impact of the deviation data on the quality of CNC machine tool casting products, identifying key deviation items that need to be adjusted, and prioritizing the deviation items to obtain a priority adjustment list;

[0024] S303: Based on the priority adjustment list and according to the identified key deviation items, matching adjustment measures are formulated, including increasing the temperature of the production line and adjusting the pressure during the production process, to obtain an adjustment decision plan.

[0025] The present invention is improved in that, based on the production parameter set and the quality control result, a multi-objective optimization algorithm is used to perform multi-objective optimization on the energy consumption and production efficiency in the production process, and a balance plan for optimizing energy consumption and production efficiency is formulated. The specific steps for obtaining the optimized production plan set are as follows:

[0026] S501: Based on the production parameter set and the quality control results, data is sorted, key production parameters and corresponding quality control results are screened, the initial point and target of optimization are identified, and optimization target definition information is obtained;

[0027] S502: Based on the optimization target definition information, evaluate the current energy consumption and production efficiency levels, set the priorities and weights of energy consumption and production efficiency by analyzing historical data and production needs, reflect actual production needs and improvement points, and formulate a weight setting plan;

[0028] S503: Based on the weight setting scheme, a multi-objective optimization algorithm is used to adjust production parameters, including heating temperature, pressure setting and cooling speed, and a parameter adjustment scheme that can achieve the predetermined optimization target is screened to obtain an optimized production scheme set.

[0029] The present invention is improved in that the multi-objective optimization algorithm is according to the formula:

[0030] ;

[0031] Calculate the weighted energy consumption, production efficiency and stability index values, where: is the temperature value, is the pressure value, is the vibration value, is the temperature change rate, is the pressure stability index, is the vibration frequency distribution skewness, , and are the weight coefficients of energy consumption, production efficiency and stability, is the weighted objective function.

[0032] The present invention is improved in that, according to the optimized production plan set, simulation evaluation is performed, the effect of the plan in the optimized production plan set is verified, and the production plan that meets the current production demand and resource utilization efficiency is analyzed and identified, and the specific steps of obtaining the production implementation plan are as follows:

[0033] S601: Based on the optimized production plan set, a plurality of optimized production plans are simulated through simulation, and the energy consumption and efficiency data during the simulation process are recorded to obtain a plan simulation evaluation record;

[0034] S602: Based on the simulation evaluation record of the scheme, analyze the performance indicators of the optimized production scheme, including the energy consumption reduction ratio, the production efficiency improvement range and the cost-effectiveness ratio, identify the scheme that matches the production demand and resource efficiency, and sort the schemes to obtain a performance optimization scheme set;

[0035] S603: Based on the performance optimization solution set, select a solution corresponding to the current production line requirements, formulate implementation measures, match energy efficiency and production efficiency requirements, and generate a production implementation plan.

[0036] Compared with the prior art, the advantages and positive effects of the present invention are:

[0037] In the present invention, by constructing a nonlinear dynamic model of the CNC machine tool casting production process, a polynomial regression method is used to analyze the complex relationship between production parameters and casting quality, so that potential deviations and defects in the production process can be identified in real time, and the casting quality can be optimized by dynamically adjusting the production parameters. A multi-objective optimization algorithm is used to balance and optimize energy consumption and production efficiency. The effectiveness of the optimization scheme is verified through simulation evaluation, which significantly improves production efficiency and product quality, reduces waste, enhances the transparency and controllability of the production process, and quickly responds to changes and demands in the production process, ensuring that the castings meet higher quality standards, while reducing energy consumption and improving the overall operating efficiency of the production line. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 A flow chart of a method for monitoring the production process of castings of a CNC machine tool is proposed for the present invention;

[0039] Figure 2 The present invention proposes a detailed flow chart of step S1 in a method for monitoring the production process of CNC machine tool castings;

[0040] Figure 3 The present invention proposes a detailed flow chart of step S2 in a method for monitoring a production process of a CNC machine tool casting;

[0041] Figure 4 The present invention proposes a detailed flow chart of step S3 in a method for monitoring a production process of a CNC machine tool casting;

[0042] Figure 5 The present invention proposes a detailed flow chart of step S4 in a method for monitoring a production process of a CNC machine tool casting;

[0043] Figure 6 The present invention proposes a detailed flow chart of step S5 in a method for monitoring a production process of a CNC machine tool casting;

[0044] Figure 7 The present invention proposes a detailed flow chart of step S6 in a method for monitoring a production process of a CNC machine tool casting. DETAILED DESCRIPTION

[0045] 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.

[0046] 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" and the like indicate positions or positional relationships 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 "plurality" is two or more, unless otherwise clearly and specifically defined.

[0047] Example

[0048] See also Figure 1 The present invention provides a technical solution: a method for monitoring the production process of CNC machine tool castings, comprising the following steps:

[0049] S1: Based on the CNC machine tool casting production line, various types of sensors are deployed, including temperature sensors, pressure sensors, and vibration sensors, to capture key production parameters, including temperature, pressure, and vibration parameters, and obtain the production parameter set;

[0050] S2: Based on the production parameter set, a nonlinear dynamic model of the CNC machine tool casting production process is constructed, and the relationship between key production parameters and casting quality is analyzed using the polynomial regression method to obtain parameter relationship identification results;

[0051] S3: Based on the parameter relationship identification results, analyze the data in the production process, identify potential deviations and defects in the production process, predict future production deviations, dynamically adjust production parameters, and obtain adjustment decision plans;

[0052] S4: Based on the adjustment decision plan, the production parameters of the CNC machine tool casting production line, including temperature, pressure, and speed, are automatically adjusted to compensate for the predicted production deviation, optimize the casting quality, and obtain the quality control results;

[0053] S5: Based on the production parameter set and quality control results, a multi-objective optimization algorithm is used to perform multi-objective optimization on the energy consumption and production efficiency in the production process, and a balance plan for optimizing energy consumption and production efficiency is formulated to obtain an optimized production plan set;

[0054] S6: Conduct simulation evaluation based on the optimized production plan set, verify the effectiveness of the plans in the optimized production plan set, analyze and identify the production plans that meet the current production needs and resource utilization efficiency, and obtain the production implementation plan.

[0055] The production parameter set includes temperature values, pressure readings, and vibration frequencies. The parameter relationship identification results include the impact of temperature adjustment on casting quality, the impact of pressure changes on yield, and the impact of vibration levels on product accuracy. The adjustment decision plan includes adjusting the heating program, optimizing pressure application, and adjusting anti-vibration measures. The quality control results include the reduction ratio of casting defect rate, quality consistency improvement indicators, and production efficiency improvement data. The optimized production plan set includes energy consumption optimization strategy, production efficiency optimization strategy, and cost-benefit analysis results. The production implementation plan includes target casting temperature setting, optimized injection speed, and adjusted pressure control parameters.

[0056] See also Figure 2 ,Based on the CNC machine tool casting production line, various types of sensors, including temperature sensors, pressure sensors and vibration sensors, are deployed to capture key production parameters, including temperature, pressure and vibration parameters.,The specific steps to obtain the production parameter set are as follows:

[0057] S101: Based on the CNC machine tool casting production line, temperature sensors, pressure sensors and vibration sensors are deployed to capture the temperature, pressure and vibration data of the CNC machine tool casting production process in real time. The specific process of obtaining the basic data set is as follows;

[0058] In sub-step S101, based on the CNC machine tool casting production line, temperature sensors, pressure sensors and vibration sensors are configured, and the sensor outputs are collected using a data acquisition system, including regularly reading data values ​​from the sensors to ensure that the data frequency and accuracy of each sensor are set correctly to reflect real-time production environment changes and generate a basic data set.

[0059] S102: Based on the basic data set, data cleaning and preprocessing operations are performed to remove outliers and noise, and to normalize the data format and range. The specific process of obtaining the preprocessed data set is as follows;

[0060] In sub-step S102, based on the basic data set, data preprocessing technology is applied to perform data cleaning operations, including using the dropna function in the pandas library to remove missing values, using the isolationforest algorithm to identify and remove outliers, and using the MinMaxScaler function to normalize the data, uniformly adjusting the data range to between 0 and 1, and generating a preprocessed data set.

[0061] S103: Based on the preprocessed data set, data clustering is performed to divide the data into three dimensions: temperature, pressure, and vibration. The specific process of obtaining the production parameter set is as follows;

[0062] In sub-step S103, based on the preprocessed data set, a data clustering operation is performed, and the K-means clustering algorithm is applied. The number of clusters is set to 3, corresponding to the temperature, pressure, and vibration data dimensions respectively. The Euclidean distance from each point to the cluster center is calculated, and the data points are assigned to the nearest cluster center. The fit_predict method is used to complete the clustering process and generate a production parameter set.

[0063] See also Figure 3 ,According to the production parameter set, a nonlinear dynamic model of the CNC machine tool casting production process is constructed, and the polynomial regression method is used to analyze the relationship between key production parameters and casting quality. The specific steps to obtain the parameter relationship identification results are as follows:

[0064] S201: Based on the production parameter set, analyze the influence of temperature, pressure and vibration parameters individually and mutually on the casting quality, and generate the specific process of single parameter analysis results as follows;

[0065] In sub-step S201, univariate and multivariate regression analysis is performed based on the production parameter set. By defining temperature, pressure, and vibration parameters as independent variables and casting quality indicators as dependent variables, linear regression analysis is used to analyze the effects of individual parameters, and multivariate regression analysis is used to analyze the interaction effects. The statsmodels library is used to implement this, and the significance level is set to 0.05. Statistically significant influencing factors are screened out to generate single parameter analysis results.

[0066] S202: Based on the single parameter analysis results, sensitivity analysis is used to identify the key production parameters that affect the casting quality. The specific process of obtaining the key parameter identification results is as follows;

[0067] In sub-step S202, based on the results of single parameter analysis, variance analysis is applied to determine the contribution of different production parameters to the variation in casting quality. The f_oneway function in Python's scipy library is used to perform the analysis. The sensitivity of the parameters is determined by comparing the F value and the p value, the parameters that have the most significant impact on the casting quality are identified, and the key parameter identification results are generated.

[0068] S203: Based on the key parameter identification results, a nonlinear relationship model between the parameters and the casting quality is constructed, and the influence of the key parameter changes on the casting quality is analyzed by using a polynomial regression method. The specific process of generating the parameter relationship identification results is as follows;

[0069] In sub-step S203, based on the key parameter identification results, a nonlinear relationship model is constructed, and the polynomial regression method is used to capture the nonlinear relationship between temperature, pressure, vibration and casting quality. The model is constructed using the numpy and sklearn libraries, and the polynomial degree is selected based on the trade-off between model fit and complexity. Model training and verification are performed to generate parameter relationship identification results.

[0070] Polynomial regression method, according to the formula:

[0071] ;

[0072] Calculate the casting quality and generate parameter relationship identification results, where: is the predicted value of casting quality, is the temperature value, which indicates the actual measured temperature during the production process. is the pressure value, which indicates the actual measured pressure during the production process. is the vibration value, which indicates the actual measured vibration level during the production process. is the temperature change rate, which indicates the maximum temperature change per unit time. is the pressure stability index, which indicates the standard deviation of pressure variation, is the skewness of the vibration frequency distribution, reflecting the asymmetry of the vibration frequency distribution. to is the regression coefficient, which indicates the weight of each parameter in the prediction model.

[0073] The specific implementation process of the improved formula is as follows:

[0074] Temperature change rate using numpy library , Pressure Stability Index , vibration frequency distribution skewness Calculate. For example, calculate When , the time series data is processed using numpy's difference function np.diff() to obtain the temperature changes between consecutive measurement points, and then the maximum value of these changes is taken as . Pressure Stability Index The standard deviation of the pressure data is obtained by calculating np.std(), which reflects the stability of pressure changes. The skewness of the vibration data distribution is calculated by the scipy.stats.skew() function, and the temperature, pressure, vibration parameters and temperature change rate are calculated by sklearn's PolynomialFeatures. , Pressure Stability Index , vibration frequency distribution skewness Combined with the above, feature expansion is performed, including high-order terms and interaction terms of parameters, regression analysis of parameters is performed through the LinearRegression model, cross-validation is used to optimize model parameters, and the optimal value of each regression coefficient is determined to improve the accuracy of the prediction and ensure that the model has the best fit and prediction accuracy.

[0075] See also Figure 4, according to the parameter relationship identification results, analyze the data in the production process, identify potential deviations and defects in the production process, and predict future production deviations, dynamically adjust production parameters, and obtain the specific steps of the adjustment decision plan as follows:

[0076] S301: Based on the parameter relationship identification results, the data in the production process are analyzed, including temperature, pressure, and speed data, and the data are compared with the preset quality standards to identify the production parameters that deviate from the standards. The specific process of obtaining the deviation identification record is as follows;

[0077] In sub-step S301, based on the parameter relationship identification results, a data comparison operation is performed, numerical calculations are performed using Python's NumPy library, the logical_and() function is used to compare the temperature, pressure, and speed data with the preset quality standards, and the where() function is used to mark data points that deviate from the standards. The comparison and marking are automatically completed to generate deviation identification records.

[0078] S302: Based on the deviation identification record, multiple deviation data are analyzed to identify the impact of the deviation data on the quality of CNC machine tool casting products, identify key deviation items that need to be adjusted, and prioritize the deviation items to obtain the priority adjustment list. The specific process is as follows;

[0079] In sub-step S302, based on the deviation identification records, deviation data analysis operations are performed, Python's Pandas library is used to sort and group data, the groupby() function is used to group the deviation data by type, and the sort_values() function is used to sort the grouped data according to the deviation size. The priority of the deviation data is automatically identified and arranged, and a priority adjustment list is generated.

[0080] S303: Based on the priority adjustment list and the identified key deviation items, matching adjustment measures are formulated, including increasing the temperature of the production line and adjusting the pressure during the production process. The specific process of obtaining the adjustment decision plan is as follows;

[0081] In sub-step S303, based on the priority adjustment list, adjustment measures are formulated. Simple conditional judgment logic is used to write conditional statements to determine the parameter values ​​that need to be increased or decreased for the identified key deviation items, such as excessive temperature or insufficient pressure. The adjustment range is set for each deviation type, such as increasing the temperature by 5°C for low temperatures and reducing the pressure by 10% for high pressure. The corresponding adjustment measures are applied directly according to the deviation type and priority to generate an adjustment decision plan.

[0082] See also Figure 5, based on the adjustment decision plan, the production parameters of the CNC machine tool casting production line, including temperature, pressure, and speed, are automatically adjusted to compensate for the predicted production deviation and optimize the casting quality. The specific steps to obtain the quality control results are as follows:

[0083] S401: Based on the adjustment decision plan, operate the equipment on the CNC machine tool casting production line, input the adjusted parameter values, and make real-time adjustments to the production line, including adjusting the temperature, pressure, and speed parameters. The specific process of obtaining the adjustment execution record is as follows;

[0084] In sub-step S401, based on the adjustment decision plan, the equipment on the CNC machine tool casting production line is automatically operated. By writing a Python script, the API interface of the machine tool is called to pass the adjusted temperature, pressure, and speed parameter values. The script uses the PySerial library to communicate with the machine tool, sending G-code and M-code for parameter adjustment to ensure real-time automatic adjustment of the production line and generate adjustment execution records.

[0085] S402: Based on the adjustment execution record, the casting production effect after the adjustment parameters are tracked, the difference in casting quality before and after the adjustment is compared, the effectiveness of the adjustment measures is analyzed, and the specific process of obtaining the effect matching analysis result is as follows;

[0086] In sub-step S402, based on the adjustment execution record, the quality data of the casting after production is automatically collected, the surface quality of the casting is analyzed by image processing technology, the casting image is collected and preliminarily processed using the OpenCV library, and then the image recognition algorithm is applied, such as the convolutional neural network based on TensorFlow, to automatically identify and classify the surface defects of the casting, compare the quality differences before and after the adjustment, and generate the effect matching analysis results.

[0087] S403: Based on the results of the effect matching analysis, the production process is audited, the adjustment measures are optimized, and the production efficiency requirements are matched. The specific process of obtaining the quality control results is as follows;

[0088] In sub-step S403, based on the results of the effect matching analysis, the decision support system is used to evaluate and optimize the quality control measures of the production process. The Python-based Pandas library is used for data processing and analysis. The decision tree algorithm in the Scikit-learn library is combined to model the relationship between production parameters and quality results. The production parameters are adjusted according to the model feedback to more finely match the production efficiency and casting quality requirements and generate quality control results.

[0089] See also Figure 6, based on the production parameter set and quality control results, a multi-objective optimization algorithm is used to perform multi-objective optimization on the energy consumption and production efficiency in the production process, and a balance plan for optimizing energy consumption and production efficiency is formulated. The specific steps for obtaining the optimized production plan set are as follows:

[0090] S501: Based on the production parameter set and quality control results, data is sorted, key production parameters and corresponding quality control results are screened, the initial point and target of optimization are identified, and the specific process of obtaining the optimization target definition information is as follows;

[0091] In sub-step S501, based on the production parameter set and quality control results, a Python script is used to perform data screening and organization. The numerical data is screened through the DataFrame.select_dtypes() method of the Pandas library, and the .dropna() method is used to remove missing values. Then, the .query() method is used to screen out records whose deviation from the quality control standard exceeds a predetermined threshold. These records are used as the starting point and target for optimization, and the optimization target definition information is generated.

[0092] S502: Based on the optimization target definition information, evaluate the current energy consumption and production efficiency levels, set the priorities and weights of energy consumption and production efficiency by analyzing historical data and production needs, reflect the actual production needs and improvement points, and formulate the specific process of the weight setting plan as follows;

[0093] In sub-step S502, based on the optimization target definition information, historical data analysis is adopted, and Pandas is used for data aggregation and descriptive statistical analysis. The average, minimum and maximum values ​​of energy consumption and production efficiency are calculated through the .groupby() and .agg() methods. Combined with actual production needs, the priority and weight of energy consumption and production efficiency are allocated through a weighted algorithm. NumPy is used for numerical calculations to generate a weight setting plan.

[0094] S503: Based on the weight setting scheme, a multi-objective optimization algorithm is used to adjust production parameters, including heating temperature, pressure setting and cooling speed, and a parameter adjustment scheme that can achieve the predetermined optimization target is screened to obtain the optimized production scheme set. The specific process is as follows;

[0095] In sub-step S503, based on the weight setting scheme, a multi-objective optimization algorithm is used to adjust parameters. The optimize.minimize() function in the SciPy library is used to set the objective function to the weighted energy consumption and production efficiency indicators. The constraints include the working range of temperature, pressure and cooling rate. The optimal solution is searched through iterative optimization, and the influence of production parameters on the optimization target is taken into account to ensure that the physical and technical limitations of actual production are followed during the search process to generate an optimized production plan set.

[0096] Multi-objective optimization algorithm, according to the formula:

[0097] ;

[0098] Calculate the weighted energy consumption, production efficiency and stability index values, where: is the temperature value, which indicates the actual measured temperature during the production process. is the pressure value, which indicates the actual measured pressure during the production process. is the vibration value, which indicates the actual measured vibration level during the production process. is the temperature change rate, which indicates the maximum temperature change per unit time. is the pressure stability index, which indicates the standard deviation of pressure change and reflects the stability of pressure. is the skewness of the vibration frequency distribution, reflecting the asymmetry of the vibration frequency distribution. , and are the weight coefficients of energy consumption, production efficiency and stability, It is a weighted objective function, which reflects the comprehensive consideration of energy consumption, production efficiency and stability.

[0099] The specific implementation process of the improved formula is as follows:

[0100] Temperature change rate The pressure stability index is calculated by taking the maximum value of the difference of the temperature time series data. The vibration frequency distribution skewness is obtained by calculating the standard deviation of the pressure time series. Calculate the distribution shape of vibration data and set weight coefficients through expert scoring and historical data analysis , and , to ensure that the model reflects the relative importance of different objectives in actual production. Through the optimize.minimize() function of the SciPy library, an iterative optimization search for the optimal solution is performed based on parameters and weights. This process follows the physical and technical limitations of actual production to ensure that the optimal combination of production parameters is found that can save energy, improve production efficiency, and ensure the stability of the production process.

[0101] See also Figure 7 , according to the optimized production plan set, simulation evaluation is carried out, the effect of the plan in the optimized production plan set is verified, and the production plan that meets the current production needs and resource utilization efficiency is analyzed and identified. The specific steps for obtaining the production implementation plan are as follows:

[0102] S601: Based on the optimized production plan set, the production process of multiple optimized production plans is simulated through simulation, and the energy consumption and efficiency data during the simulation process are recorded. The specific process of obtaining the plan simulation evaluation record is as follows;

[0103] In sub-step S601, the discrete event simulation method is adopted, and the SimPy library is used to build a production process simulation model. The production line environmental parameters such as heating temperature, pressure and cooling speed are defined. SimPy simulates various operations in the production process through event scheduling, records the energy consumption and production efficiency data in the simulation process, ensures the accuracy and reliability of the simulation results, and generates a simulation evaluation record for the solution.

[0104] S602: Based on the scheme simulation evaluation records, analyze and optimize the performance indicators of the production scheme, including the energy consumption reduction ratio, the production efficiency improvement range and the cost-effectiveness ratio, identify the scheme that matches the production demand and resource efficiency, and sort the schemes to obtain the specific process of the performance optimization scheme set as follows;

[0105] In sub-step S602, a data analysis method is adopted to process the data in the scheme simulation evaluation record using the Pandas library, and the energy consumption reduction ratio, production efficiency improvement and cost-effectiveness ratio of each optimized production scheme are calculated. The sort_values() function of Pandas sorts the schemes according to performance indicators, identifies the optimization scheme with the best performance, and generates a set of performance-optimized schemes.

[0106] S603: Based on the performance optimization solution set, a solution corresponding to the current production line requirements is selected, implementation measures are formulated, energy efficiency and production efficiency requirements are matched, and the specific process of generating a production implementation plan is as follows;

[0107] In sub-step S603, a decision analysis method is adopted, and JupyterNotebook and NumPy libraries are used for numerical calculations and logical judgments. Based on the performance optimization plan set, the most suitable plan for the current production line is selected, and implementation measures including parameter adjustment and operation steps are planned in detail to ensure that the selected plan can effectively match the energy efficiency and production efficiency requirements of the production line, and generate a production implementation plan.

[0108] 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 monitoring the production process of CNC machine tool castings, characterized in that: The following steps are involved: Based on the CNC machine tool casting production line, various types of sensors are deployed to capture key production parameters and obtain the production parameter set; According to the production parameter set, a nonlinear dynamic model of the CNC machine tool casting production process is constructed, and a polynomial regression method is used to analyze the relationship between key production parameters and casting quality to obtain parameter relationship identification results; According to the parameter relationship identification results, potential deviations and defects in the production process are identified, production parameters are dynamically adjusted, and an adjustment decision plan is obtained; Based on the adjustment decision plan, the production parameters of the CNC machine tool casting production line are automatically adjusted to optimize the casting quality and obtain quality control results; Based on the production parameter set and quality control results, a multi-objective optimization algorithm is used to perform multi-objective optimization on energy consumption and production efficiency in the production process, a balance plan for optimizing energy consumption and production efficiency is formulated, and an optimized production plan set is obtained; According to the optimized production plan set, simulation evaluation is carried out to verify the effect of the plans in the optimized production plan set, analyze and identify the production plans that meet the current production needs and resource utilization efficiency, and obtain the production implementation plan; According to the production parameter set, a nonlinear dynamic model of the CNC machine tool casting production process is constructed, and the relationship between key production parameters and casting quality is analyzed by using a polynomial regression method. The specific steps for obtaining the parameter relationship identification result are as follows: Based on the production parameter set, analyzing the influence of temperature, pressure and vibration parameters individually and mutually on casting quality, and generating single parameter analysis results; Based on the single parameter analysis results, sensitivity analysis is used to identify key production parameters that affect casting quality, and key parameter identification results are obtained; Based on the key parameter identification results, a nonlinear relationship model between the parameters and the casting quality is constructed, and a polynomial regression method is used to analyze the impact of key parameter changes on the casting quality, so as to generate parameter relationship identification results; The polynomial regression method is according to the formula: ； Calculate the casting quality and generate parameter relationship identification results, where: is the predicted value of casting quality, is the temperature value, is the pressure value, is the vibration value, is the temperature change rate, is the pressure stability index, is the vibration frequency distribution skewness, to is the regression coefficient.

2. The method for monitoring the production process of CNC machine tool castings according to claim 1, characterized in that: The production parameter set includes temperature values, pressure readings, and vibration frequencies. The parameter relationship identification results include the impact of temperature adjustment on casting quality, the impact of pressure changes on yield, and the impact of vibration levels on product precision. The adjustment decision plan includes adjusting the heating program, optimizing pressure application, and adjusting anti-vibration measures. The quality control results include the reduction ratio of casting defect rate, quality consistency improvement indicators, and production efficiency improvement data. The optimized production plan set includes energy consumption optimization strategy, production efficiency optimization strategy, and cost-benefit analysis results. The production implementation plan includes target casting temperature setting, optimized injection speed, and adjusted pressure control parameters.

3. The method for monitoring the production process of CNC machine tool castings according to claim 1, characterized in that: According to the parameter relationship identification results, the specific steps of identifying potential deviations and defects in the production process, dynamically adjusting the production parameters, and obtaining the adjustment decision plan are as follows: Based on the parameter relationship identification results, analyzing the data in the production process, including temperature, pressure, and speed data, comparing the data with the preset quality standards, identifying the production parameters that deviate from the standards, and obtaining deviation identification records; Based on the deviation identification record, multiple deviation data are analyzed to identify the impact of the deviation data on the quality of CNC machine tool casting products, identify key deviation items that need to be adjusted, and prioritize the deviation items to obtain a priority adjustment list; Based on the priority adjustment list and in accordance with the identified key deviation items, matching adjustment measures are formulated, including increasing the temperature of the production line and adjusting the pressure during the production process, to obtain an adjustment decision plan.

4. The method for monitoring the production process of CNC machine tool castings according to claim 1, characterized in that: Based on the production parameter set and quality control results, a multi-objective optimization algorithm is used to perform multi-objective optimization on energy consumption and production efficiency in the production process, and a balance plan for optimizing energy consumption and production efficiency is formulated. The specific steps for obtaining the optimized production plan set are as follows: Based on the production parameter set and quality control results, data is sorted, key production parameters and corresponding quality control results are screened, the initial point and target of optimization are identified, and optimization target definition information is obtained; Based on the optimization target definition information, evaluate the current energy consumption and production efficiency levels, set the priorities and weights of energy consumption and production efficiency by analyzing historical data and production needs, reflect actual production needs and improvement points, and formulate a weight setting plan; Based on the weight setting scheme, a multi-objective optimization algorithm is used to adjust production parameters, including heating temperature, pressure setting and cooling speed, and parameter adjustment schemes that can achieve predetermined optimization goals are screened to obtain an optimized production scheme set.

5. The method for monitoring the production process of CNC machine tool castings according to claim 1, characterized in that: The multi-objective optimization algorithm is based on the formula: ； Calculate the weighted energy consumption, production efficiency and stability index values, where: is the temperature value, is the pressure value, is the vibration value, is the temperature change rate, is the pressure stability index, is the vibration frequency distribution skewness, , and are the weight coefficients of energy consumption, production efficiency and stability, is the weighted objective function.

6. The method for monitoring the production process of CNC machine tool castings according to claim 1, characterized in that: According to the optimized production plan set, simulation evaluation is carried out, the effect of the plan in the optimized production plan set is verified, and the production plan that meets the current production demand and resource utilization efficiency is analyzed and identified. The specific steps of obtaining the production implementation plan are as follows: Based on the optimized production plan set, a plurality of optimized production plans are simulated through simulation, and the energy consumption and efficiency data during the simulation are recorded to obtain a plan simulation evaluation record; Based on the simulation evaluation records of the schemes, the performance indicators of the optimized production schemes are analyzed, including the energy consumption reduction ratio, the production efficiency improvement range and the cost-effectiveness ratio, the schemes that match the production demand and resource efficiency are identified, and the schemes are ranked to obtain a set of performance-optimized schemes; Based on the performance optimization solution set, a solution corresponding to the current production line requirements is selected, implementation measures are formulated, energy efficiency and production efficiency requirements are matched, and a production implementation plan is generated.

Images