Intelligent manufacturing equipment remote control system based on Internet

Abstract

The invention discloses an intelligent manufacturing equipment remote control system based on the Internet, and relates to the technical field of intelligent manufacturing, environment data and product data in the product manufacturing process are collected in real time, a manufacturing data set S is constructed, and according to the manufacturing data set S, an intelligent manufacturing equipment remote control system is established. The method comprises the following steps: acquiring a product surface roughness score Ra, an area change coefficient Dr and a thermal expansion coefficient Pz, analyzing extracted feature data, acquiring a comprehensive quality score Qf, performing product quality evaluation, adjusting and controlling intelligent manufacturing equipment according to a product quality evaluation result, collecting manufacturing data after the equipment is adjusted and controlled, and determining the product quality. According to the method, the product qualification rate HG of the same batch of products is obtained, the optimization effect of equipment adjustment control is evaluated in combination with the preset product qualification rate threshold HGYZ, and the stability of the product quality is analyzed when the optimization effect of equipment adjustment control is in a normal state, so that the production efficiency and the product qualification rate are improved, and the product quality is ensured.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of intelligent manufacturing, and particularly relates to an intelligent manufacturing equipment remote control system based on the Internet. BACKGROUND

[0002] As an important branch in the industrial field, intelligent manufacturing covers the integrated application of various advanced technologies such as automation, informatization, digitization and intelligence. With the development of science and technology, intelligent manufacturing gradually evolves towards higher efficiency, greater flexibility and greater accuracy, and has great potential in improving production line management, optimizing production processes and improving production quality. In the field of intelligent manufacturing, quality control is particularly critical, especially in large-scale production. How to ensure stable and consistent product quality is an important challenge faced by production enterprises. Specifically in intelligent manufacturing equipment, quality detection equipment, as an important tool to ensure production quality, undertakes tasks such as automated visual inspection and dimension measurement. Through a remote control system, manufacturing equipment can monitor and adjust various quality parameters in the production process in real time to ensure that each production link meets the predetermined quality standards.

[0003] In the Chinese invention patent with the application publication number CN117793288A, an intelligent device real-time field monitoring system for a cloud manufacturing scenario is disclosed, and an additive manufacturing system based on remote control and cloud processing is disclosed, which comprises: a video monitoring network unit for setting up a video monitoring network for N intelligent manufacturing devices; a video data monitoring unit for collecting video data of the N intelligent manufacturing devices through the video monitoring network; and an adjustment unit for adjusting the video monitoring network according to cloud fault video requirements. The application can greatly reduce the bandwidth occupation of the production line to the outside when collecting and analyzing the faults of batch intelligent manufacturing devices, thereby saving data bandwidth for the remote end of the production line based on CPS intelligent production line integration technology, such as the demand end of remotely controlling batch intelligent manufacturing devices to perform complex process operations.

[0004] The above system avoids the pressure on the video monitoring device based on the CPS intelligent production line integration technology and the management system of the video monitoring device caused by monitoring and uploading related videos of multiple intelligent manufacturing devices with faults, but in addition, in the existing intelligent manufacturing equipment remote control system, the manufacturing process of the intelligent device is usually monitored, the intelligent manufacturing equipment fault is analyzed, and the intelligent device is adjusted.

[0005] However, such a system is limited to intelligent device state monitoring and lacks production process control and quality optimization.

[0006] Therefore, the application provides an intelligent manufacturing equipment remote control system based on the Internet. SUMMARY

[0007] In response to the shortcomings of the existing technology, the present invention provides an Internet-based remote control system for intelligent manufacturing equipment. By collecting environmental data and product data in the product manufacturing process in real time, a manufacturing data set S is constructed. Based on the manufacturing data set S, the product surface roughness score Ra, area variation coefficient Dr and thermal expansion coefficient Pz are obtained, and the extracted feature data are analyzed to obtain a comprehensive quality score Qf, and product quality evaluation is performed. Based on the product quality evaluation results, the intelligent manufacturing equipment is adjusted and controlled, and the manufacturing data after the equipment adjustment and control is collected to obtain the product qualification rate HG of the same batch of products. Combined with the preset product qualification rate threshold HGYZ, the optimization effect of the equipment adjustment control is evaluated. When the optimization effect of the equipment adjustment control is in a normal state, the stability of the product quality is analyzed, thereby improving production efficiency and product qualification rate, ensuring product quality, and solving the problems in the above-mentioned background technology.

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions: an Internet-based intelligent manufacturing equipment remote control system, including a data acquisition module, a data preprocessing and feature extraction module, a quality detection and evaluation module, an adjustment control module, an equipment optimization effect evaluation module and a stability analysis module;

[0009] The data acquisition module is used to deploy infrared temperature sensors and high-definition cameras on intelligent manufacturing equipment to collect environmental data and product data during the product manufacturing process in real time and construct a manufacturing data set S;

[0010] The data preprocessing and feature extraction module is used to perform preprocessing based on the manufacturing data set S, and perform feature extraction based on the preprocessed manufacturing data set S to obtain the product surface roughness score Ra, area variation coefficient Dr, and thermal expansion coefficient Pz;

[0011] The quality inspection and assessment module is used to perform summary calculations based on the product surface roughness score Ra, area variation coefficient Dr, and thermal expansion coefficient Pz to obtain a comprehensive quality score Qf of the product, and to perform product quality assessment based on the comprehensive quality score Qf to generate a product quality assessment report;

[0012] The adjustment control module is used to adjust and control the intelligent manufacturing equipment according to the product quality assessment report when the quality of the product is in an unqualified state, generate an equipment control signal u(t) according to the PID control algorithm, and control the intelligent manufacturing equipment to perform adjustment operations according to the equipment control signal u(t);

[0013] The device optimization effect evaluation module is configured to calculate a product pass rate HG of the same batch of products according to the manufacturing data after the device adjustment control, preset a product pass rate threshold HGYZ, compare the product pass rate threshold HGYZ with the product pass rate HG, and evaluate the optimization effect of the device adjustment control.

[0014] The stability analysis module is configured to collect manufacturing data of a period of time after the device adjustment control when the optimization effect of the device adjustment control is in a normal state, draw a product quality control chart, and perform stability analysis according to the product quality control chart.

[0015] Preferably, the data collection module includes an environment data collection unit and a product data collection unit.

[0016] The environment data collection unit is configured to deploy an infrared temperature sensor on the intelligent manufacturing device to collect a temperature change amount ΔT of the product in the product manufacturing process in real time.

[0017] The product data collection unit is configured to deploy a high-definition camera on the intelligent manufacturing device to collect image data of the product in the product manufacturing process in real time, wherein the image data includes a height h of different regions of the product surface, an area size d of the product, and a length L of the product.

[0018] According to the collected environment data and product data, a manufacturing data set S is constructed, and the manufacturing data set S is transmitted to a device data center for storage through wireless transmission technology.

[0019] Preferably, the data preprocessing and feature extraction module includes a preprocessing unit and a feature extraction unit.

[0020] The preprocessing unit is configured to preprocess the manufacturing data set S, including environment data preprocessing and product data preprocessing.

[0021] The environment data preprocessing refers to data cleaning, denoising, and data standardization of the environment data in the manufacturing data set S.

[0022] The product data preprocessing refers to using Gaussian filtering to smooth the image, removing high-frequency noise in the image, using histogram equalization to uniformly distribute the gray value of the image, adjusting the contrast, and using Canny edge detection to extract the edge contour of the image.

[0023] Preferably, the feature extraction unit is configured to aggregate and calculate the manufacturing data set S after preprocessing to obtain a product surface roughness score Ra, an area change coefficient Dr, and a thermal expansion coefficient Pz.

[0024] The product surface roughness score Ra is obtained in the following manner:

[0025]

[0026] wherein L represents the length of the product, y(x) represents the height of the surface position x of the product to be measured, represents the average height of the surface of the product to be measured;

[0027] the height y(x) of the surface position x of the product to be measured and the average height of the surface of the product to be measured by using a surface scanning device, wherein the surface scanning device comprises a laser scanner and a stylus profilometer;

[0028] the area variation coefficient Dr is obtained in the following manner:

[0029]

[0030] wherein d i represents the measured area size of the i-th measuring point on the product, d ref，i represents the preset area size of the i-th measuring point on the product, i = [1, 2, 3, …, N], and N represents the number of measuring points;

[0031] the thermal expansion coefficient Pz is obtained in the following manner:

[0032]

[0033] wherein ΔL represents the length variation of the product during the heating process, L0 represents the initial length of the product, and ΔT represents the temperature variation of the material.

[0034] Preferably, the quality detection and evaluation module comprises a quality score calculation unit and a quality evaluation unit;

[0035] The quality score calculation unit is configured to calculate the comprehensive quality score Qf of the product by aggregating the surface roughness score Ra, the area variation coefficient Dr and the thermal expansion coefficient Pz, and the comprehensive quality score Qf is obtained in the following manner:

[0036]

[0037] wherein Ra max , Dr max and Pz max respectively represent the maximum values of the surface roughness score Ra, the area variation coefficient Dr and the thermal expansion coefficient Pz, ω1, ω2 and ω3 respectively represent the weight coefficients of the surface roughness score Ra, the area variation coefficient Dr and the thermal expansion coefficient Pz, and respectively represent the normalization processing of the product surface roughness score Ra, the area change coefficient Dr and the thermal expansion coefficient Pz, eliminating the differences in the dimensions and ranges of different characteristic indicators, and C represents the first correction coefficient.

[0038] Preferably, the quality evaluation unit is used to preset a quality score threshold QfYZ, and compare the quality score threshold QfYZ with the comprehensive quality score Qf to evaluate the qualification of the product, and the specific evaluation content is as follows:

[0039] If the comprehensive quality score Qf is less than the quality score threshold QfYZ, that is, Qf < QfYZ, it is judged that the quality of the product is in a qualified state, at this time, the product is continuously manufactured, and the product production process is continuously monitored;

[0040] If the comprehensive quality score is greater than or equal to the quality score threshold QfYZ, that is, Qf ≥ QfYZ, it is judged that the quality of the product is in an unqualified state, and an alarm mechanism is triggered, the intelligent manufacturing equipment is stopped, unqualified product data is recorded, a product quality evaluation report is generated, and the product quality evaluation report is transmitted to the equipment data center.

[0041] Preferably, the adjustment control module comprises a control signal generation unit and a production parameter adjustment unit.

[0042] The control signal generation unit is used to obtain the product surface roughness score deviation e Ra , the thermal expansion coefficient deviation e Pz and the area change coefficient deviation e Dr of the unqualified product according to the recorded unqualified product data when the quality of the product is in an unqualified state.

[0043] e Ra = Ra target -Ra;

[0044] e Pz = Pz target -Pz;

[0045] e Dr = Dr target -Dr;

[0046] In the formula, Ra target , Pz target and Dr target respectively represent the standard values of the product surface roughness score Ra, the thermal expansion coefficient Pz and the area change coefficient Dr, and the standard values of the product surface roughness score Ra, the thermal expansion coefficient Pz and the area change coefficient Dr Ra target , Pz target and Dr target are obtained through a related industry specification database.

[0047] According to the obtained product surface roughness score deviation e Ra , coefficient of thermal expansion deviation e Pz , and area change coefficient deviation e Dr , a PID control algorithm is used to generate a device control signal u(t), which is obtained in the following way:

[0048]

[0049] where e(t) represents the adjustment parameter error at the current time point t, e(t) = [e Ra , e Pz , e Dr ], K p represents the reaction strength of the control system to the adjustment parameter error e(t) at the current time point t, K i represents the cumulative effect of the error over a period of time, K d represents the reaction speed of the control system to the error change rate.

[0050] Preferably, the production parameter adjustment unit is used to generate a device control signal u(t) according to the device control signal u(t) obtained by the control signal generation unit, and automatically map the device control signal u(t) to a device operation parameter instruction according to the industrial automation control software TIA PROtal, and send the device operation parameter instruction to the intelligent manufacturing device through the PLC system of the production device to control the intelligent manufacturing device to perform adjustment work.

[0051] Preferably, the device optimization effect evaluation module is used to collect manufacturing data after device adjustment control, including environmental data and product data, and select a plurality of products of the same batch to construct a sample combination to be evaluated, calculate the comprehensive quality score Qf of each sample to be evaluated, evaluate the quality of the sample to be evaluated according to the comprehensive quality score Qf, and obtain the product pass rate HG of the same batch of products, wherein the product pass rate HG is obtained in the following way:

[0052]

[0053] where q represents the number of qualified samples to be evaluated, and m represents the total number of samples in the sample combination to be evaluated;

[0054] A preset product pass rate threshold HGYZ is compared with the product pass rate HG for comparative analysis to evaluate the optimization effect of device adjustment control, and the specific evaluation content is as follows:

[0055] If the product qualification rate HG is greater than or equal to the product qualification rate threshold HGYZ, i.e. HG≥HGYZ, it is determined that the optimization effect of the equipment adjustment control is in a normal state, at this time, the measures and equipment parameters of the equipment adjustment control are recorded, and an equipment optimization control report is generated and sent to relevant personnel as a basis for further optimization, and at the same time, manufacturing data in the product manufacturing process is continuously recorded, wherein the equipment optimization control report includes the optimization process and optimization result of the equipment adjustment control;

[0056] If the product qualification rate HG is less than the product qualification rate threshold HGYZ, i.e. HG<HGYZ, it is determined that the optimization effect of the equipment adjustment control is in an abnormal state, at this time, abnormal product data is recorded and fed back to the adjustment control module, the equipment adjustment parameter value u(t) is recalculated and iteratively optimized until the optimization effect of the equipment adjustment control is in a normal state.

[0057] Preferably, the stability analysis module is used to perform product quality control chart analysis when the optimization effect of the equipment adjustment control is in a normal state, and the specific analysis process is as follows:

[0058] The product production process after the equipment adjustment control is continuously monitored, and manufacturing data is collected every fixed time, and a certain number of products are randomly extracted as test samples each time;

[0059] The mean value of the characteristic index of the test samples at the same time point is calculated And the mean value of the characteristic index of the test samples at the same time point is calculated And the total average value μ of the characteristic index of the test samples at all time points is obtained, and the total average value μ is obtained in the following manner:

[0060]

[0061] In the formula, g represents the total number of data collection time points, μj represents the mean value of the characteristic index of the test samples at the jth data collection time point, j=[1, 2, 3, …, g];

[0062] According to the total average value μ of the characteristic index of the test samples at all time points, the upper control limit UCL and the lower control limit LCL are obtained, and a product quality control chart is drawn, wherein the horizontal axis of the product quality control chart is the product production time, and the vertical axis is the mean value of the characteristic index of the test samples at the same time point The upper control limit UCL and the lower control limit LCL are obtained in the following manner:

[0063] UCL=μ+3σ;

[0064] LCL=μ-3σ;

[0065] In the formula, μ represents the total average value of the characteristic index of the sample to be tested at all time points, and σ represents the standard deviation of the characteristic index of the sample to be tested at all time points.

[0066] According to the constructed product quality control chart, stability analysis is carried out, and the specific analysis contents are as follows.

[0067] If all data points in the product quality control chart are located between the upper control limit UCL and the lower control limit LCL, it is determined that the product quality is stable and no abnormality occurs.

[0068] If all data points in the product quality control chart are not located between the upper control limit UCL and the lower control limit LCL, it is determined that the product quality is abnormal, the abnormal data is recorded and sent to the equipment adjustment control personnel, and intelligent equipment adjustment control is carried out.

[0069] The application provides an intelligent manufacturing equipment remote control system based on the Internet, which has the following beneficial effects:

[0070] (1) By deploying infrared temperature sensors and high-definition cameras, the intelligent manufacturing equipment can collect and monitor environmental data and product data in real time, construct a manufacturing data set S, and based on these real-time data, extract key quality indicators such as surface roughness score, area change coefficient and thermal expansion coefficient through the data preprocessing and feature extraction module. Using these data, combined with the quality detection and evaluation module, the product is automatically evaluated for quality, a comprehensive quality score is generated, and intelligent adjustment control is triggered. This can greatly reduce human intervention, improve the automation and intelligence level of the production line, and ensure the consistency and stability of product quality. And when unqualified products are found in the quality evaluation process, the system will automatically generate adjustment control signals to quickly adjust the production parameters to ensure that the product quality is always at the expected level.

[0071] (2) By introducing the adjustment control module and the PID control algorithm, the system can automatically generate device control signals in the case of unqualified product quality, and accurately adjust the intelligent manufacturing equipment. Through real-time monitoring of the quality of the product, the PID control algorithm can effectively reduce errors and quickly optimize the adjustment of production parameters. The equipment optimization effect evaluation module compares the adjusted pass rate HG with the preset pass rate threshold HGYZ to evaluate whether the equipment adjustment is effective. If the pass rate HG is greater than or equal to the pass rate threshold HGYZ, it means that the optimization measures are effective, otherwise the system will perform iterative optimization. Through this real-time data and feedback control based method, production efficiency is significantly improved, while the pass rate is also improved and the scrap rate is reduced.

[0072] (3) Through the stability analysis module, the system not only evaluates the equipment optimization effect in the short term, but also continuously monitors the running state of the equipment under the condition of normal optimization effect, and analyzes the long-term stability of the product quality, the control chart analysis and the standard deviation analysis can help to monitor the quality fluctuation of each batch of products in real time, and ensure the stability in the production process. In the production process after the adjustment of the equipment, the stability analysis module will continuously collect manufacturing data and draw a control chart to analyze whether the data is within the control limit range. If the data point exceeds the control limit, it means that the production process has abnormal fluctuations. The system will automatically record the abnormal data and feedback to the adjustment control module for further optimization and adjustment. Such stability analysis ensures the continuous stability of product quality for a long time, and avoids the quality regression problem caused by equipment aging, environmental changes and other factors. BRIEF DESCRIPTION OF DRAWINGS

[0073] Figure 1 A block diagram of an intelligent manufacturing equipment remote control system based on the Internet is provided. DETAILED DESCRIPTION

[0074] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0075] Embodiment 1

[0076] Please refer to Figure 1 The present application provides an intelligent manufacturing equipment remote control system based on the Internet, which comprises a data acquisition module, a data preprocessing and feature extraction module, a quality detection and evaluation module, an adjustment control module, an equipment optimization effect evaluation module and a stability analysis module.

[0077] The data acquisition module is used to deploy infrared temperature sensors and high-definition cameras on intelligent manufacturing equipment, collect environmental data and product data in the product manufacturing process in real time, and construct a manufacturing data set S.

[0078] The data preprocessing and feature extraction module is used to preprocess the manufacturing data set S, and extract features from the preprocessed manufacturing data set S to obtain product surface roughness score Ra, area change coefficient Dr and thermal expansion coefficient Pz.

[0079] The quality detection and evaluation module is configured to perform summary calculation according to the product surface roughness score Ra, the area variation coefficient Dr and the thermal expansion coefficient Pz, obtain a comprehensive quality score Qf of the product, perform product quality evaluation according to the comprehensive quality score Qf, and generate a product quality evaluation report;

[0080] The adjustment control module is configured to perform adjustment control on the intelligent manufacturing equipment when the product quality is in an unqualified state according to the product quality evaluation report, generate an equipment control signal u(t) according to a PID control algorithm, and control the intelligent manufacturing equipment to perform adjustment work according to the equipment control signal u(t);

[0081] The equipment optimization effect evaluation module is configured to calculate a product pass rate HG of the same batch of products according to the manufacturing data after the adjustment control of the equipment, preset a product pass rate threshold HGYZ, compare and analyze the product pass rate threshold HGYZ and the product pass rate HG, and evaluate the optimization effect of the adjustment control of the equipment.

[0082] The stability analysis module is configured to collect manufacturing data of a period of time after the adjustment control of the equipment when the optimization effect of the adjustment control of the equipment is in a normal state, draw a product quality control chart, and perform stability analysis according to the product quality control chart.

[0083] In the embodiment, by integrating the data collection module, the data preprocessing and feature extraction module, the quality detection and evaluation module, the adjustment control module, the equipment optimization effect evaluation module and the stability analysis module, the intelligent manufacturing equipment remote control system can improve the intelligence, automation and accuracy of the manufacturing process. The data collection module collects environmental and product data in real time by deploying infrared temperature sensors and high-definition cameras, constructs a manufacturing data set S, and ensures the comprehensiveness and accuracy of the data source. The data preprocessing and feature extraction module further cleans and analyzes the data, extracts the product surface roughness score Ra, the area variation coefficient Dr and the thermal expansion coefficient Pz, and provides accurate basis for subsequent quality evaluation. The quality detection and evaluation module obtains the comprehensive quality score Qf of the product, automatically evaluates the product quality, and generates a product quality evaluation report, which facilitates timely adjustment of production parameters. The adjustment control module combines the PID control algorithm to adjust the production equipment parameters in real time, ensures that the product quality meets the requirements, and the equipment optimization effect evaluation module evaluates the product pass rate HG to feedback the adjustment effect of the equipment, and the stability analysis module monitors the long-term production stability to ensure that the optimization effect is continuous and effective. The overall system improves the production efficiency of the manufacturing equipment, reduces the scrap rate, and ensures the stability of the product quality.

[0084] Embodiment 2

[0085] Please refer to Figure 1Specifically, the data collection module includes an environment data collection unit and a product data collection unit.

[0086] The environment data collection unit is configured to deploy an infrared temperature sensor on the intelligent manufacturing equipment to collect a temperature variation AT of the product in real time during the product manufacturing process.

[0087] The product data collection unit is configured to deploy a high-definition camera on the intelligent manufacturing equipment to collect image data of the product in real time during the product manufacturing process, wherein the image data includes a height h of different regions of the product surface, an area size d of the product, and a length L of the product.

[0088] According to the collected environment data and product data, a manufacturing data set S is constructed, and the manufacturing data set S is transmitted to a device data center for storage through wireless transmission technology.

[0089] In an embodiment, by introducing the environment data collection unit and the product data collection unit, the intelligent manufacturing equipment can realize comprehensive monitoring and data collection during the product manufacturing process. The environment data collection unit can collect the temperature variation AT of the product in real time during the manufacturing process by deploying an infrared temperature sensor, which provides data for subsequent calculation of the thermal expansion coefficient and analysis of the impact of temperature on product quality. The product data collection unit can obtain the height h of different regions of the product surface, the area size d of the product, and the length L of the product in real time through a high-definition camera, which can effectively reflect the surface quality, dimensional accuracy, and shape change of the product, thereby providing an important basis for product quality evaluation. The data is integrated to obtain the manufacturing data set S, which is transmitted to the device data center for centralized storage and management through wireless transmission technology, thereby improving the visualization and intelligence level of the production process. The system can monitor and adjust various parameters in the production process in real time to ensure the stability and consistency of the production quality. In addition, the system can respond and adjust quickly based on real-time data to provide accurate data support for subsequent quality control and equipment optimization, helping enterprises to realize more efficient and accurate production processes.

[0090] Embodiment 3

[0091] Please refer to Figure 1 Specifically, the data preprocessing and feature extraction module includes a preprocessing unit and a feature extraction unit.

[0092] The preprocessing unit is configured to preprocess the manufacturing data set S, including environment data preprocessing and product data preprocessing.

[0093] The environment data preprocessing refers to data cleaning, denoising, and data standardization of the environment data in the manufacturing data set S.

[0094] The product data preprocessing refers to smoothing the image using Gaussian filtering on the product data in the manufacturing data set S, removing high-frequency noise in the image, and using histogram equalization to uniformly distribute the gray value of the image, increase the contrast, and using Canny edge detection to extract the edge profile of the image.

[0095] The feature extraction unit is used to perform summary calculation according to the preprocessed manufacturing data set S, and obtain the product surface roughness score Ra, the area change coefficient Dr and the thermal expansion coefficient Pz.

[0096] The product surface roughness score Ra is obtained in the following manner:

[0097]

[0098] In the formula, L represents the length of the product, y(x) represents the height of the product surface position x to be measured, represents the average height of the product surface to be measured;

[0099] The height y(x) of the product surface position x to be measured and the average height of the product surface to be measured are obtained by using a surface scanning device, wherein the surface scanning device includes a laser scanner and a stylus profilometer;

[0100] The area change coefficient Dr is obtained in the following manner:

[0101]

[0102] In the formula, d i represents the measurement area size of the i-th measurement point on the product, d ref，i represents the preset area size of the i-th measurement point on the product, i = [1, 2, 3, …, N], and N represents the number of measurement points.

[0103] The thermal expansion coefficient Pz is obtained in the following manner:

[0104]

[0105] In the formula, ΔL represents the length change amount of the product during heating, L0 represents the initial length of the product, and ΔT represents the temperature change amount of the material.

[0106] In the embodiment, the quality of the collected data is ensured through environmental data preprocessing and product data preprocessing. The environmental data preprocessing includes data cleaning, denoising, and standardization processing, effectively eliminating the interference of the external environment and ensuring the accuracy of subsequent data analysis. The product data preprocessing optimizes the image data through Gaussian filtering, histogram equalization, and Canny edge detection, removes image noise, enhances image features, and improves the accuracy and robustness of surface quality evaluation. In the feature extraction aspect, the feature extraction unit further refines the dimensions of product quality evaluation by calculating the product surface roughness score Ra, the area variation coefficient Dr, and the thermal expansion coefficient Pz. The product surface roughness score Ra can accurately reflect the product surface flatness, the area variation coefficient Dr is used to evaluate the stability of the product size, and the thermal expansion coefficient Pz is an important parameter of material performance, which can reflect the influence of temperature change on product deformation. Through the comprehensive analysis of these feature indicators, the quality of the product can be more comprehensively evaluated, helping to optimize the production process and timely adjust the manufacturing parameters to ensure the consistency and high pass rate of the product, ultimately improving the production efficiency and quality control capability of the intelligent manufacturing system.

[0107] Embodiment 4

[0108] Please refer to Figure 1 , specifically: the quality detection and evaluation module includes a quality score calculation unit and a quality evaluation unit;

[0109] The quality score calculation unit is used to calculate the comprehensive quality score Qf of the product based on the product surface roughness score Ra, the area variation coefficient Dr, and the thermal expansion coefficient Pz. The comprehensive quality score Qf is obtained as follows:

[0110]

[0111] In the formula, Ra max , Dr max , and Pz max represent the maximum values of the product surface roughness score Ra, the area variation coefficient Dr, and the thermal expansion coefficient Pz, respectively, ω1, ω2, and ω3 represent the weight coefficients of the product surface roughness score Ra, the area variation coefficient Dr, and the thermal expansion coefficient Pz, respectively, and represent the normalization processing of the product surface roughness score Ra, the area variation coefficient Dr, and the thermal expansion coefficient Pz, respectively, to eliminate the differences in the dimensions and ranges of different feature indicators, and C represents the first correction coefficient; the maximum values of the product surface roughness score Ra max , Dr max , and Pz maxThe quality control requirements are obtained according to relevant industry standards, wherein the weight coefficients ω1, ω2 and ω3 are set by the customer according to actual conditions, and ω1+ω2+ω3=1.

[0112] The quality evaluation unit is used to preset a quality score threshold QfYZ, and compare the quality score threshold QfYZ with the comprehensive quality score Qf to evaluate the qualification of the product, and the specific evaluation content is as follows:

[0113] If the comprehensive quality score Qf is less than the quality score threshold QfYZ, that is, Qf

[0114] If the comprehensive quality score Qf is greater than or equal to the quality score threshold QfYZ, that is, Qf≥QfYZ, it is judged that the quality of the product is in an unqualified state, and an alarm mechanism is triggered to stop the operation of the intelligent manufacturing equipment, record the unqualified product data, generate a product quality evaluation report, and transmit the product quality evaluation report to the equipment data center.

[0115] In the embodiment, by introducing the quality score calculation unit and the quality evaluation unit, the system can realize accurate and real-time product quality evaluation and automatic adjustment according to the evaluation result. The quality score calculation unit considers the product surface roughness score Ra, the area change coefficient Dr and the thermal expansion coefficient Pz, and generates a comprehensive quality score Qf by weighting and summarizing each feature index through a weight coefficient. In order to eliminate the differences in dimensions and ranges of different indexes, the system normalizes these indexes to make the score more scientific and fair. By setting the quality score threshold QfYZ, the system can automatically judge whether the product meets the quality standard. When the comprehensive quality score Qf is less than the quality score threshold QfYZ, the system considers that the product quality is qualified, and continues to produce and monitor the production process. When the comprehensive quality score Qf is greater than or equal to the quality score threshold QfYZ, the system will immediately stop the operation of the equipment, trigger the alarm mechanism, and avoid the production of unqualified products, thereby ensuring the quality of the products. This mechanism effectively reduces human errors, automatically optimizes the production process, ensures the consistency and reliability of the product quality, and provides a reliable quality guarantee means for the intelligent manufacturing equipment.

[0116] Embodiment 5

[0117] Please refer to Figure 1 , specifically: the adjustment control module includes a control signal generation unit and a production parameter adjustment unit;

[0118] The control signal generation unit is used to obtain the product surface roughness score deviation e Ra, thermal expansion coefficient deviation e Pz , and area change coefficient deviation e Dr :

[0119] e Ra = Ra target - Ra;

[0120] e Pz = Pz target - Pz;

[0121] e Dr = Dr target - Dr;

[0122] In the formula, Ra target , Pz target , and Dr target respectively represent the standard values of product surface roughness score Ra, thermal expansion coefficient Pz, and area change coefficient Dr, the standard values of product surface roughness score Ra target , Pz target , and Dr target are obtained through a related industry specification database;

[0123] According to the obtained product surface roughness score deviation e Ra , thermal expansion coefficient deviation e Pz , and area change coefficient deviation e Dr , a PID control algorithm is used to generate a device control signal u(t), and the device control signal u(t) is obtained in the following manner:

[0124]

[0125] In the formula, e(t) represents the adjustment parameter error at the current time point t, e(t) = [e Ra , e Pz , e Dr ], K p represents the reaction intensity of the control system to the adjustment parameter error e(t) at the current time point t, K i represents the cumulative effect of the error over a period of time, and K d represents the reaction speed of the control system to the error change rate, wherein the reaction intensity K p of the control system to the adjustment parameter error e(t) at the current time point t, the cumulative effect K i of the error over a period of time, and the reaction speed K d of the control system to the error change rate are determined by using the Ziegler-Nichols method;

[0126] The Ziegler-Nichols method is a classic PID control parameter tuning method, mainly used for adjusting parameters of PID controllers in industrial automation, including determination of proportional gain K p , integral gain K i , and derivative gain K d The core idea is to find the critical parameters that make the closed-loop system approach stability through experiments or system models, and then calculate the appropriate PID controller gain values based on these parameters.

[0127] In a specific example, assume there is an industrial heating furnace that requires the furnace temperature to be maintained at 200°C. However, in actual production, the furnace temperature will fluctuate due to factors such as raw materials, environmental temperature, and opening the cover. At this time, PID control is used to automatically adjust the heating power to stabilize the furnace temperature at the target value. The actual collected temperature is 180°C, which is lower than the set temperature. The proportional term of the PID controller will immediately increase the heating power, the integral term will further accumulate and continuously increase the heating intensity when the temperature is low for a long time, and the derivative term will weaken the heating signal in advance when the temperature quickly approaches the target value to avoid temperature overshoot. Using the Ziegler-Nichols method, the critical gain and critical oscillation period can be obtained through experiments, and the appropriate proportional gain K p , integral gain K i , and derivative gain K d can be calculated to make the controller restore the furnace temperature to the set value in the shortest time and maintain stability, avoiding frequent oscillation or insufficient adjustment.

[0128] The production parameter adjustment unit is used to obtain the device control signal u(t) obtained by the control signal generation unit, and automatically map the device control signal u(t) to device operation parameter instructions according to the industrial automation control software TIA PROtal, and send the device operation parameter instructions to the intelligent manufacturing device through the PLC system of the production device to control the intelligent manufacturing device to perform adjustment work.

[0129] The PLC system is a special computer system for industrial automation control, which can realize real-time monitoring and automatic control of mechanical equipment or production process, and is widely used in manufacturing, energy, transportation and other industries. It can perform complex logical operations and sequential control through pre-written programs.

[0130] The industrial automation control software TIA PROtal is a fully integrated automation software platform that integrates design, programming, debugging, and maintenance tools commonly used in industrial automation into one environment. It can be used for device control logic programming, parameter setting, signal mapping, and device debugging in industrial production lines and intelligent manufacturing systems.

[0131] In the embodiment, by adjusting the control module, the system can effectively respond to the situation of unqualified product quality and automatically optimize and adjust. The control signal generation unit calculates the deviation of the product surface roughness score Ra, the thermal expansion coefficient Pz and the area change coefficient Dr from the standard value based on the real-time collected product quality data including the product surface roughness score Ra, the thermal expansion coefficient Pz and the area change coefficient Dr, and generates the device control signal u(t) through the PID control algorithm. The PID control algorithm can adjust the production parameters in real time and accurately adjust the running state of the production equipment to realize the optimization and stability of the product quality. The system determines the PID parameters through the Ziegler-Nichols method, so that the device control signal u(t) is more sensitive and stable to the error, thereby effectively reducing the quality fluctuation, and the device control signal u(t) is mapped to the device operation parameter instruction and sent to the intelligent manufacturing equipment through the PLC system for automatic device parameter adjustment. This process can realize fast and accurate device adjustment, avoid the delay and error caused by manual intervention, improve the automation level of the production process, reduce the generation of unqualified products, and maintain the stability of the product quality in a long time.

[0132] Embodiment 6

[0133] Please refer to Figure 1 , specifically: the device optimization effect evaluation module is used to collect manufacturing data after device adjustment control, including environmental data and product data, and select a plurality of products of the same batch to construct a sample combination to be evaluated, calculate the comprehensive quality score Qf of each sample to be evaluated, evaluate the quality of the sample to be evaluated according to the comprehensive quality score Qf, and obtain the product qualification rate HG of the same batch of products. The product qualification rate HG is obtained in the following manner:

[0134]

[0135] In the formula, q represents the number of qualified samples to be evaluated, and m represents the total number of samples in the sample combination to be evaluated.

[0136] A preset product qualification rate threshold HGYZ is compared with the product qualification rate HG for analysis, and the optimization effect of the device adjustment control is evaluated. The specific evaluation content is as follows:

[0137] If the product qualification rate HG is greater than or equal to the product qualification rate threshold HGYZ, i.e. HG≥HGYZ, it is determined that the optimization effect of the device adjustment control is normal. At this time, the device adjustment control measures and device parameters are recorded, and a device optimization control report is generated. The device optimization control report is sent to relevant personnel as a basis for further optimization, and the manufacturing data in the product manufacturing process is continuously recorded. The device optimization control report includes the optimization process and optimization results of the device adjustment control.

[0138] If the product pass rate HG is less than the product pass rate threshold HGYZ, i.e. HG < HGYZ, it is determined that the optimization effect of the equipment adjustment control is abnormal, at which time abnormal product data is recorded, and the abnormal product data is fed back to the adjustment control module, the equipment adjustment parameter value u(t) is recalculated, and iterative optimization is performed until the optimization effect of the equipment adjustment control is normal.

[0139] In an embodiment, by continuously monitoring and evaluating production data after equipment adjustment control, it is ensured that the adjustment measures of the intelligent manufacturing equipment can effectively improve product quality in actual production. This module first calculates the comprehensive quality score Qf of the products in the same batch, and obtains the product pass rate HG according to the product pass rate HG. If the product pass rate HG is greater than or equal to the product pass rate threshold HGYZ, the system will determine that the optimization effect of the equipment adjustment control is normal, generate an optimization report and record the adjustment process, which provides a basis for subsequent optimization decisions. At the same time, if the product pass rate HG is less than the product pass rate threshold HGYZ, the system will automatically identify that the optimization effect of the equipment adjustment control is abnormal, record the unqualified data, and adjust the equipment parameters through the feedback adjustment unit, start the iterative optimization process until the expected effect is achieved. Such evaluation and feedback mechanism can timely find the shortcomings in equipment adjustment, avoid quality fluctuations in continuous production, and further optimize equipment performance through precise feedback, ultimately realize the continuous improvement and stability of quality in the production process. This not only improves the product pass rate, but also enhances the adaptability and intelligence level of the production system, ensuring the stable effect of equipment adjustment in different batches and time periods.

[0140] Embodiment 7

[0141] Please refer to Figure 1 , specifically: the stability analysis module is used to analyze the product quality control chart when the optimization effect of the equipment adjustment control is normal, and the specific analysis process is as follows:

[0142] Continuously monitor the product production process after equipment adjustment control, collect manufacturing data every fixed time, and randomly select a certain number of products as test samples each time;

[0143] Calculate the mean value of the characteristic index of the test samples at the same time point and according to the mean value of the characteristic index of the test samples at the same time point and obtain the total average value μ of the characteristic index of all time points of the test samples, the total average value μ is obtained in the following way:

[0144]

[0145] In the formula, g represents the total number of data collection time points, represents the mean value of the characteristic index of the sample to be tested at the jth data collection time point, j = [1, 2, 3, …, g];

[0146] According to the total mean value μ of the characteristic index of the sample to be tested at all time points, the upper control limit UCL and the lower control limit LCL are obtained, and a product quality control chart is drawn, wherein the horizontal axis is the product production time, and the vertical axis is the mean value of the characteristic index of the sample to be tested at the same time point The upper control limit UCL and the lower control limit LCL are obtained in the following manner:

[0147] UCL = μ + 3σ;

[0148] LCL = μ - 3σ;

[0149] In the formula, μ represents the total mean value of the characteristic index of the sample to be tested at all time points, and σ represents the standard deviation of the characteristic index of the sample to be tested at all time points;

[0150] According to the product quality control chart constructed, stability analysis is performed, and the specific analysis contents are as follows:

[0151] If all data points in the product quality control chart are located between the upper control limit UCL and the lower control limit LCL, it is determined that the product quality is stable and no abnormality occurs.

[0152] If all data points in the product quality control chart are not located between the upper control limit UCL and the lower control limit LCL, it is determined that the product quality is abnormal, the abnormal data is recorded, and the abnormal data is sent to the equipment adjustment control personnel for intelligent equipment adjustment control.

[0153] In the embodiment, through long-term monitoring and analysis of product quality, the product quality stability in the production process is ensured. The module continuously collects manufacturing data, and periodically extracts a plurality of product samples to calculate the characteristic index, generates a product quality control chart, and through real-time analysis of the control chart, it can be determined whether the product quality has abnormal fluctuations. Specifically, by calculating the mean value of the characteristic index at all time points and drawing a control chart, the module can set the upper control limit UCL and the lower control limit LCL, and determine whether the data points fall within the control limit. When all data points are within the control limit, it indicates that the product quality is stable and no adjustment is required. If the data points exceed the control limit, it indicates that a quality abnormality has occurred. The system automatically records the abnormal data and feeds back to the adjustment control personnel to start equipment adjustment in a timely manner. This analysis not only can find production fluctuations in the short term, but also can track the quality of products after equipment adjustment for a long time, ensuring the persistence and effectiveness of optimization measures, effectively avoiding quality regression caused by equipment or environmental changes, thereby improving the stability of the production process and the consistency of the products, enhancing the self-adjustment ability of the intelligent manufacturing system, reducing manual intervention, improving production efficiency and product qualification rate.

[0154] While embodiments of the present application have been shown and described, it is to be understood that various modifications, substitutions, replacements and variations can be made to these embodiments without departing from the principles and spirit of the present application, the scope of which is defined by the appended claims and their equivalents.

Claims

1. An Internet-based remote control system for intelligent manufacturing equipment, characterized by: It includes data acquisition module, data preprocessing and feature extraction module, quality inspection and evaluation module, adjustment control module, equipment optimization effect evaluation module and stability analysis module; The data acquisition module is used to deploy infrared temperature sensors and high-definition cameras on intelligent manufacturing equipment to collect environmental data and product data during the product manufacturing process in real time and construct a manufacturing data set S; The data preprocessing and feature extraction module is used to perform preprocessing based on the manufacturing data set S, and perform feature extraction based on the preprocessed manufacturing data set S to obtain the product surface roughness score Ra, area variation coefficient Dr, and thermal expansion coefficient Pz; The quality inspection and assessment module is used to perform summary calculations based on the product surface roughness score Ra, area variation coefficient Dr, and thermal expansion coefficient Pz to obtain a comprehensive quality score Qf of the product, and to perform product quality assessment based on the comprehensive quality score Qf to generate a product quality assessment report; The adjustment control module is used to adjust and control the intelligent manufacturing equipment according to the product quality assessment report when the quality of the product is in an unqualified state, generate an equipment control signal u(t) according to the PID control algorithm, and control the intelligent manufacturing equipment to perform adjustment operations according to the equipment control signal u(t); The equipment optimization effect evaluation module is used to calculate the product qualification rate HG of the same batch of products based on the manufacturing data after the equipment adjustment and control, and preset the product qualification rate threshold HGYZ, and compare and analyze the product qualification rate threshold HGYZ with the product qualification rate HG to evaluate the optimization effect of the equipment adjustment and control; The stability analysis module is used to collect manufacturing data for a period of time after the equipment adjustment control when the optimization effect of the equipment adjustment control is in a normal state, draw a product quality control chart, and perform stability analysis based on the product quality control chart.

2. The Internet-based intelligent manufacturing equipment remote control system according to claim 1, characterized in that: The data acquisition module includes an environmental data acquisition unit and a product data acquisition unit; The environmental data acquisition unit is used to deploy infrared temperature sensors on intelligent manufacturing equipment to collect temperature changes ΔT of products during the manufacturing process in real time; The product data acquisition unit is used to deploy a high-definition camera on the intelligent manufacturing equipment to collect image data of the product during the product manufacturing process in real time, wherein the image data includes the height h of different areas on the product surface, the area size d and length L of the product; Based on the collected environmental data and product data, a manufacturing data set S is constructed, and the manufacturing data set S is transmitted to the equipment data center for storage through wireless transmission technology.

3. The Internet-based intelligent manufacturing equipment remote control system according to claim 2, characterized in that: The data preprocessing and feature extraction module includes a preprocessing unit and a feature extraction unit; The preprocessing unit is used to perform preprocessing based on the manufacturing data set S, including environmental data preprocessing and product data preprocessing; The environmental data preprocessing refers to data cleaning, denoising and data standardization of the environmental data in the manufacturing data set S; The product data preprocessing refers to smoothing the image of the product data in the manufacturing data set S using Gaussian filtering to remove high-frequency noise in the image, uniformly distributing the grayscale value of the image using histogram equalization, increasing the contrast, and extracting the edge contour of the image using Canny edge detection.

4. The Internet-based intelligent manufacturing equipment remote control system according to claim 3, characterized in that: The feature extraction unit is used to perform summary calculation based on the pre-processed manufacturing data set S to obtain the product surface roughness score Ra, area variation coefficient Dr and thermal expansion coefficient Pz; The surface roughness score Ra of the product is obtained as follows: Where L is the length of the product, y(x) is the height of the surface position x of the product to be measured, Indicates the average height of the surface of the product to be tested; The height y(x) of the surface position x of the product to be tested and the average height of the surface of the product to be tested Acquiring by using a surface scanning device, wherein the surface scanning device includes a laser scanner and a stylus profilometer; The area variation coefficient Dr is obtained as follows: Where, d i Indicates the measurement area of ​​the i-th measurement point on the product, d ref，i Indicates the preset area size of the i-th measurement point on the product, i = [1, 2, 3, ..., N], N represents the number of measurement points; The thermal expansion coefficient Pz is obtained as follows: Where ΔL represents the length change of the product during the heating process, L0 represents the initial length of the product, and ΔT represents the temperature change of the material.

5. The Internet-based intelligent manufacturing equipment remote control system according to claim 4, characterized in that: The quality detection and assessment module includes a quality score calculation unit and a quality assessment unit; The quality score calculation unit is used to perform summary calculation based on the surface roughness score Ra, area variation coefficient Dr and thermal expansion coefficient Pz of the product to obtain the comprehensive quality score Qf of the product. The comprehensive quality score Qf is obtained as follows: Where Ra max 、Dr max and Pz max They represent the maximum values ​​of the product surface roughness score Ra, area variation coefficient Dr and thermal expansion coefficient Pz respectively. ω1, ω2 and ω3 represent the weight coefficients of the product surface roughness score Ra, area variation coefficient Dr and thermal expansion coefficient Pz respectively. and They respectively represent the normalization processing of the product surface roughness score Ra, area variation coefficient Dr and thermal expansion coefficient Pz to eliminate the differences in dimensions and ranges of different characteristic indicators. C represents the first correction coefficient.

6. The Internet-based intelligent manufacturing equipment remote control system according to claim 5, characterized in that: The quality assessment unit is used to preset a quality score threshold QfYZ and compare and analyze the quality score threshold QfYZ with the comprehensive quality score Qf to assess the eligibility of the product. The specific assessment contents are as follows: If the comprehensive quality score Qf is less than the quality score threshold QfYZ, that is, Qf<QfYZ, the product quality is judged to be qualified, and the product manufacturing will continue, and the product production process will be continuously monitored; If the comprehensive quality score is greater than or equal to the quality score threshold QfYZ, that is, Qf≥QfYZ, the product quality is judged to be unqualified, and the alarm mechanism is triggered to stop the operation of the intelligent manufacturing equipment, record the unqualified product data, generate a product quality assessment report, and transmit the product quality assessment report to the equipment data center.

7. The Internet-based intelligent manufacturing equipment remote control system according to claim 6, characterized in that: The adjustment control module includes a control signal generating unit and a production parameter adjustment unit; The control signal generating unit is used to obtain the product surface roughness score deviation e of the unqualified product based on the recorded unqualified product data when the product quality is in an unqualified state. Ra , thermal expansion coefficient deviation e Pz and the area variation coefficient deviation e Dr : e Ra =Ra target -Ra; e Pz =Pz target -Pz; and Dr =Dr target -Dr. Where Ra target 、Pz target and Dr. target Respectively represent the standard values ​​of product surface roughness score Ra, thermal expansion coefficient Pz and area variation coefficient Dr, the standard values ​​of product surface roughness score Ra, thermal expansion coefficient Pz and area variation coefficient Dr Ra target 、Pz target and Dr. target Obtained through relevant industry standard database; Based on the obtained product surface roughness score deviation e Ra , thermal expansion coefficient deviation e Pz and the area variation coefficient deviation e Dr , use the PID control algorithm to generate the device control signal u(t), and the device control signal u(t) is obtained as follows: Where, e(t) represents the adjustment parameter error at the current time point t, e(t) = [e Ra , e Pz , e Dr ], K p K represents the response intensity of the control system to the adjustment parameter error e(t) at the current time point t, i Indicates the cumulative impact of the error over a period of time, K d Indicates how quickly the control system responds to the rate of change of the error.

8. The Internet-based intelligent manufacturing equipment remote control system according to claim 7, characterized in that: The production parameter adjustment unit is used to automatically map the equipment control signal u(t) obtained by the control signal generation unit into equipment operation parameter instructions based on the industrial automation control software TIAPROtal, and send the equipment operation parameter instructions to the intelligent manufacturing equipment through the PLC system of the production equipment to control the intelligent manufacturing equipment to perform adjustment operations.

9. The Internet-based intelligent manufacturing equipment remote control system according to claim 8, characterized in that: The equipment optimization effect evaluation module is used to collect manufacturing data after equipment adjustment and control, including environmental data and product data, and select several products from the same batch to construct a sample combination to be evaluated, calculate the comprehensive quality score Qf of each sample to be evaluated, evaluate the quality of the sample to be evaluated based on the comprehensive quality score Qf, and obtain the product qualification rate HG of the same batch of products. The product qualification rate HG is obtained in the following way: Where q represents the number of qualified samples to be evaluated, and m represents the total number of samples in the sample combination to be evaluated; Preset the product qualification rate threshold HGYZ, compare and analyze the product qualification rate HG with the product qualification rate threshold HGYZ, and evaluate the optimization effect of equipment adjustment control. The specific evaluation contents are as follows: If the product qualification rate HG is greater than or equal to the product qualification rate threshold HGYZ, that is, HG ≥ HGYZ, the optimization effect of the equipment adjustment control is determined to be normal. At this time, the equipment adjustment control measures and equipment parameters are recorded, and an equipment optimization control report is generated. The equipment optimization control report is sent to relevant personnel as a basis for further optimization. At the same time, the manufacturing data of the product manufacturing process is continuously recorded. Among them, the equipment optimization control report includes the optimization process and optimization results of the equipment adjustment control; If the product qualification rate HG is less than the product qualification rate threshold HGYZ, that is, HG<HGYZ, it is determined that the optimization effect of the equipment adjustment control is in an abnormal state. At this time, the abnormal product data is recorded and fed back to the adjustment control module, the equipment adjustment parameter value u(t) is recalculated, and iterative optimization is performed until the optimization effect of the equipment adjustment control is in a normal state.

10. The Internet-based intelligent manufacturing equipment remote control system according to claim 9, characterized in that: The stability analysis module is used to perform product quality control chart analysis when the optimization effect of equipment adjustment control is in a normal state. The specific analysis process is as follows: Continuously monitor the product production process after equipment adjustment and control, collect manufacturing data at fixed intervals, and randomly select a certain number of products as test samples each time; Calculate the mean of the characteristic indicators of the samples to be tested at the same time point And based on the mean of the characteristic indicators of the samples to be tested at the same time point And obtain the total average value μ of the characteristic indicators of the samples to be tested at all time points. The method for obtaining the total average value μ of the characteristic indicators is: Where g represents the total number of data collection time points, represents the mean of the characteristic index of the sample to be tested at the jth data collection time point, j = [1, 2, 3, ..., g]; According to the total average value μ of the characteristic indicators of the samples to be tested at all time points, the upper control limit UCL and the lower control limit LCL are obtained, and a product quality control chart is drawn. The horizontal axis of the product quality control chart is the product production time, and the vertical axis is the average value of the characteristic indicators of the samples to be tested at the same time point. The upper control limit UCL and the lower control limit LCL are obtained as follows: UCL = μ + 3σ; LCL = μ-3σ; Where μ represents the total average value of the characteristic index of the samples to be tested at all time points, and σ represents the standard deviation of the characteristic index of the samples to be tested at all time points; Based on the constructed product quality control chart, stability analysis is carried out. The specific analysis contents are as follows; If all data points in the product quality control chart are between the upper control limit UCL and the lower control limit LCL, the product quality is considered stable and without abnormalities. If the positions of all data points in the product quality control chart are not all between the upper control limit UCL and the lower control limit LCL, it is judged that the product quality is abnormal, the abnormal data is recorded and sent to the equipment adjustment and control personnel for intelligent equipment adjustment and control.

Images