Production and processing data collaborative management system and method for curtain wall single aluminum plate

Abstract

The invention discloses a production processing data collaborative management system and method of a curtain wall single aluminum plate, and relates to the technical field of data collaborative management. According to the method, the production processing data and the quality detection data of the curtain wall single aluminum plate are collected, the dynamic time warping algorithm is adopted to analyze the time sequence data change between the working procedures, the time deviation and the performance fluctuation between the working procedures are recognized, then the working procedure coordination index is obtained, and the time synchronism and the efficiency matching degree between the working procedures are measured. And performing classification and regression analysis on the quality index of each processing procedure through a decision tree algorithm to obtain a quality stability index, and identifying and predicting quality fluctuation and abnormal modes in different procedures. And judging whether the sequence and priority of the production processes need to be adjusted or not through comprehensive analysis of the process coordination index and the quality stability index. And time inconsistency, efficiency bottleneck and quality fluctuation in the production process are identified, intelligent optimal scheduling of the production process is realized, and the collaborative management level of the production process is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data collaborative management, and in particular to a production and processing data collaborative management system and method for a single aluminum plate for a curtain wall. Background Art

[0002] With the development of the construction industry and the widespread application of modern curtain wall technology, single aluminum curtain wall panels, as an important building facade material, are increasingly used in high-rise buildings, commercial complexes, public facilities and other fields. Single aluminum curtain wall panels require not only excellent physical properties, but also precise processing technology and high-quality surface treatment. In order to ensure that the produced single aluminum curtain wall panels meet high quality standards, modern production lines need to manage the processing process in a refined manner and use advanced technical means to monitor and analyze data in real time for each processing link. With the advancement of intelligent manufacturing, how to improve production efficiency and quality stability through data collaborative management has become an important issue facing the manufacturing industry.

[0003] At present, although some companies have introduced data collection and monitoring systems in the production and processing of single aluminum panels for curtain walls, many existing systems lack efficient data integration and collaborative analysis capabilities, and cannot achieve real-time data transmission and collaborative optimization between different processes, resulting in information islands between various links and the inability to maximize production efficiency. Secondly, traditional abnormality monitoring mostly relies on a single data indicator, and it is difficult to comprehensively analyze the multi-dimensional data in the processing process and quality inspection, resulting in poor accuracy and timeliness of abnormality detection, and potential quality problems may be missed. Most of the existing production scheduling and process optimization methods rely on manual experience and regular inspections, lack the ability to adjust dynamically, cannot quickly respond to time deviations and performance fluctuations that occur during the processing process, and are difficult to achieve automatic coordination and real-time adjustment between processes. Therefore, there is an urgent need for a new type of curtain wall single aluminum panel production and processing data collaborative management system that can achieve comprehensive data collection, real-time monitoring, and dynamic optimization to improve production efficiency, ensure product quality, and reduce resource waste. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a collaborative management system and method for production and processing data of single aluminum panels for curtain walls, which solves the problems of the above-mentioned background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a production and processing data collaborative management system for curtain wall single aluminum plates, comprising the following modules: a data acquisition module, an abnormality monitoring module, and a collaborative management module; the data acquisition module is used to collect the production and processing data of curtain wall single aluminum plates, including curtain wall single aluminum plate processing process data and curtain wall single aluminum plate quality detection data; the abnormality monitoring module includes a processing abnormality monitoring unit and a quality abnormality monitoring unit; the processing abnormality monitoring unit is used to analyze the timing data changes of the curtain wall single aluminum plate between cutting, bending, and spraying based on the curtain wall single aluminum plate processing process data through a dynamic time warping algorithm, identify the time deviation and performance fluctuation between processes, and obtain a process coordination index for measuring the time synchronization and efficiency matching between each process; the quality abnormality monitoring unit is used to classify and regress the quality indicators of each processing process based on the curtain wall single aluminum plate quality detection data through a decision tree algorithm, and obtain a quality stability index for identifying and predicting quality fluctuations and abnormal patterns in different processes; the collaborative management module is used to comprehensively analyze the process coordination index and the quality stability index to determine whether it is necessary to adjust the order and process priority of the production process.

[0006] Furthermore, the processing process data of the single aluminum plate for the curtain wall includes cutting process data, bending process data, spraying process data and inter-process conversion data; the quality inspection data of the single aluminum plate for the curtain wall includes appearance inspection data, size inspection data and physical property inspection data.

[0007] Furthermore, based on the processing process data of single aluminum plate for curtain wall, the specific process of analyzing the changes in the timing data of single aluminum plate for curtain wall between cutting, bending and spraying is as follows: the processing process data of single aluminum plate for curtain wall is synchronized with timestamps, denoised and standardized; the matching degree of each pair of processes is calculated through the dynamic time warping algorithm, and the aligned process timing data is output; according to the process timing data, the time deviation between processes is analyzed, the time synchronization is calculated, the performance fluctuations between processes are analyzed, and the efficiency matching degree is evaluated.

[0008] Furthermore, the specific process of identifying the time deviation and performance fluctuation between processes and obtaining the process coordination index is as follows: based on the aligned process timing data, the time difference of each pair of processes is calculated to obtain the time deviation value between each process, and the delay or advance between processes is identified; the difference between the processing time of each process and the expected processing time is analyzed to evaluate the performance fluctuation of the process; the time deviation and performance fluctuation are combined, and the comprehensive coordination degree of each process is analyzed through weighted and linear combination to obtain the process coordination index.

[0009] Furthermore, based on the quality inspection data of single aluminum panels for curtain walls, the specific process of classifying and regressing the quality indicators of each processing procedure through the decision tree algorithm is as follows: preprocessing the quality inspection data of single aluminum panels for curtain walls, including removing outliers, filling missing values ​​and standardization, and extracting the processing parameters of the processing procedure data; training the model through the decision tree algorithm, taking the quality indicators of each processing procedure as the target variable, and taking the processing parameters as the input features for classification and regression analysis; building a decision tree model based on the training data to judge the quality performance of each processing procedure and predict the quality change trend; for each process, output the quality classification results and regression results to predict the stability or fluctuation of the quality.

[0010] Furthermore, the specific process of obtaining the quality stability index and identifying and predicting the quality fluctuations and abnormal patterns in different processes is as follows: summarizing the quality classification results and regression results of each process, calculating the standard deviation and mean of the quality error of each process, quantifying the amplitude of the quality fluctuation, integrating the quality fluctuations of each process by weighting, and obtaining the quality stability index; according to the preset quality stability index threshold, identifying the abnormal pattern of quality fluctuation exceeding the preset threshold.

[0011] Furthermore, the specific process of comprehensive analysis of the process coordination index and the quality stability index is as follows: normalize the process coordination index and the quality stability index; analyze the linear relationship between the normalized process coordination index and the quality stability index through the Pearson correlation coefficient; and evaluate the overall performance of each process based on the result of the Pearson correlation coefficient.

[0012] Furthermore, the specific process of judging whether it is necessary to adjust the order and priority of the production processes is as follows: based on the process coordination index and the quality stability index, analyze the priority and coordination between the processes; for processes whose Pearson correlation coefficient shows a low correlation, evaluate whether there is room for optimization and adjustment; according to the coordination and quality stability of each process, establish priority sorting rules, and give priority to adjusting processes with poor coordination or large quality fluctuations; determine whether it is necessary to adjust the order of the production processes, and rearrange the production process according to the priority of the processes.

[0013] The collaborative management method of production and processing data of single aluminum panels for curtain walls comprises the following steps: S1. Collecting production and processing data of single aluminum panels for curtain walls, including processing process data of single aluminum panels for curtain walls and quality inspection data of single aluminum panels for curtain walls; S2. Based on the processing process data of single aluminum panels for curtain walls, analyzing the changes in timing data of single aluminum panels for curtain walls during cutting, bending and spraying through a dynamic time warping algorithm, identifying the time deviation and performance fluctuation between processes, and obtaining a process coordination index, which is used to measure the time synchronization and efficiency matching between processes; S3. Based on the quality inspection data of single aluminum panels for curtain walls, classifying and regressing the quality indicators of each processing process through a decision tree algorithm, and obtaining a quality stability index, which is used to identify and predict quality fluctuations and abnormal patterns in different processes; S4. Comprehensively analyzing the process coordination index and the quality stability index to determine whether it is necessary to adjust the sequence of production processes and process priorities.

[0014] The present invention has the following beneficial effects:

[0015] (1) The production and processing data collaborative management system of the curtain wall single aluminum plate collects the processing process data and quality inspection data of the curtain wall single aluminum plate, and uses the dynamic time warping algorithm to analyze the changes in the timing data of the curtain wall single aluminum plate during cutting, bending, and spraying. It accurately identifies the time deviation and performance fluctuation between processes, and obtains the process coordination index to measure the time synchronization and efficiency matching between the processes, thereby effectively identifying the time inconsistency and efficiency bottleneck in the production process, and improving the overall coordination and efficiency of the production process.

[0016] (2) The collaborative management method of production and processing data of curtain wall single aluminum plate obtains the quality inspection data of curtain wall single aluminum plate, uses decision tree algorithm to classify and regress the quality indicators of each processing process, and obtains the quality stability index, which is used to identify and predict the quality fluctuations and abnormal patterns in different processes. Through the comprehensive analysis of the process coordination index and the quality stability index, the system can dynamically determine whether the order and priority of the production process need to be adjusted, thereby realizing the intelligent optimization and scheduling of the production process, improving the stability of product quality, reducing the occurrence of abnormal situations, and significantly enhancing the intelligent level of collaborative management of production and processing data.

[0017] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 The present invention is a flow chart of the collaborative management system for production and processing data of a single aluminum panel for curtain walls.

[0019] Figure 2 The present invention is a flow chart of the collaborative management method of production and processing data of a single aluminum panel for curtain walls. DETAILED DESCRIPTION

[0020] The embodiment of the present application solves the problems of poor time coordination, low efficiency matching and unpredictable quality fluctuations in the production process through the collaborative management system and method of production and processing data of single aluminum panels for curtain walls. Through the combination of dynamic time warping algorithm and decision tree algorithm, accurate analysis of time series data between processes and intelligent prediction of quality indicators are achieved, thereby effectively improving the synchronization and efficiency of the production process and ensuring the coordination and stability of each process. At the same time, the system can also identify and prevent quality anomalies that may occur in the production process, provide data support to optimize the order and priority of production processes, and further improve production efficiency and product quality stability.

[0021] The overall idea of ​​the solution in the embodiments of this application is as follows:

[0022] Collect the production and processing data of single aluminum curtain wall panels, including the processing procedure data and quality inspection data of single aluminum curtain wall panels.

[0023] Based on the processing process data of single aluminum curtain wall panels, the dynamic time warping algorithm is used to analyze the timing data changes of single aluminum curtain wall panels during cutting, bending, and spraying. The time deviation and performance fluctuation between processes are identified, and the process coordination index is obtained to measure the time synchronization and efficiency matching between the processes.

[0024] Based on the quality inspection data of single aluminum panels for curtain walls, the quality indicators of each processing procedure were classified and regressed through the decision tree algorithm to obtain the quality stability index, which was used to identify and predict quality fluctuations and abnormal patterns in different processes.

[0025] Conduct a comprehensive analysis of the process coordination index and quality stability index to determine whether the sequence and priority of the production processes need to be adjusted.

[0026] See also Figure 1The embodiment of the present invention provides a technical solution: a production and processing data collaborative management system for curtain wall single aluminum plates, comprising the following modules: a data acquisition module, an abnormality monitoring module, and a collaborative management module; the data acquisition module is used to collect the production and processing data of curtain wall single aluminum plates, including curtain wall single aluminum plate processing process data and curtain wall single aluminum plate quality detection data; the abnormality monitoring module includes a processing abnormality monitoring unit and a quality abnormality monitoring unit; the processing abnormality monitoring unit is used to analyze the time series data changes between cutting, bending, and spraying of curtain wall single aluminum plates based on the curtain wall single aluminum plate processing process data through a dynamic time warping algorithm, identify the time deviation and performance fluctuation between processes, and obtain a process coordination index for measuring the time synchronization and efficiency matching between each process; the quality abnormality monitoring unit is used to classify and regress the quality indicators of each processing process based on the curtain wall single aluminum plate quality detection data through a decision tree algorithm, and obtain a quality stability index for identifying and predicting quality fluctuations and abnormal patterns in different processes; the collaborative management module is used to comprehensively analyze the process coordination index and the quality stability index to determine whether it is necessary to adjust the order of production processes and process priorities.

[0027] In this implementation scheme, data acquisition module: This module is responsible for collecting the production and processing data of curtain wall single aluminum plate, including two aspects: processing process data and quality inspection data. Specifically, processing process data refers to the relevant parameters, timestamps and other information generated by each process (such as cutting, bending, spraying, etc.) in the production process of curtain wall single aluminum plate; while quality inspection data refers to the relevant data about product quality (thickness, surface smoothness) collected by detection means (visual inspection, sensors). Abnormal monitoring module: This module consists of two parts: processing abnormality monitoring unit and quality abnormality monitoring unit, which analyzes the collected data and monitors the abnormal conditions that may occur in the production process in real time. Processing abnormality monitoring unit: This unit uses dynamic time warping algorithm to analyze the processing process data of curtain wall single aluminum plate, mainly by comparing the changes in time series data between different processes, identifying the time deviation and performance fluctuation between processes. Dynamic time warping algorithm: An algorithm commonly used in time series data analysis, which can measure the similarity between different time series, especially when dealing with the situation where two sets of time series are misaligned on the time axis. In the present invention, the algorithm is used to analyze the time series data of different processes to find possible synchronization problems or time mismatches between processes during the processing. Process coordination index: Based on the analysis results, a numerical index process coordination index is calculated to measure the time synchronization and efficiency matching between the processes. The higher the index value, the better the coordination and efficiency between the processes, and the smoother the production process. Quality abnormality monitoring unit: Based on the quality inspection data, the unit uses the decision tree algorithm to classify and regress the quality indicators of each processing process. In this way, the quality performance of each process can be accurately judged and possible quality change trends can be predicted. Decision tree algorithm: A machine learning algorithm used to make decisions or predictions from a series of rules based on the input feature data. In the present invention, the decision tree is used to analyze the quality indicators of each process to help predict which processes may cause product quality problems. Quality stability index: Based on the results of the decision tree analysis, a quality stability index is generated, which is used to evaluate and predict the quality stability and volatility of each process. A high quality stability index indicates that the quality of the process is within the control range, while a low index indicates that the process may have quality fluctuations or instability. Collaborative management module: The core function of this module is to conduct a comprehensive analysis of the aforementioned process coordination index and quality stability index. By comparing and analyzing these two indicators, it is determined whether the order and priority of the production process need to be adjusted. Comprehensive analysis: During the production process, there may be mismatches between processes due to equipment failures, process problems, etc. At this time, it is necessary to comprehensively analyze the process coordination index and quality stability index to find out production bottlenecks or quality risks. If the analysis results show that some processes have serious synchronization problems or unstable quality problems, the system can optimize production efficiency and quality control by adjusting the process order or priority.

[0028] Specifically, the processing process data of the single aluminum plate for the curtain wall includes cutting process data, bending process data, spraying process data and inter-process conversion data; the quality inspection data of the single aluminum plate for the curtain wall includes appearance inspection data, size inspection data and physical property inspection data.

[0029] In this implementation scheme, the curtain wall single aluminum plate processing process data is used to describe the operation conditions at each stage of the production process, including the following types of data: Cutting process data: refers to the relevant data recorded when the cutting operation is performed during the production process. These data may include the operating parameters of the cutting machine, cutting time, cutting angle, initial size of the material, and actual size after cutting. The cutting process is the first step of the curtain wall single aluminum plate processing operation, and any inaccurate cutting will affect the quality of subsequent processes. Bending process data: refers to the working parameters of the machine equipment (including bending angle, bending force, bending speed) and the shape change data of the aluminum plate after bending in the bending process. The bending process is crucial to the overall shape of the curtain wall single aluminum plate. Therefore, accurately controlling the data of this process is the key to ensuring product accuracy. Spraying process data: In the spraying process, the working status of the spraying equipment (including spraying pressure, spraying time, coating thickness) and the final spraying uniformity, adhesion and other quality indicators are mainly collected. These data determine the surface quality and anti-corrosion performance of the curtain wall single aluminum plate. Inter-process conversion data: refers to the connection data between different processing processes. For example, in the transition stage from cutting to bending, the adjustment time of equipment and personnel, the change of setting parameters, the movement of materials, etc. These data are very important to ensure the smooth transition of each process and save production time. If the conversion between processes is not timely or unreasonable, it may lead to reduced production efficiency or quality problems. Curtain wall single aluminum plate quality inspection data Quality inspection data is used to describe the information obtained when the curtain wall single aluminum plate is inspected during the production process. It mainly includes the following categories: Appearance inspection data: refers to the surface quality data of the aluminum plate collected by visual inspection, camera or sensor, covering the detection of surface defects (scratches, stains, bubbles). This data is crucial to ensure that the appearance of the aluminum plate meets the requirements, especially in projects with high-quality appearance requirements. Dimension inspection data: refers to the data obtained by accurately measuring the size of the aluminum plate at various stages of the production process. This includes important parameters such as the length, width, and thickness of the aluminum plate. Unqualified dimensions directly affect subsequent processing and curtain wall installation, and may cause the curtain wall single aluminum plate to fail to properly cooperate with the installation structure. Physical performance test data: refers to the data obtained by testing the physical properties (hardness, tensile strength, ductility) of aluminum plates through material testing instruments. These data are the basis for ensuring that curtain wall single aluminum plates can be used stably and for a long time in the building environment. For curtain wall single aluminum plates with higher quality requirements, physical performance data plays a decisive role.

[0030] Specifically, based on the processing process data of single aluminum plate for curtain wall, the specific process of analyzing the changes in timing data of single aluminum plate for curtain wall between cutting, bending and spraying is as follows: the processing process data of single aluminum plate for curtain wall is synchronized with timestamps, denoised and standardized; the matching degree of each pair of processes is calculated through the dynamic time warping algorithm, and the aligned process timing data is output; according to the process timing data, the time deviation between processes is analyzed, the time synchronization is calculated, the performance fluctuations between processes are analyzed, and the efficiency matching degree is evaluated.

[0031] In this implementation scheme, timestamp synchronization: Since the data of different processing procedures may come from different equipment or different time points, timestamp synchronization is to ensure that all data are aligned according to a unified time reference. This can avoid analysis errors caused by inconsistent time. The specific approach is to sort the data of each process according to the timestamp and uniformly convert it into relative time, so that the timestamps of each process are aligned on the same time axis. Denoising: In the actual production process, the collected data may contain certain noise or outliers, which may be caused by sensor errors, external interference generated during data collection, etc. Denoising is to eliminate irrelevant interference signals in the data through methods such as filtering and outlier detection to ensure the accuracy of subsequent analysis. Standardization: Different processes and equipment may generate data of different dimensions and different ranges (such as time, speed, temperature, etc.). Standardization is to convert the data into a standardized form (usually zero mean and unit variance) to eliminate the influence of dimensions, so that various types of data can be compared and calculated on the same platform. Dynamic Time Warping (DTW) algorithm: DTW is an algorithm commonly used in time series data analysis, which can calculate the similarity between time series data of different lengths and different time scales. It finds the optimal alignment by minimizing the total distance between data sequences, and then calculates the matching degree of each pair of processes (such as cutting, bending, and spraying). In this process, the DTW algorithm takes into account the time distortion phenomenon (i.e., time misalignment) that may exist between processes at different time points, and outputs the aligned process time series data by optimizing the matching path. The aligned time series data means that after being processed by the DTW algorithm, the data between different processes (such as cutting, bending, and spraying) have been adjusted to the same time axis, which can reflect the correct order and relationship of each process in time. At this point, the time series data of all processes are synchronously aligned, providing an accurate basis for subsequent time deviation analysis and performance fluctuation analysis. Time deviation analysis: After DTW alignment, the time difference between each process can be calculated, which is the time deviation between processes. The goal of time deviation analysis is to detect which time differences between processes are too large, which may lead to instability in the production process or improper process coordination. By comparing the alignment time between different processes, it is possible to identify which links have delays or advances. Time synchronization calculation: In the production process, the execution of each process should be synchronized as much as possible to avoid the delay of one process affecting the subsequent processes. Time synchronization is an indicator to evaluate whether each process is completed as expected in the production process. If the time deviation between processes is small, it means that the time synchronization in the production process is good and the overall efficiency is high.

[0032] Performance fluctuation analysis: In addition to time deviation, performance fluctuation between processes is also a key factor affecting production efficiency and product quality. By analyzing the changes in the operating parameters of each process (such as cutting speed, bending pressure, spray uniformity, etc.) and the time series, it is possible to identify which processes have performance fluctuations during operation. Performance fluctuations may be caused by factors such as equipment failure, improper operation, and process problems. Timely detection of these problems helps to improve the stability of the production process. Efficiency matching evaluation: Efficiency matching refers to whether each process is coordinated and efficiently executed during the production process. By comprehensively analyzing the time synchronization and performance fluctuations of the process, the system can evaluate the efficiency matching of the entire production process. If a process has low efficiency or poor matching with other processes, it may lead to reduced production efficiency or quality problems. Evaluating efficiency matching can help optimize production plans and adjust process sequences to improve overall production efficiency.

[0033] Specifically, the specific process of identifying the time deviation and performance fluctuation between processes and obtaining the process coordination index is as follows: based on the aligned process timing data, the time difference of each pair of processes is calculated to obtain the time deviation value between each process, and the delay or advance between processes is identified; the difference between the processing time of each process and the expected processing time is analyzed to evaluate the performance fluctuation of the process; the time deviation and performance fluctuation are combined, and the comprehensive coordination degree of each process is analyzed through weighted and linear combination to obtain the process coordination index.

[0034] In this implementation scheme, in addition to installing sensors, intelligent equipment and monitoring systems on each process of the production line to collect time data and performance data of each process in real time and obtain the process coordination index, the process coordination index ( )formula: ;in: Indicates The process coordination index of a process. Indicates The time deviation value of each process. Indicates the maximum threshold of process time deviation. Indicates The performance fluctuation value of a process. Indicates the maximum threshold of performance fluctuation. and is a weighting coefficient that determines the relative importance of time deviation and performance fluctuation in comprehensive coordination. is the time difference between each pair of processes. For each process, the time deviation value can be calculated as follows ;in: It is The actual completion time of a process. It is The expected completion time of each process, usually determined by the production scheduling system or production plan. This value can reflect the delay (if the deviation value is greater than zero) or advance (if the deviation value is less than zero) between processes. Large time deviations usually indicate that the process execution is not synchronized enough, which may affect the start time of subsequent processes. Performance fluctuations ( It refers to the difference between the actual performance and the expected performance of each process during execution. For each process, performance fluctuation can be measured by comparing the difference between the actual processing time and the expected processing time of the process: in: It is The actual processing time of each process. It is The expected processing time for a process step is usually a target value set based on process parameters, equipment capabilities or historical data.

[0035] Specifically, based on the quality inspection data of single aluminum panels for curtain walls, the specific process of classifying and regressing the quality indicators of each processing procedure through the decision tree algorithm is as follows: preprocessing the quality inspection data of single aluminum panels for curtain walls, including removing outliers, filling missing values ​​and standardization, and extracting the processing parameters of the processing procedure data; training the model through the decision tree algorithm, taking the quality indicators of each processing procedure as the target variable, and taking the processing parameters as the input features for classification and regression analysis; building a decision tree model based on the training data to judge the quality performance of each processing procedure and predict the quality change trend; for each process, output the quality classification results and regression results to predict the stability or fluctuation of the quality.

[0036] In this implementation scheme, data preprocessing: Removing outliers: By identifying and eliminating extreme data that does not conform to the convention (obviously wrong or illogical values), the accuracy of quality inspection data is ensured. Filling missing values: For some missing quality inspection data, mean filling, median filling or interpolation techniques can be used to fill the gaps to ensure the integrity of the data set. Standardization: In order to avoid the influence of different dimensional data on model training, the quality inspection data and processing parameters need to be standardized so that they can be compared on the same scale. Usually, a standardization method with a mean of zero and a variance of one is used. Feature extraction: Processing parameter extraction: By extracting the key processing parameters of each processing step (such as cutting speed, bending angle, spraying thickness), these parameters are used as input features of the decision tree model. These processing parameters are important factors directly related to quality changes. Decision tree algorithm training: Training model: Use a historical data set containing quality indicators and related processing parameters of different processes to train a decision tree model. The decision tree algorithm splits the data from top to bottom and selects the optimal features for division, thereby establishing a decision rule. The quality index of each processing step is used as the target variable, and the processing parameters are used as input features. The model continuously optimizes the decision tree structure to learn how to predict quality performance based on the parameters. Classification and regression analysis: Decision trees can be used for classification and regression analysis. For the case where the quality index is a discrete variable (qualified / unqualified), a classification decision tree is used; for the case where the quality index is a continuous variable (dimensional error, strength), a regression decision tree is used. Application of decision tree model: Quality performance prediction: Based on the trained decision tree model, the quality performance of each processing step can be predicted. For example, determine whether a certain process will produce quality abnormalities, or predict possible quality fluctuations in future processing. Quality change trend prediction: By analyzing the impact of different processing parameters on quality performance, the model can predict the stability or fluctuation trend of quality, thereby helping to optimize the processing process and avoid quality problems. Output results: For each processing step, the decision tree model will output the quality classification results (qualified / unqualified) and regression results (quality deviation range, error value). These output results will help production managers evaluate the quality stability of each process and take necessary adjustment measures to ensure the quality stability of the processing process.

[0037] Specifically, the specific process of obtaining the quality stability index and identifying and predicting quality fluctuations and abnormal patterns in different processes is as follows: summarize the quality classification results and regression results of each process, calculate the standard deviation and mean of the quality error of each process, quantify the amplitude of quality fluctuations, integrate the quality fluctuations of each process by weighting, and obtain the quality stability index; according to the preset quality stability index threshold, identify the abnormal pattern of quality fluctuations exceeding the preset threshold.

[0038] In this implementation scheme, the quality stability index formula includes: ; ; ; Parameter explanation: Quality stability index is used to measure the quality stability of the entire production process. :No. The weight of a process indicates the influence of the process on the overall quality stability. :No. The number of data points in a process, that is, the number of data points for quality inspection in this process. :No. Process The quality error of each data point. :No. The mean quality error of a process indicates the average error level of the process. :No. The standard deviation of the quality error of a process indicates the degree of fluctuation of the quality error of the process. The total number of processes indicates the total number of all production processes.

[0039] Specifically, the specific process of comprehensive analysis of the process coordination index and the quality stability index is as follows: normalize the process coordination index and the quality stability index; analyze the linear relationship between the normalized process coordination index and the quality stability index through the Pearson correlation coefficient; and evaluate the overall performance of each process based on the result of the Pearson correlation coefficient.

[0040] In this embodiment, normalization processing: The purpose of normalizing the process coordination index and the quality stability index is to standardize these two different indicators to the same range [0,1] so that they are comparable. Since the dimensions and value ranges of the process coordination index and the quality stability index may be different, direct comparison may lead to unfair judgments. Through normalization processing, these differences can be eliminated, making subsequent analysis more scientific and reasonable. Pearson correlation coefficient analysis: The normalized process coordination index and quality stability index will be used for Pearson correlation coefficient analysis. The Pearson correlation coefficient is used to measure the linear relationship between the two indicators, that is, whether they affect each other to a certain extent. The results of the Pearson correlation coefficient will show the correlation strength of the two indicators, with values ​​ranging from -1 to +1. If the correlation coefficient is close to +1, it means that the two indicators have a strong positive correlation, indicating that processes with better coordination often have higher quality stability; if the correlation coefficient is close to -1, it means that there is a negative correlation between the two, and the process with poor coordination may have poor quality stability; if it is close to 0, it means that there is no significant linear relationship between the two. Evaluate the overall performance of each process: Based on the results of the Pearson correlation coefficient, the overall performance of each process can be comprehensively evaluated. If the correlation between the process coordination index and the quality stability index of certain processes is high, it indicates that these processes may be relatively stable during the production process, with better coordination and quality control; on the contrary, if the correlation is low, it may mean that there is an inconsistency between the coordination and quality stability of these processes, and these processes may need further adjustment or optimization. Therefore, by comprehensively analyzing these two indicators, the overall performance of each process can be evaluated, thereby providing a basis for optimizing the production process, adjusting the process sequence, and improving production efficiency.

[0041] Specifically, the specific process of judging whether it is necessary to adjust the order and priority of production processes is as follows: based on the process coordination index and quality stability index, analyze the priority and coordination between processes; for processes whose Pearson correlation coefficient shows a low correlation, evaluate whether there is room for optimization and adjustment; according to the coordination and quality stability of each process, establish priority sorting rules, and give priority to adjusting processes with poor coordination or large quality fluctuations; determine whether it is necessary to adjust the order of production processes, and rearrange the production process according to the priority of the process.

[0042] In this implementation scheme, the priority and coordination between processes are analyzed based on the process coordination index and the quality stability index: Based on the calculated process coordination index and the quality stability index, the priority and coordination between the processes are analyzed. The process coordination index reflects the time synchronization and efficiency matching between the processes, while the quality stability index measures the quality fluctuation of each process. Through these two indicators, it can be preliminarily determined which processes perform well and which processes may have problems of poor coordination or large quality fluctuations. If the coordination index of some processes is low, it means that the time coordination of these processes is not good, which may lead to bottlenecks or waste in the production process. If the quality stability index of some processes is low, it means that the quality fluctuations of these processes are large, which may affect the quality stability of the overall product. For processes with low correlation shown by the Pearson correlation coefficient, evaluate whether there is room for optimization and adjustment: The Pearson correlation coefficient is used to judge the relationship between the process coordination index and the quality stability index. If the Pearson correlation coefficient shows that the correlation between some processes is low, that is, the coordination is poor or the quality fluctuations are large, there may be room for optimization and adjustment. For these processes, it is necessary to further evaluate whether there is the possibility of adjustment, for example: optimize the time coordination between processes and reduce the time difference between processes; improve quality control measures and reduce quality fluctuations. If the process coordination or quality stability can be improved through optimization, these processes can be considered for adjustment. Establish priority sorting rules based on the coordination and quality stability of each process: After analyzing the process coordination and quality stability, establish priority sorting rules based on the performance of each process. Generally speaking, priority is given to those processes with poor coordination or large quality fluctuations. These processes have a greater impact on the overall production efficiency and product quality, so they need to be optimized or adjusted first. The sorting rules are based on the following factors: Poorly coordinated processes: These processes need to be prioritized to adjust the production sequence so that they can better coordinate with other processes to avoid large time differences. Processes with large quality fluctuations: The quality control of these processes needs to be improved, and the priority may need to be adjusted to ensure that these processes are prioritized or improved during the production process to stabilize the overall product quality. Determine whether the order of production processes needs to be adjusted, and rearrange the production process according to the priority of the processes: Finally, according to the priority ranking of each process, determine whether the order of production processes needs to be adjusted. If it is found that there are coordination problems (such as time asynchrony) or large quality fluctuations between some processes, the order of these processes needs to be rearranged to optimize the overall production process. The adjustment process may include: Rearrange the order of processes: Move processes with poor coordination or large quality fluctuations to the front or back of other processes to better match production needs. Adjust process priority: For processes with higher priority, ensure that they receive sufficient resources or time to be processed during the production process.

[0043] See also Figure 2, a collaborative management method for production and processing data of single aluminum panels for curtain walls, comprising the following steps: S1. Collecting production and processing data of single aluminum panels for curtain walls, including processing process data of single aluminum panels for curtain walls and quality inspection data of single aluminum panels for curtain walls; S2. Based on the processing process data of single aluminum panels for curtain walls, the dynamic time warping algorithm is used to analyze the changes in the timing data of single aluminum panels for curtain walls during cutting, bending and spraying, and the time deviation and performance fluctuation between processes are identified, and the process coordination index is obtained to measure the time synchronization and efficiency matching between the processes; S3. Based on the quality inspection data of single aluminum panels for curtain walls, the decision tree algorithm is used to classify and regress the quality indicators of each processing process to obtain a quality stability index to identify and predict quality fluctuations and abnormal patterns in different processes; S4. A comprehensive analysis is conducted on the process coordination index and the quality stability index to determine whether it is necessary to adjust the sequence of production processes and process priority.

[0044] In this implementation plan, S1. Collect production and processing data to provide basic data support for subsequent analysis. S2. Analyze processing process data through dynamic time warping algorithm: Use dynamic time warping (DTW) algorithm to analyze process data, identify time deviations and performance fluctuations between processes such as cutting, bending, and spraying, so as to obtain process coordination index and measure the time synchronization and efficiency matching between different processes. S3. Analyze quality inspection data through decision tree algorithm: Through decision tree algorithm, classify and regress the quality data of each processing process to generate a quality stability index, which is used to evaluate the quality fluctuations and potential abnormal patterns of different processes, and help predict quality problems that may occur in the process. S4. Comprehensively analyze the process coordination index and quality stability index: Comprehensively analyze the obtained process coordination index and quality stability index to determine whether there is a need for process adjustment in the production process, especially whether it is necessary to adjust the order and priority of the process according to coordination and quality stability, so as to optimize the production process and improve production efficiency and product quality.

[0045] In summary, this application has at least the following effects:

[0046] The production and processing data collaborative management system and method of curtain wall single aluminum plate can effectively identify the time deviation and performance fluctuation between processes by analyzing the time synchronization and efficiency between processes through the dynamic time warping algorithm, thereby optimizing the production process, reducing unplanned downtime and delays in production, and improving overall production efficiency. By analyzing the quality inspection data through the decision tree algorithm, it can accurately identify and predict the quality fluctuations and abnormal patterns in each process, help to warn of quality problems in the production process in advance, and thus ensure the stability of product quality. By comprehensively analyzing the process coordination index and the quality stability index, it can scientifically determine whether it is necessary to adjust the order and process priority of the production process, ensure the coordination and smoothness of the production process, and improve the efficiency of resource utilization. It realizes the intelligent monitoring and management of the production and processing process, and can dynamically adjust the production strategy according to real-time data, providing strong support for automated and intelligent production in the manufacturing industry.

[0047] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0048] The present invention is described with reference to flowcharts and / or block diagrams of systems, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0049] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0050] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0051] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0052] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. The production and processing data collaborative management system for curtain wall single aluminum panels is characterized by: It includes the following modules: data acquisition module, abnormality monitoring module, collaborative management module; The data acquisition module is used to collect the production and processing data of the curtain wall single aluminum plate, including the curtain wall single aluminum plate processing process data and the curtain wall single aluminum plate quality inspection data; The abnormality monitoring module includes a processing abnormality monitoring unit and a quality abnormality monitoring unit; The processing abnormality monitoring unit is used to analyze the time series data changes between cutting, bending and spraying of the curtain wall single aluminum plate based on the processing process data of the curtain wall single aluminum plate through a dynamic time warping algorithm, identify the time deviation and performance fluctuation between the processes, and obtain the process coordination index, which is used to measure the time synchronization and efficiency matching between the processes; The quality anomaly monitoring unit is used to classify and regress the quality indicators of each processing process based on the quality inspection data of the curtain wall single aluminum plate through a decision tree algorithm to obtain a quality stability index for identifying and predicting quality fluctuations and abnormal patterns in different processes; The collaborative management module is used to conduct a comprehensive analysis of the process coordination index and the quality stability index to determine whether the sequence and process priority of the production process need to be adjusted.

2. The production and processing data collaborative management system for curtain wall single aluminum panels according to claim 1 is characterized by: The curtain wall single aluminum plate processing process data includes cutting process data, bending process data, spraying process data and process conversion data; The quality inspection data of the curtain wall single aluminum plate includes appearance inspection data, size inspection data, and physical property inspection data.

3. The production and processing data collaborative management system for curtain wall single aluminum panels according to claim 2 is characterized by: Based on the processing data of curtain wall single aluminum plate, the specific process of analyzing the changes in the timing data of curtain wall single aluminum plate between cutting, bending and spraying by dynamic time warping algorithm is as follows: Perform timestamp synchronization, denoising and standardization on the processing data of single aluminum panels for curtain walls; The matching degree of each pair of processes is calculated through the dynamic time warping algorithm, and the aligned process timing data is output; Based on the process timing data, analyze the time deviation between processes, calculate the time synchronization, analyze the performance fluctuations between processes, and evaluate the efficiency matching.

4. The production and processing data collaborative management system for curtain wall single aluminum panels according to claim 3 is characterized by: The specific process of identifying the time deviation and performance fluctuation between processes and obtaining the process coordination index is as follows: Based on the aligned process timing data, the time difference of each pair of processes is calculated to obtain the time deviation value between each process, and the delay or advance between processes is identified; Analyze the difference between the processing time of each process and the expected processing time, and evaluate the performance fluctuation of the process; The time deviation and performance fluctuation are combined, and the comprehensive coordination degree of each process is analyzed through weighted and linear combination to obtain the process coordination index.

5. The production and processing data collaborative management system for curtain wall single aluminum panels according to claim 4 is characterized in that: Based on the quality inspection data of single aluminum panels for curtain walls, the specific process of classification and regression analysis of the quality indicators of each processing step through the decision tree algorithm is as follows: Preprocess the quality inspection data of single aluminum panels for curtain walls, including removing outliers, filling missing values ​​and standardizing, and extracting processing parameters of processing process data; The model is trained by the decision tree algorithm, with the quality index of each processing step as the target variable and the processing parameters as the input features for classification and regression analysis; Build a decision tree model based on training data to determine the quality performance of each processing step and predict the quality change trend; For each process, the quality classification results and regression results are output to predict the stability or fluctuation of quality.

6. The production and processing data collaborative management system for curtain wall single aluminum panels according to claim 5 is characterized by: The specific process of obtaining the quality stability index and identifying and predicting quality fluctuations and abnormal patterns in different processes is as follows: Summarize the quality classification results and regression results of each process, calculate the standard deviation and mean of the quality error of each process, quantify the amplitude of quality fluctuation, integrate the quality fluctuation of each process by weighting, and obtain the quality stability index; According to the preset quality stability index threshold, abnormal patterns where the quality fluctuation exceeds the preset threshold are identified.

7. The production and processing data collaborative management system for curtain wall single aluminum panels according to claim 6 is characterized by: The specific process of comprehensive analysis of process coordination index and quality stability index is as follows: Normalize the process coordination index and quality stability index; The linear relationship between the normalized process coordination index and the quality stability index was analyzed by Pearson's correlation coefficient. The overall performance of each process was evaluated based on the results of the Pearson's correlation coefficient.

8. The production and processing data collaborative management system for curtain wall single aluminum panels according to claim 7 is characterized by: The specific process of determining whether the order and priority of production processes need to be adjusted is as follows: Analyze the priority and coordination between processes based on the process coordination index and quality stability index; For processes with low correlation shown by the Pearson correlation coefficient, evaluate whether there is room for optimization and adjustment; Establish priority sorting rules based on the coordination and quality stability of each process, and give priority to adjusting processes with poor coordination or large quality fluctuations; Determine if the order of production operations needs to be adjusted and rearrange the production process based on the priority of the operations.

9. A method for collaborative management of production and processing data of a single aluminum plate for curtain wall, applied to the collaborative management system for production and processing data of a single aluminum plate for curtain wall according to any one of claims 1 to 8, characterized in that: The following steps are involved: S1. Collect the production and processing data of single aluminum curtain wall panels, including the processing process data of single aluminum curtain wall panels and the quality inspection data of single aluminum curtain wall panels; S2. Based on the processing process data of curtain wall single aluminum plate, the dynamic time warping algorithm is used to analyze the time series data changes between cutting, bending and spraying of curtain wall single aluminum plate, identify the time deviation and performance fluctuation between processes, and obtain the process coordination index to measure the time synchronization and efficiency matching between each process; S3. Based on the quality inspection data of single aluminum panels for curtain walls, the quality indicators of each processing process are classified and regressed through the decision tree algorithm to obtain the quality stability index, which is used to identify and predict quality fluctuations and abnormal patterns in different processes; S4. Conduct a comprehensive analysis of the process coordination index and quality stability index to determine whether the sequence and priority of the production process need to be adjusted.

Images