Gearbox shell production process intelligent management and control method based on online data perception

Abstract

The application discloses a gearbox shell production process intelligent management and control method based on online data sensing, comprising the following steps: firstly, collecting online data in the production process and transmitting to a data processing module; the data processing module optimizes, converts, stores and the like to the collected data, and stores the processed data; then, analyzing the data, and identifying key factors affecting production efficiency and product quality; based on historical data, an analysis model module is constructed, and an optimal production plan is automatically generated according to order requirements and real-time production data; finally, a job scheduling module automatically generates job instructions according to the production plan, and real-time monitors job execution, and dynamically adjusts the job scheduling scheme.The application makes the production process more smooth, improves production efficiency and resource utilization, and effectively supports the intelligentization of production process management and control.

Description

Technical Field

[0001] This invention relates to the field of intelligent management technology for production processes, specifically to an intelligent control method for the machining process of a gearbox housing based on online data sensing. Background Technology

[0002] As a critical component of the transmission, the machining precision and quality of the transmission housing directly affect the transmission's performance and reliability. In traditional production processes, production scheduling and dispatching primarily rely on manual operation. Manual scheduling and dispatching present numerous problems. For example, the formulation and adjustment of production plans depend on human experience, making it difficult to quickly respond to changes in market demand and fluctuations in equipment status, resulting in low production efficiency. Data generated during production is scattered across various systems, lacking effective integration and analysis, making real-time monitoring and prediction of the production process difficult, and hindering the timely detection and resolution of problems, leading to unstable product quality. Relying on manual experience to adjust machining parameters makes it difficult to optimize the production process and improve efficiency.

[0003] Utilizing big data technology to process and analyze online data during the production process can uncover the potential value behind the data, providing stronger support for production decisions. Therefore, researching an intelligent control method for the gearbox housing production process based on online data perception has significant practical implications. The development of advanced technologies such as the Industrial Internet of Things, big data, and artificial intelligence has made intelligent control of the production process possible. By collecting production process data in real time and using big data analysis and intelligent algorithms for processing and decision-making, the accuracy and timeliness of production control can be effectively improved, ensuring high-quality and high-efficiency production of gearbox housings. Summary of the Invention

[0004] To address the problems of low production efficiency, lack of collaboration, and uncontrollable processing in traditional production processes, this invention provides an intelligent control method and system for the machining process of gearbox housings based on online data sensing, thereby achieving intelligent control of the production process.

[0005] 1. Online Data Processing Based on Big Data Technology: By deploying various sensors and data acquisition devices on the production line, multi-source online data, including equipment operation data, material data, and personnel data, are collected in real time during the production process. This data is collected at a certain frequency in real time and rapidly transmitted to the big data processing platform via wired or wireless transmission. Data optimization algorithms are used to denoise, deduplicate, and correct errors in the raw data. Subsequently, data mining techniques, such as association rule mining algorithms, are employed to deeply analyze the inherent relationships between data, uncover potential correlations and patterns, and provide data support for subsequent production decisions.

[0006] 2. Establish Relationship Analysis Models and Production Performance Indicator Sets: Based on big data analysis results, establish relationship analysis models for various factors in the production process, such as the relationship between equipment operating status and product quality, and the relationship between material supply and production progress. Simultaneously, construct a comprehensive and targeted set of production performance indicators, covering key indicators such as production efficiency, product qualification rate, equipment utilization rate, and production cost. Through real-time calculation and analysis of these indicators, the operational status of the production process can be comprehensively and accurately assessed, providing quantitative basis for production process evaluation and optimization.

[0007] 3. Design a multi-objective, multi-constraint production plan evaluation method: This method comprehensively considers multiple important objectives in the production process, such as maximizing production efficiency, minimizing production costs, ensuring product quality meets standards, and delivering orders on time. Simultaneously, it fully considers various constraints, including equipment capacity limitations, tool lifespan and replacement cycles, the timeliness and quantity limitations of raw material supply, and personnel working hours and skill levels. Using mathematical methods such as the Analytic Hierarchy Process (AHP) and fuzzy comprehensive evaluation, different production plan schemes are evaluated and ranked to select the optimal production plan.

[0008] 4. Constructing an Autonomous Production Scheduling Model: Utilizing the particle swarm optimization algorithm, an autonomous production scheduling model is constructed. This model takes production orders, production resources, and production processes as inputs and automatically generates detailed production plans, including the allocation of production tasks, the arrangement of production time, and the scheduling of equipment. Furthermore, the model can dynamically adjust the production plan based on real-time production data and changes, achieving adaptive optimization of the production plan.

[0009] 5. Achieve Coordinated Optimization of Production Planning and Job Scheduling: Organically integrate production planning and job scheduling by establishing a coordinated optimization mechanism to ensure mutual coordination and promotion between the two. During production, adjust job scheduling plans promptly based on actual production progress and unforeseen circumstances to ensure the smooth execution of the production plan. Simultaneously, feedback information from job scheduling can provide a basis for optimizing the production plan, achieving a positive interaction between production planning and job scheduling.

[0010] The beneficial effects of this invention are: Compared with existing technologies, this technology has the following advantages: (1) By using big data technology to process and analyze online data in the production process, it is possible to grasp various information in the production process in a timely and accurate manner, providing a scientific basis for production decision-making and effectively solving the problems of untimely and inaccurate information in traditional production scheduling and dispatching. Data optimization and preprocessing technology ensures the quality of data, lays a solid foundation for subsequent data analysis and model building, and improves the reliability and accuracy of analysis results.

[0011] (2) By establishing a relationship analysis model and a set of production performance indicators, we can gain a deeper understanding of the interrelationships between various factors in the production process and the operation status of the production process, which provides strong support for the optimization of the production process.

[0012] (3) The multi-objective and multi-constraint plan evaluation method designed takes into account multiple objectives and constraints in the production process, and can screen out the optimal production plan, thereby improving the scientificity and rationality of the production plan.

[0013] (4) The autonomous production scheduling model constructed realizes the automatic generation and dynamic adjustment of production plans, greatly reduces manual intervention, improves the efficiency and accuracy of production scheduling, and reduces production costs.

[0014] (5) It realizes the coordinated optimization of production planning and operation scheduling, making the production process smoother, improving production efficiency and resource utilization, and effectively supporting the intelligent management and control of the production process. Attached Figure Description

[0015] Figure 1 This is a flowchart of data processing and analysis.

[0016] Figure 2 This is a flowchart of the project evaluation method.

[0017] Figure 3 This is a flowchart of the particle swarm optimization algorithm for the autonomous production scheduling model.

[0018] Figure 4 A flowchart for production planning and job scheduling.

[0019] Figure 5 The attached figure is for the abstract. Detailed Implementation

[0020] To more clearly illustrate the technical problems, technical solutions, and advantages of this invention, the technical solutions of this invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0021] The intelligent control system includes the following modules: The data acquisition module collects online data during the production process in real time and transmits it to the data processing module.

[0022] The data processing module optimizes, transforms, and stores the collected data, and then stores the processed data in a data warehouse. Data is extracted from the data warehouse to analyze key indicators in the production process and identify critical factors affecting production efficiency and product quality.

[0023] The analysis model building module, based on historical data and expert experience, establishes a relationship analysis model, a set of production performance indicators, and a multi-objective, multi-constraint plan evaluation method.

[0024] The autonomous production scheduling module automatically generates the optimal production plan based on real-time production data and market demand, using relationship analysis models, production performance index sets, and multi-objective, multi-constraint planning evaluation methods.

[0025] The job scheduling module automatically generates job instructions based on the production plan, monitors job execution in real time, and dynamically adjusts the job scheduling scheme.

[0026] 1. Data Acquisition: Various sensors are deployed on the production site according to the design plan to collect data in real time, including equipment operating parameters, material flow information, and product processing status. After sensor installation, calibration and debugging are performed to ensure the accuracy of the collected data. The data acquisition program collects sensor data periodically according to the set sampling frequency and transmits it to the big data processing platform via wired or wireless means.

[0027] 2. Data Optimization and Preprocessing: Data optimization and preprocessing are performed on a big data processing platform. First, the 3σ criterion based on statistics is used to detect outliers in the vibration data. Data exceeding three times the standard deviation of the mean are considered outliers and corrected or removed. Then, the Min-Max normalization method is used to standardize the data, with the following formula: Where X represents the original data, X min and X max X represents the minimum and maximum values ​​of the data column, respectively. norm This is the normalized data. The processed data is stored in a database for subsequent analysis.

[0028] 3. Relationship Analysis Model and Indicator Set Construction: Historical production data is extracted from the database, and association rule mining algorithms are used to analyze the relationship between equipment operating parameters and product quality, establishing a relationship analysis model. Association rules reflect the interdependencies between an object and other objects. For example, it may be found that when the temperature of a certain piece of equipment is within a certain range, the product pass rate is higher. In association rules, the support of a data item set X, support(x), is the ratio of the number of transactions containing X in the basic dataset D to the total number of transactions in D, as shown in the formula: The support formula for association rule X>=Y is: The confidence level of rule X>=Y represents the probability that transactions in D containing X also contain Y. It represents the strength of the certainty of this rule, denoted as confidence(X>=Y). Users can specify the maximum confidence threshold according to their needs. The confidence level formula is: Simultaneously, based on the needs of production management, a production performance index calculation module was developed within the production management system. This module defines a set of production performance indicators and calculates indicators such as production efficiency, processing quality, and equipment utilization rate in real time. For example, production efficiency = actual output / planned output × 100%, and product qualification rate = number of qualified products / total number of products × 100%. Furthermore, programs were written to perform real-time calculations and statistics on these indicators, allowing production managers to intuitively understand the operational status of the production process.

[0029] 4. Implementation of the Planning Evaluation Method: For a single production order, multiple different production planning schemes are developed. The Analytic Hierarchy Process (AHP) is used to determine the weights of objectives such as production efficiency, production cost, product quality, and delivery time. The core of the AHP is to calculate the weights of each factor by constructing a judgment matrix. First, the judgment matrix A = [a...] is constructed. ij ], where a ij This indicates the importance of factor i relative to j. Then, the geometric mean of each row's elements is calculated using the following formula: Normalization process: Calculate the largest eigenvalue of the judgment matrix and its corresponding eigenvector V. The formula for normalizing the eigenvector is: Finally, the comprehensive evaluation score of all the plans is calculated, and the plan with the highest score is selected as the optimal production plan by comparing the scores.

[0030] 5. Model Training and Application: Collect past production data, including processing parameters, equipment operation data, and processing quality inspection data. Use the particle swarm optimization algorithm to train the autonomous scheduling model. Set algorithm parameters and conduct multiple iterations of training to enable the model to automatically generate reasonable production plans based on the input production information.

[0031] Particle swarm optimization (PSO) simulates the social behavior of biological groups such as flocks of birds or schools of fish, finding optimal solutions through information sharing and cooperation among individuals. The algorithm first initializes the positions and velocities of the particles, calculates the fitness value of each particle, and records the individual optimal and the global optimal. Then, for each particle, its velocity and position are updated using the following formula: w is the inertia weight, c1 and c2 are learning factors, and r1 and r2 are random numbers between [0,1]. The algorithm terminates when the maximum number of iterations is reached or the fitness value meets the requirements. When a new production order is placed, the order information, production resource status, etc., are input into the trained autonomous scheduling model. The model outputs a detailed production plan, including the equipment, personnel, and production time arrangements for each production task.

[0032] 6. Dynamic Optimization and Scheduling of Production Process: During production execution, the production management system monitors production progress in real time. When a machine malfunctions, potentially impacting the production plan, the job scheduling module immediately adjusts the scheduling plan based on the machine malfunction and the priority of current production tasks, such as transferring affected tasks to other available equipment. Simultaneously, the adjusted scheduling information is fed back to the production planning module, which adjusts the production plan accordingly, such as rearranging the timing and sequence of production tasks. This collaborative optimization mechanism effectively addresses various unforeseen circumstances during production, ensuring continuity and efficiency.

Claims

1. A method for intelligent control of the gearbox housing production process based on online data sensing, characterized in that, Includes the following steps: Online data sensing and acquisition: Utilizing sensors and IoT technology to collect data such as equipment status, material information, and environmental parameters in real time during the production process; Data preprocessing and feature extraction: The collected raw data is optimized and normalized, and key features are extracted; Relationship analysis model construction: Based on big data technology, analyze the relationships between various elements in the production process and construct a set of production performance indicators; Design of a multi-objective, multi-constraint plan evaluation method: Taking into account multiple objectives such as production efficiency, cost, and quality, as well as multiple constraints such as equipment capacity and material supply, a plan evaluation method is designed. Autonomous production scheduling model construction: Based on relationship analysis model and planning evaluation method, an autonomous production scheduling model is constructed to realize the automatic generation and optimization of production plan; Production planning and job scheduling collaborative optimization: Integrate production planning and job scheduling systems to achieve collaborative optimization of production planning and job scheduling.

2. The intelligent control technology for production processes based on online data sensing according to claim 1, characterized in that, In the online data sensing and acquisition step, sensors and other devices are used to collect data such as equipment status, material information, and environmental parameters on the production line in real time, and transmit them to the data platform.

3. The intelligent control technology for production processes based on online data sensing according to claim 1, characterized in that, In the data preprocessing and feature extraction steps, the original data is optimized and normalized, and key features such as equipment fault features and product quality features are extracted.

4. The intelligent control technology for production processes based on online data sensing according to claim 1, characterized in that, In the relationship analysis model construction step, big data analysis technology is used to analyze the correlation between factors such as equipment status and product quality, material supply and production efficiency, and to construct a set of production performance indicators such as production efficiency, equipment utilization rate and product quality.

5. The intelligent control technology for production processes based on online data sensing according to claim 1, characterized in that, In the design steps of the multi-objective, multi-constraint program evaluation method, a weighted scoring method is adopted to comprehensively consider multiple objectives such as production efficiency, cost, and quality, as well as multiple constraints such as equipment capacity and material supply.

6. The intelligent control technology for production processes based on online data sensing according to claim 1, characterized in that, In the process of constructing the autonomous production scheduling model, the particle swarm optimization algorithm is used, based on the relationship analysis model and the plan evaluation method, to realize the automatic generation and optimization of the production plan.

7. The intelligent control technology for production processes based on online data sensing according to claim 1, characterized in that, In the production planning and job scheduling collaborative optimization step, the production plan is dynamically adjusted according to the real-time production situation, and the equipment scheduling scheme is optimized to achieve collaborative optimization of production planning and job scheduling.

Images