Intelligent analysis system and method for resistor R paste in resistor manufacturing process

Abstract

The invention relates to an intelligent analysis system and method for a resistor R paste in a resistor manufacturing process, and the system and method achieve the precise control and optimization of the manufacturing process of the resistor R paste (RuO2) through the introduction of an AI intelligent analysis technology, and provide a new thought and method for the production management and quality control of an enterprise. Along with continuous development of the artificial intelligence technology, more innovations can be applied to the field of production and manufacturing in the future, and intelligentization and high efficiency of industrial production are promoted. Meanwhile, the analysis system and method for the resistor R paste in the resistor manufacturing process have the advantages of being automatic, intelligent, real-time and the like, stability analysis efficiency and accuracy of the resistor manufacturing process can be remarkably improved, product waste can be reduced, and production benefits can be improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence, and in particular to an intelligent analysis system and method for resistor R paste in a resistor manufacturing process. Background Art

[0002] A resistor circuit is a circuit composed of a power supply, a resistor, and a wire. Resistors are one of the most basic components in a circuit and are used to limit the flow of current. The stability of resistors has an important influence on the performance and working state of the entire circuit.

[0003] When evaluating the stability of resistors, several aspects are usually considered, including temperature coefficient, long-term stability and age performance. Temperature coefficient refers to the rate of change of resistance value per unit temperature change, which reflects the dependence of resistance on temperature. Long-term stability focuses on whether the resistance value of the resistor will drift significantly during long-term use. Age performance refers to whether the performance of the resistor will decay or degrade after a certain period of use.

[0004] With the continuous development of science and technology, the research on resistor stability has also made a lot of progress. The research and development of new materials, such as nanomaterials, dielectric materials, magnetic materials, etc., have good resistance stability and provide new ideas for the design of new electronic devices. The application of nanotechnology in resistor stability can effectively improve the stability of resistor materials. In addition, with the development of computer technology, various simulation software has also emerged, which can help researchers conduct resistor stability research more conveniently and accurately.

[0005] In the manufacturing process of resistors, resistor R paste (RuO2) is an important component. The resistor paste determines the resistance value. In the manufacturing process, the resistor R paste (RuO2) needs to be sintered to form the final resistor. Therefore, by studying and analyzing the resistor R paste (RuO2) during the resistor manufacturing process, we can better understand and optimize the performance of resistors and improve the stability and reliability of electronic equipment. Summary of the invention

[0006] The purpose of the present invention is to provide an intelligent analysis system and method for resistor R paste in the resistor manufacturing process, aiming to effectively analyze the causes of resistor quality deviation in the resistor manufacturing process through intelligent means, improve product yield and reduce product waste.

[0007] In order to achieve the above-mentioned purpose, the present invention provides an intelligent analysis system for resistor R paste in the resistor process, including a data acquisition module, a data preprocessing module, a correlation analysis system, a feature engineering module, a model building module and a cross-validation module, wherein the data acquisition module is used to collect relevant data of the resistor process; the data preprocessing module performs preprocessing operations on the collected data; the correlation analysis system analyzes the preprocessed data, explores the correlation between each process section and the quality data, and then selects attributes with a greater correlation with the results as important features for modeling; the feature engineering module factors the data, transforms the data, and performs feature selection according to the selected model requirements; the model building module selects a suitable model to build based on the results of the correlation analysis system and the feature engineering module, which is used to predict the instability causes of the finished resistor product; the cross-validation module cross-validates the constructed model to evaluate the prediction performance of the model.

[0008] Furthermore, the data acquisition module collects relevant data of the resistor process from multiple links, and the preprocessing includes but is not limited to cleaning the data, filling missing values, standardizing or normalizing the data.

[0009] A method for intelligently analyzing the resistor R paste in the resistor manufacturing process using the above-mentioned intelligent analysis system for the resistor R paste in the resistor manufacturing process comprises the following steps:

[0010] 1. Data collection and collation;

[0011] 2. AI model establishment and training;

[0012] 3. AI intelligent analysis and optimization.

[0013] Furthermore, in step 1, the collected data includes:

[0014] (1) People: record the operator’s skill level, work experience and other information, monitor the operation process in real time, and collect operation data;

[0015] (2) Machine: record the operating status, maintenance records and fault conditions of equipment such as printing machines and sintering furnaces to ensure the normal operation of the equipment;

[0016] (3) Materials: Record in detail the type, proportion, thawing and stirring, and use time of R paste (RuO2) to ensure the stability of raw material quality;

[0017] (4) Method: Record the process parameters of the resistor layer printing, drying, high temperature sintering, etc., such as temperature, time, speed, etc., to ensure process stability;

[0018] (5) Environment: Record the temperature, humidity, cleanliness and other parameters of the production environment to ensure the stability of the production environment;

[0019] (6) Test: Record the test data of external inspection machines and charter machines to ensure the accuracy of yield assessment;

[0020] (7) Customer Complaints: Record customer complaint types and quantities to improve product quality and prevent potential problems.

[0021] Further, in step 2, the following steps are included

[0022] (1) Data preprocessing: preprocess the collected data to ensure data quality;

[0023] (2) Feature selection: Based on the characteristics of the resistor R paste (RuO2) process, the features with greater correlation are selected as model input;

[0024] (3) Model building: Select appropriate machine learning algorithms, such as neural networks and decision trees, to build AI prediction models;

[0025] (4) Model training: Use historical data to train the model, optimize model parameters, and improve prediction accuracy.

[0026] Furthermore, step 3 includes the following steps:

[0027] (1) Predictive analysis: Use the trained AI model to perform predictive analysis on real-time collected production data to determine whether the quality of the finished product is stable;

[0028] (2) Cause location: If the prediction results show that the quality of the finished product is unstable, the AI ​​model is used to analyze the impact of various factors on the quality of the finished product and locate the key factors that lead to unstable quality;

[0029] (3) Optimization and adjustment: Based on the analysis results of the AI ​​model, the factors such as people, machines, materials, methods, environment, measurement, and customer complaints in the production process are optimized and adjusted to improve the quality stability of the finished product.

[0030] The invention provides an intelligent analysis system and method for resistor R paste in a resistor manufacturing process, which has the advantages of:

[0031] The present invention realizes the precise control and optimization of the resistor R paste (RuO2) process by introducing AI intelligent analysis technology, and provides new ideas and methods for the production management and quality control of enterprises. With the continuous development of artificial intelligence technology, it is believed that there will be more innovative applications in the field of production and manufacturing in the future to promote the intelligent and efficient industrial production. At the same time, the analysis system and method of the resistor R paste in the resistor process of the present invention has the characteristics of automation, intelligence, and real-time performance, which can significantly improve the stability analysis efficiency and accuracy of the resistor process, help reduce product waste, and improve production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to make the contents of the present invention more clearly understood, the present invention is further described in detail below based on specific embodiments of the present invention in conjunction with the accompanying drawings.

[0033] Figure 1 It is a flow chart of the intelligent analysis method described in the present invention. DETAILED DESCRIPTION

[0034] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments so that those skilled in the art can better understand the present invention and implement it, but the embodiments are not intended to limit the present invention.

[0035] Combination Figure 1 The present application provides an intelligent analysis system for resistor R paste in the resistor manufacturing process, including a data acquisition module, a data preprocessing module, a correlation analysis system, a feature engineering module, a model building module and a cross-validation module.

[0036] The data acquisition module is used to collect relevant data of the resistor process from multiple links, including production data of each process section and yield rate comparison records;

[0037] The data preprocessing module performs preprocessing operations on the collected data, including but not limited to data cleaning, filling missing values, and standardizing or normalizing the data;

[0038] The correlation analysis system analyzes the pre-processed data, explores the correlation between each process section and quality data, and then selects the attributes with greater correlation with the results as important features for modeling;

[0039] The feature engineering module processes the data including but not limited to factorization, data transformation, and feature selection according to the selected model requirements;

[0040] The model building module selects a suitable model for building based on the results of the correlation analysis system and the feature engineering module, so as to predict the instability reasons of the finished resistor product;

[0041] The cross-validation module performs cross-validation on the constructed model to evaluate the prediction performance of the model.

[0042] At the same time, this embodiment also provides an intelligent analysis method for resistor R paste in a resistor manufacturing process, comprising the following steps:

[0043] 1. Data collection and collation;

[0044] 2. AI model establishment and training;

[0045] 3. AI intelligent analysis and optimization.

[0046] Among them, in step 1, data collection and sorting are performed through the data collection module, specifically including collecting the following data:

[0047] (1) People: record the operator’s skill level, work experience and other information, monitor the operation process in real time, and collect operation data;

[0048] (2) Machine: record the operating status, maintenance records and fault conditions of equipment such as printing machines and sintering furnaces to ensure the normal operation of the equipment;

[0049] (3) Materials: Record in detail the type, proportion, thawing and stirring, and use time of R paste (RuO2) to ensure the stability of raw material quality;

[0050] (4) Method: Record the process parameters of the resistor layer printing, drying, high temperature sintering, etc., such as temperature, time, speed, etc., to ensure process stability;

[0051] (5) Environment: Record the temperature, humidity, cleanliness and other parameters of the production environment to ensure the stability of the production environment;

[0052] (6) Test: Record the test data of external inspection machines and charter machines to ensure the accuracy of yield assessment;

[0053] (7) Customer Complaints: Record customer complaint types and quantities to improve product quality and prevent potential problems.

[0054] Step 2 includes the following steps:

[0055] (1) Preprocessing the data collected in step 1 through a data preprocessing module: preprocessing the collected data to ensure data quality;

[0056] (2) Feature selection through correlation analysis module: According to the characteristics of the resistor R paste (RuO2) process, the correlation between each process section of the resistor R paste (RuO2) and the quality data of the resistor R paste (RuO2) is explored, and then the features with greater correlation are selected as model input;

[0057] (3) Model building by building modules: Select appropriate machine learning algorithms, such as neural networks and decision trees, to build AI prediction models;

[0058] (4) Model training: Use historical data to train the model, optimize model parameters, and improve prediction accuracy.

[0059] Step 3 includes the following steps:

[0060] (1) Predictive analysis: Use the trained AI model to perform predictive analysis on real-time collected production data to determine whether the quality of the finished product is stable;

[0061] (2) Cause location: If the prediction results show that the quality of the finished product is unstable, the AI ​​model is used to analyze the impact of various factors on the quality of the finished product and locate the key factors that lead to unstable quality;

[0062] (3) Optimization and adjustment: Based on the analysis results of the AI ​​model, the factors such as people, machines, materials, methods, environment, measurement, and customer complaints in the production process are optimized and adjusted to improve the quality stability of the finished product.

[0063] In the description of the embodiments of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "setting" and "connection" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0064] Obviously, the above embodiments are merely examples for clear explanation and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived from these are still within the protection scope of the invention.

Claims

1. An intelligent analysis system for resistor R paste in the resistor manufacturing process, characterized by: It includes a data acquisition module, a data preprocessing module, a correlation analysis system, a feature engineering module, a model building module and a cross-validation module, wherein the data acquisition module is used to collect relevant data of the resistor process; the data preprocessing module performs preprocessing operations on the collected data; the correlation analysis system analyzes the preprocessed data, explores the correlation between each process section and the quality data, and then selects the attributes with greater correlation with the results as important features for modeling; the feature engineering module factors the data, transforms the data, and performs feature selection according to the requirements of the selected model; the model building module selects a suitable model to be built based on the results of the correlation analysis system and the feature engineering module, and is used to predict the causes of instability of the finished resistor product; the cross-validation module cross-validates the constructed model and evaluates the prediction performance of the model.

2. The intelligent analysis system for resistor R paste in the resistor manufacturing process according to claim 1, characterized in that: The data acquisition module is used to collect relevant data of the resistor process from multiple links, and the preprocessing includes cleaning the data, filling missing values, and standardizing or normalizing the data.

3. A method for intelligently analyzing resistor R paste in a resistor manufacturing process using the intelligent analysis system for resistor R paste in a resistor manufacturing process as claimed in any one of claims 1 to 2, comprising the following steps: 1) Data collection and collation; 2) AI model establishment and training; 3) AI intelligent analysis and optimization.

4. The intelligent analysis method of resistor R paste in a resistor manufacturing process according to claim 3, characterized in that: In step 1, collect the following data: (1) People: record the operator’s skill level, work experience and other information, monitor the operation process in real time, and collect operation data; (2) Machine: record the operating status, maintenance records and fault conditions of equipment such as printing machines and sintering furnaces to ensure the normal operation of the equipment; (3) Materials: Record in detail the type, proportion, thawing and stirring, and use time of R paste (RuO2) to ensure the stability of raw material quality; (4) Method: Record the process parameters of the resistor layer printing, drying, high temperature sintering, etc., such as temperature, time, speed, etc., to ensure process stability; (5) Environment: Record the temperature, humidity, cleanliness and other parameters of the production environment to ensure the stability of the production environment; (6) Test: Record the test data of external inspection machines and charter machines to ensure the accuracy of yield assessment; (7) Customer Complaints: Record customer complaint types and quantities to improve product quality and prevent potential problems.

5. The intelligent analysis method of resistor R paste in a resistor manufacturing process according to claim 3, characterized in that: In step 2, the following steps are included: (1) Data preprocessing: preprocess the collected data to ensure data quality; (2) Feature selection: Based on the characteristics of the resistor R paste (RuO2) process, the features with greater correlation are selected as model input; (3) Model building: Select appropriate machine learning algorithms, such as neural networks and decision trees, to build AI prediction models; (4) Model training: Use historical data to train the model, optimize model parameters, and improve prediction accuracy.

6. The intelligent analysis method of resistor R paste in a resistor manufacturing process according to claim 3, characterized in that: Step 3 includes the following steps: (1) Predictive analysis: Use the trained AI model to perform predictive analysis on real-time collected production data to determine whether the quality of the finished product is stable; (2) Cause location: If the prediction results show that the quality of the finished product is unstable, the AI ​​model is used to analyze the impact of various factors on the quality of the finished product and locate the key factors that lead to unstable quality; (3) Optimization and adjustment: Based on the analysis results of the AI ​​model, the factors such as people, machines, materials, methods, environment, measurement, and customer complaints in the production process are optimized and adjusted to improve the quality stability of the finished product.

Images