Method for detecting and grading crystal bar quality based on MES system data and control system

Abstract

The invention discloses a method for detecting and grading crystal bar quality based on MES system data and a control system. Traditional crystal bar quality detection depends on a special detector and has the problems of tedious process, easiness in environmental interference, insufficient precision and the like, so that the production efficiency is low, the cost is high and the grading is inaccurate. The system is composed of a flat grinding machine, a data transmission module and an MES system. The flat grinding machine collects processing data and binds a crystal bar identifier, the data transmission module encrypts transmission data, and the MES system performs data cleaning, feature extraction, quality grading and data storage management. The method comprises the steps of data acquisition binding, transmission, processing extraction, quality grading and storage management. Through communication between the MES system and the flat grinding machine, processing data is directly acquired as a grading basis, so that the production efficiency is improved, the cost is reduced, the quality grading accuracy and the system traceability are enhanced, and the method is suitable for the crystal bar production industry.

Description

Technical Field

[0001] The present invention relates to the field of ingot production and manufacturing, and particularly to an innovative method for detecting and grading the quality of ingots based on the data of the Manufacturing Execution System (MES) and a supporting control system. Background Art

[0002] In the industrial chain of ingot production, the quality inspection and grading link plays a crucial role in product quality control and enterprise economic benefits. At present, the commonly used detection method in the industry is to use a dedicated detector to detect each ingot one by one after surface grinding. This traditional detection process is extremely cumbersome, and each detection requires multiple complex steps. Before detection, the operator not only has to spend time preheating and calibrating the detector, but also carefully clamp the ingot onto the equipment and precisely adjust the position and posture to ensure the detection accuracy. During detection, the detector measures parameters such as the length, diameter, roundness, and surface roughness of the ingot one by one according to a preset program. The whole process is slow and labor-consuming. After detection, it is also necessary to manually record and analyze the data to determine the quality grade of the ingot. In the scenario of large-scale production, such a long detection process seriously slows down the production rhythm, making the detection link a key factor restricting the improvement of production efficiency.

[0003] Looking at the detection equipment itself, there are many problems that cannot be ignored. The detector has strict requirements for the working environment, and even minor changes in the external environment may have a significant impact on the detection accuracy. Temperature fluctuations in the workshop can cause the components of the detector to expand and contract thermally, thereby changing the internal mechanical structure and optical performance of the equipment, and ultimately resulting in measurement errors; changes in humidity may cause the internal electronic components of the equipment to get damp, resulting in abnormal signal transmission and affecting the accuracy of the data; and the vibrations generated by the operation of various equipment in the production workshop will also interfere with the normal operation of the detector and cause errors in the measurement results. In addition, the internal structure of the detector is precise and complex, containing a large number of optical, mechanical, and electronic components. These components are extremely prone to wear and aging during long-term use and require regular maintenance by professional technicians. However, the maintenance work of the detector is difficult and costly. Once a failure occurs, the repair cycle is often long, which not only increases the equipment maintenance cost of the enterprise but also brings huge economic losses to the enterprise due to production stagnation.

[0004] It should be noted that there is an obvious contradiction between the detection accuracy of the detector and the processing accuracy of the surface grinder. With the continuous progress of manufacturing technology, when the surface grinder processes the ingot, it can reach a high precision level, effectively ensuring that the size, shape, etc. of the ingot meet strict requirements. However, during the detection process of the detector, due to the interference of environmental factors and the limitation of its own accuracy, its detection results cannot accurately reflect the actual quality status of the ingot. For example, when detecting the surface roughness of the ingot, the detector may not be able to accurately capture the microscopic rough texture changes on the ingot surface due to insufficient sensor resolution or limitations of the measurement method; when measuring the diameter of the ingot, there may also be a deviation between the measurement result and the actual value due to limitations in the selection of measurement points or equipment calibration errors. This difference in detection accuracy makes the quality grading of the ingot based on the detector's detection results inaccurate, easily misjudging ingots with excellent actual quality as lower grades, resulting in waste of resources; or misjudging ingots with potential quality problems as qualified and flowing into subsequent production links, posing a hidden danger to the quality of end products.

[0005] With the rapid development of industries such as semiconductors and photovoltaics, the market's requirements for the quality of ingots are becoming increasingly strict. The traditional detection mode relying on detectors has difficulty meeting the comprehensive needs of enterprises in terms of production efficiency, cost control, and quality improvement. Therefore, it is urgent to develop a high-efficiency, accurate, and low-cost ingot quality detection and grading technology. Summary of the Invention

[0006] The core objective of the present invention is to construct a method and control system for detecting and grading the quality of ingots based on MES system data. By realizing the efficient communication between the MES system and the surface grinder, directly obtaining the ingot information during the processing of the surface grinder and binding quality parameters, the MES system extracts and analyzes the data, which is used as the basis for ingot grading, thereby improving production efficiency, reducing costs, and enhancing the accuracy and reliability of ingot quality grading.

[0007] In the first aspect, an embodiment of the present invention provides a control system for detecting and grading the quality of ingots based on MES system data, including:

[0008] A surface grinder module, equipped with a mechanical structure for processing ingots, and installed with a variety of high-precision sensors such as displacement sensors, force sensors, and speed sensors, used to collect data such as the size, grinding force, and grinding speed during the ingot processing in real time. It also has a data acquisition device for binding the collected data with the unique identifier of the ingot;

[0009] A data transmission module, using wired or wireless communication technology, encrypts the data bound by the surface grinder module and adds a check code, and transmits the data stably and accurately to the MES system. If the MES system fails to pass the data verification, it can request the surface grinder module to resend;

[0010] The MES system module includes a data cleaning unit for removing abnormal data points in the received data by using algorithms such as filtering; a feature extraction unit for extracting feature parameters related to the quality of the ingot, such as dimensional deviation, surface roughness related parameters, and machining process stability indicators, from the cleaned data; a quality grading unit for grading the ingot according to the extracted feature parameters according to the preset quality grading rules; and a data storage and management unit for rebinding the ingot quality grade information with the unique identifier of the ingot and storing it in the database, and at the same time classifying and managing the data.

[0011] In some embodiments of the present invention, the sensors of the above-mentioned surface grinder module continuously collect data according to a preset sampling frequency, and the data acquisition device performs preliminary processing on the data and then binds it with the unique identifier of the ingot.

[0012] In some embodiments of the present invention, the above-mentioned data transmission module encrypts the data by using a symmetric encryption algorithm to ensure the security of data transmission.

[0013] In some embodiments of the present invention, the data cleaning unit of the above-mentioned MES system module uses a median filtering algorithm to remove outliers in the data.

[0014] In some embodiments of the present invention, the feature extraction unit of the above-mentioned MES system module uses a principal component analysis algorithm to extract the main feature parameters in the data.

[0015] In some embodiments of the present invention, the above-mentioned quality grading rules of the MES system module are dynamically adjusted according to different application scenarios and quality standards of the ingot.

[0016] Furthermore, the above system specifically includes the following modules:

[0017] Surface grinder module

[0018] The surface grinder is a basic device for ingot processing. Its core function is to perform surface grinding on the ingot to make it meet the specified dimensional and surface quality requirements. In the present invention, the surface grinder also undertakes the important task of data collection. It is equipped with a variety of high-precision sensors, including displacement sensors, force sensors, speed sensors, etc. The displacement sensor is used to monitor the dimensional changes of the ingot during the grinding process in real time, the force sensor measures the magnitude of the grinding force, and the speed sensor obtains information such as the grinding speed. These sensors continuously collect data according to a preset sampling frequency to ensure that they can comprehensively and accurately reflect the processing state of the ingot. At the same time, the data acquisition device on the surface grinder is responsible for collecting the data collected by the sensors and binding it with the unique identifier of the ingot (such as batch number, serial number, etc.) to prepare for subsequent data transmission and processing.

[0019] Data transmission module

[0020] The data transmission module is the bridge between the flat grinder and the MES system. Its main function is to accurately and stably transmit the data collected and bound by the flat grinder to the MES system. It supports both wired and wireless communication modes, and enterprises can choose according to the actual production environment and needs. During the data transmission process, the module uses advanced encryption technology to encrypt the data to prevent the data from being stolen or tampered with during the transmission process. At the same time, information such as checksums are added to ensure the integrity of the data. If data is lost or wrong during the transmission process, the MES system can find the problem through the verification mechanism and require the flat grinder to resend the data to ensure the reliability of data transmission.

[0021] MES system module

[0022] The MES system is the core of the entire control system, with multiple functions such as data processing, storage, analysis and management. After receiving data from the data transmission module, it will perform a series of processing operations.

[0023] Data cleaning unit: This unit uses a specific algorithm to clean the received data and remove abnormal data points caused by sensor noise, electrical interference, etc. For example, a filtering algorithm is used to smooth the data and remove data values ​​that are beyond the normal range to ensure the quality and accuracy of the data and provide a reliable data basis for subsequent analysis.

[0024] Feature extraction unit: Extract characteristic parameters closely related to the quality of the crystal rod from the cleaned data. Through the preset feature extraction algorithm, the potential information in the data is mined, such as dimensional deviation, surface roughness related parameters, processing technology stability indicators, etc. These characteristic parameters can more accurately reflect the quality of the crystal rod and provide a key basis for quality grading.

[0025] Quality grading unit: Based on the extracted characteristic parameters, the crystal rods are graded according to the pre-set quality grading rules. These rules are formulated according to the quality standards of the crystal rods and the actual production needs. For example, the crystal rods with dimensional deviations within a very small range, low surface roughness and stable processing technology are graded as N1 (high quality grade); the crystal rods with dimensional deviations and surface roughness within a certain reasonable range and basically stable processing technology are graded as N2; the crystal rods that exceed some standards but can still meet some application requirements are classified as N3; and the crystal rods that seriously exceed the standards or have obvious defects are judged as NG (unqualified grade).

[0026] Data storage and management unit: Bind the quality grade information of the ingot with the unique identifier of the ingot again and store it in the database. At the same time, classify and manage the relevant data to facilitate the traceability and analysis of the entire life cycle of the ingot. For example, the quality grade and processing data of the ingot can be quickly queried according to information such as the batch number and production date of the ingot, providing strong support for the analysis and improvement of quality problems.

[0027] Second, the embodiment of the present application provides a method for detecting and grading the quality of an ingot based on MES system data, including the following steps:

[0028] Data acquisition and binding step: During the process of processing the ingot on the surface grinder, collect the ingot processing data through displacement sensors, force sensors, speed sensors, etc. installed on the surface grinder, and use the data acquisition device to bind the collected data with the unique identifier of the ingot to form a data packet;

[0029] Data transmission step: The data transmission module encrypts the bound data packet and adds a check code, and transmits the data packet to the MES system by wired or wireless communication. The MES system verifies the data. If the verification fails, it requests to resend;

[0030] Data processing and feature extraction step: The data cleaning unit of the MES system uses algorithms such as filtering to clean the received data, removing abnormal data points. The feature extraction unit extracts the feature parameters related to the quality of the ingot from the cleaned data;

[0031] Quality grading step: The quality grading unit of the MES system divides the grade of the ingot according to the extracted feature parameters according to the preset quality grading rules;

[0032] Data storage and management step: The data storage and management unit of the MES system rebinds the ingot quality grade information with the unique identifier of the ingot and stores it in the database, and classifies and manages the data.

[0033] In some embodiments of the present invention, in the above data acquisition and binding step, the sensor collects data according to a preset sampling frequency, and the data acquisition device performs preliminary screening on the data and then binds it with the unique identifier of the ingot.

[0034] In some embodiments of the present invention, in the above data processing and feature extraction step, the data cleaning unit uses a moving average filtering algorithm to clean the data.

[0035] In some embodiments of the present invention, in the above quality grading step, the quality grading rules are dynamically updated according to the real-time production data of the ingot and market feedback.

[0036] The embodiment of the present invention has at least the following advantages or beneficial effects:

[0037] The surface grinding machine module of the present invention is equipped with a variety of high-precision sensors, which can comprehensively and real-time collect various key data during the processing of the ingot, such as size, grinding force, grinding speed, etc., to ensure the accurate monitoring of the ingot processing state. The data acquisition device binds the collected data with the unique identifier of the ingot, providing a basis for subsequent data traceability and management, and ensuring the uniqueness and relevance of the data of each ingot.

[0038] The data transmission module of the present invention adopts encryption and verification technologies to ensure the security and integrity of data during transmission. Even in a complex industrial environment, it can effectively prevent data from being stolen or tampered with, and at the same time, through the verification mechanism, it can timely detect and correct transmission errors to ensure that the MES system receives accurate data.

[0039] Each unit of the MES system module of the present invention works in cooperation. The data cleaning unit removes abnormal data, improving the data quality; the feature extraction unit extracts key feature parameters, which helps to deeply analyze the ingot quality; the quality grading unit accurately grades according to rules; the data storage and management unit realizes the orderly storage and convenient management of data. The whole system forms a complete closed loop, realizing the automation and intelligence of ingot quality detection and grading.

[0040] The sensors of the surface grinding machine module of the present invention continuously collect data according to a preset sampling frequency, which can more accurately capture the dynamic changes during the ingot processing, avoiding data omission or inaccuracy. After the data acquisition device preliminarily processes the data and then binds it with the unique identifier of the ingot, the workload of subsequent data processing is reduced, and the efficiency and accuracy of data processing are improved.

[0041] The data transmission module of the present invention encrypts the data using a symmetric encryption algorithm. The symmetric encryption algorithm has the characteristics of fast encryption speed and high efficiency, which can ensure the security of data transmission without affecting the real-time performance of data transmission. It effectively prevents data from being illegally obtained and tampered with during transmission, providing a strong guarantee for the data security of the enterprise.

[0042] The data cleaning unit of the MES system module of the present invention uses a median filtering algorithm to remove outliers in the data. The median filtering algorithm can effectively suppress noise interference and retain the true characteristics of the data. By removing abnormal data, the quality and reliability of the data are improved, providing a more accurate data basis for subsequent feature extraction and quality grading.

[0043] The feature extraction unit of the MES system module of the present invention uses a principal component analysis algorithm to extract the main feature parameters in the data. The principal component analysis algorithm can perform dimensionality reduction on high-dimensional data, extract the most representative features, reduce the redundant information of the data, improve the efficiency and accuracy of feature extraction, and help to more accurately evaluate the ingot quality.

[0044] The quality grading rules of the MES system module of the present invention are dynamically adjusted according to different application scenarios and quality standards of the ingots, making the quality grading of the ingots more in line with actual requirements. Enterprises can timely adjust the grading rules according to market changes and customer requirements, improving the market adaptability and competitiveness of products.

[0045] The method of the present invention covers the complete processes of data collection, transmission, processing, grading, and storage management. Each step is closely connected and works collaboratively to ensure the accuracy and efficiency of ingot quality inspection and grading. From the source data collection to the final determination of the quality level and data storage, a scientific and standardized operation process is formed.

[0046] The present invention associates data with the unique identifier of the ingot through the data collection and binding step, and through the re-binding and storage in the data storage and management step, ensures the accuracy and traceability of the data. When quality problems occur, it is possible to quickly trace back to the specific ingot and related processing data, facilitating quality analysis and improvement.

[0047] In the data collection and binding step of the present invention, the sensor collects data according to a preset sampling frequency, which can obtain data more targeted and avoid unnecessary data collection. After the data collection device preliminarily screens the data and then binds it to the unique identifier of the ingot, the transmission and processing of invalid data are reduced, improving the operation efficiency of the entire system.

[0048] In the data processing and feature extraction step of the present invention, the data cleaning unit uses a moving average filtering algorithm to clean the data. The moving average filtering algorithm can smooth the data, effectively remove random noise and short-term fluctuations, and retain the long-term trend and features of the data. Through this cleaning method, the stability and reliability of the data are improved, providing better data support for subsequent feature extraction and quality grading.

[0049] In the quality grading step of the present invention, the quality grading rules are dynamically updated according to the real-time production data of the ingots and market feedback, enabling the quality grading of the ingots to timely reflect market demands and production actual situations. Enterprises can flexibly adjust the grading standards according to market changes and customer feedback, improving product quality and market competitiveness, and better meeting the personalized needs of customers. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0051] Figure 1 is the principle block diagram of the present invention;

[0052] Figure 2 is the workflow diagram of the present invention;

[0053] Figure 3 is the structural block diagram of an electronic device provided by an embodiment of the present invention.

[0054] Explanation of reference numerals: 101, memory; 102, processor; 103, communication interface. Detailed implementation manners

[0055] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Generally, the components of the embodiments of the present invention described and illustrated in the accompanying drawings herein can be arranged and designed in various different configurations.

[0056] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed present invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without making creative efforts fall within the scope of protection of the present invention.

[0057] It should be noted that: similar reference numerals and letters denote similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0058] It should be noted that, in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or sequence between these entities or operations. Moreover, the term "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or device. Without further limitation, an element defined by the phrase "comprising a..." does not exclude the existence of additional identical elements in the process, method, article, or device comprising the element.

[0059] In the description of the embodiments of the present invention, "a plurality of" represents at least two.

[0060] In the description of the embodiments of the present invention, it should also be noted that unless otherwise clearly specified and limited, if the terms "set", "install", "connect", and "link" are used, they 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 directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0061] As Figures 1-3 , in a first aspect, the embodiments of the present invention provide a control system for detecting the quality of a crystal bar and grading it based on MES system data, including:

[0062] A surface grinder module, equipped with a mechanical structure for processing crystal bars, and installed with a variety of high-precision sensors such as displacement sensors, force sensors, and speed sensors, used to collect data such as dimensions, grinding forces, and grinding speeds during the crystal bar processing in real time. It also has a data acquisition device for binding the collected data with the unique identifier of the crystal bar.

[0063] A data transmission module, using wired or wireless communication technology, encrypts the data bound by the surface grinder module and adds a check code, and stably and accurately transmits the data to the MES system. If the MES system fails to pass the data verification, it can request the surface grinder module to resend.

[0064] The MES system module includes a data cleaning unit for removing abnormal data points in the received data using algorithms such as filtering; a feature extraction unit for extracting feature parameters related to the quality of the crystal bar, such as dimensional deviation, surface roughness-related parameters, and machining process stability indicators, from the cleaned data; a quality grading unit for grading the crystal bar according to the extracted feature parameters according to the preset quality grading rules; and a data storage and management unit for binding the crystal bar quality grade information with the unique identifier of the crystal bar again and storing it in the database, and classifying and managing the data at the same time.

[0065] In some embodiments of the present invention, the sensors of the above surface grinder module continuously collect data according to a preset sampling frequency, and the data acquisition device binds the data with the unique identifier of the crystal bar after preliminary processing.

[0066] In some embodiments of the present invention, the above data transmission module encrypts the data using a symmetric encryption algorithm to ensure the security of data transmission.

[0067] In some embodiments of the present invention, the data cleaning unit of the above MES system module uses a median filtering algorithm to remove outliers in the data.

[0068] In some embodiments of the present invention, the feature extraction unit of the above MES system module extracts the main feature parameters in the data by using the principal component analysis algorithm.

[0069] In some embodiments of the present invention, the quality grading rules of the above MES system module are dynamically adjusted according to different application scenarios and quality standards of the ingots.

[0070] Second, an embodiment of the present application provides a method for detecting and grading the quality of an ingot based on MES system data, including the following steps:

[0071] Data acquisition and binding step: During the process of processing the ingot on the surface grinder, the data of the ingot processing is collected through displacement sensors, force sensors, speed sensors, etc. installed on the surface grinder, and the collected data is bound to the unique identifier of the ingot by using a data acquisition device to form a data packet;

[0072] Data transmission step: The data transmission module encrypts the bound data packet and adds a check code, and transmits the data packet to the MES system by using wired or wireless communication. The MES system checks the data. If the check fails, it requests to resend;

[0073] Data processing and feature extraction step: The data cleaning unit of the MES system uses algorithms such as filtering to clean the received data, removes abnormal data points, and the feature extraction unit extracts the feature parameters related to the quality of the ingot from the cleaned data;

[0074] Quality grading step: The quality grading unit of the MES system divides the grade of the ingot according to the extracted feature parameters according to the preset quality grading rules;

[0075] Data storage and management step: The data storage and management unit of the MES system rebinds the ingot quality grade information to the unique identifier of the ingot and stores it in the database, and classifies and manages the data.

[0076] In some embodiments of the present invention, in the above data acquisition and binding step, the sensor collects data according to a preset sampling frequency, and the data acquisition device performs preliminary screening on the data and then binds it to the unique identifier of the ingot.

[0077] In some embodiments of the present invention, in the above data processing and feature extraction step, the data cleaning unit uses a moving average filtering algorithm to clean the data.

[0078] In some embodiments of the present invention, in the above quality grading step, the quality grading rules are dynamically updated according to the real-time production data and market feedback of the ingot.

[0079] Embodiment 1:

[0080] System setup: Transform the surface grinder, install high-precision displacement sensors, force sensors, and speed sensors, and at the same time equip with data acquisition devices and wireless data transmission modules. Build an MES system, develop functional modules such as data cleaning, feature extraction, quality grading, and data storage management, and set corresponding algorithms and rules.

[0081] Data acquisition and transmission: During the crystal bar processing, the sensors collect data according to the preset sampling frequency. The data acquisition device binds the data with the batch number and serial number of the crystal bar and sends it to the MES system through the wireless data transmission module. For example, the displacement sensor monitors the change in the diameter of the crystal bar in real time, and the force sensor records the magnitude of the grinding force.

[0082] Data processing and grading: After the MES system receives the data, the data cleaning unit uses the median filtering algorithm to remove abnormal data. The feature extraction unit uses the principal component analysis algorithm to extract key feature parameters. The quality grading unit classifies the crystal bars into four grades: N1, N2, N3, and NG according to the preset rules. For example, crystal bars with extremely small dimensional deviations, low surface roughness, and stable processing technology are rated as N1 grade.

[0083] Data storage and management: The data storage and management unit binds the quality grade information of the crystal bar with the unique identifier again and stores it in the database for convenient subsequent query and traceability.

[0084] Effect evaluation: After implementation, the production efficiency of the crystal bars of this enterprise has increased by 35%, the maintenance cost of the detection equipment has been reduced by 55%, the product rework rate caused by inaccurate quality grading has been reduced by 45%, and the market competitiveness of the products has been significantly improved.

[0085] Comparative example 1:

[0086] Traditional detection machine detection mode

[0087] Detection process: After the surface grinding process is completed, the crystal bar is transported to the detection workshop. The operator preheats and calibrates the detection machine, and then clamps the crystal bar onto the detection machine for detection. The detection machine measures parameters such as the size and surface roughness of the crystal bar, and the operator records the data and judges the quality grade of the crystal bar based on experience.

[0088] Problems and deficiencies: The detection process is cumbersome, the detection time is long, and the average detection time for each crystal bar is about 30 minutes. The detection machine is easily affected by environmental factors, and the detection accuracy is unstable, resulting in inaccurate quality grading and a high product rework rate.

[0089] Effect evaluation: The production efficiency of this enterprise is low, and the daily output is 30% lower than that of the enterprise in Example 1. The maintenance cost of the detection equipment is high, and the annual maintenance cost reaches 500,000 yuan. The yield rate of the products is 80%, which is lower than that of the enterprise in Example 1 by more than 90%.

[0090] Embodiment 2:

[0091] As Figure 3 , the embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by the processor 102, it implements the system according to any one of the above first aspects. If the above functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0092] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

[0093] For those skilled in the art, it is obvious that the present application is not limited to the details of the above exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or basic characteristics of the present application. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present application is defined by the appended claims rather than the above description. Therefore, it is intended to include all changes falling within the meaning and scope of the equivalent elements of the claims in the present application. Any reference signs in the claims should not be regarded as limiting the claimed rights.

Claims

1. A control system for detecting and grading the quality of crystal bars based on MES system data, characterized in that: include: The flat grinding machine module is equipped with a mechanical structure for processing crystal rods and is equipped with a variety of high-precision sensors such as displacement sensors, force sensors, and speed sensors to collect data such as the size, grinding force, and grinding speed of the crystal rod in real time during processing. It is also equipped with a data acquisition device to bind the collected data to the unique identification of the crystal rod; The data transmission module uses wired or wireless communication technology to encrypt the data bound to the flat grinder module and add a verification code to transmit the data to the MES system stably and accurately. If the MES system fails to verify the data, the flat grinder module can be required to resend it. The MES system module includes a data cleaning unit, which is used to use filtering and other algorithms to remove abnormal data points in the received data; a feature extraction unit, which is used to extract characteristic parameters related to crystal rod quality, such as dimensional deviation, surface roughness related parameters, and processing technology stability indicators from the cleaned data; a quality grading unit, which is used to grade the crystal rods according to the extracted characteristic parameters and the preset quality grading rules; a data storage and management unit, which is used to re-bind the crystal rod quality grade information and the crystal rod unique identifier and store them in the database, and classify and manage the data at the same time.

2. The control system for detecting and grading the quality of crystal ingots based on MES system data according to claim 1, characterized in that: The sensor of the flat grinder module continuously collects data at a preset sampling frequency, and the data acquisition device performs preliminary processing on the data before binding it to the unique identification of the crystal rod.

3. The control system for detecting and grading the quality of crystal ingots based on MES system data according to claim 1, characterized in that: The data transmission module uses a symmetric encryption algorithm to encrypt data to ensure the security of data transmission.

4. The control system for detecting and grading the quality of crystal ingots based on MES system data according to claim 1, characterized in that: The data cleaning unit of the MES system module uses a median filtering algorithm to remove abnormal values ​​in the data.

5. The control system for detecting and grading the quality of crystal ingots based on MES system data according to claim 1, characterized in that: The feature extraction unit of the MES system module uses a principal component analysis algorithm to extract the main feature parameters in the data.

6. The control system for detecting and grading the quality of crystal ingots based on MES system data according to claim 1, characterized in that: The quality grading rules of the MES system module are dynamically adjusted according to different application scenarios and quality standards of the crystal ingot.

7. A method for detecting and grading the quality of a crystal ingot based on MES system data, characterized in that: The following steps are involved: Data collection and binding steps: During the process of processing the crystal rod by the flat grinder, the crystal rod processing data is collected by means of displacement sensors, force sensors, speed sensors, etc. installed on the flat grinder, and the collected data is bound to the unique identification of the crystal rod by means of a data collection device to form a data packet; Data transmission steps: The data transmission module encrypts the bound data packets and adds a check code, and transmits the data packets to the MES system using wired or wireless communication. The MES system verifies the data and requires resending if the verification fails. Data processing and feature extraction steps: The data cleaning unit of the MES system uses filtering and other algorithms to clean the received data and remove abnormal data points. The feature extraction unit extracts characteristic parameters related to the quality of the crystal rod from the cleaned data; Quality grading step: The quality grading unit of the MES system grades the crystal ingots according to the extracted characteristic parameters and the preset quality grading rules; Data storage and management steps: The data storage and management unit of the MES system binds the crystal ingot quality grade information and the crystal ingot unique identification again and stores them in the database to classify and manage the data.

8. The method for detecting and grading the quality of crystal ingots based on MES system data according to claim 7, characterized in that: In the data collection and binding step, the sensor collects data according to a preset sampling frequency, and the data collection device performs preliminary screening on the data before binding it to the unique identification of the crystal rod.

9. The method for detecting and grading the quality of crystal ingots based on MES system data according to claim 7, characterized in that: In the data processing and feature extraction step, the data cleaning unit uses a sliding average filtering algorithm to clean the data.

10. The method for detecting and grading the quality of crystal ingots based on MES system data according to claim 7, characterized in that: In the quality grading step, the quality grading rules are dynamically updated according to the real-time production data of the crystal rod and market feedback.

Images