Management method and device of route equipment and electronic equipment

Abstract

The invention discloses a route equipment management method and device and electronic equipment. The method comprises the steps of obtaining virtual measurement data, statistical process control data and fault detection collection data; determining the performance of the route equipment based on the virtual measurement data, the statistical process control data and the fault detection collection data; and carrying out grade division based on the performance of the route equipment, and carrying out differential management on the route equipment according to a division result. According to the management method, the production efficiency and the product quality can be improved, and the route equipment is easy to manage.

Description

Technical Field

[0001] The present application relates to the technical field of telematic equipment, and in particular to a method for managing telematic equipment, an electronic device, and a device for managing telematic equipment. Background Art

[0002] Chip manufacturing is a highly complex process involving thousands of process steps. With the development of technology, chip manufacturing is facing the trend of computing power evolving from general-purpose to specialized, and the innovation of architecture is also changing. With the rise of AI and big models, new challenges have been raised in chip computing power, energy efficiency, storage, and integration. These challenges have stimulated the development of semiconductors from materials, design, manufacturing to packaging technology itself. Therefore, chip manufacturing plants need to constantly update their production scheduling methods to adapt to these new trends and challenges.

[0003] At present, in existing chip manufacturing plants, manufacturing and processing tasks are only allocated based on the idle status of the machine. That is to say, in the chip manufacturing process, there are multiple different process steps, including lithography, etching, chemical vapor deposition (CVD), physical vapor deposition (PVD), etc. Each step requires a specific machine to complete. The factory management system will monitor the status of these machines in real time and identify which machines are currently idle. Once the idle machines are identified, the production scheduling system will allocate tasks based on the capabilities of the machines (such as the chip size that can be processed, process capabilities, etc.) and the upcoming task requirements (such as the required process steps, urgency, order size, etc.). This allocation method can quickly respond to production needs, reduce the idle time of the machine, and improve overall production efficiency.

[0004] However, this method of assigning tasks based solely on idle status may lead to ignoring differences in machine performance. High-performance machines and low-performance machines differ in processing power, accuracy, and stability. Simply assigning tasks based on idle status may not fully utilize the advantages of high-performance machines, and may overuse low-performance machines, affecting overall production efficiency. In addition, the use of a unified and regular management method for different machines also fails to perform differentiated management, that is, no targeted management and maintenance operations are performed for different machines. Summary of the invention

[0005] The present application aims to solve at least one of the technical problems in the related art to a certain extent. To this end, the first purpose of the present application is to propose a management method for route equipment, obtain virtual measurement data, statistical process control data and fault detection collection data, determine the performance of the route equipment based on the virtual measurement data, statistical process control data and fault detection collection data, and perform grade division based on the performance of the route equipment, so as to perform differentiated management of the route equipment according to the results of the division, thereby improving production efficiency and product quality, and facilitating the management of the route equipment.

[0006] The second objective of the present application is to provide an electronic device.

[0007] The third objective of the present application is to provide a management device for route equipment.

[0008] To achieve the above-mentioned purpose, the first aspect of the present application proposes a management method for remote equipment, the method comprising: acquiring virtual measurement data, statistical process control data and fault detection collection data; determining the performance of the remote equipment based on the virtual measurement data, the statistical process control data and the fault detection collection data; and performing grade division based on the performance of the remote equipment to perform differentiated management of the remote equipment according to the graded results.

[0009] According to the management method of the remote equipment of the embodiment of the present application, virtual measurement data, statistical process control data and fault detection collection data are obtained, the performance of the remote equipment is determined based on the virtual measurement data, statistical process control data and fault detection collection data, and the level division is performed based on the performance of the remote equipment, so as to perform differentiated management of the remote equipment according to the results of the division. Therefore, the method can improve production efficiency and product quality, and is easy to manage the remote equipment.

[0010] In addition, the management method of the route device according to the above embodiment of the present application may also have the following additional technical features:

[0011] According to one embodiment of the present application, determining the performance of the route equipment based on the virtual measurement data, the statistical process control data and the fault detection collection data includes: inputting the virtual measurement data, the statistical process control data and the fault detection collection data into a preset AI model to obtain key indicators of the route equipment, wherein the key indicators include yield and failure rate; and determining the performance of the route equipment based on the key indicators.

[0012] According to one embodiment of the present application, the method further includes: acquiring historical chip yield data and future chip yield data; and determining the performance of the process equipment based on the historical chip yield data, the future chip yield data, the virtual measurement data, the statistical process control data, and the fault detection collection data.

[0013] According to one embodiment of the present application, determining the performance of the route equipment based on the historical chip yield data, the future chip yield data, the virtual measurement data, the statistical process control data and the fault detection collection data includes: adding the historical chip yield data, the future chip yield data, the virtual measurement data, the statistical process control data and the fault detection collection data to a preset AI model to obtain key indicators of the route equipment, wherein the key indicators include yield and failure rate; and determining the performance of the route equipment based on the key indicators.

[0014] According to one embodiment of the present application, the grading based on the performance of the route equipment includes: determining that a route equipment with a yield greater than a first preset yield and a failure rate less than the first preset failure rate among multiple route equipment is the highest performance level; determining that a route equipment with a yield greater than a second preset yield and less than the first preset yield and a failure rate lower than the second preset failure rate and higher than the first preset failure rate among multiple route equipment is an intermediate performance level; wherein the first preset yield is greater than the second preset yield, and the first preset failure rate is less than the second preset failure rate; determining that a route equipment with a yield less than the second preset yield and a failure rate greater than the third preset failure rate among multiple route equipment is the lowest performance level; wherein the third preset failure rate is greater than the second preset failure rate.

[0015] According to an embodiment of the present application, the differentiated management of the remote devices according to the results of the division includes: controlling the remote devices to produce chips of different specifications according to different performance levels of the remote devices, wherein the performance level is positively correlated with the size of the chip.

[0016] According to an embodiment of the present application, the differentiated management of the remote device according to the divided results includes: when the remote device is at the highest performance level, extending the maintenance time interval of the remote device; when the remote device is at the lowest performance level, shortening the maintenance time interval of the remote device.

[0017] According to an embodiment of the present application, when the routing device is at the highest performance level, the method further includes: controlling the routing device to produce chips with a yield lower than a preset yield threshold.

[0018] To achieve the above-mentioned purpose, an electronic device proposed in the second aspect of the present application includes a memory, a processor, and a program stored in the memory and executable on the processor. When the processor executes the program, the above-mentioned method for managing the route device is implemented.

[0019] According to the electronic device of the embodiment of the present application, by executing the above-mentioned method for managing remote devices, it is possible to improve production efficiency and product quality, and it is easy to manage remote devices.

[0020] To achieve the above-mentioned purpose, the third aspect of the present application proposes a management device for remote equipment, the device comprising: an acquisition module, used to acquire virtual measurement data, statistical process control data and fault detection collection data; a determination module, used to determine the performance of the remote equipment based on the virtual measurement data, the statistical process control data and the fault detection collection data; a management module, used to classify the remote equipment based on its performance, so as to perform differentiated management of the remote equipment according to the classification results.

[0021] According to the management device of the route equipment of the embodiment of the present application, the acquisition module is used to acquire virtual measurement data, statistical process control data and fault detection collection data, the determination module is used to determine the performance of the route equipment based on the virtual measurement data, the statistical process control data and the fault detection collection data, and the management module is used to classify the performance of the route equipment based on the performance of the route equipment, so as to perform differentiated management of the route equipment according to the classification results. Therefore, the device can improve production efficiency and product quality, and is easy to manage the route equipment.

[0022] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 is a flowchart of a method for managing a route device according to an embodiment of the present application;

[0024] Figure 2 A flowchart of a method for managing a route device according to a specific example of the present application;

[0025] Figure 3 is a block diagram of an electronic device according to an embodiment of the present application;

[0026] Figure 4 Detailed description is a block diagram of a management device for a routing device according to an embodiment of the present application. DETAILED DESCRIPTION

[0027] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0028] The following describes the management method of the remote device, the electronic device and the management device of the remote device proposed in the embodiments of the present application with reference to the accompanying drawings.

[0029] Figure 1 Flow chart of a method for managing a route device according to an embodiment of the present application.

[0030] like Figure 1 As shown, the management method of the route device in the embodiment of the present application may include the following steps:

[0031] S1, obtain virtual measurement data, statistical process control data and fault detection collection data.

[0032] S2, determining the performance of the route equipment based on virtual measurement data, statistical process control data and fault detection collection data.

[0033] S3, classifying the distance devices based on their performance, so as to perform differentiated management of the distance devices according to the classification results.

[0034] Specifically, when managing the process equipment, firstly, virtual measurement data, statistical process control data and fault detection collection data can be obtained. Among them, the process equipment is the equipment used in a specific process flow, which is a mechanical or technical device used to perform specific tasks or processes on the production line, such as equipment for chip manufacturing, such as photolithography machines, etc. Virtual measurement is a technology that uses historical data and statistical models to predict the measurement results of products or production processes. It does not require actual physical measurements of each product, but estimates the quality characteristics of the product by analyzing the relevant parameters and historical data in the production process. Virtual measurement data may include process parameters such as temperature, pressure, time, etc., which can be obtained from production equipment in real time. The key to virtual measurement data is that it can reduce the need for actual measurement, reduce production cycles and improve efficiency. For example, in semiconductor manufacturing, by collecting data in the production process, such as data in the chemical mechanical polishing (CMP) process, the flatness of the wafer can be predicted, thereby avoiding the actual physical measurement steps, improving production efficiency, and maintaining or improving the control level of product quality.

[0035] Statistical process control is a technique that uses statistical methods to monitor and control the production process to ensure the stability and predictability of the production process, thereby improving product quality data. It includes offline monitoring data and online monitoring data. Offline monitoring data refers to data collected outside the production process, which is usually used to analyze and improve the process. For example, the quality control department may test product samples after the production line is off the line to analyze the performance and consistency of the product. Online monitoring data refers to data collected in real time or continuously during the production process. This data can be obtained through sensors or measuring instruments directly connected to the production equipment for real-time monitoring of the production process. Online monitoring can help detect abnormalities in the production process in a timely manner, so that measures can be taken quickly to reduce the production of defective products.

[0036] Fault detection collection data refers to data used to identify, analyze and predict potential faults during the operation of the process equipment. These data usually come from various sensors, monitoring systems and log records. For example, data on physical quantities such as vibration, temperature, pressure, and current, data from production monitoring systems, such as the operating status of the production line, the working parameters of the equipment, etc., or log information generated during the operation and maintenance of the equipment, including operation records, fault records, and maintenance records.

[0037] After obtaining virtual measurement data, statistical process control data and fault detection collection data, the performance of the process equipment can be determined based on the virtual measurement data, statistical process control data and fault detection collection data. For example, the data can be analyzed through multivariate linear regression, partial least squares method, etc. to extract key quality parameters. The degree of matching between process capability and specification limit can be quantified by process capability index, and the reliability of the equipment can be predicted by Weibull probability and statistical analysis methods. The analysis results are combined to comprehensively evaluate the performance of the equipment. For example, if the virtual measurement data shows that the quality parameters are within the control range, the statistical process control data shows that the process capability index is high, and the fault detection collection data shows that the failure rate is low, it can be considered that the equipment performance is good.

[0038] After determining the performance of the remote equipment, it can be graded according to the performance of the remote equipment, so as to perform differentiated management of the remote equipment according to the results of the classification. The performance grade of the remote equipment can be based on factors such as the yield, failure frequency, maintenance cost and production efficiency of the equipment. For example, the equipment can be divided into four grades: A, B, C, and D, where grade A represents the highest performance grade (such as low failure frequency and high yield), and grade D represents the lowest performance grade (such as high failure frequency and low yield). Differentiated management means that different maintenance and monitoring strategies are adopted according to the grade of the equipment. For example, for grade A equipment, the A equipment can handle more complex tasks with higher precision requirements, or its failure rate is low, and the maintenance frequency can be appropriately extended. For grade D equipment, it can handle tasks with lower precision requirements and high failure rate, and the maintenance frequency can be appropriately reduced.

[0039] As a result, on-the-go equipment can be managed more effectively, improving production efficiency and product quality while reducing costs and risks.

[0040] According to one embodiment of the present application, the performance of the route equipment is determined based on virtual measurement data, statistical process control data and fault detection collection data, including: inputting the virtual measurement data, statistical process control data and fault detection collection data into a preset AI model to obtain key indicators of the route equipment, wherein the key indicators include yield and failure rate; and determining the performance of the route equipment based on the key indicators.

[0041] Specifically, when determining the performance of the process equipment based on virtual measurement data, statistical process control data and fault detection collection data, the virtual measurement data, statistical process control data and fault detection collection data can be input into a preset AI model, wherein a series of data processing, model training and verification, correlation and regression analysis, weighting and prioritization and other steps can be performed in the AI ​​model. For example, before inputting into the model, the data can be preprocessed, including missing value filling, standardization, dimensionality reduction, etc., to ensure the quality and applicability of the data. Use labeled data to train AI models, such as deep learning models, to minimize prediction errors by adjusting the weights and biases in the network, and during the model training process, use the validation set to evaluate the performance of the model, avoid overfitting, and perform hyperparameter adjustment. Edit and calculate the prediction results of the model, which may include operations such as sorting the prediction results and weighted summation to optimize the output of the model. Use statistical methods, such as the Pearson correlation coefficient or the Spearman correlation coefficient, to analyze the correlation between virtual measurement data, statistical process control data and fault detection collection data to identify which factors have the greatest impact on chip yield. Building a regression model, such as linear regression, to predict chip yield involves using historical data to train the model and determine the relationship between input variables (virtual measurement data, statistical process control data, and fault detection collection data) and output (yield). Based on the weighted results, prioritize the factors that affect chip yield, identify the most critical factors, and optimize the performance of the process equipment accordingly.

[0042] Different weights can be assigned according to the importance of different models or different features. For example, using hill climbing weighting or parameter optimization weighting, the optimal weight is automatically searched to improve the prediction accuracy of the model. According to the AI ​​model, the performance indicators of the equipment, namely the yield and failure rate, can be predicted. The yield rate refers to the proportion of qualified products produced by the equipment within a certain period of time. The AI ​​model predicts the qualified rate of the product by analyzing virtual measurement data and statistical process control data. For example, the model uses algorithms such as multivariate linear regression and partial least squares to predict the yield rate. The failure rate involves the frequency and downtime of equipment failures. The AI ​​model calculates the failure rate by analyzing the data collected by fault detection and predicting the frequency and downtime of equipment failures.

[0043] Therefore, the performance of the in-progress equipment can be evaluated based on the yield and failure rate predicted by the AI ​​model. For example, the performance of the in-progress equipment can be determined through a pre-set correspondence, for example, the relationship between the yield and failure rate and the performance is pre-determined. After the yield and failure rate are determined, the performance of the in-progress equipment can be obtained by directly calling the correspondence.

[0044] According to one embodiment of the present application, the management method of the route equipment also includes: obtaining historical chip yield data and future chip yield data; determining the performance of the route equipment based on the historical chip yield data, future chip yield data, virtual measurement data, statistical process control data and fault detection collection data.

[0045] Specifically, in order to more accurately determine the performance of the en-route equipment, historical chip yield data and future chip yield data can also be obtained. In other words, not only can the performance of the en-route equipment be determined based on virtual measurement data, statistical process control data, and fault detection collection data, but also the performance of the en-route equipment can be determined by combining historical chip yield data and future chip yield data. Historical chip yield data includes yield records of chips produced in the past period of time. Yield refers to the proportion of chips that meet quality standards in a certain number of chips. Historical yield data can provide a baseline for equipment performance and help analyze and predict the future performance of the equipment. Future chip yield data is a prediction of chip yield in the future period based on the prediction model and current production conditions. These data can help formulate production plans and adjust production strategies to optimize equipment performance and improve product quality.

[0046] Therefore, the performance of the in-progress equipment can be determined based on historical chip yield data, future chip yield data, virtual measurement data, statistical process control data, and fault detection collection data. For example, by integrating the above data and using data analysis and machine learning techniques to develop a predictive model from the collected data, the performance of the in-progress equipment can be more accurately evaluated, or the generalization ability of the model can be evaluated using performance metrics such as accuracy and recall. This analysis can help identify key factors that affect equipment performance, such as equipment aging, operating errors, or material changes. Based on the analysis results, appropriate measures can be taken to optimize equipment performance, such as adjusting equipment parameters, improving maintenance plans, or replacing worn parts.

[0047] According to one embodiment of the present application, the performance of the route equipment is determined based on historical chip yield data, future chip yield data, virtual measurement data, statistical process control data and fault detection collection data, including: historical chip yield data, future chip yield data, virtual measurement data, statistical process control data and fault detection collection data are added to a preset AI model to obtain key indicators of the route equipment, wherein the key indicators include yield and failure rate; and the performance of the route equipment is determined based on the key indicators.

[0048] Specifically, when determining the performance of process equipment based on historical chip yield data, future chip yield data, virtual measurement data, statistical process control data, and fault detection collection data, it is first necessary to extract data from the semiconductor manufacturing system periodically or in real time. This includes historical and future chip yield data, virtual measurement data, statistical process control data, and fault detection collection data, which are stored in relational database management systems, data warehouses, etc. After data extraction, preprocessing can be performed, including data cleaning, feature selection, and transformation to make it suitable for input into the AI ​​model. For example, for time series data over a long period of time, the average value of the unit time period can be calculated and analyzed to reduce the amount of data.

[0049] Using the processed data, one or more neural network models are constructed to predict the chip yield. These models can be integrated, that is, multiple neural network models are combined to improve the prediction accuracy. For example, there can be different neural network models for production data, equipment data, and defect data, each of which focuses on the factors most relevant to the yield. The AI ​​model is trained by the accumulated training data, and the performance of the model is evaluated using the validation set. The output of the model is the predicted chip yield, and the input is various influencing factors, such as device number, workspace, temperature, pressure, etc. Therefore, according to the AI ​​model, the performance indicators of the equipment, namely the yield and failure rate, can be predicted, and the performance of the route equipment can be evaluated based on the yield and failure rate. For example, the performance of the route equipment can be determined by a pre-set corresponding relationship, for example, the relationship between the yield and failure rate and the performance is pre-determined, and after the yield and failure rate are determined, the performance of the route equipment can be obtained by directly calling the corresponding relationship.

[0050] According to one embodiment of the present application, the grading is performed based on the performance of the route equipment, including: determining that the route equipment with a yield greater than a first preset yield and a failure rate less than the first preset failure rate among multiple route equipment is the highest performance level; determining that the route equipment with a yield greater than a second preset yield and less than the first preset yield and a failure rate lower than the second preset failure rate and higher than the first preset failure rate among multiple route equipment is an intermediate performance level; wherein the first preset yield is greater than the second preset yield, and the first preset failure rate is less than the second preset failure rate; determining that the route equipment with a yield less than the second preset yield and a failure rate greater than the third preset failure rate among multiple route equipment is the lowest performance level; wherein the third preset failure rate is greater than the second preset failure rate.

[0051] Specifically, when the level is divided according to the performance of the route equipment, the specific level of each device needs to be determined based on the actual production data and the preset standard. For example, the yield and failure rate of multiple route equipment are judged. When there is a route equipment with a yield greater than the first preset yield and a failure rate less than the first preset failure rate, it means that the current yield of the equipment is high and the failure rate is low. The route equipment can be determined to be the highest performance level, which means that these devices show high product quality and low failure frequency in the production process, and are the equipment group with the best performance. When there is a route equipment with a yield greater than the second preset yield and less than the first preset yield and a failure rate lower than the second preset failure rate and higher than the first preset failure rate, it means that although the current equipment is not as good as the highest level, it is still higher than a lower standard and the performance is at a medium level. When there is a route equipment with a yield less than the second preset yield and a failure rate greater than the third preset failure rate, it means that the current yield of the equipment is low and the failure rate is high, that is, the product quality of these devices is low and the failure frequency is high during the production process, so they are classified as the equipment group with the worst performance.

[0052] For example, for multiple lithography machines, if the first preset yield is 90%, the second preset yield is 70%, the third preset yield is 60%, the first preset failure rate is 10%, the second preset failure rate is 20%, and the third failure rate is 30%, if the yield of the current lithography machine A is 95%, the failure rate is 3%, the yield of the lithography machine B is 92%, and the failure rate is 2%, it can be determined that the performance of lithography machines A and B is the highest performance level. If the yield of the current lithography machine C is 80%, the failure rate is 15%, the yield of the lithography machine D is 85%, and the failure rate is 12%, it can be determined that the performance of lithography machines C and D is the middle performance level. If the yield of the current lithography machine E is 55%, and the failure rate is 25%, it can be determined that the performance of lithography machine E is the lowest performance level. Therefore, such a level division helps the factory to manage and maintain the equipment more effectively, ensuring the optimization of production efficiency and product quality. Through the comprehensive evaluation of yield and failure rate, the performance of the equipment can be classified more accurately, thereby providing a scientific basis for production decisions.

[0053] According to an embodiment of the present application, differentiated management of remote devices is performed based on the results of the division, including: controlling the remote devices to produce chips of different specifications based on different performance levels of the remote devices, wherein the performance level is positively correlated with the size of the chip.

[0054] Specifically, when differentiated management of route equipment is performed according to the results of the division, the route equipment can be controlled to produce chips of different specifications according to the different performance levels of the route equipment. Among them, the performance level is positively correlated with the size of the chip. That is to say, the higher the performance level of the route equipment, the larger the size of the chip that can be processed, and the smaller the performance level of the route equipment, the smaller the size of the chip that can be processed. In semiconductor manufacturing, the performance level of route equipment (such as photolithography machines, etching machines, etc.) determines the size and complexity of the chips they can process. Differential management means that they can be allocated to produce chips of different specifications and sizes according to the performance level of the equipment. For example, for route equipment preset to the highest performance level, these equipment usually have the most advanced technology and the highest precision, and can handle large-size and high-complexity chip manufacturing tasks. Therefore, they are used to produce large-size high-performance chips to give full play to their technical advantages. For route equipment preset to the intermediate performance level, these equipment may have moderate precision and are suitable for producing moderate-size chips. For route equipment preset to the lowest performance level, these equipment may have older technology and lower precision, and are suitable for producing small-size and low-complexity chips.

[0055] Therefore, the implementation of differentiation management can optimize the production process, ensuring that high-grade equipment is used to produce high-value, high-performance chips, while low-grade equipment is focused on producing more cost-effective low-performance chips. This strategy helps improve production efficiency, reduce costs, and ensure the flexibility of the production line and the ability to respond to market changes.

[0056] According to an embodiment of the present application, differentiated management of the remote equipment is performed according to the results of the division, including: when the remote equipment is at the highest performance level, extending the maintenance time interval of the remote equipment; when the remote equipment is at the lowest performance level, shortening the maintenance time interval of the remote equipment.

[0057] Specifically, the differentiated management of remote equipment mainly involves adjusting the maintenance strategy according to the performance level of the equipment, where the division of equipment performance levels is based on multiple factors such as the criticality of the equipment, the frequency and impact of failures, maintenance costs, production efficiency impact, and safety risks. These factors jointly determine the importance of the equipment in the production process and the demand for maintenance resources. When performing differentiated management of remote equipment based on the results of the division, the performance level of the remote equipment is judged. When the remote equipment is at the highest performance level, the maintenance time interval of the remote equipment can be extended. In other words, extending the time interval can reduce the frequency of equipment maintenance, thereby reducing maintenance costs and workload. When the remote equipment is at the lowest performance level, the maintenance time interval of the remote equipment can be shortened, that is, maintenance can be performed in advance, so that the performance of the remote equipment can be restored as soon as possible, thereby producing chips with higher yields.

[0058] Therefore, for high-level equipment, extending the maintenance time interval helps reduce downtime risks and maintenance costs; for low-level equipment, shortening the maintenance time interval can quickly respond to potential failures and maintain production continuity. This strategy helps to more effectively utilize maintenance resources and improve production efficiency and overall equipment performance.

[0059] According to an embodiment of the present application, when the remote device is at the highest performance level, the remote device management method further includes: controlling the remote device to produce chips with a yield lower than a preset yield threshold, wherein the preset yield threshold can be determined according to actual conditions.

[0060] Specifically, when the process equipment is at the highest performance level, the process equipment can be controlled to produce chips with a yield lower than the preset yield threshold. In other words, the process equipment is set to the highest performance level, which means that all parameters of the equipment are adjusted to the best state to achieve the highest production efficiency and the best chip quality. The preset yield threshold is set according to historical data, customer requirements and industry standards. This threshold is the minimum qualified rate that the process equipment needs to achieve when producing chips. For chips with a yield lower than the preset yield threshold, that is, low-yield chips, the process equipment with the highest performance level can be used, so that the yield can be improved to produce higher quality chips.

[0061] Combine the following Figure 2 To describe the management method of this application.

[0062] As a specific example, the management method of the route device of the present application may include the following steps:

[0063] S101, acquiring virtual measurement data, statistical process control data, fault detection collection data, historical chip yield data and future chip yield data.

[0064] S102, historical chip yield data, future chip yield data, virtual measurement data, statistical process control data and fault detection collection data are added to a preset AI model to obtain key indicators of the process equipment, wherein the key indicators include yield and failure rate.

[0065] S103, determining the performance of the route equipment based on the key indicators.

[0066] S104, determining whether the yield rate of the process equipment is greater than a first preset yield rate and whether the failure rate is less than the first preset failure rate. If yes, executing step S105; if not, executing step S107.

[0067] S105: Determine that the performance level of the corresponding route device is the highest performance level.

[0068] S106, extending the maintenance time interval of the corresponding route equipment, and controlling the route equipment to produce chips with a yield rate lower than a preset yield rate threshold, and to produce large-size chips.

[0069] S107, determine whether the yield rate in the process equipment is greater than the second preset yield rate and less than the first preset yield rate and whether the failure rate is lower than the second preset failure rate and higher than the first preset failure rate. If yes, execute step S108; if not, execute step S109.

[0070] S108: Determine that the performance level of the corresponding route equipment is an intermediate performance level, and produce a chip of an appropriate size.

[0071] S109, determining whether the yield rate of the routing device is less than the second preset yield rate and whether the failure rate is greater than the third preset failure rate. If yes, execute step S110; if not, execute step S103.

[0072] S110: Determine that the performance level of the corresponding route device is the lowest performance level.

[0073] S111, shorten the maintenance interval of remote equipment and produce small-sized chips.

[0074] In summary, according to the management method of the route equipment of the embodiment of the present application, virtual measurement data, statistical process control data and fault detection collection data are obtained, the performance of the route equipment is determined based on the virtual measurement data, statistical process control data and fault detection collection data, and the level division is performed based on the performance of the route equipment, so as to perform differentiated management of the route equipment according to the results of the division. Therefore, the method can improve production efficiency and product quality, and is easy to manage the route equipment.

[0075] Corresponding to the above embodiment, the present application also proposes an electronic device.

[0076] like Figure 3 As shown, the electronic device 200 of the embodiment of the present application may include: a memory 210, a processor 220, and a program stored in the memory 210 and executable on the processor 220. When the processor 220 executes the program, the above-mentioned method for managing remote devices is implemented.

[0077] According to the electronic device of the embodiment of the present application, by executing the above-mentioned method for managing remote devices, it is possible to improve production efficiency and product quality, and it is easy to manage remote devices.

[0078] Corresponding to the above embodiment, the present application also proposes a management device for route equipment.

[0079] like Figure 4As shown, the management device 100 of the routing device in the embodiment of the present application includes: an acquisition module 110, a determination module 120 and a management module 130.

[0080] The acquisition module 110 is used to acquire virtual measurement data, statistical process control data and fault detection collection data. The determination module 120 is used to determine the performance of the remote equipment based on the virtual measurement data, the statistical process control data and the fault detection collection data. The management module 130 is used to classify the remote equipment based on its performance, so as to perform differentiated management of the remote equipment according to the classification results.

[0081] According to one embodiment of the present application, the determination module 120 determines the performance of the route equipment based on virtual measurement data, statistical process control data and fault detection collection data, and is specifically used to: input the virtual measurement data, statistical process control data and fault detection collection data into a preset AI model to obtain key indicators of the route equipment, wherein the key indicators include yield and failure rate; and determine the performance of the route equipment based on the key indicators.

[0082] According to one embodiment of the present application, the determination module 120 is also used to: obtain historical chip yield data and future chip yield data; determine the performance of the process equipment based on the historical chip yield data, future chip yield data, virtual measurement data, statistical process control data and fault detection collection data.

[0083] According to one embodiment of the present application, the determination module 120 determines the performance of the route equipment based on historical chip yield data, future chip yield data, virtual measurement data, statistical process control data and fault detection collection data, and is specifically used to: add the historical chip yield data, future chip yield data, virtual measurement data, statistical process control data and fault detection collection data to a preset AI model to obtain key indicators of the route equipment, wherein the key indicators include yield and failure rate; determine the performance of the route equipment based on the key indicators.

[0084] According to one embodiment of the present application, the management module 130 performs grade classification based on the performance of the route equipment, specifically for: determining that the route equipment with a yield greater than a first preset yield and a failure rate less than the first preset failure rate among multiple route equipment is the highest performance grade; determining that the route equipment with a yield greater than a second preset yield and less than the first preset yield and a failure rate lower than the second preset failure rate and higher than the first preset failure rate among multiple route equipment is the intermediate performance grade; wherein the first preset yield is greater than the second preset yield, and the first preset failure rate is less than the second preset failure rate; determining that the route equipment with a yield less than the second preset yield and a failure rate greater than the third preset failure rate among multiple route equipment is the lowest performance grade; wherein the third preset failure rate is greater than the second preset failure rate.

[0085] According to an embodiment of the present application, the management module 130 performs differentiated management of the remote devices according to the results of the division, specifically for: controlling the remote devices to produce chips of different specifications according to different performance levels of the remote devices, wherein the performance level is positively correlated with the size of the chip.

[0086] According to an embodiment of the present application, the management module 130 performs differentiated management of the remote equipment according to the divided results, specifically for: when the remote equipment is at the highest performance level, extending the maintenance time interval of the remote equipment; when the remote equipment is at the lowest performance level, shortening the maintenance time interval of the remote equipment.

[0087] According to an embodiment of the present application, when the routing device is at the highest performance level, the party management module 130 is further used to: control the routing device to produce chips with a yield lower than a preset yield threshold.

[0088] It should be noted that for details not disclosed in the management device of the route device in the embodiment of the present application, please refer to the details disclosed in the management method of the route device in the embodiment of the present application, and the details will not be repeated here.

[0089] According to the management device of the route equipment of the embodiment of the present application, the acquisition module is used to acquire virtual measurement data, statistical process control data and fault detection collection data, the determination module is used to determine the performance of the route equipment based on the virtual measurement data, the statistical process control data and the fault detection collection data, and the management module is used to classify the performance of the route equipment based on the performance of the route equipment, so as to perform differentiated management of the route equipment according to the classification results. Therefore, the device can improve production efficiency and product quality, and is easy to manage the route equipment.

[0090] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0091] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0092] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0093] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0094] In this application, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like 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 an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0095] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for managing route equipment, characterized in that: The method comprises: Acquire virtual measurement data, statistical process control data, and fault detection collection data; determining the performance of the route equipment based on the virtual measurement data, the statistical process control data and the fault detection collection data; The distance devices are graded based on their performance, so that differentiated management of the distance devices is performed according to the graded results.

2. The method for managing route equipment according to claim 1, characterized in that: The determining the performance of the route equipment based on the virtual measurement data, the statistical process control data and the fault detection collection data comprises: Inputting the virtual measurement data, the statistical process control data and the fault detection collection data into a preset AI model to obtain key indicators of the process equipment, wherein the key indicators include yield and failure rate; The performance of the remote device is determined based on the key indicators.

3. The method for managing route equipment according to claim 1, characterized in that: The method further comprises: Obtain historical chip yield data and future chip yield data; The performance of the process equipment is determined based on the historical chip yield data, the future chip yield data, the virtual measurement data, the statistical process control data, and the fault detection collection data.

4. The method for managing route equipment according to claim 3, characterized in that: The determining the performance of the process equipment based on the historical chip yield data, the future chip yield data, the virtual measurement data, the statistical process control data and the fault detection collection data includes: The historical chip yield data, the future chip yield data, the virtual measurement data, the statistical process control data and the fault detection collection data are added to a preset AI model to obtain key indicators of the process equipment, wherein the key indicators include yield and failure rate; The performance of the remote device is determined based on the key indicators.

5. The method for managing route equipment according to claim 1, characterized in that: The grading based on the performance of the route equipment includes: Determine that a process device having a yield greater than a first preset yield and a failure rate less than the first preset failure rate among the plurality of process devices has the highest performance level; Determine that among the plurality of the process devices, the process devices having a yield greater than a second preset yield and less than the first preset yield and a failure rate lower than the second preset failure rate and higher than the first preset failure rate are at an intermediate performance level; wherein the first preset yield is greater than the second preset yield, and the first preset failure rate is less than the second preset failure rate; Determine that the path equipment among the plurality of the path equipments has a yield less than the second preset yield and a failure rate greater than a third preset failure rate as the lowest performance level; wherein the third preset failure rate is greater than the second preset failure rate.

6. The method for managing route equipment according to claim 5, characterized in that: The differentiated management of the route equipment according to the divided results includes: According to different performance levels of the remote equipment, the remote equipment is controlled to produce chips of different specifications, wherein the performance level is positively correlated with the size of the chip.

7. The method for managing route equipment according to claim 6, characterized in that: The differentiated management of the route equipment according to the divided results includes: When the mobile equipment is at the highest performance level, extend the maintenance interval of the mobile equipment; When the remote equipment is at the lowest performance level, the maintenance interval of the remote equipment is shortened.

8. The method for managing route equipment according to claim 7, characterized in that: In the case where the route equipment is at the highest performance level, the method further includes: The process equipment is controlled to produce chips with a yield rate lower than a preset yield rate threshold.

9. An electronic device, characterized in that: include: A memory, a processor, and a program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for managing a route device according to any one of claims 1 to 8 is implemented.

10. A management device for route equipment, characterized in that: The device comprises: An acquisition module, used to acquire virtual measurement data, statistical process control data and fault detection collection data; a determination module, configured to determine the performance of the route equipment based on the virtual measurement data, the statistical process control data and the fault detection collection data; The management module is used to classify the distance equipment according to its performance, so as to perform differentiated management of the distance equipment according to the classification results.

Images