Production control method and equipment based on virtual measurement prediction data, medium and product

Abstract

The embodiment of the invention relates to the technical field of data processing, and discloses a production control method and equipment based on virtual measurement prediction data, a medium and a product. The method comprises the following steps: acquiring program data and actual measurement data of historical production batches; training a class neural network through the program data of the historical production batch and the actual measurement data to obtain a control model; acquiring real-time program data of the current production batch; inputting the real-time program data into the control model to obtain predicted measurement data output by the control model; and carrying out production control according to the predicted measurement data. By adopting the scheme, the measurement tool does not need to be operated, the time for acquiring the measurement data is saved, the production efficiency is improved, the operation risk of the measurement tool does not exist, and the manpower consumption is saved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a production control method, device, medium and product based on virtual measurement prediction data. Background Art

[0002] In recent years, with the rapid development of science and technology, the production of semiconductor chips has become an important factor affecting the development of equipment hardware and software.

[0003] In the semiconductor manufacturing industry, the purpose of measurement operations is to ensure the quality of semiconductor devices. These operations include program identification, tool identification, daily tool monitoring, regular tool maintenance, tool repair monitoring, program control monitoring, and product monitoring. At present, these operations are performed by operators operating measurement tools to collect measurement data. However, the time cost of operating measurement tools is very high. Furthermore, in addition to the main program steps, additional manpower is required to operate the measurement equipment, which also causes certain manpower consumption. However, the inventors have found that there are at least the following technical problems in the related art: the use of measurement tools to collect measurement data is time-consuming and costly, affecting the production efficiency of semiconductor devices. At the same time, once the measurement tool itself is damaged during operation, it will cause certain economic losses, and the labor cost will be significantly increased. Summary of the invention

[0004] One purpose of the present application is to provide a production control method, equipment, medium and product based on virtual measurement prediction data, at least to solve the problem of high time cost of collecting measurement data, affecting production efficiency and having certain operational risks. The present application obtains a control model by training a class neural network using program data of historical production batches and actual measurement data. After the real-time program data of the current production batch is input into the control model, the predicted measurement data output by the control model can be obtained, so as to perform production control according to the predicted measurement data. By adopting this solution, there is no need to operate the measurement tool, which saves time for collecting measurement data, improves production efficiency, and eliminates the risk of operating the measurement tool, saving manpower consumption.

[0005] To achieve the above objectives, some embodiments of the present application provide the following aspects:

[0006] In a first aspect, some embodiments of the present application further provide a production control method based on virtual measurement prediction data, the method comprising:

[0007] Obtain process data and actual measurement data of historical production batches;

[0008] The control model is obtained by training the quasi-neural network through the program data and actual measurement data of the historical production batches;

[0009] Get real-time process data for the current production batch;

[0010] Inputting the real-time program data into the control model to obtain predicted measurement data output by the control model;

[0011] Production control is performed according to the predicted measurement data.

[0012] In a second aspect, some embodiments of the present application further provide an electronic device, comprising: one or more processors; and a memory storing computer program instructions, wherein the computer program instructions, when executed, cause the processor to perform the steps of the method described above.

[0013] In a third aspect, some embodiments of the present application further provide a computer-readable medium having computer program instructions stored thereon, wherein the computer program instructions can be executed by a processor to implement the method as described above.

[0014] In a fourth aspect, some embodiments of the present application further provide a computer program product, comprising a computer program / instruction, which implements the steps of the method described above when executed by a processor.

[0015] Compared with the related art, the solution provided by the embodiment of the present application obtains the program data and actual measurement data of the historical production batches; trains the neural network through the program data and actual measurement data of the historical production batches to obtain the control model; obtains the real-time program data of the current production batch; inputs the real-time program data into the control model to obtain the predicted measurement data output by the control model; and performs production control according to the predicted measurement data. By adopting this solution, there is no need to operate the measurement tool, which saves the time of collecting measurement data, improves production efficiency, and eliminates the risk of operating the measurement tool, saving manpower consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0017] Figure 1 An exemplary flow chart of a production control method based on virtual measurement prediction data provided according to some embodiments of the present application;

[0018] Figure 2 An exemplary flow chart of a production control method based on virtual measurement prediction data provided according to some embodiments of the present application;

[0019] Figure 3 An exemplary structural diagram of the electronic device is disclosed. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0021] First embodiment

[0022] The first embodiment of the present application relates to a production control method based on virtual measurement prediction data. Figure 1 As shown, the method may include the following steps:

[0023] Step S101, obtaining program data and actual measurement data of historical production batches;

[0024] Among them, program data can be data related to the wafer production process, such as control data for the machine. Program data is data used, processed and generated during the program operation. These data are usually created, stored and operated by the program itself according to its design and algorithm logic. For example, in a simple calculator program, the numbers and operators entered by the user are part of the program data, and the program calculates and outputs the results based on these input data.

[0025] Program data can also be imported from other data sources, such as data read from a database, configuration information read from a file, etc. For example, an enterprise management software may obtain employee information, sales data, etc. from the company's database, and these data are used in the program to process and analyze various business processes.

[0026] Program data can contain various types of data, such as integers, floating-point numbers, strings, Boolean values, and other basic data types. For example, in a program that counts student scores, the student's test scores may be integers or floating-point numbers, and the student's name may be a string.

[0027] At the same time, program data can also have complex data structures, such as arrays, linked lists, stacks, queues, trees, graphs, etc. For example, in an image editing program, the pixel data of the image may be stored in a two-dimensional array to facilitate various processing operations on the image.

[0028] Program data is used to implement various functions and business logic of the program. For example, in an e-commerce website program, program data such as product information, user shopping cart data, and order data are used to implement functions such as product display, shopping cart management, and order processing.

[0029] It is also used to transfer information between different modules or components of a program. For example, in a game program, the position, health, attack power and other data of the game character need to be transferred and shared between different modules of the game engine (such as rendering module, physics engine module, artificial intelligence module, etc.) to realize the normal operation of the game.

[0030] Actual measurement data is the data obtained by measuring various physical quantities, phenomena or processes in the physical world through measuring instruments, sensors or other measuring equipment. For example, in meteorological observation, the temperature, air pressure, humidity and other data measured by instruments such as thermometers, barometers and hygrometers are measurement data.

[0031] These data reflect the state, characteristics or behavior of the actual physical system. For example, in the industrial production process, the equipment operation parameter data measured by various sensors installed on the production equipment (such as temperature sensors, pressure sensors, flow sensors, etc.) are used to monitor the stability of the production process and product quality.

[0032] The type of measurement data usually corresponds to the physical quantity being measured, such as length, mass, time, current, voltage, etc. For example, length measurement data may be of floating point type, representing the measurement value in meters, centimeters, or other length units. Measurement data is used to monitor, control, and optimize physical systems.

[0033] The actual measurement data may be data obtained by an actual measurement tool.

[0034] Step S102, training a neural network using the program data of the historical production batches and actual measurement data to obtain a control model;

[0035] The program data and actual measurement data of historical production batches can be input into the neural network to obtain a control model.

[0036] Among them, artificial neural network (ANN) is a mathematical model or computational model that imitates the structure and function of biological neural networks. It is composed of a large number of interconnected artificial neurons, which simulate the information processing method of biological neurons by receiving input signals, processing them and generating output signals.

[0037] In biological nervous systems, neurons are connected to each other through synapses to transmit and process information. In neural networks, artificial neurons are connected through weights, which are similar to the strength of synapses. For example, when a neuron receives multiple input signals, these signals are weighted and summed according to the weight of the connection, which is similar to the process of biological neurons integrating incoming signals from different synapses.

[0038] Step S103, obtaining real-time program data of the current production batch;

[0039] The real-time program data of the current production batch may be obtained by reading the parameters and information of the production equipment in the current production batch.

[0040] Step S104, inputting the real-time program data into the control model to obtain the predicted measurement data output by the control model;

[0041] Since the control model has been trained, the real-time program data can be input into the control model to predict the measurement data through the control model to obtain predicted measurement data.

[0042] Step S105: performing production control according to the predicted measurement data.

[0043] Among them, once the predicted measurement data is obtained, the production equipment can be controlled according to the predicted measurement data, such as adjusting the control parameters of the production equipment.

[0044] It is not difficult to find that, compared with the related art, in the solution provided by the embodiment of the present application, by obtaining the program data and actual measurement data of the historical production batches; training the class neural network through the program data and actual measurement data of the historical production batches, obtaining the control model; obtaining the real-time program data of the current production batch; inputting the real-time program data into the control model to obtain the predicted measurement data output by the control model; and performing production control according to the predicted measurement data. By adopting this solution, there is no need to operate the measurement tool, saving the time of collecting measurement data, improving production efficiency, and eliminating the risk of operating the measurement tool, saving manpower consumption.

[0045] In this embodiment, optionally, the real-time process data of the current production batch is collected through an error detection and classification system.

[0046] In this solution, real-time program data can be obtained through an error detection and classification system during the production process of semiconductor devices such as wafers of the current production batch.

[0047] Fault Detection and Classification (FDC) system is a comprehensive system used to monitor, identify and classify abnormal behaviors and faults in equipment, systems or processes. It aims to detect potential problems in a timely manner and reduce the impact of faults on production, operations or services.

[0048] In industrial production, FDC systems can help companies avoid unexpected equipment downtime and improve equipment reliability and availability. For example, in the semiconductor manufacturing process, minor equipment failures may lead to reduced product quality. FDC systems can detect failures in the early stages of the process, thereby reducing scrap rates.

[0049] In a complex software system, the FDC system can monitor the system's operating status in real time. When an abnormal situation occurs, it can promptly issue an alarm and classify it so as to quickly locate and solve the problem.

[0050] FDC systems typically include:

[0051] Data acquisition module, sensors and data sources,FDC systems need to collect data from various data sources. In industrial environments, this may include temperature sensors, pressure sensors, vibration sensors, etc. installed on equipment, which measure the operating parameters of the equipment in real time. For example, in a wind turbine, temperature and vibration sensors installed in key parts such as the gearbox and generator collect data to monitor the health of the equipment.

[0052] The frequency and accuracy of data acquisition are crucial to the performance of the FDC system. For some high-speed equipment, high-frequency data acquisition (such as collecting data several times or even dozens of times per second) may be required to capture possible fault signals. At the same time, the accuracy of the data must meet the requirements for accurate judgment of the equipment status. For example, the accuracy of the temperature sensor may need to reach ±0.1℃.

[0053] In the data analysis module, the collected data usually needs to be preprocessed, including noise removal, data normalization, outlier processing, etc. For example, in vibration signal analysis, some high-frequency noise may be introduced due to environmental factors. Removing this noise through filters can improve the quality of the data. Extract features that can reflect the state of the device or system from the preprocessed data. These features can be time domain features (such as mean, variance, peak, etc.), frequency domain features (such as spectrum peak, frequency distribution, etc.) or time-frequency domain features (such as wavelet transform coefficients, etc.). For example, in motor fault diagnosis, the amplitude of specific frequency components is extracted as fault features by performing spectrum analysis on the motor current signal. The extracted features are used to detect the occurrence of faults. Common fault detection algorithms include threshold-based methods, statistical model-based methods (such as principal component analysis PCA, independent component analysis IC A, etc.), and machine learning-based methods (such as support vector machine SVM, neural network NN, etc.). For example, in the threshold-based method, a temperature threshold is set. When the device temperature exceeds the threshold, it is judged as a temperature abnormality fault.

[0054] Classification module, once a fault is detected, it needs to be classified to determine the type and severity of the fault. The classification method can be rule-based, model-based or case-based. For example, in automobile fault diagnosis, according to different combinations of engine fault codes, rules can be formulated to classify fault types, such as ignition system fault, fuel supply system fault, etc.

[0055] Multi-classification and hierarchical classification: For complex systems, there may be multiple types of faults, which require multi-classification. At the same time, a hierarchical classification method can be used to first classify the faults into major categories and then further subdivide them into minor categories. For example, in the FDC system of a large chemical plant, the faults are first divided into two categories: equipment faults and process faults. Then, the equipment faults are further subdivided into pump faults, valve faults, etc.

[0056] Visualization and alarm module,FDC system usually provides an intuitive visualization interface, which displays the operating status and fault information of the equipment or system to the user in the form of charts, graphs, etc. For example, by drawing a real-time curve of the equipment temperature, the user can intuitively see the temperature change trend.

[0057] When a fault is detected, the system will send out an alarm signal, which can include sound alarm, light alarm, email alarm, etc. At the same time, the alarm information should contain detailed information such as the type of fault, location, severity, etc., so that operators can respond quickly.

[0058] In semiconductor manufacturing, the FDC system can monitor the equipment in the wafer manufacturing process in real time, such as etcher, photolithography machine, etc. By monitoring the key parameters of the equipment, it can timely detect equipment anomalies, such as abnormal etching rate, photolithography alignment deviation, etc., and classify them, so as to take corresponding maintenance measures to ensure the quality and production efficiency of the wafer.

[0059] In this embodiment, optionally, real-time measurement data of the current production batch is obtained as standard data, including:

[0060] Acquire real-time measurement data of the current production batch, perform pre-processing on the real-time measurement data, and obtain pre-processing result data;

[0061] The pre-processing result data is used as standard data.

[0062] Among them, the real-time measurement data can be standardized through pre-processing to avoid incorrect guidance of subsequent model improvements due to erroneous or imperfect real-time measurement data.

[0063] In this embodiment, optionally, real-time measurement data of the current production batch is obtained, and pre-processing is performed on the real-time measurement data to obtain pre-processing result data, including:

[0064] The real-time measurement data of the current production batch is obtained, and data cleaning, outlier processing and data conversion are performed on the real-time measurement data to obtain pre-processing result data.

[0065] Pre-processing of real-time measurement data is a key step in the data analysis process. For example, from the perspective of data cleaning, missing values ​​can be processed, such as using the deletion method. When the number of missing values ​​is small and has little impact on the overall data, the records containing missing values ​​can be directly deleted. For example, in a data set, if a row of data is missing a less critical attribute value, and the missing situation only accounts for a very small proportion of the entire data set, then this row of data can be considered deleted. Or, for numerical data, if a variable has missing values, the mean of the variable can be used to fill the missing values. For example, in the test score data of students in a class, some students have missing scores in a certain subject. The average score of the subject can be calculated to fill these missing values. Or, similar to mean interpolation, when the data has a skewed distribution, the median may better represent the central trend of the data. At this time, the median can be used to fill the missing values. For example, when counting resident income data, if some resident income values ​​are missing, and income data often has a skewed distribution, it is more appropriate to use median interpolation. Or, it is suitable for categorical data or discrete data. For example, when investigating consumers' preferences for a certain brand, if the brand preference values ​​in some records are missing, the brand with the highest frequency (i.e., the mode) can be used to fill in the gaps. Alternatively, by building a regression model, other related variables can be used to predict missing values. For example, it is known that variables such as house area and number of bedrooms have a linear relationship with house prices. When house price data is missing, a regression model based on these variables can be built to predict the missing house prices.

[0066] Pre-processing can also include outlier processing. When outliers are obviously caused by data collection errors or other identifiable reasons and have a greater impact on the analysis results, these outliers can be deleted. For example, when measuring human body temperature data, if an outlier appears that is obviously beyond the normal body temperature range (such as 45°C) and may be caused by a failure of the measuring instrument, the data point can be deleted. If the outlier is caused by data entry errors and other reasons, it can be corrected by checking the original data. For example, when counting the sales of goods, it is found that the sales data of a certain day is obviously too high. After inspection, it is found that the unit of sales is written incorrectly (such as writing yuan as ten thousand yuan), then the data can be corrected.

[0067] Pre-processing can also perform data conversion, such as standardization and normalization.

[0068] In this embodiment, optionally, the actual measurement data is obtained by measuring with an actual measurement tool.

[0069] Among them, the purpose of metrology operations is to ensure the quality of semiconductor devices. These operations include process qualification, tool qualification, daily tool monitoring, periodic tool maintenance, tool recovery monitoring, process control monitoring, and product monitoring. Currently, these operations are achieved by operators operating metrology tools. However, the cost of obtaining metrology tools is very high. Furthermore, in addition to the main process steps, additional manpower is required to operate the metrology equipment. These additional manpower operations will increase the product cycle time.

[0070] Through such a setting, this solution can comprehensively acquire the measurement data, so as to extract the implicit correlation between the measurement data and the program data in the subsequent model training process, so as to train the control model.

[0071] Second embodiment

[0072] The second embodiment of the present application relates to a production control method based on virtual measurement prediction data. The second implementation method is an improvement on the first embodiment, and the specific improvement is that after obtaining the real-time program data of the current production batch, the method also includes: obtaining the real-time measurement data of the current production batch as standard data; comparing whether there is a difference between the predicted measurement data and the standard data; if there is a difference, adjusting the parameters of the control model based on the standard data.

[0073] Step S201, obtaining real-time measurement data of the current production batch as standard data;

[0074] The real-time measurement data of the current production batch can be obtained by automatic measurement through some automated measurement tools, or by determining key measurement data according to needs and collecting the key measurement data through corresponding measurement tools.

[0075] Step S202, comparing whether there is a difference between the predicted measurement data and the standard data;

[0076] After obtaining the real-time measurement data of the current production batch, it can be compared with the predicted measurement data obtained by prediction to identify whether there is a difference between the two.

[0077] Here, if a certain difference threshold is exceeded, it can be determined that there is a difference, and if the difference threshold is not exceeded, it can be determined that there is no difference.

[0078] Step S203: If yes, adjust the parameters of the control model based on the standard data.

[0079] In the case of a difference, the control model can be adjusted based on the standard data. Specifically, the standard data can be given to the control model alone to adjust the parameters. Alternatively, the real-time measurement data and the standard data with a difference can be input into the control model in the form of a data pair to adjust the parameters of the control model.

[0080] In this embodiment, optionally, the real-time measurement data of the current production batch is collected through a statistical program control system.

[0081] This solution can collect the real-time measurement data of the current production batch as the basis for updating and iterating the control model, so as to more accurately predict the measurement data and improve the control accuracy.

[0082] The technical solution provided in this embodiment can be used to obtain the real-time measurement data of the current production batch. When there is a difference between the predicted value and the real-time measurement data, it can be used to update and iterate the control model to improve the prediction accuracy of the control model.

[0083] The present invention provides a measurement method and a virtual measurement system, and in particular, relates to a virtual measurement system and method suitable for semiconductor manufacturing. By receiving program data and measurement data of previous batches, predictive data for the next batch of production but not measured is generated based on the program data and measurement data through a learning control model. A virtual measurement system suitable for a manufacturing plant includes an error detection and classification system for receiving program data, and a statistical process control system for performing statistical process control on historical physical measurement data to generate measurement data, and a virtual measurement system for generating predictive data based on the program data and measurement data through a learning control model. The measurement method and virtual measurement system provided by the present invention can improve the cycle time of product manufacturing by reducing actual process or tool monitoring data.

[0084] The virtual measurement system provides a data pre-processing mechanism for collecting measurement data sensed in real time by manufacturing equipment and performing pre-processing on the measurement data. Furthermore, the virtual measurement system includes an interface connected to statistical process control (SPC) for learning a control model. One method of generating a control model is through machine learning. However, other methods can also be used to generate a control model, such as generating a learning model of a virtual measurement controller.

[0085] The virtual measurement system is a model learning application that can be integrated with other components to generate real-time prediction data. It includes statistical process control systems and fault detection and classification (FDC) systems. Once the prediction data is generated, the virtual measurement system automatically adjusts the attributes of the control model to be suitable for learning using a self-adjusting mechanism. The self-adjusting mechanism can detect the difference between the prediction data and the actual measurement data through the measurement tool.

[0086] The virtual measurement operation provided by the present invention has several advantages, including a method for providing quality assurance without the need for physical measurement operations. When compared with external measurement methods, the method can improve the cycle time of product manufacturing by reducing the actual process or tool monitoring data. The method can reduce operating costs by reducing the frequency of daily tool monitoring and the frequency of product wafer monitoring. In addition, the method can improve product yield by providing integrated wafer quality prediction values. This prediction value cannot be measured on the resulting wafer. Furthermore, the method can reduce manpower load by excluding some wafer or tool monitoring. The method can improve tool availability by reducing tool monitoring time, and provide a tool prognostic system to support extended tool monitoring cycles.

[0087] In addition, some embodiments of the present application also provide an electronic device. The electronic device may be a digital computer in various forms, such as a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, etc. The electronic device may also be a mobile device in various forms, such as a personal digital processing, a cellular phone, a smart phone, a wearable device, and other similar computing devices.

[0088] The electronic device includes: one or more processors; and a memory storing computer program instructions, wherein when the computer program instructions are executed, the processor executes the steps of the method provided in any one or more of the above embodiments. Figure 3 An exemplary structural diagram of the electronic device is disclosed. Figure 3 As shown, the electronic device includes: one or more processors 301, a memory 302, and an interface for connecting each component, including a high-speed interface and a low-speed interface. The various components are connected to each other using different buses and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the electronic device, including instructions stored in or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some other embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Among them, the components shown in this article, their connections and relationships, and their functions are only used as examples, and are not intended to limit the implementation of the present application described and / or required herein.

[0089] The electronic device may further include: an input device 303 and an output device 304. The processor 301, the memory 302, the input device 303 and the output device 304 may be connected via a bus or other means. Figure 3 The example of connecting through bus is taken in the following.

[0090] The input device 303 can receive input digital or character information, and generate key signal input related to the user settings and function control of the electronic device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick and other input devices. The output device 304 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The display device may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display and a plasma display. In some embodiments, the display device may be a touch screen.

[0091] To provide interaction with a user, the electronic device may be a computer. The computer has: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball), through which the user can provide input to the computer. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0092] In the embodiments of the present application, a computer program / instruction is stored on a computer-readable medium, and when the computer program / instruction is executed by a processor, the steps of the method provided by any one or more of the above embodiments are implemented. The computer-readable medium may be included in the electronic device described in the above embodiments; or it may exist independently without being assembled into the device. The above computer-readable medium carries one or more computer-readable instructions.

[0093] The memory 302 can be used as a non-transient computer-readable storage medium, which can be used to store non-transient software programs, non-transient computer executable programs and modules. The processor 301 executes various functional applications and data processing of the server by running the non-transient software programs, instructions and modules stored in the memory 302, so as to implement the program instructions / modules corresponding to the method provided by any one or more of the above embodiments in the embodiments of the present application.

[0094] The memory 302 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 302 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage devices. In some embodiments, the memory 302 may optionally include a memory remotely arranged relative to the processor 301, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0095] It should be noted that the computer-readable medium described in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device.

[0096] Computer readable media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, modules of programs or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device.

[0097] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0098] In the above-described embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. For example, it can be implemented by using an application specific integrated circuit (ASIC), a general-purpose computer or any other similar hardware device. In certain embodiments, the software program of the present application can be executed by a processor to implement the above steps or functions. Similarly, the software program of the present application (including relevant data structures) can be stored in a computer-readable recording medium, for example, a RAM memory, a magnetic or optical drive or a floppy disk and similar devices. In addition, some steps or functions of the present application can be implemented by hardware, for example, as a circuit that cooperates with a processor to perform each step or function.

[0099] The computer program product provided in the embodiment of the present application includes one or more computer programs / instructions, and when the computer program / instructions are executed by the processor, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from a computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state disk (SSD)), etc.

[0100] The flow chart or block diagram in the accompanying drawings shows the possible architecture, function and operation of the equipment, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated system for hardware that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0101] The scope of the present application is defined by the appended claims rather than the above description, and it is intended that all changes that fall within the meaning and scope of the equivalent elements of the claims are included in the present application. Any figure mark in the claims should not be regarded as limiting the claims involved. In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the device claim may also be implemented by one unit or device through software or hardware. The words "first", "second", etc. are only used to distinguish the description, and do not indicate any particular order, nor can they be understood as indicating or implying relative importance.

[0102] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily mention changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims, and the above embodiments should be regarded as exemplary and non-restrictive.

Claims

1. A production control method based on virtual measurement prediction data, characterized in that: Obtain process data and actual measurement data of historical production batches; The control model is obtained by training the quasi-neural network through the program data and actual measurement data of the historical production batches; Get real-time process data for the current production batch; Inputting the real-time program data into the control model to obtain predicted measurement data output by the control model; Production control is performed according to the predicted measurement data.

2. The method according to claim 1, characterized in that After acquiring the real-time process data of the current production batch, the method further includes: Obtain real-time measurement data of the current production batch as standard data; Comparing whether there is a difference between the predicted measurement data and the standard data; If so, parameters of the control model are adjusted based on the standard data.

3. The method according to claim 2, characterized in that The real-time measurement data of the current production batch is collected through a statistical program control system.

4. The method according to claim 1, characterized in that The real-time process data of the current production batch is collected by the error detection and classification system.

5. The method according to claim 1, characterized in that Obtain real-time measurement data of the current production batch as standard data, including: Acquire real-time measurement data of the current production batch, perform pre-processing on the real-time measurement data, and obtain pre-processing result data; The pre-processing result data is used as standard data.

6. The method according to claim 5, characterized in that Acquire the real-time measurement data of the current production batch, perform pre-processing on the real-time measurement data, and obtain pre-processing result data, including: The real-time measurement data of the current production batch is obtained, and data cleaning, outlier processing and data conversion are performed on the real-time measurement data to obtain pre-processing result data.

7. The method according to claim 1, characterized in that The actual measurement data is obtained by measuring with an actual measurement tool.

8. An electronic device, characterized in that: The electronic device comprises: one or more processors; and A memory storing computer program instructions, which, when executed, cause the processor to perform the steps of the method as claimed in any one of claims 1 to 7.

9. A computer readable medium having a computer program / instructions stored thereon, characterized in that: When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images