Self-adaptive energy digital twin simulation device and method for semiconductor equipment

Abstract

The invention discloses a self-adaptive digital twin simulation device and method for semiconductor equipment. The device comprises a data acquisition module, a simulation model construction and operation module and a parameter updating module which are connected through signals. The data acquisition module is used for acquiring production information and process parameter information of a semiconductor product and acquiring actual processing data in real time; the simulation model construction and operation module constructs a process equipment energy consumption simulation model according to a preset process equipment configuration unit, fuses production information and process parameter information of a semiconductor product, operates the process equipment energy consumption simulation model, and gives energy consumption simulation data in real time; and the parameter updating module is used for updating the process parameter information in the process equipment energy consumption simulation model. A real-time data feedback mechanism is introduced by setting a parameter updating module, process parameter information is dynamically updated, and the accuracy and the real-time performance of the process equipment energy consumption simulation model are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of equipment simulation, and particularly relates to an adaptive digital twin simulation device and method for energy consumption of semiconductor equipment. Background Art

[0002] During the operation of process equipment, multiple power supplies are required. Mastering the power consumption of each process equipment at different times and in different states can provide data references for process parameter adjustment, equipment maintenance, energy conservation and consumption reduction, etc.

[0003] Currently, for the power supply of process equipment, a zonal supply method is usually adopted. There is only one general monitoring instrument in each zone, and the power consumption of individual process equipment is not monitored. Moreover, the process equipment in one zone includes multiple functions and multiple models, and it is impossible to determine the power consumption of each process equipment.

[0004] Patent CN116579273A discloses a dynamic power consumption simulation method and system for semiconductor equipment. The method includes: determining the model of the process equipment and the process; disassembling the power consumption units of the process equipment; grouping the power consumption units according to the power consumption characteristics; establishing a power consumption dataset according to the grouping of the power consumption units; establishing a dynamic power consumption simulation model according to the production rhythm and processing flow of the process equipment and the process, and inputting the power consumption dataset into the dynamic power consumption simulation model; running the dynamic power consumption simulation model and performing real-time state capture, and dynamically outputting the power consumption of the real-time state of the semiconductor equipment. This method can realize the dynamic simulation of the power consumption of process equipment, and can present the power consumption curve of the equipment in a certain period, which is convenient for data analysis.

[0005] On the one hand, the above simulation method only simulates the power consumption data and is not applicable to process equipment with multiple power supplies; on the other hand, the simulation of the power consumption data in the above simulation method uses a simulation model with fixed parameters, and the accuracy of the model is limited.

[0006] How to perform energy consumption simulation on process equipment with multiple power supplies while improving the accuracy of energy consumption simulation is a problem that needs to be solved currently. Summary of the Invention

[0007] In view of the defects existing in the above-mentioned prior art, the present invention provides an adaptive digital twin simulation device and method for energy consumption of semiconductor equipment. The device includes a data acquisition module, a simulation model construction and operation module, and a parameter update module connected by signals. The data acquisition module is used to obtain the production information and process parameter information of semiconductor products, and in real time obtain the actual processing data of process equipment. The simulation model construction and operation module is used to construct an energy consumption simulation model for process equipment according to a preset process equipment configuration unit, integrate the production information and process parameter information of semiconductor products, run the energy consumption simulation model for process equipment, and give energy consumption simulation data in real time. The parameter update module is used to update the process parameter information in the energy consumption simulation model for process equipment, wherein the updated process parameter information is given based on the analysis of the actual processing data of the process equipment. Based on the analysis of the actual processing data of the process equipment and combined with the energy consumption simulation data, the process parameter information in the energy consumption simulation model for process equipment is updated. By setting up a parameter update module to introduce a real-time data feedback mechanism, the process parameters in the energy consumption simulation model for process equipment are dynamically updated, improving the accuracy and real-time performance of the energy consumption simulation model for process equipment.

[0008] In a first aspect, the present invention provides an adaptive digital twin simulation device for energy consumption of semiconductor equipment, specifically including: A data acquisition module, a simulation model construction and operation module, and a parameter update module connected by signals; The data acquisition module is used to obtain the production information and process parameter information of semiconductor products, and in real time obtain the actual processing data of process equipment; The simulation model construction and operation module is used to construct an energy consumption simulation model for process equipment according to a preset process equipment configuration unit, integrate the production information and process parameter information of semiconductor products, run the energy consumption simulation model for process equipment, and give energy consumption simulation data in real time; The parameter update module is used to update the process parameter information in the energy consumption simulation model for process equipment, wherein the updated process parameter information is given based on the analysis of the actual processing data of the process equipment.

[0009] Furthermore, the process equipment configuration unit includes a plurality of station sub-units and a plurality of manipulator sub-units; Constructing an energy consumption simulation model for process equipment according to a preset process equipment configuration unit specifically includes: Obtaining a preset process equipment configuration unit; Combining the connection relationships of each station sub-unit and each manipulator sub-unit in the process equipment configuration unit, and integrating the energy consumption logic of the process equipment to construct an energy consumption simulation model for process equipment.

[0010] Further, the production information includes the production time, processing batch, and process technology information of the semiconductor product. The process parameter information includes the set running time and set energy consumption of each station in the process equipment during the processing of the semiconductor product. The actual processing data includes the actual processing time and actual energy consumption data. The parameter update module includes a first update sub-module, a second update sub-module, and a third update sub-module; The first update sub-module is used to analyze the actual processing data of the process equipment within a preset time period, update the set running time and set energy consumption of each station in the current process parameter information during the processing of the semiconductor product, and give the first process parameter information; The second update sub-module is used to determine the current processing batch of the process equipment, and update the set energy consumption and set running time of each station in the current process parameter information during the semiconductor product processing according to the actual processing data of the process equipment corresponding to the associated processing batch, and give the second process parameter information; The third update sub-module is used to determine the current processing time, and update the current process parameter information in combination with a fixed update strategy, and give the third process parameter information.

[0011] Further, analyzing the actual processing data of the process equipment within a preset time period, updating the set running time and set energy consumption of each station in the current process parameter information during the processing of the semiconductor product, and giving the first process parameter information specifically includes: Obtain the actual energy consumption data of the process equipment at each moment within the preset time period; Perform data cleaning on the actual energy consumption data at each moment to obtain standard energy consumption data; According to the change situation of the standard energy consumption data at each moment, obtain a standard energy consumption curve, and give the average value of the standard energy consumption data; Combine the average value of the standard energy consumption data and the actual processing time of each station in the process equipment to update the set running time and set energy consumption of each station in the current process parameter information during the semiconductor product processing, and obtain the first process parameter information.

[0012] Further, determining the current processing batch of the process equipment, and updating the set energy consumption and set running time of each station in the current process parameter information during the semiconductor product processing according to the actual processing data of the process equipment corresponding to the associated processing batch, and giving the second process parameter information specifically includes: Determine the current processing batch of the process equipment; According to the association relationship of each processing batch, give the actual processing data of the process equipment corresponding to the associated processing batch of the current processing batch; Clean the actual processing data of the process equipment for associated processing batches, remove outliers and null values from the actual processing data, and provide standard processing data; Based on the change analysis of the standard processing data, update the set energy consumption and set running time of each station in the current process parameter information during the semiconductor product processing, and provide the second process parameter information.

[0013] Furthermore, determine the current processing time, and combine it with a fixed update strategy to update the current process parameter information and provide the third process parameter information, specifically including: Determine the current processing time. If the current processing time is the time value in the preset update schedule, trigger the fixed update strategy; where the fixed update strategy is to obtain the latest process parameter information; Update the current process parameter information and provide the third process parameter information.

[0014] Furthermore, run the energy consumption simulation model of the process equipment and provide the energy consumption simulation data in real time, specifically including: According to the current process parameter information, use the energy consumption simulation model of the process equipment to simulate the energy consumption of the process equipment and provide the initial energy consumption simulation data; Combine the actual energy consumption data of the process equipment to provide an energy consumption simulation correction coefficient; According to the energy consumption simulation correction coefficient, correct the initial energy consumption simulation data and provide the energy consumption simulation data in real time.

[0015] Furthermore, combine the actual energy consumption data of the process equipment to provide an energy consumption simulation correction coefficient, specifically including: Analyze the difference between the actual energy consumption data and the initial energy consumption simulation data according to the actual energy consumption data and the initial energy consumption simulation data of the process equipment per unit time, and provide a sub-correction coefficient; Combine all the sub-correction coefficients within a preset time period, analyze the change situation of the sub-correction coefficients, and provide the energy consumption simulation correction coefficient.

[0016] Furthermore, the energy consumption simulation correction coefficient is specifically expressed as:

[0017] Among them, is the energy consumption simulation correction coefficient, is the sub-correction coefficient for the nth unit time, is the initial energy consumption simulation data for the nth unit time, is the actual energy consumption data for the nth unit time.

[0018] Second aspect, the present invention further provides an adaptive digital twin simulation method for energy consumption of semiconductor devices, which is applied to the adaptive digital twin simulation device for energy consumption of semiconductor devices as described in any one of the above, including: Obtain the production information and process parameter information of semiconductor products, and in real time, obtain the actual processing data of process equipment; According to the preset process equipment configuration unit, construct an energy consumption simulation model for process equipment, integrate the production information and process parameter information of semiconductor products, run the energy consumption simulation model for process equipment, and give energy consumption simulation data in real time; Update the process parameter information in the energy consumption simulation model for process equipment, wherein the updated process parameter information is given based on the analysis of the actual processing data of the process equipment.

[0019] An adaptive digital twin simulation device and method for energy consumption of semiconductor devices provided by the present invention at least have the following beneficial effects: (1) Through the data acquisition module and the simulation model construction and operation module, based on the preset process equipment configuration unit, complete the construction of the energy consumption simulation model for process equipment. Combined with the parameter update module, based on the analysis of the actual processing data and energy consumption simulation data of the process equipment, update the process parameter information in the energy consumption simulation model for process equipment, and give energy consumption simulation data; By setting the parameter update module to introduce a real-time data feedback mechanism, dynamically update the current process parameter information in the energy consumption simulation model for process equipment, and improve the accuracy and real-time performance of the energy consumption simulation model for process equipment.

[0020] (2) Through the first update sub-module, the second update sub-module and the third update sub-module in the parameter update module, update the current process parameter information in different dimensions respectively, and correct the energy consumption simulation model for process equipment, further ensuring the simulation accuracy of the energy consumption simulation model for process equipment.

[0021] (3) Based on the initial energy consumption simulation data obtained by correcting the current process parameter information, combined with the energy consumption correction coefficient, correct the initial energy consumption simulation data, and output the energy consumption simulation data, improving the accuracy of the output prediction result of the energy consumption simulation model for process equipment. Description of the Drawings

[0022] Figure 1 It is a structural block diagram of the adaptive digital twin simulation device for energy consumption of semiconductor devices provided by an embodiment of the present invention; Figure 2 It is a flowchart of constructing an energy consumption simulation model for process equipment provided by an embodiment of the present invention; Figure 3 It is a schematic diagram of the wafer processing process provided by an embodiment of the present invention; Figure 4Flowchart for determining the first process parameter information provided by an embodiment of the present invention; Figure 5 Flowchart for determining the second process parameter information provided by an embodiment of the present invention; Figure 6 Flowchart for determining the third process parameter information provided by an embodiment of the present invention; Figure 7 Operating schematic diagram of an adaptive digital twin simulation device for energy consumption of semiconductor equipment provided by an embodiment of the present invention; Figure 8 Flowchart of an adaptive digital twin simulation method for energy consumption of semiconductor equipment provided by an embodiment of the present invention.

[0023] Among them, 10 is a data acquisition module; 20 is a simulation model construction and operation module; 30 is a parameter update module; 31 is a first update sub-module; 32 is a second update sub-module; 33 is a third update sub-module. Detailed implementation manners

[0024] In order to better understand the above technical solutions, the above technical solutions will be described in detail below in conjunction with the accompanying drawings of the specification and specific implementation manners. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0025] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "the" and "said" used in the embodiments of the present invention and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise. "Plural" generally includes at least two.

[0026] It should also be noted that the term "comprising", "including" or any other variation thereof is intended to cover a non-exclusive inclusion, so that a commodity or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such commodity or device. Without further limitations, an element defined by the statement "including one..." does not exclude the existence of another identical element in the commodity or device including said element.

[0027] Energy costs account for a relatively large proportion in the production costs of enterprises. Through energy consumption simulation of process equipment, energy demand can be predicted in advance, energy distribution can be optimized, and energy consumption can be reduced, thereby effectively controlling the production costs of enterprises.

[0028] The power consumption of process equipment is related to the commissioning of the machine tool and the setting of process parameters. The current energy consumption simulation model has the following problems: (1) There is a deviation between the set value and the actual operating value of the process parameters; (2) During the operation of the machine tool, the process equipment will adjust the process parameters of a batch of products in real time according to the processing conditions, resulting in a large gap between the predicted energy consumption value output by the energy consumption simulation model and the actual value.

[0029] In summary, the current energy consumption simulation model can only make predictions based on fixed process parameters and cannot keep pace with the process parameters of on-site process equipment. If the process parameters in the energy consumption simulation model need to be adjusted, manual intervention is required, and the energy consumption simulation model lacks the ability of self-learning or self-adaptation. When the operating conditions of the process equipment are complex or dynamically changing, the simulation accuracy of the energy consumption simulation model will decrease significantly.

[0030] Therefore, the present invention proposes an adaptive digital twin simulation device for the energy consumption of semiconductor equipment, including a data acquisition module 10, a simulation model construction and operation module 20, and a parameter update module 30 connected by signals; the data acquisition module 10 is used to acquire the commissioning information and process parameter information of semiconductor products, and to acquire the actual processing data of process equipment in real time; the simulation model construction and operation module 20 is used to construct an energy consumption simulation model of process equipment according to a preset process equipment configuration unit, integrate the commissioning information and process parameter information of semiconductor products, run the energy consumption simulation model of process equipment, and give energy consumption simulation data in real time; the parameter update module 30 is used to update the process parameter information in the energy consumption simulation model of process equipment, wherein the updated process parameter information is given based on the analysis of the actual processing data of process equipment. By setting the parameter update module 30 to introduce a real-time data feedback mechanism, the process parameters in the energy consumption simulation model of process equipment are dynamically updated, improving the accuracy and real-time performance of the energy consumption simulation model of process equipment.

[0031] Such as Figure 1As shown in the figure, an energy digital twin simulation device for an adaptive semiconductor device is provided in an embodiment of the present invention, which specifically includes a data acquisition module 10, a simulation model construction and operation module 20, and a parameter update module 30 that are connected by signals. The data acquisition module 10 acquires the production information and process parameter information of semiconductor products, and, in real time, acquires the actual processing data of process equipment. Among them, the production information includes the production time, processing batch, and process information of semiconductor products, the process parameter information includes the set operation time and set energy consumption during the processing of semiconductor products at each station in the process equipment, and the actual processing data includes the actual processing time and actual energy consumption data. The simulation model construction and operation module 20 constructs an energy consumption simulation model of the process equipment according to the preset process equipment configuration unit, integrates the production information and process parameter information of semiconductor products, runs the energy consumption simulation model of the process equipment, and gives energy consumption simulation data in real time. Among them, the process equipment configuration unit includes a plurality of station sub-units and a plurality of manipulator sub-units. The parameter update module 30 updates the process parameter information in the energy consumption simulation model of the process equipment, where the updated process parameter information is given based on the analysis of the actual processing data of the process equipment.

[0032] It should be understood that the actual processing time is the processing time of each station or manipulator during the processing of semiconductor products, and the actual energy consumption data is the energy consumption of each station or manipulator during the processing of semiconductor products. The set operation time is the processing time of each manipulator sub-unit or station sub-unit in the energy consumption simulation model of the process equipment, and the set energy consumption is the energy consumption of each manipulator sub-unit or station sub-unit in the energy consumption simulation model of the process equipment. The above set operation time and set energy consumption can be data set by relevant personnel according to the actual situation, or can be data obtained after being updated by the parameter update module 30, and no limitation is made thereto.

[0033] In the embodiments provided by the present invention, data acquisition including production start information and process parameter information is achieved by using the manufacturing execution system (MES) and the resource management system (RMS) in the factory. The process parameter information is updated by the parameter update module 30, which combines the intelligent equipment system (IES), the fault detection and classification (FDC) system, and the advanced process control (APC) system. Finally, by obtaining and analyzing the actual energy consumption data provided by the supervisory control and data acquisition (SCADA) system, an energy consumption simulation correction coefficient is given to obtain energy consumption simulation data. The present invention constructs a dynamic process equipment twin system through the above device and can give the energy consumption simulation data of the power of each process equipment at different time periods.

[0034] Among them, MES is a system for monitoring and managing the manufacturing process, connecting the semiconductor factory's Enterprise Resource Planning (EPR) system and shop floor equipment, tracking production progress, quality, equipment status, etc. in real time, and optimizing production efficiency. Among them, the semiconductor factory ERP system is management software designed specifically for semiconductor enterprises, integrating multiple core modules such as supply chain, production control, quality management, and financial management. It can help semiconductor factories achieve refined management of production processes, intelligent inventory control, and integration of financial operations, assist enterprises in optimizing resource allocation, improving operational efficiency, strengthening cost control, and providing real-time and accurate data support for enterprise decision-making. RMS is a production process recipe management system for setting and controlling the entire process equipment, including manpower, equipment, materials, etc., ensuring efficient utilization of resources and supporting production planning and scheduling. APC is an advanced control technology used in the field of industrial automation, aiming to optimize the performance of complex industrial processes. It improves production efficiency, product quality, and resource utilization rate by real-time monitoring, analyzing, and adjusting key parameters in the production process. The IES system and FDC system monitor the energy consumption of equipment within a certain time window during the production process by real-time collecting and analyzing equipment sensor data, that is, monitoring the actual processing time and actual energy consumption data of process equipment during the production process. SCADA is used for monitoring and controlling industrial processes in the facility system, collecting data in real time and providing a visual interface, supporting remote operation and automated control. The facility system covers various infrastructures and working environments supporting chip production, including water, electricity, gas supply, wastewater treatment, HVAC system (heating, ventilation, and air conditioning), etc. By real-time data collection and analysis, it ensures the normal operation of equipment and environmental parameters meet production requirements, thus guaranteeing the quality and output of semiconductor products.

[0035] Referring to Figure 2 , according to the preset process equipment configuration unit, construct an energy consumption simulation model for process equipment, specifically including: Obtain the preset process equipment configuration unit; Combining the connection relationships of each station subunit and each manipulator subunit in the process equipment configuration unit, integrate the energy consumption logic of the process equipment to construct an energy consumption simulation model for process equipment.

[0036] In the embodiment provided by the present invention, the energy consumption simulation model for process equipment is constructed by the simulation software PlantSimulation. The energy consumption simulation model for process equipment simulates the power energy consumption during the processing operation of the process equipment and monitors the actual energy consumption data of the process equipment. The energy consumption simulation model for process equipment is constructed by obtaining the preset process equipment configuration unit and combining the connection relationships of each station subunit and each manipulator subunit in the process equipment configuration unit, and integrating the energy consumption logic of the process equipment. The parameter update module 30 updates the process parameter information in the energy consumption simulation model for process equipment according to the actual energy consumption data of the process equipment, so as to realize the operation of the dynamic energy consumption simulation model for process equipment. Among them, the energy consumption logic refers to the energy consumption mode of the process equipment in different operating states, which is specifically described as the rules and modes of how the process equipment consumes energy (such as electric energy, gas, chemicals, etc.) in different operation stages and process conditions during the processing and manufacturing of semiconductor products. The energy consumption logic includes the energy requirements of the process equipment in different stages such as startup, operation, standby, and maintenance, as well as the energy consumption laws under different process parameters.

[0037] The energy consumption simulation model for process equipment mainly embeds all the machines in the factory and the rules for the machines to process products (i.e., all the real process equipment configuration units of the machines) into the model to simulate the real machine system. The process equipment simulation model is simulated according to the actual machine processing steps and operation logic, and is composed of different station modules and manipulator modules. It performs the processing operation of the machine according to the input settings, and finally outputs the energy consumption simulation data.

[0038] Taking wafer processing as an example, referring to Figure 3 , during the wafer processing, the wafer enters from the Loadport of the process equipment, and the manipulator grabs the wafer to the station for processing. The machine contains different numbers and types of stations, and each station contains different power energy consumption usage points. There are corresponding sensors for different usage points, and the sensors are used to monitor the real-time power energy consumption of the power energy consumption usage points. After the wafer completes the processing of each station, it is transferred to the next processing station by the manipulator, and then leaves the equipment from the Loadport after all the processing is completed. The machine processing is triggered by the production information. The production information includes the process information of the wafer, and the machine can be put into production according to the specific wafer loading time. By configuring different types and numbers of stations in the energy consumption simulation model for process equipment and inputting the processing time of each station and the set operation time and set energy consumption of different usage points of each station, the configuration and construction of the energy consumption simulation model for process equipment are completed.

[0039] Input wafers at different times according to the production start information, run the energy consumption simulation model of the process equipment. According to the process information of the wafers, enter the corresponding station sub-units for processing, and turn on the usage points. Monitor the indicators to output the daily average of the power energy consumption, and complete the model simulation.

[0040] It can be understood that the Loadport (wafer loader / unloader) is a key automated equipment in wafer processing, mainly used for the transfer and loading / unloading of wafers between different equipment.

[0041] The initial inputs (production start information and process parameter information) of the energy consumption simulation model of the process equipment are automatically obtained from the MES system and RMS system in the factory. The production start information of the machine tool is obtained from the MES system, including information such as the wafer loading time and corresponding process for each wafer, which serves as the production start input of the energy consumption simulation model of the process equipment to determine the production start of the machine tool. In addition, the machine tool process parameters (i.e., process parameter information) are automatically obtained from the RMS system, including the set operation and set energy consumption corresponding to different processes of the machine tool. Under different processes, the operation stations and station processing times of the machine tool determine the processing operation duration of the machine tool. In addition, there are multiple power energy usage points at different stations. According to the usage duration and energy consumption corresponding to each usage point, the dynamic superposition of the energy consumption under all processes of the machine tool is the energy consumption of the process equipment.

[0042] The operation results of the energy consumption simulation model of the process equipment include the instantaneous energy consumption, daily average energy consumption, and monthly average energy consumption of the process equipment at all simulation times.

[0043] Referring to Table 1 and Table 2, taking the input production start information and process parameter information as an example, a certain wafer wafer1 enters the machine tool for processing according to the wafer loading time and the corresponding process recipe1 in the production start information. According to the process parameter information, the process recipe1 will start the CH1~CHn stations to process the wafer in sequence, and the processing times are T1~Tn respectively. The usage points corresponding to the station CH1 are nozzle1~nozzle n. The superposition of the usage duration and usage amount corresponding to each usage point is the kinetic energy consumption of this station during this period. The instantaneous energy consumption is the superposition of the energy consumption of the energy consumption simulation model of the process equipment at different stations at this moment. The daily average value is the average of the instantaneous values every day, and the monthly average value is the average of the daily average values, specifically expressed as:

[0044] Among them, is the daily average value, is the nth instantaneous energy consumption value, is the monthly average value, is the daily average value corresponding to the mth day, m is the number of daily average values within a month, and n is the number of instantaneous energy consumption values within a day.

[0045] Table 1 Production Information

[0046] Table 2 Process Parameter Information

[0047] Further, the parameter update module 30 includes a first update sub-module 31, a second update sub-module 32, and a third update sub-module 33; The first update sub-module 31 is used to analyze the actual processing data of the process equipment within a preset time period, update the set running time and set energy consumption of each station in the current process parameter information during the processing of semiconductor products, and give the first process parameter information; The second update sub-module 32 is used to determine the current processing batch of the process equipment, and update the set energy consumption and set running time of each station in the current process parameter information during the processing of semiconductor products according to the actual processing data of the process equipment corresponding to the current processing batch, and give the second process parameter information; The third update sub-module 33 is used to determine the current processing time, and update the current process parameter information in combination with a fixed update strategy, and give the third process parameter information.

[0048] Further, referring to Figure 4 , the first process parameter information is given, specifically including: Obtain the actual energy consumption data of the process equipment at each moment within the preset time period; Perform data cleaning on the actual energy consumption data at each moment to obtain standard energy consumption data; According to the change situation of the standard energy consumption data at each moment, obtain a standard energy consumption curve, and give the average value of the standard energy consumption data; Combine the average value of the standard energy consumption data and the actual processing time of each station in the process equipment to update the set running time and set energy consumption of each station in the current process parameter information during the processing of semiconductor products, and obtain the first process parameter information.

[0049] In a specific implementation, the IES system and the FDC system will regularly update and adjust the process parameter information of the process equipment energy simulation model according to the actual machine operation conditions and energy consumption, so that the results output by the process equipment energy simulation model are closer to the actual values. In a specific example, the preset time period is that the process parameter information is adjusted once every preset time period through the IES system and the FDC system to give a first process parameter information. The specific process is: obtain the actual energy consumption data at each moment in the corresponding preset time period, and then clean the actual energy consumption data, eliminate abnormal values ​​and null values ​​in the actual energy consumption data, and obtain standard energy consumption data. According to the changes in the standard energy consumption data at each moment, a standard energy consumption curve is obtained. Then the average value of the standard energy consumption data in the preset time period is calculated to give the first process parameter information. The current process parameter information is updated according to the first process parameter information, so as to correct the process equipment energy simulation model. Average value Specifically expressed as:

[0050] in, for The standard energy consumption data corresponding to the t-th moment, for The number of internal moments.

[0051] Further, refer to Figure 5 , giving the second process parameter information, specifically including: Determine the current processing batch of the process equipment; According to the correlation relationship between each processing batch, the actual processing data of the process equipment of the processing batch corresponding to the current processing batch is given; Perform data cleaning on the actual processing data of the process equipment associated with the processing batch, remove abnormal values ​​and null values ​​in the actual processing data, and provide standard processing data; Based on the analysis of changes in the standard processing data, the set energy consumption and set operating time of each station in the semiconductor product processing process in the current process parameter information are updated to provide second process parameter information.

[0052] It is understandable that the recipes of wafers produced in different batches may be the same or different, but the power consumption data for wafers produced with the same or similar recipes are also close. Therefore, the second process parameter information provided in the embodiment of the present invention is obtained by associating the actual energy consumption data of the batches, thereby completing the correction of the energy consumption simulation model of the process equipment and improving the accuracy of the model simulation.

[0053] In a specific embodiment, the association relationships of each processing batch are obtained through an Equipment Automation Program (EAP) system. When the current processing batch is obtained, the corresponding associated batches can also be obtained. Therefore, first, data cleaning is performed on the actual energy consumption data of the associated batches to remove outliers and null values in the actual energy consumption data, obtaining standard energy consumption data. In a specific example, then the mean value of the standard energy consumption data is calculated to give the set energy consumption in the second process parameter information. In other examples, according to the different fluctuation conditions of the standard energy consumption data, different methods are used to determine the second process parameter information. For example, when the standard energy consumption data fluctuates relatively smoothly, the mode or median of the standard energy consumption data is used as the set energy consumption in the second process parameter information; otherwise, the mean value or the extreme value average is used as the set energy consumption in the second process parameter information, and this is not limited. The process parameter information can be adjusted immediately through the actual energy consumption data of the associated batches. Taking the processing batch as a unit, the process parameter information of the current processing batch is adjusted, and only the current processing batch is adjusted in real time, and the next batch automatically returns to the original state. It can be understood that when the associated processing batch is the current processing batch, the process parameter information in the associated processing batch is also adjusted in real time, and the next batch automatically returns to the original state.

[0054] The above process is the process of determining the set energy consumption. It can be understood that in the same way, the update of the set running time can be completed, which will not be elaborated here.

[0055] Among them, the EAP system is a key system for realizing equipment automation control and data acquisition in semiconductor product manufacturing.

[0056] Further, with reference to Figure 6 , the current processing time is determined, and combined with a fixed update strategy, the current process parameter information is updated to give the third process parameter information, which specifically includes: Determine the current processing time. If the current processing time is the time value in the preset update time table, trigger the fixed update strategy; where the fixed update strategy is to obtain the latest process parameter information; Update the current process parameter information to give the third process parameter information.

[0057] In the embodiment provided by the present invention, the fixed update strategy is to update the current process parameter information irregularly at a specified time, and further correct the energy consumption simulation model of the process equipment. After the fixed update strategy is triggered, the latest process parameter information will be read from the RMS system. The process parameter information in the RMS system is set or adjusted by relevant staff according to the actual situation. It can be understood that the latest process parameter information is the process parameter information currently read from the RMS system, and the latest process parameter information may be the same as the current process parameter information or different from the current process parameter information.

[0058] The above preset update schedule includes multiple time values. The time values can be set by the staff according to experience or generated randomly by a random function, and there is no limitation on this. The current processing time is obtained in real time. If the current processing time is a time value in the update schedule, the fixed update strategy is triggered, the latest process parameter information is read from the RMS system, the current process parameter information in the energy consumption simulation model of the process equipment is updated, and the third process parameter information is given.

[0059] It can be understood that the first process parameter information, the second process parameter information, and the third process parameter information are all parameters for correcting the current process parameter information. According to different actual situations, the energy consumption simulation model of the process equipment can correct the current process parameter information in any one or more of these ways, and there is no limitation on this.

[0060] In the first specific example, the current process parameter information is corrected only by the first process parameter information, that is, the current process parameter information is corrected once every preset time period. The preset time period may include only the actual energy consumption data of a certain processing batch or may include the actual energy consumption data of multiple processing batches. The number of processing batches in the preset time period does not affect the correction of the process parameter information by the first process parameter information.

[0061] Taking the first update sub-module 31 as an example, according to the actual processing time and actual energy consumption data of a certain process equipment, the current process parameter information in the energy consumption simulation model of the process equipment is updated. When a certain wafer enters the process equipment according to the wafer loading time in the production information, wafers of different process processes enter the corresponding station sub-units and start processing in sequence. After the energy consumption simulation model of the process equipment runs for a certain period of time, the initial energy consumption simulation data a1 and the set running time T1 of the process equipment are output. After an interval of a preset period of time, the initial energy consumption simulation data a1 and the set running time T1 of the process equipment during this period are compared and analyzed with the actual energy consumption data b1 and the actual processing time T1'. Each recipe for equipment processing will obtain corresponding initial energy consumption simulation data and actual energy consumption data. When the next stage of simulation starts, the process parameter information is updated again, and the average value of the actual energy consumption data b1 within the preset period is used as the input value of the new stage of process parameter information and updated into the energy consumption simulation model of the process equipment. When the simulation enters the next time interval, the process parameter information is updated in sequence, so that the output result of the energy consumption simulation model of the process equipment gradually approaches the actual value of the process equipment, and the energy consumption simulation model of the process equipment gradually approaches the actual operation situation of the process equipment, realizing the correction of the model.

[0062] In the second specific example, the process parameter information is corrected only through the second process parameter information, that is, the actual energy consumption data of the associated batch of the current processing batch is obtained, and the process parameter information (including the set running time and the set energy consumption) of the current processing batch is corrected, and the second process parameter information is given. When the current processing batch is completed, the process parameter information does not affect the next processing batch, and the initial value can be restored, or it can be corrected to the process parameter information corresponding to the next batch.

[0063] In the third specific example, the current process parameter information is corrected only through the third process parameter information, that is, when the time value in the update schedule is reached, the latest process parameter information is read from the RMS system, and the third process parameter information is given to complete the correction of the current process parameter information. The determination of the third process parameter information is only related to the time value in the update schedule and is not affected by other factors.

[0064] In the fourth specific example, the process parameter information is corrected by integrating the first process parameter information, the second process parameter information, and the third process parameter information. That is, the first update sub-module 31, the second update sub-module 32, and the third update sub-module 33 run simultaneously to correct the current process parameter information.

[0065] It should be understood that process parameter information refers to specific information, current process parameter information refers to the data actually used during the construction and operation of the process equipment energy consumption simulation model, the first process parameter information, the second process parameter information, and the third process parameter information are obtained by updating the current process parameter information at different time points or in different stages, and the current process parameter information is one of the first process parameter information, the second process parameter information, the third process parameter information, and the initial process parameter information. The initial process parameter information is the initially set process parameter information that has not been updated.

[0066] Refer to Figure 7 , the current process parameter information is updated once every preset time period by reading the actual energy consumption data through the IES system and the FDC system. In combination with the APC system, the current process parameter information is updated according to the current processing batch, and the RMS system will be updated according to the time value (such as T2) set in the time update table. The process equipment energy consumption simulation model will obtain the latest process parameter information and simulate the processing process according to the production information to output the results, thereby completing the correction of the process equipment energy consumption simulation model.

[0067] Furthermore, running the process equipment energy consumption simulation model gives real-time energy consumption simulation data, specifically including: According to the current process parameter information, the process equipment energy consumption simulation model is used to simulate the energy consumption of the process equipment to give initial energy consumption simulation data; Combined with the actual energy consumption data of the process equipment, an energy consumption simulation correction coefficient is given; According to the energy consumption simulation correction coefficient, the initial energy consumption simulation data is corrected to give real-time energy consumption simulation data.

[0068] Furthermore, combined with the actual energy consumption data of the process equipment, an energy consumption simulation correction coefficient is given, specifically including: According to the actual energy consumption data and the initial energy consumption simulation data of the process equipment per unit time, the difference between the actual energy consumption data and the initial energy consumption simulation data is analyzed to give a sub-correction coefficient; Combined with all the sub-correction coefficients within a preset time period, the change situation of the sub-correction coefficients is analyzed to give an energy consumption simulation correction coefficient.

[0069] The energy consumption simulation correction coefficient is specifically expressed as:

[0070] Among them, is the energy consumption simulation correction coefficient, is the sub-correction coefficient for the nth unit time, is the initial energy consumption simulation data for the nth unit time, is the actual energy consumption data for the nth unit time.

[0071] In the embodiment provided by the present invention, the initial energy consumption simulation data is corrected by the SCADA system. The unit time is one day. That is, the sub-correction coefficient for the current day is calculated based on the actual energy consumption data and the initial energy consumption simulation data for the current day. The energy consumption simulation correction coefficient for n days can be obtained from the sub-correction coefficients for each day. , and the energy consumption simulation data is output by the energy consumption simulation correction coefficient and the initial energy consumption simulation data , thereby realizing the correction and calibration of the simulation output result.

[0072] The energy consumption simulation data is specifically expressed as: ; wherein, is the energy consumption simulation correction coefficient, is the initial energy consumption simulation data corresponding to the nth unit time, is the energy consumption simulation data for the nth unit time.

[0073] Referring to Figure 8 , an embodiment of the present invention provides an adaptive digital twin simulation method for energy consumption of semiconductor devices, including: Obtaining the production information and process parameter information of semiconductor products, and, in real time, obtaining the actual processing data of process equipment; According to a preset process equipment configuration unit, constructing an energy consumption simulation model for process equipment, integrating the production information and process parameter information of semiconductor products, running the energy consumption simulation model for process equipment, and giving energy consumption simulation data in real time; Updating the process parameter information in the energy consumption simulation model for process equipment, wherein the updated process parameter information is given based on the analysis of the actual processing data of process equipment.

[0074] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the described steps can refer to the corresponding processes in the foregoing device embodiments, and will not be elaborated herein.

[0075] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they know the basic creative concept. Therefore, the appended claims are intended to be construed as including the preferred embodiments and all changes and modifications falling within the scope of the present invention. Obviously, those skilled in the art can make various changes and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. An adaptive semiconductor equipment energy consumption digital twin simulation device, characterized in that: include: Data acquisition module, simulation model building and operation module and parameter updating module connected by signals; A data acquisition module is used to obtain the production information and process parameter information of semiconductor products, as well as to obtain the actual processing data of process equipment in real time; The simulation model construction and operation module is used to construct a process equipment energy simulation model according to the preset process equipment configuration unit, integrate the production information and process parameter information of semiconductor products, run the process equipment energy simulation model, and provide energy simulation data in real time; The parameter updating module is used to update the process parameter information in the process equipment energy consumption simulation model, wherein the updated process parameter information is given based on the analysis of the actual processing data of the process equipment.

2. The adaptive semiconductor equipment energy consumption digital twin simulation device according to claim 1, characterized in that: The process equipment configuration unit includes a plurality of workstation sub-units and a plurality of manipulator sub-units; According to the preset process equipment configuration unit, a process equipment energy consumption simulation model is constructed, which specifically includes: Obtaining a preset process equipment configuration unit; Combined with the connection relationship between each workstation sub-unit and each robot sub-unit in the process equipment configuration unit, the energy consumption logic of the process equipment is integrated to construct a process equipment energy consumption simulation model.

3. The adaptive semiconductor equipment energy digital twin simulation device according to claim 1, characterized in that: The production information includes the production time, processing batch and process information of the semiconductor product, the process parameter information includes the set operation time and set energy consumption of each station in the process equipment during the processing of the semiconductor product, the actual processing data includes the actual processing time and the actual energy consumption data, and the parameter update module includes the first update submodule, the second update submodule and the third update submodule; A first updating submodule is used to analyze the actual processing data of the process equipment within a preset time period, update the set operating time and set energy used by each station in the process of processing semiconductor products in the current process parameter information, and provide the first process parameter information; The second updating submodule is used to determine the current processing batch of the process equipment, and update the set energy and set running time of each station in the semiconductor product processing process in the current process parameter information according to the actual processing data of the process equipment of the associated processing batch corresponding to the current processing batch, and provide the second process parameter information; The third updating submodule is used to determine the current processing time, and update the current process parameter information in combination with the fixed updating strategy to provide the third process parameter information.

4. The adaptive semiconductor equipment energy digital twin simulation device according to claim 3, characterized in that: The actual processing data of the process equipment within the preset time period is analyzed, and the set operating time and set energy used of each station in the process of processing the semiconductor product in the current process parameter information are updated to provide the first process parameter information, which specifically includes: Obtain actual energy consumption data of process equipment at each moment within a preset time period; Clean the actual energy consumption data at each moment to obtain standard energy consumption data; According to the changes of standard energy consumption data at each moment, a standard energy consumption curve is obtained, and the mean value of the standard energy consumption data is given; Combined with the average value of the standard energy consumption data and the actual processing time of each station in the process equipment, the set operating time and set energy consumption of each station in the semiconductor product processing process in the current process parameter information are updated to obtain the first process parameter information.

5. The adaptive semiconductor equipment energy digital twin simulation device according to claim 3, characterized in that: Determine the current processing batch of the process equipment, and update the set energy and set running time of each station in the semiconductor product processing process in the current process parameter information according to the actual processing data of the process equipment of the associated processing batch corresponding to the current processing batch, and provide the second process parameter information, which specifically includes: Determine the current processing batch of the process equipment; According to the correlation relationship between each processing batch, the actual processing data of the process equipment of the processing batch corresponding to the current processing batch is given; Perform data cleaning on the actual processing data of the process equipment associated with the processing batch, remove abnormal values ​​and null values ​​in the actual processing data, and provide standard processing data; Based on the analysis of changes in the standard processing data, the set energy consumption and set operating time of each station in the semiconductor product processing process in the current process parameter information are updated to provide second process parameter information.

6. The adaptive semiconductor equipment energy digital twin simulation device according to claim 3, characterized in that: Determine the current processing time, and combine the fixed update strategy to update the current process parameter information to provide the third process parameter information, including: Determine the current processing time. If the current processing time is a time value in a preset update schedule, trigger a fixed update strategy. The fixed update strategy is to obtain the latest process parameter information. The current process parameter information is updated to provide third process parameter information.

7. The adaptive semiconductor equipment energy usage digital twin simulation device according to claim 1, characterized in that: Run the process equipment energy simulation model and provide real-time energy simulation data, including: According to the current process parameter information, the process equipment energy consumption simulation model is used to simulate the energy consumption of the process equipment and provide initial energy consumption simulation data; Combined with the actual energy consumption data of process equipment, energy consumption simulation correction coefficient is given; According to the energy consumption simulation correction coefficient, the initial energy consumption simulation data is corrected and the energy consumption simulation data is given in real time.

8. The adaptive semiconductor equipment energy usage digital twin simulation device according to claim 7, characterized in that: Combined with the actual energy consumption data of process equipment, the energy consumption simulation correction coefficient is given, including: According to the actual energy consumption data of the process equipment per unit time and the initial energy consumption simulation data, the difference between the actual energy consumption data and the initial energy consumption simulation data is analyzed, and a sub-correction coefficient is given; Combine all the sub-correction coefficients within the preset time period, analyze the changes of the sub-correction coefficients, and give the energy consumption simulation correction coefficient.

9. The adaptive semiconductor equipment energy digital twin simulation device according to claim 8, characterized in that: The energy simulation correction coefficient is specifically expressed as: ； in, is the energy simulation correction factor, is the sub-correction coefficient of the nth unit time, is the initial energy consumption simulation data of the nth unit time, is the actual energy consumption data for the nth unit time.

10. An adaptive semiconductor equipment energy digital twin simulation method, characterized in that: The adaptive semiconductor equipment energy digital twin simulation device as claimed in any one of claims 1 to 9 comprises: Obtain production information and process parameter information of semiconductor products, as well as real-time acquisition of actual processing data of process equipment; According to the preset process equipment configuration unit, a process equipment energy simulation model is constructed, the production information and process parameter information of semiconductor products are integrated, the process equipment energy simulation model is run, and energy simulation data is given in real time; The process parameter information in the process equipment energy consumption simulation model is updated, wherein the updated process parameter information is given based on the analysis of actual processing data of the process equipment.

Images