Turbo molecular pump driving controller control method based on self-adaptive control algorithm

Abstract

The invention relates to the technical field of automatic control, and discloses a turbo molecular pump driving controller control method based on a self-adaptive control algorithm, and the method comprises the steps: obtaining gas parameters, collected by a miniature gas sensor in real time, in a pump body of a turbo molecular pump; calculating an optimal power output value by using an improved radial basis function neural network algorithm, and determining the optimal power output value as a power reference of the turbo molecular pump driving controller; the operation mode of the turbo molecular pump driving controller is automatically switched according to the real-time pressure intensity; according to the method, adaptive power is dynamically output by using an improved radial basis function neural network algorithm, power output is matched with gas characteristics, operation efficiency is optimized, an operation mode is automatically switched, a traditional single operation mode is replaced, and the method has the advantages that the adaptive power is dynamically output by using the improved radial basis function neural network algorithm; precise adaptation to different process stages is achieved, the PWM duty ratio is adjusted to compensate the power deviation when the load is suddenly changed, and self-adaptive control is achieved.

Description

Technical Field

[0001] This invention relates to the field of automatic control technology, and more specifically to a control method for a turbomolecular pump drive controller based on an adaptive control algorithm. Background Technology

[0002] In the field of vacuum equipment drive, the actuator, as the core control component of turbomolecular pump, directly affects the operating efficiency and stability of the equipment.

[0003] In existing technologies, turbomolecular pump drive controllers have a single operating mode, supporting only fixed speed adjustment and lacking mode setting functions, making it difficult to adapt to diverse vacuum processes. Summary of the Invention

[0004] This invention provides a control method for a turbomolecular pump drive controller based on an adaptive control algorithm, which solves the problem that existing turbomolecular pump drive controllers have a single working mode and are difficult to adapt to diverse vacuum processes.

[0005] In a first aspect, the present invention provides a control method for a turbomolecular pump drive controller based on an adaptive control algorithm, the method comprising: The gas parameters inside the turbomolecular pump are acquired in real time by a micro gas sensor. These gas parameters include molecular mass, concentration ratio, temperature, and pressure. Using gas parameters as input, the optimal power output value is calculated using an improved radial basis function neural network algorithm, and the optimal power output value is determined as the power reference for the turbomolecular pump drive controller. The system acquires the real-time pressure within the process chamber and automatically switches the operating mode of the turbomolecular pump drive controller based on the real-time pressure. The operating modes include standby mode, rapid vacuuming mode, and precision control mode. Obtain the motor operating current, and when a sudden load change is detected, adjust the PWM duty cycle until the current fluctuation is within the preset current change range.

[0006] This invention utilizes an improved radial basis function neural network algorithm to dynamically output adaptive power, achieving power output matching with gas characteristics. The calculated optimal power output value is used as the power benchmark instead of a fixed value, adapting to different operating conditions and optimizing operating efficiency. The operating mode is automatically switched according to real-time pressure, replacing the traditional single operating mode, achieving precise adaptation to different process stages. By adjusting the PWM duty cycle during load changes to compensate for power deviations and control current fluctuations within a preset range, adaptive control is achieved, ensuring equipment operating stability and expanding the equipment's applicability.

[0007] In one alternative implementation, the optimal power output value is calculated according to the following formula:

[0008] in, For the optimal power output value, For the first i The concentration percentage of each gas For the first i Molecular mass of the gas T The pump body operating temperature, Based on power, k 1. k 2. k 3 represents the weighting coefficient.

[0009] In one alternative implementation, adjusting the PWM duty cycle includes: Calculate the deviation value of the current change rate, and use the PI controller to calculate the power to be compensated corresponding to the deviation value of the current change rate according to the following formula:

[0010] in, To compensate for the power, This is the proportionality coefficient. The integral coefficient; Calculate the PWM duty cycle adjustment using the following formula:

[0011] in, This is the PWM duty cycle adjustment amount. For the rated power of the driver, The power conversion efficiency coefficient; Calculate the target PWM duty cycle using the following formula:

[0012] in, For the target PWM duty cycle, The PWM duty cycle before the load change. It is a symbolic function.

[0013] This invention utilizes a PI controller to precisely quantify the compensation power, enabling on-demand compensation. The compensation power is quantified into a specific duty cycle adjustment amount, determining the target PWM duty cycle and dynamically adapting to load changes.

[0014] In one optional implementation, the operating mode of the turbomolecular pump drive controller is automatically switched according to the real-time pressure, including: If the real-time pressure is higher than the first pressure threshold, the operating mode of the turbomolecular pump drive controller will be switched to the rapid vacuum mode. If the real-time pressure is higher than the second pressure threshold but lower than the first pressure threshold, the operating mode of the turbomolecular pump drive controller is switched to precision control mode, where the first pressure threshold is higher than the second pressure threshold. If the real-time pressure is lower than the second pressure threshold, the operating mode of the turbomolecular pump drive controller will be switched to standby mode.

[0015] This invention avoids energy waste from operating in a single mode the entire time by automatically switching the operating mode of the turbomolecular pump drive controller based on real-time pressure, and achieves intelligent energy consumption allocation of high power for high demand and low power for low demand, thereby reducing operating costs.

[0016] In one alternative implementation, the method further includes: The concentration percentage collected by the miniature gas sensor is monitored in real time. If the concentration percentage exceeds the concentration percentage threshold, or if the concentration percentage remains constant for a longer than a preset time, an alarm signal is generated. Calculate the rate of change of gas concentration. If the rate of change of gas concentration exceeds the fluctuation range, generate a sensor abnormality warning signal. If the same physical quantity is inferred using different sensors, and the inference result exceeds the error range, at least one sensor fault indication signal is generated. A heartbeat query command is periodically sent to the miniature gas sensor. If no response is received, a signal indicating that the miniature gas sensor communication link is interrupted or the miniature gas sensor has failed is generated. If alarm signals, and / or sensor abnormality indication signals, and / or sensor fault indication signals, and / or miniature gas sensor communication link interruption or miniature gas sensor failure indication signals persist during the continuous sampling period, fault-tolerant control will be implemented.

[0017] This invention improves the reliability of fault-tolerant control by monitoring faults in multiple dimensions, covering sensor failure scenarios, setting a continuous sampling period to confirm faults, and avoiding frequent control from causing disturbances to the process.

[0018] In one alternative implementation, fault-tolerant control is performed, including: Establish a pressure-flow model; Using the effective power value before switching to fault-tolerant mode, the corresponding chamber pressure value, and the total gas flow rate as data sources, the parameters in the pressure-flow model are locally corrected using the least squares method.

[0019] This invention provides a stable and reliable control benchmark by establishing a pressure-flow model, and uses local correction of parameters in the model to achieve fine-tuning of the model to adapt to the current scenario.

[0020] In one alternative implementation, the pressure-flow model is as follows:

[0021] in, This is the backup power setting calculated in fault-tolerant mode. The chamber pressure value is measured by a high-precision vacuum timer. Q This represents the total gas flow rate. This represents the overall pumping efficiency coefficient of the turbomolecular pump. K This is the proportional adjustment coefficient.

[0022] Secondly, the present invention provides a turbomolecular pump drive controller control device based on an adaptive control algorithm, the device comprising: The acquisition module is used to acquire gas parameters inside the turbomolecular pump body, which are collected in real time by the micro gas sensor. The gas parameters include molecular mass, concentration ratio, temperature and pressure. The calculation module is used to calculate the optimal power output value using an improved radial basis function neural network algorithm with gas parameters as input, and to determine the optimal power output value as the power reference for the turbomolecular pump drive controller. The mode switching module is used to acquire the real-time pressure in the process chamber and automatically switch the operating mode of the turbomolecular pump drive controller according to the real-time pressure. The operating modes include standby mode, rapid vacuuming mode and precision control mode. The adjustment module is used to obtain the motor operating current. When a sudden load change is detected, the PWM duty cycle is adjusted until the current fluctuation is within the preset current change range.

[0023] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the turbomolecular pump drive controller control method based on the adaptive control algorithm described in the first aspect or any corresponding embodiment.

[0024] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the turbomolecular pump drive controller control method based on the adaptive control algorithm described in the first aspect or any corresponding embodiment. Attached Figure Description

[0025] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0026] Figure 1 This is a schematic flowchart of a turbomolecular pump drive controller control method based on an adaptive control algorithm according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the power characteristic curves and AI adaptation ranges for different gas types according to embodiments of the present invention; Figure 3 This is a structural block diagram of a turbomolecular pump drive controller control device based on an adaptive control algorithm according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0028] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0029] As vacuum applications become increasingly complex, with dynamic changes in multi-gas environments and stringent requirements for high-precision process control, higher demands are placed on parameter adjustability. In fields such as semiconductor etching and photovoltaic thin film deposition, vacuum equipment alternately introduces mixed gases such as CF4, O2, and Ar during the etching process. During process switching, the pump load changes abruptly, facing challenges such as dynamic changes in gas composition and large instantaneous load fluctuations. Traditional drive systems, lacking real-time response capabilities, are prone to problems such as rotor instability and excessive power loss.

[0030] According to an embodiment of the present invention, a control method for a turbomolecular pump drive controller based on an adaptive control algorithm is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0031] This embodiment provides a control method for a turbomolecular pump drive controller based on an adaptive control algorithm. Figure 1This is a flowchart of a turbomolecular pump drive controller control method based on an adaptive control algorithm according to an embodiment of the present invention, as shown below. Figure 1 As shown, the process includes the following steps: Step S101: Obtain the gas parameters inside the turbomolecular pump body collected in real time by the micro gas sensor.

[0032] In this embodiment of the invention, a micro gas sensor is integrated to collect multi-dimensional gas parameters such as molecular mass, concentration ratio, temperature, and pressure of the turbomolecular pump body in real time.

[0033] Step S102: Using gas parameters as input, the optimal power output value is calculated using an improved radial basis function neural network algorithm, and the optimal power output value is determined as the power reference for the turbomolecular pump drive controller.

[0034] In this embodiment of the invention, multi-dimensional gas parameters collected by a miniature gas sensor are used as input, and an improved radial basis function (RBF) neural network algorithm is employed to calculate the optimal power output value. The improved RBF neural network algorithm replaces the traditional RBF neural network algorithm, abandoning the traditional design of a fixed number of hidden layer nodes. Instead, it uses a K-means clustering algorithm, combined with an error threshold to dynamically generate hidden layer nodes. Based on operating parameters, similar operating condition data are clustered into one hidden layer node. Simultaneously, a power error threshold is set; when the power calculation error for a certain operating condition exceeds the threshold, a new hidden layer node is automatically added, thereby ensuring the adaptation accuracy for complex operating conditions. The improved RBF neural network algorithm dynamically matches parameters such as gas characteristics, determining the optimal power output value as the power reference for the turbomolecular pump drive controller, providing a data foundation for subsequent mode switching.

[0035] Specifically, the improved RBF neural network is trained using the gradient descent method. The training dataset covers the operating conditions of various common process gases such as Ar, He, O2, and CF4. After training, the power adaptation error of the model is controllable, meeting the requirements of high-precision processes.

[0036] Step S103: Obtain the real-time pressure inside the process chamber and automatically switch the operating mode of the turbomolecular pump drive controller according to the real-time pressure.

[0037] In this embodiment of the invention, three core modes are preset: standby mode, rapid vacuuming mode, and precision control mode. The mode switching logic is based on the pressure conditions inside the chamber and automatically switches between modes.

[0038] Step S104: Obtain the motor operating current. When a sudden load change is detected, adjust the PWM duty cycle until the current fluctuation is within the preset current change range.

[0039] In this embodiment of the invention, the motor operating current is monitored in real time, and the rate of change of motor current is detected. When a sudden change in load is detected, compensation is immediately started. By adjusting the PWM duty cycle, the current fluctuation is controlled within a preset current change range, so as to keep the current fluctuation within a reasonable range and avoid speed instability.

[0040] In addition, when a high concentration of Ar gas is introduced during process switching, the load increases instantaneously. The PWM duty cycle is adjusted to control the current fluctuation and rotation speed within a reasonable range to meet the etching accuracy requirements.

[0041] like Figure 2 As shown, Figure 2 The AC section contains heavy gases, while the BC section contains light gases. Heavy gases have a larger molecular mass, so at the same rotational speed, they require a higher driving power. Light gases have a smaller molecular mass, so at the same rotational speed, they require a lower driving power.

[0042] The turbomolecular pump drive controller control method provided in this embodiment utilizes an improved radial basis function neural network algorithm to dynamically output adaptive power, achieving power output and gas characteristic matching. The calculated optimal power output value is used as the power reference instead of a fixed value to adapt to operating conditions and optimize operating efficiency. The operating mode is automatically switched according to real-time pressure, replacing the traditional single operating mode, to achieve precise adaptation to different process stages. By adjusting the PWM duty cycle during load changes to compensate for power deviations, current fluctuations are controlled within a preset range, achieving adaptive control, ensuring equipment operating stability, and expanding the equipment's applicability.

[0043] This embodiment provides a control method for a turbomolecular pump drive controller based on an adaptive control algorithm, the process of which includes the following steps: Step S201: Obtain the gas parameters inside the turbomolecular pump body collected in real time by the micro gas sensor.

[0044] Please see details Figure 1 Step S101 of the illustrated embodiment will not be described again here.

[0045] Step S202: Using gas parameters as input, the optimal power output value is calculated using an improved radial basis function neural network algorithm, and the optimal power output value is determined as the power reference for the turbomolecular pump drive controller.

[0046] Specifically, the formula for calculating the optimal power output value using the improved radial basis function neural network algorithm is as follows:

[0047] in, For the optimal power output value, For the first i The concentration percentage of each gas For the first i Molecular mass of the gas T The pump body operating temperature, Based on power, k 1. k 2. k 3 represents the weighting coefficient.

[0048] Step S203: Obtain the real-time pressure inside the process chamber and automatically switch the operating mode of the turbomolecular pump drive controller according to the real-time pressure.

[0049] Specifically, step S203 above, which automatically switches the operating mode of the turbomolecular pump drive controller based on real-time pressure, includes: Step S2031: If the real-time pressure is higher than the first pressure threshold, switch the operating mode of the turbomolecular pump drive controller to the rapid vacuum mode.

[0050] Step S2032: If the real-time pressure is higher than the second pressure threshold and lower than the first pressure threshold, then switch the operating mode of the turbomolecular pump drive controller to the precision control mode.

[0051] Step S2033: If the real-time pressure is lower than the second pressure threshold, the operating mode of the turbomolecular pump drive controller is switched to standby mode.

[0052] In this embodiment of the invention, when the real-time pressure of the chamber is high, i.e. higher than the first pressure threshold, the operating mode of the turbomolecular pump drive controller is switched to the rapid vacuum mode, and the drive motor outputs high power and high speed to shorten the pumping time.

[0053] When the pressure in the chamber drops to the low-to-medium pressure range, i.e., above the second pressure threshold but below the first pressure threshold, the turbomolecular pump drive controller switches to precision control mode to maintain constant power, ensure no speed drift, and guarantee vacuum accuracy. The first pressure threshold is higher than the second pressure threshold.

[0054] When the process is paused, or the pressure reaches a low level, i.e. below the second pressure threshold, the operating mode of the turbomolecular pump drive controller is switched to standby mode to keep the speed in the low power consumption range and avoid energy waste.

[0055] By automatically switching the operating mode of the turbomolecular pump drive controller based on real-time pressure, energy waste from operating in a single mode throughout the entire process is avoided, and intelligent energy consumption allocation is achieved for high demand with high power and low demand with low power, thereby reducing operating costs.

[0056] Step S204: Obtain the motor operating current. When a sudden load change is detected, adjust the PWM duty cycle until the current fluctuation is within the preset current change range.

[0057] Specifically, step S204 above, which adjusts the PWM duty cycle, includes: Step S2041: Calculate the current change rate deviation value, and use the PI controller to calculate the power to be compensated corresponding to the current change rate deviation value.

[0058] Step S2042: Calculate the PWM duty cycle adjustment.

[0059] Step S2043: Calculate the target PWM duty cycle.

[0060] In this embodiment of the invention, the deviation value of the current change rate is first calculated, and the power to be compensated corresponding to the deviation value of the current change rate is determined by the proportional-integral (PI) controller. The calculation formula is as follows:

[0061] in, To compensate for the power, This is the proportionality coefficient. is the integral coefficient.

[0062] Then, the PWM duty cycle adjustment is calculated using the following formula:

[0063] in, This is the PWM duty cycle adjustment amount. For the rated power of the driver, This is the power conversion efficiency coefficient.

[0064] Finally, the target PWM duty cycle is calculated using the following formula:

[0065] in, For the target PWM duty cycle, The PWM duty cycle before the load change. It is a symbolic function.

[0066] For symbolic functions ,when ≥5A / s, with increased load, use the "+" sign and increase the duty cycle to boost power. When ≤-5A / s indicates a reduced load; therefore, use "-" to decrease the duty cycle and reduce power consumption.

[0067] By using a PI controller to precisely quantify the compensation power, on-demand compensation is achieved. The compensation power is quantified into a specific duty cycle adjustment amount, the target PWM duty cycle is determined, and the load changes are dynamically adapted.

[0068] In some alternative implementations, the method further includes: Step S205: Monitor the concentration ratio collected by the miniature gas sensor in real time. If the concentration ratio exceeds the concentration ratio threshold, or if the concentration ratio remains constant for a longer than a preset time, generate an alarm signal.

[0069] Step S206: Calculate the gas concentration change rate. If the change rate of gas concentration exceeds the fluctuation range, generate a sensor abnormality warning signal.

[0070] Step S207: Use different sensors to infer the same physical quantity. If the inference result exceeds the error range, generate at least one sensor fault indication signal.

[0071] Step S208: A heartbeat query command is periodically sent to the miniature gas sensor. If no response is received, a miniature gas sensor communication link interruption or miniature gas sensor failure prompt signal is generated.

[0072] Step S209: If the alarm signal, and / or the sensor abnormality indication signal, and / or the sensor fault indication signal, and / or the miniature gas sensor communication link interruption or miniature gas sensor failure indication signal persists during the continuous sampling period, then fault-tolerant control is performed.

[0073] In this embodiment of the invention, a multi-level fault diagnosis mechanism is integrated to improve the operational reliability of the turbomolecular pump drive controller in high-end vacuum processes such as semiconductor etching.

[0074] The concentration percentage collected by the miniature gas sensor is monitored in real time. A physically possible range is set, such as 0~100%. If the concentration percentage exceeds this physically possible range, or if the concentration percentage remains constant for a longer period than the preset time (i.e., no change for a long time), an alarm signal is generated to trigger a primary alarm, thereby realizing the reasonableness judgment of the concentration percentage.

[0075] During the stabilization process phase, the rate of change in gas concentration is calculated. The system continuously monitors whether the rate of change in gas concentration exceeds the fluctuation range. This fluctuation range can be set based on empirical values; it is only an example here and not a limitation. If the rate of change in gas concentration is detected to exceed the fluctuation range without physical evidence, a sensor abnormality warning signal is generated, indicating a sensor signal abnormality.

[0076] If redundant or different types of sensors are configured, such as mass spectrometers and pressure sensors, cross-validation of data is performed. When the inference results of different sensors for the same physical quantity exceed the allowable error range, it is determined that at least one of the sensors has failed.

[0077] In addition, a heartbeat detection function is set up to periodically send a "heartbeat" query command to the miniature gas sensor. If no response is received after several consecutive attempts, it is determined that the sensor communication link terminal or the sensor itself has failed.

[0078] Once any of the above alarms is triggered, a confirmation phase lasting for several sampling cycles will begin, typically 3-5 cycles (this is just an example). During this period, if the alarm signal, and / or the sensor abnormality indication signal, and / or the sensor failure indication signal, and / or the miniature gas sensor communication link interruption or miniature gas sensor failure indication signal persists, then a "hard fault" or "serious drift fault" of the miniature gas sensor is confirmed, and the fault-tolerant control mechanism will be activated.

[0079] By monitoring faults in multiple dimensions, covering sensor failure scenarios, and setting continuous sampling cycles to confirm faults, the reliability of fault-tolerant control is improved, and frequent control can be avoided to prevent disturbances to the process.

[0080] Specifically, the fault tolerance control in step S209 above includes: Step S2091: Establish a pressure-flow model.

[0081] Step S2092: Using the effective power value before switching to fault-tolerant mode, the corresponding chamber pressure value, and the total gas flow rate as data sources, the parameters in the pressure-flow model are locally corrected using the least squares method.

[0082] In this embodiment of the invention, a pressure-flow rate model is established. This model essentially infers the power required to maintain the current vacuum level indirectly when the gas composition cannot be directly obtained. The model is as follows:

[0083] in, This is the backup power setting calculated in fault-tolerant mode. The chamber pressure value is measured by a high-precision vacuum timer. It should be noted that this sensor is independent of the faulty gas composition sensor. Q The total gas flow rate is obtained from the reading of the upstream mass flow controller or measured by the pump inlet flow meter. This is the overall pumping efficiency coefficient of the turbomolecular pump, a parameter weakly correlated with pump speed and gas type. In fault-tolerant mode, this value is taken as a conservative estimate based on historical normal operating data to ensure stability. KThis is a proportional adjustment coefficient used to fine-tune the model output and can be calibrated during the debugging phase.

[0084] To avoid a decrease in model control accuracy due to the use of fixed parameters in fault-tolerant mode, the model has online fine-tuning capabilities. It records the effective power value, corresponding chamber pressure, and total gas flow rate just before switching to fault-tolerant mode. Using this data, optimization algorithms such as the least squares method are employed to adjust the proportional gain K and the overall pumping efficiency coefficient of the turbomolecular pump in the model. Local corrections are performed to make the model's initial output closer to the control state before failure.

[0085] To prevent sudden changes in power command during switching, a weighted smooth transition algorithm is used to control the loop switching, thereby achieving a smooth transition.

[0086] The weighted smoothing algorithm is as follows:

[0087] in, For the final output power, The weighting factor decreases linearly from 1 to 0 during the control period. This is the effective power value output in AI mode, enabling a smooth transition from AI mode to fault-tolerant mode.

[0088] In fault-tolerant control mode, the speed dynamic adjustment algorithm (such as PWM compensation for load changes) remains active, working together to maintain stability.

[0089] In addition, a logging function, a downgrade operation indicator function, and a recovery mechanism are also provided.

[0090] Log function: When fault diagnosis and mode switching are triggered, the integrated communication interface sends a clear fault code and mode switching status to the host computer, and records a detailed event log, including data before sensor failure, switching time, model calibration parameters, etc., for maintenance personnel to analyze.

[0091] Degraded operation indication function: On the human-machine interface, the indicator light switches from "normal" to "fault-tolerant operation", prompting the operator that the system is in backup control mode. Although it can maintain operation at this time, some optimized functions need to be maintained first.

[0092] Recovery mechanism: When maintenance personnel replace or repair the gas sensor, the system will switch to the adaptive control mode described in steps S201 to S204 above. After the reliability of the new sensor is assessed, normal operation will resume.

[0093] By establishing a pressure-flow model, a stable and reliable control benchmark is provided. The parameters in the model are locally corrected to achieve fine-tuning of the model and adapt it to the current scenario.

[0094] The turbomolecular pump drive controller control method provided in this embodiment, based on an adaptive control algorithm, achieves real-time identification and parameter adjustment of gas composition and load fluctuations through the adaptive algorithm. Compared with the traditional fixed mode, it meets the high-precision process requirements of semiconductor etching, photovoltaic thin film deposition, and other processes, thus expanding the applicable scenarios of the equipment. Furthermore, when the core gas sensor fails, it can seamlessly switch to a backup control strategy based on a pressure-flow model, ensuring the continuous and stable operation of the vacuum process and avoiding production interruptions due to a single component failure.

[0095] This embodiment also provides a turbomolecular pump drive controller control device based on an adaptive control algorithm. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0096] This embodiment provides a turbomolecular pump drive controller control device based on an adaptive control algorithm, such as... Figure 3 As shown, it includes: The acquisition module 301 is used to acquire gas parameters in the turbomolecular pump body collected in real time by the micro gas sensor. The gas parameters include molecular mass, concentration ratio, temperature and pressure. The calculation module 302 is used to calculate the optimal power output value using an improved radial basis function neural network algorithm with gas parameters as input, and to determine the optimal power output value as the power reference of the turbomolecular pump drive controller. The mode switching module 303 is used to acquire the real-time pressure in the process chamber and automatically switch the operating mode of the turbomolecular pump drive controller according to the real-time pressure. The operating modes include standby mode, rapid vacuuming mode and precision control mode. The adjustment module 304 is used to obtain the motor operating current. When a sudden load change is detected, the PWM duty cycle is adjusted until the current fluctuation is within the preset current change range.

[0097] In some alternative implementations, the optimal power output value is calculated according to the following formula:

[0098] in, For the optimal power output value, For the first iThe concentration percentage of each gas For the first i Molecular mass of the gas T The pump body operating temperature, Based on power, k 1. k 2. k 3 represents the weighting coefficient.

[0099] In some alternative implementations, the adjustment module 304 includes: The first calculation unit is used to calculate the deviation value of the current change rate and, using the PI controller, calculates the power to be compensated corresponding to the deviation value of the current change rate according to the following formula:

[0100] in, To compensate for the power, This is the proportionality coefficient. The integral coefficient; The second calculation unit is used to calculate the PWM duty cycle adjustment according to the following formula:

[0101] in, This is the PWM duty cycle adjustment amount. For the rated power of the driver, The power conversion efficiency coefficient; The third calculation unit is used to calculate the target PWM duty cycle according to the following formula:

[0102] in, For the target PWM duty cycle, The PWM duty cycle before the load change. It is a symbolic function.

[0103] In some alternative implementations, the mode switching module 303 includes: The first switching unit is used to switch the operating mode of the turbomolecular pump drive controller to the rapid vacuum mode if the real-time pressure is higher than the first pressure threshold. The second switching unit is used to switch the operating mode of the turbomolecular pump drive controller to precision control mode if the real-time pressure is higher than the second pressure threshold and lower than the first pressure threshold, and the first pressure threshold is higher than the second pressure threshold. The third switching unit is used to switch the operating mode of the turbomolecular pump drive controller to standby mode if the real-time pressure is lower than the second pressure threshold.

[0104] In some alternative embodiments, the device includes: The first signal generation module is used to monitor the concentration ratio collected by the miniature gas sensor in real time. If the concentration ratio exceeds the concentration ratio threshold, or if the concentration ratio remains constant for a longer than a preset time, an alarm signal is generated. The second signal generation module is used to calculate the rate of change of gas concentration. If the rate of change of gas concentration exceeds the fluctuation range, a sensor abnormality warning signal is generated. The third signal generation module is used to infer the same physical quantity using different sensors. If the inference result exceeds the error range, at least one sensor fault indication signal is generated. The fourth signal generation module is used to periodically send heartbeat query commands to the miniature gas sensor. If no response is received, it generates a miniature gas sensor communication link interruption or miniature gas sensor failure prompt signal. The fault-tolerant control module is used to perform fault-tolerant control if alarm signals, and / or sensor abnormality indication signals, and / or sensor fault indication signals, and / or miniature gas sensor communication link interruption or miniature gas sensor failure indication signals persist during the continuous sampling period.

[0105] In some alternative implementations, the fault-tolerant control module includes: The model building unit is used to build pressure-flow models; The correction unit is used to locally correct the parameters in the pressure-flow model using the effective power value before switching to fault-tolerant mode, the corresponding chamber pressure value, and the total gas flow rate as data sources, and the least squares method.

[0106] In some alternative implementations, the pressure-flow model is as follows:

[0107] in, This is the backup power setting calculated in fault-tolerant mode. The chamber pressure value is measured by a high-precision vacuum timer. Q This represents the total gas flow rate. This represents the overall pumping efficiency coefficient of the turbomolecular pump. K This is the proportional adjustment coefficient.

[0108] The turbomolecular pump drive controller control device based on adaptive control algorithm provided in this embodiment of the invention can execute the turbomolecular pump drive controller control method based on adaptive control algorithm provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method execution. Further functional descriptions of the above modules and units are the same as in the corresponding embodiments described above, and will not be repeated here.

[0109] Figure 4This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0110] The following is a detailed reference. Figure 4 This diagram illustrates a structural schematic suitable for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 401, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 402 or a program loaded from memory 408 into random access memory (RAM) 403. The RAM 403 also stores various programs and data required for the operation of the electronic device. The processor 401, ROM 402, and RAM 403 are interconnected via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0111] Typically, the following devices can be connected to I / O interface 405: input devices 406 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 407 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 408 including, for example, magnetic tapes, hard disks, etc.; and communication devices 409. Communication device 409 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 4 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0112] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 409, or installed from a memory 408, or installed from a ROM 402. When the computer program is executed by the processor 401, it performs the functions defined in the turbomolecular pump drive controller control method based on an adaptive control algorithm according to embodiments of the present invention.

[0113] Figure 4 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0114] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the turbomolecular pump drive controller control method based on the adaptive control algorithm shown in the above embodiments is implemented.

[0115] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0116] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and all such modifications and variations fall within the scope defined by the appended invention.

Claims

1. A control method for a turbomolecular pump drive controller based on an adaptive control algorithm, characterized in that, The method includes: The gas parameters inside the turbomolecular pump are acquired in real time by a micro gas sensor. The gas parameters include molecular mass, concentration ratio, temperature and pressure. Using the gas parameters as input, the optimal power output value is calculated using an improved radial basis function neural network algorithm, and the optimal power output value is determined as the power reference for the turbomolecular pump drive controller. The real-time pressure inside the process chamber is obtained, and the operating mode of the turbomolecular pump drive controller is automatically switched according to the real-time pressure. The operating modes include standby mode, rapid vacuuming mode and precision control mode. Obtain the motor operating current, and when a sudden load change is detected, adjust the PWM duty cycle until the current fluctuation is within the preset current change range.

2. The method according to claim 1, characterized in that, Calculate the optimal power output value using the following formula: in, For the optimal power output value, For the first i The concentration percentage of each gas For the first i Molecular mass of the gas T The pump body operating temperature, Based on power, k 1. k 2. k 3 represents the weighting coefficient.

3. The method according to claim 1, characterized in that, The adjustment of the PWM duty cycle includes: Calculate the deviation value of the current change rate, and use the PI controller to calculate the power to be compensated corresponding to the deviation value of the current change rate according to the following formula: in, To compensate for the power, This is the proportionality coefficient. The integral coefficient; Calculate the PWM duty cycle adjustment using the following formula: in, This is the PWM duty cycle adjustment amount. For the rated power of the driver, The power conversion efficiency coefficient; Calculate the target PWM duty cycle using the following formula: in, For the target PWM duty cycle, The PWM duty cycle before the load change. It is a symbolic function.

4. The method according to claim 1, characterized in that, The automatic switching of the turbomolecular pump drive controller's operating mode based on the real-time pressure includes: If the real-time pressure is higher than the first pressure threshold, the operating mode of the turbomolecular pump drive controller will be switched to the rapid vacuum mode. If the real-time pressure is higher than the second pressure threshold but lower than the first pressure threshold, the operating mode of the turbomolecular pump drive controller is switched to the precision control mode, where the first pressure threshold is higher than the second pressure threshold. If the real-time pressure is lower than the second pressure threshold, the operating mode of the turbomolecular pump drive controller will be switched to standby mode.

5. The method according to claim 1, characterized in that, The method further includes: The concentration percentage collected by the miniature gas sensor is monitored in real time. If the concentration percentage exceeds the concentration percentage threshold, or if the concentration percentage remains constant for a longer than a preset time, an alarm signal is generated. Calculate the rate of change of gas concentration. If the rate of change of gas concentration exceeds the fluctuation range, generate a sensor abnormality warning signal. If the same physical quantity is inferred using different sensors, and the inference result exceeds the error range, at least one sensor fault indication signal is generated. A heartbeat query command is periodically sent to the miniature gas sensor. If no response is received, a signal indicating that the miniature gas sensor communication link is interrupted or the miniature gas sensor has failed is generated. If alarm signals, and / or sensor abnormality indication signals, and / or sensor fault indication signals, and / or miniature gas sensor communication link interruption or miniature gas sensor failure indication signals persist during the continuous sampling period, fault-tolerant control will be implemented.

6. The method according to claim 5, characterized in that, The fault-tolerant control includes: Establish a pressure-flow model; Using the effective power value before switching to fault-tolerant mode, the corresponding chamber pressure value, and the total gas flow rate as data sources, the parameters in the pressure-flow model are locally corrected using the least squares method.

7. The method according to claim 6, characterized in that, The pressure-flow model is as follows: in, This is the backup power setting calculated in fault-tolerant mode. The chamber pressure value is measured by a high-precision vacuum timer. Q This represents the total gas flow rate. This represents the overall pumping efficiency coefficient of the turbomolecular pump. K This is the proportional adjustment coefficient.

8. A turbomolecular pump drive controller control device based on an adaptive control algorithm, characterized in that, The device includes: The acquisition module is used to acquire gas parameters inside the turbomolecular pump body collected in real time by the micro gas sensor. The gas parameters include molecular mass, concentration ratio, temperature and pressure. The calculation module is used to calculate the optimal power output value using the gas parameters as input and an improved radial basis function neural network algorithm, and to determine the optimal power output value as the power reference of the turbomolecular pump drive controller. The mode switching module is used to acquire the real-time pressure in the process chamber and automatically switch the operating mode of the turbomolecular pump drive controller according to the real-time pressure. The operating modes include standby mode, rapid vacuuming mode and precision control mode. The adjustment module is used to obtain the motor operating current. When a sudden load change is detected, the PWM duty cycle is adjusted until the current fluctuation is within the preset current change range.

9. An electronic device, characterized in that, include: The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform the turbomolecular pump drive controller control method based on the adaptive control algorithm as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the turbomolecular pump drive controller control method based on the adaptive control algorithm according to any one of claims 1 to 7.

Images