Energy efficiency optimization method and device of multi-channel intelligent temperature control system

Abstract

The invention relates to semiconductor temperature control, and provides an energy efficiency optimization method and device of a multi-channel intelligent temperature control system. In the semiconductor production process, the real-time temperature of each channel is collected through a sensor array; inputting the real-time temperature into a spatial-temporal feature extraction network, determining a temperature difference gradient between the channels, and determining an output proportion of each channel through dynamic weight distribution based on the temperature difference gradient; based on the production parameters and the real-time temperature in the semiconductor production process, the heat dissipation rate of the channel in the cavity is determined; generating a power distribution strategy for each channel according to the output proportion and the heat dissipation rate of each channel; and dynamically adjusting the energy supply of each channel based on a power distribution strategy. According to the process temperature difference gradient, the output proportion is dynamically distributed, the heat dissipation rate is determined in combination with the production parameters and the real-time temperature, finally, the power distribution strategy is generated, energy supply is dynamically adjusted, accurate temperature control is achieved, unnecessary energy waste is avoided, and the overall energy efficiency and the system stability are improved.

Description

Technical Field

[0001] This application relates to semiconductor temperature control. Specifically, it relates to an energy efficiency optimization method and device for a multi-channel intelligent temperature control system. Background Art

[0002] Multi-channel intelligent temperature control systems are widely used in various scenarios that require precise temperature control, such as industrial production. With the rising energy prices and increasing environmental awareness, improving energy efficiency has become an important consideration in the design and operation of these systems. Energy efficiency optimization can not only reduce operating costs but also reduce carbon emissions, meeting the requirements of sustainable development.

[0003] A multi-channel intelligent temperature control system needs to monitor and control multiple temperature channels to ensure that each channel can reach a predetermined temperature range. In some scenarios with high requirements for temperature control accuracy, temperature fluctuations may have a significant impact on device performance and product quality. However, in the prior art, there are problems with inaccurate temperature control during multi-channel temperature control. Summary of the Invention

[0004] This application provides an energy efficiency optimization method and device for a multi-channel intelligent temperature control system, which can at least to a certain extent solve the problem of inaccurate temperature control during multi-channel temperature control.

[0005] Other features and advantages of this application will become apparent through the following detailed description, or be learned in part through the practice of this application.

[0006] According to one aspect of this application, an energy efficiency optimization method for a multi-channel intelligent temperature control system is provided, including: during the semiconductor production process, collecting the real-time temperature of each channel through a sensor array; inputting the real-time temperature into a spatio-temporal feature extraction network to determine the temperature difference gradient between channels, and determining the output proportion of channels based on the temperature difference gradient through dynamic weight allocation; based on the production parameters and the real-time temperature during the semiconductor production process, determining the thermal resistance corresponding to each dimension of the channels in the cavity, and determining the heat dissipation rate of the channels based on the thermal resistance; generating a power allocation strategy for each channel according to the output proportion and the heat dissipation rate of the channels; dynamically adjusting the energy supply of each channel based on the power allocation strategy.

[0007] In this application, based on the foregoing solution, the step of collecting the real-time temperature of each channel through a sensor array during the semiconductor production process includes: through a semiconductor thermistor array, integrating a temperature and voltage conversion circuit in each channel to collect the real-time temperature of each channel through the semiconductor thermistor array during the semiconductor production process; performing linear processing on the real-time temperature based on a preset channel specificity coefficient to obtain the processed real-time temperature.

[0008] In the present application, based on the foregoing solution, inputting the real-time temperature into the spatio-temporal feature extraction network to determine the temperature difference gradient between channels, and determining the output proportion of channels through dynamic weight allocation based on the temperature difference gradient, includes: constructing a spatio-temporal feature extraction network based on a preset convolutional kernel and time domain length; forming a temperature sequence with the real-time temperature of the channels, inputting the temperature sequence into the spatio-temporal feature extraction network, and outputting the temperature difference gradient between channels; determining the output proportion of channels through dynamic weight allocation based on the temperature difference gradient.

[0009] In the present application, based on the foregoing solution, determining the thermal resistance corresponding to each dimension of the channels in the cavity based on the production parameters and the real-time temperature in the semiconductor production process, and determining the heat dissipation rate of the channels based on the thermal resistance, includes: determining the first thermal resistance from the chip to the channels in the cavity based on the normal temperature thermal resistance corresponding to the production material of the semiconductor and the real-time temperature; determining the second thermal resistance from the channels in the cavity to the radiator based on the material parameters of the production material and the real-time temperature; determining the heat dissipation rate of the channels in the cavity based on the first thermal resistance and the second thermal resistance.

[0010] In the present application, based on the foregoing solution, generating a power allocation strategy for each channel according to the output proportion and the heat dissipation rate of the channels, includes: determining the initial power of each channel based on the output proportion; adjusting the initial power according to the heat dissipation rate to generate a power allocation strategy for each channel.

[0011] In the present application, based on the foregoing solution, dynamically adjusting the energy supply of each channel based on the power allocation strategy, includes: obtaining the real-time temperature of each channel based on a set period; dynamically adjusting the power allocation strategy according to the real-time temperature, and simultaneously adjusting the energy supply of each channel.

[0012] In the present application, based on the foregoing solution, after collecting the real-time temperature of each channel through a sensor array during the semiconductor production process, it further includes: displaying the real-time temperature of each channel on the display screen of the control terminal.

[0013] According to one aspect of the present application, there is provided an energy efficiency optimization device for a multi-channel intelligent temperature control system, including:

[0014] An acquisition unit, configured to collect the real-time temperature of each channel through a sensor array during the semiconductor production process;

[0015] A proportion unit, configured to input the real-time temperature into a spatio-temporal feature extraction network to determine the temperature difference gradient between channels, and determine the output proportion of channels through dynamic weight allocation based on the temperature difference gradient;

[0016] A heat dissipation unit, configured to determine the thermal resistance corresponding to each dimension of the channels in the cavity based on the production parameters and the real-time temperature during the semiconductor production process, and determine the heat dissipation rate of the channels based on the thermal resistance;

[0017] A power unit, configured to generate a power distribution strategy for each channel according to the output ratio and the heat dissipation rate of the channels;

[0018] A supply unit, configured to dynamically adjust the energy supply of each channel based on the power distribution strategy.

[0019] In this application, based on the foregoing solution, during the semiconductor production process, collecting the real-time temperature of each channel through a sensor array includes: through a semiconductor thermistor array, integrating a temperature and voltage conversion circuit in each channel to collect the real-time temperature of each channel during the semiconductor production process; based on a preset channel-specific coefficient, performing linear processing on the real-time temperature to obtain the processed real-time temperature.

[0020] In this application, based on the foregoing solution, inputting the real-time temperature into a spatio-temporal feature extraction network to determine the temperature difference gradient between channels, and determining the output ratio of channels through dynamic weight allocation includes: constructing a spatio-temporal feature extraction network based on a preset convolution kernel and time domain length; forming a temperature sequence with the real-time temperature of the channels, inputting the temperature sequence into the spatio-temporal feature extraction network, and outputting the temperature difference gradient between channels; determining the output ratio of channels through dynamic weight allocation based on the temperature difference gradient.

[0021] In this application, based on the foregoing solution, determining the thermal resistance corresponding to each dimension of the channels in the cavity based on the production parameters and the real-time temperature during the semiconductor production process, and determining the heat dissipation rate of the channels based on the thermal resistance includes: determining the first thermal resistance from the chip to the channels in the cavity based on the normal temperature thermal resistance corresponding to the production material of the semiconductor and the real-time temperature; determining the second thermal resistance from the channels in the cavity to the radiator based on the material parameters of the production material and the real-time temperature; determining the heat dissipation rate of the channels in the cavity based on the first thermal resistance and the second thermal resistance.

[0022] In this application, based on the foregoing solution, generating a power distribution strategy for each channel according to the output ratio and the heat dissipation rate of the channels includes: determining the initial power of each channel based on the output ratio; adjusting the initial power according to the heat dissipation rate to generate a power distribution strategy for each channel.

[0023] In the present application, based on the foregoing solution, the dynamic adjustment of the energy supply for each channel based on the power distribution strategy includes: obtaining the real-time temperature of each channel based on a set period; dynamically adjusting the power distribution strategy according to the real-time temperature, and simultaneously adjusting the energy supply for each channel.

[0024] In the present application, based on the foregoing solution, after collecting the real-time temperature of each channel through a sensor array during the semiconductor production process, it further includes: displaying the real-time temperature of each channel on the display screen of the control terminal.

[0025] According to one aspect of the present application, there is provided a computer-readable medium having a computer program stored thereon, and when the computer program is executed by a processor, it implements the energy efficiency optimization method of the multi-channel intelligent temperature control system as described in the above embodiments.

[0026] According to one aspect of the present application, there is provided an electronic device, including: one or more processors; a storage device for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement the energy efficiency optimization method of the multi-channel intelligent temperature control system as described in the above embodiments.

[0027] According to one aspect of the present application, there is provided a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the energy efficiency optimization method of the multi-channel intelligent temperature control system provided in the above various optional implementation manners.

[0028] In the technical solution of the present application, during the semiconductor production process, the real-time temperature of each channel is collected through a sensor array; the real-time temperature is input into a spatio-temporal feature extraction network to determine the temperature difference gradient between channels, and based on the temperature difference gradient, the output ratio of each channel is determined through dynamic weight distribution; based on the production parameters and the real-time temperature during the semiconductor production process, the thermal resistance corresponding to each dimension of the channels in the cavity is determined, and the heat dissipation rate of each channel is determined based on the thermal resistance; according to the output ratio and the heat dissipation rate of each channel, a power distribution strategy for each channel is generated; and the energy supply for each channel is dynamically adjusted based on the power distribution strategy. The above process collects the real-time temperature through a sensor array, then dynamically distributes the output ratio based on the temperature difference gradient, then determines the heat dissipation rate in combination with the production parameters and the real-time temperature, and finally generates a power distribution strategy and dynamically adjusts the energy supply, achieving precise temperature control, avoiding unnecessary energy waste, and improving the overall energy efficiency and system stability.

[0029] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and do not limit the present application. Brief Description of the Drawings

[0030] The drawings herein are incorporated into the specification and form a part of this specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application. Obviously, the drawings in the following description are only some embodiments of the present application, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts.

[0031] Figure 1 A flowchart of an energy efficiency optimization method for a multi-channel intelligent temperature control system in an embodiment of the present application is schematically shown.

[0032] Figure 2 A flowchart of determining the output ratio of each channel in an embodiment of the present application is schematically shown.

[0033] Figure 3 A schematic diagram of an energy efficiency optimization device for a multi-channel intelligent temperature control system in an embodiment of the present application is schematically shown.

[0034] Figure 4 A schematic structural diagram of a computer system of an electronic device suitable for implementing the embodiments of the present application is shown. Detailed Embodiments

[0035] Example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be more complete and comprehensive, and will fully convey the concept of the example embodiments to those skilled in the art.

[0036] In addition, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of the embodiments of the present application. However, those skilled in the art will realize that the technical solutions of the present application can be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, well-known methods, devices, implementations, or operations are not shown or described in detail to avoid obscuring aspects of the present application.

[0037] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0038] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they have to be executed in the described order. For example, some operations / steps can be decomposed, while some operations / steps can be combined or partially combined, so the actual execution order may change according to the actual situation.

[0039] The implementation details of the technical solution of this application are elaborated in detail below:

[0040] Figure 1 A flowchart of an energy efficiency optimization method for a multi-channel intelligent temperature control system according to an embodiment of this application is shown. Referring to Figure 1 As shown, the energy efficiency optimization method for the multi-channel intelligent temperature control system includes at least steps S110 to S150, which are introduced in detail as follows:

[0041] In step S110, during the semiconductor production process, the real-time temperature of each channel is collected through a sensor array.

[0042] In this embodiment, during the semiconductor production process, minute temperature fluctuations may cause unstable performance, reduced reliability, or even functional failures of semiconductor devices. Precise temperature control can ensure that the wafer obtains a uniform and stable heat treatment effect during the manufacturing process, improve product quality, and ensure the safety and efficiency of the production process.

[0043] In this embodiment, the real-time temperature of each channel is collected through a sensor array. Communicate with the sensor array through a hardware interface to obtain temperature data. These data temperatures are usually transmitted to a microcontroller or an embedded system in the form of analog signals or digital signals.

[0044] In an embodiment of this application, during the semiconductor production process, collecting the real-time temperature of each channel through a sensor array includes:

[0045] Through a semiconductor thermistor array, a temperature and voltage conversion circuit is integrated in each channel to collect the real-time temperature of each channel through the semiconductor thermistor array during the semiconductor production process;

[0046] Based on a preset channel-specific coefficient, perform linear processing on the real-time temperature to obtain the processed real-time temperature.

[0047] Specifically, in this embodiment, a temperature sensor with high precision and high response speed, such as a thermistor, a thermocouple, or a digital temperature sensor, is adopted to improve the accuracy and real-time performance of temperature measurement.

[0048] Exemplarily, thermistors are arranged at different positions, each corresponding to a channel. Such a design can achieve temperature monitoring of multiple key points, ensuring temperature uniformity and stability throughout the production process. For example, during the wafer manufacturing process, the temperatures in different regions may vary due to uneven heat dissipation of equipment or changes in process parameters. Through multi-channel monitoring, it can be detected and adjusted in a timely manner. By increasing the number and distribution density of sensors, a more comprehensive monitoring of the temperature field in the semiconductor production environment is achieved.

[0049] Optionally, a positive temperature coefficient thermistor is adopted, whose resistance value changes with temperature. A temperature and voltage conversion circuit, namely an operational amplifier or an analog-to-digital converter, is integrated in each channel to convert the resistance change into a linear voltage signal. For example, the thermistor is connected in series with a fixed resistor through a voltage division circuit to output a voltage value related to temperature.

[0050] Optionally, after obtaining the real-time temperature, the collected temperature data is preliminarily processed. For example, the analog signal is converted into a digital signal through an analog-to-digital converter, and a filtering algorithm is applied to remove noise and outliers. The filtered temperature data is used for the feedback control system to adjust the power of the heating equipment during the semiconductor production process to maintain the temperature required by the process.

[0051] In this embodiment, aiming at the high-frequency thermal fluctuation characteristics in the semiconductor process, based on the preset channel-specific coefficient, the real-time temperature is linearly processed to obtain the processed real-time temperature y i (t) as follows:

[0052]

[0053] where α is the preset channel-specific coefficient, y′ i (t) is the real-time temperature of channel i at time t, N is the total number of channels, and i is the channel identifier. The processed real-time temperature obtained through the above linear processing improves the reliability of the real-time temperature data.

[0054] Optionally, the processed data is stored and transmitted to the host computer or the cloud platform for further analysis and visual display.

[0055] Optionally, real-time monitoring can also be performed according to the preset temperature threshold, and an alarm mechanism is triggered when the temperature is abnormal to ensure the stability and safety of the production process.

[0056] In the above process, by using a semiconductor thermistor array and integrating a temperature and voltage conversion circuit, high-precision temperature acquisition is achieved. The thermistor array provides high-precision temperature data, providing a reliable basis for subsequent calculations. The real-time temperature is filtered through a filter bank to effectively remove the noise in the temperature data and improve the accuracy of the data.

[0057] In an embodiment of the present application, after obtaining the real-time temperature, it is displayed to the user through the display screen of the control terminal. It is also possible to perform operations of drawing and updating the graphical interface for the real-time temperature, and dynamically display the real-time temperature of each channel on the screen according to the latest state of the real-time data.

[0058] Furthermore, the display screen will be refreshed in real time to reflect the latest changes in the real-time temperature, enabling the user to monitor the temperature status of each channel in real time.

[0059] In step S120, the real-time temperature is input into the spatio-temporal feature extraction network to determine the temperature difference gradient between channels, and based on the temperature difference gradient, the output proportion of each channel is determined through dynamic weight allocation.

[0060] In this embodiment, the collected real-time temperature data is transmitted to the microcontroller or embedded system through the hardware interface to calculate the temperature difference gradient between channels to evaluate the uniformity of the temperature distribution. Then, based on the temperature difference gradient, a dynamic weight allocation algorithm is used to allocate corresponding weights to each channel. The magnitude of the weight is inversely proportional to the temperature difference gradient to ensure that the channels with higher temperatures have a lower proportion in the output, while the channels with lower temperatures have an increased proportion. Finally, the system uses the weighted temperature data for further analysis or control to achieve temperature balance and optimize the stability of the production process.

[0061] As Figure 2 shown, in an embodiment of the present application, inputting the real-time temperature into the spatio-temporal feature extraction network to determine the temperature difference gradient between channels, and determining the output proportion of channels through dynamic weight allocation based on the temperature difference gradient includes:

[0062] S210, constructing a spatio-temporal feature extraction network based on a preset convolution kernel and time domain length;

[0063] S220, forming a temperature sequence from the real-time temperature of the channels, inputting the temperature sequence into the spatio-temporal feature extraction network, and outputting the temperature difference gradient between channels;

[0064] S230, determining the output proportion of channels through dynamic weight allocation based on the temperature difference gradient.

[0065] In this embodiment, a spatio-temporal feature extraction network is constructed by combining the dual characteristics of spatial locality and temporal dependence. Specifically, in the spatial dimension, multi-scale feature extraction is performed on the input data through a preset convolutional kernel; the convolutional layer can capture the spatial correlation between adjacent channels. For example, in a temperature sequence, the spatial distribution patterns of different sensor channels can be hierarchically abstracted into local features through multiple layers of convolution. In the temporal dimension, a reasonable time-domain length is set, such as a sliding window or a fixed time step, and combined with a bidirectional gated recurrent unit or a long short-term memory network to model the forward and backward dynamic changes of the sequence. For example, the bidirectional structure can capture both historical and future information simultaneously, enhancing the modeling ability of the long-term dependence relationship of the temperature time series. Finally, the network forms parallel branches by stacking convolutional layers and recurrent layers to achieve explicit separation and joint optimization of spatio-temporal features.

[0066] Exemplarily, in this embodiment, a spatio-temporal feature extraction network is constructed based on a preset convolutional kernel and time-domain length. Among them, the number of convolutional kernels can be 128, and the time-domain length can be 64.

[0067] After inputting the real-time temperature sequence of each channel into the spatio-temporal feature extraction network, the network first extracts spatial features through the convolutional layer, such as local temperature change patterns. Subsequently, the time-series dynamics are modeled through the recurrent layer, such as periodic fluctuation trends. During this process, the feature maps of different channels generate high-dimensional feature vectors after passing through a non-linear activation function and a pooling operation, which are used to characterize the temperature characteristics of each channel. Further, the network interacts the spatio-temporal features through a feature fusion module and calculates the similarity matrix or covariance matrix between channels, thereby quantifying the temperature difference gradient between channels.

[0068] In this embodiment, a temperature sequence is composed of the real-time temperatures of the channels, and the temperature sequence is input into the spatio-temporal feature extraction network, and the temperature difference gradient G ij (t) between channels i and j at time t is:

[0069]

[0070] where σ(·) represents the activation function; N is the total number of channels, i and j are channel identifiers; L represents the time-domain length, l represents the time step; ω il is the convolutional kernel weight corresponding to channel i at time step l, T i (t - l) and T j (t - l) represent the real-time temperatures corresponding to channels i and j at time t - l respectively, t represents time, and b represents the temperature factor trained according to historical data.

[0071] In this embodiment, the core of dynamic weight allocation lies in using the temperature difference gradient as the feature importance criterion. By introducing the attention mechanism, the model can allocate dynamic weights to different channels. First, the temperature difference gradient is weighted with the historical hidden state output by the hidden layer to generate attention scores. Second, the Softmax function is used to normalize the attention scores to obtain the output proportion of each channel.

[0072] Exemplarily, in the global attention mechanism, the weight matrix is adjusted according to the real-time temperature gradient, enabling the model to focus on abnormal temperature regions or key sensor nodes. In addition, parameter tuning can be performed on the weight allocation process to avoid the traditional gradient descent falling into local optima, thereby improving the robustness and prediction accuracy of weight allocation. Finally, the weighted features are mapped to the output proportion of each channel through the fully connected layer to achieve the adaptive reconstruction of the temperature field.

[0073] In this embodiment, the calculated temperature difference gradient is used to measure the temperature difference between different channels. When the temperature gradient between channels exceeds the set threshold, it indicates that the temperature between channels has become very unstable. Then, based on the temperature difference gradient, the output proportion ρ corresponding to channel i is determined through dynamic weight allocation. i It is:

[0074]

[0075] where K p (t) and K d (t) respectively represent the proportional gain and integral gain corresponding to time t. represents the system weight coefficient between channel i and channel j, T i (t) represents the real-time temperature of channel i, τ represents the time component, and t represents time.

[0076] In the above process, by constructing a spatio-temporal feature extraction network and using the convolution kernel and time domain length to process the temperature sequence, the spatio-temporal feature extraction network can accurately capture the spatio-temporal features of temperature changes and achieve intelligent weight allocation. Based on the temperature difference gradient, the output proportion of each channel is determined through dynamic weight allocation to ensure more reasonable energy supply for each channel.

[0077] In step S130, based on the production parameters and the real-time temperature in the semiconductor production process, the thermal resistance corresponding to each dimension of the channels in the cavity is determined, and the heat dissipation rate of the channels is determined based on the thermal resistance.

[0078] In the embodiments of the present application, during the semiconductor production process, temperature data of each channel in the cavity is collected in real time by a sensor array, analyzed in combination with production parameters, and the heat dissipation rate of each channel is calculated through a thermodynamic model. Based on the calculation results, the heat dissipation strategy is dynamically adjusted, such as adjusting the fan speed or optimizing the coolant flow rate, to ensure the uniformity and stability of the temperature distribution in the cavity. The entire process is implemented through an embedded system or host computer software and can be adaptively optimized according to real-time feedback.

[0079] In one embodiment of the present application, based on the production parameters and the real-time temperature during the semiconductor production process, the thermal resistance corresponding to each dimension of the channel in the cavity is determined, and the heat dissipation rate of the channel is determined based on the thermal resistance, including:

[0080] Based on the normal temperature thermal resistance corresponding to the production material of the semiconductor and the real-time temperature, determine the first thermal resistance from the chip to the channel in the cavity;

[0081] Based on the material parameters of the production material and the real-time temperature, determine the second thermal resistance from the channel in the cavity to the radiator;

[0082] Based on the first thermal resistance and the second thermal resistance, determine the heat dissipation rate of the channel in the cavity.

[0083] In practical applications, thermal resistance is a physical quantity that describes the ability of an object to impede heat transfer and reflects the magnitude of the heat transfer ability between media. In this embodiment, the heat dissipation rate of the channel in the cavity is determined by integrating thermal resistance information.

[0084] In one embodiment of the present application, obtain the normal temperature thermal resistance of the production material of the semiconductor at normal temperature. Based on the normal temperature thermal resistance and the real-time temperature, determine the first thermal resistance R th，c (T) as:

[0085]

[0086] where T represents the real-time temperature, and R th，c0 represents the normal temperature thermal resistance of the production material at normal temperature, exp(·) represents the natural exponential operation, and E α represents the activation energy, and K B represents the Boltzmann constant. The first thermal resistance is calculated through the above process and is used to measure the heat dissipation efficiency from the chip to each channel in the cavity.

[0087] After that, obtain the material parameters of the production material, where the material parameters include material density, specific heat capacity, contact area, contact surface deformation, and thermal conductivity. After that, based on the material parameters of the production material and the real-time temperature, determine the second thermal resistance R th，s (T) as:

[0088]

[0089] Among them, ρ c represents the material density of the production material, c ρ represents the specific heat capacity of the production material, Δh represents the deformation amount of the contact surface between each channel in the cavity and the radiator, A represents the contact area between each channel in the cavity and the radiator, T represents the real-time temperature, and k TIM represents the thermal conductivity of the production material. The second thermal resistance is obtained through the above calculation, and is used to characterize the heat dissipation efficiency from each channel in the cavity to the radiator through the second thermal resistance.

[0090] After calculating and obtaining the first thermal resistance from the chip to the channels in the cavity and the second thermal resistance from each channel in the cavity to the radiator, the first thermal resistance and the second thermal resistance are weighted, and then the heat dissipation rate of each channel in the cavity can be obtained.

[0091] In the above process, the first thermal resistance and the second thermal resistance are calculated based on the normal temperature thermal resistance, real-time temperature, material parameters, etc. of the production material. Combining the first thermal resistance and the second thermal resistance, the heat dissipation rate of each channel is determined. It can flexibly adjust the calculation method of the heat dissipation rate according to different production materials and real-time temperatures, and has good adaptability. Considering various factors comprehensively, the heat dissipation rate is accurately calculated, providing an accurate basis for power distribution.

[0092] In step S140, according to the output ratio and the heat dissipation rate of the channel, a power distribution strategy for each channel is generated.

[0093] In this embodiment, after determining the output ratio and the heat dissipation rate of each channel, through a dynamic weight distribution algorithm, combining the heat dissipation rate and the output ratio, an optimized power distribution strategy is generated for each channel. For example, channels with a lower output ratio and heat dissipation rate will be allocated lower power to avoid overheating, while channels with a higher output ratio and heat dissipation rate may be allocated higher power to make full use of their heat dissipation capacity. The system ensures the uniformity of the temperature distribution in the cavity and the stability of the production process by adjusting the power distribution in real time, while optimizing the overall energy consumption.

[0094] In an embodiment of the present application, generating a power distribution strategy for each channel according to the output ratio and the heat dissipation rate of the channel includes:

[0095] Determining the initial power of each channel based on the output ratio;

[0096] Adjusting the initial power according to the heat dissipation rate to generate a power distribution strategy for each channel.

[0097] In this embodiment, after determining the output ratio and the heat dissipation rate, the power for each channel is determined according to the output ratio and the heat dissipation rate of each channel. First, a basic allocation is performed based on the output ratio, that is, the total power is allocated according to the ratio of the output ratio to determine the initial power of each channel, which is used to adapt the working state of each channel through the initial power.

[0098] After that, the initial power of each channel is dynamically adjusted according to the heat dissipation rate, so that during the process of intelligently controlling the channel temperature, both the action state of each channel can be guaranteed and the heat dissipation situation of each channel can be adapted. On the basis of ensuring the temperature control efficiency, the energy efficiency is improved.

[0099] In the above process, the initial power is determined based on the output ratio. The initial power is adjusted according to the heat dissipation rate to generate the final power allocation strategy. Combining the output ratio and the heat dissipation rate, the reasonable allocation of power is realized to avoid energy waste. At the same time, the power allocation strategy can be dynamically adjusted according to the change of the heat dissipation rate to ensure the temperature control effect.

[0100] In step S150, the energy supply of each channel is dynamically adjusted based on the power allocation strategy.

[0101] In the embodiment of the present application, based on the power allocation strategy of each channel, the energy supply is dynamically adjusted by real-time monitoring the temperature and heat dissipation rate of each channel. For example, a channel with a lower heat dissipation rate will be allocated less energy to avoid overheating, while a channel with a higher heat dissipation rate may obtain more energy to maintain efficient operation. The whole process is realized through an embedded system or a host computer software to ensure the real-time performance and stability of the energy supply, while optimizing the overall energy consumption and production efficiency.

[0102] In an embodiment of the present application, dynamically adjusting the energy supply of each channel based on the power allocation strategy includes:

[0103] Obtaining the real-time temperature of each channel based on a set period;

[0104] Dynamically adjusting the power allocation strategy according to the real-time temperature, and at the same time adjusting the energy supply of each channel.

[0105] In this embodiment, according to a preset period, the real-time temperature of each channel is regularly obtained to ensure that the change of the temperature can be captured in time. Then, based on these real-time temperature data, the current power allocation strategy is dynamically adjusted. If the temperature of a certain real-time channel is too high, the working power allocation of this channel is reduced and the heat dissipation work allocation is increased to avoid the risk of overheating; on the contrary, if the real-time temperature is relatively low, the working power allocation can be increased to improve the efficiency.

[0106] While adjusting the power distribution strategy, the energy supply of each channel is adjusted accordingly to ensure energy balance and efficient utilization among channels while meeting the overall energy demand.

[0107] The above process obtains the real-time temperature of each channel based on a set period, dynamically adjusts the power distribution strategy according to the real-time temperature, and at the same time adjusts the energy supply of each channel. It can respond to temperature changes in real time, adjust the energy supply in a timely manner to ensure the temperature control effect. The dynamic adjustment strategy can cope with temperature fluctuations and improve the stability of the system.

[0108] In an embodiment of the present application, during the semiconductor production process, the real-time temperature of each channel is collected through a sensor array; the real-time temperature is input into a spatio-temporal feature extraction network to determine the temperature difference gradient between channels, and the output ratio of each channel is determined through dynamic weight distribution based on the temperature difference gradient; based on the production parameters and the real-time temperature during the semiconductor production process, the thermal resistance corresponding to each dimension of the channels in the cavity is determined, and the heat dissipation rate of the channels is determined based on the thermal resistance; according to the output ratio and the heat dissipation rate of the channels, a power distribution strategy for each channel is generated; the energy supply of each channel is dynamically adjusted based on the power distribution strategy. The above process collects real-time temperature through a sensor array, then dynamically distributes the output ratio based on the temperature difference gradient, then determines the heat dissipation rate in combination with production parameters and real-time temperature, and finally generates a power distribution strategy and dynamically adjusts the energy supply, achieving precise temperature control, avoiding unnecessary energy waste, and improving the overall energy efficiency and system stability.

[0109] The following introduces the device embodiments of the present application, which can be used to execute the energy efficiency optimization method of the multi-channel intelligent temperature control system in the above embodiments of the present application. It can be understood that the device can be a computer program (including program code) running in a computer device, for example, the device is an application software; the device can be used to execute the corresponding steps in the method provided by the embodiments of the present application. For the details not disclosed in the device embodiments of the present application, please refer to the embodiments of the energy efficiency optimization method of the multi-channel intelligent temperature control system in the above of the present application.

[0110] Figure 3 The block diagram of the energy efficiency optimization device of the multi-channel intelligent temperature control system according to an embodiment of the present application is shown.

[0111] Refer to Figure 3 As shown, the energy efficiency optimization device of the multi-channel intelligent temperature control system according to an embodiment of the present application includes:

[0112] An acquisition unit 310, configured to collect the real-time temperature of each channel through a sensor array during the semiconductor production process;

[0113] The proportion unit 320 is configured to input the real-time temperature into the spatio-temporal feature extraction network, determine the temperature difference gradient between channels, and determine the output proportion of channels through dynamic weight allocation based on the temperature difference gradient;

[0114] The heat dissipation unit 330 is configured to determine the thermal resistance corresponding to each dimension of the channels in the cavity based on the production parameters and the real-time temperature during the semiconductor production process, and determine the heat dissipation rate of the channels based on the thermal resistance;

[0115] The power unit 340 is configured to generate a power allocation strategy for each channel according to the output proportion and the heat dissipation rate of the channels;

[0116] The supply unit 350 is configured to dynamically adjust the energy supply of each channel based on the power allocation strategy.

[0117] In this application, based on the foregoing solution, during the semiconductor production process, the real-time temperature of each channel is collected through a sensor array, including: through a semiconductor thermistor array, a temperature and voltage conversion circuit is integrated in each channel to collect the real-time temperature of each channel during the semiconductor production process; based on a preset channel specificity coefficient, linear processing is performed on the real-time temperature to obtain the processed real-time temperature.

[0118] In this application, based on the foregoing solution, the step of inputting the real-time temperature into the spatio-temporal feature extraction network, determining the temperature difference gradient between channels, and determining the output proportion of channels through dynamic weight allocation based on the temperature difference gradient includes: constructing a spatio-temporal feature extraction network based on a preset convolution kernel and time domain length; forming a temperature sequence with the real-time temperature of the channels, inputting the temperature sequence into the spatio-temporal feature extraction network, and outputting the temperature difference gradient between channels; determining the output proportion of channels through dynamic weight allocation based on the temperature difference gradient.

[0119] In this application, based on the foregoing solution, the step of determining the thermal resistance corresponding to each dimension of the channels in the cavity based on the production parameters and the real-time temperature during the semiconductor production process, and determining the heat dissipation rate of the channels based on the thermal resistance includes: determining a first thermal resistance from the chip to the channels in the cavity based on the normal temperature thermal resistance corresponding to the production material of the semiconductor and the real-time temperature; determining a second thermal resistance from the channels in the cavity to the radiator based on the material parameters of the production material and the real-time temperature; determining the heat dissipation rate of the channels in the cavity based on the first thermal resistance and the second thermal resistance.

[0120] In the present application, based on the foregoing solution, generating a power allocation strategy for each channel according to the output ratio and the heat dissipation rate of the channel includes: determining the initial power of each channel based on the output ratio; and adjusting the initial power according to the heat dissipation rate to generate a power allocation strategy for each channel.

[0121] In the present application, based on the foregoing solution, dynamically adjusting the energy supply of each channel based on the power allocation strategy includes: obtaining the real-time temperature of each channel based on a set period; dynamically adjusting the power allocation strategy according to the real-time temperature, and simultaneously adjusting the energy supply of each channel.

[0122] In the present application, based on the foregoing solution, after collecting the real-time temperature of each channel through a sensor array during the semiconductor production process, it further includes: displaying the real-time temperature of each channel on the display screen of the control terminal.

[0123] Figure 4 The structural diagram of a computer system of an electronic device suitable for implementing the embodiments of the present application is shown.

[0124] It should be noted that the computer system of the electronic device in this embodiment is only an example, and should not impose any restrictions on the functions and usage scopes of the embodiments of the present application.

[0125] The computer system in this embodiment includes a central processing unit 401, which can perform various appropriate actions and processes according to the program stored in the read-only memory 402 or the program loaded from the storage section 408 into the random access memory 403, such as executing the energy efficiency optimization method of the multi-channel intelligent temperature control system described in the foregoing embodiments. In the random access memory 403, various programs and data required for system operation are also stored. The central processing unit 401, the read-only memory 402, and the random access memory 403 are connected to each other through a bus 404. The input / output interface 405 is also connected to the bus 404.

[0126] The following components are connected to the input / output interface 405: an input section 406 including a keyboard, a mouse, etc.; an output section 407 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the input / output interface 405 as required. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as required so that a computer program read from it can be installed into the storage section 408 as required.

[0127] Specifically, according to an embodiment of the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, an embodiment of the present application includes a computer program product that includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 409, and / or installed from the removable medium 411. When the computer program is executed by the central processing unit 401, various functions defined in the system of the present application are executed.

[0128] It should be noted that the computer-readable medium shown in the embodiments of the present application can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of a computer-readable storage medium can include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present application, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable computer program is carried. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, and this computer-readable medium can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The computer program contained on a computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0129] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. Among them, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code, and the above module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, and the combination of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0130] The units involved in the embodiments described in this application can be implemented in software or in hardware, and the described units can also be provided in a processor. Among them, the names of these units do not, in some cases, constitute a limitation on the unit itself.

[0131] According to one aspect of the present application, there is provided a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in the above various alternative implementation manners.

[0132] As another aspect, the present application further provides a computer-readable medium, which may be included in the electronic device described in the above embodiments; or may exist alone without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the one or more programs are executed by an electronic device, the electronic device implements the energy efficiency optimization method of the multi-channel intelligent temperature control system described in the above embodiments.

[0133] It should be noted that although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of the two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0134] Through the description of the above embodiments, those skilled in the art can easily understand that the example embodiments described herein can be implemented in software or in a manner of software combined with necessary hardware. Therefore, the technical solutions according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (such as a personal computer, a server, a touch terminal, or a network device, etc.) to execute the methods according to the embodiments of the present application.

[0135] After considering the specification and practicing the disclosed embodiments herein, those skilled in the art will readily conceive of other embodiments of the present application. The present application is intended to cover any variations, uses, or adaptations of the present application, which follow the general principles of the present application and include common general knowledge or conventional technical means in the technical field not disclosed in the present application.

[0136] It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present application is only limited by the appended claims.

Claims

1. An energy efficiency optimization method for a multi-channel intelligent temperature control system, characterized in that Comprising: During the semiconductor production process, the real-time temperature of each channel is collected through a sensor array; The real-time temperature is input into a spatio-temporal feature extraction network to determine the temperature difference gradient between channels, and based on the temperature difference gradient, the output proportion of each channel is determined through dynamic weight allocation; Based on the production parameters and the real-time temperature during the semiconductor production process, the thermal resistance corresponding to each dimension of the channels in the cavity is determined, and based on the thermal resistance, the heat dissipation rate of the channels is determined; According to the output proportion and the heat dissipation rate of the channels, a power allocation strategy for each channel is generated; Based on the power allocation strategy, the energy supply of each channel is dynamically adjusted.

2. The energy efficiency optimization method of the multi-channel intelligent temperature control system according to claim 1, characterized in that The step of, during the semiconductor production process, collecting the real-time temperature of each channel through a sensor array includes: Through a semiconductor thermistor array, a temperature and voltage conversion circuit is integrated in each channel to collect the real-time temperature of each channel through the semiconductor thermistor array during the semiconductor production process; Based on a preset channel specificity coefficient, linear processing is performed on the real-time temperature to obtain the processed real-time temperature.

3. The energy efficiency optimization method for the multi-channel intelligent temperature control system according to claim 1, characterized in that, The step of inputting the real-time temperature into a spatio-temporal feature extraction network to determine the temperature difference gradient between channels, and based on the temperature difference gradient, determining the output proportion of each channel through dynamic weight allocation includes: Construct a spatio-temporal feature extraction network based on a preset convolution kernel and time domain length; A temperature sequence is formed by the real-time temperature of the channels, and the temperature sequence is input into the spatio-temporal feature extraction network to output the temperature difference gradient between channels; Based on the temperature difference gradient, the output proportion of each channel is determined through dynamic weight allocation.

4. The energy efficiency optimization method of the multi-channel intelligent temperature control system according to claim 1, characterized in that The step of, based on the production parameters and the real-time temperature during the semiconductor production process, determining the thermal resistance corresponding to each dimension of the channels in the cavity and determining the heat dissipation rate of the channels based on the thermal resistance includes: Based on the normal temperature thermal resistance corresponding to the production material of the semiconductor and the real-time temperature, determine the first thermal resistance from the chip to the channels in the cavity; Based on the material parameters of the production material and the real-time temperature, determine the second thermal resistance from the channels in the cavity to the radiator; Based on the first thermal resistance and the second thermal resistance, determine the heat dissipation rate of the channels in the cavity.

5. The energy efficiency optimization method of the multi-channel intelligent temperature control system according to claim 1, characterized in that The step of, according to the output proportion and the heat dissipation rate of the channels, generating a power allocation strategy for each channel includes: Based on the output proportion, determine the initial power of each channel; According to the heat dissipation rate, adjust the initial power to generate a power allocation strategy for each channel.

6. The energy efficiency optimization method of the multi-channel intelligent temperature control system according to claim 1, characterized in that The step of, based on the power allocation strategy, dynamically adjusting the energy supply of each channel includes: Obtain the real-time temperature of each channel based on a set period; Dynamically adjust the power allocation strategy according to the real-time temperature, and at the same time adjust the energy supply of each channel.

7. The energy efficiency optimization method of the multi-channel intelligent temperature control system according to claim 1, characterized in that After the step of, during the semiconductor production process, collecting the real-time temperature of each channel through a sensor array, it further includes: Display the real-time temperature of each channel on the display screen of the control terminal.

8. An energy efficiency optimization device for a multi-channel intelligent temperature control system, characterized in that, Comprising: An acquisition unit for collecting the real-time temperature of each channel through a sensor array during the semiconductor production process; A proportion unit for inputting the real-time temperature into a spatio-temporal feature extraction network, determining the temperature difference gradient between channels, and determining the output proportion of channels through dynamic weight allocation based on the temperature difference gradient; A heat dissipation unit for determining the thermal resistance corresponding to each dimension of the channels in the cavity based on the production parameters and the real-time temperature during the semiconductor production process, and determining the heat dissipation rate of the channels based on the thermal resistance; A power unit for generating a power allocation strategy for each channel according to the output proportion and the heat dissipation rate of the channels; A supply unit for dynamically adjusting the energy supply of each channel based on the power allocation strategy.

9. The energy efficiency optimization device of the multi-channel intelligent temperature control system according to claim 8, characterized in that During the semiconductor production process, collecting the real-time temperature of each channel through a sensor array, including: Integrating a temperature and voltage conversion circuit in each channel through a semiconductor thermistor array to collect the real-time temperature of each channel through the semiconductor thermistor array during the semiconductor production process; Performing linear processing on the real-time temperature based on a preset channel specificity coefficient to obtain the processed real-time temperature.

10. The energy efficiency optimization device of the multi-channel intelligent temperature control system according to claim 8, characterized in that, Inputting the real-time temperature into a spatio-temporal feature extraction network, determining the temperature difference gradient between channels, and determining the output proportion of channels through dynamic weight allocation based on the temperature difference gradient, including: Constructing a spatio-temporal feature extraction network based on a preset convolution kernel and time domain length; Composing a temperature sequence from the real-time temperature of the channels, inputting the temperature sequence into the spatio-temporal feature extraction network, and outputting the temperature difference gradient between channels; Determining the output proportion of channels through dynamic weight allocation based on the temperature difference gradient.

Images