Integrating sphere diffuse reflection laser cooling optimization method based on Bayesian optimization

Abstract

The invention provides an integrating sphere diffuse reflection laser cooling optimization method based on Bayesian optimization, which can find an optimal parameter combination within a small number of iterations and improve the parameter optimization efficiency of an integrating sphere diffuse reflection laser cooling experiment. The method comprises the following steps: determining optimization parameter ranges of frequencies and powers of cooling light, re-pumping light and probe light; within the range, selecting at least one group of initial parameters of frequencies and powers of cooling light, re-pumping light and detection light to perform an experiment in an integrating sphere diffuse reflection laser cooling system, obtaining a cost function value corresponding to each group of initial parameters, forming an initial data set by each group of initial parameters and the cost function value corresponding to each group of initial parameters, and obtaining a cost function value corresponding to each group of initial parameters on the basis of the initial data set; fitting a cost function by using a Bayesian optimization algorithm, and predicting an optimal parameter; performing an experiment on the optimal parameter to obtain a cost function value corresponding to the optimal parameter; and subsequently judging whether the cost function value corresponding to the optimal parameter reaches a preset condition or not so as to determine a final optimal parameter.

Description

Technical Field

[0001] The present application relates to the technical field of cold atomic frequency standards, and in particular to an integrating sphere diffuse reflection laser cooling optimization method, system, device and storage medium based on Bayesian optimization. Background Art

[0002] The basic working principle of the integrating sphere cooling process is to lock the output frequency of the local oscillator to the transition spectrum of the cold atom cooled by diffuse laser, so that the local oscillator outputs a highly stable and accurate frequency signal. Its frequency stability and uncertainty can reach extremely high levels, and it can achieve more accurate time synchronization and measurement in fields with extremely high requirements for time accuracy, such as scientific research, navigation and positioning. Diffuse laser cooling is a key technology for integrating sphere cold atomic clocks, and optimizing the parameters in the process plays a vital role in the cooling of the integrating sphere. The diffuse light field in the integrating sphere includes: detection light, four cooling lasers and re-pumping light. In order to achieve efficient cooling of atoms in the integrating sphere, it is necessary to optimize the frequency, power and incident direction of the detection light, cooling light and re-pumping light. According to the experimental measurement of diffuse laser cooling parameters, the adjustment range of experimental parameters exists in a specific area according to physical theory, and can be optimized in stages according to the theory. However, the adjustment between the frequency, power and incident directions of the detection light, cooling light and re-pumping light is generally not independent of each other. The experimental parameters obtained based on empirical optimization are easily affected by external factors and subjective factors. The same experimental parameters may produce different measurement results in different experimental environments. In addition, it takes a lot of time and effort to optimize the parameters based on experimental results.

[0003] At present, the method of combining machine learning with physical experiments to optimize the parameters of diffuse laser cooling can greatly save time and improve optimization efficiency. The algorithm is used to optimize the system parameters, and the cost function is designed by combining the experimental system. The optimization algorithm is used to maximize the cost function, and finally the optimal experimental parameters can be determined. However, the methods for online optimization of quantum system parameters using machine learning algorithms mainly include artificial neural networks and differential evolution algorithms. Such algorithms still have obvious disadvantages. Artificial neural network algorithms usually require a large amount of training data to obtain better performance. When the amount of data is insufficient, overfitting problems may occur; differential evolution algorithms also rely on the quality and number of the initial population.

[0004] Therefore, in order to overcome the limitations of commonly used optimization algorithms, it is necessary to find a better machine learning algorithm to combine with the integrating sphere diffuse reflection laser cooling experimental parameters to improve the optimization efficiency of the integrating sphere diffuse reflection laser cooling experimental parameters. Summary of the invention

[0005] The embodiments of the present application provide an integrating sphere diffuse reflection laser cooling optimization method, system, device and storage medium based on Bayesian optimization. By combining the Bayesian optimization machine learning algorithm with physical experiments, the optimal parameter combination can be efficiently found within a small number of iterations, thereby improving the optimization efficiency of the integrating sphere diffuse reflection laser cooling experiment parameters.

[0006] In order to achieve the above objectives, this application adopts the following technical solutions:

[0007] In a first aspect, the present application provides an integrating sphere diffuse reflection laser cooling optimization method based on Bayesian optimization, the method comprising: S1, determining the optimization parameter range of the frequency and power of cooling light, re-pumping light, and detection light; S2, within the optimization parameter range, selecting at least one set of initial parameters of the frequency and power of cooling light, re-pumping light, and detection light to experiment in an integrating sphere diffuse reflection laser cooling system, obtaining the cost function value corresponding to each set of initial parameters, each set of initial parameters and the cost function value corresponding to each set of initial parameters constitute an initial data set, wherein the cost function value corresponding to each set of initial parameters is the intensity value of the laser cooling absorption signal in the integrating sphere obtained from the experiment of each set of initial parameters; S3, based on the initial data set, using the Bayesian optimization algorithm to fit the cost function, and predict the optimal Parameters; S4. Experiment the optimal parameters in the integrating sphere diffuse reflection laser cooling system to obtain the cost function value corresponding to the optimal parameters; S5. Compare the cost function value corresponding to the optimal parameters with the cost function value in the initial data set to determine whether the cost function value corresponding to the optimal parameters is the maximum value; S6. If so, record the optimal parameters, and further determine whether the preset exit conditions are met. If the preset exit conditions are met, output the optimal parameters. If the preset exit conditions are not met, add the optimal parameters and the cost function value corresponding to the optimal parameters to the initial data set, and return to execute S3 until the preset exit conditions are met; S7. If not, add the optimal parameters and the cost function value corresponding to the optimal parameters to the initial data set, and return to execute S3 until the preset exit conditions are met.

[0008] In a possible design scheme, the method of the first aspect also includes that the optimized parameter ranges of the frequency and power of the cooling light are: 115 MHz to 125 MHz, and 5 mW to 85 mW, respectively.

[0009] In a possible design scheme, the method of the first aspect further includes that the optimized parameter ranges of the frequency and power of the re-pumping light are: 120 MHz to 130 MHz, and 3 mW to 20 mW, respectively.

[0010] In a possible design scheme, the method of the first aspect also includes that the optimized parameter ranges of the frequency and power of the detection light are: 110 MHz to 120 MHz, and 0 mW to 10 mW, respectively.

[0011] A possible design scheme, the method of the first aspect also includes, based on the initial data set, using a Bayesian optimization algorithm to fit a cost function and predict the optimal parameters, including: using the initial data set to build a proxy model to approximate the objective function, wherein the objective function is the final fitted cost function; based on the acquisition function, selecting at least one set of parameters, calculating the cost function value corresponding to each of at least one set of parameters, optimizing the proxy model, and obtaining the objective function; based on the objective function, predicting the optimal parameters.

[0012] A possible design scheme, the method of the first aspect also includes that the exit condition includes: reaching a predetermined iteration number threshold, or the cost function values ​​corresponding to the optimal parameters predicted N consecutive times do not exceed the previous maximum value, where N is a positive integer greater than or equal to zero.

[0013] In a second aspect, the present application provides an integrating sphere diffuse reflection laser cooling optimization system based on Bayesian optimization, the system comprising: a determination module, a processing module and a judgment module;

[0014] A determination module, used to determine the optimized parameter range of the frequency and power of the cooling light, the re-pumping light, and the detection light;

[0015] A processing module is used to select at least one set of initial parameters of the frequency and power of cooling light, re-pumping light, and detection light within the optimization parameter range, and conduct experiments in an integrating sphere diffuse reflection laser cooling system to obtain cost function values ​​corresponding to each set of initial parameters, wherein each set of initial parameters and the cost function values ​​corresponding to each set of initial parameters constitute an initial data set, wherein the cost function value corresponding to each set of initial parameters is the intensity value of the laser cooling absorption signal in the integrating sphere obtained from the experiment of each set of initial parameters; and to fit the cost function based on the initial data set using a Bayesian optimization algorithm and predict the optimal parameters; and also to conduct experiments on the optimal parameters in an integrating sphere diffuse reflection laser cooling system to obtain the cost function values ​​corresponding to the optimal parameters;

[0016] A judgment module is used to compare the cost function value corresponding to the optimal parameter with the cost function value in the initial data set to determine whether the cost function value corresponding to the optimal parameter is the maximum value; if so, the optimal parameter is recorded, and further judgment is made as to whether the preset exit condition is met. If the preset exit condition is met, the optimal parameter is output; if the preset exit condition is not met, the optimal parameter and the cost function value corresponding to the optimal parameter are added to the initial data set, and the process returns to execute S3 until the preset exit condition is met; if not, the optimal parameter and the cost function value corresponding to the optimal parameter are added to the initial data set, and the process returns to execute S3 until the preset exit condition is met.

[0017] In a third aspect, an integrating sphere diffuse reflection laser cooling optimization device based on Bayesian optimization is provided, and the integrating sphere diffuse reflection laser cooling optimization device based on Bayesian optimization includes a module for executing the method of the first aspect mentioned above.

[0018] In a possible design scheme, the integrating sphere diffuse reflection laser cooling optimization device based on Bayesian optimization of the third aspect may also include a transceiver. The transceiver may be a transceiver circuit or an interface circuit. The transceiver may be used for the integrating sphere diffuse reflection laser cooling optimization device based on Bayesian optimization of the third aspect to communicate with other devices.

[0019] In a possible design scheme, the integrating sphere diffuse reflection laser cooling optimization device based on Bayesian optimization of the third aspect may also include a memory. The memory may be integrated with the processor or may be separately provided. The memory may be used to store instructions involved in the method of the first aspect.

[0020] In a fourth aspect, an integrating sphere diffuse reflection laser cooling optimization device based on Bayesian optimization is provided. The integrating sphere diffuse reflection laser cooling optimization device based on Bayesian optimization comprises: a processor coupled to a memory, the processor being used to execute instructions stored in the memory so that the integrating sphere diffuse reflection laser cooling optimization device based on Bayesian optimization performs the method of the first aspect.

[0021] In a possible design scheme, the integrating sphere diffuse reflection laser cooling optimization device based on Bayesian optimization of the fourth aspect may also include a transceiver. The transceiver may be a transceiver circuit or an interface circuit. The transceiver may be used for the integrating sphere diffuse reflection laser cooling optimization device based on Bayesian optimization of the fourth aspect to communicate with other devices.

[0022] In the fifth aspect, an integrating sphere diffuse reflection laser cooling optimization device based on Bayesian optimization is provided, comprising: a processor and a memory; the memory is used to store instructions, and when the processor executes the instructions, the integrating sphere diffuse reflection laser cooling optimization device based on Bayesian optimization executes the method of the first aspect.

[0023] In a possible design scheme, the integrating sphere diffuse reflection laser cooling optimization device based on Bayesian optimization in the fifth aspect may also include a transceiver. The transceiver may be a transceiver circuit or an interface circuit. The transceiver may be used for the integrating sphere diffuse reflection laser cooling optimization device based on Bayesian optimization in the fifth aspect to communicate with other devices.

[0024] In a sixth aspect, a computer-readable storage medium is provided, which includes a computer program or instruction stored therein. When the computer program or instruction is executed, the integrating sphere diffuse reflection laser cooling optimization method based on Bayesian optimization of the first aspect is executed.

[0025] In the embodiment of the present application, according to the method of combining the machine learning algorithm of Bayesian optimization with physical experiments, a cost function is designed to form a multi-parameter autonomous optimization system, and then the optimal parameter combination of integrating sphere diffuse reflection laser cooling is obtained. This method can not only ensure the reliability of the optimization parameter set including the frequency and power of cooling light, re-pumping light, and detection light in integrating sphere diffuse reflection laser cooling, but also can efficiently find the optimal parameter combination of integrating sphere diffuse reflection laser cooling optimization within a small number of iterations, which greatly improves the optimization efficiency compared with the traditional method of combining machine learning with physical experiments.

[0026] Other features and advantages of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0028] Figure 1 A schematic diagram of the process of the integrating sphere diffuse reflection laser cooling optimization method based on Bayesian optimization provided in an embodiment of the present application;

[0029] Figure 2 Schematic diagram of the structure of the integrating sphere diffuse reflection laser cooling optimization device based on Bayesian optimization provided in the embodiment of the present application Figure 1 ;

[0030] Figure 3 Schematic diagram of the structure of the integrating sphere diffuse reflection laser cooling optimization device based on Bayesian optimization provided in the embodiment of the present application Figure 2 . DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present application. At the same time, in the description of the embodiments of the present application, the terms "first", "second", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more features. In the description of the embodiments of the present application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0032] Figure 1 A schematic diagram of the process of integrating sphere diffuse reflection laser cooling optimization based on Bayesian optimization provided in an embodiment of the present application.

[0033] The process of integrating sphere diffuse reflection laser cooling optimization based on Bayesian optimization is as follows:

[0034] Step S101, determining the optimized parameter ranges of the frequency and power of the cooling light, the repumping light, and the detection light.

[0035] That is to say, in order to ensure the high efficiency of integrating sphere diffuse reflection laser cooling optimization based on Bayesian optimization, before selecting the optimization parameters, it is necessary to determine the range of the optimization parameters that can be selected to ensure the effectiveness of Bayesian optimization sampling. Therefore, the range of cooling light frequency is 115MHz-125MHz, the power range is 5-85mw, the range of pumping light frequency is 120MHz-130MHz, the power range is 3-20mw, the range of detection light frequency is 110MHz-120MHz, the power range is 0-10uw, where MHz represents megahertz and mw represents milliwatts.

[0036] Step S102, within the optimization parameter range, select at least one set of initial parameters of the frequency and power of the cooling light, the re-pumping light, and the detection light to experiment in an integrating sphere diffuse reflection laser cooling system, and obtain the cost function value corresponding to each set of initial parameters. Each set of initial parameters and the cost function value corresponding to each set of initial parameters constitute an initial data set, wherein the cost function value corresponding to each set of initial parameters is the intensity value of the laser cooling absorption signal in the integrating sphere obtained from the experiment for each set of initial parameters.

[0037] It can be understood that within the above optimization parameter range, at least one set of initial parameters of the frequency and power of the cooling light, the re-pumping light, and the detection light is selected to conduct experiments in the integrating sphere diffuse reflection laser cooling system to obtain the cost function value corresponding to each set of initial parameters. n (n=1,2,3,4,5) as an example, 5 sets of initial parameters x n (n=1,2,3,4,5) respectively carried out physical experiments to measure the intensity y of the laser cooling absorption signal in the integrating sphere n (n=1,2,3,4,5), where y n is the cost function value corresponding to the initial parameters. 5 sets of initial parameters x n (n=1,2,3,4,5) and the corresponding y n (n=1, 2, 3, 4, 5) constitute the initial data set.

[0038] Step S103, based on the initial data set, a cost function is fitted using a Bayesian optimization algorithm, and optimal parameters are predicted.

[0039] It can be understood as using the initial data set to build a proxy model to approximate the objective function, where the objective function is the final fitted cost function; based on the acquisition function, at least one set of parameters is selected, the cost function value corresponding to at least one set of parameters is calculated, the proxy model is optimized, and the objective function is obtained; based on the objective function, the optimal parameters are predicted.

[0040] Step S104, experimenting with the optimal parameters in an integrating sphere diffuse reflection laser cooling system to obtain cost function values ​​corresponding to the optimal parameters.

[0041] Step S105 , comparing the cost function value corresponding to the optimal parameter with the cost function value in the initial data set to determine whether the cost function value corresponding to the optimal parameter is a maximum value.

[0042] For example, the cost function values ​​in the initial data set are Y1, Y2, Y3, Y4, and Y5, and the cost function value corresponding to the optimal parameter is Y6. Determine whether Y6 is greater than Y1, Y2, Y3, Y4, and Y5.

[0043] Step S106, if yes, record the optimal parameters, and further determine whether the preset exit conditions are met. If the preset exit conditions are met, output the optimal parameters. If the preset exit conditions are not met, add the optimal parameters and the cost function values ​​corresponding to the optimal parameters to the initial data set, and return to execute S103 until the preset exit conditions are met.

[0044] Corresponding to the above example, if Y6 is greater than Y1, Y2, Y3, Y4, and Y5, then the optimal parameters corresponding to Y6 are recorded, that is, the frequency and power values ​​of the cooling light, the re-pumping light, and the detection light.

[0045] Among them, the exit conditions include: reaching a predetermined iteration number threshold, or the cost function values ​​corresponding to the optimal parameters predicted for N consecutive times do not exceed the previous maximum value, and N is a positive integer greater than or equal to zero.

[0046] It can be understood that the predetermined threshold of the number of iterations is 80 times, and the maximum value obtained this time is obtained at the 60th iteration loop, then the loop continues, the optimal parameters and the cost function values ​​corresponding to the optimal parameters are added to the initial data set, and return to execute S103 until the preset exit condition is met. If the maximum value obtained this time is obtained at the 80th iteration loop, the preset exit condition is met and the optimal parameters are output. If the cost function values ​​corresponding to the optimal parameters predicted for N consecutive times do not exceed the previous maximum value, you can also refer to it for understanding. For example, the cost function values ​​corresponding to the optimal parameters predicted for 20 consecutive times do not exceed the previous maximum value, such as the optimal parameter Yl predicted for the first time, and the subsequent predictions are all less than Yl of that time, then the exit condition is met.

[0047] Step S107: if not, then the optimal parameters and the cost function values ​​corresponding to the optimal parameters are added to the initial data set, and the process returns to execute S103 until a preset exit condition is met.

[0048] In summary, according to the method of combining Bayesian optimization machine learning algorithm with physical experiments, the cost function is designed to form a multi-parameter autonomous optimization system, and then the optimal parameter combination of integrating sphere diffuse reflection laser cooling is obtained. This method can not only ensure the reliability of the optimization parameter set including the frequency and power of cooling light, re-pumping light, and detection light in integrating sphere diffuse reflection laser cooling, but also efficiently find the optimal parameter combination of integrating sphere diffuse reflection laser cooling optimization within a small number of iterations. Compared with the traditional method of combining machine learning with physical experiments, the optimization efficiency is greatly improved.

[0049] Combination of the above Figure 1 The integrating sphere diffuse reflection laser cooling optimization method based on Bayesian optimization provided in the embodiment of the present application is described in detail. The integrating sphere diffuse reflection laser cooling optimization system based on Bayesian optimization provided in the embodiment of the present application is described in detail below.

[0050] The system specifically includes: a determination module, a determination module and a judgment module, as shown below.

[0051] A determination module, used to determine the optimized parameter range of the frequency and power of the cooling light, the re-pumping light, and the detection light;

[0052] A determination module is used to select at least one set of initial parameters of the frequency and power of cooling light, re-pumping light, and detection light within the optimization parameter range, and to experiment in an integrating sphere diffuse reflection laser cooling system to obtain a cost function value corresponding to each set of initial parameters. Each set of initial parameters and the cost function value corresponding to each set of initial parameters constitute an initial data set, wherein the cost function value corresponding to each set of initial parameters is an intensity value of the laser cooling absorption signal in the integrating sphere obtained from the experiment of each set of initial parameters; and to fit the cost function based on the initial data set using a Bayesian optimization algorithm and predict the optimal parameters; and to experiment the optimal parameters in an integrating sphere diffuse reflection laser cooling system to obtain the cost function value corresponding to the optimal parameters;

[0053] A judgment module is used to compare the cost function value corresponding to the optimal parameter with the cost function value in the initial data set to determine whether the cost function value corresponding to the optimal parameter is the maximum value; if so, the optimal parameter is recorded, and further judgment is made as to whether the preset exit condition is met. If the preset exit condition is met, the optimal parameter is output; if the preset exit condition is not met, the optimal parameter and the cost function value corresponding to the optimal parameter are added to the initial data set, and the process returns to execute S3 until the preset exit condition is met; if not, the optimal parameter and the cost function value corresponding to the optimal parameter are added to the initial data set, and the process returns to execute S3 until the preset exit condition is met.

[0054] In addition, for the above-mentioned specific implementation of the system, since it is basically similar to the method implementation, the description is relatively simple, and the relevant parts can be referred to the partial description of the method implementation. Moreover, it should be noted that in each module of the system of the present application, the components therein are logically divided according to the functions to be implemented, but the present application is not limited thereto, and the components can be re-divided or combined as needed.

[0055] The above describes the integrating sphere diffuse reflection laser cooling optimization method and system based on Bayesian optimization provided by the embodiments of the present application. Figure 2-Figure 3 A detailed description is given of an integrating sphere diffuse reflection laser cooling optimization device based on Bayesian optimization for executing the embodiments of the present application.

[0056] Figure 2 The structure of the integrating sphere diffuse reflection laser cooling optimization device based on Bayesian optimization provided in the embodiment of the present application is shown in FIG. Figure 1 For example, Figure 2 As shown, the integrating sphere diffuse reflection laser cooling optimization device 200 based on Bayesian optimization includes: a transceiver module 201 and a processing module 202. For ease of description, Figure 2 Only the main components of the integrating sphere diffuse reflection laser cooling optimization device based on Bayesian optimization are shown.

[0057] Among them, the transceiver module 201 is used to perform the transceiver function of the above-mentioned integrating sphere diffuse reflection laser cooling optimization method based on Bayesian optimization, and the processing module 202 is used to perform other functions of the above-mentioned integrating sphere diffuse reflection laser cooling optimization method based on Bayesian optimization except the transceiver function.

[0058] Optionally, the transceiver module 201 may include a sending module ( Figure 2 ) and a receiving module ( Figure 2 (not shown in the figure). The sending module is used to realize the sending function of the integrating sphere diffuse reflection laser cooling optimization device 200 based on Bayesian optimization, and the receiving module is used to realize the receiving function of the integrating sphere diffuse reflection laser cooling optimization device 200 based on Bayesian optimization.

[0059] Optionally, the integrating sphere diffuse reflection laser cooling optimization device 200 based on Bayesian optimization may further include a storage module ( Figure 2 ), the storage module stores a program or instruction. When the processing module 202 executes the program or instruction, the integrating sphere diffuse reflection laser cooling optimization device 200 based on Bayesian optimization can execute the integrating sphere diffuse reflection laser cooling optimization method based on Bayesian optimization in the embodiment of the present application.

[0060] Combine the following Figure 3 Each component of the integrating sphere diffuse reflection laser cooling optimization device 300 based on Bayesian optimization is specifically introduced:

[0061] The processor 301 is the control center of the integrating sphere diffuse reflection laser cooling optimization device 300 based on Bayesian optimization, and can be a processor or a general term for multiple processing elements. For example, the processor 301 is one or more central processing units (CPUs), or can be an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application, such as one or more microprocessors (digital signal processors, DSPs), or one or more field programmable gate arrays (field programmable gate arrays, FPGAs).

[0062] Optionally, the processor 301 can perform various functions of the integrating sphere diffuse reflection laser cooling optimization device 300 based on Bayesian optimization by running or executing a software program stored in the memory 302, and calling data stored in the memory 302, such as executing the integrating sphere diffuse reflection laser cooling optimization method based on Bayesian optimization in the embodiment of the present application.

[0063] In a specific implementation, as an embodiment, the processor 301 may include one or more CPUs, such as Figure 3 CPU0 and CPU1 are shown in FIG.

[0064] In a specific implementation, as an embodiment, the integrating sphere diffuse reflection laser cooling optimization device 300 based on Bayesian optimization may also include multiple processors, such as Figure 3 The processor 301 and processor 304 shown in . Each of these processors can be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). The processor here can refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions). Among them, the memory 302 is used to store the software program for executing the solution of the present application, and the execution is controlled by the processor 301. The specific implementation method can refer to the above method embodiment, which will not be repeated here.

[0065] Optionally, the memory 302 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 302 may be integrated with the processor 301, or may exist independently, and may be connected to the processor 301 through the interface circuit ( Figure 3 (not shown) is coupled to the processor 301, which is not specifically limited in the embodiment of the present application.

[0066] The transceiver 303 is used for communication with other communication devices. For example, the integrating sphere diffuse reflection laser cooling optimization device 300 based on Bayesian optimization is a first device, and the transceiver 303 can be used for communication with a second device or a third device.

[0067] Optionally, the transceiver 303 may include a receiver and a transmitter ( Figure 3The receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0068] Optionally, the transceiver 303 can be integrated with the processor 301, or can exist independently and be connected to the interface circuit of the integrating sphere diffuse reflection laser cooling optimization device 300 based on Bayesian optimization ( Figure 3 (not shown) is coupled to the processor 301, which is not specifically limited in the embodiment of the present application.

[0069] Understandably, Figure 3 The structure of the integrating sphere diffuse reflection laser cooling optimization device 300 based on Bayesian optimization shown in the figure does not constitute a limitation of the integrating sphere diffuse reflection laser cooling optimization device based on Bayesian optimization. The actual integrating sphere diffuse reflection laser cooling optimization device based on Bayesian optimization may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0070] In addition, the technical effects of the integrating sphere diffuse reflection laser cooling optimization device 300 based on Bayesian optimization can refer to the technical effects of the method described in the above method embodiment, and will not be repeated here.

[0071] It should be understood that the processor in the embodiments of the present application may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0072] It should also be understood that the memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0073] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

Claims

1. An integrating sphere diffuse reflection laser cooling optimization method based on Bayesian optimization, characterized in that: The method comprises: S1. Determine the optimal parameter range of the frequency and power of the cooling light, the re-pumping light, and the detection light; S2. Within the optimization parameter range, select at least one set of initial parameters of the frequency and power of the cooling light, the re-pumping light, and the detection light to experiment in an integrating sphere diffuse reflection laser cooling system, and obtain the cost function value corresponding to each set of initial parameters. Each set of initial parameters and the cost function value corresponding to each set of initial parameters constitute an initial data set, wherein the cost function value corresponding to each set of initial parameters is the intensity value of the laser cooling absorption signal in the integrating sphere obtained from the experiment of each set of initial parameters; S3. Based on the initial data set, a cost function is fitted using a Bayesian optimization algorithm, and optimal parameters are predicted; S4, experimenting the optimal parameters in the integrating sphere diffuse reflection laser cooling system to obtain cost function values ​​corresponding to the optimal parameters; S5, comparing the cost function value corresponding to the optimal parameter with the cost function value in the initial data set to determine whether the cost function value corresponding to the optimal parameter is a maximum value; S6. If yes, record the optimal parameter, and further determine whether the preset exit condition is met. If the preset exit condition is met, output the optimal parameter. If the preset exit condition is not met, add the optimal parameter and the cost function value corresponding to the optimal parameter to the initial data set, and return to execute S3 until the preset exit condition is met. S7. If not, then add the optimal parameters and the cost function values ​​corresponding to the optimal parameters to the initial data set, and return to execute S3 until the preset exit condition is met.

2. The integrating sphere diffuse reflection laser cooling optimization method based on Bayesian optimization according to claim 1, characterized in that: The optimized parameter ranges of the frequency and power of the cooling light are respectively: 115 MHz to 125 MHz, and 5 mW to 85 mW.

3. The integrating sphere diffuse reflection laser cooling optimization method based on Bayesian optimization according to claim 1, characterized in that: The optimized parameter ranges of the frequency and power of the repumping light are 120 MHz to 130 MHz and 3 mW to 20 mW respectively.

4. The integrating sphere diffuse reflection laser cooling optimization method based on Bayesian optimization according to claim 1, characterized in that: The optimized parameter ranges of the frequency and power of the detection light are respectively: 110 MHz to 120 MHz, and 0 mW to 10 mW.

5. The integrating sphere diffuse reflection laser cooling optimization method based on Bayesian optimization according to claim 1, characterized in that: Based on the initial data set, the cost function is fitted using a Bayesian optimization algorithm, and the optimal parameters are predicted, including: Using the initial data set, constructing a proxy model to approximate the objective function, wherein the objective function is the final fitted cost function; Based on the acquisition function, at least one set of parameters is selected, cost function values ​​corresponding to each of the at least one set of parameters are calculated, the proxy model is optimized, and an objective function is obtained; Based on the objective function, optimal parameters are predicted.

6. The integrating sphere diffuse reflection laser cooling optimization method based on Bayesian optimization according to claim 1, characterized in that: The exit condition includes: reaching a predetermined iteration number threshold, or the cost function values ​​corresponding to the optimal parameters predicted for N consecutive times do not exceed the previous maximum value, where N is a positive integer greater than or equal to zero.

7. An integrating sphere diffuse reflection laser cooling optimization system based on Bayesian optimization, characterized in that: The system comprises: A determination module, used to determine the optimized parameter range of the frequency and power of the cooling light, the re-pumping light, and the detection light; A processing module, used to select at least one group of initial parameters of the frequency and power of the cooling light, the re-pumping light, and the detection light within the optimization parameter range, and conduct experiments in an integrating sphere diffuse reflection laser cooling system to obtain cost function values ​​corresponding to each group of initial parameters, wherein each group of initial parameters and the cost function values ​​corresponding to each group of initial parameters constitute an initial data set, wherein the cost function value corresponding to each group of initial parameters is an intensity value of the laser cooling absorption signal in the integrating sphere obtained by the experiment of each group of initial parameters; and to fit a cost function based on the initial data set using a Bayesian optimization algorithm and predict optimal parameters; and also to conduct experiments on the optimal parameters in the integrating sphere diffuse reflection laser cooling system to obtain cost function values ​​corresponding to the optimal parameters; A judgment module is used to compare the cost function value corresponding to the optimal parameter with the cost function value in the initial data set to determine whether the cost function value corresponding to the optimal parameter is the maximum value; if so, record the optimal parameter, and further determine whether the preset exit condition is met. If the preset exit condition is met, output the optimal parameter; if the preset exit condition is not met, add the optimal parameter and the cost function value corresponding to the optimal parameter to the initial data set, return to execute S3, and continue until the preset exit condition is met; if not, add the optimal parameter and the cost function value corresponding to the optimal parameter to the initial data set, return to execute S3, and continue until the preset exit condition is met.

8. An integrating sphere diffuse reflection laser cooling optimization device based on Bayesian optimization, characterized in that: The apparatus comprises: a module for executing the method according to any one of claims 1-6.

9. An integrating sphere diffuse reflection laser cooling optimization device based on Bayesian optimization, characterized in that: The device comprises: a processor and a memory; the memory is used to store computer instructions, and when the processor executes the instructions, the integrating sphere diffuse reflection laser cooling optimization device based on Bayesian optimization executes the method as described in any one of claims 1-6.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a computer program or instruction stored therein, and when the computer program or instruction is executed, the method according to any one of claims 1 to 6 is performed.

Images