Multi-level multi-parameter coupling control method, device, electronic device and storage medium

Abstract

The present invention relates to the field of measurement and analysis methods, and in particular to a multi-level multi-parameter coupling control method, device, electronic device and storage medium, wherein the method comprises the following steps: acquiring multi-source scene data, analyzing the multi-source scene data, and generating scene analysis information; calculating the adjustment weight of the preset adjustable parameter according to the multi-source scene data; calculating the adjustment value of the adjustable parameter by a swarm intelligence optimization algorithm according to the scene analysis information and the adjustment weight; and adjusting the adjustable parameter according to the adjustment value. The present invention has the effect of improving the autonomous adjustment level and detection capability of a deep space in-situ spectrometer.

Description

Technical Field

[0001] The present invention relates to the field of measurement and analysis methods, and in particular to a multi-level multi-parameter coupling control method, device, electronic equipment and storage medium. Background Art

[0002] In-situ spectral detection technology is an effective detection method currently used in lunar and deep space surface exploration missions. It can achieve close-range detection on the surface of extraterrestrial bodies to obtain the target's reflection and emission spectral information, and to gain a detailed understanding of the target's material composition and physical property parameters.

[0003] Different from the spectral analysis and remote sensing detection scenes in the laboratory, the deep space in-situ spectral detection is particularly affected by the scene characteristics. The scene elements such as target characteristics, illumination angle, thermal radiation level, instrument temperature and observation angle are coupled with each other and are complex and changeable. In the same detection scene, strong and weak nonlinear large dynamic signals often coexist, and complex time-varying backgrounds are coupled with the target intrinsic signals. This poses a great challenge to the detection sensitivity, dynamic range and other detection capabilities of the in-situ spectral deep space in-situ spectrometer and the consistency level. According to different detection scenarios, flexible adjustment of detection parameters (integration time, gain, modulation frequency, etc.) is one of the effective means to improve the detection capability of the deep space in-situ spectrometer. However, limited by the current level of understanding of the interaction mechanism between deep space scene elements and spectral detection links, as well as the constraints of resources such as weight, power consumption, computing power, and communication capabilities of deep space in-situ spectrometers, most parameters are fixed or rely on the engineering experience of R&D personnel for evaluation and adjustment, which makes it difficult to take into account both detection sensitivity and dynamic range in different scenarios, and it is difficult to further improve the spectral detection capability.

[0004] At present, some studies have focused on the impact of scene elements on the spectral detection link and carried out research on related automatic parameter control methods. For example, an infrared imaging spectrometer based on Fourier spectroscopy realizes the circumference remote sensing detection of the 2-15μm spectrum band. The device has developed an embedded adaptive control system that can automatically perform resampling, fast Fourier transform (FFT), averaging and dispersion correction according to the data obtained on orbit. The fiber optic spectroscopy system used in the polar sea ice environment will be affected by the dual effects of extremely low temperature (-40℃) and light intensity transmission attenuation between sea ice depths, which affects the signal-to-noise ratio of the spectral data. Through simulation experiments, the signal output of the spectral system under different integration times, temperatures and incident light intensities, as well as the related noise characteristics and the signal-to-noise ratio of the data are studied. A measurement method for automatically setting the integration time for any temperature and incident light is proposed, so that the signals of all wavelengths output by the spectrometer are within the linear working range of the instrument, ensuring that the signals at most wavelengths have a high signal-to-noise ratio. In order to solve the problem that the integration time of Raman spectrometer is difficult to control quickly and affects the signal capture efficiency due to the coupling of linear and nonlinear factors such as Raman scattering effect, capture noise, fluorescence effect and spectrometer optical path, a self-correcting fuzzy PID adaptive control method based on model parameters is proposed. By constructing an initial parameter prediction model and combining it with a fuzzy PID controller, the automatic calculation and optimal control of the integration time of the Raman spectrometer are realized. Experimental results show that this method can effectively suppress the coupling influence of linear and nonlinear factors and improve the signal capture efficiency.

[0005] However, the above-mentioned technical solutions are mostly aimed at regulating a single parameter, and there is little research on multi-parameter coupling regulation. With the continuous deepening of deep space exploration, more and more deep space in-situ spectrometers are used in the exploration of the surface of extraterrestrial bodies. The environment is also more complex and harsh. The computational difficulty and complexity of multi-parameter coupling regulation have been significantly improved. The traditional parameter control mode can no longer fully meet the future deep space exploration and planetary science research for spectral detection capabilities and high-quality spectral detection data requirements. Summary of the invention

[0006] In order to improve the autonomous adjustment level and detection capability of a deep space in-situ spectrometer, the present invention provides a multi-level multi-parameter coupling control method, device, electronic equipment and storage medium.

[0007] The present invention provides a multi-level multi-parameter coupling control method, which adopts the following technical solution:

[0008] A multi-level multi-parameter coupling control method comprises the following steps:

[0009] Acquire multi-source scene data, analyze the multi-source scene data, and generate scene analysis information;

[0010] Calculate the adjustment weight of the preset adjustable parameter according to the multi-source scene data;

[0011] According to the scenario analysis information and adjustment weights, the adjustment values ​​of the adjustable parameters are calculated through the swarm intelligence optimization algorithm;

[0012] Adjust the adjustable parameters according to the adjustment value.

[0013] In a specific implementation scheme, the multi-source scene data includes telemetry data of a deep space in-situ spectrometer, current values ​​of adjustable parameters, and pre-collected spectral data of the adjustable parameters using the current values.

[0014] In a specific implementation scheme, when analyzing multi-source scene data, the highest value DN in the pre-collected spectral data is extracted. max , minimum value DN min With the average DN mean , and calculate the signal-to-noise ratio (SNR) of the data y .

[0015] In a specific embodiment, the signal-to-noise ratio (SNR) of the data is y Optimization is used as the objective function of the swarm intelligence optimization algorithm.

[0016] In a specific feasible implementation scheme, in the swarm intelligence optimization algorithm, an adjustable parameter function is constructed according to the adjustable range of the adjustable parameter;

[0017] Construct scene characteristic functions based on scene analysis information;

[0018] Based on the adjustable parameter function and the scene characteristic function, a mathematical model between the signal-to-noise ratio of the data and the adjustable parameter function and the scene characteristic function is constructed.

[0019] In a specific implementation scheme, the adjustable parameters include the spectral detection observation angle, the field of view aperture specifications of the deep space in-situ spectrometer, the input RF power of the in-situ spectral spectrometer and the modulation frequency of the RF power amplifier, as well as the gain of the electronics and the integration time of the detector.

[0020] In a specific implementation scheme, the method for calculating the adjustment weight includes the following steps:

[0021] Construct an adjustable parameter correlation analysis database to record the changes of other adjustable parameters when a certain adjustable parameter is fixed;

[0022] Based on the fuzzy logic algorithm, multi-source scene data is used as input variables to calculate the adjustment weights of each adjustable parameter and output them.

[0023] The present invention provides a multi-level multi-parameter coupling control device, which adopts the following technical solution:

[0024] A multi-level multi-parameter coupling control device, comprising

[0025] one or more processors; memory;

[0026] and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions, which, when executed by the processor, enable the multi-level multi-parameter coupling control device to perform the above-mentioned multi-level multi-parameter coupling control method.

[0027] The present invention provides an electronic device, which adopts the following technical solution:

[0028] An electronic device comprises: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned multi-level multi-parameter coupling control method.

[0029] The present invention provides a non-transitory computer-readable storage medium storing computer instructions, which adopts the following technical solution:

[0030] A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute the above-mentioned multi-level multi-parameter coupling control method.

[0031] In summary, the present invention includes at least one of the following beneficial technical effects:

[0032] 1. According to the different environments, it can automatically analyze the surrounding environment, autonomously adjust the detection parameters, and simultaneously improve the sensitivity and dynamic range of detection, thereby improving the autonomous adjustment level and detection capability of the deep space in-situ spectrometer.

[0033] 2. By calculating the adjustment weights, the complexity of coordinated control of multiple adjustable parameters is reduced, and efficient and optimal coordinated control of multiple adjustable parameters is achieved while ensuring the reduction of computing resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 This is the overall flow chart of Example 1.

[0035] Figure 2 This is a flowchart of step S200.

[0036] Figure 3 It is a flowchart of steps A210-A220.

[0037] Figure 4 This is the overall flow chart of Example 2. DETAILED DESCRIPTION

[0038] The following is combined with Figure 1-4 The present invention is described in further detail.

[0039] Embodiment 1:

[0040] The multi-level multi-parameter coupling control method provided in the embodiment of the present invention can be applied to a server or a terminal. The server can be a physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms. The terminal can be a user equipment (User Equipment, UE) such as a mobile phone, smart phone, laptop, digital broadcast receiver, personal digital assistant (PDA), tablet computer (PAD) with strong computing power, handheld device, vehicle-mounted device, wearable device, computing device or other processing device connected to a wireless modem, mobile station (Mobile Station, MS), mobile terminal (Mobile Terminal), etc., and the present invention is not limited here.

[0041] Reference Figure 1 , the multi-level multi-parameter coupling control method includes the following steps:

[0042] S100, the scene perception and evaluation module collects real-time multi-source scene data, analyzes the multi-source scene data, and generates scene analysis information.

[0043] The multi-source scene data acquired by the scene perception and evaluation module include the telemetry data of the deep space in-situ spectrometer, the current values ​​of preset adjustable parameters, and the spectral data pre-collected using the current values ​​of the adjustable parameters. Among them, the telemetry data include the temperature of each part of the in-situ spectrometer measured by thermistors, the primary power supply voltage V1 of the deep space in-situ spectrometer, the secondary power supply voltage V2 of the deep space in-situ spectrometer, and the current solar altitude angle θ; the temperature of each part of the in-situ spectrometer can be specifically the optical base plate temperature T1, the slit temperature T2, the spectrometer temperature T3, the detector temperature T4, and the electronics temperature T5.

[0044] The adjustable parameters include the spectrum detection observation angle α, the field aperture specification φ of the deep space in-situ spectrometer, the input RF power Gs of the in-situ spectrum splitter and the modulation frequency ft of the RF power amplifier, as well as the gain n of the electronics and the integration time t of the detector. The in-situ spectrum splitter used in this embodiment is an acousto-optic tunable filter, which can adjust the output diffracted light wavelength by changing the RF frequency of the input device, and the change of RF power can adjust the diffraction efficiency.

[0045] The pre-collected spectral data is the digital value of the spectral data of each band obtained by using preset adjustable parameters, that is, the DN value.

[0046] The telemetry data is compared with the preset error range. If there is data in the telemetry data that exceeds the error range, it indicates that the data is noise or abnormal, and then the data is removed, thereby removing the noise and abnormal values ​​in the telemetry data. The actual value of the adjustable parameter is compared with the preset value of the preset adjustable parameter. If the actual value is different from the preset value, it indicates that the adjustable parameter is noise or abnormal.

[0047] Extract the highest DN value from the pre-collected spectral data max , minimum value DN min With the average DN mean The signal-to-noise ratio (SNR) of the data is calculated using the pre-collected spectral data. y .

[0048] The scene perception and evaluation module analyzes the temperature of each part of the in-situ spectrometer in the telemetry data to obtain temperature information; analyzes the spectrum detection observation angle α, the current solar altitude angle θ and the pre-collected spectrum data to obtain the illumination angle and intensity information. The scene perception and evaluation module extracts different data from multi-source scene data, analyzes and obtains various scene analysis information, and provides important input conditions for the subsequent adjustment of adjustable parameters.

[0049] Reference Figure 2 and Figure 3 , S200, the parameter weight calculation module calculates the adjustment weight of the adjustable parameter according to the multi-source scene data.

[0050] A210, build an adjustable parameter correlation analysis database, and use the adjustable parameter correlation analysis database to record the changes in telemetry data and adjustable parameters when a certain adjustable parameter is fixed and other adjustable parameters are changed one by one with the minimum step size. This makes it easier to analyze the impact of a certain adjustable parameter change on other adjustable parameters and telemetry data, and to analyze the correlation between multi-source scene data.

[0051] A220 uses the multi-source scene data as input variables and the calculated adjustment weights of each adjustable parameter as output variables. The fuzzy logic algorithm is used to call the data in the adjustable parameter correlation analysis database to calculate the spectral detection observation angle adjustment weight W α , Field stop specification adjustment weight W φ , the input RF power adjustment weight W of the in-situ spectrum splitter Gs The adjustment weight W of the modulation frequency of the RF power amplifier ft , the adjustment weight W of the detector integration time t and the electronics gain adjustment weight W n .

[0052] S300, the multi-parameter collaborative adaptive control module obtains the scene analysis information output by the scene perception and evaluation module, and the adjustment weights of the adjustable parameters output by the parameter weight calculation module, and automatically adjusts the adjustable parameters through the swarm intelligent optimization algorithm.

[0053] The swarm intelligence optimization algorithm takes the optimization of the signal-to-noise ratio of the data as the objective function. The optimization of the signal-to-noise ratio of the data means obtaining the maximum value of the signal-to-noise ratio of the data in the current scenario. The swarm intelligence optimization algorithm first initializes a group of random solutions, each of which represents a possible parameter combination. Then, through iterative calculations, each solution in the group will be updated according to its own historical optimal solution and the global optimal solution of the group, simulating the search behavior of swarm intelligence. In each iteration, the swarm intelligence optimization algorithm will evaluate the performance of the current solution, and adjust the search direction according to the evaluation results, gradually approaching the optimal solution. Through this step-by-step control method, the swarm intelligence optimization algorithm can quickly find the optimal parameter combination that meets the constraints and achieve optimal control of the overall performance.

[0054] To facilitate understanding, an example is given below.

[0055] According to the scene analysis information in step S100, the following scene characteristic function is constructed:

[0056] f characteristic =Q(T1, T2, T3, T4, T5, V1, V2, θ, SNR y , D.N. max , D.N. min , D Nmean )

[0057] According to the adjustable range of the adjustable parameters, the following adjustable parameter function is further constructed:

[0058] f ad_parameter =P(α,φ,Gs,ft,t,n)

[0059] Establish a mathematical model between the signal-to-noise ratio of the data, scene characteristics and adjustable parameters, take the signal-to-noise ratio of the data as the optimization objective function, and construct the function: f SNR (f characteristic , f ad_parameter ), reflecting the signal-to-noise ratio of the data and the scene characteristic function f characteristic and the adjustable parameter function f ad_parameter The relationship between the two makes it easier to analyze the changes in the signal-to-noise ratio of the data after the adjustable parameters change.

[0060] The swarm intelligence optimization algorithm uses the particle swarm optimization algorithm, with the preset swarm size as N, the number of iterations as T, and the adjustment value of the adjustable parameter as the particle. The adjustment value is the minimum step size of the adjustable parameter, through the formula:

[0061] v i (k+1)=ωv i (k)+c1r1(p i (k)-x i (k))+c2r2(P global (k))-x i (k)

[0062] x i (k+1)=x i (k)+v i (k+1)

[0063] Find the optimal parameter combination. i (k) represents the position of the i-th particle in the k-th iteration; v i (k) represents the velocity of the particle; p i (k) represents the optimal position of the particle; P glonal (k) represents the optimal position of the particle in the world; ω is the weight of the adjustable parameter; c1 represents the preset individual learning factor; c2 is the preset group learning factor; r1 and r2 are random numbers with a value range of (0, 1], which are used to increase the randomness of the search. After multiple iterations, when the objective function reaches the global optimum, the iteration is stopped and the adjustment value of the adjustable parameter is output. The adjustment value can be the difference between the optimal parameter combination and the current adjustable parameter, or it can be the value of each adjustable parameter in the optimal parameter combination. The deep space in-situ spectrometer automatically adjusts the adjustable parameters according to the adjustment value and performs detection. It can be understood that in addition to the above-mentioned particle swarm optimization algorithm, a group intelligence optimization algorithm such as a differential evolution algorithm can also be used to calculate the adjustment value.

[0064] In order to further improve the efficiency and accuracy of the swarm intelligence optimization algorithm, the model can also be trained using the actual on-orbit historical control parameter data of the deep space in-situ spectrometer and the control parameter data in the simulation environment. Through training, the swarm intelligence optimization algorithm can better understand and adapt to the control needs in different scenarios. While ensuring the quantitative level, it can continuously optimize its own parameters and structure to improve scene adaptability and control accuracy.

[0065] The specific implementation of the present invention also discloses a multi-level multi-parameter coupling control device, including one or more processors; a memory;

[0066] And one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions, which, when executed by the processor, enable the multi-level multi-parameter coupling control device to perform the above-mentioned multi-level multi-parameter coupling control method.

[0067] A specific embodiment of the present invention also discloses an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned multi-level multi-parameter coupling control method.

[0068] The specific implementation of the present invention also discloses a non-transitory computer-readable storage medium storing computer instructions, where the computer instructions are used to enable a computer to execute the above-mentioned multi-level multi-parameter coupling control method.

[0069] Embodiment 2:

[0070] Embodiment 2 of the present invention further provides a multi-parameter control method, comprising the following steps:

[0071] Obtain scene analysis information and build scene feature functions.

[0072] Get the preset adjustable parameters and the adjustment weights of the adjustable parameters, and construct the adjustable parameter function according to the adjustable range of the adjustable parameters.

[0073] The pre-collected spectral data and the signal-to-noise ratio of the data are obtained, the signal-to-noise ratio of the data is used as the optimization objective function, and a mathematical model that can reflect the relationship between the signal-to-noise ratio of the data and the scene characteristic function and the adjustable parameter function is constructed.

[0074] Select a suitable swarm intelligence optimization algorithm, iteratively solve the optimal parameter combination, calculate the difference between the optimal parameter combination and the actual adjustable parameters, that is, the adjustment value, output the adjustment value, and adjust the adjustable parameters according to the adjustment value.

[0075] The swarm intelligence optimization algorithm still uses the particle swarm optimization algorithm as an example: the preset swarm size is N, the number of iterations is T, the adjustment value of the adjustable parameter is used as the particle, and the adjustment value is the minimum step size of the adjustable parameter. Through the formula:

[0076] v i (k+1)=ωv i (k)+c1r1(p i (k)-x i (k))+c2r2(P global (k))-x i (k)

[0077] x i (k+1)=x i (k)+v i (k+1)

[0078] Find the optimal parameter combination. i (k) represents the position of the i-th particle in the k-th iteration; v i (k) represents the velocity of the particle; p i (k) represents the optimal position of the particle; P global (k) represents the optimal position of the particle in the world; ω is the weight of the adjustable parameter; c1 represents the preset individual learning factor; c2 is the preset group learning factor; r1 and r2 are random numbers used to increase the randomness of the search. After multiple iterations, when the objective function reaches the global optimum, the iteration is stopped and the adjusted value of the adjustable parameter is output. The deep space in-situ spectrometer automatically adjusts the adjustable parameter according to the adjusted value and performs detection.

[0079] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made according to the structure, shape, and principle of the present invention specification should be included in the protection scope of the present invention.

Claims

1. A multi-level multi-parameter coupling control method, characterized in that: The steps include: Acquire multi-source scene data, analyze the multi-source scene data, and generate scene analysis information; Calculate the adjustment weight of the preset adjustable parameter according to the multi-source scene data; According to the scenario analysis information and adjustment weights, the adjustment values ​​of the adjustable parameters are calculated through the swarm intelligence optimization algorithm; Adjust the adjustable parameters according to the adjustment value; The multi-source scene data includes telemetry data of a deep space in-situ spectrometer, current values ​​of adjustable parameters, and spectral data pre-collected using the current values ​​of the adjustable parameters; When analyzing multi-source scene data, extract the highest value from the pre-collected spectral data , minimum value With the average , and calculate the signal-to-noise ratio of the data ; The signal-to-noise ratio of the data Optimization as the objective function of the swarm intelligence optimization algorithm; In the swarm intelligence optimization algorithm, an adjustable parameter function is constructed according to the adjustable range of the adjustable parameter; Construct scene characteristic functions based on scene analysis information; Based on the adjustable parameter function and the scene characteristic function, a mathematical model between the signal-to-noise ratio of the data and the adjustable parameter function and the scene characteristic function is constructed; The adjustable parameters include the spectral detection observation angle, the field aperture specifications of the deep space in-situ spectrometer, the input RF power of the in-situ spectral spectrometer and the modulation frequency of the RF power amplifier, as well as the gain of the electronics and the integration time of the detector.

2. The multi-level multi-parameter coupling control method according to claim 1, characterized in that: The method for calculating the adjustment weight includes the following steps: Construct an adjustable parameter correlation analysis database to record the changes of other adjustable parameters when a certain adjustable parameter is fixed; Based on the fuzzy logic algorithm, multi-source scene data is used as input variables to calculate the adjustment weights of each adjustable parameter and output them.

3. A multi-level multi-parameter coupling control device, characterized in that: include one or more processors; Memory; And one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions, which, when executed by the processor, enable the multi-level multi-parameter coupling control device to perform the multi-level multi-parameter coupling control method as described in any one of claims 1-2.

4. An electronic device, characterized in that: include: at least one processor; And a memory communicatively connected to at least one processor; wherein the memory stores instructions executable by at least one processor, and the instructions are executed by at least one processor so that at least one processor can execute the multi-level multi-parameter coupling control method described in any one of claims 1-2.

5. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to enable a computer to execute the multi-level multi-parameter coupling control method described in any one of claims 1-2.

Images