Bionic vision optimization method adaptive to GIS internal signal intensity and imaging device

Abstract

The invention discloses a bionic visual optimization method and an imaging device adaptive to GIS internal signal intensity, and the method comprises the steps: constructing an event pulse flow collection model based on bionic visual perception, and collecting event pulse flow signals caused by different discharge phenomena in a GIS; the event pulse stream signal is preprocessed, and the imaging accuracy of the bionic vision sensor is calculated; off-line learning is carried out, optimization of bionic vision light intensity change threshold values is realized, and the optimal light intensity change threshold values of all to-be-learned discharge phenomena are output; the light intensity change in the GIS is detected in real time by using the event pulse flow acquisition model, and different discharge phenomena in the GIS are sensed. The invention designs a bionic visual optimization method which can realize closed-loop feedback optimization between off-line learning and on-line application, is high in imaging accuracy and accords with the actual situation, can accurately detect different discharge phenomena of the GIS, and improves the bionic imaging efficiency of the GIS equipment and the imaging recognition accuracy of the discharge phenomenon of the GIS.

Description

Technical Field

[0001] The present invention belongs to the field of discharge detection, and more specifically, relates to a bionic vision optimization method and an imaging device adapted to the internal signal strength of a GIS. Background Art

[0002] As the new power system continues to develop in the direction of digitalization and scale, more and more stringent requirements are put forward for the reliability of power equipment, especially high-voltage switchgear. Gas Insulated Metal Enclosed Switchgear (GIS), as the core component of the power grid, has been widely used in the control and protection of high-voltage switchgear in the power system due to its advantages such as small footprint and high reliability. However, due to problems such as aging of insulation materials, overload of power systems and insulation defects of equipment, various internal discharge phenomena including partial discharge, corona discharge, surface discharge and breakdown discharge will occur inside GIS, which can easily cause insulation breakdown, equipment failure and fire, and electromagnetic interference, seriously endangering the stable operation of the power system. At the same time, different types of discharge phenomena will generate signals of different intensities. For example, partial discharge usually generates low-intensity signals, while breakdown discharge generates high-intensity signals. Therefore, in order to ensure the reliable and safe operation of GIS equipment, it is urgent to study high-precision discharge detection methods for discharge phenomena with different signal intensities.

[0003] Bionic visual perception technology can capture the optical signals radiated outward from GIS local discharge by imitating the functions and principles of biological visual systems, and use image processing and pattern recognition algorithms to analyze their characteristics and states, thereby realizing real-time detection and identification of local discharge phenomena inside GIS. It has the characteristics of strong anti-interference, high detection sensitivity and accuracy.

[0004] There are some studies on the monitoring of discharge phenomena with different signal intensities inside GIS based on image sensors. The invention patent No. 202211400731.6 proposes a GIS partial discharge detection device based on ultraviolet infrared fusion imaging. Based on ultraviolet infrared fusion imaging, GIS partial discharge detection is realized to achieve high sensitivity and high reliability of partial discharge detection, visualization of discharge signals and anti-electromagnetic interference of partial discharge detection. The invention patent No. 202311509376.0 proposes a multi-signal fusion monitoring method for partial discharge faults of GIS pot-type insulators. The optical signals of GIS pot-type insulators are monitored in real time by ultraviolet imaging detectors and photomultiplier tubes. The state of GIS pot-type insulators is monitored in real time without power outages, and reliable, accurate and comprehensive monitoring data is provided for judging the working state of GIS pot-type insulators. However, the above method does not take into account the differences in the threshold of light intensity change of discharge phenomena caused by reflection, shielding and other factors inside GIS equipment under various signal intensities, and cannot dynamically adjust the threshold based on the differentiated discharge phenomena inside GIS. The imaging detection time is long and the accuracy is low. At the same time, the above methods often only rely on the results of offline training, and are difficult to respond to new discharge phenomena generated inside the GIS. They are unable to learn the optimal light intensity change threshold through new discharge phenomena collected in online applications, and thus are unable to achieve closed-loop feedback optimization between offline learning and online applications, affecting the imaging accuracy of discharge phenomena inside the GIS. Summary of the invention

[0005] In order to solve the shortcomings of the prior art that the threshold cannot be dynamically adjusted based on the differentiated discharge phenomenon inside GIS, the imaging detection time is long and the accuracy is low, the present invention provides a bionic vision optimization method and imaging device adapted to the internal signal strength of GIS.

[0006] The present invention adopts the following technical solution.

[0007] The first aspect of the present invention proposes a bionic visual optimization method for adapting the internal signal strength of GIS, comprising the following steps:

[0008] Construct an event pulse flow acquisition model based on bionic visual perception to collect event pulse flow signals caused by different discharge phenomena inside GIS, and preset the real event pulse flow according to the historical discharge phenomena;

[0009] Preprocessing the event pulse stream signal, and calculating the imaging accuracy of the bionic visual sensor, to obtain a set M of discharge phenomena to be learned;

[0010] Offline learning is performed on the set M of discharge phenomena to be learned, a reward function and a loss function are constructed, and the event pulse stream in the set M of discharge phenomena to be learned is iteratively trained to optimize the threshold of light intensity change of bionic vision, and the optimal light intensity change threshold of all discharge phenomena to be learned is output;

[0011] Based on the optimal light intensity change threshold set, the event pulse stream acquisition model is used to detect the light intensity change inside the GIS in real time and perceive different discharge phenomena inside the GIS.

[0012] Preferably, the event pulse stream acquisition model includes an event camera deployed inside the GIS and including ultraviolet, infrared and visible light visual sensors. The visual sensors respond to changes in light intensity in discharge phenomena inside the GIS in the form of asynchronous sparse events. When the light intensity of a pixel at a current moment changes by more than a threshold compared to a preset standard light intensity of the pixel, the visual sensor outputs an event pulse at the pixel. All event pulses output by each visual sensor constitute an event pulse stream under the spectrum.

[0013] Preferably, the set of different types of discharge phenomena occurring inside the GIS is defined as E = {e1, ..., e o ,…,e O},e o , is the oth discharge phenomenon, O is the total number of different types of discharge phenomena;

[0014] The discharge phenomena collected by ultraviolet vision sensors, infrared vision sensors, and visible light vision sensors o The generated event pulse stream is recorded as:

[0015]

[0016] Wherein, L = {UV, IR, VIS}, UV represents ultraviolet vision sensor, IR represents infrared vision sensor, VIS represents visible light vision sensor, is the nth event of the event pulse stream generated by the sensor represented by L, and N is the total number of event pulses generated by the sensor represented by L;

[0017] Each event pulse is characterized in the form of a quaternion:

[0018]

[0019] in, for The two-dimensional pixel position of for The trigger time; for The polarity of When , it means that the light intensity at the pixel is enhanced, and when , it means that the light intensity at the pixel is weakened.

[0020] Preferably, the preprocessing refers to slicing the event pulse stream generated by the visual sensor and the real event pulse stream at a reference frame rate f to obtain a sliced ​​image set.

[0021] Preferably, the calculation model for calculating the accuracy of bionic visual imaging specifically includes:

[0022] Calculate the mutual information of the acquired event pulse stream slice image set obtained by slicing the event pulse stream generated by the visual sensor and the real event pulse stream and the normalized corresponding images in the event pulse stream slice image set;

[0023]

[0024] Wherein, L = {UV, IR, VIS}, UV represents ultraviolet vision sensor, IR represents infrared vision sensor, and VIS represents visible light vision sensor; are respectively a collection of event pulse stream slice images obtained by the sensor corresponding to L after slicing and the lth image in the event pulse stream slice image collection; For images and images The mutual information of Respectively, images and images Entropy of

[0025] The imaging accuracy is obtained by weighted summation of the normalized mutual information of different visual sensors. Calculation formula:

[0026]

[0027] in, The total number of images in the collection of event pulse stream slice images obtained by slicing the images collected by the ultraviolet, infrared and visible light sensors, respectively, and The discharge phenomena are collected by the set ultraviolet, infrared and visible light sensors respectively. o The weight of is in the range of 0 to 1, and

[0028] Preferably, the optimization of the bionic vision light intensity change threshold is achieved by:

[0029] The optimization objective P1 formula is:

[0030]

[0031] In the formula, and are the light intensity change thresholds of the ultraviolet, infrared and visible light bionic sensors for all discharge phenomena, They are discharge phenomena e o The light intensity change threshold of the ultraviolet, infrared and visible light bionic sensors should be constrained between the minimum and maximum light intensity change thresholds;

[0032] The optimization goal of maximizing the average imaging accuracy is transformed into maximizing the imaging accuracy of each discharge phenomenon:

[0033]

[0034] Preferably, the reward function constructed is specifically the discharge phenomenon e o Imaging accuracy i is the number of iterations.

[0035] Preferably, the constructed loss function is specifically:

[0036]

[0037] In the formula,

[0038]

[0039] Where γ is the discount factor; Q(S(i),ρ(i); θ main ) is the output of the main network; Q(S(i+1),ρ(i+1);θ target ) is the output of the target network; S(i+1) and S(i) are the states when the iterations are i+1 and i respectively; ρ(i+1) and ρ(i) are the actions when the iterations are i+1 and i respectively; Γ(i) represents the experience replay pool; represents some samples randomly drawn from the experience replay pool, for The number of samples in θ main represents the main network, θ target represents the target network;

[0040] Based on this loss function, the main network is updated. Among them, μ represents the update step size.

[0041] Preferably, the obtained optimal light intensity change threshold set uses an event pulse stream acquisition model to detect the light intensity change inside the GIS in real time and sense different discharge phenomena inside the GIS as follows:

[0042] The event camera maintains a detection state, and when the detected light intensity change exceeds the minimum light intensity change threshold in the optimal light intensity change threshold set, the event pulse stream signal caused by the discharge signal is collected, and preprocessed to obtain a set of perceived pulse stream slice images;

[0043] Calculate the imaging accuracy of the perceived pulse flow slice image set and the real event pulse flow of all known discharge phenomena, and determine whether it is a known discharge phenomenon based on the imaging accuracy;

[0044] If it is a known discharge phenomenon, the discharge phenomenon that occurs is the discharge phenomenon with the highest imaging accuracy. The optimal light intensity change threshold of the discharge phenomenon that occurs is selected to collect the discharge phenomenon that occurs in the current GIS, and generate the corresponding event pulse stream. If the maximum waiting time is set, If no light intensity change exceeding the optimal light intensity change threshold for the discharge phenomenon is detected, the pulse flow sensing of this event ends;

[0045] If it is not a known discharge phenomenon, closed-loop feedback update learning is performed, and the light intensity change threshold of the phenomenon with the highest imaging accuracy is used to collect the current discharge phenomenon, and a corresponding event pulse stream is generated, which is placed in the set M of discharge phenomena to be learned, and the optimal threshold of the set M of discharge phenomena to be learned is learned again.

[0046] Preferably, the specific scheme for determining whether it is a known discharge phenomenon is: comparing the imaging accuracy of the perceived pulse flow slice image set with the real event pulse flow of all known discharge phenomena with a set minimum matching threshold Ω min In contrast, when one or more imaging accuracy rates are higher than the set minimum matching threshold Ω min When , it is considered that a known discharge phenomenon has occurred inside the GIS; all imaging accuracies are lower than the minimum matching threshold Ω min It is considered that a new discharge phenomenon occurs at this time.

[0047] The second aspect of the present invention proposes a bionic visual imaging device for adapting the internal signal strength of GIS using the method described in the first aspect of the present invention, comprising an event camera module, a preprocessing module, a calculation module, and an execution module, characterized in that:

[0048] The event camera module is used to build an event pulse flow acquisition model based on bionic visual perception, collect event pulse flow signals caused by different discharge phenomena inside the GIS, and preset the real event pulse flow according to the historical discharge phenomena;

[0049] A preprocessing module is used to preprocess the event pulse flow signal and calculate the imaging accuracy of the bionic visual sensor to obtain a set M of discharge phenomena to be learned;

[0050] A computing module is used to perform offline learning on the set M of discharge phenomena to be learned, construct a reward function and a loss function, iteratively train the event pulse stream in the set M of discharge phenomena to be learned, optimize the threshold of light intensity change of bionic vision, and output the optimal light intensity change threshold of all discharge phenomena to be learned;

[0051] The execution module is used to detect the light intensity change inside the GIS in real time based on the optimal light intensity change threshold set and use the event pulse flow acquisition model to perceive different discharge phenomena inside the GIS.

[0052] The beneficial effect of the present invention is that, compared with the prior art, by considering the difference in light signal intensity of different discharge phenomena, differentiated light intensity change thresholds are set for different discharge phenomenon characteristics, and an event pulse stream with high imaging accuracy and in line with the actual situation is generated based on the light intensity change threshold, thereby supporting accurate visual perception under multiple signal intensities, enhancing the accurate description of the GIS discharge phenomenon process by the event camera, and improving the perception accuracy of the GIS discharge phenomenon. A two-stage event-driven bionic visual perception optimization method is proposed, which combines offline learning with online data to improve the adaptability of the algorithm to field conditions. In the first stage, offline iterative learning is performed on each known discharge phenomenon inside the GIS by constructing a main network and a target network to optimize the imaging accuracy of the discharge phenomenon, and the offline training results are used for the second stage online discharge detection application; in the second stage, the unknown discharge phenomenon in the online discharge detection application is closed-loop fed back to the offline learning stage to learn the optimal threshold of light intensity change. The optimal light intensity change threshold can be learned through the new discharge phenomenon collected in the online application, realizing closed-loop feedback optimization between offline learning and online application, and further improving the bionic imaging efficiency of GIS equipment and the imaging recognition accuracy of GIS discharge phenomenon. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 It is a bionic visual perception framework diagram that adapts to various signal strengths within GIS;

[0054] Figure 2 It is the principle diagram of the bionic visual perception optimization method;

[0055] Figure 3 It is a flow chart of the bionic visual optimization method that adapts to various signal strengths within GIS;

[0056] Figure 4 It is a bionic visual imaging device that adapts to various signal strengths inside GIS. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical scheme and advantages of the present invention clearer, the technical scheme of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. The embodiments described in this application are only embodiments of a part of the present invention, rather than all embodiments. Based on the spirit of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work belong to the protection scope of the present invention.

[0058] like Figure 3 As shown, embodiment 1 of the present invention proposes a bionic visual optimization method for adapting the internal signal strength of GIS, comprising the following steps:

[0059] Construct an event pulse flow acquisition model based on bionic visual perception to collect event pulse flow signals caused by different discharge phenomena inside GIS, and preset the real event pulse flow according to the historical discharge phenomena;

[0060] like Figure 1 As shown, the event pulse stream signal is preprocessed, and the imaging accuracy of the bionic visual sensor is calculated to obtain a set M of discharge phenomena to be learned;

[0061] Offline learning is performed on the set M of discharge phenomena to be learned, a reward function and a loss function are constructed, and the event pulse stream in the set M of discharge phenomena to be learned is iteratively trained to optimize the threshold of light intensity change of bionic vision, and the optimal light intensity change threshold of all discharge phenomena to be learned is output;

[0062] Based on the optimal light intensity change threshold set, the event pulse stream acquisition model is used to detect the light intensity change inside the GIS in real time and perceive different discharge phenomena inside the GIS.

[0063] Preferably, the event pulse stream acquisition model includes an event camera deployed inside the GIS and including ultraviolet, infrared and visible light visual sensors. The visual sensors respond to changes in light intensity in discharge phenomena inside the GIS in the form of asynchronous sparse events. When the light intensity of a pixel at a current moment changes by more than a threshold compared to a preset standard light intensity of the pixel, the visual sensor outputs an event pulse at the pixel. All event pulses output by each visual sensor constitute an event pulse stream under the spectrum.

[0064] Preferably, the set of different types of discharge phenomena occurring inside the GIS is defined as E = {e1, ..., e o ,…,e O},e o , is the oth discharge phenomenon, O is the total number of different types of discharge phenomena;

[0065] The discharge phenomena collected by ultraviolet vision sensors, infrared vision sensors, and visible light vision sensors oThe generated event pulse stream is recorded as:

[0066]

[0067] Wherein, L = {UV, IR, VIS}, UV represents ultraviolet vision sensor, IR represents infrared vision sensor, VIS represents visible light vision sensor, is the nth event of the event pulse stream generated by the sensor represented by L, and N is the total number of event pulses generated by the sensor represented by L;

[0068] Each event pulse is characterized in the form of a quaternion:

[0069]

[0070] in, for The two-dimensional pixel position of for The trigger time; for The polarity of When , it means that the light intensity at the pixel is enhanced, and when , it means that the light intensity at the pixel is weakened.

[0071] Preferably, the preprocessing refers to slicing the event pulse stream generated by the visual sensor and the real event pulse stream at a reference frame rate f to obtain a sliced ​​image set.

[0072] Preferably, the calculation model for calculating the accuracy of bionic visual imaging specifically includes:

[0073] Calculate the mutual information of the acquired event pulse stream slice image set obtained by slicing the event pulse stream generated by the visual sensor and the real event pulse stream and the normalized corresponding images in the event pulse stream slice image set;

[0074]

[0075] Wherein, L = {UV, IR, VIS}, UV represents ultraviolet vision sensor, IR represents infrared vision sensor, and VIS represents visible light vision sensor; are respectively a collection of event pulse stream slice images obtained by the sensor corresponding to L after slicing and the lth image in the event pulse stream slice image collection; For images and images The mutual information of Respectively, images and images Entropy of

[0076] The imaging accuracy is obtained by weighted summation of the normalized mutual information of different visual sensors. Calculation formula:

[0077]

[0078] in, The total number of images in the collection of event pulse stream slice images obtained by slicing the images collected by the ultraviolet, infrared and visible light sensors, respectively, and The discharge phenomena are collected by the set ultraviolet, infrared and visible light sensors respectively. o The weight of is in the range of 0 to 1, and

[0079] Preferably, if Figure 2 As shown, the optimization of the bionic visual light intensity change threshold is achieved, specifically:

[0080] The optimization objective P1 formula is:

[0081]

[0082] In the formula, and are the light intensity change thresholds of the ultraviolet, infrared and visible light bionic sensors for all discharge phenomena, They are discharge phenomena e o The light intensity change threshold of the ultraviolet, infrared and visible light bionic sensors should be constrained between the minimum and maximum light intensity change thresholds;

[0083] The optimization goal of maximizing the average imaging accuracy is transformed into maximizing the imaging accuracy of each discharge phenomenon:

[0084]

[0085] Preferably, the reward function constructed is specifically the discharge phenomenon e o Imaging accuracy i is the number of iterations.

[0086] Preferably, the constructed loss function is specifically:

[0087]

[0088] In the formula,

[0089]

[0090] Where γ is the discount factor; Q(S(i),ρ(i); θ main ) is the output of the main network; Q(S(i+1),ρ(i+1);θtarget ) is the output of the target network; S(i+1) and S(i) are the states when the iterations are i+1 and i respectively; ρ(i+1) and ρ(i) are the actions when the iterations are i+1 and i respectively; Γ(i) represents the experience replay pool; represents some samples randomly drawn from the experience replay pool, for The number of samples in θ main represents the main network, θ target represents the target network;

[0091] Based on this loss function, the main network is updated. Among them, μ represents the update step size.

[0092] Preferably, the obtained optimal light intensity change threshold set uses an event pulse stream acquisition model to detect the light intensity change inside the GIS in real time and sense different discharge phenomena inside the GIS as follows:

[0093] The event camera maintains a detection state, and when the detected light intensity change exceeds the minimum light intensity change threshold in the optimal light intensity change threshold set, the event pulse stream signal caused by the discharge signal is collected, and preprocessed to obtain a set of perceived pulse stream slice images;

[0094] Calculate the imaging accuracy of the perceived pulse flow slice image set and the real event pulse flow of all known discharge phenomena, and determine whether it is a known discharge phenomenon based on the imaging accuracy;

[0095] If it is a known discharge phenomenon, the discharge phenomenon that occurs is the discharge phenomenon with the highest imaging accuracy. The optimal light intensity change threshold of the discharge phenomenon that occurs is selected to collect the discharge phenomenon that occurs in the current GIS, and generate the corresponding event pulse stream. If the maximum waiting time is set, If no light intensity change exceeding the optimal light intensity change threshold for the discharge phenomenon is detected, the pulse flow sensing of this event ends;

[0096] If it is not a known discharge phenomenon, closed-loop feedback update learning is performed, and the light intensity change threshold of the phenomenon with the highest imaging accuracy is used to collect the current discharge phenomenon, and a corresponding event pulse stream is generated, which is placed in the set M of discharge phenomena to be learned, and the optimal threshold of the set M of discharge phenomena to be learned is learned again.

[0097] Preferably, the specific scheme for determining whether it is a known discharge phenomenon is: comparing the imaging accuracy of the perceived pulse flow slice image set with the real event pulse flow of all known discharge phenomena with a set minimum matching threshold Ω min In contrast, when one or more imaging accuracy rates are higher than the set minimum matching threshold Ω minWhen , it is considered that a known discharge phenomenon has occurred inside the GIS; all imaging accuracies are lower than the minimum matching threshold Ω min It is considered that a new discharge phenomenon occurs at this time.

[0098] like Figure 4 As shown, Embodiment 2 of the present invention proposes a bionic visual imaging device for adapting the internal signal strength of GIS using the method described in Embodiment 1 of the present invention, including an event camera module, a preprocessing module, a calculation module, and an execution module, characterized in that:

[0099] The event camera module is used to build an event pulse flow acquisition model based on bionic visual perception, collect event pulse flow signals caused by different discharge phenomena inside the GIS, and preset the real event pulse flow according to the historical discharge phenomena;

[0100] A preprocessing module is used to preprocess the event pulse flow signal and calculate the imaging accuracy of the bionic visual sensor to obtain a set M of discharge phenomena to be learned;

[0101] A computing module is used to perform offline learning on the set M of discharge phenomena to be learned, construct a reward function and a loss function, iteratively train the event pulse stream in the set M of discharge phenomena to be learned, optimize the threshold of light intensity change of bionic vision, and output the optimal light intensity change threshold of all discharge phenomena to be learned;

[0102] The execution module is used to detect the light intensity change inside the GIS in real time based on the optimal light intensity change threshold set and use the event pulse flow acquisition model to perceive different discharge phenomena inside the GIS.

[0103] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A bionic visual optimization method for adapting the internal signal strength of GIS, characterized in that: include: Construct an event pulse flow acquisition model based on bionic visual perception to collect event pulse flow signals caused by different discharge phenomena inside GIS, and preset the real event pulse flow according to the historical discharge phenomena; Preprocessing the event pulse stream signal, and calculating the imaging accuracy of the bionic visual sensor, to obtain a set M of discharge phenomena to be learned; Offline learning is performed on the set M of discharge phenomena to be learned, a reward function and a loss function are constructed, and the event pulse stream in the set M of discharge phenomena to be learned is iteratively trained to optimize the threshold of light intensity change of bionic vision, and the optimal light intensity change threshold of all discharge phenomena to be learned is output; Based on the optimal light intensity change threshold set, the event pulse stream acquisition model is used to detect the light intensity change inside the GIS in real time and perceive different discharge phenomena inside the GIS.

2. The bionic visual optimization method for adapting the internal signal strength of GIS according to claim 1 is characterized in that: The event pulse stream acquisition model includes an event camera deployed inside the GIS that includes ultraviolet, infrared and visible light visual sensors. The visual sensors respond to changes in light intensity in discharge phenomena inside the GIS in the form of asynchronous sparse events. When the light intensity of a pixel at the current moment changes by more than a threshold compared to the preset standard light intensity of the pixel, the visual sensor outputs an event pulse at the pixel. All event pulses output by each visual sensor constitute an event pulse stream under the spectrum.

3. The bionic visual optimization method for adapting the internal signal strength of GIS according to claim 2 is characterized in that: The set of different types of discharge phenomena occurring inside GIS is defined as E = {e1,…,e o ,…,e O },e o , is the oth discharge phenomenon, O is the total number of different types of discharge phenomena; The discharge phenomena collected by ultraviolet vision sensors, infrared vision sensors, and visible light vision sensors o The generated event pulse stream is recorded as: Wherein, L = {UV, IR, VIS}, UV represents ultraviolet vision sensor, IR represents infrared vision sensor, VIS represents visible light vision sensor, is the nth event of the event pulse stream generated by the sensor represented by L, and N is the total number of event pulses generated by the sensor represented by L; Each event pulse is characterized in the form of a quaternion: in, for The two-dimensional pixel position of for The trigger time; for The polarity of When , it means that the light intensity at the pixel is enhanced, and when , it means that the light intensity at the pixel is weakened.

4. The bionic visual optimization method for adapting the internal signal strength of GIS according to claim 1 is characterized in that: The preprocessing refers to slicing the event pulse stream generated by the visual sensor and the real event pulse stream at a reference frame rate f to obtain a sliced ​​image set.

5. The bionic visual optimization method for adapting the internal signal strength of GIS according to claim 4 is characterized in that: The computational model of bionic visual imaging accuracy includes: Calculate the mutual information of the acquired event pulse stream slice image set obtained by slicing the event pulse stream generated by the visual sensor and the real event pulse stream and the normalized corresponding images in the event pulse stream slice image set; Wherein, L = {UV, IR, VIS}, UV represents ultraviolet vision sensor, IR represents infrared vision sensor, and VIS represents visible light vision sensor; are respectively a collection of event pulse stream slice images obtained by the sensor corresponding to L after slicing and the lth image in the event pulse stream slice image collection; For images and images The mutual information of Respectively, images and images Entropy of The imaging accuracy is obtained by weighted summation of the normalized mutual information of different visual sensors. Calculation formula: in, The total number of images of the collection event pulse stream slice image set obtained by slicing the images collected by the ultraviolet, infrared and visible light sensors, respectively, and The discharge phenomena are collected by the set ultraviolet, infrared and visible light sensors respectively. o The weight of is in the range of 0 to 1, and 6. A bionic visual optimization method for adapting the internal signal strength of GIS according to any one of claims 1 to 5, characterized in that: The optimization of the bionic visual light intensity change threshold is realized as follows: The optimization objective P1 formula is: In the formula, and are the light intensity change thresholds of the ultraviolet, infrared and visible light bionic sensors for all discharge phenomena, They are discharge phenomena e o The light intensity change threshold of the ultraviolet, infrared and visible light bionic sensors should be constrained between the minimum and maximum light intensity change thresholds; The optimization goal of maximizing the average imaging accuracy is transformed into maximizing the imaging accuracy of each discharge phenomenon:

7. The bionic visual optimization method for adapting the internal signal strength of GIS according to claim 6 is characterized in that: The reward function constructed is specifically the discharge phenomenon e o Imaging accuracy i is the number of iterations.

8. A bionic visual optimization method for adapting the internal signal strength of GIS according to claim 7, characterized in that: The constructed loss function is specifically: In the formula, Where γ is the discount factor; Q(S(i),ρ(i); θ main ) is the output of the main network; Q(S(i+1),ρ(i+1);θ target ) is the output of the target network; S(i+1) and S(i) are the states when the iterations are i+1 and i respectively; ρ(i+1) and ρ(i) are the actions when the iterations are i+1 and i respectively; Γ(i) represents the experience replay pool; represents some samples randomly drawn from the experience replay pool, for The number of samples in θ main represents the main network, θ target represents the target network; Based on this loss function, the main network is updated. Among them, μ represents the update step size.

9. A bionic visual optimization method for adapting the internal signal strength of GIS according to claim 8, characterized in that: The optimal light intensity change threshold set obtained above uses the event pulse stream acquisition model to detect the light intensity change inside the GIS in real time and sense the different discharge phenomena inside the GIS: The event camera maintains a detection state, and when the detected light intensity change exceeds the minimum light intensity change threshold in the optimal light intensity change threshold set, the event pulse stream signal caused by the discharge signal is collected, and preprocessed to obtain a set of perceived pulse stream slice images; Calculate the imaging accuracy of the perceived pulse flow slice image set and the real event pulse flow of all known discharge phenomena, and determine whether it is a known discharge phenomenon based on the imaging accuracy; If it is a known discharge phenomenon, the discharge phenomenon that occurs is the discharge phenomenon with the highest imaging accuracy. The optimal light intensity change threshold of the discharge phenomenon that occurs is selected to collect the discharge phenomenon that occurs in the current GIS, and generate the corresponding event pulse stream. If the maximum waiting time is set, If no light intensity change exceeding the optimal light intensity change threshold for the discharge phenomenon is detected, the pulse flow sensing of this event ends; If it is not a known discharge phenomenon, closed-loop feedback update learning is performed, and the light intensity change threshold of the phenomenon with the highest imaging accuracy is used to collect the current discharge phenomenon, and a corresponding event pulse stream is generated, which is placed in the set M of discharge phenomena to be learned, and the optimal threshold of the set M of discharge phenomena to be learned is learned again.

10. A bionic visual optimization method for adapting the internal signal strength of GIS according to claim 9, characterized in that: The specific scheme for determining whether it is a known discharge phenomenon is: comparing the imaging accuracy of the perceived pulse flow slice image set with the real event pulse flow of all known discharge phenomena with the set minimum matching threshold Ω min In contrast, when one or more imaging accuracy rates are higher than the set minimum matching threshold Ω min When , it is considered that a known discharge phenomenon has occurred inside the GIS; all imaging accuracies are lower than the minimum matching threshold Ω min It is considered that a new discharge phenomenon occurs at this time.

11. A bionic visual imaging device for adapting the internal signal strength of GIS using the method according to any one of claims 1 to 10, comprising an event camera module, a preprocessing module, a calculation module, and an execution module, characterized in that: The event camera module is used to build an event pulse flow acquisition model based on bionic visual perception, collect event pulse flow signals caused by different discharge phenomena inside the GIS, and preset the real event pulse flow according to the historical discharge phenomena; A preprocessing module is used to preprocess the event pulse flow signal and calculate the imaging accuracy of the bionic visual sensor to obtain a set M of discharge phenomena to be learned; A computing module is used to perform offline learning on the set M of discharge phenomena to be learned, construct a reward function and a loss function, iteratively train the event pulse stream in the set M of discharge phenomena to be learned, optimize the threshold of light intensity change of bionic vision, and output the optimal light intensity change threshold of all discharge phenomena to be learned; The execution module is used to detect the light intensity change inside the GIS in real time based on the optimal light intensity change threshold set and use the event pulse flow acquisition model to perceive different discharge phenomena inside the GIS.

Images