Laser limiter monitoring method and device, electronic equipment and storage medium
By forming a multi-dimensional cross-laser beam network within the monitoring area of the laser limiter, and combining deep learning and machine learning algorithms to dynamically adjust the monitoring threshold, the problem of insufficient monitoring accuracy and reliability of the laser limiter is solved, achieving high-precision automated monitoring and redundant protection.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SHENZHEN EXCELLENCE INFORMATION TECH CO LTD
- Filing Date
- 2026-02-05
- Publication Date
- 2026-05-01
AI Technical Summary
Existing laser limiter monitoring solutions are inadequate in terms of monitoring accuracy and reliability, with a high incidence of false alarms and missed alarms.
By deploying multiple laser limiters within the monitoring area to form a multi-dimensional cross-laser beam network, the intensity, propagation time, and frequency characteristics of light are acquired and fused. Combined with deep learning models and machine learning algorithms, the monitoring threshold is dynamically adjusted to achieve adaptive optimization and automatic identification of interference sources.
It significantly improves monitoring accuracy and reliability, reduces false alarms and missed alarms, realizes a fully automated process from monitoring to early warning response, and provides redundant protection through a multi-dimensional cross laser beam network, thereby improving system stability.
Smart Images
Figure CN121955878A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of monitoring technology, and specifically to a laser limiter monitoring method, device, electronic equipment, and storage medium. Background Technology
[0002] A laser limiter is a device that uses laser technology for precise positioning and limiting. It typically consists of a laser, optical elements (such as lenses and mirrors), sensors, and a controller. The working principle of a laser limiter is to emit a laser beam, which, through adjustment and control of the optical elements, is precisely projected onto the target object. The sensor then receives the position and direction information of the laser beam and converts it into an electrical signal, which is output to the controller, thereby achieving precise positioning and limiting of the target object. Compared to traditional limit devices, laser limiters offer higher accuracy, longer service life, and lower cost, and are therefore widely used in modern industrial production. However, current monitoring schemes based on laser limiters perform poorly in terms of monitoring accuracy and reliability, with a relatively high incidence of false alarms and missed alarms. Summary of the Invention
[0003] Based on the above-mentioned problems, this invention proposes a laser limiter monitoring method, device, electronic equipment, and storage medium. Through the solution of this invention, the monitoring accuracy and reliability can be improved, and false alarms and missed alarms can be reduced.
[0004] In view of this, one aspect of the present invention proposes a laser limiter monitoring method, comprising: Multiple laser limiters are deployed within the monitoring area according to a preset spatial topology. Each laser limiter contains a laser transmitter and a laser receiver, forming a multi-dimensional cross laser beam network. When the system starts, it acquires the reference light intensity value, reference propagation time and reference frequency characteristics of each laser beam in the multi-dimensional cross laser beam network, and constructs the reference beam state matrix. The real-time light intensity, real-time propagation time and real-time frequency characteristics of each laser beam in the multi-dimensional cross laser beam network are continuously monitored to generate a real-time beam state matrix. The real-time beam state matrix and the reference beam state matrix are differentially calculated to obtain the light intensity change ΔI, the propagation time change Δt, and the frequency change Δf. The three types of changes are then weighted and fused based on a preset fusion weight coefficient to calculate the comprehensive change index CCI. Based on the spatial coordinates of the changing laser beam in the multi-dimensional intersecting laser beam network, the three-dimensional spatial position of the interference source is determined by a triangulation algorithm, and the motion trajectory of the interference source is reconstructed based on time series analysis. The Comprehensive Change Index (CCI), spatial location information, and motion trajectory features are input into a pre-trained deep learning model to identify and classify interference source types, and output the category label and confidence level of the interference source. Based on the category labels of the interference sources and historical monitoring data, machine learning algorithms are used to dynamically adjust the monitoring thresholds corresponding to each type of interference source, thereby achieving adaptive optimization of the monitoring system. When the Comprehensive Change Index (CCI) exceeds the dynamic threshold of the corresponding type of interference source, a graded early warning message is generated, and corresponding processing measures are automatically triggered according to the preset response strategy.
[0005] Optionally, the laser limiter matrix deployment in the step of deploying multiple laser limiters according to a preset spatial topology within the monitoring area employs an adaptive spatial optimization algorithm, the objective function of which is:
[0006] Where M is the total number of laser limiters and N is the number of spatial grid points in the monitoring area; This is the coverage weighting coefficient. This is the redundancy weighting coefficient. Energy consumption weighting coefficient; The coverage contribution of the m-th laser limiter to the n-th spatial grid point; The redundancy protection degree of the m-th laser limiter at the n-th spatial grid point; This represents the energy consumption of the m-th laser limiter at the n-th spatial grid point.
[0007] Optionally, the formula for calculating the reference beam state matrix is:
[0008] in, Let K be the reference state value of the laser beam in row p and column q, and K be the number of calibration samples. For light intensity feature weights, For time feature weights, For spectral feature weights; Let k be the light intensity value of the kth sample. The propagation time value for the kth sample. The frequency characteristic value of the k-th sample is... The center value of the number of samples, This is the time decay factor.
[0009] Optionally, the real-time beam state monitoring in the step of continuously monitoring the real-time light intensity, real-time propagation time, and real-time frequency characteristics of each laser beam in the multi-dimensional cross-beam network to generate a real-time beam state matrix employs an adaptive filtering algorithm. The formula for calculating the filtered real-time state value is as follows:
[0010] in, Let be the filtered real-time state value of the laser beam in row p and column q at time t; The filtered real-time state value at time t-1; The original monitoring value at time t; The filtering smoothing coefficient (0 < <1); For nonlinear gain coefficients; This represents the change in the original monitoring value; This is the sensitivity threshold parameter; It is the hyperbolic tangent function.
[0011] Optionally, the weighted fusion of the three types of changes based on preset fusion weight coefficients, and the calculation of the Comprehensive Change Index (CCI) employs a dynamic weight allocation mechanism; the formula for calculating the Comprehensive Change Index (CCI) is as follows:
[0012] Dynamic weighting coefficients The calculation formula is:
[0013] Where U represents the total number of monitored parameters; Let be the dynamic weighting coefficient of the u-th parameter at time t; The change in the u-th parameter; This is the baseline value for the u-th parameter; Let be the nonlinear exponent of the u-th parameter; Let be the periodic modulation coefficient of the u-th parameter; For monitoring cycle; Let u be the importance coefficient of the i-th parameter. Let be the variance of the u-th parameter at time t.
[0014] Optionally, in the step of determining the three-dimensional spatial position of the interference source using a triangulation algorithm based on the spatial coordinates of the changing laser beam in the multi-dimensional intersecting laser beam network, and reconstructing the motion trajectory of the interference source based on time series analysis, the spatial positioning and trajectory reconstruction employ a multi-constraint optimization algorithm, and the formula for calculating the three-dimensional spatial position is: ,satisfy:
[0015] The velocity estimation formula for trajectory reconstruction is:
[0016] in, Let S be the three-dimensional coordinates of the interference source to be solved, and S be the number of laser limiters involved in the positioning. Let S be the spatial coordinates of the s-th laser limiter; Let be the measured distance from the s-th laser limiter to the interference source; Let be the weighting coefficient of the s-th laser limiter; Let be the regularization coefficient of the s-th laser limiter; This represents the gradient of the distance function with respect to the coordinates. Let be the velocity vector at time t. Let be the position vector at time t. For the integral coefficient of acceleration, The memory decay coefficient, For a moment The acceleration vector.
[0017] Optionally, the step of inputting the Comprehensive Change Index (CCI), spatial location information, and motion trajectory features into a pre-trained deep learning model to identify and classify interference source types, and output the category label and confidence level of the interference source, employs a multi-level confidence evaluation mechanism for identification and classification. The final confidence level is calculated using the following formula:
[0018] The formula for calculating the entropy value ENTR is:
[0019] The formula for calculating the category fusion score is as follows:
[0020] in, The final confidence level is given by H, where H is the number of layers in the neural network. Let h be the confidence level of the h-th layer. The weight index of the h-th layer, The entropy penalty coefficient is... To output the entropy value of the probability distribution, Here, C is the entropy normalization parameter; C is the total number of categories. Let c be the predicted probability of the c-th category. For numerical stability parameters; Let F be the fusion score for the c-th category, and F be the number of feature dimensions. The weight of the f-th feature is... For the f-th eigenvalue, Let be the confidence level for the c-th category. Let c be the confidence threshold for the c-th category. Let be the confidence scale parameter for the c-th category. This is the Sigmoid function.
[0021] A second aspect of the present invention provides a laser limiter monitoring device for performing a laser limiter monitoring method, comprising: a plurality of laser limiters deployed in a monitoring area according to a preset spatial topology; a processing module; wherein each laser limiter includes a laser transmitter and a laser receiver, forming a multi-dimensional cross laser beam network; The processing module is configured as follows: When the system starts, it acquires the reference light intensity value, reference propagation time and reference frequency characteristics of each laser beam in the multi-dimensional cross laser beam network, and constructs the reference beam state matrix. The real-time light intensity, real-time propagation time and real-time frequency characteristics of each laser beam in the multi-dimensional cross laser beam network are continuously monitored to generate a real-time beam state matrix. The real-time beam state matrix and the reference beam state matrix are differentially calculated to obtain the light intensity change ΔI, the propagation time change Δt, and the frequency change Δf. The three types of changes are then weighted and fused based on a preset fusion weight coefficient to calculate the comprehensive change index CCI. Based on the spatial coordinates of the changing laser beam in the multi-dimensional intersecting laser beam network, the three-dimensional spatial position of the interference source is determined by a triangulation algorithm, and the motion trajectory of the interference source is reconstructed based on time series analysis. The Comprehensive Change Index (CCI), spatial location information, and motion trajectory features are input into a pre-trained deep learning model to identify and classify interference source types, and output the category label and confidence level of the interference source. Based on the category labels of the interference sources and historical monitoring data, machine learning algorithms are used to dynamically adjust the monitoring thresholds corresponding to each type of interference source, thereby achieving adaptive optimization of the monitoring system. When the Comprehensive Change Index (CCI) exceeds the dynamic threshold of the corresponding type of interference source, a graded early warning message is generated, and corresponding processing measures are automatically triggered according to the preset response strategy.
[0022] A third aspect of the present invention provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of a laser limiter monitoring method.
[0023] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a laser limiter monitoring method.
[0024] The laser limiter monitoring method of this invention significantly improves monitoring accuracy and reliability through multi-parameter fusion analysis (light intensity, propagation time, frequency); it combines a deep learning model to achieve automatic identification and classification of different types of interference sources; it dynamically adjusts the monitoring threshold through machine learning algorithms to reduce false alarms and missed alarms; it uses a triangulation algorithm to accurately determine the three-dimensional position and motion trajectory of the interference source; it realizes a fully automated process from monitoring to early warning response; and a multi-dimensional cross-beam network provides redundancy protection to improve system stability. Attached Figure Description
[0025] Figure 1 This is a flowchart of a laser limiter monitoring method provided in one embodiment of the present invention; Figure 2 This is a schematic block diagram of a laser limiter monitoring device provided in one embodiment of the present invention. Detailed Implementation
[0026] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.
[0027] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.
[0028] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.
[0029] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.
[0030] The following reference Figures 1 to 2 This invention describes a laser limiter monitoring method, apparatus, electronic device, and storage medium provided according to some embodiments of the present invention.
[0031] like Figure 1 As shown, one embodiment of the present invention provides a laser limiter monitoring method, comprising: Multiple laser limiters are deployed within the monitoring area according to a preset spatial topology. Each laser limiter contains a laser transmitter and a laser receiver, forming a multi-dimensional cross laser beam network. When the system starts, it acquires the reference light intensity value, reference propagation time and reference frequency characteristics of each laser beam in the multi-dimensional cross laser beam network, and constructs the reference beam state matrix. The real-time light intensity, real-time propagation time and real-time frequency characteristics of each laser beam in the multi-dimensional cross laser beam network are continuously monitored to generate a real-time beam state matrix. The real-time beam state matrix and the reference beam state matrix are differentially calculated to obtain the light intensity change ΔI, the propagation time change Δt, and the frequency change Δf. The three types of changes are then weighted and fused based on a preset fusion weight coefficient to calculate the comprehensive change index CCI. Based on the spatial coordinates of the changing laser beam in the multi-dimensional intersecting laser beam network, the three-dimensional spatial position of the interference source is determined by a triangulation algorithm, and the motion trajectory of the interference source is reconstructed based on time series analysis. The Comprehensive Change Index (CCI), spatial location information, and motion trajectory features are input into a pre-trained deep learning model to identify and classify interference source types, and output the category label and confidence level of the interference source. Based on the category labels of the interference sources and historical monitoring data, machine learning algorithms are used to dynamically adjust the monitoring thresholds corresponding to each type of interference source, thereby achieving adaptive optimization of the monitoring system. When the Comprehensive Change Index (CCI) exceeds the dynamic threshold of the corresponding type of interference source, a graded early warning message is generated, and corresponding processing measures are automatically triggered according to the preset response strategy.
[0032] The technical solution adopted in this embodiment significantly improves monitoring accuracy and reliability through multi-parameter fusion analysis (light intensity, propagation time, frequency); it combines a deep learning model to achieve automatic identification and classification of different types of interference sources; it dynamically adjusts the monitoring threshold through machine learning algorithms to reduce false alarms and missed alarms; it uses a triangulation algorithm to accurately determine the three-dimensional position and motion trajectory of the interference source; it realizes a fully automated process from monitoring to early warning response; and a multi-dimensional cross-beam network provides redundancy protection to improve system stability.
[0033] In some possible embodiments of the present invention, the laser limiter matrix deployment in the step of deploying multiple laser limiters according to a preset spatial topology within the monitoring area employs an adaptive spatial optimization algorithm, the objective function of which is:
[0034] Where M is the total number of laser limiters and N is the number of spatial grid points in the monitoring area; This is the coverage weighting coefficient. This is the redundancy weighting coefficient. Energy consumption weighting coefficient; The coverage contribution of the m-th laser limiter to the n-th spatial grid point; The redundancy protection degree of the m-th laser limiter at the n-th spatial grid point; This represents the energy consumption of the m-th laser limiter at the n-th spatial grid point.
[0035] The solution in this embodiment can minimize system energy consumption and improve deployment efficiency while ensuring monitoring coverage and redundant protection.
[0036] In some possible embodiments of the present invention, the formula for calculating the reference beam state matrix is as follows:
[0037] in, Let K be the reference state value of the laser beam in row p and column q, and K be the number of calibration samples. For light intensity feature weights, For time feature weights, For spectral feature weights; Let k be the light intensity value of the kth sample. The propagation time value for the kth sample. The frequency characteristic value of the k-th sample is... The center value of the number of samples, This is the time decay factor.
[0038] The scheme in this embodiment establishes a stable and reliable baseline state through weighted averaging and a Gaussian decay function, thereby improving the accuracy of subsequent monitoring.
[0039] In some possible embodiments of the present invention, the real-time beam state monitoring in the step of continuously monitoring the real-time light intensity, real-time propagation time, and real-time frequency characteristics of each laser beam in the multi-dimensional cross-beam network to generate a real-time beam state matrix employs an adaptive filtering algorithm, and the formula for calculating the filtered real-time state value is as follows:
[0040] in, Let be the filtered real-time state value of the laser beam in row p and column q at time t; The filtered real-time state value at time t-1; The original monitoring value at time t; The filtering smoothing coefficient (0 < <1); For nonlinear gain coefficients; This represents the change in the original monitoring value; This is the sensitivity threshold parameter; It is the hyperbolic tangent function.
[0041] The solution in this embodiment can smooth out noise while maintaining sensitivity to rapid changes, thereby improving the real-time performance and accuracy of monitoring.
[0042] In some possible embodiments of the present invention, a dynamic weight allocation mechanism is used in the weighted fusion of the three types of changes based on preset fusion weight coefficients to calculate the Comprehensive Change Index (CCI); the formula for calculating the Comprehensive Change Index (CCI) is as follows:
[0043] Where U represents the total number of monitored parameters; Let be the dynamic weighting coefficient of the u-th parameter at time t; The change in the u-th parameter; This is the baseline value for the u-th parameter; Let be the nonlinear exponent of the u-th parameter; Let be the periodic modulation coefficient of the u-th parameter; For monitoring cycle; Dynamic weighting coefficients The calculation formula is:
[0044] in, Let u be the importance coefficient of the i-th parameter. Let be the variance of the u-th parameter at time t.
[0045] The scheme in this embodiment improves the adaptability and accuracy of fusion analysis through dynamic weight adjustment and periodic modulation.
[0046] In some possible embodiments of the present invention, in the step of determining the three-dimensional spatial position of the interference source using a triangulation algorithm based on the spatial coordinates of the changing laser beam in the multi-dimensional intersecting laser beam network, and reconstructing the motion trajectory of the interference source based on time series analysis, the spatial positioning and trajectory reconstruction employ a multi-constraint optimization algorithm, and the formula for calculating the three-dimensional spatial position is: ,satisfy:
[0047] in, Let S be the three-dimensional coordinates of the interference source to be solved, and S be the number of laser limiters involved in the positioning. Let S be the spatial coordinates of the s-th laser limiter; Let be the measured distance from the s-th laser limiter to the interference source; Let be the weighting coefficient of the s-th laser limiter; Let be the regularization coefficient of the s-th laser limiter; This represents the gradient of the distance function with respect to the coordinates. The velocity estimation formula for trajectory reconstruction is:
[0048] in, Let be the velocity vector at time t. Let be the position vector at time t. For the integral coefficient of acceleration, The memory decay coefficient, For a moment The acceleration vector.
[0049] The solution in this embodiment improves positioning accuracy and trajectory reconstruction smoothness through multi-constraint optimization and memory integration.
[0050] In some possible embodiments of the present invention, the step of inputting the Comprehensive Change Index (CCI), spatial location information, and motion trajectory features into a pre-trained deep learning model to identify and classify interference source types, and outputting the category label and confidence level of the interference source, employs a multi-level confidence evaluation mechanism for identification and classification. The final confidence level is calculated using the following formula:
[0051] in, The final confidence level is given by H, where H is the number of layers in the neural network. Let h be the confidence level of the h-th layer. The weight index of the h-th layer, The entropy penalty coefficient is... To output the entropy value of the probability distribution, This is the entropy normalization parameter; The formula for calculating the entropy value ENTR is:
[0052] in: C represents the total number of categories. Let c be the predicted probability of the c-th category. For numerical stability parameters; The formula for calculating the category fusion score is:
[0053] in, Let F be the fusion score for the c-th category, and F be the number of feature dimensions. The weight of the f-th feature is... For the f-th eigenvalue, Let be the confidence level for the c-th category. Let c be the confidence threshold for the c-th category. Let be the confidence scale parameter for the c-th category. This is the Sigmoid function.
[0054] The scheme in this embodiment improves the reliability and robustness of the recognition results through multi-level confidence assessment and entropy regularization.
[0055] Please see Figure 2 Another embodiment of the present invention provides a laser limiter monitoring device for performing a laser limiter monitoring method, comprising: a plurality of laser limiters deployed in a monitoring area according to a preset spatial topology; a processing module; wherein each laser limiter includes a laser transmitter and a laser receiver, forming a multi-dimensional cross laser beam network; The processing module is configured as follows: When the system starts, it acquires the reference light intensity value, reference propagation time and reference frequency characteristics of each laser beam in the multi-dimensional cross laser beam network, and constructs the reference beam state matrix. The real-time light intensity, real-time propagation time and real-time frequency characteristics of each laser beam in the multi-dimensional cross laser beam network are continuously monitored to generate a real-time beam state matrix. The real-time beam state matrix and the reference beam state matrix are differentially calculated to obtain the light intensity change ΔI, the propagation time change Δt, and the frequency change Δf. The three types of changes are then weighted and fused based on a preset fusion weight coefficient to calculate the comprehensive change index CCI. Based on the spatial coordinates of the changing laser beam in the multi-dimensional intersecting laser beam network, the three-dimensional spatial position of the interference source is determined by a triangulation algorithm, and the motion trajectory of the interference source is reconstructed based on time series analysis. The Comprehensive Change Index (CCI), spatial location information, and motion trajectory features are input into a pre-trained deep learning model to identify and classify interference source types, and output the category label and confidence level of the interference source. Based on the category labels of the interference sources and historical monitoring data, machine learning algorithms are used to dynamically adjust the monitoring thresholds corresponding to each type of interference source, thereby achieving adaptive optimization of the monitoring system. When the Comprehensive Change Index (CCI) exceeds the dynamic threshold of the corresponding type of interference source, a graded early warning message is generated, and corresponding processing measures are automatically triggered according to the preset response strategy.
[0056] It should be known that, Figure 2 The block diagram of the laser limiter monitoring device shown is for illustrative purposes only, and the number of modules shown does not limit the scope of protection of this invention. The laser limiter monitoring device provided in this embodiment can be used to execute various embodiments of the corresponding laser limiter monitoring method. For specific implementation details, please refer to the descriptions of the respective method embodiments, which will not be repeated here.
[0057] Another embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of a laser limiter monitoring method.
[0058] Another embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a laser limiter monitoring method.
[0059] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.
[0060] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.
[0061] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical or other forms.
[0062] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0063] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0064] If the integrated units described above are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.
[0065] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.
[0066] The embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.
[0067] While the present invention has been disclosed above, it is not limited thereto. Any person skilled in the art can easily conceive of variations or substitutions without departing from the spirit and scope of the present invention, and various modifications and alterations can be made, including combinations of the different functions and implementation steps described above, as well as software and hardware implementation methods, all of which are within the protection scope of the present invention.
Claims
1. A laser limiter monitoring method, characterized in that, include: Multiple laser limiters are deployed within the monitoring area according to a preset spatial topology. Each laser limiter contains a laser transmitter and a laser receiver, forming a multi-dimensional cross laser beam network. When the system starts, it acquires the reference light intensity value, reference propagation time and reference frequency characteristics of each laser beam in the multi-dimensional cross laser beam network, and constructs the reference beam state matrix. The real-time light intensity, real-time propagation time and real-time frequency characteristics of each laser beam in the multi-dimensional cross laser beam network are continuously monitored to generate a real-time beam state matrix. The real-time beam state matrix and the reference beam state matrix are differentially calculated to obtain the light intensity change ΔI, the propagation time change Δt, and the frequency change Δf. The three types of changes are then weighted and fused based on a preset fusion weight coefficient to calculate the comprehensive change index CCI. Based on the spatial coordinates of the changing laser beam in the multi-dimensional intersecting laser beam network, the three-dimensional spatial position of the interference source is determined by a triangulation algorithm, and the motion trajectory of the interference source is reconstructed based on time series analysis. The Comprehensive Change Index (CCI), spatial location information, and motion trajectory features are input into a pre-trained deep learning model to identify and classify interference source types, and output the category label and confidence level of the interference source. Based on the category labels of the interference sources and historical monitoring data, machine learning algorithms are used to dynamically adjust the monitoring thresholds corresponding to each type of interference source, thereby achieving adaptive optimization of the monitoring system. When the Comprehensive Change Index (CCI) exceeds the dynamic threshold of the corresponding type of interference source, a graded early warning message is generated, and corresponding processing measures are automatically triggered according to the preset response strategy.
2. The laser limiter monitoring method according to claim 1, characterized in that, The laser limiter matrix deployment in the step of deploying multiple laser limiters according to a preset spatial topology within the monitoring area employs an adaptive spatial optimization algorithm, the objective function of which is: Where M is the total number of laser limiters and N is the number of spatial grid points in the monitoring area; This is the coverage weighting coefficient. This is the redundancy weighting coefficient. Energy consumption weighting coefficient; The coverage contribution of the m-th laser limiter to the n-th spatial grid point; The redundancy protection degree of the m-th laser limiter at the n-th spatial grid point; This represents the energy consumption of the m-th laser limiter at the n-th spatial grid point.
3. The laser limiter monitoring method according to claim 2, characterized in that, The formula for calculating the reference beam state matrix is as follows: in, Let K be the reference state value of the laser beam in row p and column q, and K be the number of calibration samples. For light intensity feature weights, For time feature weights, For spectral feature weights; Let k be the light intensity value of the kth sample. The propagation time value for the kth sample. The frequency characteristic value of the k-th sample is... The center value of the number of samples, This is the time decay factor.
4. The laser limiter monitoring method according to claim 3, characterized in that, The real-time beam state monitoring in the step of continuously monitoring the real-time light intensity, real-time propagation time, and real-time frequency characteristics of each laser beam in the multi-dimensional cross-beam network to generate a real-time beam state matrix employs an adaptive filtering algorithm. The formula for calculating the filtered real-time state value is as follows: in, Let be the filtered real-time state value of the laser beam in row p and column q at time t; The filtered real-time state value at time t-1; The original monitoring value at time t; The filtering smoothing coefficient (0 < <1); For nonlinear gain coefficients; This represents the change in the original monitoring value; This is the sensitivity threshold parameter; It is the hyperbolic tangent function.
5. The laser limiter monitoring method according to claim 4, characterized in that, The three types of changes are weighted and fused based on preset fusion weight coefficients, and a dynamic weight allocation mechanism is used in the calculation of the Comprehensive Change Index (CCI). The formula for calculating the Comprehensive Change Index (CCI) is as follows: Dynamic weighting coefficients The calculation formula is: Where U represents the total number of monitored parameters; Let be the dynamic weighting coefficient of the u-th parameter at time t; The change in the u-th parameter; This is the baseline value for the u-th parameter; Let be the nonlinear exponent of the u-th parameter; Let be the periodic modulation coefficient of the u-th parameter; For monitoring cycle; Let u be the importance coefficient of the i-th parameter. Let be the variance of the u-th parameter at time t.
6. The laser limiter monitoring method according to claim 5, characterized in that, In the step of determining the three-dimensional spatial position of the interference source using a triangulation algorithm based on the spatial coordinates of the changing laser beam in the multi-dimensional intersecting laser beam network, and reconstructing the motion trajectory of the interference source based on time series analysis, the spatial positioning and trajectory reconstruction employ a multi-constraint optimization algorithm. The formula for calculating the three-dimensional spatial position is as follows: ,satisfy: The velocity estimation formula for trajectory reconstruction is: in, Let S be the three-dimensional coordinates of the interference source to be solved, and S be the number of laser limiters involved in the positioning. Let S be the spatial coordinates of the s-th laser limiter; Let be the measured distance from the s-th laser limiter to the interference source; Let be the weighting coefficient of the s-th laser limiter; Let be the regularization coefficient of the s-th laser limiter; This represents the gradient of the distance function with respect to the coordinates. Let be the velocity vector at time t. Let be the position vector at time t. For the integral coefficient of acceleration, The memory decay coefficient, For a moment The acceleration vector.
7. The laser limiter monitoring method according to claim 6, characterized in that, The step of inputting the Comprehensive Change Index (CCI), spatial location information, and motion trajectory features into a pre-trained deep learning model to identify and classify interference source types, and output the category label and confidence level of the interference source, employs a multi-level confidence evaluation mechanism for identification and classification. The final confidence level is calculated using the following formula: The formula for calculating the entropy value ENTR is: The formula for calculating the category fusion score is as follows: in, The final confidence level is given by H, where H is the number of layers in the neural network. Let h be the confidence level of the h-th layer. The weight index of the h-th layer, The entropy penalty coefficient is... To output the entropy value of the probability distribution, Here, C is the entropy normalization parameter; C is the total number of categories. Let c be the predicted probability of the c-th category. For numerical stability parameters; Let F be the fusion score for the c-th category, and F be the number of feature dimensions. The weight of the f-th feature is... For the f-th eigenvalue, Let be the confidence level for the c-th category. Let c be the confidence threshold for the c-th category. Let be the confidence scale parameter for the c-th category. This is the Sigmoid function.
8. A laser limiter monitoring device, used to perform the laser limiter monitoring method as described in any one of claims 1 to 7, characterized in that, include: Multiple laser limiters are deployed within the monitoring area according to a preset spatial topology; a processing module; wherein each laser limiter contains a laser transmitter and a laser receiver, forming a multi-dimensional cross laser beam network; The processing module is configured as follows: When the system starts, it acquires the reference light intensity value, reference propagation time and reference frequency characteristics of each laser beam in the multi-dimensional cross laser beam network, and constructs the reference beam state matrix. The real-time light intensity, real-time propagation time and real-time frequency characteristics of each laser beam in the multi-dimensional cross laser beam network are continuously monitored to generate a real-time beam state matrix. The real-time beam state matrix and the reference beam state matrix are differentially calculated to obtain the light intensity change ΔI, the propagation time change Δt, and the frequency change Δf. The three types of changes are then weighted and fused based on a preset fusion weight coefficient to calculate the comprehensive change index CCI. Based on the spatial coordinates of the changing laser beam in the multi-dimensional intersecting laser beam network, the three-dimensional spatial position of the interference source is determined by a triangulation algorithm, and the motion trajectory of the interference source is reconstructed based on time series analysis. The Comprehensive Change Index (CCI), spatial location information, and motion trajectory features are input into a pre-trained deep learning model to identify and classify interference source types, and output the category label and confidence level of the interference source. Based on the category labels of the interference sources and historical monitoring data, machine learning algorithms are used to dynamically adjust the monitoring thresholds corresponding to each type of interference source, thereby achieving adaptive optimization of the monitoring system. When the Comprehensive Change Index (CCI) exceeds the dynamic threshold of the corresponding type of interference source, a graded early warning message is generated, and corresponding processing measures are automatically triggered according to the preset response strategy.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the laser limiter monitoring method as described in any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the laser limiter monitoring method as described in any one of claims 1 to 7.