An online libs laser real-time detection device

Abstract

The application relates to the technical field of new material related services, in particular to an online Libs laser real-time detection device, which comprises a laser generator, a data acquisition instrument, a power supply, an online monitoring system, a sensor node group and a shell, the online monitoring system comprises a data acquisition module, a data processing module, a first detection tuning module and a second detection tuning module, the application dynamically adjusts the computing power according to the change of the actual detection task, guarantees the accurate computing power calculation, thereby improving the accuracy of the detection result when new materials are detected, the online monitoring system flexibly allocates the electric quantity through the second detection tuning module, reduces the electric quantity consumption, so that the electric quantity balance is more durable, resource waste is avoided, the resource utilization rate when new materials are detected is improved, thereby increasing the endurance of the online Libs laser real-time detection device, improving the efficiency and accuracy of the new material detection.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of new material related services, and particularly relates to an online Libs laser real-time detection device. BACKGROUND

[0002] Due to the volume, weight and energy supply of the unmanned aerial vehicle, the performance of the computing device carried by the unmanned aerial vehicle cannot be compared with that of the ground large computing center, however, the data processing process of the Libs technology is relatively complex, from the collection of the plasma spectrum signal generated by the laser induction to the feature extraction and element analysis of the spectrum data, a large amount of computing resources are needed, and the existing Libs laser real-time detection device usually adopts a fixed computing power distribution mode, cannot dynamically adjust the computing power according to the change of the actual detection task, cannot flexibly allocate the power, and causes the waste of resources, and a device capable of optimizing the computing power and allocating the power is needed.

[0003] Chinese patent publication No. CN105223187A discloses a device for measuring heavy metal elements in gas based on Libs, this scheme still has the problems that the computing power cannot be dynamically adjusted according to the change of the actual detection task, the detection result is inaccurate when detecting the new material, the power cannot be flexibly allocated, and the resources are wasted when detecting the new material, and a device capable of dynamically adjusting the computing power and flexibly allocating the power is needed to solve these problems. SUMMARY

[0004] Therefore, the present application provides an online Libs laser real-time detection device to overcome the problems in the prior art that the computing power cannot be dynamically adjusted according to the change of the actual detection task, the detection result is inaccurate when detecting the new material, and the power cannot be flexibly allocated, and the resources are wasted when detecting the new material.

[0005] To achieve the above-mentioned purpose, the present application provides an online Libs laser real-time detection device, comprising:

[0006] a laser generator connected with a data acquisition instrument, an online monitoring system, a sensor node group and a shell, for emitting a laser beam;

[0007] a data acquisition instrument connected with the laser generator and the shell, for collecting target environment data;

[0008] a power supply connected with the online monitoring system, for providing power for the online Libs laser real-time detection device;

[0009] An online monitoring system connected with the laser generator and the power supply, the online monitoring system being connected with the data acquisition instrument and the sensor node group through internal connecting lines, and used for controlling the online Libs laser real-time detection device;

[0010] A sensor node group connected with the laser generator and the shell, the sensor node group including a voltage sensor, a current sensor and a temperature sensor, and used for collecting target device data;

[0011] A shell connected with the laser generator, the data acquisition instrument and the sensor node group, and used for protecting the online Libs laser real-time detection device.

[0012] Further, the online monitoring system includes:

[0013] A data acquisition module used for acquiring target environment data and target device data;

[0014] A data processing module used for performing data processing on the target environment data according to a data processing method to obtain a laser detection result;

[0015] A first detection tuning module used for calculating an algorithm requirement according to the target environment data through an algorithm requirement calculation method, and performing algorithm adjustment on the data processing method according to the algorithm requirement, and used for performing algorithm optimization on the algorithm requirement according to an algorithm requirement optimization method;

[0016] A second detection tuning module used for calculating a total power requirement value according to the target device data through a total power requirement value calculation method, and used for performing secondary algorithm adjustment on the algorithm requirement optimization method according to the total power requirement value through an algorithm optimization adjustment method.

[0017] Further, the data processing module performs data preprocessing on the target environment data according to a data preprocessing strategy, and the data preprocessing strategy includes:

[0018] Step J01, calculating a normalized spectrum data value set Sop={Sop1, Sop2, Sop3,..., Sopi} according to a spectrum data value set s={s1, s2, s3,..., si}, a spectrum data minimum value Smin and a spectrum data maximum value Smax, obtaining a normalized spectrum data value set Sop={Sop1, Sop2, Sop3,..., Sopi}, and setting ;

[0019] Step J02, according to the size of the segmentation window h and the time resolution data set t = {t1, t2, t3,..., tj}, the processed time resolution data set t` = {t`1, t`2, t`3,..., t`j} is calculated, and the processed time resolution data set t` = {t`1, t`2, t`3,..., t`j} is obtained, and the following is set ;

[0020] Step J03, according to the general transverse Mercator grid system, each projection coordinate (am, b m, g m) is obtained according to each spatial position data, and m is the total number of measurement points.

[0021] Step J04, the normalized spectral data value set Sop = {Sop1, Sop2, Sop3,..., Sopi}, the processed time resolution data set t` = {t`1, t`2, t`3,..., t`j} and each projection coordinate (am, b m, g m) are taken as the first target processing data.

[0022] Further, when the data processing module performs data preprocessing on the target environment data according to the data preprocessing strategy, the data processing module constructs a spectral data feature vector model according to a spectral data feature vector model construction method, and the spectral data feature vector model construction method comprises:

[0023] Step K01, the historical spectral data set is divided into 70% spectral training set, 20% spectral verification set and 10% spectral test set;

[0024] Step K02, the spectral parameter initialization is performed on the first convolutional neural network model;

[0025] Step K03, the spectral training set is input into the first convolutional neural network model after parameter initialization for training, and the spectral verification set is input into the first convolutional neural network model after training for spectral parameter optimization, and then the spectral test set is input into the first convolutional neural network model after parameter optimization for testing, and the test accuracy is output;

[0026] Step K04, the first convolutional neural network model after parameter optimization with an accuracy of 90% is output as a spectral data feature vector model.

[0027] Further, the data processing module extracts features from the first target processing data according to the feature extraction strategy, and the feature extraction strategy comprises:

[0028] Step D01, inputting the normalized spectrum data value set Sop={Sop1, Sop2, Sop3,..., Sopi} into the spectrum data feature vector model to obtain a spectrum feature vector set Foh={Foh1, Foh2, Foh3,..., Fohi} output by the spectrum data feature vector model;

[0029] Step D02, inputting the processed time resolution data set t`={t`1, t`2, t`3,..., t`j} into the time resolution feature vector model to obtain a time feature vector set Fom={Fom1, Fom2, Fom3,..., Fomj} output by the time resolution feature vector model;

[0030] Step D03, calculating each space distance dm according to each projection coordinate (αm, βm, γm) and each preset coordinate (αy, βy, γy), and setting ;

[0031] Step D04, taking the spectrum feature vector set Foh={Foh1, Foh2, Foh3,..., Fohi}, the time feature vector set Fom={Fom1, Fom2, Fom3,..., Fomj} and each space distance dm as the second target processing data.

[0032] Further, the data processing module performs data fusion on the second target processing data according to a data fusion strategy, and the data fusion strategy comprises:

[0033] Step E01, performing matrix processing on the spectrum feature vector set Foh={Foh1, Foh2, Foh3,..., Fohi}, the time feature vector set Fom={Fom1, Fom2, Fom3,..., Fomj} and each space distance dm to obtain a first matrix X;

[0034] Step E02, setting a first data sampling point Xzv, wherein z is the zth row in the first matrix X, and v is the vth column in the first matrix X;

[0035] Step E03, calculating each column mean μv and each column standard deviation σv according to the total number of measurement points m and the first data sampling point Xzv to obtain each column mean μv and each column standard deviation σv, and setting ;

[0036] Step E04, calculating a second data sampling point Gz0v0 according to each column mean μv and each column standard deviation σv to obtain the second data sampling point Gz0v0, and setting ;

[0037] Step E05, matrix processing is performed on the second data sampling point Gz0v0 to obtain a second matrix G;

[0038] Step E06, the second matrix G is transposed to obtain a transposed second matrix G';

[0039] Step E07, the covariance matrix C is calculated according to the total number of measurement points m, the second matrix G and the transposed second matrix G', and the covariance matrix C is obtained, and it is set that ;

[0040] Step E08, the covariance matrix C is subjected to eigenvalue decomposition to obtain an eigenvalue;

[0041] Step E09, the eigenvalue is arranged in a preset order to obtain an ordered eigenvalue, and the ordered eigenvalue is subjected to value processing according to a value ratio to obtain a laser detection result.

[0042] Further, the first detection optimization module calculates the computing power requirement according to the target environment data by a computing power requirement calculation method, and the computing power requirement calculation method comprises:

[0043] Step B01, the spectral data computing power requirement Q1 is calculated according to the spectral data amount Iv to obtain the spectral data computing power requirement Q1, and it is set that Q1=4i`;

[0044] Step B02, the time resolution computing power requirement Q2 is calculated according to the time resolution data point jq and the split window size h to obtain the time resolution computing power requirement Q2, and it is set that Q2=3×jq-2×h+1;

[0045] Step B03, the spatial position computing power requirement Q3 is calculated according to the total number of measurement points m to obtain the spatial position computing power requirement Q3, and it is set that Q3=38×n3;

[0046] Step B04, the total computing power requirement Q is calculated according to the spectral data computing power requirement Q1, the time resolution computing power requirement Q2 and the spatial position computing power requirement Q3 to obtain the total computing power requirement Q, and it is set that Q=Q1+Q2+Q3;

[0047] When the first detection optimization module adjusts the computing power of the data processing method according to the computing power requirement, the total computing power requirement Q is compared with a preset computing power requirement Q0, the total computing power requirement is judged according to the comparison result, and the computing power of the data processing method is adjusted according to the judgment result, wherein:

[0048] When Q≤Q0, the first detection optimization module determines that the total computing power requirement is low, and does not adjust the computing power of the data processing method;

[0049] When Q>Q0, the first detection tuning module determines that the total computing power demand is high, adjusts the computing power of the data processing method, sends the second target processing data to the cloud, performs data fusion through the cloud, and obtains the laser detection result.

[0050] Further, the first detection tuning module optimizes the computing power demand according to a computing power demand optimization method, and the computing power demand optimization method comprises:

[0051] Step L01, the data generation rate Vs is calculated according to the data acquisition frequency Cf and the data acquisition amount Ns, and the data generation rate Vs is obtained, and Vs=Cf*Ns is set;

[0052] Step L02, compare the data generation rate Vs with the preset generation rate Vs0, judge the state of the data generation rate Vs according to the comparison result, and update the total computing power demand Q according to the judgment result, wherein:

[0053] When Vs≤Vs0, the first detection tuning module determines that the state of the data generation rate Vs is low rate, and does not update the total computing power demand Q;

[0054] When Vs> Vs0, the first detection tuning module determines that the state of the data generation rate Vs is high rate, updates the total computing power demand Q, sets the computing power update coefficient as ε, sets ε=1.3-0.3e -0.7×(Vs-Vs0) , the updated total computing power demand is Q`, Q`=ε×Q, the updated total computing power demand Q` is compared with the preset computing power demand Q0, and the total computing power demand is re-judged;

[0055] Step L03, compare the parallel task amount Bq with the preset parallel task amount Bq0, judge the situation of the parallel task amount Bq according to the comparison result, and correct the preset generation rate Vs0 according to the judgment result, wherein:

[0056] When Bq≤Bq0, the first detection tuning module determines that the parallel task amount Bq is low task amount, and does not correct the preset generation rate Vs0;

[0057] When Bq>Bq0, the first detection tuning module determines that the parallel task amount Bq is high task amount, corrects the preset generation rate Vs0, sets the rate correction coefficient as θ, sets ; the corrected preset generation rate is Vs0`, Vs0`=Vs0×θ, the preset generation rate Vs0 is replaced by the corrected preset generation rate Vs0`, and the data generation rate Vs is compared with the corrected preset generation rate Vs0` again.

[0058] Further, the second detection and optimization module calculates the total power demand value according to the target device data by a total power demand value calculation method, and the total power demand value calculation method comprises:

[0059] Step P01, calculate the data acquisition required power R1 according to the working voltage Ug, the working current Ig and the data acquisition frequency Cf, obtain the data acquisition required power R1, and set R1=Ug×Ig×Cf;

[0060] Step P02, calculate the data processing required power R2 according to the data processing power Pc and the data processing time tl, obtain the data processing required power R2, and set R2=Pc×tl;

[0061] Step P03, calculate the computing power required power R3 according to the computing power Px and the computing power time Tx, obtain the computing power required power R3, and set R3=Px×Tx;

[0062] Step P04, calculate the power distribution required power R4 according to the control circuit power Pk, the communication frequency nt and the communication time tt, obtain the power distribution required power R4, and set R4=Pk×nt×tt;

[0063] Step P05, calculate the total power demand R according to the data acquisition required power R1, the data processing required power R2, the computing power required power R3 and the power distribution required power R4, obtain the total power demand R, and set R=R1+R2+R3+R4.

[0064] Further, the second detection and optimization module performs secondary computing power adjustment on the computing power demand optimization method according to a computing power optimization adjustment method, and the computing power optimization adjustment method comprises:

[0065] Step U01, compare the total power demand R with the power margin R0, judge the demand condition of the total power demand R according to the comparison result, and perform secondary computing power adjustment on the data processing method and the computing power demand optimization method according to the judgment result, wherein:

[0066] When R≤R0, the second detection and optimization module determines that the demand condition of the total power demand R is low demand, and does not perform secondary computing power adjustment on the data processing method and the computing power demand optimization method;

[0067] When R > R0, the second detection tuning module determines that the demand condition of the total power demand R is high demand, performs secondary computing power adjustment on the computing power demand optimization method, sets the adjusted data collection frequency as Cf`, Cf` = Cf x (R - R0) / R0, replaces the data collection frequency Cf with the adjusted data collection frequency Cf`, re-calculates the data generation rate Vs, sets the adjusted preset parallel task quantity as Bq0`, Bq0` = Bq0 x (1 - (R - R0) / R0), replaces the preset parallel task quantity Bq0 with the adjusted preset parallel task quantity Bq0`, and re-compares the parallel task quantity Bq with the adjusted preset parallel task quantity Bq0`;

[0068] In step U02, the working temperature Wh is compared with the preset working temperature Wh0, the state of the working temperature Wh is judged according to the comparison result, and the power margin R0 is secondarily adjusted in computing power according to the judgment result, wherein:

[0069] When Wh≤Wh0, the second detection tuning module determines that the state of the working temperature Wh is a low temperature state, and does not perform secondary computing power correction on the power margin R0;

[0070] When Wh>Wh0, the second detection tuning module determines that the state of the working temperature Wh is a high temperature state, and performs secondary computing power correction on the power margin R0, sets the corrected power margin as R0`, R0` = R0 x Wh / Wh0, replaces the power margin R0 with the corrected power margin R0`, and re-compares the total power demand R with the corrected power margin R0`;

[0071] In step U03, the heat dissipation efficiency Vv is compared with the preset heat dissipation efficiency Vv0, the heat dissipation degree of the heat dissipation efficiency Vv is judged according to the comparison result, and the preset working temperature Wh0 is secondarily updated in computing power according to the judgment result, wherein:

[0072] When Vv≤Vv0, the second detection tuning module determines that the heat dissipation degree of the heat dissipation efficiency Vv is low, and does not perform secondary computing power update on the preset working temperature Wh0;

[0073] When Vv> Vv0, the second detection tuning module determines that the heat dissipation degree of the heat dissipation efficiency Vv is high, does not perform secondary computing power update on the preset working temperature Wh0, sets the updated preset working temperature as Wh0`, Wh0` = Wh0 x Vv / Vv0, replaces the preset working temperature Wh0 with the updated preset working temperature Wh0`, and re-compares the working temperature Wh with the updated preset working temperature Wh0`.

[0074] Compared with the prior art, the beneficial effects of the present application are that the online monitoring system acquires, processes, calculates and optimizes the computing power and allocates the power through the data acquisition module, the data processing module, the first detection optimization module and the second detection optimization module, so as to standardize the data, maintain the detection stability, improve the detection efficiency and accuracy of new material detection, save computing power and improve resource utilization, and increase the endurance of the online Libs laser real-time detection device, wherein the online monitoring system saves the computing power of the online Libs laser real-time detection device through the first detection optimization module, dynamically adjusts the computing power according to the actual detection task, guarantees accurate computing power calculation, and thus improves the accuracy of the detection result when detecting new materials, the online monitoring system performs flexible power allocation through the second detection optimization module, reduces power consumption, makes the power balance more durable, avoids resource waste, improves resource utilization when detecting new materials, and thus increases the endurance of the online Libs laser real-time detection device and improves the efficiency and accuracy of new material detection. BRIEF DESCRIPTION OF DRAWINGS

[0075] Figure 1 It is a structure schematic view of the online Libs laser real-time detection device used in the embodiment.

[0076] Figure 2 It is a structure schematic view of the online monitoring system of the embodiment. DETAILED DESCRIPTION

[0077] In order to make the purpose and advantages of the present application clearer, the present application will be further described below in conjunction with the embodiments; it should be understood that the specific embodiments described herein are only used to explain the present application, and not to limit the present application.

[0078] The preferred embodiments of the present application will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present application, and are not intended to limit the protection scope of the present application.

[0079] It should be noted that in the description of the present application, the terms "up", "down", "left", "right", "in", "out" and the like indicate the direction or positional relationship of the terms based on the direction or positional relationship shown in the drawings, which is only for the convenience of description, and does not indicate or imply that the device or element must have a particular orientation, be constructed and operated in a particular orientation, therefore it cannot be understood as a limitation of the present application.

[0080] Moreover, it needs to be explained that, in the description of the present application, unless otherwise explicitly specified and limited, the terms "mounting", "connecting", "connecting" should be understood broadly, for example, it can be fixedly connected, or it can be detachably connected, or integrally connected; it can be mechanically connected, or it can be electrically connected; it can be directly connected, or it can be indirectly connected through an intermediate medium, or it can be the communication inside two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0081] Please refer to Figure 1 The structure diagram of the online Libs laser real-time detection device is shown, which comprises:

[0082] The laser generator 1 is connected with the data acquisition instrument 2, the online monitoring system 4, the sensor node group 5 and the shell 6, and is used for emitting laser beams;

[0083] The data acquisition instrument 2 is connected with the laser generator 1 and the shell 6, and is used for collecting target environment data;

[0084] The power supply 3 is connected with the online monitoring system 4, and is used for providing power for the online Libs laser real-time detection device;

[0085] The online monitoring system 4 is connected with the laser generator 1 and the power supply 3, and the online monitoring system 4 is connected with the data acquisition instrument 2 and the sensor node group 5 through internal connecting lines, and is used for controlling the online Libs laser real-time detection device;

[0086] The sensor node group 5 is connected with the laser generator 1 and the shell 6, and the sensor node group comprises a voltage sensor, a current sensor and a temperature sensor, and is used for collecting target device data;

[0087] The shell 6 is connected with the laser generator 1, the data acquisition instrument 2 and the sensor node group 5, and is used for protecting the online Libs laser real-time detection device.

[0088] Specifically, the online Libs laser real-time detection device is applied to the unmanned aerial vehicle Libs laser detection device, and the online Libs laser real-time detection device collects, controls and powers target environment data and target device data through the cooperation of various components, so as to realize accurate detection of samples, ensure stable operation of the device, prolong the service life, and thus improve the overall performance and reliability of the online Libs laser real-time detection device. The online Libs laser real-time detection device emits a laser beam through a laser generator to ensure that the detection process is effectively carried out. The online Libs laser real-time detection device collects target environment data through a data acquisition instrument to ensure that the obtained target environment data truly reflects the information of the sample. The online Libs laser real-time detection device provides power through a power supply to provide stable energy support for the detection process. The online Libs laser real-time detection device controls the online Libs laser real-time detection device through an online monitoring system, dynamically adjusts the computing power according to the changes of the actual detection task, and ensures accurate computing power calculation, thereby improving the accuracy of the detection results when detecting new materials. The online monitoring system also flexibly allocates power through a second detection optimization module to reduce power consumption, so that the power balance is more durable, resource waste is avoided, resource utilization when detecting new materials is improved, detection tasks are efficiently and stably completed, and the efficiency and accuracy of new material detection are improved, thereby improving the detection accuracy when detecting new materials. The online Libs laser real-time detection device collects target device data through a sensor node group to monitor the working state of the device itself in real time and ensure safe and reliable operation of the device. The online Libs laser real-time detection device protects the online Libs laser real-time detection device through a shell to resist interference and damage of external environmental factors on internal components and prolong the service life of the device, thereby ensuring stable operation of the device.

[0089] Specifically, the data acquisition instrument 2 collects target environment data, and the target environment data includes spectral data, time-resolved data and spatial position data.

[0090] Specifically, the spectral data refers to the data obtained by analyzing the specific light radiation generated after the laser beam emitted by the laser generator irradiates the surface of the object. The time-resolved data refers to spectral data associated with time information, which records the characteristic information of the specific light radiation at different times. The spatial position data refers to the data set recording the specific position of each measurement point on the sample when the online Libs laser real-time detection device detects different positions of the sample. The specific position includes the longitude coordinate, latitude coordinate and height of the measurement point. The measurement point refers to the position of the sample detected by the online Libs laser real-time detection device.

[0091] Specifically, the data acquisition instrument 2 determines the types and contents of elements contained in the sample according to specific light radiation generated after the laser beam emitted by the laser generator irradiates the surface of the object, thereby accurately collecting spectral data. The data acquisition instrument 2 records the characteristic information of specific light radiation at different times through time-resolved data, thereby improving the accuracy of data in the time dimension. The data acquisition instrument 2 obtains the distribution of elements in the sample through spatial position data, thereby discovering impurities, defects or component differences in different regions in the sample, and improving detection accuracy.

[0092] Specifically, the sensor node group 5 collects target device data, including working current, working voltage and working temperature. The sensor node group 5 obtains the working current through the current sensor, obtains the working voltage through the voltage sensor, and obtains the working temperature through the temperature sensor.

[0093] Specifically, the working current refers to the current size passed by the online Libs laser real-time detection device during normal operation, the working voltage refers to the power supply voltage required by the online Libs laser real-time detection device during normal operation, and the working temperature refers to the real-time temperature of the online Libs laser real-time detection device during normal operation. The current sensor refers to a device for detecting and measuring current in a circuit, the voltage sensor refers to a device for measuring voltage in a circuit, and the temperature sensor refers to a device for measuring the temperature of an object.

[0094] Specifically, the sensor node group 5 collects working current, working voltage and working temperature through the sensor node group, so as to monitor the running state of the device in real time, provide data reference for subsequent power allocation, and improve the reliability and service life of the device.

[0095] Please refer to Figure 2 The online monitoring system includes:

[0096] The data acquisition module is used to acquire target environment data and target device data.

[0097] The data processing module is used to process the target environment data according to a data processing method to obtain a laser detection result. The data processing module is connected to the data acquisition module.

[0098] The first detection and optimization module is connected with the data processing module, and is configured to calculate the computing power demand according to the target environment data by using a computing power demand calculation method, and to adjust the data processing method according to the computing power demand, and to optimize the computing power demand according to a computing power demand optimization method.

[0099] The second detection and optimization module is connected with the first detection and optimization module, and is configured to calculate the total power demand value according to the target device data by using a total power demand value calculation method, and to perform secondary computing power adjustment on the computing power demand optimization method according to the total power demand value by using a computing power optimization adjustment method.

[0100] Specifically, the online monitoring system is applied to an online Libs laser real-time detection device. The online monitoring system acquires, processes, calculates computing power, optimizes computing power, calculates power, and performs distribution operations on target environment data and target device data through a data acquisition module, a data processing module, a first detection and optimization module, and a second detection and optimization module, so as to standardize the target environment data, maintain detection stability, improve detection efficiency and accuracy, save computing power, improve resource utilization, and increase the endurance of the online Libs laser real-time detection device. The online monitoring system acquires target environment data and target device data in real time through the data acquisition module, thereby improving detection efficiency. The online monitoring system simplifies data while retaining important information through the data processing module, thereby improving detection accuracy and efficiency. The online monitoring system saves computing power of the online Libs laser real-time detection device through the first detection and optimization module, ensures accurate computing power calculation, avoids resource waste, thereby improving detection efficiency. The online monitoring system reduces power consumption through the second detection and optimization module, so that the power balance is more durable, avoids power consumption, improves resource utilization, thereby increasing the endurance of the online Libs laser real-time detection device, and improving the efficiency and accuracy of detection.

[0101] Specifically, the data acquisition module acquires target environment data and target device data. The data acquisition module acquires target environment data through a data acquisition instrument. The data acquisition module acquires target device data through a sensor node group.

[0102] Specifically, the data acquisition module acquires target environment data and target device data in real time, so as to subsequently process the target environment data and the target device data, thereby improving detection efficiency.

[0103] Specifically, the data processing module processes target environment data according to a data processing method. The data processing method includes a data preprocessing strategy, a feature extraction strategy, and a data fusion strategy.

[0104] Specifically, the data processing module performs data preprocessing on the target environment data according to a data preprocessing strategy, and the data preprocessing strategy includes:

[0105] Step J01, according to the spectral data value set s={s1, s2, s3,..., si}, the spectral data minimum value Smin and the spectral data maximum value Smax, the normalized spectral data value set Sop={Sop1, Sop2, Sop3,..., Sopi} is calculated, and the normalized spectral data value set Sop={Sop1, Sop2, Sop3,..., Sopi} is obtained, and it is set that ;

[0106] Step J02, according to the split window size h and the time resolution data set t={t1, t2, t3,..., tj}, the processed time resolution data set t`={t`1, t`2, t`3,..., t`j} is calculated, and the processed time resolution data set t`={t`1, t`2, t`3,..., t`j} is obtained, and it is set that ;

[0107] Step J03, obtaining each projection coordinate (αm, βm, γm) according to each spatial position data according to the universal transverse Mercator grid system;

[0108] Step J04, taking the normalized spectral data value set Sop={Sop1, Sop2, Sop3,..., Sopi}, the processed time resolution data set t`={t`1, t`2, t`3,..., t`j} and each projection coordinate (αm, βm, γm) as the first target processing data.

[0109] Specifically, the set of spectral data values s={s1, s2, s3,..., si} refers to a data set composed of values of each spectral data point, wherein i is the order of the spectral data point, i is a positive integer, the maximum value of i is the total number of spectral data points, s1 is the value of the first spectral data point in the set of spectral data values, s2 is the value of the second spectral data point in the set of spectral data values, s3 is the value of the third spectral data point in the set of spectral data values, si is the value of the i-th spectral data point in the set of spectral data values, the minimum spectral data value Smin refers to the value with the smallest signal intensity in the spectral data, the embodiment does not limit the acquisition method of the minimum spectral data value Smin, and a person skilled in the art can freely choose according to actual needs, as long as the requirement of acquiring the minimum spectral data value Smin is met, for example, the minimum spectral data value Smin is acquired by using spectral analysis software in the embodiment, the maximum spectral data value Smax refers to the value with the largest signal intensity in the spectral data, the embodiment does not limit the acquisition method of the maximum spectral data value Smax, for example, the maximum spectral data value Smax is acquired by using spectral analysis software in the embodiment, the set of normalized spectral data values Sop={Sop1, Sop2, Sop3,..., Sopi} refers to a data set composed of each normalized spectral data value obtained by mapping the set of spectral data values s={s1, s2, s3,..., si} to the [0, 1] interval in step J01, wherein Sop1 is the first normalized spectral data value in the set of normalized spectral data values Sop, Sop2 is the second normalized spectral data value in the set of normalized spectral data values Sop, Sop3 is the third normalized spectral data value in the set of normalized spectral data values Sop, and Sopi is the i-th normalized spectral data value in the set of normalized spectral data values Sop, the split window size h refers to that the split preset number a of data points are selected before and after the current data point to be processed with the current data point to be processed as the center, the split window size h is calculated according to the split preset number a of data points, and h is set to 2a+1, the split preset number a refers to a preset number value, the embodiment does not limit the split preset number a, for example, the split preset number a is set to 2 in the embodiment, then the split window size h is 5, and the time resolution data set t={t1, t2, t3,...tj} is a data set composed of values of each time-resolved data point, wherein j is the order of the time-resolved data point, j is a positive integer, and the maximum value of j is the total number of time-resolved data points, t1 is the value of the first time-resolved data point in the time-resolved data set, t2 is the value of the second time-resolved data point in the time-resolved data set, t3 is the value of the third time-resolved data point in the time-resolved data set, tj is the value corresponding to the jth data point in the time-resolved data set, and the processed time-resolved data set t` = {t`1, t`2, t`3,..., t`j} is a data set composed of values of each processed time-resolved data point obtained by processing the time-resolved data set t = {t1, t2, t3,..., tj} through step J02, wherein t`1 is the value of the first processed time-resolved data point in the processed time-resolved data set, t`2 is the value of the second processed time-resolved data point in the processed time-resolved data set, t`3 is the value of the third processed time-resolved data point in the processed time-resolved data set, and t`j is the value of the jth processed time-resolved data point in the processed time-resolved data set, the universal transverse Mercator grid system is a calculation software taking longitude coordinates, latitude coordinates and height as input data and taking projection coordinates as output data, and the implementation of the universal transverse Mercator grid system is not limited in the embodiment, for example, the universal transverse Mercator grid system is realized by a professional geographic information system software, each spatial position data is spatial position data of a position preset number of measurement points collected by a data collection instrument, the position preset number is a preset value, and the position preset number is not limited in the embodiment, and a person skilled in the art can freely select the position preset number according to actual conditions, as long as the requirement of limiting the position preset number is met, for example, the position preset number is set to 3000, each projection coordinate (αm, βm, γm) is a plane rectangular coordinate representing geographic position information of each measurement point, the earth's surface is divided into 60 projection zones, each zone is numbered from 1 to 60 from west longitude 180°, and each projection zone is numbered from west to east every 6°, the central meridian is taken as the longitudinal axis and the equator is taken as the transverse axis in each projection zone, the intersection of the central meridian and the equator is taken as the origin, the longitudinal axis is positive to the north and negative to the south, and the transverse axis is positive to the east and negative to the west, wherein αm is a coordinate value representing the north-south direction, βm is a coordinate value representing the east-west direction, γm is the projection zone number, and 0m is the order of the projection coordinate.

[0110] Specifically, the data processing module performs data preprocessing on the target environment data to standardize each data point in the target environment data, improve data quality, data consistency and comparability, and thus improve detection efficiency.

[0111] Specifically, when the data processing module performs data preprocessing on the target environment data according to the data preprocessing strategy, the data processing module constructs a spectral data feature vector model according to a spectral data feature vector model construction method, the spectral data feature vector model construction method comprising:

[0112] Step K01, dividing the historical spectral data set into a 70% spectral training set, a 20% spectral validation set, and a 10% spectral test set;

[0113] Step K02, performing spectral parameter initialization on the first convolutional neural network model;

[0114] Step K03, inputting the spectral training set into the first convolutional neural network model after parameter initialization for training, inputting the spectral validation set into the first convolutional neural network model after training for spectral parameter optimization, and inputting the spectral test set into the first convolutional neural network model after parameter optimization for testing, and outputting the test accuracy rate;

[0115] Step K04, outputting the first convolutional neural network model after parameter optimization with an accuracy rate of 90% as the spectral data feature vector model;

[0116] When the data processing module performs data preprocessing on the target environment data according to the data preprocessing strategy, the data processing module constructs a time-resolved feature vector model according to a time-resolved feature vector model construction method, the time-resolved feature vector model construction method comprising:

[0117] Step C01, dividing the historical time-resolved data set into a 70% time training set, a 20% time validation set, and a 10% time test set;

[0118] Step C02, performing time parameter initialization on the second convolutional neural network model;

[0119] Step C03, inputting the time training set into the second convolutional neural network model after parameter initialization for training, inputting the time validation set into the second convolutional neural network model after training for time parameter optimization, and inputting the time test set into the second convolutional neural network model after parameter optimization for testing, and outputting the test accuracy rate;

[0120] Step C04, outputting the second convolutional neural network model after parameter optimization with an accuracy rate of 90% as the time-resolved feature vector model.

[0121] In particular, the historical spectrum data set refers to historical normalized spectrum data values and spectrum feature vectors corresponding to the historical normalized spectrum data values, the normalized spectrum data values are taken as input data of a spectrum data feature vector model, and the spectrum feature vectors are taken as output data of the spectrum data feature vector model, the spectrum training set refers to a data set in the historical spectrum data set for training the first convolutional neural network model, the spectrum verification set refers to a data set for adjusting parameters of the first convolutional neural network model in a training process, the spectrum test set refers to a data set for evaluating final performance of the first convolutional neural network model after the first convolutional neural network model completes spectrum parameter optimization, the first convolutional neural network model refers to a statistical model for describing a linear relationship between the normalized spectrum data values and the spectrum feature vectors, the spectrum parameter initialization refers to a process of setting initial values of spectrum weights and spectrum biases of the first convolutional neural network model when the spectrum data feature vector model is constructed, the spectrum weights refer to parameters for measuring connection strength between neurons in the first convolutional neural network model, and the spectrum biases refer to parameters for output of a neuron in the first convolutional neural network model when input is zero, the embodiment is not limited to the spectrum parameter initialization mode, and a person skilled in the related art can freely select according to actual needs, as long as the requirement of setting initial values of the spectrum weights and the spectrum biases of the first convolutional neural network model is met, for example, random initialization, the spectrum parameter optimization refers to a process of adjusting the spectrum weights and the spectrum biases of the first convolutional neural network model to make performance of the first convolutional neural network model on the spectrum verification set optimal when the spectrum verification set is used to evaluate the trained first convolutional neural network model, the embodiment is not limited to the way of adjusting the spectrum weights and the spectrum biases of the first convolutional neural network model, and a person skilled in the related art can freely select according to actual needs, as long as the requirement of adjusting the spectrum weights and the spectrum biases of the first convolutional neural network model to make performance of the first convolutional neural network model on the spectrum verification set optimal is met, for example, adjustment by a calculation software, the historical time-resolved data set refers to historical processed time-resolved data and time feature vectors corresponding to the historical processed time-resolved data, the processed time-resolved data are taken as input data of a time-resolved feature vector model, and the time feature vectors are taken as output data of the time-resolved feature vector model, the time training set refers to a data set in the historical time-resolved data set for training the second convolutional neural network model, the time verification set refers to a data set for adjusting parameters of the second convolutional neural network model in a training process, the time test set refers to a data set for evaluating final performance of the second convolutional neural network model after the second convolutional neural network model completes time parameter optimization, and the second convolutional neural network model refers to a statistical model for describing a linear relationship between the processed time-resolved data and the time feature vectors.The time parameter initialization refers to the process of setting initial values for the time weights and time biases of the second convolutional neural network model when constructing the time-resolved feature vector model. The present embodiment does not limit the time parameter initialization method, and the related technical personnel can freely choose according to the actual needs, as long as the initial value setting requirement of the time weights and time biases of the second convolutional neural network model is met, such as random initialization. The time parameter optimization refers to the process of adjusting the time weights and time biases of the second convolutional neural network model to make the performance of the second convolutional neural network model on the time validation set optimal when evaluating the trained second convolutional neural network model using the time validation set. The present embodiment does not limit the adjustment method of the spectral weights and spectral biases of the second convolutional neural network model, and the related technical personnel in the field can freely choose according to the actual needs, as long as the adjustment requirement of the time weights and time biases of the second convolutional neural network model to make the performance of the second convolutional neural network model on the spectral validation set optimal is met, such as adjustment by calculation software. The time weight refers to the parameter in the second convolutional neural network model for measuring the connection strength between neurons. The time bias refers to the parameter of the neuron output when the input is zero.

[0122] Specifically, the data processing module constructs a spectral data feature vector model and a time-resolved feature vector model to facilitate subsequent convenient and accurate acquisition of each feature vector, thereby improving the detection efficiency.

[0123] Specifically, the data processing module extracts features from the first target processing data according to a feature extraction strategy. The feature extraction strategy includes:

[0124] Step D01, inputting the normalized spectral data value set Sop={Sop1, Sop2, Sop3,..., Sopi} into the spectral data feature vector model to obtain the spectral feature vector set Foh={Foh1, Foh2, Foh3,..., Fohi} output by the spectral data feature vector model;

[0125] Step D02, inputting the processed time-resolved data set t`={t`1, t`2, t`3,..., t`j} into the time-resolved feature vector model to obtain the time feature vector set Fom={Fom1, Fom2, Fom3,..., Fomj} output by the time-resolved feature vector model;

[0126] Step D03, calculating each spatial distance dm according to each projection coordinate (αm, βm, γm) and each preset coordinate (αy, βy, γy), and setting ;

[0127] Step D04, the spectral feature vector set Foh = {Foh1, Foh2, Foh3, …, Fohi}, the time feature vector set Fom = {Fom1, Fom2, Fom3, …, Fomj} and each spatial distance dm are taken as the second target processing data.

[0128] Specifically, the spectral feature vector set Foh = {Foh1, Foh2, Foh3, …, Fohi} refers to a data set composed of vector values obtained by taking the normalized spectral data value set Sop = {Sop1, Sop2, Sop3, …, Sopi} as input data of a spectral data feature vector model, to represent the feature information corresponding to the normalized spectral data value set Sop = {Sop1, Sop2, Sop3, …, Sopi}, wherein Foh1 is the first vector value in the spectral feature vector set Foh, Foh2 is the second vector value in the spectral feature vector set Foh, Foh3 is the third vector value in the spectral feature vector set Foh, and Fohi is the i-th vector value in the spectral feature vector set Foh. The time feature vector set Fom = {Fom1, Fom2, Fom3, …, Fomj} refers to a data set composed of vector values obtained by taking the processed time resolution data set t` = {t`1, t`2, t`3, …, t`j} as input data of a time resolution feature vector model, to represent the feature information corresponding to the processed time resolution data set t` = {t`1, t`2, t`3, …, t`j}, wherein Fom1 refers to the first vector value in the time feature vector set Fom, Fom2 refers to the second vector value in the time feature vector set Fom, Fom3 refers to the third vector value in the time feature vector set Fom, and Fomj refers to the j-th vector value in the time feature vector set Fom. Each preset coordinate (αy, βy, γy) refers to a preset measurement point position coordinate, which is not limited in the embodiment and can be freely selected by a person skilled in the art according to actual needs, as long as it meets the requirement of calculating each spatial distance dm. For example, αy = 50000, βy = 400000, and γy = 32N. Each spatial distance dm refers to the distance between each projection coordinate (αm, βm, γm) and each preset coordinate (αy, βy, γy).

[0129] Specifically, the data processing module extracts features from the first target processing data to reduce data dimension and data analysis difficulty, thereby obtaining vector features represented by the data and improving detection accuracy.

[0130] Specifically, the data processing module performs data fusion on the second target processing data according to a data fusion strategy, and the data fusion strategy includes:

[0131] Step E01, matrix processing is performed on the spectral feature vector set Foh={Foh1, Foh2, Foh3,..., Fohi}, the time feature vector set Fom={Fom1, Fom2, Fom3,..., Fomj} and each spatial distance dm, to obtain a first matrix X;

[0132] Step E02, a first data sampling point Xzv is set, wherein z is the zth row in the first matrix X, and v is the vth column in the first matrix X;

[0133] Step E03, according to the total number of measurement points m and the first data sampling point Xzv, each column mean μv and each column standard deviation σv are calculated, to obtain each column mean μv and each column standard deviation σv, and set ;

[0134] Step E04, according to each column mean μv and each column standard deviation σv, a second data sampling point Gz0v0 is calculated, to obtain the second data sampling point Gz0v0, and set ;

[0135] Step E05, matrix processing is performed on the second data sampling point Gz0v0, to obtain a second matrix G;

[0136] Step E06, the second matrix G is transposed to obtain a transposed second matrix G`;

[0137] Step E07, according to the total number of measurement points m, the second matrix G and the transposed second matrix G`, a covariance matrix C is calculated, to obtain the covariance matrix C, and set ;

[0138] Step E08, eigenvalue decomposition is performed on the covariance matrix C, to obtain eigenvalues;

[0139] Step E09, the eigenvalues are arranged in a preset order to obtain sorted eigenvalues, and the sorted eigenvalues are processed according to a value ratio to obtain a laser detection result.

[0140] In particular, the matrixing process refers to arranging different types of data vectors in rows and columns so that they have specific positions in a matrix, such as setting the total number of normalized spectral data values in the spectral feature vector set Foh = {Foh1, Foh2, Foh3,..., Fohi} as ik, the total number of processed time-resolved data in the time feature vector set Fom = {Fom1, Fom2, Fom3,..., Fomj} as jk, and the total number of measurement points as mk, then the first matrix X is mk x (ik + jk + 1), which refers to the data structure obtained by matrixing the data points in the second target processing data, the first data sampling point Xzv refers to the data point in the zth row and the vth column in the first matrix X, where z is the order of the number of rows in the first matrix X, z is a positive integer, the maximum value of z is the total number of rows in the first matrix X, v is the order of the number of columns in the first matrix X, v is a positive integer, the maximum value of v is the total number of columns in the first matrix X, the column mean μv refers to the average value of the vth column in the first matrix X, the column standard deviation σv refers to a statistical quantity that measures the degree of dispersion of the data in the vth column in the first matrix X, the second data sampling point Gz0v0 refers to the data point in the z0th row and the v0th column in the second matrix G, where z0 is the order of the number of rows in the second matrix G, z0 is a positive integer, the maximum value of z0 is the total number of rows in the second matrix G, v0 is the order of the number of columns in the second matrix G, v0 is a positive integer, the maximum value of v0 is the total number of columns in the second matrix G, the second matrix G refers to the data structure obtained by matrixing the second data sampling point Gz0v0, the transpose refers to the operation of transposing a matrix, such as exchanging the rows and columns in the second matrix G, the transposed second matrix G' refers to the new matrix obtained by transposing the second matrix G, the covariance matrix C refers to a matrix used to measure the covariance relationship between variables, such as describing the correlation between spectral feature vectors, time feature vectors, and spatial distances, the eigenvalue decomposition refers to a method of decomposing a matrix into eigenvalues and eigenvectors, such as calculating eigenvalues according to the covariance matrix C and the identity matrix IP, setting The unit matrix IP refers to a pre-set standard matrix, and the embodiment does not limit the unit matrix IP, and a person skilled in the art can freely select according to actual needs, as long as the requirement of calculating the eigenvalue is met, for example, the unit matrix IP is set as a 3*3 matrix, the eigenvalue refers to data obtained by performing eigenvalue decomposition on the covariance matrix C to measure the importance of data characteristics, the larger the eigenvalue, the greater the importance of data, the preset order refers to a pre-set arrangement order, and the embodiment does not limit the specific arrangement manner of arranging the eigenvalue according to the preset order, and a person skilled in the art can set it according to actual needs, for example, the eigenvalue is arranged in descending order according to the preset order, the sorted eigenvalue refers to a numerical sequence obtained by arranging the eigenvalue according to the preset order, the value number ratio refers to a percentage of the value in the sorted eigenvalue, and the embodiment does not limit the value number, for example, the value number is set as 80%, and the value processing refers to a process of taking the value according to the value ratio, for example, the first 80% data of the sorted eigenvalue is extracted, the last 20% data is removed, and the first 80% data of the sorted eigenvalue is taken as the laser detection result.

[0141] Specifically, the data processing module simplifies the vector data by performing matrix processing on the second target processing data, thereby facilitating subsequent data processing. The data processing module obtains the second matrix G by calculating the column mean and standard deviation of the first data sampling point Xzv, so as to convert different dimensional features in the second target processing data into data with the same scale, thereby improving data accuracy. The data processing module also analyzes the relationship between different dimensions of data and observes the correlation between different features by transposing the second matrix G, thereby improving the accuracy of data information. The data processing module arranges and takes the eigenvalue to extract data with high importance, so that the data is simplified while the information in the data is accurately retained, thereby improving the accuracy of the data.

[0142] Specifically, the first detection optimization module calculates the computing power requirement according to the target environment data by using a computing power requirement calculation method, and the computing power requirement calculation method includes:

[0143] Step B01, calculating the spectral data computing power requirement Q1 according to the spectral data quantity Iv to obtain the spectral data computing power requirement Q1, and setting Q1=4i`;

[0144] Step B02, calculating the time resolution computing power requirement Q2 according to the time resolution data point jq and the split window size h to obtain the time resolution computing power requirement Q2, and setting Q2=3*jq-2*h+1;

[0145] Step B03: Calculate the spatial location computing power requirement Q3 based on the total number of measurement points m to obtain the spatial location computing power requirement Q3, and set Q3 = 38 × n3;

[0146] Step B04: Calculate the total computing power requirement Q based on the spectral data computing power requirement Q1, the time-resolved computing power requirement Q2, and the spatial position computing power requirement Q3 to obtain the total computing power requirement Q, and set Q = Q1 + Q2 + Q3;

[0147] When the first detection and tuning module adjusts the computing power of the data processing method according to the computing power demand, the total computing power demand Q is compared with the preset computing power demand Q0, the total computing power demand is judged according to the comparison result, and the computing power of the data processing method is adjusted according to the judgment result, wherein:

[0148] When Q≤Q0, the first detection and tuning module determines that the total computing power demand is low and does not adjust the computing power of the data processing method;

[0149] When Q>Q0, the first detection tuning module determines that the total computing power demand is high, adjusts the computing power of the data processing method, sends the second target processing data to the cloud, performs data fusion through the cloud, and obtains the laser detection results.

[0150] Specifically, the spectral data volume Iv refers to the total number of data points of spectral data in the target environment data, the spectral data computing power requirement Q1 refers to the computing power required for data processing of the spectral data volume Iv, the time-resolved data points jq refers to the total number of data points of time-resolved data in the target environment data, the time-resolved computing power requirement Q2 refers to the computing power required for data processing of the time-resolved data points jq, and the spatial position computing power requirement Q3 refers to the computing power required for data processing of each projection coordinate.

[0151] Specifically, the first detection tuning module calculates the computing power requirements to facilitate subsequent optimization of the computing power requirements and flexibly adjust the computing power, thereby improving detection efficiency.

[0152] Specifically, the first detection and tuning module optimizes the computing power requirement according to a computing power requirement optimization method, and the computing power requirement optimization method includes:

[0153] Step L01, calculating the data generation rate Vs according to the data acquisition frequency Cf and the data acquisition amount Ns, obtaining the data generation rate Vs, and setting Vs = Cf × Ns;

[0154] Step L02: Compare the data generation rate Vs with the preset generation rate Vs0, determine the state of the data generation rate Vs based on the comparison result, and update the total computing power requirement Q based on the determination result, where:

[0155] When Vs≤Vs0, the first detection and tuning module determines that the state of the data generation rate Vs is low rate, and does not update the total computing power demand Q;

[0156] When Vs> Vs0, the first detection and tuning module determines that the state of the data generation rate Vs is high rate, updates the total computing power demand Q, sets the computing power update coefficient as ε, sets ε = 1.3-0.3e -0.7×(Vs-Vs0) , the updated total computing power demand is Q`, Q` = ε × Q, compares the updated total computing power demand Q` with the preset computing power demand Q0, and rejudges the total computing power demand;

[0157] Step L03, compares the parallel task amount Bq with the preset parallel task amount Bq0, judges the situation of the parallel task amount Bq according to the comparison result, and modifies the preset generation rate Vs0 according to the judgment result, wherein:

[0158] When Bq≤Bq0, the first detection and tuning module determines that the situation of the parallel task amount Bq is low task amount, and does not modify the preset generation rate Vs0;

[0159] When Bq> Bq0, the first detection and tuning module determines that the situation of the parallel task amount Bq is high task amount, modifies the preset generation rate Vs0, sets the rate modification coefficient as θ, sets ; the modified preset generation rate is Vs0`, Vs0` = Vs0 × θ, the preset generation rate Vs0 is replaced by the modified preset generation rate Vs0`, and the data generation rate Vs is compared with the modified preset generation rate Vs0` again.

[0160] In particular, the preset computing power requirement Q0 refers to a preset value for judging the requirement of the total computing power requirement Q. The present embodiment does not limit the preset computing power requirement Q0, and a person skilled in the relevant art can freely choose according to actual requirements, as long as the requirement of limiting the preset computing power requirement Q0 is met. For example, the preset computing power requirement Q0 is set to 800 KFLOPS in the present embodiment. The cloud refers to a remote server cluster based on the Internet for data fusion storage of the second target processing data in the data processing module. The present embodiment does not limit the selection of the cloud, and a person skilled in the relevant art can freely choose according to actual requirements, as long as the requirement of data fusion of the second target processing data is met. For example, the Internet. The total computing power requirement condition refers to the degree of the total computing power requirement judged by the preset computing power requirement Q0. The total computing power requirement condition includes high requirement and low requirement. The data acquisition frequency Cf refers to the number of times of data acquisition by the data acquisition instrument of the online Libs laser real-time detection device within a preset time. The present embodiment does not limit the acquisition method of the data acquisition frequency Cf, and a person skilled in the relevant art can freely choose according to actual requirements, as long as the requirement of acquiring the data acquisition frequency Cf is met. For example, the acquisition is performed by the online Libs laser real-time detection device specification in the present embodiment. The preset time refers to a preset length of time. The present embodiment does not limit the preset time, and a person skilled in the relevant art can freely choose according to actual requirements, as long as the requirement of limiting the preset time is met. For example, the preset time is set to 1 hour. The data acquisition amount Ns refers to the total amount of data acquired by the online Libs laser real-time detection device in a single data acquisition. The present embodiment does not limit the acquisition method of the data acquisition amount Ns, and a person skilled in the relevant art can freely choose according to actual requirements, as long as the requirement of acquiring the data acquisition amount Ns is met. For example, a data monitoring software is installed. The data generation rate Vs refers to the rate of data acquisition by the online Libs laser real-time detection device within a preset time, which is used to represent the speed of generating laser detection results. The preset generation rate Vs0 refers to a preset value for judging the state of the data generation rate Vs. The present embodiment does not limit the preset generation rate Vs0, and a person skilled in the relevant art can freely choose according to actual requirements, as long as the requirement of limiting the preset generation rate Vs0 is met. For example, Vs0 is set to 3 MB / s. The state of the data generation rate Vs refers to the speed of the data generation rate judged by the preset generation rate Vs0. The state of the data generation rate Vs includes low rate and high rate. The parallel task amount Bq refers to the number of detection tasks simultaneously running by the online Libs laser real-time detection device. The present embodiment does not limit the acquisition method of the parallel task amount Bq,The person skilled in the art can freely choose according to the actual needs, as long as the demand for obtaining the parallel task amount Bq is met, such as the online Libs laser real-time detection device specification in this embodiment, the preset parallel task amount Bq0 is a preset value for judging the situation of the parallel task amount Bq, and the preset parallel task amount Bq0 is not limited in this embodiment. The person skilled in the art can freely choose according to the actual needs, as long as the demand for limiting the preset parallel task amount Bq0 is met, such as the embodiment Bq0=5, the situation of the parallel task amount Bq refers to the degree of parallel task load judged by the preset parallel task amount Bq0, and the situation of the parallel task amount Bq includes low task amount and high task amount.

[0161] Specifically, the first detection optimization module judges the demand situation of the total computing power demand Q, so that when the total computing power demand Q is high demand, the data fusion process is calculated by the cloud, thereby saving the computing power of the online Libs laser real-time detection device, ensuring the detection effect, the first detection optimization module judges the state of the data generation rate Vs, so that the total computing power demand Q increases with the increase of the data generation rate Vs, avoiding the inaccuracy of the computing power demand Q when the data generation rate Vs is too high, thereby timely adjusting the data processing method, maintaining the detection stability of the online Libs laser real-time detection device, the first detection optimization module judges the situation of the parallel task amount Bq, so that the preset generation rate Vs0 decreases with the increase of the parallel task amount Bq, avoiding the inaccurate state judgment of the data generation rate Vs when the parallel task amount Bq is too much, thereby ensuring the accurate computing power calculation of the online Libs laser real-time detection device, avoiding resource waste, and improving the accuracy and detection efficiency of the detection result.

[0162] Specifically, the second detection optimization module calculates the total power demand value according to the target device data by the total power demand value calculation method, and the total power demand value calculation method includes:

[0163] Step P01, calculating the data acquisition required power R1 according to the working voltage Ug, the working current Ig and the data acquisition frequency Cf, obtaining the data acquisition required power R1, and setting R1=Ug×Ig×Cf;

[0164] Step P02, calculating the data processing required power R2 according to the data processing power Pc and the data processing time tl, obtaining the data processing required power R2, and setting R2=Pc×tl;

[0165] Step P03, according to the computing power Px and the computing power calculation time Tx, the required power R3 for the computing power analysis is calculated, the required power R3 for the computing power analysis is obtained, and R3 = Px × Tx is set;

[0166] Step P04, according to the control circuit power Pk, the communication frequency nt and the communication time tt, the required power R4 for power distribution is calculated, the required power R4 for power distribution is obtained, and R4 = Pk × nt × tt is set;

[0167] Step P05, according to the data acquisition required power R1, the data processing required power R2, the computing power analysis required power R3 and the power distribution required power R4, the total power demand R is calculated, the total power demand R is obtained, and R = R1 + R2 + R3 + R4 is set.

[0168] Specifically, the data acquisition required power R1 refers to the power value required for data acquisition, the data processing power Pc refers to the data amount processed by the data processing module within a preset processing time when performing data processing, which is used to measure the processing capacity and efficiency of the data processing module, and the preset processing time is not limited in the embodiment, for example, the preset processing time is set to 20 min, the data processing time tl refers to the time required for measuring a single measurement point to obtain target environmental data according to the data processing power Pc, the data processing required power R2 refers to the power required for data processing by the data processing module, the computing power Px refers to the data amount calculated by the first detection and optimization module within a preset calculation time when calculating the computing power demand, and the preset calculation time is not limited in the embodiment, for example, the preset calculation time is set to 10 min, the computing power calculation time Tx refers to the time for the first detection and optimization module to calculate the computing power demand of the target environmental data, the computing power analysis required power R3 refers to the power required by the first detection and optimization module, the control circuit power Pk refers to the power consumed by the control circuit of the online Libs laser real-time detection device during operation, the communication times nt refers to the number of times that the online Libs laser real-time detection device transmits the laser detection result to the cloud, the communication time tt refers to the time for the online Libs laser real-time detection device to transmit the laser detection result to the cloud, and the power allocation required power R4 refers to the power consumed by the power allocation and data upload of the online Libs laser real-time detection device. The data processing power Pc, the data processing time tl, the computing power Px, the computing power calculation time Tx, the control circuit power Pk, the communication times nt and the communication time tt are not limited in the embodiment, and a person skilled in the art can freely select them according to actual needs, as long as the data processing power Pc and the data processing time tl are obtained, for example, the online Libs laser real-time detection device specification is used to obtain them, and the total power demand R refers to the total power required for the online monitoring system to complete control.

[0169] Specifically, the second detection and optimization module calculates the total power demand R to adjust the power subsequently, so as to improve the resource utilization rate.

[0170] Specifically, the second detection and optimization module adjusts the computing power demand optimization method again according to the computing power optimization adjustment method, and the computing power optimization adjustment method comprises:

[0171] Step U01, comparing the total power demand R with the power margin R0, judging the demand condition of the total power demand R according to the comparison result, and adjusting the data processing method and the computing power demand optimization method again according to the judgment result, wherein:

[0172] When R≤R0, the second detection and tuning module determines that the demand situation of the total power demand R is low demand, and does not perform secondary power adjustment on the data processing method and the power demand optimization method;

[0173] When R>R0, the second detection and tuning module determines that the demand situation of the total power demand R is high demand, performs secondary power adjustment on the power demand optimization method, sets the adjusted data collection frequency as Cf`, Cf`=Cf×(R-R0) / R0, replaces the data collection frequency Cf with the adjusted data collection frequency Cf`, re-calculates the data generation rate Vs, sets the adjusted preset parallel task quantity as Bq0`, Bq0`=Bq0×(1-(R-R0) / R0), replaces the preset parallel task quantity Bq0 with the adjusted preset parallel task quantity Bq0`, and re-compares the parallel task quantity Bq with the adjusted preset parallel task quantity Bq0`;

[0174] Step U02, compare the working temperature Wh with the preset working temperature Wh0, judge the state of the working temperature Wh according to the comparison result, and perform secondary power correction on the power margin R0 according to the judgment result, wherein:

[0175] When Wh≤Wh0, the second detection and tuning module determines that the state of the working temperature Wh is a low temperature state, and does not perform secondary power correction on the power margin R0;

[0176] When Wh>Wh0, the second detection and tuning module determines that the state of the working temperature Wh is a high temperature state, and performs secondary power correction on the power margin R0, sets the corrected power margin as R0`, R0`=R0×Wh / Wh0, replaces the power margin R0 with the corrected power margin R0`, and re-compares the total power demand R with the corrected power margin R0`;

[0177] Step U03, compare the heat dissipation efficiency Vv with the preset heat dissipation efficiency Vv0, judge the heat dissipation degree of the heat dissipation efficiency Vv according to the comparison result, and perform secondary power update on the preset working temperature Wh0 according to the judgment result, wherein:

[0178] When Vv≤Vv0, the second detection and tuning module determines that the heat dissipation degree of the heat dissipation efficiency Vv is low, and does not perform secondary power update on the preset working temperature Wh0;

[0179] When Vv > Vv0, the second detection tuning module determines that the heat dissipation degree of the heat dissipation efficiency Vv is high, does not perform secondary computing power update on the preset working temperature Wh0, sets the updated preset working temperature as Wh0`, Wh0` = Wh0 x Vv / Vv0, replaces the preset working temperature Wh0 with the updated preset working temperature Wh0`, and recompares the working temperature Wh with the updated preset working temperature Wh0`.

[0180] Specifically, the power balance R0 refers to the power contained in the power supply at the current moment, the preset working temperature Wh0 refers to a preset value for judging the state of the working temperature Wh, the preset working temperature Wh0 is not limited in the embodiment, and a person skilled in the art can freely select according to actual needs, as long as the requirement of limiting the preset working temperature Wh0 is met, for example, the embodiment sets Wh0 = 25℃, the heat dissipation efficiency Vv refers to the ability of the online Libs laser real-time detection device to dissipate the heat generated inside to the surrounding environment, the embodiment does not limit the acquisition method of the heat dissipation efficiency Vv, for example, the embodiment is acquired through the online Libs laser real-time detection device specification, the preset heat dissipation efficiency Vv0 refers to a preset value for judging the heat dissipation degree of the heat dissipation efficiency Vv, the preset heat dissipation efficiency Vv0 is not limited in the embodiment, and a person skilled in the art can freely select according to actual needs, as long as the requirement of limiting the preset heat dissipation efficiency Vv0 is met, for example, the embodiment sets Vv0 = 30%, the demand situation of the total power demand R refers to the demand degree of the total power through the power balance R0, the demand situation of the total power demand R includes that the demand situation of the total power demand R is low demand and the demand situation of the total power demand R is high demand, the state of the working temperature Wh refers to the high-low situation of the working temperature through the preset working temperature Wh0, the state of the working temperature Wh includes that the state of the working temperature Wh is a low-temperature state and the state of the working temperature Wh is a high-temperature state, the heat dissipation degree of the heat dissipation efficiency Vv refers to the heat dissipation ability through the preset heat dissipation efficiency Vv0, and the heat dissipation degree of the heat dissipation efficiency Vv includes that the heat dissipation degree of the heat dissipation efficiency Vv is low and the heat dissipation degree of the heat dissipation efficiency Vv is high.

[0181] Specifically, the second detection and optimization module judges the demand situation of the total power demand R, so that when the total power demand R is high demand, the data collection frequency Cf and the preset parallel task quantity Bq0 in the computing power demand optimization method are adjusted, so that the data collection frequency Cf decreases with the increase of the total power demand R, and the preset parallel task quantity Bq0 decreases with the increase of the total power demand R, thereby reducing power consumption, saving power margin, avoiding resource waste, the second detection and optimization module judges the state of the working temperature Wh, so that the power margin R0 increases with the increase of the working temperature Wh, when the working temperature Wh is high, the power margin R0 is more durable, avoids inaccurate judgment of the power margin R0 when the working temperature Wh is high, thereby improving the comprehensiveness and accuracy of detection, the second detection and optimization module judges the heat dissipation degree of the heat dissipation efficiency Vv, so that the working temperature Wh0 increases with the increase of the heat dissipation efficiency Vv, avoids inaccurate judgment of the working temperature Wh0 when the heat dissipation degree is high, thereby improving the detection efficiency, saving power, and increasing the endurance of the online Libs laser real-time detection device.

[0182] So far, the technical scheme of the present application has been described in combination with the preferred embodiments shown in the drawings, but those skilled in the art can easily understand that the protection scope of the present application is obviously not limited to these specific embodiments. Those skilled in the art can make equivalent changes or replacements to related technical features without departing from the principles of the present application, and the technical schemes after these changes or replacements will fall within the protection scope of the present application.

Claims

1. A device for online Libs laser real-time detection, characterized in that: The device comprises: A laser generator, which is connected to the data acquisition instrument, the online monitoring system, the sensor node group and the housing, and is used to emit a laser beam; A data acquisition instrument connected to the laser generator and the housing, for acquiring target environment data, wherein the target environment data includes spectral data, time-resolved data, and spatial position data; A power supply connected to the online monitoring system for providing power to the online Libs laser real-time detection device; An online monitoring system connected to the laser generator and the power supply, and connected to the data acquisition instrument and the sensor node group via internal connecting lines, for controlling the online Libs laser real-time detection device; A sensor node group connected to the laser generator and the housing, the sensor node group including a voltage sensor, a current sensor, and a temperature sensor for collecting target device data, the target device data including operating current, operating voltage, and operating temperature; A housing connected to the laser generator, the data acquisition instrument and the sensor node group, and used to protect the online Libs laser real-time detection device; The online monitoring system comprises: A data acquisition module, used to acquire target environment data and target device data; A data processing module is used to process the target environment data according to the data processing method to obtain the laser detection results; A first detection and tuning module is used to calculate the computing power requirement based on the target environment data using a computing power requirement calculation method, adjust the data processing method based on the computing power requirement, and optimize the computing power requirement based on the computing power requirement optimization method; A second detection and tuning module is used to calculate the total power demand value based on the target device data using the total power demand value calculation method, and is also used to perform a secondary computing power adjustment on the computing power demand optimization method based on the total power demand value using the computing power optimization adjustment method; The first detection and tuning module calculates the computing power requirement according to the target environment data using a computing power requirement calculation method, wherein the computing power requirement calculation method includes: Step B01, calculate the spectral data computing power demand Q1 according to the spectral data volume Iv, obtain the spectral data computing power demand Q1, set Q1 = 4 × lv; Step B02, calculate the time-resolved computing power requirement Q2 based on the time-resolved data point jq and the segmentation window size h, obtain the time-resolved computing power requirement Q2, and set Q2=3×(jq-2)×h+1; Step B03: Calculate the spatial location computing power requirement Q3 based on the total number of measurement points m to obtain the spatial location computing power requirement Q3, and set Q3=38×m; Step B04: Calculate the total computing power requirement Q based on the spectral data computing power requirement Q1, the time-resolved computing power requirement Q2, and the spatial position computing power requirement Q3 to obtain the total computing power requirement Q, and set Q = Q1 + Q2 + Q3; The first detection and tuning module optimizes the computing power requirement according to a computing power requirement optimization method, wherein the computing power requirement optimization method includes: Step L01, based on the data acquisition frequency Cf and the amount of data collected Ns, the data generation rate Vs is calculated to obtain the data generation rate Vs, and Vs = Cf × Ns is set; Step L02: Compare the data generation rate Vs with the preset generation rate Vs0, determine the state of the data generation rate Vs based on the comparison result, and update the total computing power requirement Q based on the determination result, where: When Vs≤Vs0, the first detection and tuning module determines that the data generation rate Vs is a low rate and does not update the total computing power demand Q; When Vs>Vs0, the first detection and tuning module determines that the data generation rate Vs is at a high rate, updates the total computing power demand Q, and sets the computing power update coefficient to ,set up , the total computing power requirement after the update is Q`, , compare the updated total computing power requirement Q' with the preset computing power requirement Q0, and re-evaluate the total computing power requirement; Step L03: Compare the parallel task quantity Bq with the preset parallel task quantity Bq0, judge the situation of the parallel task quantity Bq based on the comparison result, and make a computing power correction to the preset generation rate Vs0 based on the judgment result, where: When Bq≤Bq0, the first detection and tuning module determines that the parallel task amount Bq is a low task amount and does not perform computing power correction on the preset generation rate Vs0; When Bq>Bq0, the first detection and tuning module determines that the parallel task volume Bq is a high task volume, performs a computing power correction on the preset generation rate Vs0, sets the rate correction coefficient to θ, and sets The corrected preset generation rate is Vs0`, Vs0`=Vs0×θ, and the preset generation rate Vs0 is replaced by the corrected preset generation rate Vs0`, and the data generation rate Vs is re-compared with the corrected preset generation rate Vs0`; The second detection and tuning module calculates the total power requirement value according to the target device data using a total power requirement value calculation method, wherein the total power requirement value calculation method includes: Step P01: Calculate the power R1 required for data acquisition based on the operating voltage Ug, the operating current Ig, and the data acquisition frequency Cf to obtain the power R1 required for data acquisition, and set R1 = Ug × Ig × Cf; Step P02, calculating the power R2 required for data processing based on the data processing power Pc and the data processing time tl, obtaining the power R2 required for data processing, and setting R2 = Pc × tl; Step P03, calculate the power R3 required for power analysis based on the power calculation power Px and the power calculation time Tx, obtain the power R3 required for power analysis, and set R3=Px×Tx; Step P04, calculating the power R4 required for power distribution based on the control circuit power Pk, the number of communications nt, and the communication time tt, to obtain the power R4 required for power distribution, and setting R4 = Pk × nt × tt; Step P05: Calculate the total power demand R based on the power required for data acquisition R1, the power required for data processing R2, the power required for computing power analysis R3, and the power required for power distribution R4 to obtain the total power demand R, and set R=R1+R2+R3+R4; The second detection and tuning module performs a secondary computing power adjustment on the computing power demand optimization method according to the computing power optimization adjustment method, and the computing power optimization adjustment method includes: Step U01: compare the total power demand R with the remaining power R0, determine the demand for the total power demand R based on the comparison result, and perform secondary computing power adjustments on the data processing method and computing power demand optimization method based on the determination result, where: When R≤R0, the second detection and tuning module determines that the total power demand R is low, and does not perform secondary computing power adjustment on the data processing method and the computing power demand optimization method; When R>R0, the second detection and tuning module determines that the demand situation of the total power demand R is high, performs a secondary computing power adjustment on the computing power demand optimization method, sets the adjusted data acquisition frequency to Cf`, Cf`=Cf×(R-R0) / R0, and replaces the data acquisition frequency Cf with the adjusted data acquisition frequency Cf`, recalculates the data generation rate Vs, sets the adjusted preset parallel task volume to Bq0`, Bq0`=Bq0×(1-(R-R0) / R0), replaces the preset parallel task volume Bq0 with the adjusted preset parallel task volume Bq0`, and recomputes the parallel task volume Bq with the adjusted preset parallel task volume Bq0`; Step U02: compare the working temperature Wh with the preset working temperature Wh0, determine the state of the working temperature Wh based on the comparison result, and perform a secondary calculation power correction on the remaining power R0 based on the determination result, wherein: When Wh≤Wh0, the second detection and tuning module determines that the operating temperature Wh is in a low temperature state and does not perform a secondary computing power correction on the remaining power R0; When Wh>Wh0, the second detection and tuning module determines that the operating temperature Wh is in a high temperature state, performs a secondary computing power correction on the power reserve R0, sets the corrected power reserve to R0`, R0`=R0×Wh / Wh0, replaces the power reserve R0 with the corrected power reserve R0`, and re-compares the total power demand R with the corrected power reserve R0`; In step U03, the heat dissipation efficiency Vv is compared with the preset heat dissipation efficiency Vv0, and the heat dissipation degree of the heat dissipation efficiency Vv is judged according to the comparison result. The preset working temperature Wh0 is updated with a secondary computing power according to the judgment result, wherein: When Vv≤Vv0, the second detection and tuning module determines that the heat dissipation degree of the heat dissipation efficiency Vv is low, and does not perform a secondary computing power update on the preset operating temperature Wh0; When Vv>Vv0, the second detection and tuning module determines that the heat dissipation degree of the heat dissipation efficiency Vv is high, performs a secondary computing power update on the preset working temperature Wh0, sets the updated preset working temperature to Wh0`, Wh0`=Wh0×Vv / Vv0, replaces the preset working temperature Wh0 with the updated preset working temperature Wh0`, and re-compares the working temperature Wh with the updated preset working temperature Wh0`.

2. The device for online Libs laser real-time detection according to claim 1, characterized in that: The data processing module performs data preprocessing on the target environment data according to a data preprocessing strategy, wherein the data preprocessing strategy includes: Step J01: Based on the spectrum data value set s={s1,s2,s3,...,si}, the spectrum data minimum value S min and the maximum value of the spectral data S max Calculate the normalized spectral data value set Sop={Sop1, Sop2, Sop3, ..., Sopi}, where i is the order of the spectral data point, i is a positive integer, and the maximum value of i is the total number of spectral data points, and obtain the normalized spectral data value set Sop={Sop1, Sop2, Sop3, ..., Sopi}, set ; Step J02: Calculate the processed time-resolved data set t`={t`1,t`2,t`3,...,t`j} according to the segmentation window size h and the time-resolved data set t={t1,t2,t3,...,tj}, where j is the order of the time-resolved data points, j is a positive integer, and the maximum value of j is the total number of time-resolved data points. The processed time-resolved data set t`={t`1,t`2,t`3,...,t`j} is obtained, and set ; Step J03: Obtain projection coordinates (αm, βm, γm) of each spatial position data according to the universal transverse Mercator grid system, where m is the total number of measurement points; In step J04 , the normalized spectral data value set Sop={Sop1, Sop2, Sop3, ..., Sopi}, the processed time-resolved data set t`={t`1, t`2, t`3, ..., t`j} and the projection coordinates (αm, βm, γm) are used as the first target processing data.

3. The device for online Libs laser real-time detection according to claim 2, characterized in that: When the data processing module performs data preprocessing on the target environment data according to the data preprocessing strategy, the data processing module constructs a spectral data feature vector model according to a spectral data feature vector model construction method, and the spectral data feature vector model construction method includes: Step K01, divide the historical spectral dataset into a 70% spectral training set, a 20% spectral validation set, and a 10% spectral test set; Step K02, initializing the spectral parameters of the first convolutional neural network model; Step K03: Input the spectral training set into the first convolutional neural network model after parameter initialization for training, input the spectral validation set into the trained first convolutional neural network model, optimize the spectral parameters of the trained first convolutional neural network model, and then input the spectral test set into the first convolutional neural network model after parameter optimization for testing, and output the test accuracy; Step K04: outputting the first convolutional neural network model after parameter optimization with an accuracy rate of 90% as the spectral data feature vector model; The data processing module constructs a time-resolved feature vector model according to a time-resolved feature vector model construction method, and the time-resolved feature vector model construction method includes: Step C01, divide the historical time-resolved dataset into a 70% time training set, a 20% time validation set, and a 10% time test set; Step C02, initializing the time parameters of the second convolutional neural network model; Step C03: Input the time training set into the second convolutional neural network model after parameter initialization for training, input the time verification set into the trained second convolutional neural network model, optimize the time parameters of the trained second convolutional neural network model, and then input the time test set into the second convolutional neural network model after parameter optimization for testing, and output the test accuracy; In step C04, the second convolutional neural network model after parameter optimization with an accuracy rate of 90% is output as a time-resolved feature vector model.

4. The device for online Libs laser real-time detection according to claim 3, characterized in that: The data processing module extracts features from the first target processing data according to a feature extraction strategy, wherein the feature extraction strategy includes: Step D01, inputting a normalized spectral data value set Sop={Sop1, Sop2, Sop3, ..., Sopi} into a spectral data feature vector model to obtain a spectral feature vector set Foh={Foh1, Foh2, Foh3, ..., Fohi} output by the spectral data feature vector model; Step D02: input the processed time-resolved data set t`={t`1, t`2, t`3, ..., t`j} into the time-resolved feature vector model to obtain the time feature vector set Fom={Fom1, Fom2, Fom3, ..., Fomj} output by the time-resolved feature vector model; Step D03, calculate each spatial distance dm according to each projection coordinate (αm, βm, γm) and each preset coordinate (αy, βy, γy), and set ; In step D04, the spectral feature vector set Foh={Foh1, Foh2, Foh3, ..., Fohi}, the time feature vector set Fom={Fom1, Fom2, Fom3, ..., Fomj} and each spatial distance dm are used as second target processing data.

5. The device for online Libs laser real-time detection according to claim 4, characterized in that: The data processing module performs data fusion on the second target processing data according to a data fusion strategy, wherein the data fusion strategy includes: Step E01, the spectral feature vector set Foh = {Foh1, Foh2, Foh3, ..., Fohi}, the time feature vector set Fom = {Fom1, Fom2, Fom3, ..., Fomj} and each spatial distance dm are matrixed to obtain a first matrix X; Step E02, setting the first data sampling point Xzv, where z is the zth row in the first matrix X, and v is the vth column in the first matrix X; Step E03, calculate the mean μv and the standard deviation σv of each column according to the total number of measurement points m and the first data sampling point Xzv, and obtain the mean μv and the standard deviation σv of each column, and set , ; Step E04, calculate the second data sampling point Gz0v0 according to the mean value μv of each column and the standard deviation σv of each column, and obtain the second data sampling point Gz0v0, and set ; Step E05, matrix processing is performed on the second data sampling point Gz0v0 to obtain a second matrix G; Step E06, the second matrix G is transposed to obtain the transposed second matrix G '; Step E07, calculate the covariance matrix C according to the total number of measurement points m, the second matrix G and the transposed second matrix G' to obtain the covariance matrix C, set ; Step E08, performing eigendecomposition on the covariance matrix C to obtain eigenvalues; Step E09: Arrange the eigenvalues ​​in a preset order to obtain sorted eigenvalues, perform value processing on the sorted eigenvalues ​​according to the value ratio, and obtain the laser detection result.

6. The on-line Libs laser real-time detection device according to claim 5, characterized in that: When the first detection and tuning module adjusts the computing power of the data processing method according to the computing power demand, the total computing power demand Q is compared with the preset computing power demand Q0, the total computing power demand is judged according to the comparison result, and the computing power of the data processing method is adjusted according to the judgment result, wherein: When Q≤Q0, the first detection and tuning module determines that the total computing power demand is low and does not adjust the computing power of the data processing method; When Q>Q0, the first detection tuning module determines that the total computing power demand is high, adjusts the computing power of the data processing method, sends the second target processing data to the cloud, performs data fusion through the cloud, and obtains the laser detection results.

Images