Nonlinear synchronous fluorescence path selection method and device based on intelligent algorithm

Abstract

A nonlinear synchronous fluorescence path selection method and device based on an intelligent algorithm, comprising the following: a path optimization model is built based on a nonlinear synchronous fluorescence scanning principle, a genetic algorithm is used as the core, and a fitness function is set to represent the optimization planning of the path optimization model; three-dimensional fluorescence spectrum data of multiple test objects are input into the built path optimization model to obtain an optimal nonlinear synchronous scanning path. The method can significantly shorten the path screening time, improve the path quality and analysis efficiency, and thus provide researchers with more accurate and efficient nonlinear synchronous fluorescence scanning path selection means.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of fluorescence detection of multi-component substances, and particularly to a nonlinear synchronous fluorescence path selection method and device based on an intelligent algorithm. BACKGROUND

[0002] The nonlinear synchronous fluorescence method is a technique of simultaneously scanning along a certain curve passing through the contour spectrum map, and the scanning rates of the two monochromators can be dynamically changed without maintaining a fixed ratio, and the method can select a corresponding path according to different needs. By selecting a suitable path, the influence of scattered light can be avoided in detection, the resolution of a spectral overlap system is further improved, the number of spectral scans is reduced, and the method is widely applied in mixed component system analysis.

[0003] In the application of the nonlinear synchronous fluorescence method, the most important point is the selection of the scanning path before measurement, and the selection is based on obtaining the best nonlinear synchronous fluorescence spectrum, which generally has good separation effect on various to-be-measured substances, and has the largest spectral intensity and the smallest interference for each to-be-measured substance.

[0004] However, in the selection of the nonlinear synchronous fluorescence scanning path, currently, researchers generally determine the scanning path through multiple attempts, that is, the researchers first determine a plurality of scanning paths through their own experience, and then obtain a series of fluorescence spectra along the paths through actual detection, and select the path corresponding to the best fluorescence spectrum as the scanning path. This path selection method not only consumes time and effort, but also depends on the personal experience of researchers. In order to reduce the time consumed by researchers in the path selection process, it is of great significance to develop a method capable of quickly finding a suitable scanning path. SUMMARY

[0005] The main purpose of the present application is to overcome the path selection problem in the prior art, and to propose a nonlinear synchronous fluorescence path selection method and device based on an intelligent algorithm, to help researchers quickly find a suitable scanning path and avoid the consumption of manpower and material resources in a large number of experiments.

[0006] The present application adopts the following technical solutions:

[0007] A nonlinear synchronous fluorescence path selection method based on an intelligent algorithm, comprising the following:

[0008] A path optimization model with a genetic algorithm as the core is built based on the principle of nonlinear synchronous fluorescence scanning, and a fitness function is set to represent the optimization planning of the path optimization model; three-dimensional fluorescence spectrum data of a plurality of to-be-measured substances are input into the constructed path optimization model to obtain an optimal nonlinear synchronous scanning path.

[0009] The optimal nonlinear synchronous scanning path is obtained by the path optimization model, and specifically includes the following steps:

[0010] 1) A weight distribution is generated based on three-dimensional fluorescence spectral data, and a group of initial scanning paths is generated based on the weight distribution as an initial population;

[0011] 2) A fitness function is set based on peak intensity, signal interference control, path smoothness and density distribution to evaluate the pros and cons of each scanning path;

[0012] 3) The fitness value of each initial scanning path is calculated according to the fitness function, and the scanning path with high fitness value is selected as the parent for reproduction by using the tournament selection method;

[0013] 4) The best individual is found from the population after reproduction and is copied to the next generation as an elite, and the remaining individuals are subjected to crossover and mutation operations, and the path control points of the scanning path corresponding to the parent are recombined;

[0014] 5) The fitness value is recalculated and the population is updated, and it is judged whether the iteration number or the fitness value reaches the set value, if yes, the optimal nonlinear synchronous scanning path is output; if not, step 3) is entered.

[0015] The fitness function expression is as follows:

[0016] ;

[0017] Wherein, is the fitness value, P is the average peak intensity, reflecting the scanning path's ability to capture the fluorescence peak value of each analyte; I is the total interference, indicating the signal interference between the analytes at the peak value; C is the curvature penalty, used to suppress excessive bending of the scanning path; R is the loop penalty, preventing the scanning path from invalid looping in the high reward area; S is the self-intersection penalty, preventing the scanning path from unreasonable self-intersection; D is the density reward, encouraging the scanning path to pass through the high importance area; λ, α, β, γ, δ are weight factors.

[0018] The calculation formula of the average peak intensity is as follows:

[0019] ;

[0020] The peak value is detected in the fluorescence intensity sequence of the analyte j , and the maximum peak value is recorded as , if all analytes have available peak values, P is the maximum average peak intensity; N is the number of path points of the scanning path; M is the number of analytes.

[0021] For the peak position set {Ij,m}, check the normalized value z of all other to-be-tested substances k≠j at the peak position k (l j,m ), the total interference is defined as:

[0022] ;

[0023] wherein m is the index of each detected peak position, indicating the traversal of each peak position possibly generated by the path under the same to-be-tested substance j.

[0024] The curvature penalty is characterized by penalizing excessively curved scanning paths to avoid the occurrence of path mutations, and the specific formula is defined as: the vector angle of every three adjacent points on the scanning path is calculated, and let and , then:

[0025] ;

[0026] wherein (x , ), (x , ), and (x , ) are the coordinates of three adjacent points on the scanning path, i=1,…,N, N is the number of path points of the scanning path, and ε is a small amount to prevent the denominator from being 0.

[0027] The loop penalty is characterized by the phenomenon of invalid loops of the scanning path, and the calculation formula is defined as follows:

[0028] Define the direction angle of the i-th segment of the scanning path , then:

[0029]

[0030] wherein (x , ), (x , ) are the coordinates of two adjacent points on the i-th segment of the scanning path, and N is the number of path points of the scanning path. represents the direction angle corresponding to the (i-1)-th segment.

[0031] The self-intersection penalty is characterized by the intersection of all non-adjacent line segments, and the formula is specifically defined as:

[0032] Divide the scanning path into N-1 line segments , define the line segment intersection indicator function :

[0033]

[0034] ;

[0035] wherein, is the intersection indicator function of line segment and line segment is the coordinate of two adjacent points on the i-th segment of the scanning path.

[0036] The density reward is characterized as the average value of the density of the area passed by the scanning path, and the formula is specifically defined as:

[0037] ;

[0038] wherein, is the coordinate of the point on the i-th segment of the scanning path, is the average value of the density of the area passed by the scanning path, and N represents the number of path points.

[0039] A nonlinear synchronous fluorescence path selection device based on an intelligent algorithm, comprising:

[0040] A path optimization module, based on the principle of nonlinear synchronous fluorescence scanning and taking a genetic algorithm as the core, sets a fitness function to represent the optimization planning of the path optimization model.

[0041] A scanning path acquisition module inputs the three-dimensional fluorescence spectrum data of a plurality of test objects into the constructed path optimization model to obtain an optimal nonlinear synchronous scanning path.

[0042] As can be known from the above description of the present application, compared with the prior art, the present application has the following beneficial effects:

[0043] The present application fully utilizes the synergistic advantages of computer technology and intelligent algorithms, converts the principles of spectroscopy into mathematical models, and realizes them through computer language. By combining nonlinear synchronous fluorescence technology with intelligent optimization algorithms, the optimal path can be efficiently screened, and the time and effort consumed by researchers in path selection can be greatly reduced, and the path quality and analysis efficiency can be improved.

[0044] The present application provides a systematic and automated optimization scheme for the selection process of nonlinear paths, which can solve the problem of time and effort consumption of traditional methods, and has effective practical value. At the same time, the present application introduces spectral simulation technology, and provides reliable decision-making reference for users through the theoretical spectrum generated based on the selected path, thereby effectively avoiding a large number of invalid experiments and significantly improving experimental efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0045] Figure 1 is the flowchart of the path optimization model of the present application.

[0046] ​Figure 2 Density map generated by the method of the present application.

[0047] Figure 3 Three-dimensional fluorescence contour map of benz(a)pyrene (BaP) and fluoranthene (Fla) and the path selected by the method of the present application.

[0048] Figure 4 Theoretical spectral simulation map of each component possibly obtained by scanning the scanning path obtained by the method of the present application.

[0049] Figure 5 Actual scanning spectrum of the scanning path obtained by the present application.

[0050] The present application is further described in detail below in conjunction with the accompanying drawings and specific embodiments. DETAILED DESCRIPTION

[0051] The present application is further described below in detail through specific embodiments.

[0052] Reference Figure 1 A nonlinear synchronous fluorescence path selection method based on an intelligent algorithm, comprising the following: a path optimization model with a genetic algorithm as the core is built based on a nonlinear synchronous fluorescence scanning principle, and a fitness function is set to represent the optimization planning of the path optimization model; three-dimensional fluorescence spectrum data of multiple test objects are input into the built path optimization model to obtain an optimal nonlinear synchronous scanning path.

[0053] The path selection principle proposed by the present application refers to that based on three-dimensional fluorescence data of multiple test objects, interpolation and automatic spectral map drawing are performed on the original data, the fluorescence distribution of the test objects in a specific spectral interval can be obtained, including drawing a basic spectral map such as a contour map for scanning path selection based on three-dimensional fluorescence spectrum data of each test object, and further generating a density map based on normalized fluorescence intensity and gradient information, and generating a scanning path through a high signal region by using the density map of the target region. The initialization parameters of the intelligent optimization algorithm are determined by the material object to be detected. The present application builds a path optimization model with a genetic algorithm as the core based on a nonlinear synchronous fluorescence scanning principle.

[0054] The selection of the nonlinear synchronous scanning path is influenced by multiple factors in cooperation, the present application sets adaptive adjustment of parameters, that is, a fitness function is constructed to represent the optimization planning by comprehensively considering factors such as peak intensity of multiple test objects, signal interference control, path smoothness and density distribution.

[0055] The optimization model used in this invention combines an optimization technique based on the principle of nonlinear synchronous fluorescence and an adaptive intelligent evolutionary algorithm as its core. This optimizes the selection of the fitness function, enabling the optimization model to obtain the optimal nonlinear synchronous scanning path that can effectively distinguish the fluorescence signals of each component and reduce signal overlap and interference.

[0056] In this invention, the three-dimensional fluorescence spectral data of each analyte is obtained by performing a three-dimensional spectral scan using a general fluorescence instrument. It is generally a data matrix composed of excitation wavelength, emission wavelength and corresponding fluorescence intensity. The nonlinear synchronous fluorescence scanning path is a curve, and scanning along this path can obtain the fluorescence peaks corresponding to each analyte.

[0057] This invention obtains the optimal nonlinear synchronous scanning path through a path optimization model, specifically including the following:

[0058] 1) Generate a weight distribution based on three-dimensional fluorescence spectral data, and generate an initial set of scanning paths as the initial population based on the weight distribution.

[0059] 2) Set fitness functions based on peak intensity, signal interference control, path smoothness and density distribution to evaluate the quality of each scan path.

[0060] 3) Calculate the fitness value of each initial scan path based on the fitness function, and use the tournament selection method to select the scan path with the higher fitness value as the parent for reproduction.

[0061] 4) Find the best individuals from the reproduced population, use them as elites to replicate to the next generation, perform crossover and mutation operations on the remaining individuals, and reorganize the path control points of the scanning path corresponding to the parent generation.

[0062] 5) Recalculate the fitness value and update the population. Determine if the number of iterations or the fitness value has reached the set value. If yes, output the optimal nonlinear synchronous scan path. If not, proceed to step 3.

[0063] In step 1), the density map, by fusing normalized fluorescence intensity and gradient information, effectively characterizes the relative importance of different regions and can be directly used as a weight distribution through mathematical transformation. Specifically, the density map is obtained by mapping the spectrum of the analyte onto a two-dimensional plane using a formula:

[0064]

[0065]

[0066] In the formula, This represents the density value at the coordinate point (x, y). F(x, y) = (F(x, y) - min) / (max - min), where F(x, y) represents the raw fluorescence intensity value at coordinate point (x, y), max denotes the maximum value of all points in the density map, and min denotes the minimum value of all points in the density map, is a small quantity to prevent the denominator from being zero, denotes the normalization result of the i-th group of data. This formula represents the statistics of the density area passed by the scanning path, and the method adopted is to sample the mapping of the path points on the density map. In the spectral space, the non-linear synchronous scanning path is defined by multiple control points, which determine the shape and position of the path. Then the initial population generation includes path construction, density map guidance generation, population diversity maintenance, etc.

[0067] wherein the path construction includes:

[0068] Bezier curve path: by selecting the starting point, the ending point and a number of intermediate control points, a smooth non-linear path is generated.

[0069] Linear path: composed of control points connected by straight line segments, suitable for scanning simple regions.

[0070] Mixed path: combines the characteristics of Bezier curves and linear segments, used to adapt to complex spectral intervals.

[0071] Density map guidance generation includes: using the density map of the target region to preferentially generate paths passing through high signal areas, improving the quality of the initial population solution.

[0072] Population diversity maintenance includes: ensuring the diversity of the initial population in path shape and distribution, avoiding the optimization process from falling into local extrema.

[0073] wherein in steps 2) and 3), the fitness function is used to evaluate the pros and cons of each path, which takes into account the following factors:

[0074] Fluorescence signal peak intensity: maximize the intensity of the peak signal on the path to improve the signal capture ability of the target analyte.

[0075] Signal interference: minimize the signal overlap between different analytes to reduce the impact of interference on the detection results.

[0076] Path smoothness: by setting a penalty term for curvature, encourage the generation of smooth paths to avoid path mutations.

[0077] Path detour and self-intersection penalty: detect whether the path has unreasonable detours or self-intersections and give corresponding penalties.

[0078] Density reward: encourage the path to cover high signal areas in the density map to improve the overall efficiency of the path.

[0079] Based on this, the fitness function mathematical expression form of the application can be expressed by the following formula:

[0080] ;

[0081] Among them, is the adaptive value, P is the average peak intensity, reflecting the scanning path's ability to capture the peak value of each measured object; I is the total interference, indicating the signal interference between the measured objects at the peak value; C is the curvature penalty, used to suppress excessive bending of the scanning path; R is the winding penalty, preventing the scanning path from invalid winding in the high reward area; S is the self-intersection penalty, preventing the scanning path from unreasonable self-intersection phenomenon; D is the density reward, encouraging the scanning path to pass through the high importance area; λ, α, β, γ, δ are weight factors.

[0082] Among them, the calculation formula of the average peak intensity is as follows:

[0083] ;

[0084] In the fluorescence intensity sequence of the measured object j , the peak value is detected, and the maximum peak value is recorded as , if all measured objects have available peak values, P is the average maximum peak intensity; N is the number of path points of the scanning path; M is the number of measured objects.

[0085] For the peak position set {I j,m} of the measured object j, the normalized value z k (l j,m ) of all other measured objects k≠j is checked at the peak position, and the total interference is defined as:

[0086] ;

[0087] Among them, m is the index of each detected peak position, indicating that each peak position generated by the path under the same measured object j is traversed.

[0088] The curvature penalty is characterized by punishing the excessively curved scanning path to avoid the occurrence of path mutation, and the specific formula is defined as: the vector angle of every three adjacent points on the scanning path is calculated, and and , then:

[0089] ;

[0090] C is the curvature penalty; ( , ), ( , ), and ( , ) are the coordinates of three adjacent points on the scan path, i = 1,..., N, N is the number of path points of the scan path, and ε is a small quantity to prevent the denominator from being zero.

[0091] The wrap penalty represents the phenomenon of invalid wrap of the scan path, and its calculation formula is defined as follows:

[0092] The direction angle of the i-th segment of the scan path is defined as

[0093]

[0094] wherein, is the wrap penalty, , ), ( , ) are the coordinates of two adjacent points on the i-th segment of the scan path, and N is the number of path points of the scan path. is the direction angle corresponding to the (i-1)-th segment. This formula is mainly used to measure the cumulative difference of the direction angles of each segment in the scan path.

[0095] The self-intersection penalty represents the intersection of all non-adjacent line segments, and its formula is specifically defined as:

[0096] The scan path is divided into N-1 line segments , and the line segment intersection indicator function is defined as:

[0097]

[0098] ;

[0099] wherein, is the self-intersection penalty, is the intersection indicator function of line segment and line segment , ( , ), ( , ) are the coordinates of two adjacent points on the i-th segment of the scan path.

[0100] The density reward represents the average value of the density of the area passed by the scan path, and its formula is specifically defined as:

[0101] ;

[0102] wherein, is the density reward, is the average value of the density of the area passed by the scan path, and N represents the number of path points.

[0103] ​In step 4), selection, crossover, mutation and elitism are included. For selection, a tournament selection mechanism is used to select individuals with higher fitness from the population as parents, and key genes of excellent paths are reserved. Crossover is a control point operation on the parent path: randomly select a crossover point, exchange the control points of the two paths, generate child paths; and dynamically adjust the crossover point position to fully combine the characteristics of Bezier, linear and mixed paths. Mutation is to introduce random mutation to enhance population diversity: adjust the position of the path control point, and add small Gaussian noise; and use the density map for local optimization, and preferentially guide the path to the high signal area. Elitism is to retain the individual with the highest fitness to ensure the continuation of the optimal solution in the optimization process.

[0104] To further improve the efficiency of the algorithm and adapt to different experimental needs, the following adaptive mechanisms are added:

[0105] Dynamic adjustment of fitness: according to the fitness distribution of each generation, the normalization strategy is adjusted adaptively to ensure the stability of the optimization process.

[0106] Dynamic adjustment of mutation probability: when the population diversity decreases, the mutation probability is appropriately increased to avoid premature convergence. When the population is concentrated around the optimal solution, the mutation probability is reduced to speed up convergence.

[0107] User feedback fusion: periodically display the current optimal path, and optimize the direction based on user ratings. The control points of high-rated paths are used as templates for offspring generation to improve the quality of population solutions.

[0108] Step 5) includes termination conditions and optimal path output, and the optimization process terminates when one of the following conditions is met:

[0109] Condition one: the number of iterations reaches the preset maximum limit value (maxIter).

[0110] Condition two: there is no significant improvement in the optimal fitness value for consecutive generations, indicating that the algorithm has converged.

[0111] Finally, the algorithm outputs the scanning path with the highest fitness in the current population as the optimal path for nonlinear synchronous fluorescence scanning.

[0112] The application simulates and verifies the fluorescence signal based on the obtained optimal scanning path, realizes separation and rapid identification of components of the measured object: according to the determined scanning path, the algorithm is used to simulate the control of the excitation and emission monochromator to scan simultaneously, the intensity and wavelength of the nonlinear synchronous fluorescence spectrum are recorded, the process of the fluorescence signal of each measured object is obtained, and the corresponding theoretical fluorescence spectrum is drawn, which is convenient for researchers to modify. The excitation wavelength and emission wavelength corresponding to the optimal path obtained by the method of the application are used to extract the fluorescence intensity corresponding to each measurement point in the path from the mixed spectrum, and the fluorescence intensity is drawn into a time sequence atlas, which is similar to the theoretically scanned spectrum, and is convenient for researchers to judge the advantages and disadvantages of the scanning path.

[0113] Compared with the traditional path selection method, the method of the application can significantly shorten the path screening time, improve the path quality and analysis efficiency, and thus provide researchers with a more accurate and efficient nonlinear synchronous fluorescence scanning path selection means.

[0114] Based on this, the application also provides a nonlinear synchronous fluorescence path selection device based on an intelligent algorithm, which is used to execute the nonlinear synchronous fluorescence path selection method based on an intelligent algorithm, and includes: a path optimization module, which is based on the principle of nonlinear synchronous fluorescence scanning and uses a genetic algorithm as the core, sets up a fitness function to represent the optimization planning of the path optimization model. A scanning path acquisition module inputs the three-dimensional fluorescence spectrum data of multiple measured objects into the constructed path optimization model to obtain the optimal nonlinear synchronous scanning path. The path optimization module is used to execute steps 1) to 5).

[0115] Embodiment: simultaneous detection path selection of a mixture of benzo(a) anthracene (BaP) and fluoranthene (Fla)

[0116] The three-dimensional fluorescence contour map of each measured object based on the mixture of benzo(a) anthracene (BaP) and fluoranthene (Fla) is as shown in Figure 3 , and the generated density weight map is as shown in Figure 2 , which is used to guide the generation of the initial population and the adjustment of the path. According to the separation needs of the two substances, 30 iterations and 400 path points are set as initial parameters. In this embodiment, the optimization technology based on the adaptive genetic algorithm is used as the core, the fitness of each path is investigated, the paths with high fitness are rewarded, and the similar offspring is generated, the paths with low fitness are punished, and the similar paths are reduced in the generation of the offspring. After 30 iterations, it is found that the optimal fitness value remains basically unchanged in the later iteration, so it is considered that the path obtained by the algorithm meets the preset target, and the selected path is as shown in Figure 3 . Based on the optimal path obtained in Figure 3 , the simulation fluorescence spectrum map is obtained by mapping the path points and the corresponding points in the three-dimensional spectrum asFigure 4 As shown, according to the simulation atlas, each of the to-be-tested substances is basically not interfered at the maximum determination peak thereof, and can be used for experimental verification.

[0117] After the scanning path is acquired (as shown in Table 1), the scanning path is imported into an instrument with a nonlinear synchronous fluorescence scanning function, and actual detection work is carried out. In this embodiment, the result of detection along the selected optimal scanning path is as shown in FIG. 4. Figure 5 As shown, the fluorescence signals of the two to-be-tested substances are effectively separated, and mutual independence is basically achieved. This result verifies the practicability and reliability of the present application, and can effectively assist researchers in quickly screening out an optimal path suitable for nonlinear synchronous fluorescence scanning, and effectively improve experimental efficiency.

[0118] Table 1: Scanning path example

[0119]

[0120]

[0121] It should be noted that although several modules or units of the device for action execution are mentioned in the foregoing detailed description, such a division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into several modules or units embodied.

[0122] Through the above description of the embodiments, those skilled in the art can easily understand that the example embodiments described herein can be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a U disk, a mobile hard disk, etc.) or a network, and includes several instructions to make a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) execute the method according to the embodiments of the present disclosure.

[0123] Other embodiments of the present disclosure will be readily apparent to those skilled in the art upon considering the specification and the practice of the disclosed application. The present disclosure is intended to cover any variations, uses, or adaptive changes of the present disclosure that follow the general principles of the present disclosure and include common knowledge or conventional technical means in the art that are not disclosed by the present disclosure.

[0124] The above merely illustrates the specific embodiments of the present application, but the design concept of the present application is not limited thereto, and any non-essential modification of the present application by using the concept shall be deemed as the infringement of the protection scope of the present application.

Claims

1. A method for intelligent algorithm based nonlinear synchronous fluorescence path selection, characterized in that, Including the following: A path optimization model based on a genetic algorithm is built based on the principle of nonlinear synchronous fluorescence scanning, and a fitness function is set to characterize the optimization planning of the path optimization model; the three-dimensional fluorescence spectrum data of multiple analytes are input into the constructed path optimization model to obtain the optimal nonlinear synchronous scanning path; The optimal nonlinear synchronous scanning path is obtained through the path optimization model, specifically including the following: 1) Generate a weight distribution based on three-dimensional fluorescence spectroscopy data, and generate an initial set of scanning paths as the initial population based on the weight distribution; 2) A fitness function is set based on peak intensity, signal interference control, path smoothness, and density distribution to evaluate the quality of each scan path; 3) Calculate the fitness value of each initial scan path according to the fitness function, and use the tournament selection method to select the scan path with the higher fitness value as the parent for reproduction; 4) Find the best individual from the reproduced population, use it as an elite to replicate to the next generation, perform crossover and mutation operations on the remaining individuals, and reorganize the path control points of the scanning path corresponding to the parent generation; 5) Recalculate the fitness value and update the population. Determine if the number of iterations or the fitness value has reached the set value. If yes, output the optimal nonlinear synchronous scan path; otherwise, proceed to step 3). The fitness function expression is as follows: ； wherein, P is an adaptive value, P is the average peak intensity, reflecting the scanning path's ability to capture the fluorescence peak of each test object; I is the total interference, indicating the signal interference between the test objects at the peak; C is the curvature penalty, used to suppress excessive bending of the scanning path; R is the loop penalty, preventing the scanning path from invalid looping in the high reward area; S is the self-intersection penalty, preventing the scanning path from unreasonable self-intersection phenomenon; D is the density reward, encouraging the scanning path to pass through the high importance area; λ, α, β, γ, δ are weight factors.

2. The nonlinear synchronous fluorescence path selection method based on intelligent algorithms as described in claim 1, characterized in that: The formula for calculating the average peak intensity is as follows: ； The fluorescence intensity sequence of analyte j The peak value detected in the middle is denoted as the maximum peak value. If all analytes have usable peak values, then P is the maximum average peak intensity; N is the number of path points in the scanning path; and M is the number of analytes.

3. The nonlinear synchronous fluorescence path selection method based on intelligent algorithms as described in claim 1, characterized in that: For the peak position set {I j,m} of the test substance j, the normalized values z k (l j,m ) of all other test substances k ≠ j are checked at this peak position, and the total interference is defined as: ； Where m is the index of each detected peak position, indicating that the positions of each possible peak position that may be generated under the same test object j are traversed.

4. The nonlinear synchronous fluorescence path selection method based on intelligent algorithms as described in claim 1, characterized in that: The curvature penalty is characterized by penalizing excessively curved scan paths to avoid abrupt path changes. The specific formula is defined as follows: calculate the angle between vectors for every three adjacent points on the scan path, and let... and Then we have: ； in( , (), , ), ( , Let ε be the coordinates of three adjacent points on the scanning path, i=1,…,N, where N is the number of path points on the scanning path, and ε is a small quantity to prevent the denominator from being 0.

5. The nonlinear synchronous fluorescence path selection method based on intelligent algorithms as described in claim 1, characterized in that: The looping penalty is characterized by the phenomenon of invalid loops occurring in the scan path, and its calculation formula is defined as follows: Definition of the direction angle of the i-th segment of the scan path i = arctan2(y i − y i−1 , x i − x i−1 ) has the following properties: in,( , (), , ) represents the coordinates of two adjacent points on the i-th segment of the scanning path, and N is the number of path points on the scanning path; This represents the direction angle corresponding to the (i-1)th segment.

6. The nonlinear synchronous fluorescence path selection method based on intelligent algorithms as described in claim 1, characterized in that: The self-intersection penalty is characterized by the condition that all non-adjacent line segments intersect, and its formula is specifically defined as follows: Divide the scanning path into N-1 segments. Define the line segment intersection indicator function. : ； in, For line segments and line segments Intersection indicator function; , (), , ) represents the coordinates of two adjacent points on the i-th segment of the scanning path.

7. The nonlinear synchronous fluorescence path selection method based on intelligent algorithms as described in claim 1, characterized in that: The density bonus is characterized as the average density of the regions traversed by the scan path, and its formula is specifically defined as follows: ； in,( , () represents the coordinates of a point on the i-th segment of the scan path. N represents the average density of the regions traversed by the scan path, where N is the number of path points.

8. A nonlinear synchronous fluorescence path selection device based on intelligent algorithms, characterized in that, include: The path optimization module is based on the principle of nonlinear synchronous fluorescence scanning and uses a genetic algorithm as its core. It sets a fitness function to characterize the optimization planning of the path optimization model. The scanning path acquisition module inputs the three-dimensional fluorescence spectral data of multiple analytes into the constructed path optimization model to obtain the optimal nonlinear synchronous scanning path. The optimal nonlinear synchronous scanning path is obtained through the path optimization model, specifically including the following: 1) Generate a weight distribution based on three-dimensional fluorescence spectroscopy data, and generate an initial set of scanning paths as the initial population based on the weight distribution; 2) A fitness function is set based on peak intensity, signal interference control, path smoothness, and density distribution to evaluate the quality of each scan path; 3) Calculate the fitness value of each initial scan path according to the fitness function, and use the tournament selection method to select the scan path with the higher fitness value as the parent for reproduction; 4) Find the best individual from the reproduced population, use it as an elite to replicate to the next generation, perform crossover and mutation operations on the remaining individuals, and reorganize the path control points of the scanning path corresponding to the parent generation; 5) Recalculate the fitness value and update the population. Determine if the number of iterations or the fitness value has reached the set value. If yes, output the optimal nonlinear synchronous scan path; otherwise, proceed to step 3). The fitness function expression is as follows: ； in, For the fitness values, P is the average peak intensity, reflecting the scanning path's ability to capture the fluorescence peaks of each analyte; I is the total interference, representing the signal interference between analytes at the peak; C is the curvature penalty, used to suppress excessive bending of the scanning path; R is the looping penalty, preventing the scanning path from ineffectively looping in high-reward regions; S is the self-crossing penalty, preventing unreasonable self-crossing phenomena in the scanning path; D is the density reward, encouraging the scanning path to pass through high-importance regions; λ, α, β, γ, δ are weighting factors.

Images