Method for determining spectral splitting node and related device

Abstract

The present application provides a method for determining a spectral splitting node and related devices, which relates to the technical field of spectral splitting. According to the gene mapping values corresponding to different wavelength values within a target wavelength range of the spectral signals detected by a target spectrometer, the present application generates splitting chromosomes corresponding to multiple combinations of wavelength segmentation thresholds. Then, all the obtained splitting chromosomes are divided into a preset number of splitting populations, each consisting of a preset number of splitting chromosomes, and the survival fitness value of each splitting chromosome is calculated. Subsequently, gene reproduction iteration is performed on the target chromosomes whose survival fitness values in all splitting populations meet the preset survival conditions, so as to extract the combination of wavelength segmentation thresholds corresponding to the target splitting chromosome with the largest survival fitness value from the splitting populations that meet the preset iteration termination conditions, and construct an optical signal splitting interval of a laser spectrometer that is adapted to laser processing operations and maximizes the interval difference.

Description

Technical Field

[0001] This application relates to the field of spectral splitting technology. Specifically, it relates to a method for determining a spectral splitting node and related devices. Background Art

[0002] With the continuous development of science and technology, the application of laser technology is becoming more and more extensive. Among them, the industrial production field is an important application field of laser technology. In the actual application operations of laser technology in the industrial production field (such as laser cleaning operations, laser welding operations, and laser polishing operations, etc.), it is necessary to focus high-power lasers on the surface of the base material to be processed for relevant processing operations. During the operation process, a series of complex signals such as sound, electricity, magnetism, and light are often generated. These signals are a result mapping of the laser processing operation process and can reflect the states of metal gasification, melting, thermal radiation, metal vapor, and plasma in the specific laser processing operation process to a certain extent. Measuring and processing these states can judge the quality of the laser processing operation.

[0003] Therefore, during the laser processing operation process, it is often necessary to use optoelectronic detection devices (such as laser spectrometers) to collect the optical signals during the processing according to different pre-divided optical signal intervals (such as visible light (metal vapor), reflected light (laser reflection), and infrared light (molten pool thermal radiation)), and generate electrical signals based on the optical signals within each optical signal interval as the analysis basis for subsequent laser processing process monitoring.

[0004] During this process, it is worth noting that the selection of the optical signal interval will affect the accuracy of the laser processing quality detection and judgment. However, the existing laser processing process monitoring scheme uses fixed optical signal wavelengths (such as 600nm and 1100nm) as the spectral splitting nodes, and simply and fixedly divides the optical detection range into several optical signal intervals, resulting in the detection accuracy of the corresponding optoelectronic detection device being unable to meet the increasing detection accuracy requirements, and the equipment applicability in the actual production operation process is poor. Summary of the Invention

[0005] In view of this, the purpose of this application is to provide a method and device for determining a spectral splitting node, a computer device, and a readable storage medium, which can flexibly configure an adaptable and maximally interval-differentiated optical signal spectral splitting interval for a laser spectrometer for laser processing operations by using the genetic algorithm idea, so as to effectively improve the optical detection accuracy and production operation applicability of the laser spectrometer, and effectively improve the monitoring accuracy of the laser processing quality.

[0006] To achieve the above purpose, the technical solutions adopted in the embodiments of this application are as follows:

[0007] In a first aspect, the present application provides a method for determining a spectral splitting node, the method comprising:

[0008] Obtaining gene mapping values corresponding to respective different wavelength values within a target wavelength range of a spectral signal detected by a target spectrometer;

[0009] Generating a plurality of wavelength segmentation threshold combinations within the target wavelength range according to a preset number of wavelength segmentation thresholds, and performing chromosome encoding on each wavelength segmentation threshold combination according to the obtained gene mapping values to obtain splitting chromosomes respectively corresponding to the respective wavelength segmentation threshold combinations, wherein each wavelength segmentation threshold combination is composed of the number of wavelength segmentation thresholds of the wavelength segmentation threshold;

[0010] Dividing all the obtained splitting chromosomes into a preset number of splitting populations, and calculating the survival fitness value of each splitting chromosome, wherein each splitting population is composed of a preset number of splitting chromosomes;

[0011] Performing gene reproduction iteration on target chromosomes in each splitting population whose survival fitness values meet a preset survival condition until the corresponding splitting population meets a preset iteration termination condition;

[0012] Determining an expected splitting node of the spectral signal within the target wavelength range according to the wavelength segmentation threshold combination corresponding to the target splitting chromosome, wherein the target splitting chromosome is the splitting chromosome having the maximum survival fitness value within all splitting populations that meet the preset iteration termination condition.

[0013] In an alternative embodiment, the method further comprises:

[0014] Obtaining an encodable data amount and an expected encoded data amount corresponding to the wavelength measurement range of the target spectrometer;

[0015] In the case where the encodable data amount is greater than the expected encoded data amount, determining the target wavelength range that meets the expected encoded data amount within the wavelength measurement range according to the encodable data amount, the expected encoded data amount, and the spectral resolution of the target spectrometer;

[0016] In the case where the encodable data amount is less than or equal to the expected encoded data amount, directly using the wavelength measurement range as the target wavelength range.

[0017] In an alternative embodiment, the step of obtaining the encodable data amount and the expected encoded data amount corresponding to the wavelength measurement range of the target spectrometer comprises:

[0018] Calculating a difference between an upper wavelength value and a lower wavelength value of the wavelength measurement range to obtain a corresponding wavelength interval value;

[0019] Calculate the quotient between the wavelength interval value and the spectral resolution to obtain the amount of encodable data corresponding to the wavelength measurement range;

[0020] Determine the number of binary encoding bits whose corresponding encoding quantity is closest to the amount of encodable data;

[0021] Use the encoding quantity corresponding to the number of binary encoding bits as the expected encoding data quantity corresponding to the wavelength measurement range.

[0022] In an alternative embodiment, the step of determining the target wavelength range that meets the expected encoding data quantity within the wavelength measurement range according to the amount of encodable data, the expected encoding data quantity, and the spectral resolution of the target spectrometer includes:

[0023] Calculate the difference between the amount of encodable data and the expected encoding data quantity to obtain the corresponding encoding quantity difference;

[0024] Calculate the product of the encoding quantity difference and the spectral resolution to obtain the length of the wavelength interval to be discarded in the wavelength measurement range;

[0025] Starting from the lower wavelength limit value of the wavelength measurement range, discard the wavelength band corresponding to the length of the wavelength interval to be discarded within the wavelength measurement range to obtain the target wavelength range.

[0026] In an alternative embodiment, the step of obtaining the gene mapping values corresponding to different wavelength values within the target wavelength range of the spectral signal detected by the target spectrometer includes:

[0027] Calculate the difference between each wavelength value within the target wavelength range and the lower wavelength limit value of the target wavelength range respectively to obtain a plurality of wavelength differences;

[0028] Calculate the quotient between each wavelength difference and the spectral resolution of the target spectrometer to obtain the gene mapping values corresponding to the respective wavelength values within the target wavelength range.

[0029] In an alternative embodiment, the step of calculating the survival fitness value of each spectrally split chromosome includes:

[0030] Calculate the ratio between the gene mapping value of each wavelength value within the target wavelength range and the sum value of all gene mapping values within the target wavelength range to obtain the wavelength mapping proportion of each wavelength value within the target wavelength range;

[0031] Taking the wavelength mapping proportion of each wavelength value within the target wavelength range as the mapping weight, perform a weighted sum of the gene mapping values of all wavelength values within the target wavelength range to obtain the spectral mapping proportion mean value of the target wavelength range;

[0032] Divide the target wavelength range into multiple spectral bands according to the wavelength segmentation threshold combination corresponding to the spectral chromosome;

[0033] Calculate the sum value between the wavelength mapping proportions of each wavelength value within each spectral band to obtain the wavelength mapping proportion sum value corresponding to each spectral band;

[0034] For each spectral band, calculate the band fitness value of the spectral band according to the spectral mapping proportion mean value, the wavelength mapping proportion sum value of the spectral band, and the gene mapping values and wavelength mapping proportions of each wavelength value within the spectral band;

[0035] Taking the wavelength mapping proportion sum value of each spectral band as the band weight, perform a weighted sum of the band fitness values of all spectral bands to obtain the survival fitness value of the spectral chromosome.

[0036] In an alternative embodiment, the step of calculating the band fitness value of the spectral band according to the spectral mapping proportion mean value, the wavelength mapping proportion sum value of the spectral band, and the gene mapping values and wavelength mapping proportions of each wavelength value within the spectral band includes:

[0037] Taking the wavelength mapping proportion of the gene mapping values of each wavelength value within the spectral band as the mapping weight, perform a weighted sum of the gene mapping values of each wavelength value within the spectral band to obtain the band mapping proportion mean value of the spectral band;

[0038] Calculate the ratio between the band mapping proportion mean value and the wavelength mapping proportion sum value of the spectral band to obtain the band appearance probability of the spectral band;

[0039] Perform a perfect square difference operation on the band appearance probability of the spectral band and the spectral mapping proportion mean value to obtain the band fitness value of the spectral band.

[0040] In an alternative embodiment, each spectral chromosome is formed by sequentially splicing the gene coding data of the wavelength lower limit value, the randomly selected number of wavelength segmentation thresholds, and the wavelength upper limit value within the target wavelength range. Then, the steps for performing a single gene reproduction iteration on the target chromosome within a single spectral population include:

[0041] Randomly select at least one chromosome group to be reproduced from the target chromosomes within the spectral population according to a preset population reproduction probability, where each chromosome group to be reproduced includes two adjacent target chromosomes;

[0042] For each chromosome group to be propagated, exchange the gene coding data of the wavelength values corresponding to the splicing positions in the two target chromosomes included in the chromosome group to be propagated;

[0043] Randomly select at least one spectrochromosome to be mutated from the spectro population after completing the chromosome propagation operation according to a preset population mutation probability;

[0044] For each spectrochromosome to be mutated, adjust the gene coding of the gene coding data of the partial wavelength values recorded by the spectrochromosome to be mutated;

[0045] Use the spectro population that has completed the chromosome mutation operation as the spectro population obtained after performing one gene propagation iteration operation.

[0046] In an alternative embodiment, the method further includes:

[0047] Perform optical signal splitting processing on the spectral signal according to the expected splitting nodes of the spectral signal within the target wavelength range.

[0048] In a second aspect, the present application provides a spectral splitting node determination device, the device includes:

[0049] A parameter acquisition module, configured to acquire the gene mapping values corresponding to different wavelength values of the spectral signal detected by a target spectrometer within a target wavelength range;

[0050] A segmented coding module, configured to generate a plurality of wavelength segmentation threshold combinations within the target wavelength range according to a preset number of wavelength segmentation thresholds, and perform chromosome coding on each wavelength segmentation threshold combination according to the acquired all gene mapping values to obtain the spectrochromosomes corresponding to each wavelength segmentation threshold combination, where each wavelength segmentation threshold combination consists of the number of wavelength segmentation thresholds of the wavelength segmentation threshold;

[0051] A population verification module, configured to divide all the obtained spectrochromosomes into a preset number of spectro populations, and calculate the survival fitness value of each spectrochromosome, where each spectro population consists of a preset number of spectrochromosomes;

[0052] A population propagation module, configured to perform gene propagation iteration on the target chromosomes in each spectro population whose survival fitness values meet the preset survival conditions until the corresponding spectro population meets the preset iteration termination conditions;

[0053] A node confirmation module, configured to determine an expected spectral splitting node of the spectral signal within the target wavelength range according to a wavelength segmentation threshold combination corresponding to a target spectral splitting chromosome, where the target spectral splitting chromosome is a spectral splitting chromosome with the maximum survival fitness value among all spectral splitting populations that meet a preset iteration termination condition.

[0054] In an alternative embodiment, the apparatus further includes a range determination module;

[0055] The parameter acquisition module is further configured to acquire a codiable data volume and an expected coded data volume corresponding to a wavelength measurement range of the target spectrometer;

[0056] The range determination module is configured to, when the codiable data volume is greater than the expected coded data volume, determine a target wavelength range that meets the expected coded data volume within the wavelength measurement range according to the codiable data volume, the expected coded data volume, and the spectral resolution of the target spectrometer;

[0057] The range determination module is further configured to, when the codiable data volume is less than or equal to the expected coded data volume, directly use the wavelength measurement range as the target wavelength range.

[0058] In an alternative embodiment, the apparatus further includes:

[0059] A spectral splitting module, configured to perform optical signal splitting processing on the spectral signal according to the expected spectral splitting node of the spectral signal within the target wavelength range.

[0060] In a third aspect, the present application provides a computer device, including a processor and a memory, where the memory stores a computer program that can be executed by the processor, and the processor can execute the computer program to implement the spectral splitting node determination method according to any one of the foregoing embodiments.

[0061] In a fourth aspect, the present application provides a readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the spectral splitting node determination method according to any one of the foregoing embodiments is implemented.

[0062] In this case, the beneficial effects of the embodiments of the present application may include the following:

[0063] Based on the gene mapping values corresponding to different wavelength values within the target wavelength range of the spectral signals detected by the target spectrometer, the present application generates multiple spectral chromosomes corresponding to each wavelength segmentation threshold combination composed of the number of wavelength segmentation thresholds of the wavelength segments. Then, all the obtained spectral chromosomes are divided into a preset number of spectral populations composed of a preset number of spectral chromosomes, and the survival fitness value of each spectral chromosome is calculated. Then, for each spectral population, gene reproduction iteration is performed on the target chromosomes within the spectral population whose corresponding survival fitness values meet the preset survival conditions until the corresponding spectral population meets the preset iteration termination conditions. Finally, the target spectral chromosome with the maximum survival fitness value is extracted from all the spectral populations that meet the preset iteration termination conditions, and based on the wavelength segmentation threshold combination corresponding to the extracted target spectral chromosome, the expected spectral splitting nodes of the spectral signals within the target wavelength range are effectively determined, so as to be able to flexibly configure an adapted and maximally different interval optical signal splitting interval for the laser spectrometer for laser processing operations by using the genetic algorithm idea, effectively improving the optical detection accuracy and production operation applicability of the laser spectrometer, and effectively improving the monitoring accuracy of the laser processing quality.

[0064] To make the above objects, features, and advantages of the present application more obvious and understandable, the following specifically gives preferred embodiments and, in conjunction with the accompanying drawings, makes the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] To more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments. It should be understood that the following drawings only show some embodiments of the present application and should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0066] Figure 1 Schematic diagram of the composition of the computer device provided by the embodiment of the present application;

[0067] Figure 2 Schematic diagram of the process of the spectral splitting node determination method provided by the embodiment of the present application;

[0068] Figure 3 For Figure 2 Schematic diagram of the sub-steps included in step S210 in

[0069] Figure 4 Schematic diagram of the steps for calculating the survival fitness value of the spectral chromosome provided by the embodiment of the present application;

[0070] Figure 5 For Figure 2 Schematic diagram of the sub-steps included in step S240 in

[0071] Figure 6 This is the second flowchart diagram of the spectral splitting node determination method provided by the embodiments of the present application;

[0072] Figure 7 This is the third flowchart diagram of the spectral splitting node determination method provided by the embodiments of the present application;

[0073] Figure 8 This is the first composition diagram of the spectral splitting node determination device provided by the embodiments of the present application;

[0074] Figure 9 This is the second composition diagram of the spectral splitting node determination device provided by the embodiments of the present application.

[0075] Icon: 10 - Computer device; 11 - Memory; 12 - Processor; 13 - Communication unit; 100 - Spectral splitting node determination device; 110 - Parameter acquisition module; 120 - Segment coding module; 130 - Population verification module; 140 - Population reproduction module; 150 - Node confirmation module; 160 - Range determination module; 170 - Spectral splitting module. Detailed implementation manners

[0076] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Apparently, the described embodiments are some, but not all, of the embodiments of the present application. The components of the embodiments of the present application described and illustrated in the accompanying drawings here can be arranged and designed in various different configurations.

[0077] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the claimed present application, but merely represents selected embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts fall within the scope of protection of the present application.

[0078] It should be noted that: Similar reference numerals and letters denote similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0079] In the description of the present application, it should be understood that relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variation thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising a..." does not exclude the existence of additional identical elements in the process, method, article or device comprising the element. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0080] The following will describe in detail some embodiments of the present application with reference to the accompanying drawings. Without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0081] Please refer to Figure 1 , Figure 1 which is a schematic diagram of the composition of the computer device 10 provided by the embodiment of the present application. In the embodiment of the present application, the computer device 10 can flexibly configure an adapted and maximally different optical signal splitting interval for a laser spectrometer for laser processing operations by using the genetic algorithm idea, so as to greatly reduce the optical signal coupling between different optical signal splitting intervals. Thus, the optical signal splitting intervals configured can effectively improve the optical detection accuracy and production operation applicability of the laser spectrometer, and effectively improve the monitoring accuracy of the laser processing quality. Among them, the computer device can be, but is not limited to, a personal computer, a tablet computer, a smart phone, a server, a laptop computer, etc.

[0082] In the embodiment of the present application, the computer device 10 may include a memory 11, a processor 12, a communication unit 13 and a spectral splitting node determination device 100. Among them, the memory 11, the processor 12 and the communication unit 13 are directly or indirectly electrically connected to each other to realize data transmission or interaction. For example, these elements of the memory 11, the processor 12 and the communication unit 13 can be electrically connected to each other through one or more communication buses or signal lines.

[0083] In an embodiment of the present application, the memory 11 may be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc. Among them, the memory 11 is used to store a computer program, and after receiving an execution instruction, the processor 12 can execute the computer program accordingly.

[0084] In this embodiment, the processor 12 may be an integrated circuit chip with signal processing capabilities. The processor 12 may be a general-purpose processor, including at least one of a central processing unit (CPU), a graphics processing unit (GPU), a network processor (NP), a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc., which can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application.

[0085] In this embodiment, the communication unit 13 is used to establish a communication connection between the computer device 10 and other electronic devices through a network, and transmit and receive data through the network, where the network includes a wired communication network and a wireless communication network. For example, the computer device 10 may be communicatively connected to one or several laser spectrometers through the communication unit 13, and is used to obtain the spectral information of the process light that can actually be collected during the laser processing operation of the corresponding laser spectrometer, so as to determine the actual wavelength measurement range of the corresponding laser spectrometer for the laser processing operation, where the wavelength measurement range is used to describe the range of the optical signal wavelengths of the process light that can be collected by the corresponding laser spectrometer (for example, 350 nm to 1700 nm).

[0086] In an embodiment of the present application, the spectral spectrometry node determination device 100 may include at least one software function module that can be stored in the memory 11 in the form of software or firmware or fixed in the operating system of the computer device 10. The processor 12 can be used to execute the executable modules stored in the memory 11, such as the software function modules and computer programs included in the spectral spectrometry node determination device 100. The computer device 10 can flexibly configure an optical signal spectrometry interval that is adapted for laser processing operations and maximizes the interval difference for the laser spectrometer by using the idea of ​​genetic algorithm through the spectral spectrometry node determination device 100, so that the optical signal coupling between different optical signal spectrometry intervals is greatly reduced, so that the optical detection accuracy and production operation applicability of the laser spectrometer can be effectively improved through the configured multiple optical signal spectrometry intervals, and the monitoring accuracy of the laser processing quality can be effectively improved.

[0087] Understandably, Figure 1 The block diagram shown is only a schematic diagram of a composition of the computer device 10. The computer device 10 may also include Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown. Figure 1 Each component shown in the figure can be implemented by hardware, software or a combination thereof.

[0088] In the present application, in order to ensure that the computer device 10 can flexibly use the genetic algorithm idea to configure the laser spectrometer for the laser processing operation and maximize the interval difference of the optical signal spectrometry interval, so as to effectively improve the optical detection accuracy and production operation applicability of the laser spectrometer, and effectively improve the monitoring accuracy of the laser processing quality, the embodiment of the present application provides a method for determining the spectral spectrometry node to achieve the above-mentioned purpose. The spectral spectrometry node determination method provided by the present application is described in detail below.

[0089] Please refer to Figure 2 , Figure 2 This is one of the flow charts of the method for determining a spectral splitting node provided in the embodiment of the present application. In the embodiment of the present application, the method for determining a spectral splitting node may include steps S210 to S250.

[0090] Step S210, obtaining gene mapping values ​​corresponding to different wavelength values ​​of the spectral signal detected by the target spectrometer within the target wavelength range, and obtaining iterative configuration parameters for the target spectrometer.

[0091] In this embodiment, the iterative configuration parameters that can be stored in the computer device 10 for the target spectrometer may include a preset population number, a wavelength segmentation threshold number, and a preset chromosome number for each spectral population. The preset population number is used to represent the total number of populations that need to be iterated genetically when determining the spectral splitting boundary wavelength of the corresponding laser spectrometer. The wavelength segmentation threshold number is used to represent the total number of spectral splitting boundary wavelengths of the corresponding laser spectrometer within the target wavelength range. The preset chromosome number is used to represent the total number of spectral splitting chromosomes that need to be constructed within a single population. Each spectral splitting chromosome is formed by sequentially splicing the lower wavelength limit value that can be genetically encoded within the target wavelength range, the wavelength segmentation threshold number of wavelength segmentation thresholds, and the genetic encoding data of each lower wavelength limit value. The target wavelength range is the effective wavelength range within the wavelength measurement range of the target spectrometer that can be normally mapped to the range of genetically encoded data for genetic encoding.

[0092] In this embodiment, the gene mapping value of a certain wavelength value within the target wavelength range is used to represent the arrangement serial number value when the corresponding wavelength value is mapped to the binary gene encoding data range, so as to imitate the gene chain performance status through the binary coding rule. At this time, the gene encoding data of this wavelength value can be obtained by using the gene mapping value of the corresponding wavelength value for binary data expression. If the binary gene encoding data range is converted to decimal, the decimal gene encoding data range is 0 to (2^specific binary coding digits - 1).

[0093] Optionally, please refer to Figure 3 , Figure 3 Yes Figure 2 is the schematic flowchart of the sub-steps included in step S210 in

[0094] Sub-step S211: Calculate the difference between each wavelength value within the target wavelength range and the lower wavelength limit value of the target wavelength range to obtain a plurality of wavelength differences.

[0095] Sub-step S212: Calculate the quotient of each wavelength difference and the spectral resolution of the target spectrometer to obtain the gene mapping values corresponding to each wavelength value within the target wavelength range.

[0096] In this embodiment, the spectral resolution is used to represent the minimum wavelength interval (e.g., 0.02 nm) for the target spectrometer to detect spectral radiation energy. The computer device 10 can effectively determine the maximum gene coding data range adaptable to the wavelength detection range of the target spectrometer based on the spectral resolution of the target spectrometer. Then, by mapping each wavelength value within the target wavelength range of the target spectrometer to the maximum gene coding data range, gene mapping values corresponding to each wavelength value within the target wavelength range are obtained. At this time, each gene coding data within the gene coding data range corresponds to a wavelength value within the target wavelength range, and the gene mapping value can be used to represent the wavelength difference condition of the corresponding wavelength value relative to the wavelength lower limit value that can be gene-coded when mapped to the gene coding data range.

[0097] Taking the above target wavelength range of 89.3 nm to 1700 nm and a spectral resolution of 0.02 as an example, the wavelength lower limit value of the target wavelength range is 389.3 nm, the wavelength upper limit value of the target wavelength range is 1700 nm, and the wavelength difference between two adjacent wavelength values within the target wavelength range is 0.02 nm. Among them, the gene mapping values corresponding to the wavelength values of 600 nm and 1100 nm within the gene coding data range that conforms to the 16-bit binary coding rule are 10535 and 35535 respectively, and the gene coding data of these two wavelength values are 0010100100100111 and 1000101011001111 respectively.

[0098] Thus, the present application can effectively determine the gene mapping values of different wavelength values that can be gene-coded for the spectral signal detected by the target spectrometer within the target wavelength range by executing the above sub-steps S211 and S212.

[0099] Step S220: Generate a plurality of wavelength segmentation threshold combinations within the target wavelength range according to the preset number of wavelength segmentation thresholds, and perform chromosome coding on each wavelength segmentation threshold combination based on the obtained gene mapping values to obtain the spectral splitting chromosomes corresponding to each wavelength segmentation threshold combination.

[0100] In this embodiment, each wavelength segmentation threshold combination is composed of a number of wavelength segmentation thresholds equal to the preset number of wavelength segmentation thresholds. Each of the wavelength segmentation thresholds is randomly selected by the computer device 10 within the target wavelength range. At this time, each spectral splitting chromosome can be formed by sequentially splicing the gene coding data of the wavelength lower limit value, the randomly selected number of wavelength segmentation thresholds, and the wavelength upper limit value within the target wavelength range.

[0101] Taking the above-mentioned target wavelength range of 389.3 nm to 1700 nm and the spectral resolution of 0.02 as an example, if the number of wavelength segmentation thresholds is 2, and the randomly selected wavelength segmentation thresholds are 600 nm and 1100 nm, then within this target wavelength range, the gene mapping value wavelength of the lower wavelength limit value of 389.3 nm is 0, the gene coding data of the lower wavelength limit value of 389.3 nm is 0000000000000000, the gene mapping value wavelength of the upper wavelength limit value of 1700 nm is 65535, the gene coding data of the upper wavelength limit value of 1700 nm is 1111111111111111, and the gene coding data of the two wavelength segmentation thresholds are 0010100100100111 and 1000101011001111 respectively. At this time, the corresponding spectral chromosome is 0000000000000000_0010100100100111_1000101011001111_1111111111111111.

[0102] Step S230, divide all the obtained spectral chromosomes into a preset number of spectral populations, and calculate the survival fitness value of each spectral chromosome.

[0103] In this embodiment, each spectral population is composed of a preset number of spectral chromosomes; the preset number of populations can be 1 or multiple; each spectral chromosome within each spectral population corresponds to a chromosome serial number, and the spectral chromosomes within the same spectral population are arranged in descending or ascending order according to the chromosome serial number. The survival fitness value can be used to represent the survival probability of the corresponding spectral chromosome in the process of natural selection.

[0104] Optionally, please refer to Figure 4 , Figure 4 is a schematic diagram of the steps for calculating the survival fitness value of the spectral chromosome provided by the embodiment of the present application. In the embodiment of the present application, for each spectral chromosome, the steps for calculating the survival fitness value of the spectral chromosome may include Step S310 to Step S360.

[0105] Step S310, calculate the ratio between the gene mapping value of each wavelength value within the target wavelength range and the sum value of all the gene mapping values within the target wavelength range, to obtain the wavelength mapping proportion of each wavelength value within the target wavelength range.

[0106] Among them, the wavelength mapping proportion is used to represent the proportion relationship of the gene mapping value of the corresponding wavelength value relative to the sum value of all the obtained gene mapping values.

[0107] Step S320: Using the wavelength mapping proportion of each wavelength value within the target wavelength range as the mapping weight, perform a weighted sum of the gene mapping values of all wavelength values within the target wavelength range to obtain the spectral mapping proportion mean of the target wavelength range.

[0108] Step S330: Divide the target wavelength range into multiple spectral bands according to the wavelength segmentation threshold combination corresponding to the spectral chromosome, obtaining multiple spectral bands.

[0109] Among them, if the number of wavelength segmentation thresholds is 1, the number of bands corresponding to the spectral band is 2; if the number of wavelength segmentation thresholds is 2, the number of bands corresponding to the spectral band is 3. Thus, the total number of bands of the spectral band is obtained by adding one to the number of wavelength segmentation thresholds, and there are multiple wavelength values distributed at intervals according to the spectral resolution within each spectral band.

[0110] Step S340: Calculate the sum value between the wavelength mapping proportions of each wavelength value within each spectral band to obtain the wavelength mapping proportion sum value corresponding to each spectral band.

[0111] Among them, the wavelength mapping proportion sum value of the same spectral band is the sum value between the wavelength mapping proportions of each wavelength value within this spectral band.

[0112] Step S350: For each spectral band, calculate the band fitness value of this spectral band according to the spectral mapping proportion mean, the wavelength mapping proportion sum value of this spectral band, and the gene mapping values and wavelength mapping proportions of each wavelength value within this spectral band.

[0113] In this embodiment, the band fitness value is used to characterize the survival ability of the corresponding spectral band being naturally selected during the natural selection simulation process. In an implementation manner of this embodiment, for a single spectral band, the step of calculating the band fitness value of this spectral band according to the spectral mapping proportion mean, the wavelength mapping proportion sum value of this spectral band, and the gene mapping values and wavelength mapping proportions of each wavelength value within this spectral band may include:

[0114] Using the wavelength mapping proportion of the gene mapping values of each wavelength value within this spectral band as the mapping weight, perform a weighted sum of the gene mapping values of each wavelength value within this spectral band to obtain the band mapping proportion mean of this spectral band;

[0115] Calculate the ratio between the band mapping proportion mean of this spectral band and the wavelength mapping proportion sum value to obtain the band appearance probability of this spectral band;

[0116] Perform a perfect square difference operation on the band appearance probability of this spectral band and the spectral mapping proportion mean to obtain the band fitness value of this spectral band.

[0117] Among them, the above perfect square difference operation can be expressed as: the band fitness value of a single spectral band = (the probability of occurrence of the spectral band - the average value of the spectral mapping ratio of the target wavelength range)^2.

[0118] It can be understood that in addition to the above band fitness calculation process, any other fitness calculation formula disclosed in the prior art can be applied to the above step S50 to calculate the band fitness values of different spectral bands under the same division method from different dimensions.

[0119] Step S360, using the sum of the wavelength mapping ratios of each spectral band as the band weight, perform weighted summation on the band fitness values of all spectral bands respectively to obtain the survival fitness value of this spectral chromosome.

[0120] Thus, this application can calculate the survival fitness value of a single spectral chromosome by executing the above steps S310 to S360.

[0121] Step S240, perform gene reproduction iteration on the target chromosomes in each spectral population whose survival fitness values meet the preset survival conditions until the corresponding spectral population meets the preset iteration termination conditions.

[0122] In this embodiment, the preset survival conditions can be expressed in a manner that conforms to natural selection. For each spectral population, after the computer device 10 determines the spectral chromosomes in this spectral population that do not meet the preset survival conditions, it can reconstruct a new spectral chromosome whose corresponding survival fitness value meets the preset survival conditions with reference to the above step S220 to replace the spectral chromosome that does not meet the preset survival conditions, so as to perform chromosome re - coding on all spectral chromosomes in each spectral population that do not meet the preset survival conditions, so that all the final existing spectral chromosomes in each spectral population are target chromosomes whose corresponding survival fitness values meet the preset survival conditions. At this time, the corresponding spectral population will also conform to natural selection.

[0123] Then, for each spectral population that conforms to natural selection, the computer device 10 will perform at least one gene reproduction iteration operation on the target chromosomes in this spectral population until the finally iterated spectral chromosomes substantially meet the preset iteration termination conditions. At this time, the spectral population to which the finally iterated spectral chromosomes belong is a spectral population that meets the preset iteration termination conditions.

[0124] In this process, it can be understood that after each execution of the gene reproduction iteration operation, the above-mentioned chromosome re-encoding method can be used to update the chromosomes for the spectral population obtained after the gene reproduction iteration, so as to ensure that each spectral chromosome in the spectral population obtained after the corresponding gene reproduction iteration is the target chromosome. Only then will the computer device 10 perform the next gene reproduction iteration operation on the spectral population after chromosome update, so as to ensure the population survival rate of the spectral population.

[0125] In addition, the preset iteration termination condition can be the number of iterations configured for the gene reproduction operation (for example, 5 times); the preset iteration termination condition can also be that the fitness mean / fitness variance / fitness standard deviation among the survival fitness values of each spectral chromosome in the iterated spectral population exceeds a preset value; the preset iteration termination condition can also be that there is a spectral chromosome composed of specific gene coding data in the iterated spectral population; where the preset iteration termination condition can be configured differently by the operator of the target spectrometer according to needs.

[0126] Optionally, for a single spectral chromosome, the steps of detecting whether the survival fitness value of the spectral chromosome meets the preset survival condition may include:

[0127] For each spectral chromosome, use a random number generation algorithm to generate a random fitness threshold corresponding to the spectral chromosome;

[0128] Compare the survival fitness value of the spectral chromosome with the corresponding random fitness threshold;

[0129] If the individual fitness value of the spectral chromosome is greater than the corresponding random fitness threshold, mark the spectral chromosome as the target chromosome that meets natural selection;

[0130] If the individual fitness value of the spectral chromosome is less than or equal to the corresponding random fitness threshold, mark the spectral chromosome as a spectral chromosome that does not meet natural selection.

[0131] Optionally, please refer to Figure 5 , Figure 5 Yes Figure 2 is the flowchart of the sub-steps included in step S240 in

[0132] Sub-step S241, randomly select at least one chromosome group to be reproduced from the target chromosomes in the spectral population according to the preset population reproduction probability, where each chromosome group to be reproduced includes two adjacent target chromosomes in sequence number.

[0133] In this embodiment, the population reproduction probability is used to represent the specific probability of chromosome reproduction between adjacent spectral chromosomes within the corresponding population.

[0134] Sub-step S242: For each chromosome group to be reproduced, perform data exchange on the gene coding data of the partial wavelength values corresponding to the splicing positions of the two target chromosomes included in the chromosome group to be reproduced.

[0135] Among them, the coding splicing positions of one or several wavelength values for which gene coding data needs to be exchanged can be randomly selected from the two spectral chromosomes within a single chromosome group to be reproduced. The coding splicing positions for which gene coding data needs to be exchanged in the two spectral chromosomes are kept consistent. Then, perform data exchange on the gene coding data of the partial wavelength values corresponding to the corresponding coding splicing positions of the two spectral chromosomes to obtain two new spectral chromosomes, thereby completing the chromosome reproduction operation for the chromosome group to be reproduced. Among them, the partial wavelength values may include the lower limit value of the wavelength within the above-mentioned target wavelength range, may also include the upper limit value of the wavelength within the above-mentioned target wavelength range, or may not include the upper limit value and the lower limit value of the wavelength within the above-mentioned target wavelength range.

[0136] Taking the example that the two spectral chromosomes within the same chromosome group to be reproduced are each obtained by sequentially splicing the gene coding data of 5 optical wavelength values (including the upper limit value and the lower limit value of the wavelength within the above-mentioned target wavelength range), the gene coding data of the first three optical wavelength values of the two spectral chromosomes can be exchanged to obtain two new spectral chromosomes; the gene coding data of the last three optical wavelength values of the two spectral chromosomes can also be exchanged to obtain two new spectral chromosomes; or the gene coding data of one optical wavelength value in the middle of the two spectral chromosomes can be exchanged to obtain two new spectral chromosomes.

[0137] Sub-step S243: Randomly select at least one spectral chromosome to be mutated from the spectral population after the chromosome reproduction operation according to the preset population mutation probability.

[0138] In this embodiment, the population mutation probability is used to represent the probability of gene coding mutation for each spectral chromosome within the corresponding population.

[0139] Sub-step S244: For each spectral chromosome to be mutated, perform gene coding adjustment on the gene coding data of the partial wavelength values recorded by the spectral chromosome to be mutated.

[0140] In this embodiment, the partial wavelength values corresponding to the spectrochromosomes to be mutated that require gene coding adjustment may include the lower wavelength limit value of the above target wavelength range, may also include the upper wavelength limit value of the above target wavelength range, or may not include the upper wavelength limit value and the lower wavelength limit value of the above target wavelength range. The gene coding adjustment process of the partial wavelength values can be achieved by adding / subtracting a specific number (e.g., 3) to / from the gene coding data of the partial wavelength values in the spectrochromosome to be mutated, or by performing bitwise OR / AND / XOR operations on the gene coding data of the partial wavelength values in the spectrochromosome to be mutated using a specific mask with the binary coding bits.

[0141] Sub-step S245: Use the spectro population that has completed the chromosome mutation operation as the spectro population obtained after performing one gene reproduction iteration operation.

[0142] Thus, this application can complete the gene reproduction iteration operation for all target chromosomes within a single spectro population by executing the above sub-steps S241 to S245.

[0143] Step S250: Determine the expected spectro nodes of the spectral signal within the target wavelength range according to the wavelength segmentation threshold combination corresponding to the target spectrochromosome.

[0144] In this embodiment, after the computer device 10 obtains multiple spectrochromosomes included in all spectro populations that meet the preset iteration termination conditions, it will screen out the target spectrochromosome with the largest corresponding survival fitness value from all the spectrochromosomes obtained by iteration. Then, for the selected target spectrochromosome, by removing the gene coding data corresponding to the upper wavelength limit value and the lower wavelength limit value of the above target wavelength range in the target spectrochromosome, a binary gene coding data obtained by splicing the gene coding data of each of the wavelength segmentation threshold numbers of wavelength segmentation thresholds is obtained. Then, according to the binary coding bits, the binary gene coding data is split into the gene coding data of each of the wavelength segmentation threshold numbers of wavelength segmentation thresholds, and the gene coding data of each wavelength segmentation threshold is converted to a decimal number to obtain the gene mapping value corresponding to the wavelength segmentation threshold. Furthermore, based on the lower wavelength limit value of the above target wavelength range and the spectral resolution, the specific wavelength value of this wavelength segmentation threshold is calculated, so that the calculated wavelength segmentation threshold numbers of wavelength segmentation thresholds can be used as the expected spectro nodes when the spectral signal detected by the target spectrometer is spectroscopically analyzed within the above target wavelength range. At this time, the computer device 10 can effectively divide the wavelength measurement range of the target spectrometer into multiple optical signal spectroscopically analyzed intervals with maximized interval differences based on the determined expected spectro nodes, so as to effectively improve the optical detection accuracy and production operation applicability of the laser spectrometer, and effectively improve the monitoring accuracy of the laser processing quality.

[0145] Thus, this application can flexibly configure an adaptable and maximally interval-differentiated optical signal splitting interval for a laser spectrometer for laser processing operations by performing the above steps S210 to S250 using the genetic algorithm idea, greatly reducing the optical signal coupling between different optical signal splitting intervals. Therefore, through the configured multiple optical signal splitting intervals, the optical detection accuracy and production operation applicability of the laser spectrometer can be effectively improved, and the monitoring accuracy of the laser processing quality can be effectively improved.

[0146] Optionally, please refer to Figure 6 , Figure 6 FIG. 2 is a second flowchart of the spectral splitting node determination method provided by an embodiment of this application. In the embodiment of this application, before performing the above step S210, the spectral splitting node determination method may further include steps S207 to S209 to effectively determine a target wavelength range that can implement gene coding within the wavelength measurement range of the target spectrometer.

[0147] Step S207: Obtain the encodable data volume and the expected encoding data volume corresponding to the wavelength measurement range of the target spectrometer.

[0148] In this embodiment, the encodable data volume is used to represent the total number of encodings when gene coding operations are performed on all wavelength values within the wavelength measurement range of the target spectrometer, and the expected encoding data volume is used to represent the maximum number of encodings that limit the target wavelength range of the target spectrometer.

[0149] Optionally, the step of obtaining the encodable data volume and the expected encoding data volume corresponding to the wavelength measurement range of the target spectrometer may include:

[0150] Calculate the difference between the upper wavelength value and the lower wavelength value of the wavelength measurement range to obtain the corresponding wavelength interval value;

[0151] Calculate the quotient of the wavelength interval value and the spectral resolution to obtain the encodable data volume corresponding to the wavelength measurement range;

[0152] Determine the number of binary encoding digits whose corresponding encoding quantity is closest to the encodable data volume;

[0153] Use the encoding quantity corresponding to the number of binary encoding digits as the expected encoding data volume corresponding to the wavelength measurement range.

[0154] Among them, for the binary encoding rule, when the number of binary encoding digits is set, the corresponding expected encoding data volume is the power of 2 to the number of binary encoding digits. Thus, the computer device 10 can determine the number of binary encoding digits that is most adaptable to the encodable data volume of the wavelength measurement range.

[0155] Taking the wavelength measurement range of 350 nm to 1700 nm and the spectral resolution of 0.02 as an example, the corresponding encodable data volume is (1700 - 350) / 0.02 = 67500. At this time, the expected encoded data volume closest to this encodable data volume is 2^16 = 65536, and the corresponding binary encoding bits are 16. Therefore, the gene encoding data range that conforms to the binary encoding rule is 0000000000000000 to 1111111111111111, and the data range after converting this gene encoding data range to decimal is 0 to 65535.

[0156] Thus, the present application can determine the maximum gene encoding volume and the specific gene encoding result content when performing gene encoding on different wavelength values within the wavelength measurement range of the spectral signal detected by the target spectrometer by executing the specific step flow included in the above sub-step S207.

[0157] Sub-step S208, in the case where the encodable data volume is greater than the expected encoded data volume, determine a target wavelength range that conforms to the expected encoded data volume within the wavelength measurement range according to the encodable data volume, the expected encoded data volume, and the spectral resolution of the target spectrometer.

[0158] In this embodiment, if the encodable data volume is greater than the expected encoded data volume, it means that all wavelength values in the current wavelength measurement range cannot be fully gene-encoded, and the computer device 10 needs to screen out the optical wavelength values that can be gene-encoded from the wavelength measurement range.

[0159] Optionally, the step of determining a target wavelength range that conforms to the expected encoded data volume within the wavelength measurement range according to the encodable data volume, the expected encoded data volume, and the spectral resolution of the target spectrometer may include:

[0160] Calculate the difference between the encodable data volume and the expected encoded data volume to obtain the corresponding encoding volume difference;

[0161] Calculate the product of the encoding volume difference and the spectral resolution to obtain the length of the wavelength interval to be discarded in the wavelength measurement range;

[0162] Starting from the lower wavelength limit value of the wavelength measurement range, discard the band corresponding to the length of the wavelength interval to be discarded within the wavelength measurement range to obtain the target wavelength range.

[0163] Among them, since the radiation energy in the short wavelength band is weak during the laser processing, its influence on the monitoring accuracy of the entire laser processing quality is not significant. Therefore, when the computer device 10 screens the light wavelength values that can be gene-encoded, a to-be-discarded short wavelength band range can be constructed at the lower wavelength limit value of the wavelength measurement range according to the length of the to-be-discarded wavelength interval, and then directly discard this to-be-discarded short wavelength band range within the wavelength measurement range, that is, the target wavelength range that can be normally mapped into the gene-encoded data range for gene encoding is obtained.

[0164] For each light wavelength value within the target wavelength range, the gene mapping value of this light wavelength value within the gene-encoded data range = (this light wavelength value - the lower wavelength limit value of the target wavelength range) / spectral resolution. At this time, the gene-encoded data of this light wavelength value within the binary gene-encoded data range can be obtained by binary encoding the gene mapping value of this light wavelength value according to the above-mentioned binary encoding bits.

[0165] Taking the above wavelength measurement range of 350nm - 1700nm and the spectral resolution of 0.02 as an example, the encodable data volume (i.e., 67500) is greater than the expected encoding data volume (i.e., 65536) closest to this encodable data volume. Then the length of the to-be-discarded wavelength interval is (67500 - 65536) * 0.02nm = 39.28nm, and the corresponding to-be-discarded short wavelength band range is 350nm - 389.28nm. At this time, the target wavelength range after removing the to-be-discarded short wavelength band range from the wavelength measurement range is 389.3nm - 1700nm, where the lower wavelength limit value of the target wavelength range is 389.3nm, the upper wavelength limit value of the target wavelength range is 1700nm, and the wavelength difference between two adjacent wavelength values within the target wavelength range is 0.02nm. Among them, the gene mapping values corresponding to the wavelength values 600nm and 1100nm within the gene-encoded data range that conform to the 16-bit binary encoding rule are 10535 and 35535 respectively, and the gene-encoded data of these two wavelength values are 0010100100100111 and 1000101011001111 respectively.

[0166] Step S209, in the case where the encodable data volume is less than or equal to the expected encoding data volume, directly use the wavelength measurement range as the target wavelength range.

[0167] In this embodiment, if the encodable data volume is less than or equal to the expected encoding data volume, it means that all the light wavelength values in the current wavelength measurement range can be gene-encoded, and this wavelength measurement range is the target wavelength range.

[0168] Thus, by performing the above steps S207 to S209, the present application can effectively determine the target wavelength range that can achieve gene encoding within the wavelength measurement range of the target spectrometer.

[0169] Optionally, please refer to Figure 7 , Figure 7 which is the third schematic flowchart of the spectral splitting node determination method provided by the embodiments of the present application. In the embodiments of the present application, compared with the spectral splitting node determination methods shown in Figure 2 or Figure 7 , the spectral splitting node determination method shown in Figure 7 may further include step S260.

[0170] Step S260: Perform optical signal splitting processing on the spectral signal according to the expected splitting nodes of the spectral signal within the target wavelength range.

[0171] In this embodiment, after obtaining the expected splitting nodes of the target spectrometer within the target wavelength range, the computer device 10 can directly use the wavelength values corresponding to the respective expected splitting nodes as the band division boundary lines, divide the wavelength measurement range of the target spectrometer into multiple splitting bands, and allocate each optical signal included in the obtained spectral signal to each splitting band according to the spectral wavelength distribution, so as to implement the optical signal splitting operation on the laser radiation spectral information.

[0172] Thus, the present application can perform the optical signal splitting operation on the laser radiation spectral information according to the flexibly configured optical signal splitting interval by executing the above step S260.

[0173] In the present application, to ensure that the computer device 10 can effectively execute the above spectral splitting node determination method, the present application realizes the foregoing functions by means of functional module division of the spectral splitting node determination device 100 stored in the computer device 10. The following describes the specific composition of the spectral splitting node determination device 100 applied to the above computer device 10 provided by the present application.

[0174] Please refer to Figure 8 , Figure 8 which is the first schematic diagram of the composition of the spectral splitting node determination device 100 provided by the embodiments of the present application. In the embodiments of the present application, the spectral splitting node determination device 100 may include a parameter acquisition module 110, a segmentation encoding module 120, a population verification module 130, a population reproduction module 140, and a node confirmation module 150.

[0175] The parameter acquisition module 110 is configured to acquire the gene mapping values corresponding to different wavelength values of the spectral signal detected by the target spectrometer within the target wavelength range.

[0176] The segmented coding module 120 is configured to generate a plurality of wavelength segmented threshold combinations within a target wavelength range according to the number of wavelength segmentation thresholds, and perform chromosome coding on each wavelength segmented threshold combination according to the obtained gene mapping value to obtain spectral chromosomes corresponding to the respective wavelength segmented threshold combinations, where each wavelength segmented threshold combination is composed of the number of wavelength segmentation thresholds of wavelength segments.

[0177] The population verification module 130 is configured to divide all the obtained spectral chromosomes into a preset number of spectral populations, and calculate the survival fitness value of each spectral chromosome, where each spectral population is composed of a preset number of spectral chromosomes.

[0178] The population reproduction module 140 is configured to perform gene reproduction iteration on the target chromosomes in each spectral population whose survival fitness value meets the preset survival condition until the corresponding spectral population meets the preset iteration termination condition.

[0179] The node confirmation module 150 is configured to determine the expected spectral splitting node of the spectral signal within the target wavelength range according to the wavelength segmented threshold combination corresponding to the target spectral chromosome, where the target spectral chromosome is the spectral chromosome with the maximum survival fitness value in all spectral populations that meet the preset iteration termination condition.

[0180] Optionally, please refer to Figure 9 , Figure 9 FIG. is the second schematic diagram of the composition of the spectral splitting node determination device 100 provided by the embodiment of the present application. In the embodiment of the present application, the spectral splitting node determination device 100 may further include a range determination module 160.

[0181] The parameter acquisition module 110 is further configured to acquire the amount of encodable data and the expected amount of encoded data corresponding to the wavelength measurement range of the target spectrometer.

[0182] The range determination module 160 is configured to, when the amount of encodable data is greater than the expected amount of encoded data, determine a target wavelength range that meets the expected amount of encoded data within the wavelength measurement range according to the amount of encodable data, the expected amount of encoded data, and the spectral resolution of the target spectrometer.

[0183] The range determination module 160 is further configured to, when the amount of encodable data is less than or equal to the expected amount of encoded data, directly use the wavelength measurement range as the target wavelength range.

[0184] Optionally, in the embodiment of the present application, the spectral splitting node determination device 100 may further include a spectral splitting module 170.

[0185] The spectral splitting module 170 is configured to perform optical signal splitting processing on the spectral signal according to the expected splitting nodes of the spectral signal within the target wavelength range.

[0186] It should be noted that the spectral splitting node determination device 100 provided in the embodiments of the present application has the same basic principle and technical effects as the aforementioned spectral splitting node determination method. For the sake of brief description, for the parts not mentioned in this embodiment, reference can be made to the description of the spectral splitting node determination method above.

[0187] In the present application, the embodiments of the present application also provide a readable storage medium storing a computer program, which includes a number of machine instructions for causing a processor of an electronic device to execute the computer program to implement any of the above spectral splitting node determination methods. Among them, the computer program can be implemented in the form of software function modules.

[0188] In summary, in a spectral splitting node determination method, device, computer device, and readable storage medium provided in the embodiments of the present application, the present application generates a plurality of splitting chromosomes corresponding to each of the wavelength segment threshold combinations composed of the number of wavelength segment thresholds according to the gene mapping values corresponding to different wavelength values of the spectral signal detected by the target spectrometer within the target wavelength range. Then, all the obtained splitting chromosomes are divided into a preset number of splitting populations composed of a preset number of splitting chromosomes, and the survival fitness value of each splitting chromosome is calculated. Then, for each splitting population, genetic reproduction iteration is performed on the target chromosomes in the splitting population whose corresponding survival fitness values meet the preset survival conditions until the corresponding splitting population meets the preset iteration termination conditions. Finally, the target splitting chromosome with the maximum survival fitness value is extracted from all the splitting populations that meet the preset iteration termination conditions, and according to the wavelength segment threshold combination corresponding to the extracted target splitting chromosome, the expected splitting nodes of the spectral signal within the target wavelength range are effectively determined, so as to flexibly configure an adaptable and interval-differentiated optical signal splitting interval for the laser spectrometer for laser processing operations by using the genetic algorithm idea, effectively improving the optical detection accuracy and production operation applicability of the laser spectrometer, and effectively improving the monitoring accuracy of the laser processing quality.

[0189] The above are only various embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present application, and all should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for determining a spectral splitting node, characterized in that, the method includes: obtaining gene mapping values corresponding to different wavelength values within a target wavelength range of a spectral signal detected by a target spectrometer; generating a plurality of wavelength segmentation threshold combinations within the target wavelength range according to a preset number of wavelength segmentation thresholds, and performing chromosome coding on each wavelength segmentation threshold combination according to the obtained gene mapping values to obtain spectral chromosomes respectively corresponding to the wavelength segmentation threshold combinations, wherein each wavelength segmentation threshold combination is composed of the number of wavelength segmentation thresholds of the wavelength segmentation threshold; dividing all the obtained spectral chromosomes into a preset number of spectral populations, and calculating the survival fitness value of each spectral chromosome, wherein each spectral population is composed of a preset number of spectral chromosomes; performing gene reproduction iteration on target chromosomes whose survival fitness values in each spectral population meet a preset survival condition until the corresponding spectral population meets a preset iteration termination condition; determining an expected spectral splitting node of the spectral signal within the target wavelength range according to the wavelength segmentation threshold combination corresponding to the target spectral chromosome, wherein the target spectral chromosome is the spectral chromosome with the maximum survival fitness value in all spectral populations that meet the preset iteration termination condition.

2. The method according to claim 1, characterized in that, the method further includes: obtaining the amount of encodable data and the expected amount of encoded data corresponding to the wavelength measurement range of the target spectrometer; in the case where the amount of encodable data is greater than the expected amount of encoded data, determining the target wavelength range that meets the expected amount of encoded data within the wavelength measurement range according to the amount of encodable data, the expected amount of encoded data, and the spectral resolution of the target spectrometer; in the case where the amount of encodable data is less than or equal to the expected amount of encoded data, directly using the wavelength measurement range as the target wavelength range.

3. The method according to claim 2, characterized in that, the step of obtaining the amount of encodable data and the expected amount of encoded data corresponding to the wavelength measurement range of the target spectrometer includes: calculating the difference between the upper wavelength value and the lower wavelength value of the wavelength measurement range to obtain a corresponding wavelength interval value; calculating the quotient of the wavelength interval value and the spectral resolution to obtain the amount of encodable data corresponding to the wavelength measurement range; determining the number of binary coding bits whose corresponding coding quantity is closest to the amount of encodable data; using the coding quantity corresponding to the number of binary coding bits as the expected amount of encoded data corresponding to the wavelength measurement range.

4. The method according to claim 2, characterized in that, the step of determining the target wavelength range that meets the expected amount of encoded data within the wavelength measurement range according to the amount of encodable data, the expected amount of encoded data, and the spectral resolution of the target spectrometer includes: calculating the difference between the amount of encodable data and the expected amount of encoded data to obtain a corresponding coding quantity difference; Calculate the product of the difference in the amount of coding and the spectral resolution to obtain the length of the wavelength interval to be discarded within the wavelength measurement range; Starting from the lower limit value of the wavelength within the wavelength measurement range, discard the wavelength band corresponding to the length of the wavelength interval to be discarded within the wavelength measurement range to obtain the target wavelength range.

5. The method according to claim 1, wherein, the step of obtaining the gene mapping values corresponding to different wavelength values within the target wavelength range of the spectral signal detected by the target spectrometer includes: Calculate the difference between each wavelength value within the target wavelength range and the lower limit value of the wavelength within the target wavelength range respectively to obtain a plurality of wavelength differences; Calculate the quotient of each wavelength difference and the spectral resolution of the target spectrometer to obtain the gene mapping values corresponding to the respective wavelength values within the target wavelength range.

6. The method according to any one of claims 1-5, wherein, the step of calculating the survival fitness value of each spectral chromosome includes: Calculate the ratio of the gene mapping value of each wavelength value within the target wavelength range to the sum value of all gene mapping values within the target wavelength range to obtain the wavelength mapping ratio of each wavelength value within the target wavelength range; Using the wavelength mapping ratio of each wavelength value within the target wavelength range as the mapping weight, perform weighted summation on the gene mapping values of all wavelength values within the target wavelength range respectively to obtain the average value of the spectral mapping ratio within the target wavelength range; Perform band division on the target wavelength range according to the wavelength segmentation threshold combination corresponding to the spectral chromosome to obtain a plurality of spectral bands; Calculate the sum value of the wavelength mapping ratios within each spectral band to obtain the sum value of the wavelength mapping ratios corresponding to each spectral band; For each spectral band, calculate the band fitness value of the spectral band according to the average value of the spectral mapping ratio, the sum value of the wavelength mapping ratios of the spectral band, and the gene mapping values and wavelength mapping ratios of the wavelength values within the spectral band; Using the sum value of the wavelength mapping ratios of each spectral band as the band weight, perform weighted summation on the band fitness values of all spectral bands respectively to obtain the survival fitness value of the spectral chromosome.

7. The method according to claim 6, wherein, the step of calculating the band fitness value of the spectral band according to the average value of the spectral mapping ratio, the sum value of the wavelength mapping ratios of the spectral band, and the gene mapping values and wavelength mapping ratios of the wavelength values within the spectral band includes: Using the wavelength mapping ratio of the gene mapping values of the wavelength values within the spectral band as the mapping weight, perform weighted summation on the gene mapping values of the wavelength values within the spectral band to obtain the average value of the band mapping ratio of the spectral band; Calculate the ratio of the average value of the band mapping ratio of the spectral band to the sum value of the wavelength mapping ratios to obtain the band occurrence probability of the spectral band; Perform a perfect square difference operation on the band occurrence probability of the spectral band and the average value of the spectral mapping ratio to obtain the band fitness value of the spectral band.

8. The method according to any one of claims 1-5, characterized in that, each spectral chromosome is formed by sequentially splicing the gene coding data of the lower limit value of the wavelength within the target wavelength range, the number of wavelength segmentation thresholds randomly selected, and the upper limit value of the wavelength. The steps of performing one gene reproduction iteration on the target chromosome within a single spectral population include: randomly selecting at least one chromosome group to be reproduced from the target chromosomes within the spectral population according to a preset population reproduction probability, where each chromosome group to be reproduced includes two adjacent target chromosomes in sequence number; for each chromosome group to be reproduced, perform data exchange on the gene coding data of the partial wavelength values corresponding to each other in the splicing positions of the two target chromosomes included in the chromosome group to be reproduced; randomly selecting at least one spectral chromosome to be mutated from the spectral population after the chromosome reproduction operation according to a preset population mutation probability; for each spectral chromosome to be mutated, perform gene coding adjustment on the gene coding data of the partial wavelength values recorded by the spectral chromosome to be mutated; take the spectral population after the chromosome mutation operation as the spectral population obtained after performing one gene reproduction iteration operation.

9. The method according to any one of claims 1-5, characterized in that, the method further includes: performing optical signal splitting processing on the spectral signal according to the expected splitting node of the spectral signal within the target wavelength range.

10. A spectral splitting node determination device, characterized in that, the device includes: a parameter acquisition module, configured to acquire the gene mapping values corresponding to different wavelength values of the spectral signal detected by a target spectrometer within a target wavelength range; a segmentation coding module, configured to generate a plurality of wavelength segmentation threshold combinations within the target wavelength range according to a preset number of wavelength segmentation thresholds, and perform chromosome coding on each wavelength segmentation threshold combination according to the acquired all gene mapping values to obtain spectral chromosomes corresponding to each wavelength segmentation threshold combination, where each wavelength segmentation threshold combination is composed of the number of wavelength segmentation thresholds; a population verification module, configured to divide all the obtained spectral chromosomes into a preset number of spectral populations, and calculate the survival fitness value of each spectral chromosome, where each spectral population is composed of a preset number of spectral chromosomes; a population reproduction module, configured to perform gene reproduction iteration on the target chromosomes within each spectral population whose survival fitness value meets a preset survival condition until the corresponding spectral population meets a preset iteration termination condition; a node confirmation module, configured to determine the expected splitting node of the spectral signal within the target wavelength range according to the wavelength segmentation threshold combination corresponding to the target spectral chromosome, where the target spectral chromosome is the spectral chromosome with the maximum survival fitness value within all spectral populations that meet the preset iteration termination condition.

11. The device according to claim 10, characterized in that, the device further includes a range determination module; The parameter acquisition module is further configured to acquire the encodable data volume and the desired encoded data volume corresponding to the wavelength measurement range of the target spectrometer; The range determination module is configured to, when the encodable data volume is greater than the desired encoded data volume, determine the target wavelength range that meets the desired encoded data volume within the wavelength measurement range according to the encodable data volume, the desired encoded data volume, and the spectral resolution of the target spectrometer; The range determination module is further configured to, when the encodable data volume is less than or equal to the desired encoded data volume, directly use the wavelength measurement range as the target wavelength range.

12. The apparatus according to claim 10 or 11, wherein, the apparatus further comprises: a spectral splitting module, configured to perform optical signal splitting processing on the spectral signal according to the desired splitting nodes of the spectral signal within the target wavelength range.

13. A computer device, wherein, it comprises a processor and a memory, the memory stores a computer program that can be executed by the processor, and the processor can execute the computer program to implement the spectral splitting node determination method according to any one of claims 1-9.

14. A readable storage medium, on which a computer program is stored, wherein, when the computer program is executed by a processor, the spectral splitting node determination method according to any one of claims 1-9 is implemented.

Images