Water environment quality detection method and system based on spectral data analysis

Abstract

The invention relates to the technical field of water quality detection, and discloses a water environment quality detection method and system based on spectral data analysis. According to the method, detection points are arranged in a water environment quality detection area, Internet of Things equipment is installed, and water quality samples of different batches and water flux data of the detection points in the water environment quality detection area at corresponding moments are collected based on the set detection points; collecting spectral data of different batches of water quality samples in real time to construct a training sample set, preprocessing the spectral data in the constructed training sample set through a data processing method, estimating the water quality of each detection point based on the preprocessed spectral data, and calculating the water quality of each detection point based on the estimated water quality of each detection point. The standard overall environment of the water environment quality detection area is predicted through the particle swarm algorithm, the water environment quality grade parameters are constructed based on the predicted standard overall environment, meanwhile, real-time monitoring is carried out, and the accuracy of water environment quality detection is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of water quality detection, and in particular to a water environment quality detection method and system based on spectral data analysis. Background Art

[0002] Most of the current water environment monitoring methods are semi-automatic data collection, which has slow data analysis time and low efficiency, making it difficult to monitor water environment quality in real time and effectively.

[0003] The existing open patent application CN107643335A selects the material of the sensor probe and its application scenario, and collects the detection values ​​of water quality environmental parameters in real time through the selected sensor, and selects the corresponding estimation error function; and obtains the error correction value using the selected estimation error function; uses the error correction value to correct the detection value of the sensor to obtain the actual value, and performs evaluation based on the actual value obtained; but since the correction is only performed through the estimation error function, the accuracy of the water quality environmental parameter detection value cannot be guaranteed, and it has certain limitations. Summary of the invention

[0004] 1. Technical issues to be resolved In view of the shortcomings of the prior art, the present invention provides a water environment quality detection method and system based on spectral data analysis, which has the advantages of accuracy, high efficiency and real-time, and solves the problems of slow data analysis time, low efficiency and difficulty in real-time and effective monitoring of water environment quality.

[0005] (II) Technical solution In order to solve the above technical problems of slow data analysis time, low efficiency, and difficulty in real-time and effective monitoring of water environment quality, the present invention provides the following technical solutions: The present invention discloses a water environment quality detection method based on spectral data analysis, which specifically comprises the following steps: S1. Set up testing points and install IoT devices in the water environment quality testing area, and collect different batches of water quality samples based on the set testing points; S2, irradiating different batches of water samples using a spectrometer and collecting the spectral data after irradiation in real time to build a training sample set; S3, preprocessing the spectral data in the constructed training sample set by a data processing method to obtain preprocessed spectral data; S4. Collect water flow data of each detection point in the water environment quality detection area at the corresponding time through the installed Internet of Things device, and estimate the water quality of each detection point based on the pre-processed spectral data; S5, based on the estimated water quality of each detection point, predict the overall environment of the water environment quality detection area standard through the particle swarm algorithm; S6. Construct water environment quality grade parameters based on the predicted standard overall environment and monitor them in real time.

[0006] The present invention sets detection points in a water environment quality detection area and installs Internet of Things devices, collects water quality samples of different batches and water flow data of each detection point in the water environment quality detection area at corresponding moments based on the set detection points, collects spectral data of water quality samples of different batches in real time to construct a training sample set, pre-processes the spectral data in the constructed training sample set through a data processing method, estimates the water quality of each detection point based on the pre-processed spectral data, predicts the standard overall environment of the water environment quality detection area through a particle swarm algorithm based on the estimated water quality of each detection point, constructs water environment quality grade parameters based on the predicted standard overall environment, and performs real-time monitoring, thereby improving the accuracy of water environment quality detection.

[0007] Preferably, setting up detection points and installing Internet of Things devices in the water environment quality detection area, and collecting different batches of water quality samples based on the set detection points include the following steps: Collect a sample of pure water as a reference water quality sample; The time interval for collecting water quality samples at the detection points is set, and different batches of water quality samples from different detection points are collected based on the set time interval.

[0008] Preferably, the step of preprocessing the spectral data in the training sample set by a data processing method to obtain the preprocessed spectral data comprises the following steps: S31, calculating the average value of all spectral data as an average spectrum; ; in, represents the calculated average spectrum, represents the spectral data of the kth spectral band sequence after normalization, represents the number of spectral bands, k represents the spectral band sequence, k=1,2,3,...,n; S32, performing a univariate linear regression on the spectrum of each sample and the average spectrum, solving the least squares problem to obtain the baseline translation and offset of each sample; ; in, represents the spectral data of the sth sample after linear regression calculation, represents the baseline shift of the spectral data of the sth sample, Indicates the offset of the spectral data of the sth sample; S33, performing multi-source scattering correction based on the obtained baseline translation and offset of each sample; The multi-source scatter correction formula is as follows:

[0009] in, represents the corrected spectral data.

[0010] The present invention calculates the average value of all spectral data as the average spectrum through an averaging algorithm, and performs a univariate linear regression on the spectrum of each sample and the average spectrum, solves the least squares problem to obtain the baseline shift and offset of each sample, and performs multi-source scattering correction based on the obtained baseline shift and offset of each sample, thereby ensuring the reliability of the spectral data.

[0011] Preferably, the collecting of water flow data of each detection point in the water environment quality detection area at a corresponding time by the installed Internet of Things device, and estimating the water quality of each detection point based on the pre-processed spectral data comprises the following steps: S41, calculating the pollutant concentration at each detection point; S42. Estimate the water quality at each testing point based on the calculated pollutant concentration at each testing point.

[0012] Preferably, the calculation of the pollutant concentration at each detection point comprises the following steps: The spectral data of the reference water quality sample is set as the benchmark, the pre-processed spectral data of each detection point is compared with the benchmark data, and the content of each element in the spectral data is calculated; The calculation formula for the content of each element in the spectral data is as follows: ; in, Indicates the content of each element in the spectral data, represents the spectral intensity, are the constants set for the spectrometer respectively; Calculate the pollutant concentration of the water quality sample at each detection point based on the content of each element in the obtained spectral data; The pollutant concentration of the water quality samples at each testing point = the content of each element in the spectral data ÷ the content of each element in the spectral data of the reference water quality samples.

[0013] Preferably, estimating the water quality at each detection point based on the calculated pollutant concentration at each detection point comprises the following steps: The estimation formula is as follows: ; in, represents the estimated period, represents the function of pollutant concentration with respect to time, represents the water flux as a function of time, Indicates time, represents the average pollutant concentration during the period, represents the average water flow rate during the period, represents the number of samples for the estimation period, represents the pollutant concentration deviation in the i-th period, The water flux deviation in the i-th period, Indicates that the pollutant is at the current detection point The flux in time, Indicates about time The differential of represents the change in time within the i-th period; Among them, average pollutant concentration = total pollutant concentration of water quality samples at each testing point ÷ time period; average water flow = total water flow at each testing point ÷ time period; Set the pollutant at the current detection point The flux threshold within the time period is when the calculated pollutant is at the current detection point. When the flux within the time is less than or equal to the set threshold, it means that the water quality is qualified. When the flux within the time is greater than the set threshold, it means that the water quality is unqualified.

[0014] The present invention sets a benchmark and compares the preprocessed spectral data of each detection point with the benchmark data, calculates the content of each element in the spectral data, and estimates the water quality of each detection point based on the calculated pollutant concentration of each detection point, thereby improving the real-time performance of estimating the water quality of each detection point by spectral data.

[0015] Preferably, the method of predicting the overall environment of the water environment quality detection area standard based on the estimated water quality of each detection point by using a particle swarm algorithm comprises the following steps: S51, particle swarm optimization algorithm parameter initialization; Set each particle to represent the pollutant concentration estimation data of a group of water quality samples at the detection point, set the group size, and the maximum number of iterations , random position of particles , particle speed and the inertia factor ; S52, calculating the fitness of each particle; The fitness calculation formula for each particle is as follows: ; in, represents the particle fitness; S53, updating of the best position of a single particle; The update formula for a single particle velocity is as follows: ; in, Represents particles In the The speed during the iteration, Represents particles In the The speed during the iteration, represents the inertia factor, Represents particles In the The position during the iteration, , is the acceleration constant, , represents a random number in the interval [0,1], Represents particles The individual extreme value of Represents the global extreme value of all particles; The formula for updating the position of a single particle is as follows: ; in, Represents particles In the The position during the iteration; For each particle calculated, the fitness of its current position is compared with the best position it has passed. If the fitness of the current position is greater than the best position it has passed, The current position is taken as the current best position. , if the fitness of the current position is less than or equal to the best position it has passed The fitness of , then the current best position will not be changed ; S54, updating of the optimal position of the group; For each particle calculated, the fitness of its current position is compared with the best position that the particle in its population has passed. If the fitness of the current position is greater than the best position that the particle in the population has passed through, The current position is taken as the current best position. , if the fitness of the current position is less than or equal to the best position that the particle in its population has passed The fitness of , then the current best position will not be changed ; S55, updating the inertia factor, and updating the positions and velocities of all particles based on the updated inertia factor; The inertia factor update formula is as follows: ; in, represents the inertia factor at the beginning of iteration, represents the inertia factor at the final iteration, Indicates the current iteration number, Indicates the maximum number of iterations; S56, repeating steps S52-S55 until the maximum number of iterations is reached, and outputting the inertia factor corresponding to the optimal position; The inertia factor corresponding to the optimal position of the output is set to be the calculated overall environment of the water environment quality detection area standard.

[0016] The present invention initializes the parameters of the particle swarm optimization algorithm, uses the spectrum data to estimate the water quality of each detection point as a fitness function, obtains the standard overall environment through continuous iterative calculation, and improves the efficiency of water quality environment detection.

[0017] Preferably, the water environment quality grade parameters are constructed based on the predicted standard overall environment, and real-time monitoring includes the following steps: The predicted standard overall environment is set as the standard, and every 20% parameter difference value is set as the grade parameter to construct the water environment quality grade. Based on the constructed water environment quality grade, water quality samples are collected in real time for real-time testing.

[0018] The present invention also discloses a system for a water environment quality detection method based on spectral data analysis, comprising: a data acquisition module, a spectral data processing module, a water quality estimation module, a water environment quality prediction module and a water environment quality grade module; The data acquisition module is used to collect spectral data of different batches of water quality samples; The spectral data processing module is used to process the spectral data of different batches of water quality samples collected; The water quality estimation module is used to estimate the water quality of each detection point based on the processed spectral data; The water environment quality prediction module is used to predict the overall environment of the water environment quality detection area standard; The water environment quality grade module is used to construct water environment quality grade parameters according to the prediction results.

[0019] (III) Beneficial effects Compared with the prior art, the present invention provides a water environment quality detection method and system based on spectral data analysis, which has the following beneficial effects: 1. The invention sets detection points and installs Internet of Things devices in the water environment quality detection area, collects water quality samples of different batches and water flow data of each detection point in the water environment quality detection area at the corresponding time based on the set detection points, and collects spectral data of water quality samples of different batches in real time to construct a training sample set, and pre-processes the spectral data in the constructed training sample set through a data processing method, and estimates the water quality of each detection point based on the pre-processed spectral data, and based on the estimated water quality of each detection point, predicts the standard overall environment of the water environment quality detection area through a particle swarm algorithm, and constructs water environment quality grade parameters based on the predicted standard overall environment, and conducts real-time monitoring, thereby improving the accuracy of water environment quality detection.

[0020] 2. The invention calculates the average value of all spectral data as the average spectrum through an averaging algorithm, and performs a univariate linear regression on the spectrum of each sample and the average spectrum, solves the least squares problem to obtain the baseline shift and offset of each sample, and performs multi-source scattering correction based on the obtained baseline shift and offset of each sample, thereby ensuring the reliability of the spectral data.

[0021] 3. The invention sets a benchmark and compares the pre-processed spectral data of each detection point with the benchmark data, calculates the content of each element in the spectral data, and estimates the water quality of each detection point based on the calculated pollutant concentration of each detection point, thereby improving the real-time performance of estimating the water quality of each detection point by spectral data.

[0022] 4. The invention initializes the parameters of the particle swarm optimization algorithm, and uses the spectral data to estimate the water quality of each detection point as the fitness function. Through continuous iterative calculation, the standard overall environment is obtained, thereby improving the efficiency of water quality environment detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a schematic diagram of the water environment quality detection process structure of the present invention. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] Example 1 See also Figure 1 This embodiment discloses a water environment quality detection method based on spectral data analysis, which specifically includes the following steps: S1. Set up testing points and install IoT devices in the water environment quality testing area, and collect different batches of water quality samples based on the set testing points; S2, irradiating different batches of water samples using a spectrometer and collecting the spectral data after irradiation in real time to build a training sample set; S3, preprocessing the spectral data in the constructed training sample set by a data processing method to obtain preprocessed spectral data; S4. Collect water flow data of each detection point in the water environment quality detection area at the corresponding time through the installed Internet of Things device, and estimate the water quality of each detection point based on the pre-processed spectral data; S5, based on the estimated water quality of each detection point, predict the overall environment of the water environment quality detection area standard through the particle swarm algorithm; S6. Construct water environment quality grade parameters based on the predicted standard overall environment and monitor them in real time; For further information, see Figure 1 , setting up detection points and installing IoT devices in the water environment quality detection area, and collecting different batches of water quality samples based on the set detection points include the following steps: Collect a sample of pure water as a reference water quality sample; Furthermore, the time interval for collecting water quality samples at the detection points is set, and different batches of water quality samples at different detection points are collected based on the set time interval; For further information, see Figure 1 , preprocessing the spectral data in the training sample set by a data processing method, and obtaining the preprocessed spectral data includes the following steps: S31, calculating the average value of all spectral data as an average spectrum; ; in, represents the calculated average spectrum, represents the spectral data of the kth spectral band sequence after normalization, represents the number of spectral bands, k represents the spectral band sequence, k=1,2,3,...,n; S32, performing a univariate linear regression on the spectrum of each sample and the average spectrum, solving the least squares problem to obtain the baseline translation and offset of each sample; ; in, represents the spectral data of the sth sample after linear regression calculation, represents the baseline shift of the spectral data of the sth sample, Indicates the offset of the spectral data of the sth sample; S33, performing multi-source scattering correction based on the obtained baseline translation and offset of each sample; The multi-source scatter correction formula is as follows:

[0026] in, represents the corrected spectral data.

[0027] For further information, see Figure 1 , collecting water flow data of each detection point in the water environment quality detection area at the corresponding time through the installed Internet of Things equipment, and estimating the water quality of each detection point based on the pre-processed spectral data includes the following steps: S41, calculating the pollutant concentration at each detection point; The spectral data of the reference water quality sample is set as the benchmark, the pre-processed spectral data of each detection point is compared with the benchmark data, and the content of each element in the spectral data is calculated; The calculation formula for the content of each element in the spectral data is as follows: ; in, Indicates the content of each element in the spectral data, represents the spectral intensity, are the constants set for the spectrometer respectively; Further, the pollutant concentration of the water quality sample at each detection point is calculated based on the content of each element in the obtained spectral data; Pollutant concentration of water samples at each testing point = content of each element in the spectral data ÷ content of each element in the spectral data of the reference water sample; S42, estimating the water quality at each detection point based on the calculated pollutant concentration at each detection point; The estimation formula is as follows: ; in, represents the estimated period, represents the function of pollutant concentration with respect to time, represents the water flux as a function of time, Indicates time, represents the average pollutant concentration during the period, represents the average water flow rate during the period, represents the number of samples for the estimation period, represents the pollutant concentration deviation in the i-th period, The water flux deviation in the i-th period, Indicates that the pollutant is at the current detection point The flux in time, Indicates about time The differential of represents the change in time within the i-th period; Among them, average pollutant concentration = total pollutant concentration of water quality samples at each testing point ÷ time period; average water flow = total water flow at each testing point ÷ time period; Set the pollutant at the current detection point The flux threshold within the time period is when the calculated pollutant is at the current detection point. When the flux within the time is less than or equal to the set threshold, it means that the water quality is qualified. When the flux within a time period is greater than the set threshold, it indicates that the water quality is unqualified; For further information, see Figure 1 ,Based on the estimated water quality of each detection point, the particle swarm algorithm is used to predict the overall environment of the water environment quality detection area standard, which includes the following steps: S51, particle swarm optimization algorithm parameter initialization; Set each particle to represent the pollutant concentration estimation data of a group of water quality samples at the detection point, set the group size, and the maximum number of iterations , random position of particles , particle speed and the inertia factor ; S52, calculating the fitness of each particle; The fitness calculation formula for each particle is as follows: ; in, represents the particle fitness; S53, updating of the best position of a single particle; The update formula for a single particle velocity is as follows: ; in, Represents particles In the The speed during the iteration, Represents particles In the The speed during the iteration, represents the inertia factor, Represents particles In the The position during the iteration, , is the acceleration constant, , represents a random number in the interval [0,1], Represents particles The individual extreme value of Represents the global extreme value of all particles; The formula for updating the position of a single particle is as follows: ; in, Represents particles In the The position during the iteration; For each particle calculated, the fitness of its current position is compared with the best position it has passed. If the fitness of the current position is greater than the best position it has passed, The current position is taken as the current best position. , if the fitness of the current position is less than or equal to the best position it has passed The fitness of , then the current best position will not be changed ; S54, updating of the optimal position of the group; For each particle calculated, the fitness of its current position is compared with the best position that the particle in its population has passed. If the fitness of the current position is greater than the best position that the particle in the population has passed through, The current position is taken as the current best position. , if the fitness of the current position is less than or equal to the best position that the particle in its population has passed The fitness of , then the current best position will not be changed ; S55, updating the inertia factor, and updating the positions and velocities of all particles based on the updated inertia factor; The inertia factor update formula is as follows: ; in, represents the inertia factor at the beginning of iteration, represents the inertia factor at the final iteration, Indicates the current iteration number, Indicates the maximum number of iterations; S56, repeating steps S52-S55 until the maximum number of iterations is reached, and outputting the inertia factor corresponding to the optimal position; The inertia factor corresponding to the optimal position of the output is set to be the calculated overall environment of the water environment quality detection area standard; For further information, see Figure 1 , based on the predicted standard overall environment, water environment quality grade parameters are constructed, and real-time monitoring includes the following steps: The predicted standard overall environment is set as the standard, and each 20% parameter difference value is set as the grade parameter to construct the water environment quality grade. Based on the constructed water environment quality grade, water quality samples are collected in real time for real-time testing; Example 2 See also Figure 1 , this embodiment also discloses a water environment quality detection system based on spectral data analysis, which is used to implement a water environment quality detection method based on spectral data analysis, and the system includes: a data acquisition module, a spectral data processing module, a water quality estimation module, a water environment quality prediction module and a water environment quality grade module; The data acquisition module is used to collect spectral data of different batches of water quality samples; The spectral data processing module is used to process the spectral data of different batches of water quality samples collected; The water quality estimation module is used to estimate the water quality of each detection point based on the processed spectral data; The water environment quality prediction module is used to predict the overall environment of the water environment quality detection area standard; The water environment quality grade module is used to construct water environment quality grade parameters according to the prediction results.

[0028] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A water environment quality detection method based on spectral data analysis, characterized in that: The following steps are involved: S1. Set up testing points and install IoT devices in the water environment quality testing area, and collect different batches of water quality samples based on the set testing points; S2, irradiating different batches of water samples using a spectrometer and collecting the spectral data after irradiation in real time to build a training sample set; S3, preprocessing the spectral data in the constructed training sample set by a data processing method to obtain preprocessed spectral data; S4. Collect water flow data of each detection point in the water environment quality detection area at the corresponding time through the installed Internet of Things equipment, and estimate the water quality of each detection point based on the pre-processed spectral data; S5, based on the estimated water quality of each detection point, predict the overall environment of the water environment quality detection area standard through the particle swarm algorithm; S6. Construct water environment quality grade parameters based on the predicted standard overall environment and monitor them in real time.

2. A water environment quality detection method based on spectral data analysis according to claim 1, characterized in that: Setting detection points and installing IoT devices in the water environment quality detection area, and collecting different batches of water quality samples based on the set detection points, includes the following steps: Collect a sample of pure water as a reference water quality sample; The time interval for collecting water quality samples at the detection points is set, and different batches of water quality samples from different detection points are collected based on the set time interval.

3. The water environment quality detection method based on spectral data analysis according to claim 1 is characterized in that: The method of preprocessing the spectral data in the training sample set by the data processing method to obtain the preprocessed spectral data comprises the following steps: S31, calculating the average value of all spectral data as an average spectrum; ； in, represents the calculated average spectrum, represents the spectral data of the kth spectral band sequence after normalization, represents the number of spectral bands, k represents the spectral band sequence, k=1,2,3,...,n; S32, performing a univariate linear regression on the spectrum of each sample and the average spectrum, solving the least squares problem to obtain the baseline translation and offset of each sample; ； in, represents the spectral data of the sth sample after linear regression calculation, represents the baseline shift of the spectral data of the sth sample, Indicates the offset of the spectral data of the sth sample; S33, performing multi-source scattering correction based on the obtained baseline translation and offset of each sample; The multi-source scatter correction formula is as follows: ； in, represents the corrected spectral data.

4. The water environment quality detection method based on spectral data analysis according to claim 1 is characterized in that: The method of collecting water flow data of each detection point in the water environment quality detection area at the corresponding time through the installed Internet of Things device and estimating the water quality of each detection point based on the pre-processed spectral data includes the following steps: S41, calculating the pollutant concentration at each detection point; S42. Estimate the water quality at each testing point based on the calculated pollutant concentration at each testing point.

5. The water environment quality detection method based on spectral data analysis according to claim 4 is characterized in that: The calculation of the pollutant concentration at each detection point comprises the following steps: The spectral data of the reference water quality sample is set as the benchmark, the pre-processed spectral data of each detection point is compared with the benchmark data, and the content of each element in the spectral data is calculated; The calculation formula for the content of each element in the spectral data is as follows: ； in, Indicates the content of each element in the spectral data, represents the spectral intensity, are the constants set for the spectrometer respectively; Calculate the pollutant concentration of the water quality sample at each detection point based on the content of each element in the obtained spectral data; The pollutant concentration of the water quality samples at each testing point = the content of each element in the spectral data ÷ the content of each element in the spectral data of the reference water quality samples.

6. A water environment quality detection method based on spectral data analysis according to claim 4, characterized in that: The method of estimating the water quality at each detection point based on the calculated pollutant concentration at each detection point comprises the following steps: The estimation formula is as follows: ； in, represents the estimated period, represents the function of pollutant concentration with respect to time, represents the water flux as a function of time, Indicates time, represents the average pollutant concentration during the period, represents the average water flow rate during the period, represents the number of samples for the estimation period, represents the pollutant concentration deviation in the i-th period, The water flux deviation in the i-th period, Indicates that the pollutant is at the current detection point The flux in time, Indicates about time The differential of represents the change in time within the i-th period; Among them, average pollutant concentration = total pollutant concentration of water quality samples at each testing point ÷ time period; average water flow = total water flow at each testing point ÷ time period; Set the pollutant at the current detection point The flux threshold within the time period is when the calculated pollutant is at the current detection point. When the flux within the time is less than or equal to the set threshold, it means that the water quality is qualified. When the flux within the time is greater than the set threshold, it means that the water quality is unqualified.

7. The water environment quality detection method based on spectral data analysis according to claim 1 is characterized in that: The method of predicting the overall environment of the water environment quality detection area standard based on the estimated water quality of each detection point by using a particle swarm algorithm includes the following steps: S51, particle swarm optimization algorithm parameter initialization; Set each particle to represent the pollutant concentration estimation data of a group of water quality samples at the detection point, set the group size, and the maximum number of iterations , random position of particles , particle speed and the inertia factor ; S52, calculating the fitness of each particle; The fitness calculation formula for each particle is as follows: ； in, represents the particle fitness; S53, updating of the best position of a single particle; The update formula for a single particle velocity is as follows: ； in, Represents particles In the The speed during the iteration, Represents particles In the The speed during the iteration, represents the inertia factor, Represents particles In the The position during the iteration, , is the acceleration constant, , represents a random number in the interval [0,1], Represents particles The individual extreme value of Represents the global extreme value of all particles; The formula for updating the position of a single particle is as follows: ； in, Represents particles In the The position during the iteration; For each particle calculated, the fitness of its current position is compared with the best position it has passed. If the fitness of the current position is greater than the best position it has passed, The current position is taken as the current best position. , if the fitness of the current position is less than or equal to the best position it has passed The fitness of , then the current best position will not be changed ; S54, updating of the optimal position of the group; For each particle calculated, the fitness of its current position is compared with the best position that the particle in its population has passed. If the fitness of the current position is greater than the best position that the particle in the population has passed through, The current position is taken as the current best position. , if the fitness of the current position is less than or equal to the best position that the particle in its population has passed The fitness of , then the current best position will not be changed ; S55, updating the inertia factor, and updating the positions and velocities of all particles based on the updated inertia factor; The inertia factor update formula is as follows: ； in, represents the inertia factor at the beginning of iteration, represents the inertia factor at the final iteration, Indicates the current iteration number, Indicates the maximum number of iterations; S56, repeating steps S52-S55 until the maximum number of iterations is reached, and outputting the inertia factor corresponding to the optimal position; The inertia factor corresponding to the optimal position of the output is set to be the calculated overall environment of the water environment quality detection area standard.

8. The water environment quality detection method based on spectral data analysis according to claim 1 is characterized in that: The method of constructing water environment quality grade parameters based on the predicted standard overall environment and real-time monitoring includes the following steps: The predicted standard overall environment is set as the standard, and every 20% parameter difference value is set as the grade parameter to construct the water environment quality grade. Based on the constructed water environment quality grade, water quality samples are collected in real time for real-time testing.

9. A system for implementing the water environment quality detection method based on spectral data analysis according to any one of claims 1 to 8, characterized in that: include: Data acquisition module, spectral data processing module, water quality estimation module, water environment quality prediction module and water environment quality grade module; The data acquisition module is used to collect spectral data of different batches of water quality samples; The spectral data processing module is used to process the spectral data of different batches of water quality samples collected; The water quality estimation module is used to estimate the water quality of each detection point based on the processed spectral data; The water environment quality prediction module is used to predict the overall environment of the water environment quality detection area standard; The water environment quality grade module is used to construct water environment quality grade parameters according to the prediction results.

Images