Training system and method of semi-supervised machine learning model for water pollutant detection

Abstract

The invention discloses a training system and method of a semi-supervised machine learning model for water pollutant detection, and relates to the field of environment detection. The problem that an existing semi-supervised machine learning model is insufficient in universality is solved. The system comprises a water body sampling module used for collecting a water body sample of a monitoring area; the pollutant adding module is used for adding pollutants to the water body sample according to randomly obtained pollutant types and concentration settings of different combinations to obtain the water body sample, and sending the water body sample to the data sampling module; the data sampling module is used for collecting physicochemical properties of the water body samples of the water body sampling module and the pollutant adding module through a sensor; and the data analysis module is used for inputting the physicochemical property data of the water body sample acquired by the water body sampling module into a semi-supervised machine learning model, and constructing and training the semi-supervised machine learning model by taking the physicochemical property data as input. The method is also suitable for the field of real-time training and detection of water pollutants.

Description

Technical Field

[0001] The present invention relates to the field of environmental detection technology, and in particular to a training system and method for a semi-supervised machine learning model for water pollutant detection. Background Art

[0002] The patent publication numbers are CN 114778647 A, CN 118549501 A, CN 117390503 A and CN113820376A, respectively. They disclose that the composition and concentration of water pollutants can be inferred from differences and / or changes in physical and chemical properties, such as conductivity, pH value, turbidity, residual chlorine and color. However, due to the difficulty for researchers to analyze the complex and subtle differences between the data, it is impossible to establish the relationship between these physical and chemical properties and water pollutants. Machine learning is a process of mining deep-level laws through data. In recent years, it has been widely coupled with the coupling of physical and chemical properties and water pollutants. Through machine learning, the response signal relationship of the physical and chemical properties of water pollutants of different types and concentrations is deeply analyzed, and finally the quantitative and / or qualitative analysis of dissolved substances is achieved.

[0003] However, in actual applications, due to the complex composition of the water samples to be tested, it is necessary to construct a relatively large set of standard curves in the laboratory, that is, to obtain a machine learning model trained based on pure substances or mixtures of different pure substances. However, this work is very time-consuming and labor-intensive. In addition, the physical and chemical properties of water quality are very numerous and complex, and the detection methods available in different regions are also different, which makes it impossible for machine learning models to obtain good generalization effects, that is, models trained based on laboratory data or models trained on water samples from other places may not be applicable to the target water samples. A better method is needed to combine in-situ water samples for detection, so that even if the composition of the water sample to be tested changes, it can be trained in real time to obtain a model with better generalization ability. Summary of the Invention

[0004] The present invention aims to address the existing problem that, due to the complex composition of the water samples to be tested, a relatively large set of standard curves must be constructed in the laboratory. This involves obtaining a machine learning model trained based on pure substances or mixtures of different pure substances. However, this work is very time-consuming and labor-intensive. In addition, the physical and chemical properties of water quality are very diverse and complex, and the detection methods available in different regions also vary, making the machine learning model less versatile.

[0005] To solve the above technical problems, the present invention is achieved through the following technical solutions:

[0006] Solution 1: The present invention proposes a training system for a semi-supervised machine learning model for water pollutant detection, the system comprising a water sampling module, a pollutant dosing module, a data sampling module, and a data analysis module;

[0007] The water sampling module is used to collect the original water samples in the monitoring area, and send the pure water samples, the original water samples, and the diluted original water samples to the pollutant dosing module, and then send the pure water samples and the original water samples to the data sampling module;

[0008] Water samples include original water samples, pure water samples, and diluted original water samples;

[0009] The pollutant dosing module is used to add pollutants to the water sample according to the randomly obtained different combinations of pollutant types and concentration settings, obtain water samples, and send them to the data sampling module;

[0010] The data sampling module is used to collect the physical and chemical properties of water samples from the water sampling module and the pollutant dosing module through detection equipment or sensors;

[0011] The data analysis module is used to input the data on the physical and chemical properties of water samples collected by the water sampling module into the semi-supervised machine learning model, and to construct and train the semi-supervised machine learning model with the physical and chemical property data as input.

[0012] Furthermore, a preferred embodiment is provided, in which the water sample is transmitted in the water sampling module to the pollutant dosing module and the data sampling module through gravity flow, water inlet pressure flow or water pump pressure flow.

[0013] Furthermore, a preferred embodiment is provided, wherein the diluted original water sample after dilution by the water sampling module is obtained by randomly selecting the mixing ratio of the original water sample and the pure water sample from 1:4, 2:3, 3:2 and 4:1.

[0014] Furthermore, a preferred implementation is provided, in which the ratio of the training set to the test set in step 2 is 8:2.

[0015] Furthermore, a preferred embodiment is provided, wherein the physical and chemical properties of the water sample in the data acquisition module include pH value, temperature, dissolved oxygen, turbidity, and conductivity.

[0016] Furthermore, a preferred embodiment is provided, in which the model of machine learning training in the data analysis module includes one or more combinations of greedy algorithm, dynamic programming algorithm, divide and conquer algorithm, backtracking algorithm, and branch and bound algorithm.

[0017] Furthermore, a preferred embodiment is provided, wherein the method for constructing the semi-supervised machine learning model includes:

[0018] S1. Take the physical and chemical properties of a pure water sample as input and the blank value as output, and refer to the input and output data as data a; take the physical and chemical properties of a pure water sample with pollutants added as input and the type and concentration of pollutants set for the pure water sample as output, and refer to the input and output data as data b. Use data a and data b to train a model in a data analysis module to obtain a model M. If a pre-trained model M already exists, continue training on model M.

[0019] S2, based on the model M, taking the physical and chemical properties of the original water sample as input, obtain the model output, which is outputT;

[0020] S3. The original water sample after the addition of pollutants and the diluted original water sample are respectively designated as polluted water sample c and polluted water sample d; the physical and chemical properties of the polluted water sample c are used as input, and the sum of output T and the pollutant type and concentration set for the polluted water sample c is used as output, and the input and output data are referred to as data c; the physical and chemical properties of the polluted water sample d are used as input, the dilution degree of the original water sample diluted by output T is calculated, and the sum of the output T and the pollutant type and concentration set for the polluted water sample d is used as output, and the input and output data are referred to as data d; the model M is trained in the data analysis module using data c and data d;

[0021] S4. Repeat S1.

[0022] Furthermore, a preferred embodiment is provided, in which a data transmission module is provided between the data sampling module and the data analysis module for realizing remote monitoring.

[0023] Solution 2: A method for training a semi-supervised machine learning model for water pollutant detection, characterized in that the training method is implemented based on the system described in any one of Solution 1, and the method comprises the following steps:

[0024] Step 1: The water sampling module sends the pure water sample, the original water sample, and the diluted original water sample to the pollutant dosing module, and sends the water sample and the original water sample to the data analysis module;

[0025] Step 2: The pollutant dosing module randomly selects a set of pollutant types and concentration settings, and adds pollutants to the water samples of the water sampling module;

[0026] Step 3: The data sampling module obtains the physical and chemical property information of the water samples from the water sampling module and the pollutant dosing module;

[0027] Step 4: The data transmission module sends the physical and chemical property information collected by the data sampling module to the data analysis module;

[0028] Step 5: The data analysis module inputs the physical and chemical property information into the semi-supervised machine learning model, and trains the semi-supervised machine learning model using the construction method of the semi-supervised machine learning model;

[0029] Step 6: Repeat steps 1 to 5 to train a semi-supervised machine learning model for water pollutant detection.

[0030] Solution 3: A computer device includes a memory and a processor, wherein the memory stores a computer program. When the processor runs the computer program stored in the memory, the processor executes the method described in Solution 2.

[0031] Solution 4: A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in Solution 2 are implemented.

[0032] The present invention is beneficial in that:

[0033] The present invention proposes a training system and method for a semi-supervised machine learning model for water pollutant detection. The system collects and analyzes the physical and chemical properties of different types of water samples to construct a machine learning model. The system then trains the model using a semi-supervised learning algorithm by randomly setting pollutant concentrations and combining it with in-situ detection data. This allows the machine learning model to achieve stable training capabilities for different target water bodies, making the model more versatile. That is, the sampling and training methods used in the present invention can improve the model's generalizability to different water conditions, thereby facilitating real-time training and detection of water pollutants.

[0034] The present invention is also applicable to the field of real-time training and detection of water pollutants. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 Schematic diagram of the principle of a training system for a semi-supervised machine learning model for water pollutant detection as described in Implementation Method 1.

[0036] Figure 2 This is a model training flowchart in the data analysis module of the training method of a semi-supervised machine learning model for water pollutant detection described in Implementation Example 8.

[0037] Among them, 11 is the original water sample, 12 is the diluted original water sample, 13 is the pure water sample, 14 is valve 1, 15 is valve 2, 16 is the original water sample sampling port, 17 is the diluted original water sample sampling port, and 18 is the sampling port of pure water; 1 is the pollutant dosing module, 21 is the water sample inlet of the pollutant dosing module 1, 22 is the CCl4 doser, 23 is the CCl3 doser, and 24 is the CCl2 doser; 2 is the data sampling module, 31 is the pH analyzer, 32 is the turbidity analyzer, 33 is the spectrophotometer, 34 is the voltammetric cycle analyzer, and 35 is the chlorine analyzer; 3 is the data transmission module; 4 is the data analysis module. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical solutions and advantages of the implementation methods of this application clearer, the technical solutions in the implementation methods of this application will be clearly and completely described below in combination with the drawings in the implementation methods of this application. Obviously, the described implementation methods are only part of the implementation methods of this application, not all of the implementation methods.

[0039] Implementation 1. This implementation proposes a training system for a semi-supervised machine learning model for water pollutant detection, the system comprising a water sampling module, a pollutant dosing module, a data sampling module, and a data analysis module;

[0040] The water sampling module is used to collect the original water samples in the monitoring area, and send the pure water samples, the original water samples, and the diluted original water samples to the pollutant dosing module, and then send the pure water samples and the original water samples to the data sampling module;

[0041] Water samples include original water samples, pure water samples, and diluted original water samples;

[0042] The pollutant dosing module is used to add pollutants to the water sample according to the randomly obtained different combinations of pollutant types and concentration settings, obtain water samples, and send them to the data sampling module;

[0043] The data sampling module is used to collect the physical and chemical properties of water samples from the water sampling module and the pollutant dosing module through detection equipment or sensors;

[0044] The data analysis module is used to input the data on the physical and chemical properties of water samples collected by the water sampling module into the semi-supervised machine learning model, and to construct and train the semi-supervised machine learning model with the physical and chemical property data as input.

[0045] Implementation method 2. This implementation method further limits the training system of a semi-supervised machine learning model for water quality pollutant detection described in implementation method 1. The water sample is transmitted to the pollutant dosing module and the data sampling module in the water body sampling module through gravity flow, water inlet pressure flow or water pump pressure flow.

[0046] Implementation method three. This implementation method further limits the training system of a semi-supervised machine learning model for water pollutant detection described in implementation method one. The diluted original water sample after dilution by the water sampling module is obtained by randomly selecting the mixing ratio of the original water sample and the pure water sample from 1:4, 2:3, 3:2 and 4:1.

[0047] Implementation method 4. This implementation method further limits the training system of a semi-supervised machine learning model for water pollutant detection described in implementation method 1. The physical and chemical properties of the water sample in the data acquisition module include pH value, temperature, dissolved oxygen, turbidity, and conductivity.

[0048] Implementation method five. This implementation method further limits the training system of a semi-supervised machine learning model for water pollutant detection described in implementation method one. The machine learning training model in the data analysis module includes one or more combinations of greedy algorithm, dynamic programming algorithm, divide and conquer algorithm, backtracking algorithm, and branch and bound algorithm.

[0049] Implementation 6: This implementation further defines the training system for a semi-supervised machine learning model for water pollutant detection described in Implementation 1. The method for constructing the semi-supervised machine learning model includes:

[0050] S1. Take the physical and chemical properties of a pure water sample as input and the blank value as output, and refer to the input and output data as data a; take the physical and chemical properties of a pure water sample with pollutants added as input and the type and concentration of pollutants set for the pure water sample as output, and refer to the input and output data as data b. Use data a and data b to train a model in a data analysis module to obtain a model M. If a pre-trained model M already exists, continue training on model M.

[0051] S2, based on the model M, taking the physical and chemical properties of the original water sample as input, obtain the model output, which is outputT;

[0052] S3. The original water sample after the addition of pollutants and the diluted original water sample are respectively designated as polluted water sample c and polluted water sample d; the physical and chemical properties of the polluted water sample c are used as input, and the sum of output T and the pollutant type and concentration set for the polluted water sample c is used as output, and the input and output data are referred to as data c; the physical and chemical properties of the polluted water sample d are used as input, the dilution degree of the original water sample diluted by output T is calculated, and the sum of the output T and the pollutant type and concentration set for the polluted water sample d is used as output, and the input and output data are referred to as data d; the model M is trained in the data analysis module using data c and data d;

[0053] S4. Repeat S1.

[0054] Implementation method seven: This implementation method further limits the training system of a semi-supervised machine learning model for water pollutant detection described in implementation method one. A data transmission module is also provided between the data sampling module and the data analysis module to realize remote monitoring.

[0055] Embodiment 8: This embodiment provides a training method for a semi-supervised machine learning model for water pollutant detection. The training method is implemented based on the system described in any one of Embodiments 1 to 7, and the method includes the following steps:

[0056] Step 1: The water sampling module sends the pure water sample, the original water sample, and the diluted original water sample to the pollutant dosing module, and sends the water sample and the original water sample to the data analysis module;

[0057] Step 2: The pollutant dosing module randomly selects a set of pollutant types and concentration settings, and adds pollutants to the water samples of the water sampling module;

[0058] Step 3: The data sampling module obtains the physical and chemical property information of the water samples from the water sampling module and the pollutant dosing module;

[0059] Step 4: The data transmission module sends the physical and chemical property information collected by the data sampling module to the data analysis module;

[0060] Step 5: The data analysis module inputs the physical and chemical property information into the semi-supervised machine learning model, and trains the semi-supervised machine learning model using the construction method of the semi-supervised machine learning model;

[0061] Step 6: Repeat steps 1 to 5 to train a semi-supervised machine learning model for water pollutant detection.

[0062] Implementation method 9: This implementation method proposes a computer device, including a memory and a processor, wherein the memory stores a computer program. When the processor runs the computer program stored in the memory, the processor executes the method described in implementation method 8.

[0063] Implementation 10: This implementation proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the method described in Implementation 8 are implemented.

[0064] Implementation 11: This implementation provides an example, which is used to explain the above implementations 1 to 10. Specifically, the example is as follows:

[0065] See also Figure 1 and Figure 2 This embodiment specifically includes the following steps:

[0066] The present invention proposes a training method for a semi-supervised machine learning model for water pollutant detection. By combining in-situ target water sample data and using a semi-supervised mode, a more versatile machine learning model is obtained.

[0067] A training system for a semi-supervised machine learning model for water pollutant detection includes a water sampling module, a pollutant dosing module, a data sampling module, and a data analysis module. When remote monitoring is required, a data transmission module can be added between the data sampling and data analysis modules.

[0068] The water sampling module is used to collect original water samples in the monitoring area, and send pure water samples, original water samples, and diluted original water samples to the pollutant dosing module, and then send pure water samples and original water samples to the data sampling module.

[0069] Original water samples, pure water samples, and diluted original water samples are collectively referred to as water samples.

[0070] In the water sampling module, water samples are transmitted to the pollutant dosing module and the data sampling module through gravity flow, water inlet pressure flow or water pump pressure flow.

[0071] The diluted original water sample is obtained by mixing the original water sample with the pure water sample in a certain ratio. The dilution degree is a random value. For example, based on the random seed setting, the mixing ratio of the original water sample and the pure water sample is randomly selected from 1:4, 2:3, 3:2, and 4:1. The dilution degree is not limited to the values mentioned above.

[0072] The pollutant dosing module is used to add pollutants to the water samples in the water sampling module. Based on the randomly obtained pollutant types and concentration settings, pollutants are added to the water samples to obtain polluted water samples, which are then sent to the data sampling module.

[0073] The data sampling module collects the physical and chemical properties of water samples from the water sampling module and the pollutant dosing module through detection equipment and / or sensors, including:

[0074] pH value, temperature, dissolved oxygen, turbidity, conductivity, total organic carbon (TOC), ammonia nitrogen (NH3-N), nitrate nitrogen (NO3 - -N), phosphate (PO4 3- ), chemical oxygen demand (COD), biochemical oxygen demand (BOD), dissolved solids (TDS), suspended solids (SS), heavy metal ions (such as lead, mercury, copper, cadmium, etc.), chloride (Cl - ), sulfate (SO4 2-), amino acids, volatile organic compounds (VOCs), pesticide residues, total nitrogen, total phosphorus, dissolved gas content (such as nitrogen, oxygen, carbon dioxide), changes in water pH (pH), dissolved oxygen saturation, total dissolved gas pressure, total suspended particulate matter (TSS) concentration, etc., and / or current distribution curve obtained by cyclic voltammetry, and / or peak signal obtained by liquid chromatography, and / or absorbance measured by ultraviolet-visible spectrophotometry, and / or gas composition measured by gas chromatography, and / or ion mass-to-charge ratio data obtained by mass spectrometry, and / or fluorescence intensity data obtained by fluorescence spectroscopy, and / or determination by atomic absorption spectrometry. metal ion concentration, and / or ion concentration determined by ion selective electrode method, and / or ion composition obtained by ion chromatography, and / or infrared absorption spectrum obtained by Fourier transform infrared spectroscopy (FTIR), and / or molecular structure data of organic matter in water obtained by nuclear magnetic resonance (NMR), and / or water pollutant concentration information obtained by electrochemical sensors, and / or assessment of microbial activity in water by microbial electrode method, and / or detection of volatile organic compounds (VOCs) in water by electronic nose technology, and / or multidimensional water quality data obtained by multi-parameter spectroscopy, and / or particle size distribution of particulate matter in water determined by laser particle size analysis, and / or detecting the concentration of suspended matter in water by light scattering method, and / or obtaining quantitative analysis data of organic pollutants by high performance liquid chromatography-mass spectrometry (HPLC-MS), and / or determining the concentration of trace elements in water by trace element analysis method, and / or obtaining molecular information of pollutants by self-assembled nanosensors, and / or obtaining the concentration of harmful gases in water by non-metallic sensors, and / or detecting molecular vibration modes in water by Raman spectroscopy to obtain molecular structure information of pollutants in water, and / or detecting the content of heavy metals in water by laser induced breakdown spectroscopy (LIBS), and / or monitoring the sound wave propagation characteristics of pollutants in water by acoustic sensors, and / or Non-invasive analysis of the distribution of pollutants in water bodies by magnetic resonance imaging (MRI) technology, and / or quantitative assessment of solid pollutants in water by thermogravimetric analysis (TGA), and / or simultaneous determination of organic pollutants and heavy metals in water by ultraviolet spectroscopy-fluorescence (UV-Fluorescence), and / or analysis of molecular interactions of pollutants in water bodies by surface plasmon resonance (SPR), and / or real-time dynamic observation of particles in water by holographic microscopy, and / or real-time determination of the reactivity and concentration changes of chemical substances in water by capacitance-conductivity method, and / or high-throughput analysis of trace pollutants in water by droplet microfluidic chip technology.and / or monitor the dynamic changes of water temperature, pH and nitrogen and phosphorus pollutants through meteorological satellite data combined with remote sensing technology, and / or detect heavy metal pollutants in water through thermoluminescence analysis (TLPS), and / or detect microparticles in water and their properties through polarized light scattering technology, and / or sensitively detect trace organic matter in water through quantum dot sensors, and / or simultaneously detect chemical and physical pollutants in water through acousto-optic composite sensors, and / or monitor changes in microbial communities in water and their responses to pollutants through gene chip technology, and / or conduct rapid on-site water quality testing through portable water quality detectors, and / or monitor the spatial distribution of pollutants in water in real time through multispectral imaging technology, and / or detect pollutants in deep water areas through endoscopic underwater sensors, and / or monitor the dynamic changes of suspended particulate matter in water in real time through holographic interferometer technology, and / or monitor the concentration of harmful chemicals in water and their changes through microwave sensing technology.

[0075] The data analysis module is used to input the physical and chemical properties of water samples collected by the water sampling module into the machine learning model, and train the machine learning model with the physical and chemical properties data as input. The models used for machine learning training include:

[0076] Exhaustive search, greedy algorithm, dynamic programming algorithm, divide and conquer algorithm, backtracking algorithm, branch and bound algorithm, simulated annealing algorithm, tabu search algorithm, ant colony algorithm, particle swarm algorithm, artificial bee colony algorithm, genetic algorithm, Monte Carlo method, gradient descent algorithm, forgetting learning algorithm, neural network algorithm, genetic programming algorithm, reinforcement genetic algorithm, Bayesian optimization algorithm, Lagrange relaxation algorithm, convex optimization algorithm, Newton method, quasi-Newton method, interior point method, Lagrange multiplier method, alternating direction multiplier method, graph algorithm, permutation algorithm, probabilistic graphical model, fuzzy logic algorithm, neuro-fuzzy system, quantum algorithm, linear programming algorithm, nonlinear programming algorithm, multi-objective optimization algorithm, Markov decision process, game theory algorithm, differential evolution algorithm, XGBoost (extreme gradient boosting), LightGBM (lightweight gradient boosting), random forest, support vector machine (SVM), K-nearest neighbor algorithm (KNN), linear regression, ridge regression and Lasso regression One or more of the following: Regression), Self-Attention Mechanism, Autoencoder and Generative Adversarial Network (GAN), Convolutional Neural Network (CNN), Long Short-Term Memory Network (LSTM), Graph Convolutional Network (GCN), Graph Neural Network (GNN), Reinforcement Learning (Q Learning, Policy Gradient, Deep Q Network DQN), Transfer Learning, Deep Neural Network (DNN), Naive Bayes Classifier, K-means Clustering, DBSCAN (Density-based Spatial Clustering), Laplace Smoothing, Pseudo-Inverse, Monte Carlo Tree Search (MCTS), Markov Chain Monte Carlo (MCMC), Variational Autoencoder (VAE), Transformer algorithm.

[0077] The output acquisition and training of the semi-supervised machine learning model is carried out according to the following steps. This is the construction method of the semi-supervised model in the data analysis module:

[0078] S1. The input and output data are the physical and chemical properties of a pure water sample and the blank value, respectively. These data are called data a. The input and output data are the physical and chemical properties of a pure water sample spiked with pollutants and the output data are the pollutant types and concentrations specified for the pure water sample. Data a and b are used to train a model in the data analysis module to obtain model M. If a pre-trained model M already exists, training is continued on model M.

[0079] S2. Based on model M, the physical and chemical properties of the original water sample are used as input to obtain model output. The model output at this point means the types and concentrations of pollutants in the original water sample predicted by model M. This set of outputs is called output T.

[0080] S3. The original water sample after the addition of the pollutant and the diluted original water sample are respectively designated as polluted water sample c and polluted water sample d. The physical and chemical properties of polluted water sample c are used as input, and the sum of output T and the pollutant type and concentration set for polluted water sample c is used as output. This pair of input and output data is referred to as data c. The physical and chemical properties of polluted water sample d are used as input, and output T is calculated as the dilution of the diluted original water sample. This is then summed with the pollutant type and concentration set for polluted water sample d as output. This pair of input and output data is referred to as data d. Model M is trained in the data analysis module using data c and data d.

[0081] S4. Repeat step 1.

[0082] When remote monitoring is required, a data transmission module is added between the data sampling module and the data analysis module.

[0083] The data transmission module sends the collected information of the data sampling module to the data analysis module through a remote signal transmitter. The remote signal transmitter includes one or more of: 2G / 3G / 4G / 5G DTU (data transmission unit), Wi-Fi module, Bluetooth module, ZigBee module, LoRa module, NB-IoT module, and satellite communication module.

[0084] Water sampling module, pollutant dosing module, data sampling module, data analysis module. When remote monitoring is required, a data transmission module can be added between the data sampling module and the data analysis module.

[0085] The present invention provides the following technical steps:

[0086] S1. The water sampling module sends the water sample, the original water sample and the diluted original water sample to the pollutant dosing module, and sends the water sample and the original water sample to the data analysis module;

[0087] S2, the pollutant dosing module randomly selects a set of pollutant types and concentration settings, and adds pollutants to the water samples from the water sampling module;

[0088] S3, the data sampling module obtains the physical and chemical property information of the water samples from the water sampling module and the pollutant dosing module;

[0089] S4, the data transmission module sends the collected information of the data sampling module to the data analysis module;

[0090] S5. The data analysis module inputs the physical and chemical property information into the machine learning model and trains the model based on the semi-supervised model construction method mentioned above;

[0091] S6. Repeat from step 1.

[0092] The present invention utilizes in-situ target detection water sample data and, through a semi-supervised learning method, enables the machine learning model to achieve stable training capabilities for different target water bodies, making the model more versatile.

[0093] Those skilled in the art will understand that the above description is only a preferred embodiment of the present invention, and the features described in the various embodiments and / or claims of the present disclosure may be combined or coupled in various ways, even if such a combination or coupling is not explicitly described in the present disclosure. It is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art may still modify the technical solutions described in the aforementioned embodiments or make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included in the scope of protection of the present invention.

[0094] Although preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they are aware of the basic inventive concepts. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention. Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, the present invention is intended to include such changes and modifications as fall within the scope of the claims and their equivalents.

Claims

1. A training system for a semi-supervised machine learning model for water pollutant detection, characterized in that: The system includes a water sampling module, a pollutant dosing module, a data sampling module, and a data analysis module; The water sampling module is used to collect the original water samples in the monitoring area, and send the pure water samples, the original water samples, and the diluted original water samples to the pollutant dosing module, and then send the pure water samples and the original water samples to the data sampling module; Water samples include original water samples, pure water samples, and diluted original water samples; The pollutant dosing module is used to add pollutants to the water sample according to the randomly obtained different combinations of pollutant types and concentration settings, obtain water samples, and send them to the data sampling module; The data sampling module is used to collect the physical and chemical properties of water samples from the water sampling module and the pollutant dosing module through detection equipment or sensors; The data analysis module is used to input the data on the physical and chemical properties of water samples collected by the water sampling module into the semi-supervised machine learning model, and to construct and train the semi-supervised machine learning model with the physical and chemical property data as input.

2. The training system for a semi-supervised machine learning model for water pollutant detection according to claim 1, characterized in that: The water sample is transported in the water sampling module to the pollutant dosing module and the data sampling module through gravity flow, water inlet pressure flow or water pump pressure flow.

3. The training system for a semi-supervised machine learning model for water pollutant detection according to claim 1, characterized in that: The diluted original water sample after dilution by the water sampling module is obtained by randomly selecting the mixing ratio of the original water sample and the pure water sample from 1:4, 2:3, 3:2 and 4:

1.

4. The training system for a semi-supervised machine learning model for water pollutant detection according to claim 1, characterized in that: The physical and chemical properties of the water sample in the data acquisition module include pH value, temperature, dissolved oxygen, turbidity, and conductivity.

5. The training system for a semi-supervised machine learning model for water pollutant detection according to claim 1, characterized in that: The model of machine learning training in the data analysis module includes one or more combinations of greedy algorithm, dynamic programming algorithm, divide and conquer algorithm, backtracking algorithm, and branch and bound algorithm.

6. The training system for a semi-supervised machine learning model for water pollutant detection according to claim 1, characterized in that: The method for constructing the semi-supervised machine learning model includes: S1. Take the physical and chemical properties of a pure water sample as input and the blank value as output, and refer to the input and output data as data a; take the physical and chemical properties of a pure water sample with pollutants added as input and the type and concentration of pollutants set for the pure water sample as output, and refer to the input and output data as data b. Use data a and data b to train a model in a data analysis module to obtain a model M. If a pre-trained model M already exists, continue training on model M. S2. Based on the model M, the physical and chemical properties of the original water sample are used as input to obtain the model output, which is output T; S3. The original water sample after the addition of pollutants and the diluted original water sample are respectively designated as polluted water sample c and polluted water sample d; the physical and chemical properties of the polluted water sample c are used as input, and the sum of output T and the pollutant type and concentration set for the polluted water sample c is used as output, and the input and output data are referred to as data c; the physical and chemical properties of the polluted water sample d are used as input, the dilution degree of the original water sample diluted by output T is calculated, and the sum of the output T and the pollutant type and concentration set for the polluted water sample d is used as output, and the input and output data are referred to as data d; the model M is trained in the data analysis module using data c and data d; S4. Repeat S1.

7. The training system for a semi-supervised machine learning model for water pollutant detection according to claim 1, characterized in that: A data transmission module is also provided between the data sampling module and the data analysis module for realizing remote monitoring.

8. A method for training a semi-supervised machine learning model for water pollutant detection, characterized in that: The training method is implemented based on the system according to any one of claims 1 to 7, and the method comprises the following steps: Step 1: The water sampling module sends the pure water sample, the original water sample, and the diluted original water sample to the pollutant dosing module, and sends the water sample and the original water sample to the data analysis module; Step 2: The pollutant dosing module randomly selects a set of pollutant types and concentration settings, and adds pollutants to the water samples of the water sampling module; Step 3: The data sampling module obtains the physical and chemical property information of the water samples from the water sampling module and the pollutant dosing module; Step 4: The data transmission module sends the physical and chemical property information collected by the data sampling module to the data analysis module; Step 5: The data analysis module inputs the physical and chemical property information into the semi-supervised machine learning model, and trains the semi-supervised machine learning model using the construction method of the semi-supervised machine learning model; Step 6: Repeat steps 1 to 5 to train a semi-supervised machine learning model for water pollutant detection.

9. A computer device comprising a memory and a processor, characterized in that A computer program is stored in the memory. When the processor runs the computer program stored in the memory, the processor executes the method according to claim 8.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to claim 8 are implemented.

Images