River water ecological environment monitoring device based on Internet of Things

Abstract

The invention discloses a river water ecological environment monitoring device based on the Internet of Things, and relates to the technical field of intelligent control, and the river water ecological environment monitoring device is characterized in that a central control unit is initialized and is connected with a remote server, and communication parameters and monitoring frequency are configured through low-power-consumption wireless communication; based on the configured parameters and frequency, a water quality sensor in the central control unit is used for collecting key water quality data; the collected water quality data are uploaded to a remote server through low-power-consumption wireless communication and are analyzed; according to the analysis result, making a water quality purification decision by using artificial intelligence aided decision; operation parameters of the purification equipment are automatically adjusted by adopting an intelligent control algorithm based on decision, and rapid scanning of a water surface area is performed by combining an unmanned aerial vehicle and satellite remote sensing. Through application of a series of technologies, the efficiency and precision of water quality management are remarkably improved, and sustainable protection and utilization of water resources are achieved.

Description

Technical Field

[0001] The invention relates to the technical field of intelligent control, in particular to a river water ecological environment monitoring device based on the Internet of Things. Background Art

[0002] As an important part of the environment, water quality monitoring plays a vital role in water resource protection and management. Traditional water quality monitoring methods mainly rely on manual sampling and laboratory analysis, which is not only time-consuming and labor-intensive, but also difficult to achieve continuous monitoring and real-time data feedback. In recent years, with the rapid development of Internet of Things technology, more and more intelligent water quality monitoring systems have emerged. They integrate various sensors and wireless communication technologies to realize the automatic collection and remote transmission of water quality parameters, improving monitoring efficiency and data timeliness. However, most of the existing water quality monitoring systems still have some limitations, such as the lack of effective comprehensive water quality evaluation methods and intelligent decision support systems, which makes the monitoring results not intuitive enough and difficult to provide solutions when facing complex water quality problems.

[0003] In response to various problems, the present invention proposes a river water ecological environment monitoring device based on the Internet of Things, which realizes the comprehensive evaluation of water quality and abnormal identification by introducing the water quality index WQI calculation method and the abnormal detection algorithm, and optimizes the water purification decision-making process by using the decision tree algorithm and the reinforcement learning mechanism. Compared with the existing technology, the present invention can more accurately evaluate the water quality status and provide a more accurate and efficient water purification strategy based on the water quality monitoring data, thereby significantly improving the efficiency and effectiveness of water quality management and protection. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a river water ecological environment monitoring device based on the Internet of Things to solve the problems of untimely and discontinuous data collection during monitoring and excessive manual intervention in the water purification process leading to low efficiency and waste of resources.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In the first aspect, an embodiment of the present invention provides a river water ecological environment monitoring device based on the Internet of Things, which includes an initialization module: a central control unit initializes and establishes a connection with a remote server, and configures communication parameters and monitoring frequency through low-power wireless communication; a data acquisition module: based on the configured parameters and frequency, the water quality sensor in the central control unit is used to collect key water quality data; a transmission analysis module: the collected water quality data is uploaded to the remote server through low-power wireless communication, and analyzed; a decision-making module: based on the analysis results, artificial intelligence is used to assist in decision-making to make water purification decisions; a purification module: based on the decision, an intelligent control algorithm is used to automatically adjust the operating parameters of the purification equipment, and a rapid scan of the water surface area is performed in combination with drones and satellite remote sensing; a feedback recording module: if the water quality does not meet the standard after the scan, the purification process is repeated, and each purification process and result is recorded using blockchain technology.

[0008] As a preferred solution of the river water ecological environment monitoring device based on the Internet of Things of the present invention, the central control unit initializes and establishes a connection with the remote server, and the specific steps are as follows:

[0009] When the power is connected, the central control unit starts and performs self-test, initializing all connected sensors, wireless communications, and intelligent water purification;

[0010] The central control unit establishes a secure connection with the remote server via low-power wireless communication LoRaWAN.

[0011] As a preferred solution of the river water ecological environment monitoring device based on the Internet of Things of the present invention, wherein: the communication parameters and monitoring frequency are configured through low-power wireless communication, and the specific steps are as follows:

[0012] The central control unit sends status confirmation information, including device ID, hardware version, and software version, to the remote server via low-power wireless communication LoRaWAN;

[0013] The remote server configures the communication parameters and monitoring frequency according to the status information, and sends the configured communication parameters and monitoring frequency back to the central control unit via the low-power wireless communication LoRaWAN.

[0014] As a preferred solution of the river water ecological environment monitoring device based on the Internet of Things of the present invention, wherein: based on the configured parameters and frequency, the water quality sensor in the central control unit is used to collect key water quality data, and the specific steps are as follows:

[0015] According to the configured communication parameters and monitoring frequency sent by the remote server, the central control unit starts the water quality sensor and starts collecting water quality analog signal data;

[0016] The water quality sensor converts the collected water quality analog signal data into water quality digital signal data through the built-in digital converter A / D, and stores the water quality digital signal data in the memory of the central control unit.

[0017] As a preferred solution of the river water ecological environment monitoring device based on the Internet of Things described in the present invention, the key water quality data include pH value, dissolved oxygen DO, electrical conductivity EC, temperature, turbidity, and oxidation-reduction potential ORP.

[0018] As a preferred solution of the river water ecological environment monitoring device based on the Internet of Things of the present invention, wherein: the collected water quality data is uploaded to the remote server via low-power wireless communication, the specific steps are as follows:

[0019] The central control unit uploads the collected water quality digital signal data to the remote server via low-power wireless communication LoRaWAN;

[0020] During the uploading process, the central control unit will regularly upload its own battery status, communication transmission status, sensor status, storage status and operation status.

[0021] As a preferred solution of the river water ecological environment monitoring device based on the Internet of Things of the present invention, the specific steps of analyzing the water quality data uploaded to the remote server are as follows:

[0022] After receiving the water quality data, the remote server first uses the water quality index WQI to evaluate the overall water quality and identifies the outliers through the anomaly detection algorithm.

[0023] As a preferred solution of the river water ecological environment monitoring device based on the Internet of Things of the present invention, wherein: according to the analysis results, artificial intelligence is used to assist decision-making to make a decision on water purification, the specific steps are:

[0024] Based on the analysis results, the remote server uses the information gain algorithm of the decision tree and the reinforcement Q-learning mechanism to determine the best purification decision;

[0025] Strengthen the Q-learning mechanism algorithm;

[0026] When the information gain value is larger and the Q value is higher, the best purification decision can be determined.

[0027] As a preferred solution of the river water ecological environment monitoring device based on the Internet of Things of the present invention, wherein: the decision-making based on the use of intelligent control algorithm to automatically adjust the operating parameters of the purification equipment, combined with drones and satellite remote sensing to quickly scan the water surface area, the specific steps are:

[0028] The remote server determines the best purification scheme based on the completed decision and generates purification instructions;

[0029] The remote server sends the purification instructions to the central control unit via low-power wireless communication LoRaWAN;

[0030] After receiving the instruction, the central control unit starts the intelligent water purification method and adjusts the operating state of the purification equipment according to the parameters in the instruction;

[0031] Use drones and satellite remote sensing to quickly scan the water surface area and collect water surface information, including the distribution of floating objects on the water surface, water color changes, water surface temperature distribution, water surface fluctuations, location of water surface pollution sources, water surface vegetation coverage, and water transparency.

[0032] As a preferred solution of the river water ecological environment monitoring device based on the Internet of Things described in the present invention, if the water quality does not meet the standard after scanning, the purification process is repeated, and the blockchain method is used to record each purification process and results. The specific steps are:

[0033] When the water quality does not meet the standard, the remote server continues to adjust the purification instructions until the water quality returns to normal;

[0034] When the water quality returns to normal, the central control unit notifies the remote server to stop the purification command;

[0035] Use blockchain methods to record each purification process and results;

[0036] The central control unit summarizes the data from the monitoring period and generates a water quality monitoring report.

[0037] The beneficial effects of the present invention are as follows: through artificial intelligence-assisted decision-making technology, the automation and intelligence of the water purification process are realized; the technology can evaluate the water quality status according to the water quality index WQI, and timely discover water quality problems through anomaly detection algorithm; combined with the information gain algorithm of the decision tree and the enhanced Q-learning mechanism, the system can automatically formulate the optimal purification plan, and automatically adjust the operating parameters of the purification equipment through the intelligent control algorithm; the application of this technology significantly improves the efficiency and accuracy of water quality management, and realizes the sustainable protection and utilization of water resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0039] Figure 1This is a flow chart of the river water ecological environment monitoring device based on the Internet of Things in Example 1.

[0040] Figure 2 This is a flow chart of the decision-making process for purified water quality in Example 1. DETAILED DESCRIPTION

[0041] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0042] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0043] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0044] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a river water ecological environment monitoring device based on the Internet of Things, comprising the following steps:

[0045] S1. The central control unit initializes and establishes a connection with the remote server, and configures communication parameters and monitoring frequency through low-power wireless communication.

[0046] Furthermore, when the power is connected, the central control unit starts and performs self-tests, initializing all connected sensors, wireless communications, and intelligent water purification;

[0047] The central control unit establishes a secure connection with the remote server through low-power wireless communication LoRaWAN to receive instructions and upload data;

[0048] The central control unit sends status confirmation information, including device ID, hardware version, and software version, to the remote server via low-power wireless communication LoRaWAN;

[0049] The remote server configures the communication parameters and monitoring frequency according to the status information, and sends the configured communication parameters and monitoring frequency back to the central control unit via the low-power wireless communication LoRaWAN.

[0050] It should be noted that low-power wireless communication LoRaWAN is a wireless communication protocol designed specifically for low-power wide area networks; the design goal of LoRaWAN is to achieve long-distance communication, low power consumption and low cost, making it particularly suitable for IoT applications, especially those that require long-term operation without frequent battery replacement.

[0051] It should be noted that in order to ensure the secure transmission of data, a variety of encryption methods can be used; in water quality environment monitoring, considering the characteristics of LoRaWAN, TLS / SSL protocol can be used to protect the security of wireless communications; in addition, AES encryption can also be used to encrypt data packets to ensure the security of data during transmission.

[0052] It should be noted that TLS / SSL certificate management: obtain a certificate from a trusted certificate authority (CA); install it on the server; ensure that the validity of the certificate is checked regularly and updated in a timely manner.

[0053] Generation and exchange of AES keys: Generate keys using a cryptographically secure pseudo-random number generator (CSPRNG); exchange keys securely using a public key infrastructure (PKI) or the Diffie-Hellman protocol; keys should be stored securely to avoid leakage.

[0054] It should be noted that this step is to ensure that the central control unit can establish a connection with the remote server safely and efficiently, and configure the communication parameters and monitoring frequency to facilitate the accurate collection and transmission of water quality data; specifically, through power access and self-test, the central control unit initializes all connected sensors, wireless communications and intelligent water purification equipment to prepare for subsequent data collection; then, the central control unit establishes a secure connection with the remote server through low-power wireless communication LoRaWAN, and sends status confirmation information, including device ID, hardware version and software version, to ensure that the remote server can accurately identify and configure appropriate communication parameters and monitoring frequency; the remote server configures the communication parameters and monitoring frequency according to these status information, and sends these configurations back to the central control unit through LoRaWAN. In order to ensure the secure transmission of data, TLS / SSL protocol and AES encryption are used to protect the security of wireless communication, thereby ensuring the confidentiality and integrity of water quality data during transmission.

[0055] S2. Collect key water quality data using water quality sensors in the central control unit based on configured parameters and frequency.

[0056] Furthermore, according to the configured communication parameters and monitoring frequency sent by the remote server, the central control unit starts the water quality sensor and starts collecting water quality analog signal data;

[0057] The water quality sensor converts the collected water quality analog signal data into water quality digital signal data through the built-in digital converter A / D, and stores the water quality digital signal data in the memory of the central control unit and waits for uploading to the remote server;

[0058] Key water quality data, including pH, dissolved oxygen DO, conductivity EC, temperature, turbidity, oxidation-reduction potential ORP.

[0059] It should be noted that this step is to ensure that the central control unit can accurately collect key water quality data according to the pre-configured parameters and frequency. Specifically, the central control unit starts the water quality sensor according to the communication parameters and monitoring frequency sent by the remote server, and starts to collect water quality analog signal data; then, the water quality sensor converts the collected analog signal data into digital signal data through the built-in digital converter A / D, and stores these digital signal data in the memory of the central control unit for subsequent uploading to the remote server for analysis; these key water quality data include pH value, dissolved oxygen DO, conductivity EC, temperature, turbidity and redox potential ORP, etc., which are crucial for evaluating water quality conditions.

[0060] S3. Upload the collected water quality data to a remote server via low-power wireless communication and analyze it.

[0061] Furthermore, the central control unit uploads the collected water quality data to a remote server via low-power wireless communication LoRaWAN;

[0062] During the upload process, the central control unit will also regularly upload its own battery status, communication transmission status, sensor status, storage status and operation status;

[0063] Battery status: remaining power percentage, battery voltage, battery temperature, etc.;

[0064] Communication transmission status: signal strength, communication success rate, packet loss rate, communication module temperature, etc.;

[0065] Sensor status: whether the sensor is online, sensor calibration status, sensor fault alarm, etc.;

[0066] Storage status: remaining storage space, percentage of used space, etc.

[0067] Running status: software version, recent error log, system self-test results, etc.;

[0068] After receiving the water quality data, the remote server first uses the water quality index WQI to evaluate the overall water quality and identifies the abnormal values ​​through the anomaly detection algorithm. If an abnormal value is detected, the central control unit will mark it and further analyze the cause of the abnormality. The expression is:

[0069]

[0070] Where n is the number of water quality parameters, w i is the weight of the i-th water quality parameter, P i is the measured value of the ith water quality parameter, P i,min is the minimum acceptable value of the ith water quality parameter, P i,max is the maximum acceptable value of the i-th water quality parameter, i is the index of the water quality parameter;

[0071] Anomaly detection algorithm, the expression is:

[0072]

[0073] Among them, X i is the observed value of the ith water quality parameter, μ is the mean of the observed values, σ is the standard deviation of the observed values, and k is a threshold, usually 2 or 3, which is used to determine the boundary of outliers.

[0074] It should be noted that regarding the water quality index (WQI) formula, a value can be obtained through calculation, which can reflect the overall condition of water quality; the higher the value, the better the water quality; the lower the value, the poorer the water quality; the calculation of WQI involves the measured values, minimum acceptable values, maximum acceptable values ​​and weights of water quality parameters; these weights reflect the importance of different parameters to the overall condition of water quality; WQI can be used to compare water quality conditions at different times and places, and can also be used to assess whether water quality meets specific standards or regulations.

[0075] Regarding the anomaly detection algorithm, a set of water quality parameter observations marked as abnormal can be obtained through calculation; these anomalies can help you identify situations where water quality parameters deviate from the normal range, which may indicate water quality problems or failures in the monitoring system; they are also used to identify anomalies in water quality data, which may be caused by measurement errors, equipment failures or other unknown factors. Identifying these anomalies can timely discover potential problems and take appropriate measures; anomaly detection helps maintain the reliability of the water quality monitoring system and ensure the validity and accuracy of the data; it can also help to quickly respond to possible water quality deterioration events.

[0076] It should be noted that P i,min and P i,maxIt is set based on environmental standards or regulations of regulatory agencies, or it may be based on historical data statistics. These values ​​define the acceptable range of each water quality parameter and are used to assess whether the water quality condition meets the standard;

[0077] Environmental protection departments in various countries or regions may publish water quality standards, which contain minimum and maximum acceptable values ​​for various water quality parameters;

[0078] In the absence of specific standards, historical data can be used to determine these values; statistical analysis of historical data can be used to determine the minimum and maximum values ​​within the normal range of water quality parameters.

[0079] It should be noted that the parameter weight w in the decision tree i This can be determined in a number of ways, including:

[0080] The weight of a parameter can be a function of the information gain of that parameter;

[0081] The greater the parameter information gain, the higher its weight;

[0082] The weight of the parameter can be determined based on the degree of reduction in the Gini impurity of the subsets divided using the parameter;

[0083] The more the Gini impurity decreases, the higher the weight;

[0084] During the training process, feature importance methods can be used to evaluate the impact of each parameter on the classification results;

[0085] The more important a feature is, the higher its weight is.

[0086] It should be noted that this step is to ensure that the central control unit can upload the collected key water quality data to the remote server safely and efficiently through the low-power wireless communication LoRaWAN, and evaluate the water quality status and detect anomalies; specifically, when the central control unit uploads the water quality data to the remote server, it will also upload its own status information, including battery status, communication transmission status, sensor status, storage status and operation status, to ensure that the remote server can fully understand the working status of the central control unit; after receiving the water quality data, the remote server uses the water quality index WQI to evaluate the overall water quality status and identifies the existing anomalies through the anomaly detection algorithm; the water quality index WQI is calculated based on the measured values, minimum acceptable values ​​and maximum acceptable values ​​of the water quality parameters. These values ​​can be set based on environmental standards or regulations of regulatory agencies, or can be derived based on historical data statistics; the anomaly detection algorithm identifies anomalies by judging whether the deviation between the observed value of the water quality parameter and the average value exceeds a certain standard deviation range.

[0087] S4. Based on the analysis results, use artificial intelligence to assist in making decisions on water purification.

[0088] Furthermore, based on the analysis results, the remote server uses the information gain algorithm of the decision tree and the reinforced Q-learning mechanism to determine the best purification decision. If the water quality index WQI shows that the water quality does not meet the standard, the central control unit will predict the optimal purification plan based on the current water quality parameters and historical data, and continuously optimize the decision-making strategy to improve purification efficiency.

[0089] The information gain of the decision tree is expressed as:

[0090]

[0091] Among them, G(S,A) represents the information gain value of attribute A on data set S, H(S) is the entropy of data set S, S is the data set, A is an attribute in the attribute set, S v is a subset of the dataset S whose attribute A takes value v, |S v | is a subset S v is the size of the dataset S, |S| is the size of the dataset S, H(S v ) is a subset S v Entropy of

[0092] Strengthen the Q learning mechanism algorithm, the expression is:

[0093]

[0094] Among them, Q ′ (s t ,a t ) is the updated Q value, Q(s t ,a t ) is in state s t Take action t The current Q value, s t Represents the current state value, a t Represents in state s t The action value taken under t+1 From the state s t Take action t After reaching state s t+1 The immediate reward value obtained, α is the learning rate value, which determines the importance of new information, usually a value between 0 and 1, γ is the discount factor, which determines the importance of future rewards, s t+1 is the next state value, that is, take action a t The state reached later, a ′ is in state s t+1 The best action value that can be taken is For state s t+1Take the best action a ′ The maximum value of the cumulative reward expected to be obtained after

[0095] When the information gain value is larger and the Q value is higher, the best purification decision can be determined.

[0096] It should be noted that, regarding the decision tree information gain algorithm, through the decision tree information gain algorithm, it is possible to determine which water quality parameters have the greatest impact on the water quality status; specifically, the information gain value of each water quality parameter can be obtained, which reflects the importance of the parameter in water quality assessment;

[0097] In the process of decision tree construction, the split points are selected according to the information gain, so that the parameters with higher information gain can be given priority as nodes, thereby constructing a decision tree model that can efficiently distinguish water quality conditions; these important water quality parameters may include pH value, dissolved oxygen DO, electrical conductivity EC, etc.

[0098] The reinforcement Q learning mechanism can help the system learn how to adjust the purification strategy according to the current state of water quality parameters and historical data to achieve the best water purification effect. Specifically, a series of Q values ​​will be obtained, which represent the expected return of taking specific actions under specific conditions.

[0099] Based on these Q values, the system can automatically learn which purification strategies are most effective and apply these strategies to the actual water purification process; for example, the system can automatically adjust the type or concentration of the purifier according to the current state of the water quality parameters to achieve the best water purification effect.

[0100] For example, for a decision tree, the threshold for determining the best decision for information gain is as follows: set an information gain threshold, such as 0.5 (this depends on the specific data distribution); only when the information gain is greater than or equal to 0.5, the feature will be selected as the split feature; this can help avoid too subtle a split, thereby reducing the risk of overfitting;

[0101] An example of a threshold for determining the best decision for a reinforcement Q-learning mechanism: set a Q-value threshold, such as 1000 (this depends on the reward range and scale); when the Q-value of an action is greater than or equal to 1000, it can be considered the best action in the current state.

[0102] It should be noted that for each attribute A, the data set S can be divided by different values ​​v of attribute A to obtain different subsets S v For example, if attribute A is "temperature", then S v It could be the set of all samples with temperature v.

[0103] It should be noted that α controls the balance between new knowledge and old knowledge; the value range is usually [0, 1]; choosing a smaller α value will lead to a slower learning process, while a larger α value may lead to unstable learning; a common strategy is to start with a larger value and then gradually reduce it;

[0104] Determines the importance of future rewards; the value range is also [0, 1]. When γ is close to 1, it means that long-term rewards are more important; when γ is close to 0, short-term rewards are more important;

[0105] s t+1 Usually determined by the environment, it depends on the current state s t and the action taken t ; Specifically, in a reinforcement learning environment, when the agent performs an action, the environment updates the next state based on the action and the current state.

[0106] It should be noted that the experimental data modeling t+1 The process is:

[0107] Experimental data can be collected through practical operations;

[0108] Record each action t The state of t and the following state s t+1 ;

[0109] Use machine learning algorithms (e.g., decision trees, neural networks) to train a model to predict s t+1 ;

[0110] The model input is s t and a t , the output is s t+1 .

[0111] It should be noted that H(S v ) is a subset S v Entropy; Assume S v There are c categories, for each category j, p j is the proportion of samples belonging to this category, then H(S v ) is calculated as:

[0112]

[0113] It should be noted that in reinforcement learning, the state s t+1 Usually the current state s t and the action taken t jointly determined; this depends on the dynamic characteristics of the environment; for example, if the current state is a certain state of water quality and the action taken is to increase the amount of purifier, then the next state st+1 will be the state of the water after this operation; this process is usually part of the environment and can be modeled using experimental data.

[0114] It should be noted that decision trees can help determine which water quality parameters have the greatest impact on water quality conditions and thus prioritize these parameters; for example, if the decision tree analysis shows that dissolved oxygen levels are the most important factor, then increasing dissolved oxygen levels will be prioritized when developing a purification plan.

[0115] Q-learning can help the system automatically learn how to adjust the parameters of purification equipment to achieve the best results; for example, by continuously trying different purification strategies (such as changing the type or concentration of purifiers), the system can gradually learn which strategies are most effective and apply these strategies to the actual water purification process.

[0116] It should be noted that this step uses artificial intelligence technology to assist decision-making in order to develop the best water purification plan; specifically, the remote server uses the information gain algorithm of the decision tree to analyze the water quality data, determine which water quality parameters have the greatest impact on the water quality status, and give priority to these parameters accordingly; in addition, through the reinforcement Q learning mechanism, the system can automatically learn how to adjust the parameters of the purification equipment to achieve the best effect; the decision tree algorithm determines the best attribute segmentation point by calculating the information gain, thereby constructing a decision tree model to identify the key factors of water quality status; the reinforcement Q learning algorithm continuously tries different purification strategies, updates the strategies according to the results of water quality improvement, and gradually optimizes the decision strategy to improve purification efficiency.

[0117] S5. Based on the decision, intelligent control algorithms are used to automatically adjust the operating parameters of the purification equipment, and drones and satellite remote sensing are combined to conduct rapid scanning of the water surface area.

[0118] Furthermore, the remote server determines the best purification scheme based on the completed decision and generates purification instructions;

[0119] The remote server sends the purification instructions to the central control unit via low-power wireless communication LoRaWAN;

[0120] After receiving the instruction, the central control unit starts the intelligent water purification method and adjusts the operating state of the purification equipment according to the parameters in the instruction;

[0121] Use drones and satellite remote sensing to quickly scan water surface conditions, collect water surface information, and assist in water quality assessment, including the distribution of floating objects on the water surface, water color changes, water surface temperature distribution, water surface fluctuations, location of water surface pollution sources, water surface vegetation coverage, and water transparency.

[0122] It should be noted that drones can be equipped with equipment such as high-definition cameras, multispectral cameras or multi-band radars to obtain water surface information; for example, multispectral cameras can be used to detect the content of suspended matter in water bodies.

[0123] Once the data is collected, the images can be analyzed using image processing and machine learning techniques, for example, using computer vision algorithms to identify pollutants or floating objects on the water surface.

[0124] Satellite remote sensing can provide a wide range of water surface information, such as using synthetic aperture radar (SAR) to monitor water surface fluctuations, or using optical satellites to obtain changes in water surface color and vegetation coverage.

[0125] It should be noted that the specific image processing and machine learning algorithms used are:

[0126] Image preprocessing, including: radiation correction, geometric correction, etc.; using Gaussian filter to reduce noise impact; histogram equalization, etc.;

[0127] Feature extraction: Use the Canny operator to extract edges in the image; gray-level co-occurrence matrix to extract texture features;

[0128] Use support vector machine (SVM), random forest (RF) and other algorithms for classification; K-means clustering for identification and classification.

[0129] Use convolutional neural networks for automatic feature extraction and classification; use transfer learning to pre-train models to speed up training and improve accuracy.

[0130] It should be noted that this step realizes a high degree of automation and intelligence in the water purification process; the remote server determines the best purification plan based on the previously completed decision analysis and generates specific purification instructions; these instructions are transmitted to the central control unit via the low-power wireless communication technology LoRaWAN, which automatically adjusts the working parameters of the purification equipment according to the instructions to achieve precise control; at the same time, drones and satellite remote sensing technology are used to quickly scan the water surface area to collect water surface information, such as the distribution of floating objects, water color changes, temperature distribution, fluctuations, pollution source location and vegetation coverage, etc. This information is used to assist water quality assessment and further optimize purification strategies; drones are equipped with a variety of sensors, such as high-definition cameras and multi-spectral cameras, while satellites can provide a wide range of monitoring data; by analyzing these image data through image processing technology and machine learning algorithms, changes in water quality conditions can be effectively identified and monitored, thereby guiding the efficient execution of purification work.

[0131] S6. If the water quality does not meet the standard after scanning, the purification process will be repeated, and blockchain technology will be used to record each purification process and results.

[0132] Furthermore, when the water quality does not meet the standard, the remote server continues to adjust the purification instructions until the water quality returns to normal;

[0133] When the water quality returns to normal, the central control unit notifies the remote server to stop the purification command;

[0134] Use blockchain to record each purification process and results to ensure that the data is not tampered with;

[0135] The central control unit summarizes the data from the monitoring period, generates a water quality monitoring report, and sends it to the remote server via low-power wireless communication LoRaWAN for management personnel to review and analyze.

[0136] It should be noted that this step ensures that the water quality continues to meet the standards and records all purification activities in an unalterable way; when the water quality monitoring results show that the water quality does not meet the standards, the remote server will continue to adjust and issue new purification instructions until the water quality returns to normal; once the water quality meets the standards, the central control unit will send a notification to the remote server to stop sending purification instructions; in order to improve the reliability and transparency of the data, all purification processes and related results will be recorded through blockchain technology to ensure the authenticity and unalterability of the data. In addition, the central control unit will summarize the data at the end of each monitoring cycle, generate a detailed water quality monitoring report, and send it to the remote server through low-power wireless communication LoRaWAN, so that managers can check the water quality status and purification effect at any time, so as to make timely and effective management decisions. This set of processes realizes the continuous monitoring and improvement of water quality through automated and intelligent water quality management and the application of blockchain technology, while ensuring the security and credibility of all operation records.

[0137] In summary, the present invention realizes the automation and intelligence of the water purification process through artificial intelligence assisted decision-making technology; this technology can evaluate the water quality status according to the water quality index WQI, and timely discover water quality problems through anomaly detection algorithm; combined with the information gain algorithm of the decision tree and the enhanced Q learning mechanism, the system can automatically formulate the optimal purification plan, and automatically adjust the operating parameters of the purification equipment through the intelligent control algorithm; the application of this technology has significantly improved the efficiency and accuracy of water quality management, and realized the sustainable protection and utilization of water resources.

[0138] Example 2, referring to Table 1, is the second example of the present invention. To further verify the present invention, experimental simulation data of a river water ecological environment monitoring device based on the Internet of Things is provided.

[0139] In order to verify the effectiveness and advantages of the invention, this embodiment tested the water quality monitoring and purification system in a lake; during the test, the system performed continuous monitoring and automatic water purification for two weeks. The system mainly includes the following components: a central control unit, a remote server, a water quality sensor, a drone, and a satellite remote sensing device.

[0140] First, after the device is started, it performs a self-check and initializes all connected sensors, wireless communications, and intelligent water purification devices; the central control unit establishes a secure connection with the remote server through LoRaWAN and sends information such as device ID, hardware version, and software version; the remote server configures the communication parameters and monitoring frequency according to the status information, and sends the configuration information back to the central control unit; the central control unit starts the water quality sensor according to the parameters and frequency configured by the remote server to collect key water quality data, including pH value, dissolved oxygen DO, conductivity EC, temperature, turbidity, redox potential ORP, etc.; the central control unit also regularly uploads information such as battery status, communication transmission status, sensor status, storage status, and operating status; the central control unit uploads water quality data to the remote server through LoRaWAN. The server uses the water quality index WQ I to evaluate the overall water quality and identifies abnormal values ​​through anomaly detection algorithms.

[0141] Secondly, the remote server uses the information gain algorithm of the decision tree and the reinforced Q-learning mechanism to decide the best purification plan based on water quality data and status information. The remote server sends the purification instructions to the central control unit via LoRaWAN. The central control unit adjusts the operating parameters of the purification equipment according to the purification instructions. UAVs and satellite remote sensing quickly scan the water surface area, collect water surface information, and assist in water quality assessment.

[0142] Finally, the central control unit continuously monitors the water quality and sends a notification to the remote server when the water quality meets the standard. Blockchain technology is used to record each purification process and results to ensure the reliability and non-tamperability of the data. The central control unit aggregates the data, generates a water quality monitoring report, and sends it to the remote server.

[0143] The details are shown in the following table:

[0144] Table 1. Experimental record of river water ecological environment monitoring based on Internet of Things

[0145]

[0146]

[0147] It can be seen from the record table that the application of the water quality monitoring and purification system of the present invention on the four central control units has achieved remarkable results; the water quality parameters of all central control units, including pH value, dissolved oxygen DO, temperature and turbidity, are within the appropriate range, and the water quality index WQ I is between 0.74 and 0.82, indicating that the water quality is generally in good condition; more importantly, the water purification results of all central control units are "up to standard", proving that the water quality monitoring and purification system of the present invention can effectively improve water quality and ensure that the water quality continues to meet the standards.

[0148] It can be seen from the above data analysis that the water quality monitoring and purification system of the present invention has significant advantages. The system can automatically complete water quality monitoring, data analysis, decision-making and purification processes, greatly reducing the need for manual intervention; through decision trees and reinforcement learning mechanisms, the system can automatically learn and optimize purification strategies, thereby improving purification efficiency; the use of TLS / SSL protocol and AES encryption technology ensures the security of data transmission, while blockchain technology is used to ensure the non-tamperability of data records; combined with drone and satellite remote sensing technology, the system can comprehensively monitor the status of water surface areas, thereby improving the accuracy and reliability of water quality assessment; the present invention has obvious innovation and advantages in the field of water quality monitoring and purification, which not only improves the automation and intelligence level of water quality management, but also enhances the security and transparency of data, and is an important progress in the field of water quality monitoring and purification.

[0149] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A river water ecological environment monitoring device based on the Internet of Things, characterized by: include, Initialization module: The central control unit initializes and establishes a connection with the remote server, and configures communication parameters and monitoring frequency through low-power wireless communication; Data acquisition module: uses water quality sensors in the central control unit to collect key water quality data based on configured parameters and frequencies; Transmission and analysis module: upload the collected water quality data to the remote server through low-power wireless communication and analyze it; Decision-making module: Based on the analysis results, AI is used to assist in making decisions on water purification; Purification module: Based on decision-making, intelligent control algorithms are used to automatically adjust the operating parameters of purification equipment, and drones and satellite remote sensing are combined to quickly scan the water surface area; Feedback recording module: If the water quality does not meet the standard after scanning, the purification process will be repeated, and blockchain technology will be used to record each purification process and results.

2. The river water ecological environment monitoring device based on the Internet of Things as claimed in claim 1, characterized in that: The central control unit initializes and establishes a connection with the remote server, specifically in the following steps: When the power is connected, the central control unit starts and performs self-test, initializing all connected sensors, wireless communications, and intelligent water purification; The central control unit establishes a secure connection with the remote server via low-power wireless communication LoRaWAN.

3. The river water ecological environment monitoring device based on the Internet of Things as claimed in claim 2 is characterized by: The specific steps of configuring communication parameters and monitoring frequency through low-power wireless communication are as follows: The central control unit sends status confirmation information, including device ID, hardware version, and software version, to the remote server via low-power wireless communication LoRaWAN; The remote server configures the communication parameters and monitoring frequency according to the status information, and sends the configured communication parameters and monitoring frequency back to the central control unit via the low-power wireless communication LoRaWAN.

4. The river water ecological environment monitoring device based on the Internet of Things as claimed in claim 3 is characterized by: Based on the configured parameters and frequency, the water quality sensor in the central control unit is used to collect key water quality data. The specific steps are as follows: According to the configured communication parameters and monitoring frequency sent by the remote server, the central control unit starts the water quality sensor and starts collecting water quality analog signal data; The water quality sensor converts the collected water quality analog signal data into water quality digital signal data through the built-in digital converter A / D, and stores the water quality digital signal data in the memory of the central control unit.

5. The river water ecological environment monitoring device based on the Internet of Things as claimed in claim 4 is characterized by: The key water quality data include pH, dissolved oxygen DO, conductivity EC, temperature, turbidity, and oxidation-reduction potential ORP.

6. The river water ecological environment monitoring device based on the Internet of Things as claimed in claim 5, characterized in that: The collected water quality data is uploaded to the remote server via low-power wireless communication, and the specific steps are: The central control unit uploads the collected water quality digital signal data to the remote server via low-power wireless communication LoRaWAN; During the uploading process, the central control unit will regularly upload its own battery status, communication transmission status, sensor status, storage status and operation status.

7. The river water ecological environment monitoring device based on the Internet of Things as claimed in claim 6 is characterized by: The specific steps of analyzing the water quality data uploaded to the remote server are as follows: After receiving the water quality data, the remote server first uses the water quality index WQI to evaluate the overall water quality and identifies the outliers through the anomaly detection algorithm.

8. The river water ecological environment monitoring device based on the Internet of Things as claimed in claim 7, characterized in that: According to the analysis results, artificial intelligence is used to assist decision-making in making water purification decisions. The specific steps are: Based on the analysis results, the remote server uses the information gain algorithm of the decision tree and the reinforcement Q-learning mechanism to determine the best purification decision; Strengthen the Q-learning mechanism algorithm; When the information gain value is larger and the Q value is higher, the best purification decision can be determined.

9. The river water ecological environment monitoring device based on the Internet of Things as claimed in claim 7, characterized in that: The decision-making based intelligent control algorithm is used to automatically adjust the operating parameters of the purification equipment, and the drone and satellite remote sensing are combined to quickly scan the water surface area. The specific steps are: The remote server determines the best purification scheme based on the completed decision and generates purification instructions; The remote server sends the purification instructions to the central control unit via low-power wireless communication LoRaWAN; After receiving the instruction, the central control unit starts the intelligent water purification method and adjusts the operating state of the purification equipment according to the parameters in the instruction; Use drones and satellite remote sensing to quickly scan the water surface area and collect water surface information, including the distribution of floating objects on the water surface, water color changes, water surface temperature distribution, water surface fluctuations, location of water surface pollution sources, water surface vegetation coverage, and water transparency.

10. The river water ecological environment monitoring device based on the Internet of Things as claimed in claim 9, characterized in that: If the water quality does not meet the standard after scanning, the purification process is repeated, and the blockchain method is used to record each purification process and results. The specific steps are: When the water quality does not meet the standard, the remote server continues to adjust the purification instructions until the water quality returns to normal; When the water quality returns to normal, the central control unit notifies the remote server to stop the purification command; Use blockchain methods to record each purification process and results; The central control unit summarizes the data from the monitoring period and generates a water quality monitoring report.

Images