Online monitoring method and system for black and odorous pit pond
Through the combination of multi-parameter water quality sensor and radial basis function neural network model, the low efficiency and data lag of water quality monitoring of black and odor ponds are solved, and comprehensive, efficient, real-time monitoring and abnormal alarm of black and odor ponds are achieved, improving the Management level.
Patent Information
- Application Number
- CN202411001667.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-25
- Publication Date
- 2024-12-06
AI Technical Summary
The existing technology cannot effectively monitor the water quality of black and odorous ponds, resulting in low monitoring efficiency and lagging data feedback, making it difficult to achieve comprehensive, efficient and real-time monitoring of black and odorous ponds.
Multi-parameter water quality sensors are used to collect data in real time, and data processing and outlier analysis are performed through the radial basis function neural network diffusion tracking model. Combined with wireless transmission and Ethernet communication, in-depth analysis of water quality and real-time monitoring and alarm.
It has achieved comprehensive, efficient and real-time monitoring of the water quality of black and odorous ponds, improved monitoring efficiency and management level, and can timely identify abnormal situations and trigger alarms.
Smart Images

Figure CN119086851A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of water treatment, and in particular relates to an online monitoring method and system for black and odorous ponds. Background Art
[0002] Black and smelly ponds refer to ponds with foul odors and black bottom mud due to the discharge of sewage, garbage, industrial wastewater and other pollution sources and environmental factors. Black and smelly ponds have the following characteristics: first, the water body has a distinct foul smell, which causes discomfort to the surrounding environment and residents; second, the surface of the water body is black or dark, and the bottom mud shows characteristics such as increased sediments and enriched organic matter; at the same time, there may be a large number of microorganisms such as algae and bacteria in the water body, resulting in eutrophication and euoxidation of the water quality.
[0003] Black and smelly ponds are prone to mosquito breeding and disease transmission, and have become a problem that affects the green ecology of cities and the health of residents. At present, the monitoring of black and smelly ponds mainly relies on traditional manual sampling and laboratory analysis. This method is inefficient, and there is a significant lag in data feedback, which makes it difficult to provide strong support for timely and accurate governance. Although there are some online water quality monitoring systems on the market, they can often only monitor a few parameters, lack real-time performance, and have a low level of intelligence, making it difficult to achieve comprehensive, efficient, and real-time monitoring of black and smelly ponds. Summary of the invention
[0004] The present invention provides an online monitoring method and system for black and odorous ponds, which are used to solve the technical problems of single parameters, weak real-time performance and low intelligence level in existing online monitoring of black and odorous ponds.
[0005] In order to achieve the above object, the technical solution adopted by the present invention is as follows:
[0006] An online monitoring method for black and smelly ponds, the online monitoring method comprising:
[0007] (1) Data collection and transmission: Multi-parameter water quality sensors are used to collect water quality data of black and odorous ponds in real time. The water quality data includes transparency S t1 , redox potential u t2 、Ammonia nitrogen t3 , dissolved oxygen I t4 , the water quality data is transmitted via wired or wireless means;
[0008] (2) Data processing and analysis: repairing and outlier processing the water quality data, and then using the radial basis function neural network diffusion tracking model to conduct in-depth analysis on the processed water quality data to determine whether the water quality is abnormal;
[0009] (3) Real-time monitoring and alarm: According to the pre-set alarm rules, when the water quality index exceeds the threshold or other abnormal conditions occur, the alarm mechanism is automatically triggered.
[0010] Furthermore, the water quality data to be repaired include missing data and distorted data, and the missing data is processed using a linear interpolation method.
[0011] Furthermore, the distorted data is processed by the mean smoothing method.
[0012] Furthermore, the water quality data is processed for outliers using the interquartile range method.
[0013] Furthermore, the interquartile range method processing flow is as follows:
[0014] (1) Calculate quartiles:
[0015] Calculate data x t The first quartile (Q1), i.e. 25% of the data points are less than or equal to this value.
[0016] Calculate data x t The second quartile (Q2), where 50% of the data points are less than or equal to this value.
[0017] Calculate data x t The third quartile (Q3), where 75% of the data points are less than or equal to this value;
[0018] (2) Calculate IQR:
[0019] IQR = Q3-Q1, which is the difference between the third quartile and the first quartile;
[0020] (3) Determine the outlier threshold:
[0021] Select a constant k to adjust the range of the IQR;
[0022] Calculate the lower limit lower = Q1-k*IQR and the upper limit upper = Q3+k*IQR;
[0023] (4) Identify outliers:
[0024] Iterate over each data point in the water quality dataset;
[0025] If a data point is less than lower or greater than upper, it is considered an outlier;
[0026] (5) Handling outliers:
[0027] Process the identified outliers.
[0028] Furthermore, k is set to 1.5 or 3. When k = 1.5, it is called the inner limit, and the classic box plot uses this as the boundary to calculate the outliers;
[0029] When k = 3, it is called the outer limit, and data points outside this range are considered extreme outliers.
[0030] Furthermore, the specific process of the radial basis function neural network diffusion tracking model is as follows:
[0031] Assume that the network input x is M-dimensional: x = [x1, x2, ..., x M ] T The hidden layer has a total of K nodes, the output y is L-dimensional, the length of the input and output sample pairs is N, and the action function of the hidden layer nodes of the radial basis network;
[0032] The input data vector is mapped to the hidden layer.
[0033] The hidden layer to output layer of the RBF network realizes a linear mapping of the conversion dimension.
[0034] Furthermore, the state characteristics include two states: normal and abnormal.
[0035] An online monitoring system for black and smelly ponds, the online monitoring system comprising:
[0036] Perception layer: The perception layer is the data source of the online monitoring system. It collects water quality data of black and smelly ponds in real time through multi-parameter water quality sensors. The water quality data is transmitted to the network layer via wired or wireless means.
[0037] Network layer: responsible for data transmission and communication, using a combination of wireless transmission and Ethernet communication to transmit data from the perception layer to the communication service layer;
[0038] Communication service layer: The communication service layer is the data processing center of the online monitoring system. It is connected to the perception layer through a data interface and receives water quality data from the perception layer. At the same time, the communication service layer repairs and processes the water quality data, and then uses the radial basis function neural network diffusion tracking model to conduct in-depth analysis of the processed water quality data to determine whether the water quality is abnormal;
[0039] Application layer: It is the user interface and information display platform of the online monitoring system. If the data in the communication service layer is abnormal and enters the alarm processing mechanism, users can view the monitoring points, basic information, and real-time status of the black and smelly ponds in real time through the visual interface.
[0040] Furthermore, the alarm processing mechanism notifies relevant personnel via text messages, and the alarm text messages include alarm type, alarm time, and alarm location.
[0041] Compared with the prior art, the present invention has the following beneficial effects:
[0042] The present invention adopts a multi-parameter water quality sensor to monitor the water quality in real time, and combines artificial intelligence data analysis function and real-time monitoring and alarm function to achieve comprehensive, efficient and real-time monitoring of black and smelly pond water quality, thereby improving monitoring efficiency and management level. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] Figure 1 It is a structural diagram of the online monitoring system of the present invention. DETAILED DESCRIPTION
[0044] The present invention is described in detail below in conjunction with specific embodiments. The following embodiments will help those skilled in the art to further understand the present invention, but are not intended to limit the present invention in any form. It should be noted that, for those of ordinary skill in the art, several changes and improvements can also be made without departing from the concept of the present invention. These all belong to the protection scope of the present invention.
[0045] An online monitoring method for black and smelly ponds, comprising:
[0046] (1) Data collection and transmission: Multi-parameter water quality sensors are used to collect water quality data of black and smelly ponds in real time. The water quality data contains transparency S t1 , redox potential u t2 、Ammonia nitrogen t3 , dissolved oxygen I t4 , the water quality data is transmitted via wired or wireless means;
[0047] (2) Data processing and analysis: Repair and process water quality data and outliers, then use the radial basis function neural network diffusion tracking model to conduct in-depth analysis of the processed water quality data to determine whether the water quality is abnormal;
[0048] The water quality data to be repaired include missing data and distorted data, and the missing data are processed by linear interpolation: Where: x t and x t-j are the data parameters sampled at time t and time tj respectively; x t-n is the missing data parameter at ti, ω i is the weight value at time i,
[0049] The distorted data is processed by the mean smoothing method:
[0050] or In the formula, and are the thresholds of the errors of adjacent sampling data, respectively, where
[0051]
[0052] After the above-mentioned linear interpolation and mean smoothing methods, the data were processed by the interquartile range method to eliminate outliers.
[0053] The specific process is as follows:
[0054] 1. Calculate quartiles:
[0055] Calculate data x t The first quartile (Q1), i.e. 25% of the data points are less than or equal to this value.
[0056] Calculate data x t The second quartile (Q2, also called the median) of the value, that is, 50% of the data points are less than or equal to this value.
[0057] Calculate data x t The third quartile (Q3) of the data, i.e. 75% of the data points are less than or equal to this value.
[0058] 2. Calculate IQR:
[0059] IQR = Q3-Q1, which is the difference between the third quartile and the first quartile.
[0060] 3. Determine the outlier threshold:
[0061] Select a constant k (usually 1.5 or 3) to adjust the range of the IQR.
[0062] Calculate the lower limit lower = Q1-k*IQR and the upper limit upper = Q3+k*IQR.
[0063] When k = 1.5, it is called the inner limit, and the classic box plot uses this as the boundary to calculate outliers.
[0064] When k = 3, it is called the outer limit, and data points outside this range are considered extreme outliers.
[0065] 4. Identify outliers:
[0066] Iterate over every data point in the dataset.
[0067] If a data point is less than lower or greater than upper, it is considered an outlier.
[0068] 5. Handling outliers:
[0069] The identified outliers are processed and repaired using the aforementioned linear interpolation method.
[0070] Specific process of radial basis function neural network diffusion tracking model:
[0071] Assume that the network input x is M-dimensional: x = [x1, x2, ..., x M ] T The hidden layer has a total of K nodes, the output y is L-dimensional, the length of the input and output sample pairs is N, and the action function of the hidden layer nodes of the radial basis network takes the Gaussian basis function:
[0072]
[0073] The input data vector is mapped to the hidden layer, and the output of the hidden layer node j is:
[0074]
[0075] Where: δ is the standardization constant of the hidden layer nodes, c is the center vector of the Gaussian function of the hidden layer nodes, c j =[c j1 ,c j2 ,...,c jM ] T
[0076] The hidden layer to output layer of the RBF network realizes a linear mapping of the conversion dimension, that is, the output of the output layer node k is:
[0077]
[0078] Where: jk is the adjustment weight from the hidden layer to the output layer; θ k is the bias of the output layer node k; y k As a response to the corresponding input signal, it is output to the workspace as an important control variable according to different backgrounds; the above x is the input water quality data, and the output y is the state feature, which includes normal and abnormal states.
[0079] (3) Real-time monitoring and alarm: According to the pre-set alarm rules, when the water quality index exceeds the threshold or other abnormal conditions occur, the alarm mechanism is automatically triggered.
[0080] like Figure 1 As shown, an online monitoring system for black and smelly ponds, the online monitoring system comprises:
[0081] Perception layer: The perception layer is the data source of the online monitoring system. It collects water quality data of black and smelly ponds in real time through multi-parameter water quality sensors. The water quality data is transmitted to the network layer via wired or wireless means.
[0082] Network layer: responsible for data transmission and communication, using a combination of wireless transmission and Ethernet communication to transmit data from the perception layer to the communication service layer;
[0083] Communication service layer: The communication service layer is the data processing center of the online monitoring system. It is connected to the perception layer through a data interface and receives water quality data from the perception layer. At the same time, the communication service layer repairs and processes the water quality data, and then uses the radial basis function neural network diffusion tracking model to conduct in-depth analysis of the processed water quality data to determine whether the water quality is abnormal;
[0084] Application layer: It is the user interface and information display platform of the online monitoring system. If the data in the communication service layer is abnormal and enters the alarm processing mechanism, users can view the monitoring points, basic information, and real-time status of the black and smelly ponds in real time through the visual interface.
[0085] The alarm processing mechanism notifies relevant personnel via text messages, which include the alarm type, alarm time, and alarm location.
[0086] Use multi-parameter water quality sensors to monitor water quality in real time and collect key water quality data including transparency S t1 , redox potential u t2 、Ammonia nitrogen t3 , dissolved oxygen I t4 , which can comprehensively reflect the water quality of black and smelly ponds.
[0087] Through wireless transmission and Ethernet communication, efficient and stable data transmission is ensured. The system data processing function is used to process abnormal data and use artificial models to perform data analysis, thereby identifying abnormal values and realizing real-time monitoring and alarm.
[0088] The above describes the specific embodiments of the present invention. It should be understood that the present invention is not limited to the above specific embodiments, and those skilled in the art can make various changes or modifications within the scope of the claims, which does not affect the essence of the present invention. In the absence of conflict, the embodiments of the present application and the features in the embodiments can be combined with each other arbitrarily.
Claims
1. An online monitoring method for black and smelly ponds, characterized in that: The online monitoring method comprises: (1) Data collection and transmission: Multi-parameter water quality sensors are used to collect water quality data of black and odorous ponds in real time. The water quality data includes transparency S t1 , redox potential u t2 、Ammonia nitrogen t3 , dissolved oxygen I t4 , the water quality data is transmitted via wired or wireless means; (2) Data processing and analysis: repairing and outlier processing the water quality data, and then using the radial basis function neural network diffusion tracking model to conduct in-depth analysis on the processed water quality data to determine whether the water quality is abnormal; (3) Real-time monitoring and alarm: According to the pre-set alarm rules, when the water quality index exceeds the threshold or other abnormal conditions occur, the alarm mechanism is automatically triggered.
2. The online monitoring method for black and smelly ponds according to claim 1, characterized in that: The water quality data to be repaired include missing data and distorted data, and the missing data are processed by linear interpolation.
3. The online monitoring method for black and smelly ponds according to claim 2 is characterized in that: The distorted data is processed using the mean smoothing method.
4. The online monitoring method for black and smelly ponds according to claim 1, characterized in that: The water quality data were processed for outliers using the interquartile range method.
5. The online monitoring method for black and smelly ponds according to claim 4 is characterized in that: The interquartile range method processing flow is as follows: (1) Calculate quartiles: Calculate data x t The first quartile (Q1), i.e. 25% of the data points are less than or equal to this value. Calculate data x t The second quartile (Q2), where 50% of the data points are less than or equal to this value. Calculate data x t The third quartile (Q3), where 75% of the data points are less than or equal to this value; (2) Calculate IQR: IQR = Q3-Q1, which is the difference between the third quartile and the first quartile; (3) Determine the outlier threshold: Select a constant k to adjust the range of the IQR; Calculate the lower limit lower = Q1-k*IQR and the upper limit upper = Q3+k*IQR; (4) Identify outliers: Iterate over each data point in the water quality dataset; If a data point is less than lower or greater than upper, it is considered an outlier; (5) Handling outliers: Process the identified outliers.
6. The online monitoring method for black and smelly ponds according to claim 5, characterized in that: k is 1.5 or 3. When k = 1.5, it is called the inner limit. The classic box plot uses this as the boundary to calculate outliers. When k = 3, it is called the outer limit, and data points outside this range are considered extreme outliers.
7. The online monitoring method for black and smelly ponds according to claim 1, characterized in that: The specific process of the radial basis function neural network diffusion tracking model is as follows: Assume that the network input x is M-dimensional: x = [x1, x2, ..., x M ] T The hidden layer has a total of K nodes, the output y is L-dimensional, the length of the input and output sample pairs is N, and the action function of the hidden layer nodes of the radial basis network; The input data vector is mapped to the hidden layer. The hidden layer to output layer of the RBF network realizes a linear mapping of the conversion dimension.
8. The online monitoring method for black and smelly ponds according to claim 7, characterized in that: The state characteristics include normal and abnormal states.
9. An online monitoring system for black and smelly ponds, characterized in that: The online monitoring method for black and smelly ponds according to any one of claims 1 to 8 comprises: Perception layer: The perception layer is the data source of the online monitoring system. It collects water quality data of black and smelly ponds in real time through multi-parameter water quality sensors. The water quality data is transmitted to the network layer via wired or wireless means. Network layer: responsible for data transmission and communication, using a combination of wireless transmission and Ethernet communication to transmit data from the perception layer to the communication service layer; Communication service layer: The communication service layer is the data processing center of the online monitoring system. It is connected to the perception layer through a data interface and receives water quality data from the perception layer. At the same time, the communication service layer repairs and processes the water quality data, and then uses the radial basis function neural network diffusion tracking model to conduct in-depth analysis of the processed water quality data to determine whether the water quality is abnormal; Application layer: It is the user interface and information display platform of the online monitoring system. If the data in the communication service layer is abnormal and enters the alarm processing mechanism, users can view the monitoring points, basic information, and real-time status of the black and smelly ponds in real time through the visual interface.
10. An online monitoring system for black and smelly ponds, characterized in that: The alarm processing mechanism notifies relevant personnel via text messages, and the alarm text messages include the alarm type, alarm time, and alarm location.
