Drainage monitoring data intelligent platform

Abstract

The invention discloses a drainage monitoring data intelligent platform, and belongs to the technical field of data processing. Collecting drainage information in real time through intelligent monitoring equipment, recording collection time, integrating to generate a monitoring log, and transmitting the monitoring log to a cloud database for storage; water quality parameters are obtained through laboratory analysis of a water sample and are converted into standardized numerical values so as to eliminate differences among different dimensions; based on the weight corresponding to the water quality parameter, calculating to obtain a comprehensive water quality index, and performing early warning prompt according to the comprehensive water quality index; the average flow velocity is obtained by obtaining the flow velocity collected in the monitoring period, and the pressure loss value is calculated and compared with the preset threshold value so as to adjust the operation parameters of the pump station. A comprehensive water quality index, a pressure loss value, a water level and a flow rate are selected as target features, a decision function output result of a support vector machine (SVM) is utilized to predict a drainage operation state, and an early warning prompt is given out according to a prediction result.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an intelligent drainage monitoring data platform. Background Art

[0002] With the acceleration of urbanization, urban drainage systems are facing more and more challenges. Problems such as rainwater retention and sewage overflow have had a serious impact on urban life and the environment. The traditional drainage management model can no longer meet the development needs of modern cities.

[0003] However, traditional drainage data monitoring mainly relies on manual inspections and simple sensor equipment. This method is not only inefficient, but also difficult to achieve real-time monitoring. In addition, existing drainage monitoring systems often lack effective data analysis and prediction capabilities, and cannot predict the drainage operation status and provide early warnings, resulting in poor accuracy and efficiency in drainage monitoring. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent drainage monitoring data platform to solve the deficiencies in the background technology.

[0005] The object of the present invention can be achieved by the following technical solutions: an intelligent drainage monitoring data platform, including an information collection module, which collects drainage information in real time and records the collection time, integrates and generates monitoring logs, and transmits the monitoring logs to a cloud database for storage via a wireless or wired network;

[0006] The water quality monitoring module conducts laboratory analysis on water samples obtained from monitoring sites during the monitoring period and standardizes the corresponding water quality parameters; based on the weights corresponding to the water quality parameters, it calculates the comprehensive water quality index and issues early warning prompts based on the comprehensive water quality index;

[0007] The drainage pipe monitoring module obtains the drainage flow rate by traversing the monitoring log, calculates the pressure loss value, and compares it with the preset threshold to adjust the pump station operation parameters;

[0008] The prediction model building module selects the comprehensive water quality index, pressure loss value, water level and flow rate as target features, uses the decision function output results of the support vector machine (SVM) to predict the drainage operation status, and issues early warning prompts based on the prediction results.

[0009] Preferably, the drainage information includes water level, flow rate, flow velocity and water sample.

[0010] Preferably, the specific contents of the water quality monitoring module include: converting the detected values ​​of water quality parameters into standardized values, and the calculation formula is:

[0011]

[0012] In the formula, S m is the standardized value of the mth water quality parameter; C m is the detection value of the mth water quality parameter; C max and C min They are the maximum and minimum concentration values ​​of the water quality parameter during the monitoring period, respectively.

[0013] Preferably, different water quality parameters are assigned different weights according to their importance, and then weighted summation is performed to obtain a comprehensive water quality index W;

[0014] The calculation formula is:

[0015] W=Σ(β m ×S m );

[0016] Where W is the comprehensive water quality index; β m is the weight coefficient of the mth water quality parameter; S m is the standardized value of the mth water quality parameter;

[0017] The obtained comprehensive water quality index W is compared with the preset standard value. If the comprehensive water quality index W is greater than or equal to the preset standard value, an early warning prompt is automatically generated and sent to notify relevant departments and personnel to pay attention to changes in water quality; otherwise, it is prompted that the water quality is normal.

[0018] Preferably, the specific implementation content of the drainage pipe monitoring module includes: traversing the monitoring log to obtain the flow velocity at different time points during the monitoring period, obtaining the average flow velocity v, and calculating the pressure loss value using the Darcy-Weisbach equation;

[0019] The calculation formula is:

[0020]

[0021] Where P is the pressure loss value, f is the friction factor, also known as the resistance coefficient along the way, I is the pipe length, d is the pipe diameter, ρ is the fluid density, and v is the average flow velocity;

[0022] According to the system operation requirements, the pressure loss threshold is set, and the calculated pressure loss value is compared with the pressure loss threshold. If the pressure loss value is less than the pressure loss threshold, there is no need to adjust the operating parameters of the pump station; otherwise, an early warning prompt is issued and the operating parameters of the pump station are adjusted.

[0023] Preferably, the output result of the decision function of the support vector machine (SVM) is used to predict the drainage operation state, specifically including:

[0024] Set the input feature vector to X = [W, P, L, Q]; where W represents the comprehensive water quality index; P represents the pressure loss value; L represents the water level; Q represents the flow rate;

[0025] Obtain training sample data based on historical monitoring logs, including support vector X i and the corresponding label y i ; Where i = 1, 2, ..., n, n is the number of support vectors;

[0026] The labels corresponding to the support vectors indicate that the drainage operation status includes normal state and abnormal state, which can be expressed as:

[0027] y=1, drainage operation status is abnormal;

[0028] y=0, drainage operation is normal;

[0029] Get the input feature vector and construct a hyperplane that satisfies the equation Σω·X+b=0; where ω is the weight vector, X=[W,P,L,Q] is the input feature vector; b is the bias term;

[0030] The minimization objective function for building a prediction model can be expressed as:

[0031]

[0032] Where ω is the weight vector; b is the bias term; ω T is the transpose of the weight vector; X i is the support vector; st is the abbreviation of “subject to”, which means the constraint condition of minimizing the objective function.

[0033] Preferably, the minimum objective function is optimized using the Lagrange multiplier method, and a slack variable is introduced to handle the linear inseparable situation to obtain a decision function;

[0034] The calculation formula is:

[0035]

[0036] Where f(X) is the output of the decision function; X is the input feature vector; X i is the support vector; α i is the Lagrange multiplier; y i is the label corresponding to the support vector; K(X i ,X) is the kernel function; b is the bias term; n is the number of support vectors; sign() represents the sign function;

[0037] When used, the output of the decision function is the result of a sign function, that is, the value of f(X); if f(X)≥0, the prediction result is a positive class, that is, the output label is y=1, the drainage operation status is abnormal, and an early warning prompt is issued; if f(X)<0, the prediction result is a negative class, that is, the output label is y=0, and the drainage operation status is normal.

[0038] Preferably, verification sample data is obtained based on historical monitoring logs to evaluate the prediction model;

[0039] Count the prediction results and actual observation results of the validation sample data, obtain the accuracy and recall rate of the validation sample data, and quantify the performance of the prediction model by calculating the F1 score;

[0040] Based on the prediction model F1 score, the prediction model is optimized by adjusting the penalty parameter C or kernel function parameter of the prediction model until the prediction model F1 score reaches the performance standard value.

[0041] Furthermore, the number of samples TP with correct prediction results as positive class, the number FP with wrong prediction results as positive class, and the number FN with wrong prediction results as negative class are counted to obtain the precision and recall rate of the model;

[0042] The calculation formula is:

[0043]

[0044]

[0045] In the formula, represents the accuracy of the model, and R represents the recall rate of the model;

[0046] Based on the accuracy and recall of the model, the formula Calculate the F1 score.

[0047] Compared with the existing solutions, the present invention achieves the following beneficial effects:

[0048] The present invention collects drainage information in real time through intelligent monitoring equipment, reduces the workload of manual inspections, and is conducive to improving the timeliness of information acquisition; the generated monitoring logs are transmitted to the cloud database for storage, providing an efficient and reliable data storage method and improving data security.

[0049] The present invention obtains water quality parameters through laboratory analysis of water samples, and converts them into standardized values ​​to eliminate the differences between different dimensions; based on the weights corresponding to the water quality parameters, a comprehensive water quality index is calculated, and early warning prompts are given according to the comprehensive water quality index; it is conducive to timely discovering potential water quality problems, taking corresponding measures to deal with them, ensuring water quality safety, and preventing the occurrence of environmental pollution accidents;

[0050] The present invention obtains the flow rate collected during the monitoring period, obtains the average flow rate, calculates the pressure loss value and compares it with the preset threshold value to adjust the pump station operation parameters, which helps to optimize the operation efficiency of the pump station;

[0051] The present invention selects comprehensive water quality index, pressure loss value, water level and flow rate as target features, uses the decision function output results of support vector machine (SVM) to predict the drainage operation status, and issues early warning prompts according to the prediction results; the accuracy and reliability of the prediction model are improved, and a scientific basis is provided for the management and decision-making of the drainage system. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The present invention will be further described below in conjunction with the accompanying drawings.

[0053] Figure 1 This is a module block diagram of the drainage monitoring data intelligent platform of the present invention. DETAILED DESCRIPTION

[0054] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0055] Embodiment 1, as Figure 1 As shown, the drainage monitoring data intelligent platform includes information collection module, water quality monitoring module and drainage pipe monitoring module;

[0056] The information collection module collects drainage information in real time and records the collection time by deploying intelligent monitoring equipment at the monitoring site, integrates the drainage information with the corresponding collection time, generates a monitoring log, and transmits it to the cloud database for storage via wireless or wired networks;

[0057] Among them, drainage information includes water level, flow, flow rate, and water sample; intelligent monitoring equipment includes but is not limited to sensors, cameras, flow meters, liquid level meters, and flow meters;

[0058] In this embodiment, through all-round monitoring of monitoring sites and real-time monitoring of key parameters such as water level, manhole cover movement, flow rate, flow velocity, etc., the platform can quickly and accurately obtain drainage information, reduce the workload of manual inspections, and improve the timeliness of information acquisition.

[0059] The water quality monitoring module traverses the monitoring log to obtain water samples from the monitoring sites within the monitoring period, and performs laboratory analysis on the water samples; determines the water quality parameters as the detection target based on the pollution characteristics of the water body at the monitoring site, and obtains the detection values ​​of the water quality parameters;

[0060] The monitoring period is determined according to the change speed and importance of the parameter to be monitored, for example, the monitoring period is one day or one week;

[0061] Water quality parameters include but are not limited to pH, dissolved oxygen, chemical oxygen demand, five-day biochemical oxygen demand, total nitrogen, and total phosphorus;

[0062] Convert the detected values ​​of water quality parameters into standardized values ​​to eliminate the differences between different dimensions;

[0063] The calculation formula is:

[0064]

[0065] In the formula, S m is the standardized value of the mth water quality parameter; C m is the detection value of the mth water quality parameter; C max and C min are the maximum and minimum concentration values ​​of the water quality parameter during the monitoring period respectively;

[0066] Different water quality parameters are assigned different weights according to their importance, and then weighted summation is performed to obtain the comprehensive water quality index W;

[0067] The calculation formula is:

[0068] W = ∑(β m ×S m );

[0069] Where W is the comprehensive water quality index; β m is the weight coefficient of the mth water quality parameter; S m is the standardized value of the mth water quality parameter;

[0070] In practical applications, the importance of different water quality parameters is determined based on their impact on human health, ecosystem balance, and water resource management;

[0071] The obtained comprehensive water quality index W is compared with the preset standard value. If the comprehensive water quality index W is greater than or equal to the preset standard value, an early warning prompt is automatically generated and sent to notify relevant departments and personnel to pay attention to changes in water quality; otherwise, the water quality is normal; among them, the preset standard value is determined by comprehensive evaluation based on historical water quality monitoring data and relevant national or local water quality standards.

[0072] In this embodiment, by regularly testing the water quality at the monitoring site and generating early warning prompts, potential water quality problems can be discovered in a timely manner, water quality safety can be guaranteed, and strong support can be provided for environmental protection and water resources management.

[0073] The drainage pipe monitoring module traverses the monitoring log to obtain the flow velocity at different time points during the monitoring period, obtains the average flow velocity v, and uses the Darcy-Weisbach equation to calculate the pressure loss value;

[0074] The calculation formula is:

[0075]

[0076] Where P is the pressure loss value, f is the friction factor, also known as the resistance coefficient along the way, I is the pipe length, d is the pipe diameter, ρ is the fluid density, and v is the average flow velocity;

[0077] In practical applications, the friction factor f usually needs to be determined by experiments or empirical formulas because it is related to the viscosity of the fluid, the Reynolds number, and the relative roughness of the pipe wall;

[0078] According to the operating requirements of the system, the pressure loss threshold is set, and the calculated pressure loss value is compared with the pressure loss threshold. If the pressure loss value is less than the pressure loss threshold, there is no need to adjust the operating parameters of the pump station; otherwise, an early warning prompt is issued and the operating parameters of the pump station, such as flow rate and head, are adjusted to ensure the stable operation of the drainage system and extend the service life of the equipment.

[0079] In this embodiment, by calculating the pressure loss value and comparing it with the pressure loss threshold, corresponding measures are taken to reduce the pressure loss, which is beneficial to ensuring the stable operation of the drainage system and improving the operating efficiency of the system.

[0080] Embodiment 2, based on embodiment 1, further comprises:

[0081] The prediction model construction module selects the comprehensive water quality index, pressure loss value, water level and flow rate as the target features, and uses the decision function output results of the support vector machine (SVM) to predict the drainage operation status, including:

[0082] Set the input feature vector to X = [W, P, L, Q]; where W represents the comprehensive water quality index; P represents the pressure loss value; L represents the water level; Q represents the flow rate;

[0083] Obtain training sample data based on historical monitoring logs, including support vector X i and the corresponding label y i ; Where i = 1, 2, ..., n, n is the number of support vectors;

[0084] It should be noted that the labels corresponding to the support vectors indicate that the drainage operation status includes normal status and abnormal status, which can be expressed as:

[0085] y=1, drainage operation status is abnormal;

[0086] y=0, drainage operation is normal;

[0087] Get the input feature vector and construct a hyperplane that satisfies the equation ∑ω·X+b=0; where ω is the weight vector, X=[W,P,L,Q] is the input feature vector; b is the bias term;

[0088] The minimization objective function for building a prediction model can be expressed as:

[0089]

[0090] Where ω is the weight vector; b is the bias term; ω T is the transpose of the weight vector; X i is the support vector; st is the abbreviation of “subject to”, which means the constraint condition of minimizing the objective function;

[0091] The Lagrange multiplier method is used to optimize the minimum objective function, and slack variables are introduced to deal with the linear inseparable situation to obtain the decision function;

[0092] The calculation formula is:

[0093]

[0094] Where f(X) is the output of the decision function; X is the input feature vector; X i is the support vector; α i is the Lagrange multiplier; y i is the label corresponding to the support vector; K(X i ,X) is the kernel function; b is the bias term; n is the number of support vectors; sign() represents the sign function;

[0095] When used, the output of the decision function is the result of a sign function, that is, the value of f(X); if f(X)≥0, the prediction result is a positive class, that is, the output label is y=1, the drainage operation status is abnormal, and an early warning prompt is issued; if f(X)<0, the prediction result is a negative class, that is, the output label is y=0, and the drainage operation status is normal.

[0096] Obtain verification sample data based on historical monitoring logs to evaluate the prediction model;

[0097] Count the prediction results and actual observation results of the validation sample data, obtain the accuracy and recall rate of the validation sample data, and quantify the performance of the prediction model by calculating the F1 score;

[0098] Furthermore, the number of samples TP with correct prediction results as positive class, the number FP with wrong prediction results as positive class, and the number FN with wrong prediction results as negative class are counted to obtain the precision and recall rate of the model;

[0099] The calculation formula is:

[0100]

[0101]

[0102] In the formula, represents the accuracy of the model, and R represents the recall rate of the model;

[0103] Based on the accuracy and recall of the model, the formula Calculate and obtain the F1 score; and optimize the prediction model by adjusting the penalty parameter C or kernel function parameter of the prediction model until the F1 score of the prediction model reaches the performance standard value;

[0104] Among them, the performance standard value can be determined by cooperating with domain experts or referring to the experience of similar projects to determine a reasonable performance standard;

[0105] In this embodiment, a prediction model is constructed using a support vector machine to predict the drainage operation status, which is conducive to timely issuing early warning prompts based on the prediction results, and timely adjusting the drainage resource allocation plan to ensure urban water safety; by adjusting the prediction model parameters, the prediction model is optimized, which is conducive to improving the accuracy of the model prediction.

[0106] In the several embodiments provided by the present invention, it should be understood that the disclosed system can be implemented in other ways. For example, the above-described embodiments of the invention are only illustrative, for example, the division of modules is only a logical function division, and there may be other division methods in actual implementation.

[0107] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0108] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0109] It is obvious to a person skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the essential characteristics of the present invention.

[0110] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution 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 solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. Drainage monitoring data intelligent platform, characterized by: include: The information collection module collects drainage information in real time and records the collection time, integrates and generates monitoring logs, and transmits the monitoring logs to the cloud database for storage via wireless or wired networks; The water quality monitoring module conducts laboratory analysis on water samples obtained from monitoring sites during the monitoring period and standardizes the corresponding water quality parameters; Based on the weights corresponding to the water quality parameters, a comprehensive water quality index is calculated, and early warning prompts are issued based on the comprehensive water quality index; The drainage pipe monitoring module obtains the flow rate collected during the monitoring period, obtains the average flow rate, calculates the pressure loss value and compares it with the preset threshold value to adjust the pump station operation parameters; The prediction model building module selects the comprehensive water quality index, pressure loss value, water level and flow rate as target features, uses the decision function output results of the support vector machine (SVM) to predict the drainage operation status, and issues early warning prompts based on the prediction results.

2. The drainage monitoring data intelligent platform according to claim 1 is characterized in that: Drainage information includes water level, flow, flow rate, and water sample.

3. The drainage monitoring data intelligent platform according to claim 2 is characterized in that: The specific contents of the water quality monitoring module include: converting the detected values ​​of water quality parameters into standardized values, and the calculation formula is: In the formula, S m is the standardized value of the mth water quality parameter; C m is the detection value of the mth water quality parameter; C max and C min They are the maximum and minimum concentration values ​​of the water quality parameter during the monitoring period, respectively.

4. The drainage monitoring data intelligent platform according to claim 3 is characterized in that: Different water quality parameters are assigned different weights according to their importance, and then weighted summation is performed to obtain the comprehensive water quality index W; The calculation formula is: W=∑(β m ×S m ); Where W is the comprehensive water quality index; β m is the weight coefficient of the mth water quality parameter; S m is the standardized value of the mth water quality parameter; The obtained comprehensive water quality index W is compared with the preset standard value. If the comprehensive water quality index W is greater than or equal to the preset standard value, an early warning prompt is automatically generated and sent to notify relevant departments and personnel to pay attention to changes in water quality; otherwise, it is prompted that the water quality is normal.

5. The drainage monitoring data intelligent platform according to claim 1 is characterized in that: The specific implementation content of the drainage pipe monitoring module includes: traversing the monitoring log to obtain the flow velocity at different time points during the monitoring period, obtaining the average flow velocity v, and using the Darcy-Weisbach equation to calculate the pressure loss value; The calculation formula is: Where P is the pressure loss value, f is the friction factor, also known as the resistance coefficient along the way, I is the pipe length, d is the pipe diameter, ρ is the fluid density, and v is the average flow velocity; According to the system operation requirements, the pressure loss threshold is set, and the calculated pressure loss value is compared with the pressure loss threshold. If the pressure loss value is less than the pressure loss threshold, there is no need to adjust the operating parameters of the pump station; otherwise, an early warning prompt is issued and the operating parameters of the pump station are adjusted.

6. The drainage monitoring data intelligent platform according to claim 1 is characterized in that: The decision function output of the support vector machine (SVM) is used to predict the drainage operation status, including: Set the input feature vector to X = [W, P, L, Q]; where W represents the comprehensive water quality index; P represents the pressure loss value; L represents the water level; Q represents the flow rate; Obtain training sample data based on historical monitoring logs, including support vector X i and the corresponding label y i ; Where i = 1, 2, ..., n, n is the number of support vectors; The labels corresponding to the support vectors indicate that the drainage operation status includes normal state and abnormal state, which can be expressed as: y=1, drainage operation status is abnormal; y=0, drainage operation is normal; Get the input feature vector and construct a hyperplane that satisfies the equation Σω·X+b=0; where ω is the weight vector, X=[W,P,L,Q] is the input feature vector; b is the bias term; The minimization objective function for building a prediction model can be expressed as: Where ω is the weight vector; b is the bias term; ω T is the transpose of the weight vector; X i is the support vector; st is the abbreviation of "subject to", which means the constraint condition of minimizing the objective function.

7. The drainage monitoring data intelligent platform according to claim 6 is characterized in that: The Lagrange multiplier method is used to optimize the minimum objective function, and slack variables are introduced to deal with the linear inseparable situation to obtain the decision function; The calculation formula is: Where f(X) is the output of the decision function; X is the input feature vector; X i is the support vector; α i is the Lagrange multiplier; y i is the label corresponding to the support vector; K(X i ,X) is the kernel function; b is the bias term; n is the number of support vectors; sign() represents the sign function; When used, the output of the decision function is the result of a sign function, that is, the value of f(X); if f(X)≥0, the prediction result is a positive class, that is, the output label is y=1, the drainage operation status is abnormal, and an early warning prompt is issued; if f(X)<0, the prediction result is a negative class, that is, the output label is y=0, and the drainage operation status is normal.

8. The drainage monitoring data intelligent platform according to claim 7 is characterized in that: Obtain verification sample data based on historical monitoring logs to evaluate the prediction model; Count the prediction results and actual observation results of the validation sample data, obtain the accuracy and recall rate of the validation sample data, and quantify the performance of the prediction model by calculating the F1 score; Based on the prediction model F1 score, the prediction model is optimized by adjusting the penalty parameter C or kernel function parameter of the prediction model until the prediction model F1 score reaches the performance standard value.

9. The drainage monitoring data intelligent platform according to claim 8, characterized in that: Count the number of samples with correct prediction results as positive class TP, the number of samples with incorrect prediction results as positive class FP, and the number of samples with incorrect prediction results as negative class FN to obtain the precision and recall rate of the model; The calculation formula is: In the formula, represents the accuracy of the model, and R represents the recall rate of the model; Based on the accuracy and recall of the model, the formula Calculate the F1 score.

Images