Intelligent Diagnostic Expert System for Underground Drainage Pipe Networks Based on Fuzzy Rules of Water Flow Velocity
By placing water flow velocity sensors at both ends of the drainage pipe and using fuzzy rules for pipe health diagnosis, the problems of poor safety and limited effectiveness of traditional detection methods are solved, and efficient pipe detection with automation and no manual operation is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- ZHEJIANG COLLEGE OF CONSTR
- Filing Date
- 2026-04-03
- Publication Date
- 2026-06-30
Smart Images
Figure CN122310179A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of underground pipeline inspection and evaluation, specifically to an intelligent diagnostic expert system for underground drainage pipe networks based on fuzzy rules of water flow velocity. Background Technology
[0002] The likelihood of accidents in underground drainage pipelines increases dramatically over time. Problems such as pipeline aging, corrosion, sedimentation, foreign object intrusion, and accidental damage will continuously arise, necessitating effective measures to minimize the occurrence of accidents. Regular pipeline inspections using advanced technologies, accurately assessing pipeline conditions, and promptly repairing pipelines with serious defects according to established principles can prevent accidents and significantly extend pipeline lifespan. Currently, numerous methods exist for drainage pipeline inspection, including visual inspection, manual mirror inspection, underwater inspection, pipeline television inspection, sonar inspection, and periscope inspection. These methods have been widely applied in drainage pipeline inspection both domestically and internationally, achieving excellent results.
[0003] However, each of the common drainage pipe inspection methods has its own drawbacks. For example, manual methods are unsafe and operate in harsh environments. Pipe television inspection requires that there is no water or that the water level in the pipe is very low. Sonar inspection requires that there is sufficient water depth in the pipe. Periscope inspection can only provide general information.
[0004] In summary, conventional drainage pipe inspection methods require manual labor, are time-consuming and have limited effectiveness, making it difficult to meet the fault detection needs of complex underground pipe networks in cities. Summary of the Invention
[0005] The technical problem this invention aims to solve is that traditional manual inspection methods for underground drainage pipes suffer from poor safety and harsh working environments. Methods such as pipe television inspection, sonar inspection, and periscope inspection have limitations, still requiring manual intervention, which is time-consuming and has limited effectiveness, making it difficult to meet the fault detection needs of complex urban underground pipe networks. This invention provides an intelligent diagnostic expert system for underground drainage pipe networks based on fuzzy rules of water flow velocity. By placing multiple symmetrical water flow velocity sensors at both ends of the drainage pipe to be inspected, and employing fuzzy inference methods, the health status of the drainage pipe is diagnosed.
[0006] The technical solution adopted by the present invention to solve its technical problem is: an intelligent diagnostic expert system for underground drainage pipe networks based on fuzzy rules of water flow velocity, characterized in that it includes external factors, internal processes of the pipe network, water flow velocity data and operating condition analysis and diagnosis system, wherein the operating condition analysis and diagnosis system is implemented using fuzzy rules of water flow velocity.
[0007] The operating condition analysis and diagnosis system consists of two parts: establishing a fuzzy rule base and fuzzy processing.
[0008] The steps for establishing the fuzzy rule base are as follows: S11, determining the structure of the fuzzy inference engine; S12, determining the membership function of the fuzzy subset; S13, establishing fuzzy control rules and identifying water flow velocity parameters.
[0009] Step S11 includes: placing multiple water flow velocity sensors at both ends of the underground drainage pipe to record water flow velocity data. ,in , The number of sensors at one end. and These represent the corresponding water flow velocities at the upstream and downstream ends, respectively. The fuzzy inference engine uses the data... The analysis yielded the diagnostic results. The determined fuzzy inference engine structure is a multi-input single-output type, and the fuzzy inference engine has a total of One input.
[0010] The water flow velocity sensor includes, but is not limited to, mechanical, turbine, ultrasonic, Doppler, and electromagnetic flow meters.
[0011] The water flow velocity sensors are placed at multiple locations on the drain pipe and are symmetrically arranged at both ends of the drain pipe. The positions can be flexibly determined as needed, such as being placed at equal distances along the axis or distributed on the same plane of the cross-section.
[0012] Step S12 includes: selecting three fuzzy subsets, namely, slow water flow rate (… ), water flow velocity ( ) and fast water flow ( ), used to cover input quantities Their membership functions are as follows: Five fuzzy subsets were selected to cover the output, namely, the pipeline is severely damaged ( Minor damage () ) and in good condition ( Their membership functions are as follows: .
[0013] The step S13 of establishing fuzzy control rules includes: water flow velocity data corresponding to each pair of sensors. Three fuzzy rules are established, with two types: "The slower the water flow, the more severe the pipe damage; at a medium water flow, the pipe is slightly damaged; the faster the water flow, the better the pipe condition" or "The faster the water flow, the more severe the pipe damage; at a medium water flow, the pipe is slightly damaged; the slower the water flow, the better the pipe condition." Combining these rules, a total of [number] fuzzy rules are established. Rules.
[0014] The water flow velocity parameter identification in step S13 includes: measuring the input of the drain pipe. and output Multiple sets of data are used to perform parameter identification of fuzzy rules, obtaining the fuzzy rules corresponding to each pair of sensors, thereby determining the specific... Rules.
[0015] The fuzzy processing includes the following steps: S21, fuzzification of water flow velocity data; S22, fuzzy inference engine; S23, data defuzzification.
[0016] The beneficial effects of this invention are that by placing multiple symmetrical water flow velocity sensors at both ends of the drainage pipe to be inspected, and employing fuzzy inference methods, the health status of the drainage pipe is diagnosed, resulting in a high degree of automation and more significant effects. This expert system for intelligent diagnosis of underground pipe networks using fuzzy rules of water flow velocity has the advantage of requiring no manual operation and can be applied to the complex working conditions of underground pipe networks. Attached Figure Description
[0017] Figure 1 This is a system structure diagram of the intelligent diagnostic expert system for underground drainage pipe networks of the present invention.
[0018] Figure 2 This is a flowchart of the working condition analysis and diagnosis system in the intelligent diagnostic expert system for underground drainage pipe networks of the present invention.
[0019] Figure 3 This is a schematic diagram of a water flow velocity sensor placed at both ends of an underground drainage pipe according to an embodiment of the present invention.
[0020] Figure 4 This is a schematic diagram showing the locations of multiple water flow velocity sensors at one end of an underground drainage pipe according to an embodiment of the present invention.
[0021] Figure 5 This is a fuzzy subset distribution diagram of the input quantities in an embodiment of the present invention.
[0022] Figure 6 This is a fuzzy subset distribution diagram of the output quantity in an embodiment of the present invention. Detailed Implementation
[0023] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, illustrating only the basic structure of the invention, and therefore only show the components relevant to the invention.
[0024] like Figure 1As shown, this invention discloses an intelligent diagnostic expert system for underground drainage pipe networks based on fuzzy rules for water flow velocity. The system comprises four sub-modules: external factors, pipe network processes, water flow velocity data, and a condition analysis and diagnostic system. External factors, such as rainfall and sewage discharge, can lead to accidental damage, aging, corrosion, deposition, or foreign object intrusion into the pipes. These external factors cause changes in the processes within the pipe network, the most significant of which is the change in water flow velocity at different locations within the pipe. Water flow velocity data is collected using water flow velocity sensors and transmitted to the condition analysis and diagnostic system. The diagnostic system processes the data according to fuzzy rules and finally outputs the diagnostic results.
[0025] As can be seen, a significant feature of this method is that it collects water flow velocity data in the pipeline as key data and uses fuzzy inference.
[0026] The operating condition analysis and diagnosis system consists of two parts: establishing a fuzzy rule base and fuzzy processing, such as... Figure 2 As shown. Establishing a fuzzy rule base includes the following steps: S11, determining the fuzzy inference engine structure; S12, determining the fuzzy subset membership functions; S13, establishing fuzzy control rules and identifying water flow velocity parameters. Fuzzy processing includes the following steps: S21, fuzzifying water flow velocity data; S22, fuzzy inference engine; S23, data defuzzification.
[0027] Example
[0028] The present invention will be further illustrated by specific embodiments below. In this embodiment, a smart diagnostic expert system for underground drainage pipe networks is implemented using fuzzy rules for water flow velocity, and four sub-modules are constructed: external factors, pipe network processes, water flow velocity data, and operating condition analysis and diagnostic system. The key components are the acquisition of water flow velocity data and the operation of the operating condition analysis and diagnostic system.
[0029] Water flow velocity data is acquired using a water flow velocity sensor. For example... Figure 3 As shown, water flow velocity sensors are placed at both ends of an underground drainage pipe to record the corresponding water flow velocities at the upstream and downstream ends. Figure 4 As shown, five sensors are placed at one end of the drain pipe. See also Figure 3 and Figure 4 Water flow velocity sensors are symmetrically placed at both ends of the drain pipe, with multiple sensors placed at equal intervals at one end. The recorded water flow velocity data is as follows: ,in , and These are the water flow velocities at the upstream and downstream ends, respectively, resulting in a total of 10 sensor data points.
[0030] The operating condition analysis and diagnosis system consists of two parts: establishing a fuzzy rule base and fuzzy processing. Establishing the fuzzy rule base involves measuring the input from the drainage pipe. and output Multiple sets of data are used to identify the parameters of fuzzy rules, obtaining the fuzzy rules corresponding to each pair of sensors. The fuzzy processing part then collects water flow velocity data from the drainage pipe to be tested and uses fuzzy inference to diagnose the health status of the drainage pipe.
[0031] The establishment of the fuzzy rule base in this embodiment is carried out according to the following steps: Step 1: Determine that the fuzzy inference engine structure is a multi-input single-output type with a total of 10 inputs.
[0032] Step 2: Determine the amount to cover the input. The membership functions of the three fuzzy subsets are as follows: Functions such as Figure 5 As shown. This formula is used for calculation for each water flow velocity data point.
[0033] Step 3: Determine the amount to cover the output. The membership functions are as follows: Functions such as Figure 6 As shown.
[0034] Step 4: Correspond to the water flow rate data for each pair of sensors Three fuzzy rules are established, with two types: "The slower the water flow, the more severe the pipe damage; at a medium water flow, the pipe is slightly damaged; the faster the water flow, the better the pipe condition" or "The faster the water flow, the more severe the pipe damage; at a medium water flow, the pipe is slightly damaged; the slower the water flow, the better the pipe condition." Combining these rules, a total of [number] fuzzy rules are established. Rules.
[0035] Step 5: Measure the inlet of the drain pipe and output Multiple sets of data were used to perform fuzzy rule parameter identification, obtaining the fuzzy rules corresponding to each pair of sensors, thereby determining 32 specific rules. In this embodiment, a total of 100 sets of data were measured, and 32 rules were obtained after parameter identification. Two representative rules are as follows:
[0036] If is and is and is and is and is then is ;
[0037] If is and is and is and is and is then is .
[0038] The fuzzy processing in this embodiment is implemented according to the following steps: Step 1: Collect the water flow velocity data of the underground pipeline to be detected, which are (0.453, 0.423), (0.452, 0.432), (0.344, 0.324), (0.634, 0.543), (0.555, 0.533). According to the membership function of the input quantity, the water flow velocity data is fuzzified to obtain FD(0.8764), FD(0.9115), FD(0.8837), FD(0.7129), FD(0.9207).
[0039] Step 2: Input the fuzzification result into the fuzzy inference engine. You will see that of the 32 rules obtained earlier, only the following rule applies:
[0040] If is and is and is and is and is then is .
[0041] Therefore, the calculated results are G(0.7528), G(0.8230), G(0.7674), G(0.4259), G(0.8414), and the average value is 0.7221.
[0042] Step 3: Deblurring the result data reveals the final test result as: "The underground drainage pipe is in good condition, with a condition index of 0.7221."
[0043] Thus, the entire diagnostic expert system of this embodiment has been constructed and executed.
[0044] Based on the preferred embodiments of the present invention described above, those skilled in the art can make various changes and modifications without departing from the technical concept of the invention. The technical scope of this invention is not limited to the contents of the specification, but must be determined by the scope of the claims.
Claims
1. An intelligent diagnostic expert system for underground drainage pipe networks based on fuzzy rules of water flow velocity, characterized in that, It includes external factors, pipeline processes, water flow velocity data, and a working condition analysis and diagnosis system, in which the working condition analysis and diagnosis system is implemented using fuzzy rules for water flow velocity.
2. The drainage pipe diagnostic expert system as described in claim 1, characterized in that, The operating condition analysis and diagnosis system consists of two parts: establishing a fuzzy rule base and fuzzy processing.
3. The expert system for diagnosing drainage pipes as described in claims 1 and 2, characterized in that, The steps for establishing the fuzzy rule base are as follows: S11, determining the structure of the fuzzy inference engine; S12, determining the membership function of the fuzzy subset; S13, establishing fuzzy control rules and identifying water flow velocity parameters.
4. The drain pipe diagnostic expert system as described in claims 1 and 3, characterized in that, Step S11 includes: placing multiple water flow velocity sensors at both ends of the underground drainage pipe to record water flow velocity data. ,in , The number of sensors at one end. and These represent the corresponding water flow velocities at the upstream and downstream ends, respectively. The fuzzy inference engine uses the data... The analysis yielded the diagnostic results. The determined fuzzy inference engine structure is a multi-input single-output type, and the fuzzy inference engine has a total of One input.
5. The drain pipe diagnostic expert system as described in claims 1 and 4, characterized in that, The water flow velocity sensor includes, but is not limited to, mechanical, turbine, ultrasonic, Doppler, and electromagnetic flow meters.
6. The drain pipe diagnostic expert system as described in claims 1 and 4, characterized in that, The water flow velocity sensors are placed at multiple locations on the drain pipe and are symmetrically arranged at both ends of the drain pipe. The positions can be flexibly determined as needed, such as being placed at equal distances along the axis or distributed on the same plane of the cross-section.
7. The drain pipe diagnostic expert system as described in claims 1 and 3, characterized in that, Step S12 includes: selecting three fuzzy subsets, namely, slow water flow rate (… ), water flow velocity ( ) and fast water flow ( ), used to cover input quantities Their membership functions are as follows: Five fuzzy subsets were selected to cover the output, namely, the pipeline is severely damaged ( Minor damage () ) and in good condition ( Their membership functions are as follows: .
8. The drain pipe diagnostic expert system as described in claims 1 and 3, characterized in that, The step S13 of establishing fuzzy control rules includes: water flow velocity data corresponding to each pair of sensors. Three fuzzy rules are established, with two types: "The slower the water flow, the more severe the pipe damage; at a medium water flow, the pipe is slightly damaged; the faster the water flow, the better the pipe condition" or "The faster the water flow, the more severe the pipe damage; at a medium water flow, the pipe is slightly damaged; the slower the water flow, the better the pipe condition." Combining these rules, a total of [number] fuzzy rules are established. Rules.
9. The expert system for diagnosing drainage pipes as described in claims 1 and 3, characterized in that, The water flow velocity parameter identification in step S13 includes: measuring the input of the drain pipe. and output Multiple sets of data are used to perform parameter identification of fuzzy rules, obtaining the fuzzy rules corresponding to each pair of sensors, thereby determining the specific... Rules.
10. The drain pipe diagnostic expert system as described in claims 1 and 2, characterized in that, The fuzzy processing includes the following steps: S21, fuzzification of water flow velocity data; S22, fuzzy inference engine; S23, data defuzzification.