Detection Method, Device and Computer Readable Storage Medium for Fault Area of Water Pipe Network

Abstract

The present invention discloses a method, device and computer-readable storage medium for detecting a fault area of a water pipe network. The method includes: detecting the water pressure, water flow rate and pipe wall pressure at a preset position in the water pipe network; determining whether the water pipe network has a fault according to the water pressure, the water flow rate and the pipe wall pressure; when the water pipe network has a fault, determining a first change curve corresponding to the water pressure according to the water pressure and historical water pressure data, determining a second change curve corresponding to the water flow rate according to the water flow rate and historical water flow rate data, and determining a third change curve corresponding to the pipe wall pressure according to the pipe wall pressure and historical pipe wall pressure; obtaining the fault area corresponding to the first change curve, the second change curve and the third change curve. The present invention can improve the detection efficiency of the fault area of the water pipe network.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular, to a method, device, and computer-readable storage medium for detecting a fault area of a water pipe network. Background Art

[0002] In urban water supply, a data acquisition system is provided in the water pipe network system. The data acquisition system can monitor data such as water pressure and water flow at preset positions of the water pipe network and transmit them back to the central server, so that managers can obtain data such as water pressure and water flow at preset positions of the water pipe network based on the terminal of the central server for fault analysis. However, in the fault detection of the water pipe network, it is often necessary to manually analyze the water pressure, water flow, and pipe wall pressure corresponding to each preset position to determine the fault location, and the detection efficiency of the fault area of the water pipe network is low. Summary of the Invention

[0003] Embodiments of the present invention provide a method, device, and computer-readable storage medium for detecting a fault area of a water pipe network, aiming to solve the technical problem of how to improve the detection efficiency of the fault area of the water pipe network.

[0004] Embodiments of the present invention provide a method for detecting a fault area of a water pipe network, and the method for detecting the fault area of the water pipe network includes:

[0005] Detecting the water pressure, water flow, and pipe wall pressure at preset positions in the water pipe network;

[0006] Determining whether the water pipe network fails according to the water pressure, the water flow, and the pipe wall pressure;

[0007] When the water pipe network fails, determining a first change curve corresponding to the water pressure according to the water pressure and historical water pressure data, determining a second change curve corresponding to the water flow according to the water flow and historical water flow data, and determining a third change curve corresponding to the pipe wall pressure according to the pipe wall pressure and historical pipe wall pressure;

[0008] Obtaining the fault area corresponding to the first change curve, the second change curve, and the third change curve.

[0009] In an embodiment, the step of obtaining the fault area corresponding to the first change curve, the second change curve, and the third change curve includes:

[0010] Taking the first change curve, the second change curve, and the third change curve as input parameters and inputting them into a preset trained neural network model, where the neural network model outputs the target area according to the first change curve, the second change curve, and the third change curve.

[0011] In one embodiment, before the step of inputting the first change curve, the second change curve, and the third change curve as input parameters into a preset trained neural network model, the method further includes:

[0012] Obtain a training set, where the training set includes a water pressure change curve sample, a water flow rate change curve sample, and a pipe wall pressure change curve sample, and the training set is collected at a preset position when a sample area in the water pipe network fails;

[0013] Construct a model to be trained, and perform model training on the model to be trained according to the training set;

[0014] When the loss function of the model to be trained converges, use the current model to be trained as the neural network model.

[0015] In one embodiment, the step of determining whether the water pipe network fails according to the water pressure, the water flow rate, and the pipe wall pressure includes:

[0016] Determine whether the water pressure belongs to a preset water pressure range, determine whether the water flow rate belongs to a preset water flow rate range, and determine whether the pipe wall pressure is greater than a preset pressure;

[0017] When the water pressure does not belong to the preset water pressure range and / or the water flow rate does not belong to the preset water flow rate range and / or the pipe wall pressure is greater than the preset pressure, determine that the water pipe network fails.

[0018] In one embodiment, the step of obtaining the fault area corresponding to the first change curve, the second change curve, and the third change curve includes:

[0019] Obtain the associated water pipe network coordinate positions according to the first change curve, the second change curve, and the third change curve;

[0020] Determine the target area according to the water pipe network coordinate positions.

[0021] In one embodiment, after the step of determining the fault area according to the water pressure change curve and the water flow rate change curve, the method further includes:

[0022] Determine the fault type according to the second change curve.

[0023] In one embodiment, the step of determining the fault type according to the second change curve includes:

[0024] Determine the time difference between the previous time point when the water flow rate is equal to 0 and the current time point according to the second change curve;

[0025] Determine whether the time difference is greater than a preset duration;

[0026] When the time difference is greater than the preset duration, determine that the fault type is a water pipe leak.

[0027] In one embodiment, after the step of determining the fault type according to the second change curve, the following steps are further included:

[0028] Output a prompt message indicating that there is a fault in the water pipe in the target area according to the fault type.

[0029] An embodiment of the present invention further provides a detection device for a fault area of a water pipe network. The detection device for a fault area of a water pipe network includes: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, each step of the detection method for a fault area of a water pipe network as described above is implemented.

[0030] An embodiment of the present invention further provides a computer-readable storage medium. A computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, each step of the detection method for a fault area of a water pipe network as described above is implemented.

[0031] In the technical solution of this embodiment, the detection device for a fault area of a water pipe network detects the water pressure, water flow rate, and pipe wall pressure at a preset position in the water pipe network; determines whether the water pipe network has a fault according to the water pressure, the water flow rate, and the pipe wall pressure; when the water pipe network has a fault, determines a first change curve corresponding to the water pressure according to the water pressure and historical water pressure data, determines a second change curve corresponding to the water flow rate according to the water flow rate and historical water flow rate data, determines a third change curve corresponding to the pipe wall pressure according to the pipe wall pressure and historical pipe wall pressure; obtains the fault area corresponding to the first change curve, the second change curve, and the third change curve. Since the detection device for a fault area of a water pipe network uses the water pressure, water flow rate, and pipe wall pressure as the initial conditions of the fault, generates change curves in combination with known historical data, and then takes the position in the water pipe network corresponding to each curve as the fault position, compared with manually analyzing a large number of numerical type data in the water pipe network, the detection efficiency of the fault area of the water pipe network can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0033] Figure 1 It is a schematic diagram of the hardware architecture of the detection device for the fault area of the water pipe network involved in the embodiments of the present invention;

[0034] Figure 2 It is a schematic flowchart of the first embodiment of the method for detecting the fault area of the water pipe network of the present invention;

[0035] Figure 3 It is a detailed flowchart of step S30 in the second embodiment of the method for detecting the fault area of the water pipe network of the present invention;

[0036] Figure 4 It is a detailed flowchart of step S30 in the third embodiment of the method for detecting the fault area of the water pipe network of the present invention;

[0037] Figure 5 It is a schematic flowchart of the fourth embodiment of the method for detecting the fault area of the water pipe network of the present invention. Specific embodiments

[0038] To better understand the above technical solutions, the exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0039] The main solution of the present invention is that the detection device for the fault area of the water pipe network detects the water pressure, water flow rate, and pipe wall pressure at preset positions in the water pipe network; determines whether the water pipe network fails according to the water pressure, the water flow rate, and the pipe wall pressure; when the water pipe network fails, determines the first change curve corresponding to the water pressure according to the water pressure and historical water pressure data, determines the second change curve corresponding to the water flow rate according to the water flow rate and historical water flow rate data, determines the third change curve corresponding to the pipe wall pressure according to the pipe wall pressure and historical pipe wall pressure; and obtains the fault area corresponding to the first change curve, the second change curve, and the third change curve.

[0040] Since the detection device for the fault area of the water pipe network uses the water pressure, water flow rate, and pipe wall pressure as the initial conditions for faults, generates change curves in combination with known historical data, and then takes the position in the water pipe network corresponding to each curve as the fault position, compared with the artificial analysis of numerous numerical type data in the water pipe network, the detection efficiency of the fault area of the water pipe network can be improved.

[0041] As an implementation, the detection device for the fault area of the water pipe network can be as Figure 1 .

[0042] The solution of the embodiment of the present invention relates to a detection device for a fault area of a water pipe network. The detection device for the fault area of the water pipe network includes: a processor 101, such as a CPU, a memory 102, and a communication bus 103. Among them, the communication bus 103 is used to realize the connection and communication between these components.

[0043] The memory 102 can be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. Figure 1 As such, a detection program can be included in the memory 103 as a computer-readable storage medium; and the processor 101 can be used to call the detection program stored in the memory 102 and perform the following operations:

[0044] Detect the water pressure, water flow rate, and pipe wall pressure at a preset position in the water pipe network;

[0045] Determine whether the water pipe network fails according to the water pressure, the water flow rate, and the pipe wall pressure;

[0046] When the water pipe network fails, determine a first change curve corresponding to the water pressure according to the water pressure and historical water pressure data, determine a second change curve corresponding to the water flow rate according to the water flow rate and historical water flow rate data, and determine a third change curve corresponding to the pipe wall pressure according to the pipe wall pressure and historical pipe wall pressure;

[0047] Obtain the fault area corresponding to the first change curve, the second change curve, and the third change curve.

[0048] In an embodiment, the processor 101 can be used to call the detection program stored in the memory 102 and perform the following operations:

[0049] Input the first change curve, the second change curve, and the third change curve as input parameters into a preset trained neural network model, where the neural network model outputs the target area according to the first change curve, the second change curve, and the third change curve.

[0050] In an embodiment, the processor 101 can be used to call the detection program stored in the memory 102 and perform the following operations:

[0051] Obtain a training set, where the training set includes a water pressure change curve sample, a water flow rate change curve sample, and a pipe wall pressure change curve sample, and the training set is collected at the preset position when a sample area in the water pipe network fails;

[0052] Construct a model to be trained, and perform model training on the model to be trained according to the training set;

[0053] When the loss function of the model to be trained converges, use the current model to be trained as the neural network model.

[0054] In one embodiment, the processor 101 may be configured to call a detection program stored in the memory 102 and perform the following operations:

[0055] Determine whether the water pressure belongs to a preset water pressure range, whether the water flow rate belongs to a preset water flow rate range, and whether the pipe wall pressure is greater than a preset pressure;

[0056] When the water pressure does not belong to the preset water pressure range and / or the water flow rate does not belong to the preset water flow rate range and / or the pipe wall pressure is greater than the preset pressure, determine that a failure has occurred in the water pipe network.

[0057] In one embodiment, the processor 101 may be configured to call a detection program stored in the memory 102 and perform the following operations:

[0058] Obtain the associated water pipe network coordinate positions according to the first change curve, the second change curve, and the third change curve;

[0059] Determine the target area according to the water pipe network coordinate positions.

[0060] In one embodiment, the processor 101 may be configured to call a detection program stored in the memory 102 and perform the following operations:

[0061] Determine the type of failure according to the second change curve.

[0062] In one embodiment, the processor 101 may be configured to call a detection program stored in the memory 102 and perform the following operations:

[0063] Determine the time difference between the previous time point when the water flow rate was equal to 0 and the current time point according to the second change curve;

[0064] Determine whether the time difference is greater than a preset duration;

[0065] When the time difference is greater than the preset duration, determine that the type of failure is a water pipe leak.

[0066] In one embodiment, the processor 101 may be configured to call a detection program stored in the memory 102 and perform the following operations:

[0067] Output a prompt message indicating that a failure has occurred in the water pipe in the target area according to the type of failure.

[0068] In the technical solution of this embodiment, the detection device for the water pipe network failure area detects the water pressure, water flow rate, and pipe wall pressure at a preset position in the water pipe network; determines whether the water pipe network fails according to the water pressure, the water flow rate, and the pipe wall pressure; when the water pipe network fails, determines a first change curve corresponding to the water pressure according to the water pressure and historical water pressure data, determines a second change curve corresponding to the water flow rate according to the water flow rate and historical water flow rate data, and determines a third change curve corresponding to the pipe wall pressure according to the pipe wall pressure and historical pipe wall pressure; obtains the failure area corresponding to the first change curve, the second change curve, and the third change curve. Since the detection device for the water pipe network failure area uses the water pressure, water flow rate, and pipe wall pressure as the initial conditions for failure, generates change curves in combination with known historical data, and then takes the position in the water pipe network corresponding to each curve as the failure position, compared with the artificial analysis of numerous numerical type data in the water pipe network, the detection efficiency of the water pipe network failure area can be improved.

[0069] To better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings of the specification and specific embodiments.

[0070] Refer to Figure 2 , Figure 2 This is the first embodiment of the method for detecting the failure area of the water pipe network of the present invention, and the method includes the following steps:

[0071] Step S10, detecting the water pressure, water flow rate, and pipe wall pressure at a preset position in the water pipe network.

[0072] In this embodiment, the water pipe network includes the existing water pipe network in the water supply area. The above preset position can be understood as multiple positions set in the water pipe network. The above water pressure, water flow rate, and pipe wall pressure are all taken by the detection station for the water pipe network failure area from the determined preset positions.

[0073] Step S20, determining whether the water pipe network fails according to the water pressure, the water flow rate, and the pipe wall pressure.

[0074] In this embodiment, the detection device for the water pipe network failure area can monitor the collected water pressure, water flow rate, and pipe wall pressure, and determine whether the water pipe network is abnormal according to the detection results.

[0075] Optionally, determining whether the water pressure belongs to a preset water pressure range, determining whether the water flow rate belongs to a preset water flow rate range, and determining whether the pipe wall pressure is greater than a preset pressure; when the water pressure does not belong to the preset water pressure range and / or the water flow rate does not belong to the preset water flow rate range and / or the pipe wall pressure is greater than the preset pressure, it is determined that the water pipe network fails.

[0076] Step S30, when a failure occurs in the water pipe network, determine a first change curve corresponding to the water pressure according to the water pressure and historical water pressure data, determine a second change curve corresponding to the water flow rate according to the water flow rate and historical water flow rate data, and determine a third change curve corresponding to the pipe wall pressure according to the pipe wall pressure and historical pipe wall pressure.

[0077] In this embodiment, when it is determined that a failure occurs in the water pipe network, the detection of the failure area of the water pipe network will generate change curves for the collected water pressure, water flow rate, and pipe wall pressure, including a first curve reflecting the change of water pressure, a second curve reflecting the change of water flow rate, and a third curve reflecting the pipe wall pressure.

[0078] Step S40, obtain the failure area corresponding to the first change curve, the second change curve, and the third change curve.

[0079] In this embodiment, the first change curve, the second change curve, and the third change curve are jointly associated with a failure area. Among them, the above association relationship can be preset based on big data statistics. It is easy to understand that when the detection device of the failure area of the water pipe network generates the above curves, it can be determined that the area jointly corresponding to the above curves is the failure area.

[0080] Optionally, obtain a training set, where the training set includes water pressure change curve samples, water flow rate change curve samples, and pipe wall pressure change curve samples, and the training set is collected at a preset position when a failure occurs in a sample area in the water pipe network; construct a model to be trained, and perform model training on the model to be trained according to the training set; when the loss function of the model to be trained converges, use the current model to be trained as the neural network model.

[0081] An artificial neural network is a mathematical model that processes information using a structure similar to the synaptic connections in the brain. In engineering and academia, it is often simply referred to as a neural network or a neural-like network. A neural network is an operation model composed of a large number of nodes (or neurons) interconnected with each other. Each node represents a specific output function, called an activation function. The connection between every two nodes represents a weighted value for the signal passing through this connection, which is called a weight, equivalent to the memory of the artificial neural network. The output of the network varies depending on the connection method, weight values, and activation functions of the network. Usually, the network itself approximates a certain algorithm or function in nature, or may be an expression of a logical strategy. Its construction concept is inspired by the operation of the biological (human or other animal) neural network function. An artificial neural network is usually optimized through a learning method based on mathematical statistics, so the artificial neural network is also a practical application of mathematical statistics methods. Through the standard mathematical methods of statistics, we can obtain a large number of local structure spaces that can be expressed by functions. On the other hand, in the field of artificial perception in artificial intelligence, we can use the application of mathematical statistics to make decisions in artificial perception (that is, through statistical methods, the artificial neural network can have simple decision-making and simple judgment abilities similar to humans). This method has more advantages than formal logical reasoning and calculation.

[0082] The loss function describes the loss of the system under different parameter values. To apply the loss function, the loss must be measurable through some medium. The most important application of the loss function in practice is to assist us in continuously reducing the variation of the target value through process improvement, rather than simply pursuing logical consistency. Now, for example: the output of the personnel in a certain factory is calculated in terms of yuan per hour, and what the loss function shows is the situation where the output changes with the indoor ventilation conditions. Each person working in the factory has their own loss function. For the sake of simplicity, assume that each person's loss function is a parabola, and the bottom point of it represents the ventilation condition when the output value is the largest. By superimposing the loss functions of all personnel, the overall loss function of the company must also be a parabola. If the ventilation condition deviates from this optimal level, additional losses will occur. When the parabola is tangent to the horizontal axis, there is a small section on each side of the tangent point that is almost coincident with the horizontal axis. That is to say, when there is a small deviation from the optimal point, the loss is so small that it can be ignored. Therefore, when the indoor ventilation condition slightly deviates from the equilibrium point, the resulting loss can be ignored. However, when far from the equilibrium point, someone always has to bear this loss. If we can derive a loss function with specific figures, we can calculate the optimal equilibrium point, what the most suitable ventilation condition is at the equilibrium point, and how much the cost expenditure to meet the requirements is. The loss function is not necessarily symmetric. Sometimes one side is very steep, and sometimes both sides are very steep. For example, in order to make the steel sheet easier to weld, columbium needs to be added. However, if the amount of columbium added is less than the required amount, it is purely a waste and has no benefit to welding at all. However, if the amount of columbium used is higher than one in a hundred thousand, it is also a waste, and the additional benefit is quite limited.

[0083] Optionally, obtain a training set, where the training set includes a water pressure change curve sample, a water flow change curve sample, and a pipe wall pressure change curve sample, and the training set is collected at a preset position when a fault occurs in a sample area in the water pipe network; construct a model to be trained, and perform model training on the model to be trained according to the training set; when the loss function of the model to be trained converges, use the current model to be trained as the neural network model.

[0084] In this embodiment, through the neural network for big data analysis and statistics, the efficiency of artificially pre-statistically analyzing the relationship between the fault rules of the water pipe network and the preset positions is significantly improved.

[0085] In the technical solution of this embodiment, since the detection device for the fault area of the water pipe network uses water pressure, water flow, and pipe wall pressure as the initial conditions of the fault, generates change curves by combining known historical data, and then takes the position in the water pipe network corresponding to each curve as the fault position, compared with artificially analyzing the numerous numerical type data in the water pipe network, the detection efficiency of the fault area of the water pipe network can be improved.

[0086] Refer to Figure 3 , Figure 3 This is the second embodiment of the detection method for the fault area of the water pipe network of the present invention. Based on the first embodiment, step S30 includes:

[0087] Step S31, determining whether the water pressure belongs to a preset water pressure range, determining whether the water flow rate belongs to a preset water flow rate range, and determining whether the pipe wall pressure is greater than a preset pressure.

[0088] In this embodiment, the above-mentioned preset water pressure range, preset water flow rate range, and preset pressure can be determined through the collected big data.

[0089] Step S32, when the water pressure does not belong to the preset water pressure range and / or the water flow rate does not belong to the preset water flow rate range and / or the pipe wall pressure is greater than the preset pressure, it is determined that the water pipe network has a fault.

[0090] In this embodiment, the independent detection of the water pipe network fault can be performed through one of multiple data. For example, data of the above-mentioned water pressure, water flow rate, and pipe wall pressure, etc.

[0091] In the technical solution of this embodiment, the detection of the water pipe network fault is determined by multiple criteria. Compared with using a single criterion, the detection ability is stronger, and the timeliness of the water pipe network fault detection is indirectly improved.

[0092] Refer to Figure 4 , Figure 4 This is the third embodiment of the detection method for the fault area of the water pipe network of the present invention. Based on any one of the first to second embodiments, step S30 includes:

[0093] Step S33, obtaining the associated water pipe network coordinate positions according to the first change curve, the second change curve, and the third change curve.

[0094] Step S34, determining the target area according to the water pipe network coordinate positions.

[0095] In this embodiment, considering the characteristics of the curves, it is easy to have calculation errors when finding a single fault position corresponding to multiple curves. Therefore, virtual coordinates can be set for each position in the water pipe network. When there are multiple coordinate points corresponding to the first curve, the second curve, and the third curve at the same time, the target fault area can be determined based on each coordinate point. For example: when there are two coordinate points corresponding to the three curves, the midline between the two points can be used as the fault area; when there are more than two, the coordinate points commonly corresponding to the above curves can be connected, and then the end of the obtained shape can be used as the above-mentioned fault area.

[0096] In the technical solution of this embodiment, each position in the water pipe network is marked by the shape of coordinate points. When determining the fault area, the determination method of the regular area can be made more powerful, reducing the probability of reporting multiple areas simultaneously.

[0097] Referring to Figure 5 , Figure 5 This is the fourth embodiment of the method for detecting the fault area of the water pipe network of the present invention. Based on any one of the first to third embodiments, after step S40, it further includes:

[0098] Step S50, determining the fault type according to the second change curve.

[0099] Optionally, determine the time difference between the previous time point when the water flow rate is equal to 0 and the current time point according to the second change curve; determine whether the time difference is greater than a preset duration; when the time difference is greater than the preset duration, determine that the fault type is water pipe leakage. Among them, when the water flow rate does not return to 0 for a long time, the fault type can be judged as water pipe leakage.

[0100] Optionally, output a prompt message indicating that the water pipe in the target area has a fault according to the fault type. Among them, by means of the prompt message for reminder, the maintenance personnel can timely understand the fault type.

[0101] In this embodiment, by determining the fault type and notifying, the maintenance personnel can make preparations for repair in advance, without having to go to the fault area to analyze the fault type, improving the efficiency of fault repair.

[0102] To achieve the above object, an embodiment of the present invention further provides a device for detecting the fault area of a water pipe network. The device for detecting the fault area of the water pipe network includes: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements each step of the method for detecting the fault area of the water pipe network as described above.

[0103] To achieve the above object, an embodiment of the present invention further provides a computer-readable storage medium. A computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, it implements each step of the method for detecting the fault area of the water pipe network as described above.

[0104] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program implemented on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0105] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices to produce a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices produce means for implementing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 block or multiple blocks.

[0106] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including instruction means that implement the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 block or multiple blocks.

[0107] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 block or multiple blocks.

[0108] It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention can be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In a unit claim listing several means, several of these means can be embodied by the same item of hardware. The use of the words first, second, and third, etc. does not denote any order. These words can be interpreted as names.

[0109] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments and all changes and modifications falling within the scope of the present invention.

[0110] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A detection method for a failure area of a water pipe network, characterized in that, The detection method for the faulty area of the water pipe network includes: Detecting the water pressure, water flow rate, and pipe wall pressure at preset positions in the water pipe network; Determining whether the water pipe network has a fault based on the water pressure, water flow rate, and pipe wall pressure; When the water pipe network has a fault, determining the first change curve corresponding to the water pressure based on the water pressure and historical water pressure data, determining the second change curve corresponding to the water flow rate based on the water flow rate and historical water flow rate data, and determining the third change curve corresponding to the pipe wall pressure based on the pipe wall pressure and historical pipe wall pressure; Obtaining a training set, where the training set includes water pressure change curve samples, water flow rate change curve samples, and pipe wall pressure change curve samples, and is collected at the preset positions when a sample area in the water pipe network has a fault; Constructing a model to be trained, and training the model to be trained according to the training set; When the loss function of the model to be trained converges, taking the current model to be trained as a neural network model, where the neural network model is a mathematical model that processes information using a structure similar to the synaptic connections in the brain; Taking the first change curve, the second change curve, and the third change curve as input parameters and inputting them into the preset trained neural network model, obtaining the coordinate points corresponding to the first change curve, the second change curve, and the third change curve, determining the faulty area based on each coordinate point. If the number of coordinate points corresponding to the three curves is two, then taking the midline between the two points as the faulty area. When the number of coordinate points is greater than two, the coordinate points commonly corresponding to the three curves can be connected, and then taking the terminal of the obtained shape as the faulty area, where the neural network model outputs the target area according to the first change curve, the second change curve, and the third change curve.

2. The detection method of the water pipe network fault area according to claim 1, characterized in that The step of determining whether the water pipe network has a fault based on the water pressure, water flow rate, and pipe wall pressure includes: Determining whether the water pressure belongs to a preset water pressure range, determining whether the water flow rate belongs to a preset water flow rate range, and determining whether the pipe wall pressure is greater than a preset pressure; When the water pressure does not belong to the preset water pressure range and / or the water flow rate does not belong to the preset water flow rate range and / or the pipe wall pressure is greater than the preset pressure, determining that the water pipe network has a fault.

3. The detection method for the failure area of the water pipe network according to claim 1, characterized in that, The step of obtaining the faulty area corresponding to the first change curve, the second change curve, and the third change curve includes: Obtaining the coordinate positions of the water pipe network associated with the first change curve, the second change curve, and the third change curve; Determining the target area based on the coordinate positions of the water pipe network.

4. The detection method for the failure area of the water pipe network according to claim 1, characterized in that After the step of determining the faulty area based on the water pressure change curve and the water flow rate change curve, the method further includes: Determining the type of fault according to the second change curve.

5. The detection method for the failure area of the water pipe network according to claim 4, characterized in that, The step of determining the type of fault according to the second change curve includes: Determining the time difference between the previous time point when the water flow rate is equal to 0 and the current time point according to the second change curve; Determine whether the time difference is greater than a preset duration; When the time difference is greater than the preset duration, determine that the fault type is a water pipe leak.

6. The detection method for the fault area of the water pipe network according to claim 4, wherein After the step of determining the fault type according to the second change curve, the method further includes: Output a prompt message indicating that there is a fault in the water pipe in the target area according to the fault type.

7. A detection device for a failure area of a water pipe network, characterized in that, The detection device for the water pipe network fault area includes: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the steps of the detection method for the water pipe network fault area according to any one of claims 1 to 6 are implemented.

8. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium. When the computer program is executed by the processor, the steps of the detection method for the water pipe network fault area according to any one of claims 1 to 6 are implemented.

Images