Intelligent simulation fault early warning method for urban central heating pipe network

Abstract

The invention belongs to the technical field of fault detection, and provides an intelligent simulation fault early warning method for an urban central heating pipe network, which comprises the following steps of: S1, constructing a high-precision mathematical simulation model containing dynamic behaviors of a pipe network section based on physical characteristics and operating parameters of the heating primary pipe network section; s2, collecting operation data of a heat supply primary pipe network section in real time; s3, inputting the acquired operation data into the simulation model, performing real-time or near-real-time dynamic simulation, and simulating the actual operation state of the pipe network section; according to the invention, the high-precision mathematical simulation model is constructed, the operation data is collected in real time, the data analysis algorithm is used for fault prediction, and when a fault or an abnormal state is predicted to reach a preset threshold value, an early warning mechanism is automatically triggered, so that automation and intelligentization of fault early warning are realized; according to the method, the accuracy and timeliness of fault early warning are remarkably improved, and a powerful guarantee is provided for safe and stable operation of a heat supply system.

Description

Technical Field

[0001] The present invention belongs to the technical field of fault detection, and in particular relates to an intelligent simulation fault early warning method for a city centralized heating pipe network. Background Art

[0002] In urban heating systems, primary pipe networks play a crucial role in heat transmission. However, due to the long-term high loads and the impact of various factors, such as the external environment, material aging, and improper operation, these pipe networks are at high risk of failure.

[0003] Traditional fault detection methods often rely on manual inspections and empirical judgment. This approach is not only inefficient but also difficult to detect potential faults in a timely and accurate manner. With the continuous development of intelligent technology, people have begun to explore the application of intelligent technology in fault warning of primary heating pipe networks to improve the accuracy and timeliness of warnings.

[0004] However, existing intelligent fault warning methods still have some shortcomings, such as low model accuracy, incomplete data collection, inaccurate fault prediction, etc., which make it difficult to meet the heating system's needs for efficient and accurate fault warning.

[0005] To this end, those skilled in the art have proposed an intelligent simulation fault warning method for urban centralized heating pipe networks to solve the problems raised in the background technology. Summary of the Invention

[0006] In order to solve the above technical problems, the present invention provides an intelligent simulation fault warning method for urban centralized heating pipeline networks to solve some shortcomings of the intelligent fault warning methods in the existing technology, such as low model accuracy, incomplete data collection, inaccurate fault prediction, etc., which are difficult to meet the heating system's needs for efficient and accurate fault warning.

[0007] The intelligent simulation fault warning method for urban centralized heating pipe networks includes:

[0008] S1. Based on the physical characteristics and operating parameters of the primary heating network segment, a high-precision mathematical simulation model that includes the dynamic behavior of the network segment is constructed;

[0009] S2. Real-time collection of operating data of the primary heating pipe network, including but not limited to temperature, pressure, flow, vibration and external environmental data;

[0010] S3. Input the collected operation data into the simulation model to perform real-time or near real-time dynamic simulation to simulate the actual operation status of the pipe network segment;

[0011] S4. Process the simulation results through data analysis algorithms to identify potential failure modes or abnormal conditions;

[0012] S5. When the predicted fault or abnormal state reaches the preset threshold, the early warning mechanism is automatically triggered, the early warning information is sent to the designated terminal, and a preliminary fault handling guide is provided.

[0013] Preferably, the high-precision mathematical simulation model is constructed using a machine learning algorithm (including a gradient descent algorithm) in combination with physical laws to adaptively optimize model parameters and improve simulation accuracy, wherein the machine learning algorithm uses a gradient descent algorithm to minimize prediction errors;

[0014] The high-precision mathematical simulation model constructed at the same time also combines the energy conservation equation to ensure the accuracy and reliability of the model.

[0015] Preferably, in step S2, a distributed sensor network is used to achieve all-round and multi-dimensional data monitoring of the pipe network segment. The distributed sensor network uses a network data fusion algorithm to perform fusion processing to improve the accuracy and reliability of the data.

[0016] Preferably, in step S4, it also includes introducing an integrated deep learning algorithm (including a neural network) to perform deep mining on the simulation data to improve the accuracy and robustness of fault prediction.

[0017] Preferably, in step S4, an anomaly detection algorithm (including a statistical-based method) is introduced to identify potential failure modes or abnormal conditions.

[0018] Preferably, in step S5, the warning information includes the fault type, expected occurrence time, impact range and recommended emergency treatment measures.

[0019] Preferably, in step S5, when it is predicted that the fault or abnormal state reaches a preset threshold, the threshold in the automatic triggering early warning mechanism is determined by a statistical method (including historical data analysis).

[0020] The intelligent simulation fault warning system for the primary heating pipe network uses the above-mentioned intelligent simulation fault warning method for the urban centralized heating pipe network, including:

[0021] Model building module: Based on the physical characteristics and operating parameters of the primary heating network segment, a high-precision mathematical simulation model that includes the dynamic behavior of the network segment is constructed;

[0022] Data acquisition module: real-time collection of operating data of the primary heating pipe network, including but not limited to temperature, pressure, flow, vibration and external environment data;

[0023] Simulation operation module: inputs the collected operation data into the simulation model to perform real-time or near real-time dynamic simulation to simulate the actual operation status of the pipeline network segment;

[0024] Fault prediction module: processes simulation results through data analysis algorithms to identify potential fault modes or abnormal conditions;

[0025] Early warning release module: When a fault or abnormal state is predicted to reach a preset threshold, the early warning mechanism is automatically triggered, the early warning information is sent to the designated terminal, and a preliminary fault handling guide is provided.

[0026] A processor is configured to execute the above-mentioned intelligent simulation fault warning method for urban centralized heating pipeline network.

[0027] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the above-mentioned intelligent simulation fault warning method for a city centralized heating pipe network.

[0028] Compared with the prior art, the present invention has the following beneficial effects:

[0029] 1. The present invention significantly improves the accuracy of the simulation model by constructing a high-precision mathematical simulation model and using machine learning algorithms combined with physical laws to optimize parameters. It can more realistically simulate the dynamic behavior of the primary heating pipe network segment and provide a reliable basis for fault warning.

[0030] 2. The present invention adopts a distributed sensor network to carry out all-round and multi-dimensional data monitoring, and improves the accuracy and reliability of data through a network data fusion algorithm, effectively solving the problem of incomplete and inaccurate traditional data collection methods, and providing more comprehensive and accurate data support for fault warning.

[0031] 3. The present invention introduces an integrated deep learning algorithm to conduct in-depth mining of simulation data, which improves the accuracy and robustness of fault prediction, can detect potential faults earlier, provides maintenance personnel with more sufficient maintenance time, and reduces the impact of faults on the heating system.

[0032] 4. The present invention automatically triggers the early warning mechanism through a preset threshold, and sends early warning information including the fault type, expected time of occurrence, scope of impact and recommended emergency treatment measures to the designated terminal, thereby realizing the automation and intelligence of fault early warning, improving the timeliness and effectiveness of the early warning, and providing a strong guarantee for the safe and stable operation of the heating system. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 This is a flow chart of the intelligent simulation fault warning method for urban centralized heating pipe networks of the present invention;

[0034] Figure 2 This is a framework diagram of the intelligent simulation fault warning system for the primary heating pipe network section of the present invention. DETAILED DESCRIPTION

[0035] The following embodiments of the present invention are described in further detail with reference to the accompanying drawings and examples. The following examples are used to illustrate the present invention but are not intended to limit the scope of the present invention.

[0036] Embodiment: The present invention provides an intelligent simulation fault warning method for urban centralized heating pipe network, such as Figure 1 As shown, including:

[0037] S1. Based on the physical characteristics and operating parameters of the primary heating network segment, a high-precision mathematical simulation model that includes the dynamic behavior of the network segment is constructed;

[0038] S2. Real-time collection of operating data of the primary heating pipe network, including but not limited to temperature, pressure, flow, vibration and external environmental data;

[0039] S3. Input the collected operation data into the simulation model to perform real-time or near real-time dynamic simulation to simulate the actual operation status of the pipe network segment;

[0040] S4. Process the simulation results through data analysis algorithms to identify potential failure modes or abnormal conditions;

[0041] S5. When the predicted fault or abnormal state reaches the preset threshold, the early warning mechanism is automatically triggered, the early warning information is sent to the designated terminal, and a preliminary fault handling guide is provided.

[0042] From the above, we can see that by constructing a high-precision mathematical simulation model and collecting operating data in real time, using data analysis algorithms to predict faults, and automatically triggering the early warning mechanism when the predicted fault or abnormal state reaches the preset threshold, the automation and intelligence of fault early warning are realized; this method significantly improves the accuracy and timeliness of fault early warning, provides a strong guarantee for the safe and stable operation of the heating system, and effectively solves the problem of low efficiency and difficulty in timely detection of potential faults in traditional fault detection methods.

[0043] Furthermore, the high-precision mathematical simulation model is constructed using a machine learning algorithm (including a gradient descent algorithm) in combination with physical laws to adaptively optimize model parameters and improve simulation accuracy. The machine learning algorithm uses a gradient descent algorithm to minimize prediction errors. The formula of the machine learning algorithm includes:

[0044]

[0045] Among them, θ i is the model parameter of the i-th iteration, η is the learning rate, and L is the loss function;

[0046] The high-precision mathematical simulation model constructed at the same time also combines the energy conservation equation to ensure the accuracy and reliability of the model. The formula of the energy conservation equation includes:

[0047]

[0048] in, is the rate of change of energy in the system, is the energy rate input into the system, is the energy rate of the output system, is the rate of energy lost to the system.

[0049] From the above, we can see that this high-precision mathematical simulation model is constructed using a machine learning algorithm combined with physical laws, and the prediction error is minimized through the gradient descent algorithm, which realizes the adaptive optimization of model parameters and significantly improves the simulation accuracy; at the same time, the energy conservation equation is combined to ensure the accuracy and reliability of the model, further enhancing the credibility of the model; this modeling method can more realistically simulate the dynamic behavior of the primary heating pipe network section, provide a reliable basis for fault warning, and help improve the accuracy and efficiency of fault warning.

[0050] Furthermore, in step S2, a distributed sensor network is used to achieve all-round and multi-dimensional data monitoring of the pipe network segment. The distributed sensor network uses a network data fusion algorithm to perform fusion processing to improve the accuracy and reliability of the data. The formula of the network data fusion algorithm includes:

[0051]

[0052] in, is the fused data, y i is the data of the i-th sensor, w i is the corresponding weight.

[0053] From the above, it can be seen that the present invention adopts a distributed sensor network to realize all-round and multi-dimensional data monitoring of the pipeline segment, and uses a network data fusion algorithm to perform data fusion processing, which significantly improves the accuracy and reliability of the data; this data collection and processing method effectively solves the problem of incomplete and inaccurate traditional data collection methods, provides more comprehensive and accurate data support for fault warning, and further enhances the reliability and accuracy of fault warning.

[0054] Furthermore, the simulation model describes the dynamic behavior of the system by using a state space model and performs state estimation using a Kalman filter algorithm. The formula of the Kalman filter algorithm includes:

[0055]

[0056] in, is the state estimate, A is the state transfer matrix, B is the control matrix, u k is the control input, Kk is the Kalman gain, z k is the observation value, and H is the observation matrix.

[0057] From the above, it can be seen that the present invention uses a state-space model to describe the dynamic behavior of the primary heating pipe network segment, and combines it with the Kalman filter algorithm for state estimation. This method can track the state changes of the system in real time and accurately; the application of the state-space model and the Kalman filter algorithm not only improves the simulation accuracy of the actual operating status of the pipe network segment, but also enhances the ability to predict faults, so that the fault warning system can detect potential faults earlier and provide maintenance personnel with more sufficient maintenance time, thereby reducing the impact of faults on the heating system and improving the stability and safety of the entire system.

[0058] Furthermore, in step S4, an integrated deep learning algorithm (including a neural network) is introduced to perform deep mining on the simulation data to improve the accuracy and robustness of fault prediction. The formula of the deep learning algorithm includes:

[0059] z l =W l ·a l-1 +b l ;

[0060] a l =σ(z l );

[0061] Among them, z l is the weighted input of layer l, W l is the weight matrix of layer l, a l-1 is the output of layer l-1 (also the input of layer l), b l is the bias vector of layer l, and σ is the activation function.

[0062] From the above, we can see that by deeply mining the simulation data, the accuracy and robustness of fault prediction can be significantly improved; the application of this algorithm helps to detect potential faults earlier and provide maintenance personnel with more sufficient repair time, thereby reducing the impact of faults on the heating system and further improving the stability and safety of the entire heating system.

[0063] Furthermore, in step S4, an anomaly detection algorithm (including a statistical-based method) is introduced to identify potential failure modes or abnormal conditions. The formula of the anomaly detection algorithm includes:

[0064]

[0065] Where X is the data point to be detected, μ is the mean of the data, σ is the standard deviation of the data.

[0066] As can be seen from the above, by calculating the deviation between the data point and the data mean to identify potential failure modes or abnormal conditions, the application of this algorithm further enhances the sensitivity and accuracy of the fault warning system; it can effectively filter out abnormal information from a large amount of data, helping maintenance personnel to locate and handle faults in a timely manner, thereby avoiding the expansion of faults and ensuring the normal operation of the heating system.

[0067] Furthermore, in step S5, the warning information includes the fault type, expected occurrence time, impact range and recommended emergency treatment measures.

[0068] Furthermore, in step S5, when the predicted fault or abnormal state reaches a preset threshold, the threshold in the automatic triggering early warning mechanism is determined by a statistical method (including historical data analysis), and the formula of the statistical method includes:

[0069] T′=μ+k·σ;

[0070] Among them, T′ is the warning threshold, μ is the mean of historical data, σ is the standard deviation of historical data, and k is a coefficient (determined based on experience or statistical tests).

[0071] From the above, we can see that by scientifically and rationally determining the warning threshold through statistical methods, the warning mechanism can be triggered more accurately, which not only avoids unnecessary interference caused by false alarms, but also ensures that faults can be discovered and handled in a timely manner; this design greatly improves the practicality and efficiency of fault warnings, and provides a strong guarantee for the safe and stable operation of the heating system.

[0072] Intelligent simulation fault warning system for primary heating pipe network, such as Figure 2 As shown, the above-mentioned urban centralized heating pipe network intelligent simulation fault warning method includes:

[0073] Model building module: Based on the physical characteristics and operating parameters of the primary heating network segment, a high-precision mathematical simulation model that includes the dynamic behavior of the network segment is constructed;

[0074] Data acquisition module: real-time collection of operating data of the primary heating pipe network, including but not limited to temperature, pressure, flow, vibration and external environment data;

[0075] Simulation operation module: inputs the collected operation data into the simulation model to perform real-time or near real-time dynamic simulation to simulate the actual operation status of the pipeline network segment;

[0076] Fault prediction module: processes simulation results through data analysis algorithms to identify potential fault modes or abnormal conditions;

[0077] Early warning release module: When a fault or abnormal state is predicted to reach a preset threshold, the early warning mechanism is automatically triggered, the early warning information is sent to the designated terminal, and a preliminary fault handling guide is provided.

[0078] Furthermore, the results of the intelligent simulation fault warning method for the urban centralized heating pipe network of the embodiment are compared with the current traditional fault detection method (comparative example), and the following table is obtained:

[0079]

[0080]

[0081] As can be seen from the above table, the intelligent simulation fault warning method of the embodiment is superior to the traditional fault detection method in many aspects, especially in terms of timeliness of fault discovery, accuracy of fault prediction, integrity of data collection, data processing efficiency, warning mechanism, detail of warning information, and system stability and security.

[0082] Working principle: A high-precision mathematical simulation model is constructed based on the physical characteristics and operating parameters of the primary heating pipe network segment. The operating data of the pipe network segment is collected in real time and input into the simulation model for dynamic simulation to simulate the actual operating status of the pipe network segment. The simulation results are processed through data analysis algorithms to identify potential failure modes or abnormal conditions. When the predicted failure or abnormal condition reaches the preset threshold scientifically and reasonably determined by statistical methods, the early warning mechanism is automatically triggered and early warning information containing the failure type, expected time of occurrence, scope of impact and recommended emergency treatment measures is sent to the designated terminal, realizing the automation and intelligence of fault early warning.

[0083] The present application provides an electronic device applicable to the above-mentioned intelligent simulation fault warning method for a city centralized heating network, including:

[0084] Memory, used to protect computer programs and data;

[0085] Processor, used to run system programs.

[0086] An embodiment of the present application provides a computer storage medium, which is applicable to the above-mentioned intelligent simulation fault warning method for a city centralized heating pipeline network, and performs hierarchical confidentiality management on the above-mentioned system and data in accordance with confidentiality management requirements.

[0087] Those skilled in the art will appreciate that the embodiments of the present application can be provided as a system or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0088] The present application is described with reference to the flowcharts and / or block diagrams of the devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0089] These computer program instructions may 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, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0090] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0091] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0092] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0093] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology for information storage. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media such as modulated data signals and carrier waves.

[0094] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, commodity, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, commodity, or apparatus comprising the element.

[0095] The embodiments of the present invention are provided for the purpose of illustration and description. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations of the present invention. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. An intelligent simulation fault warning method for urban centralized heating pipe networks, characterized by: include: S1. Based on the physical characteristics and operating parameters of the primary heating network segment, a high-precision mathematical simulation model that includes the dynamic behavior of the network segment is constructed; S2. Real-time collection of operating data of the primary heating pipe network, including but not limited to temperature, pressure, flow, vibration and external environmental data; S3. Input the collected operation data into the simulation model to perform real-time or near real-time dynamic simulation to simulate the actual operation status of the pipe network segment; S4. Process the simulation results through data analysis algorithms to identify potential failure modes or abnormal conditions; S5. When the predicted fault or abnormal state reaches the preset threshold, the early warning mechanism is automatically triggered, the early warning information is sent to the designated terminal, and a preliminary fault handling guide is provided.

2. The urban centralized heating network intelligent simulation fault warning method according to claim 1, characterized in that: The high-precision mathematical simulation model is constructed using a machine learning algorithm combined with physical laws to adaptively optimize model parameters; The high-precision mathematical simulation model constructed at the same time also combines the energy conservation equation to ensure the accuracy and reliability of the model.

3. The intelligent simulation fault warning method for urban centralized heating pipe network according to claim 1, characterized in that: In step S2, a distributed sensor network is used to realize all-round and multi-dimensional data monitoring of the pipe network segment. The distributed sensor network uses a network data fusion algorithm to perform fusion processing.

4. The intelligent simulation fault warning method for urban centralized heating pipe network according to claim 1, characterized in that: In step S4, it also includes introducing an integrated deep learning algorithm to perform deep mining on the simulation data.

5. The intelligent simulation fault warning method for urban centralized heating pipe network according to claim 4, characterized in that: In step S4, an anomaly detection algorithm is introduced to identify potential failure modes or abnormal conditions.

6. The intelligent simulation fault warning method for urban centralized heating pipe network according to claim 1, characterized in that: In step S5, the warning information includes the fault type, expected occurrence time, impact range and recommended emergency treatment measures.

7. The intelligent simulation fault warning method for urban centralized heating pipe network according to claim 6, characterized in that: In step S5, when it is predicted that the fault or abnormal state reaches a preset threshold, the threshold in the automatic triggering early warning mechanism is determined by a statistical method.

8. Intelligent simulation fault warning system for primary heating pipe network, characterized by: The method for intelligent simulation fault warning of a city centralized heating pipe network according to any one of claims 1 to 7 comprises: Model building module: Based on the physical characteristics and operating parameters of the primary heating network segment, a high-precision mathematical simulation model that includes the dynamic behavior of the network segment is constructed; Data acquisition module: real-time collection of operating data of the primary heating pipe network, including but not limited to temperature, pressure, flow, vibration and external environment data; Simulation operation module: inputs the collected operation data into the simulation model to perform real-time or near real-time dynamic simulation to simulate the actual operation status of the pipeline network segment; Fault prediction module: processes simulation results through data analysis algorithms to identify potential fault modes or abnormal conditions; Early warning release module: When a fault or abnormal state is predicted to reach a preset threshold, the early warning mechanism is automatically triggered, the early warning information is sent to the designated terminal, and a preliminary fault handling guide is provided.

9. A processor, characterized in that: It is configured to execute an intelligent simulation fault warning method for a city centralized heating pipe network according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, an intelligent simulation fault warning method for a city centralized heating pipe network as described in any one of claims 1 to 7 is implemented.

Images