Filling pipeline leakage monitoring and positioning method, device and equipment and storage medium

Abstract

The invention provides a filling pipeline leakage monitoring and positioning method, device and equipment and a storage medium, and relates to the technical field of pipeline monitoring. The method comprises the following steps: acquiring time-varying data of pressure in a pipeline through a pressure sensing unit, and identifying leakage triggering characteristics; transmitting a pressure pulse wave at the starting end of the pipeline and receiving an echo signal, and calculating a pressure wave propagation speed under the current working condition according to the echo signal; and the arrival time of the pressure waves arriving at the sensors is extracted, and based on the pressure wave propagation speed and the pressure wave arrival time difference, leakage point coordinates are obtained through calculation. According to the method, the leakage characteristics are rapidly identified through real-time pressure collection, the real-time wave velocity under the current working condition is obtained through the active pulse echo technology, and the wave velocity calculation deviation caused by medium characteristic changes is effectively eliminated; and the actually measured wave velocity and the time difference of arrival are combined for calculation, so that error accumulation in long-distance transportation is overcome, and the precision and reliability of pipeline leakage positioning are remarkably improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of pipeline monitoring, and in particular to a filling pipeline leakage monitoring and positioning method, device, equipment and storage medium. BACKGROUND

[0002] Industrial pipeline transportation systems are widely used in mine filling, petrochemical industry, water conservancy engineering and urban heating fields, and are the main arteries of modern industrial logistics transportation. In particular, in the mine filling process, filling slurry is transported to the underground goaf through long-distance pipelines, which plays a decisive role in maintaining the stability of the mine ground pressure and ensuring safety in production. However, due to the abrasive, corrosive or high-pressure nature of the transported medium, the pipeline is prone to leakage due to wear, aging or external damage during long-term operation. Pipeline leakage not only leads to loss of valuable materials, causes transportation interruption and production stagnation, but also can cause serious environmental pollution accidents, and even endanger the personal safety of on-site personnel. Therefore, developing a technology that can monitor the operating state of the pipeline in real time and sensitively, and quickly and accurately locate the leakage position when leakage occurs, is of great significance to ensuring the intrinsic safety of industrial pipeline transportation systems, reducing operation and maintenance costs, and preventing and resolving major risks.

[0003] In the existing pipeline leakage monitoring technology system, the method based on pressure signal analysis is widely concerned due to its fast response speed and relatively convenient installation and maintenance. In the prior art, specific pressure wave signals generated when leakage occurs are usually used for detection. For example, a related technology discloses a multi-path pipeline network leakage detection method based on negative pressure wave monitoring. This technology mainly focuses on the propagation process of negative pressure waves in a single straight pipeline, and attempts to calculate the propagation time of negative pressure waves, and combines the pressure sensor signals deployed at the key nodes of the pipeline to establish a time delay standard library, so as to realize the positioning of the leakage point. For another example, a mine slurry pipeline leakage position positioning method using negative pressure wave method is also proposed in the prior art. The principle is to analyze the time difference of the negative pressure wave generated at the leakage point instantaneously propagating to the upstream and downstream pump stations, and combine the wave velocity formula to determine the specific position of the leakage point. This kind of technology indeed has the advantages of lower equipment requirement, simple operation logic, etc. when applied in single, short-distance and stable working condition straight pipe sections.

[0004] However, with the increasing complexity and long-distance of industrial conveying networks, the above prior art gradually exposes a series of limitations that are difficult to overcome in actual engineering applications. First, when faced with complex pipe networks with multiple paths, multiple branches or ring structure, the pressure wave generated by the leakage will have complex reflection, refraction and transmission phenomena at the three-way, elbow and reducing, resulting in a large amount of superimposed waves and interference noise in the signal received by the sensor, which directly destroys the accuracy of the positioning algorithm based on the simple straight pipe propagation model. Secondly, for long-distance conveying pipelines, the pressure wave signal will have significant amplitude attenuation and waveform distortion during propagation as the distance increases, resulting in a very low signal-to-noise ratio of the signal captured by the sensor at the far end, and even it is difficult to extract the effective feature signal from the background noise. In addition, the existing technology usually assumes that the propagation speed of the pressure wave is a constant value or only makes a simple correction, but in actual working conditions, the fluid concentration, density, temperature and pressure in the pipeline are real-time fluctuations, which will cause the actual wave speed to change nonlinearly.

[0005] In summary, the existing pipeline leakage monitoring technology has obvious shortcomings in dealing with complex pipe network topology and long-distance dynamic working conditions. Due to the lack of deep analysis capability of signal characteristics in complex wave field environment and adaptive compensation mechanism for changes in working conditions, the existing system often faces problems such as low leakage detection sensitivity, large positioning error (which can reach tens of meters or even hundreds of meters), high false alarm and missed alarm rates. Especially in the early stage of small leakage or in severely disturbed industrial sites, the traditional method of passively capturing pressure wave signals cannot achieve high-precision positioning at the meter level, and cannot meet the urgent needs of modern industry for high reliability and high precision of pipeline safety monitoring. SUMMARY

[0006] The purpose of the present application is to provide a filling pipeline leakage monitoring and positioning method, device, equipment and storage medium, which quickly locks the leakage event through real-time pressure monitoring, and uses the active pulse echo velocity measurement technology to obtain the real wave speed under the current working condition, eliminating the calculation deviation caused by the change of medium characteristics; combined with the measured wave speed and the time difference, the accuracy is calculated, which effectively overcomes the error accumulation in long-distance conveying, and significantly improves the accuracy and reliability of pipeline leakage positioning.

[0007] In order to achieve the above purpose of the present application, the following technical scheme is adopted: In a first aspect, the present application provides a filling pipeline leakage monitoring and positioning method, comprising: acquiring the pressure change data in the pipeline with the pressure sensing unit, and identifying the leakage trigger characteristics; transmitting a pressure pulse wave at the starting end of the pipeline and receiving a return wave signal, and calculating the pressure wave propagation speed under the current working condition according to the return wave signal; The arrival time of the pressure wave to each sensor is extracted, and based on the pressure wave propagation speed and the arrival time difference of the pressure wave, the coordinates of the leakage point are calculated.

[0008] In an optional embodiment, the collecting, by the pressure sensing unit, of the pressure change data in the pipeline over time, and the identifying of the leakage trigger feature, comprises: controlling the pressure sensing unit to collect pressure data in the pipeline, and generating a pressure curve graph of pressure change over time; establishing a pressure basic model of the pipeline based on a pressure wave equation; analyzing the pressure curve graph, and determining that the leakage trigger feature is identified when a pressure drop section appears in the pressure curve graph.

[0009] In an optional embodiment, the establishing of the pressure basic model of the pipeline based on the pressure wave equation comprises: real-time monitoring of the environmental temperature of the pipeline, and correcting the elastic modulus in the pressure wave equation according to a temperature-elasticity coefficient correlation model; the expression of the temperature-elasticity coefficient correlation model is: E=E0[1+α(T-T0)]; wherein E represents the elastic modulus at the real-time monitored temperature T; E0 represents the elastic modulus at the reference temperature; a represents the temperature coefficient; T represents the real-time monitored environmental temperature; and T0 represents the reference temperature.

[0010] In an optional embodiment, the controlling of the pressure sensing unit to collect the pressure data in the pipeline comprises: controlling the pressure sensing unit to collect at a sampling frequency of no less than 10 kHz, so as to capture the transient characteristics of the pressure drop.

[0011] In an optional embodiment, the controlling of the pressure sensing unit to collect the pressure data in the pipeline further comprises: performing signal preprocessing on the collected pressure data; the signal preprocessing comprises: performing 100 times to 500 times signal amplification processing on the collected pressure data; and / or, performing filtering processing on the pressure data by using a low-pass filtering module with a cutoff frequency of 500 Hz.

[0012] In an optional embodiment, the emitting of the pressure pulse wave at the starting end of the pipeline and the receiving of the echo signal, and the calculating of the pressure wave propagation speed under the current working condition according to the echo signal, comprises: emitting at least two groups of pressure pulse waves with different frequencies at the starting end of the pipeline, and the duration of each group of pressure pulse waves is 0.5 ms to 2.0 ms; performing fast Fourier transform on the received echo signal, and converting the echo signal into a frequency domain signal; identify a first feature point corresponding to a first peak value and a second feature point corresponding to a second peak value in the frequency domain signal, and calculate a time difference between the first feature point and the second feature point; calculate a pressure wave propagation speed under a current working condition according to the time difference.

[0013] In an optional implementation, after the pressure wave propagation speed under the current working condition is calculated according to the time difference, the method further includes: obtain real-time fluid concentration and temperature data in the pipeline; fine-tune the calculated pressure wave propagation speed based on the real-time fluid concentration and the temperature data by using an AI parameter adjustment module; wherein the AI parameter adjustment module is trained based on historical leakage data under different working conditions by using a random forest-LSTM hybrid algorithm.

[0014] In an optional implementation, after the received echo signal is converted into a frequency domain signal by using a fast Fourier transform, the method further includes: perform a smoothing filter processing on the converted frequency domain signal to eliminate pseudo-peak values in the frequency domain signal.

[0015] In an optional implementation, the calculation of the time difference between the first feature point and the second feature point includes: obtain a sampling period of the pressure sensing unit; calculate the time difference based on the following formula: ; wherein Δt represents the time difference; k1 represents a sampling point serial number corresponding to the first feature point; k2 represents a sampling point serial number corresponding to the second feature point; and T represents the sampling period of the pressure sensing unit.

[0016] In an optional implementation, the calculation expression of the pressure wave propagation speed is: ; wherein V represents the pressure wave propagation speed; and Δt represents the time difference.

[0017] In an optional implementation, after the pressure pulse wave is emitted at the starting end of the pipeline and the echo signal is received, the method further includes: verify that the echo signal satisfies the following condition: ; wherein S(t) represents the echo signal; P represents a pulse intensity; R(t) represents an original echo; a represents an attenuation factor; and n represents a number of time points.

[0018] ​In an optional implementation, after calculating the coordinates of the leak point, the method further includes: Repeat the steps of collecting pressure change data in the pipeline over time through the pressure sensing unit, calculating the pressure wave propagation speed under the current operating conditions, and calculating the coordinates of the leak point until multiple sets of parallel leak point coordinates are obtained. Calculate the deviation between multiple sets of leak point coordinates; Determine whether the deviation value is not greater than a first preset deviation threshold; If so, the average value of the multiple sets of leak point coordinates or any one set of coordinates will be determined as the final leak point location; If not, the peak recognition threshold is adjusted using the AI ​​parameter adjustment module, and the leak point coordinates are recalculated using the adjusted peak recognition threshold until the deviation value meets the first preset deviation threshold.

[0019] In an optional implementation, after calculating the deviation values ​​between multiple sets of leak point coordinates, the method further includes: Determine whether the deviation value is greater than a second preset deviation threshold; wherein the second preset deviation threshold is greater than the first preset deviation threshold; If so, then initiate redundant sensor data verification; retrieve historical data from at least three pressure sensors around the leak point, and determine the leak location range through spatiotemporal correlation analysis.

[0020] In an optional embodiment, the method for monitoring and locating leaks in the filling pipeline further includes: Based on the pressure data collected by the pressure sensing unit, the leakage orifice diameter and leakage amount are calculated. When the leakage orifice diameter is ≥20mm, or the leakage amount is ≥1m 3 / hour, triggering a high-risk warning and controlling the pipeline valve to shut off or shut off within the first preset time; When 20mm > the leakage orifice diameter ≥ 5mm, or 1m 3 / hour > Leakage amount ≥ 0.1m 3 / hour, triggering a medium-risk warning and controlling the pipeline valve to shut off or shut off within a second preset time; wherein, the first preset time is not greater than the second preset time; A low-risk warning is triggered when the leakage orifice diameter is less than 5 mm or the leakage rate is less than 0.1 m³ / hour.

[0021] Secondly, the present invention provides a device for monitoring and locating leaks in filling pipelines, comprising: The data identification module is used to collect data on the pressure change in the pipeline over time through the pressure sensing unit and to identify leakage triggering characteristics. The velocity calculation module is used to transmit pressure pulse waves at the beginning of the pipeline and receive echo signals, and calculate the pressure wave propagation velocity under the current operating conditions based on the echo signals. The coordinate calculation module is used to extract the arrival time of the pressure wave to each sensor, and calculate the coordinates of the leak point based on the propagation speed of the pressure wave and the time difference of the pressure wave arrival.

[0022] Thirdly, the present invention provides a computer device, the computer device including a processor and a memory, the memory storing a computer program, and the processor executing the computer program to implement the filling pipeline leakage monitoring and location method described in any of the foregoing embodiments.

[0023] Fourthly, the present invention provides a leak monitoring and location system for filling pipelines, comprising: A high-precision pressure sensing unit is used to be installed on the filling pipeline to collect data on the pressure change in the pipeline over time. A pressure pulse transmitting device is installed at the beginning of the filling pipe to transmit pressure pulse waves into the pipe; A data acquisition unit, connected to the high-precision pressure sensing unit, is used to receive and process the pressure change data over time. The display and early warning unit is used to display monitoring results and issue early warnings. The main control and analysis unit is connected to the pressure pulse transmitter, the data acquisition unit, and the display and warning unit, respectively. The main control analysis unit is used to execute the filling pipeline leakage monitoring and location method as described in any of the foregoing embodiments.

[0024] Fifthly, the present invention provides a computer storage medium storing a computer program, which, when executed on a processor, implements the filling pipeline leakage monitoring and location method according to any one of the foregoing embodiments.

[0025] This application provides a method, apparatus, equipment, and storage medium for monitoring and locating leaks in filled pipelines. The method for monitoring and locating leaks in filled pipelines uses a pressure sensing unit to collect pressure change data within the pipeline in real time, enabling timely detection of leak triggering characteristics such as sudden pressure drops, thereby quickly initiating the monitoring process and ensuring timely response to leak events.

[0026] Unlike traditional methods that rely on theoretical models or historical experience to determine wave velocity, this method actively emits pressure pulse waves at the beginning of the pipeline and calculates the current pressure wave propagation speed by analyzing the echo signals. This active detection mechanism can obtain the true wave velocity that reflects the actual state of the fluid in the pipeline, effectively avoiding the problem of wave velocity parameters not matching reality due to dynamic changes in the characteristics of the transported medium (such as concentration and temperature).

[0027] Furthermore, by utilizing the measured pressure wave propagation speed, which conforms to the current operating conditions, and combining it with the precise time difference of the pressure wave arrival at each sensor, the accuracy of the leak point coordinate calculation is significantly improved. This processing method fundamentally eliminates the positioning error accumulated due to the deviation in wave velocity values ​​during long-distance transportation, thereby achieving high-precision positioning of the leak location in the filling pipeline. Attached Figure Description

[0028] To more clearly illustrate the technical solutions of this application, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of this application and therefore should not be considered as a limitation on the scope of protection of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0029] Figure 1 This is a schematic diagram of the hardware operating environment involved in an embodiment of the leak monitoring and location method for filling pipelines of the present invention; Figure 2 This is a schematic flowchart of Embodiment 1 of the method for monitoring and locating leaks in filled pipelines according to the present invention; Figure 3 This is a detailed flowchart of step S100 in Embodiment 2 of the filling pipeline leakage monitoring and location method of the present invention; Figure 4 This is a detailed flowchart of step S200 in Embodiment 3 of the filling pipeline leakage monitoring and location method of the present invention; Figure 5 A schematic diagram illustrating the signal transformation concept before and after FFT algorithm processing in Example 3 of the invention's method for monitoring and locating leaks in filled pipelines; Figure 6 This is a flowchart illustrating the supplementary steps following step S300 in Embodiment 4 of the filling pipeline leakage monitoring and location method of the present invention. Figure 7 This is a flowchart illustrating a supplementary scheme in Embodiment 5 of the method for monitoring and locating leaks in filled pipelines according to the present invention. Figure 8 This is a schematic diagram of the module connection of the filling pipeline leakage monitoring and positioning device of the present invention. Detailed Implementation

[0030] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0031] The components of the embodiments of this application described and illustrated in the accompanying drawings can be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of this application provided in the drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0032] In the following, the terms “comprising,” “having,” and their cognates, which may be used in various embodiments of this application, are intended only to indicate a particular feature, number, step, operation, element, component, or combination thereof, and should not be construed as excluding, firstly, the presence of one or more other features, numbers, steps, operations, elements, components, or combinations thereof, or adding the possibility of one or more features, numbers, steps, operations, elements, components, or combinations thereof.

[0033] Furthermore, the terms "first," "second," and "third" are used only to distinguish descriptions and should not be interpreted as indicating or implying relative importance.

[0034] Unless otherwise specified, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which the various embodiments of this application pertain. Terms (such as those defined in commonly used dictionaries) shall be interpreted as having the same meaning as in their contextual meaning in the relevant technical field and shall not be construed as having an idealized or overly formal meaning, unless clearly defined in the various embodiments of this application.

[0035] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0036] like Figure 1 The diagram shown is a structural schematic of the hardware operating environment of the terminal involved in an embodiment of the present invention.

[0037] The filling pipeline leak monitoring and location system of this invention can be a PC, or a mobile terminal device such as a smartphone, tablet, or laptop. The system may include: a processor 1001 (e.g., a CPU), a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. The communication bus 1002 is used to establish communication between these components. The user interface 1003 may include a display screen, an input unit such as a keyboard, or a remote control; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be a high-speed RAM memory or a stable memory, such as a disk storage device. Optionally, the memory 1005 may also be a storage device independent of the processor 1001. Optionally, the filling pipeline leak monitoring and location system may also include RF (Radio Frequency) circuitry, audio circuitry, a Wi-Fi module, etc. In addition, the filling pipeline leakage monitoring and location system can also be equipped with other sensors such as gyroscopes, barometers, hygrometers, thermometers, and infrared sensors, which will not be elaborated here.

[0038] Those skilled in the art will understand that Figure 1 The filling pipe leak monitoring and location system shown is not intended to limit the system and may include more or fewer components than illustrated, or combine certain components, or have different component arrangements. Figure 1 As shown, the memory 1005, which is a computer-readable storage medium, may include an operating system, a data interface control program, a network connection program, and a filling pipeline leak monitoring and location program.

[0039] Example 1 Reference Figure 2 This embodiment provides a method for monitoring and locating leaks in filling pipelines, including: Step S100: Collect data on the pressure change in the pipeline over time using a pressure sensing unit to identify leakage triggering characteristics.

[0040] This step involves using pressure sensing units (such as sensors) deployed on the pipeline to continuously monitor the pressure inside the pipeline, record the trend of pressure value changes over time, and filter out specific signal features that can indicate the occurrence of a leak.

[0041] Specifically, the pressure sensing unit first converts the physical pressure signal within the pipeline into an electrical signal and acquires it. To capture instantaneous changes, the acquisition typically requires a certain frequency (for example, the manual mentions a sampling frequency of 10kHz and a sampling period of 0.1ms). Then, the system performs real-time analysis on the acquired continuous pressure-time curve, searching for abnormal fluctuations to obtain a pressure data stream containing timestamps. Upon identifying a specific abnormal waveform, it determines that a "suspected leak event has occurred," thereby triggering subsequent detection procedures.

[0042] This step enables real-time, 24 / 7 monitoring of the pipeline status, allowing for rapid detection of anomalies and providing trigger signals for subsequent precise positioning, thus avoiding invalid calculations when there are no leaks.

[0043] For example, in terms of hardware, a bidirectional precision digital pressure sensor is used to collect data, and the data is preprocessed through a signal amplification module (e.g., amplification of 100-500 times) and a filtering module (e.g., low-pass filtering). Algorithmically, a monitoring model or threshold is set. For instance, the system can identify a "sudden pressure drop" as a leakage trigger characteristic. When the monitored pressure curve shows a significant drop within a very short time (the slope exceeds the set threshold), it is determined that a leakage trigger characteristic has been identified.

[0044] Step S200: A pressure pulse wave is emitted at the beginning of the pipeline and the echo signal is received. The pressure wave propagation speed under the current operating condition is calculated based on the echo signal.

[0045] This step is an "active detection" process.

[0046] The system does not rely on theoretically estimated wave speeds. Instead, when a leak is suspected (or periodic detection occurs), it actively generates a pressure pulse at the beginning of the pipeline. By analyzing the signal of this pulse propagating in the pipeline and being reflected back, the system can measure the pressure wave propagation speed under the current pipeline environment.

[0047] Its processing may include: (1) Control the transmitting device to generate a pressure pulse at the starting point of the pipeline (for example, multiple sets of pulse waves with different frequencies such as 100Hz, 200Hz, and 300Hz, with a duration of 0.5-2ms can be emitted).

[0048] (2) The receiving device records the echo signal inside the pipe.

[0049] (3) Analyze the time relationship between the transmitted wave and the echo (or a specific peak in the echo), and calculate the velocity by combining the known distance or time difference of the characteristic point.

[0050] Through the above process, a specific numerical value is obtained, representing the actual propagation speed of the pressure wave at the current moment and under the current operating conditions (temperature, concentration, etc.).

[0051] It should be noted that the concentration and temperature of the fluid inside the pipeline change in real time, causing a deviation between the theoretical and actual wave velocity. The wave velocity V obtained through "actual measurement" can dynamically adapt to changes in operating conditions, eliminating positioning errors caused by incorrect wave velocity estimation.

[0052] Step S300: Extract the arrival time of the pressure wave to each sensor, and calculate the coordinates of the leak point based on the propagation speed of the pressure wave and the time difference of arrival of the pressure wave.

[0053] This step utilizes the previously calculated precise wave velocity V, combined with the time difference between the pressure wave generated by the leak and its transmission to different sensors, to determine the specific location of the leak point through mathematical and geometric calculations.

[0054] Specific data processing procedures may include, for example, the following: First, accurately extract the time (i.e., arrival time) of the pressure wave generated by the leak from the data collected by each sensor; then calculate the time difference between the pressure wave arriving at the upstream sensor and the downstream sensor (or any two sensors); substitute the "measured wave velocity V" and the "arrival time difference" into the positioning formula to calculate the specific location coordinates of the leak point on the pipeline (e.g., the distance Lx from the starting point of the pipeline).

[0055] This step incorporates the positioning calculation based on "measured wave velocity," which can significantly improve positioning accuracy and achieve meter-level positioning (e.g., accuracy ±1m).

[0056] In summary, this method for monitoring and locating leaks in filled pipelines quickly identifies leak characteristics by monitoring pipeline pressure changes in real time; it utilizes actively emitted pressure pulse waves to obtain the measured wave velocity under the current operating conditions, effectively avoiding wave velocity calculation deviations caused by changes in fluid characteristics (such as concentration and temperature); and it combines the measured wave velocity with the arrival time difference for joint calculation, eliminating error accumulation during long-distance transportation and significantly improving the accuracy and reliability of pipeline leak location.

[0057] Example 2 Reference Figure 3 Based on the foregoing embodiments, this embodiment provides a method for monitoring and locating leaks in filled pipelines. Step S100 involves collecting pressure change data within the pipeline over time using a pressure sensing unit to identify leak triggering characteristics, including: Step S110: Control the pressure sensing unit to collect pressure data in the pipeline and generate a pressure curve graph showing the change of pressure over time.

[0058] The backplane step refers to the system's continuous, real-time digital recording of the pressure state inside the pipeline. By controlling the pressure sensing unit, the physical pressure signal of the fluid inside the pipeline is converted into an electrical signal and arranged in a time series to form a visualized or algorithm-processable dataset.

[0059] The processing can be described as follows: the system controls a high-precision pressure sensing unit (such as a bidirectional precision digital pressure sensor) to sample the pressure inside the pipeline at a preset frequency. Each pressure point collected corresponds to the current sampling time, thereby constructing a two-dimensional "pressure-time" relationship data, i.e., generating a pressure curve, and finally generating a time series data or graph (pressure curve) reflecting the real-time pressure fluctuations inside the pipeline. This curve records the dynamic change trajectory of pressure over time.

[0060] This step provides continuous monitoring data, which can capture the instantaneous characteristics of pipeline pressure changes, providing the original data foundation for subsequent feature identification and ensuring the real-time and continuous nature of monitoring.

[0061] Further, step S110, controlling the pressure sensing unit to collect pressure data within the pipeline, includes: Step S111: Control the pressure sensing unit to collect data at a sampling frequency of not less than 10kHz in order to capture the instantaneous characteristics of a sudden drop in pressure.

[0062] This step specifies the time resolution standard for data acquisition. Specifically, the system instructs the pressure sensing unit (or its connected data acquisition unit) to read the pressure values ​​within the pipeline at extremely high speeds, ensuring at least 10,000 data points are collected per second.

[0063] In this step, during the data acquisition phase, the frequency of the analog-to-digital converter (ADC) or sensor readout is set to 10kHz. This means the time interval (sampling period) between two adjacent pressure data points. The time intervals are controlled to no more than 0.1 milliseconds (ms), thereby obtaining a high-density data stream of pressure changing over time.

[0064] In this data stream, the details of pressure changes are magnified, with extremely high resolution on the time axis.

[0065] It should be noted that when a pipeline leak occurs, the pressure often changes drastically in a very short instant (pressure drop). If the sampling frequency is too low, this sudden and abrupt change may be missed, resulting in unclear or unidentifiable characteristics. High-frequency sampling of at least 10kHz ensures that the instantaneous waveform characteristics of the pressure drop are captured completely and clearly, thus providing a reliable basis for leak detection.

[0066] Specifically, for example, the sampling clock of the data acquisition card or sensor can be configured to be set to 10kHz or higher. For example, the sampling period can be set. =0.1ms.

[0067] Furthermore, step S110, controlling the pressure sensing unit to collect pressure data within the pipeline, further includes: Step S112: Perform signal preprocessing on the collected pressure data.

[0068] The signal preprocessing includes: amplifying the collected pressure data by 100 to 500 times; and / or filtering the pressure data using a low-pass filter module with a cutoff frequency of 500 Hz.

[0069] This step involves amplifying the gain of the raw, weak electrical signal output by the sensor. Since pressure wave signals in long-distance pipelines can be very weak and difficult to identify directly, their amplitude needs to be amplified.

[0070] In the above method, the signal amplification module in the data acquisition unit is used to linearly amplify the voltage or current amplitude of the received pressure sensor analog signal by 100 to 500 times (for example, it can be 100 times, 200 times, 300 times, 400 times, 500 times, etc.), thereby outputting an analog or digital signal with a more obvious characteristic and amplitude within the processable range (such as suitable for the ADC input range).

[0071] This step significantly improves the signal strength, enabling pressure fluctuation signals that were originally submerged in the background or too weak to be effectively identified and processed by the back-end main control analysis unit, thereby enhancing the system's sensitivity to detecting minute leak signals.

[0072] Specifically, an operational amplifier circuit or an integrated instrumentation amplifier module can be used, and its gain resistor can be adjusted to keep the gain coefficient between 100 and 500.

[0073] The pressure data is filtered using a low-pass filter module with a cutoff frequency of 500Hz, which is a signal denoising process. Through a frequency selection mechanism, it retains the effective low-frequency pressure wave signal while eliminating useless high-frequency interference noise.

[0074] In this step, the signal passes through a low-pass filter (which can be a hardware circuit or a digital filtering algorithm) with a "threshold" (cutoff frequency) set at 500Hz. Signal components with frequencies higher than 500Hz (usually electromagnetic interference, environmental noise, etc.) are significantly attenuated or filtered out, while signal components with frequencies lower than 500Hz (including valid pressure wave signals, such as 100Hz, 200Hz, and 300Hz pulse waves) are allowed to pass.

[0075] This step yields a clean, smooth pressure signal, where stray high-frequency spikes and noise have been removed.

[0076] This step eliminates the interference of high-frequency noise on subsequent feature identification (such as finding peaks), prevents false triggering of leakage alarms due to noise, and ensures the purity of the signal when performing frequency-based analysis (such as FFT), thereby improving the accuracy of monitoring.

[0077] Specifically, in terms of hardware, an RC low-pass filter circuit or an active filter can be used before A / D conversion, with the cutoff frequency parameter set to 500Hz; while in terms of software, a digital low-pass filter algorithm can be applied to the acquired digital signal to filter out frequency bands above 500Hz.

[0078] Step S120: Establish a basic pressure model for the pipeline based on the pressure fluctuation equation.

[0079] This step involves using the principles of pressure wave propagation in fluid mechanics to construct a mathematical model that describes the normal propagation of pressure waves within a pipeline or their propagation under specific operating conditions. This model serves as a "benchmark" or "reference frame" for subsequent analysis.

[0080] Specifically, this can be achieved by using the pressure wave propagation path analysis software in the main control analysis unit, based on the pressure wave equation in physics, and combining the geometric parameters of the pipeline (such as pipe diameter and length) and fluid characteristics, to establish a simulation model or basic calculation model that can simulate or describe the behavior of pressure waves in the pipeline.

[0081] Through the above processing, a pressure-based model of the pipeline can be obtained. This model can reflect the propagation laws and characteristics that pressure waves should follow under the current physical conditions of the pipeline.

[0082] This step provides a theoretical basis for identifying abnormal signals by establishing a model based on physical principles (wave equations). Compared to simple data statistics, models based on physical equations can more realistically reflect the fluid dynamics characteristics within the pipeline, helping to distinguish between noise and real physical fluctuations.

[0083] Furthermore, step S120, establishing a basic pressure model for the pipeline based on the pressure fluctuation equation, includes: Step S121: Monitor the ambient temperature of the pipeline in real time, and correct the elastic modulus in the pressure fluctuation equation according to the temperature-elastic coefficient correlation model; the expression of the temperature-elastic coefficient correlation model (Formula 1) is: E = E0[1 + α(T - T0)]; Where E represents the elastic modulus at the real-time monitored temperature T; E0 represents the elastic modulus at the reference temperature; α represents the temperature coefficient; T represents the real-time monitored ambient temperature; and T0 represents the reference temperature.

[0084] This step refers to continuously and in real-time acquiring temperature data of the pipeline's environment during the monitoring process. Its purpose is to capture the dynamic impact of environmental factors on the pipeline's physical properties (especially material elasticity).

[0085] The temperature around the pipeline or on its walls is continuously sampled using temperature monitoring equipment (such as the temperature compensation module or thermocouple mentioned in the technical disclosure). The processing involves converting the physical temperature signal into a digital signal T that can be read by the system. This step obtains the real-time ambient temperature value T, which reflects the current thermodynamic state of the pipeline.

[0086] The physical properties of pipe materials (such as steel and composite materials) drift with temperature changes. Real-time temperature monitoring can provide accurate input parameters for subsequent model corrections, avoiding model errors caused by ignoring the effects of temperature, thereby improving the environmental adaptability of the monitoring system.

[0087] Specifically, temperature sensors (such as thermocouples and resistance temperature detectors) can be installed along the pipeline or at key nodes (such as sensor installation sites). Data acquisition: The data acquisition unit reads the temperature sensor values ​​and timestamps them to synchronize them with the pressure data.

[0088] Then, the elastic modulus in the pressure fluctuation equation is corrected according to the temperature-elasticity coefficient correlation model. This step refers to using a specific mathematical relationship to dynamically adjust the parameter representing the "hardness" of the pipe material in the pressure fluctuation equation: the elastic modulus (E).

[0089] Specifically, the system reads preset benchmark parameters (benchmark temperature, benchmark elastic modulus, temperature coefficient) and real-time temperature T, substitutes these data into the temperature-elastic coefficient correlation model for calculation, and thus calculates an elastic modulus value E that is temperature-corrected and conforms to the current actual operating conditions. This E value will be used to update the pipeline's pressure baseline model.

[0090] The elastic modulus E is a key parameter affecting the propagation characteristics of pressure waves (it directly affects the propagation speed and waveform characteristics of pressure waves in pipelines). By dynamically correcting the value of E, the accuracy of the pressure fluctuation equation in describing the actual physical process can be significantly improved, thereby eliminating calculation deviations caused by temperature changes and improving the accuracy of the final leak location.

[0091] Specifically, for example, a calculation module can be pre-configured in the software of the main control analysis unit, which triggers an update calculation of the E value every time new temperature data T is acquired.

[0092] Step S130: Analyze the pressure curve. When a sudden drop in pressure is detected in the pressure curve, it is determined that a leakage trigger feature has been detected.

[0093] This step involves comparing the collected real-time data with preset fault characteristics. The system aims to filter out specific waveform characteristics—namely, a sudden drop in pressure—that clearly indicate a "leakage has occurred" from continuous pressure fluctuations.

[0094] Specifically, the system can first perform real-time analysis algorithms on the pressure curve generated in step S110 to monitor the rate or amount of change in pressure amplitude. When a significant drop in pressure value is detected within a very short period of time (forming a "pressure drop segment"), the system logic determines that this phenomenon conforms to the physical characteristics of a leak.

[0095] Through the above steps, a judgment result can be output: "Leakage triggering feature" has been identified. This is usually used as a trigger signal to initiate subsequent more complex wave velocity detection and location processes.

[0096] In this step, "sudden pressure drop" is the most direct and typical physical phenomenon of pipeline leakage. Using it as a trigger feature can effectively filter out normal minor pressure fluctuations or slow drifts, ensuring that subsequent high-precision positioning calculations are only initiated when a real leak is likely to occur, saving system resources and reducing false alarms.

[0097] Example 3 Reference Figure 4 Based on the foregoing embodiments, this embodiment provides a method for monitoring and locating leaks in filled pipelines. Step S200 involves transmitting a pressure pulse wave at the beginning of the pipeline and receiving the echo signal, then calculating the pressure wave propagation speed under the current operating conditions based on the echo signal. This includes: In step S210, at least two sets of pressure pulse waves of different frequencies are emitted at the beginning of the pipeline, and the duration of each pressure pulse wave is 0.5ms to 2.0ms. For example, the duration can be 0.5ms, 0.6ms, 0.7ms, 0.8ms, 0.9ms, 1.0ms, 1.5ms, 2.0ms, etc.

[0098] This step involves actively generating the detection signal. Instead of passively waiting for a leak signal, the system actively inputs a specific detection wave source into the pipeline, utilizing the signal characteristics of different frequencies to detect the pipeline's transmission characteristics.

[0099] Specifically, a pressure pulse transmitter can be used to continuously or intermittently transmit multiple sets of pressure pulse signals with different frequencies at the starting point of the pipeline. For example, three sets of pulse waves with frequencies of 100Hz, 200Hz, and 300Hz can be transmitted. At the same time, the duration of each set of pulse waves is strictly controlled between 0.5ms and 2ms.

[0100] It should be noted that in complex multi-branch pipe networks, single-frequency signals are prone to aliasing or attenuation. Transmitting pulse waves of different frequencies, with specific durations (0.5ms~2ms), can ensure that the signal produces identifiable superimposed peaks in multi-branch pipes, thereby improving signal identification in complex pipe network environments; short pulses of specific duration help maintain waveform characteristics during long-distance transmission, facilitating subsequent echo capture.

[0101] Step S220: Perform a fast Fourier transform on the received echo signal to convert it into a frequency domain signal.

[0102] This step is a signal domain conversion step. The continuously acquired pressure echo signal in the time domain is converted into a signal in the frequency domain (or transform domain) to facilitate noise separation and feature extraction. What processing is performed: After the receiving device acquires the echo signal S(t) from inside the pipe, the processor applies a Fast Fourier Transform (FFT) algorithm to it, thereby converting the original "pressure-time" signal S(t) into a "amplitude-frequency / sequence" frequency domain signal.

[0103] By using FFT transformation, the characteristics of periodic pulse signals submerged in time-domain noise can be highlighted in the frequency domain, making it easier to accurately identify specific echo peaks generated by the transmitted pulse and laying the foundation for high-precision time difference calculation.

[0104] like Figure 5 The figure shows a conceptual diagram of the signal conversion using the FFT algorithm in this embodiment. As shown in the coordinate system on the left, the original echo signal acquired by the receiving device is represented as a time-domain waveform (Amplitude-Time). Due to reflection, superposition, and noise interference within the pipe, this time-domain waveform often exhibits a complex wave pattern, making it difficult to directly identify the specific characteristics generated by the transmitted pulse.

[0105] As shown by the arrows and the coordinate system on the right, the time-domain signal is converted into a frequency-domain signal by performing a Fast Fourier Transform (FFT). In the frequency domain, the original signal is decomposed into amplitude distributions of different frequency components. It can be seen that the transformed frequency-domain signal exhibits clear spectral peaks. These peaks correspond to specific frequencies emitted by the transmitting device (e.g., 100Hz, 200Hz, or 300Hz as mentioned above), thus highlighting the effective signal characteristics that are submerged in time-domain noise.

[0106] As shown in the figure, through this time-frequency domain conversion, the system can accurately identify the frequency bands with concentrated energy in the spectrum, and thus accurately locate the first feature point corresponding to the first peak and the second feature point corresponding to the second peak, providing a reliable data foundation for subsequent high-precision time difference calculation.

[0107] Step S230: Identify the first feature point corresponding to the first peak and the second feature point corresponding to the second peak in the frequency domain signal, and calculate the time difference between the first feature point and the second feature point.

[0108] This step is the key feature extraction step. It involves identifying key markers (feature points) in the transformed signal that represent the arrival or reflection of echoes, and quantizing the time intervals between them.

[0109] First, peak identification can be performed, that is, scanning the point with the largest amplitude in the transformed signal to identify the position index corresponding to the first peak (denoted as the first feature point, such as k1) and the position index corresponding to the second peak (denoted as the second feature point, such as k2); then the time difference is calculated by combining the index difference of the feature points with the sampling parameters.

[0110] Further, step S230, calculating the time difference between the first feature point and the second feature point, includes: Step S231: Obtain the sampling period of the pressure sensing unit.

[0111] This step refers to the system reading or confirming the time interval between two adjacent data points when the pressure sensing unit (or the data acquisition device connected to it) collects pressure data. This is a key parameter for converting digitized discrete data points into a real physical time reference.

[0112] The system reads the sampling period value (denoted as ) from preset configuration parameters, hardware registers, or initialization settings. For example, if the system is set to collect data at a fixed frequency, this step is to obtain the time value of the reciprocal of that frequency, thereby obtaining a specific time value (e.g., 0.1ms or 0.0001s), representing the duration of each data point.

[0113] This step establishes the benchmark for time quantization. Since computers process discrete digital sequences (point 1, point 2, etc.), only by obtaining the sampling period can these sequence numbers be converted into physically meaningful time values, providing the necessary prerequisites for subsequent calculations.

[0114] Specifically, during the software initialization phase, the sampling rate setting stored in the system configuration file can be read and its reciprocal can be calculated as the sampling period; or the clock setting parameters of the analog-to-digital converter (ADC) can be read directly.

[0115] Step S232, calculate the time difference based on the following formula (Formula 2): ; Where Δt represents the time difference; k1 represents the sampling point number corresponding to the first feature point; k2 represents the sampling point number corresponding to the second feature point (i.e., which data point), and the absolute difference between the two represents how many sampling points are between the two peaks. The sampling period of the pressure sensing unit is represented by "the length of time represented by each sampling point".

[0116] The above The location difference is represented by the principle that time difference = (interval between sampling points) × (time for each sampling point).

[0117] This calculation method is based directly on the index of the underlying raw data, avoiding measurement errors in analog signal processing and maximizing the utilization of the system's sampling accuracy. This method only involves subtraction and multiplication operations, and the calculation speed is extremely fast, making it suitable for real-time processing in industrial settings.

[0118] For example, assuming the sampling period =0.1ms. Analysis identified the first peak at the 100th data point (k1=100) and the second peak at the 600th data point (k2=600). The calculation process is: |600-100|×0.1ms=500×0.1ms=50ms. The final time difference Δt is 50ms.

[0119] Step S240: Calculate the pressure wave propagation speed under the current operating condition based on the time difference.

[0120] This step is the final step in calculating the wave velocity. Using the measured time difference information, the wave velocity under the current fluid environment is inferred.

[0121] In this step, the time difference Δt calculated above is substituted into the preset wave velocity calculation model for solution.

[0122] Furthermore, the calculation expression for the pressure wave propagation speed (Formula 3) is as follows: ; Where V represents the propagation speed of the pressure wave; Δt represents the time difference.

[0123] Its specific calculation logic is to convert the time difference into a velocity value through Formula 3 or other correlation formulas based on physical models, thereby obtaining the pressure wave propagation velocity V under the current working condition.

[0124] In this step, the velocity V is calculated based on the current real-time echo signal, thus naturally including and reflecting the influence of environmental factors such as the current fluid concentration and temperature within the pipeline. Compared to using a theoretical wave velocity with a fixed constant, this measured wave velocity can greatly reduce the positioning error caused by fluctuations in operating conditions (such as concentration changes), ensuring the accuracy of subsequent leak point calculations.

[0125] Furthermore, after calculating the pressure wave propagation speed under the current operating condition based on the time difference, step S240 further includes: Step S250: Obtain real-time fluid concentration and temperature data within the pipeline.

[0126] This step refers to the system reading two key environmental variables that affect the propagation characteristics of pressure waves in real time: fluid concentration and temperature. This is to perceive the current physical environment state inside the pipeline.

[0127] In terms of data processing, the system reads real-time fluid concentration values ​​(such as slurry concentration) and fluid temperature values ​​through sensor interfaces or data acquisition units connected to the pipeline, thereby obtaining two specific operating parameter values: the current fluid concentration C and temperature T.

[0128] It should be noted that the propagation speed of pressure waves varies in media with different concentrations and temperatures. Acquiring this real-time data provides the necessary input features for subsequent correction of the wave velocity using AI models, ensuring that the correction process is based on "real-world conditions" rather than "hypothetical conditions."

[0129] Specifically, data can be collected by concentration meters and temperature sensors (or reused temperature monitoring devices) deployed on pipelines and transmitted to the main control and analysis unit.

[0130] Step S260: The AI ​​parameter adjustment module is used to fine-tune the calculated pressure wave propagation speed based on the real-time fluid concentration and temperature data; wherein, the AI ​​parameter adjustment module adopts a random forest-LSTM hybrid algorithm, which is trained based on historical leakage data containing different operating conditions.

[0131] This step is an intelligent, high-precision correction step. It utilizes artificial intelligence algorithms to calibrate the wave velocity, which was roughly calculated through physical measurements in the previous steps, based on the current operating conditions (concentration, temperature) to eliminate nonlinear errors.

[0132] The "initial pressure wave propagation velocity" calculated in the preceding steps, along with the acquired "fluid concentration" and "temperature," are used as input data and fed into a pre-trained AI parameter adjustment module. This module calculates correction coefficients based on its internal model weights or directly outputs the corrected wave velocity value, thus obtaining a finely tuned, high-precision pressure wave propagation velocity V'. This fine-tuning ensures extremely low calculation errors (e.g., 2% or even 1%).

[0133] Although the wave velocity was calculated using measured time differences in the aforementioned steps, the complex fluid conditions during long-distance transport mean that simple physical calculations may still contain errors. AI fine-tuning can address the nonlinear effects of fluid concentration and temperature on wave velocity, significantly improving the accuracy of wave velocity values ​​and thus enhancing the precision of final leak location.

[0134] Specifically, the AI ​​inference program can be run in the main control analysis unit (industrial control computer) to process input data in real time and output correction results.

[0135] The RandomForest algorithm described above is an ensemble learning algorithm. In this method, it is mainly used to optimize the weights for parameter adjustment. It can handle high-dimensional data and evaluate the importance of different operating parameters (such as temperature and concentration) on wave velocity.

[0136] The LSTM (Long Short-Term Memory) network mentioned above is a special type of recurrent neural network (RNN) that excels at processing time-series data. Using LSTM in combination means that the system not only considers the current single-point state but may also utilize the temporal correlations of historical states to predict trends in wave speed changes.

[0137] The training data mentioned above is derived from "historical leakage data containing different operating conditions". The training set can cover a wide range of operating conditions, such as (but not limited to) fluid concentration of 30% to 70%, temperature of -10℃ to 50℃, and pipeline pressure of 0.5MPa to 2.0MPa.

[0138] Before system deployment or during updates, this step uses historical data (e.g., more than 1000 sets) containing different operating conditions to train the model, enabling it to learn the complex nonlinear relationship between "temperature / concentration" and "wave velocity deviation".

[0139] The method described in this embodiment has the advantages of strong generalization ability, high accuracy, and dynamic adaptability. The random forest algorithm has excellent anti-overfitting ability and can adapt to various working conditions. Through training with a large amount of historical data, the model can "remember" the wave velocity characteristics under various extreme or special working conditions, making it more adaptable to complex and ever-changing industrial environments than a single physical formula. Combining the decision-making ability of random forest and the time-series processing ability of LSTM makes wave velocity correction smoother and more accurate.

[0140] Furthermore, step S220, after performing a fast Fourier transform on the received echo signal to convert it into a frequency domain signal, also includes: Step S270: Perform smoothing filtering on the converted frequency domain signal to eliminate spurious peaks in the frequency domain signal.

[0141] This step involves "cleaning up" the frequency domain data obtained after Fast Fourier Transform (FFT). Due to potential electromagnetic interference or other high-frequency random noise in the environment, sharp spikes (pseudo-peaks) that do not represent the true pressure wave echo may appear on the converted frequency domain spectrum. This step aims to smooth out these noise points using algorithms.

[0142] Specifically, the system can apply smoothing filtering algorithms to frequency domain signal sequences. For example, a smoothing filtering method with a window size of 5 data points can be used. This means that for each frequency domain data point, the system will average or weight the amplitudes of its surrounding neighboring data to correct the amplitude of the current point. Through this step, a smoother frequency domain signal curve with suppressed noise and spikes can be obtained. On this curve, isolated spikes caused by random interference are weakened, while broad peaks representing the true echo energy are preserved.

[0143] The core objective of this step is to "eliminate spurious peaks caused by electromagnetic interference." Without smoothing, subsequent steps (such as peak identification) are highly likely to misidentify a high-amplitude noise spike as the first or second feature point, leading to errors in time difference calculation and ultimately causing serious deviations in wave velocity calculation and positioning. Smoothing filtering significantly improves the robustness of feature extraction.

[0144] For example, a moving average filter or a Gaussian smoothing filter can be implemented in a software algorithm to iterate through the array of FFT outputs.

[0145] Furthermore, after transmitting a pressure pulse wave and receiving the echo signal at the beginning of the pipeline, step S200 further includes: The echo signal is verified to meet the following condition (Formula 4): ; Where S(t) represents the echo signal; P represents the pulse intensity; R(t) represents the original echo; a represents the attenuation factor; and n represents the number of time points.

[0146] The above steps (algorithm) are a signal quality control or preprocessing model matching step. It defines the mathematical model that the effective echo signal S(t) used for subsequent analysis (such as FFT) should follow, or in other words, the process of modifying the original acquired signal to conform to the model.

[0147] The above steps ensure that the signal input to the FFT transform module meets specific physical constraints. This is achieved by subtracting... This can eliminate DC drift or low-frequency linear interference that may exist in sensors or circuits, and prevent these non-wave components from causing interference in spectrum analysis (such as huge energy near zero frequency), thereby ensuring that the wave velocity calculated subsequently is accurate and reliable.

[0148] Example 4 Reference Figure 6 Based on the foregoing embodiments, this embodiment provides a method for monitoring and locating leaks in filled pipelines. After calculating the coordinates of the leak point in step S300, the method further includes: Step S400: Repeat the steps of collecting pressure change data in the pipeline over time through the pressure sensing unit, calculating the pressure wave propagation speed under the current operating conditions, and calculating the coordinates of the leak point until multiple sets of parallel leak point coordinates are obtained.

[0149] This step initiates data accumulation and parallel validation. Instead of relying on a single calculation result, the system runs the core monitoring and location processes multiple times to obtain multiple sets of independent data samples.

[0150] Specifically, the system control hardware and software modules repeatedly execute the core steps of the aforementioned method: collecting pressure data, measuring wave velocity, and calculating coordinates. The system will continuously or intermittently collect three (or more) sets of parallel data, thereby obtaining a set containing multiple calculation results, i.e., multiple sets of parallel leak point coordinates (e.g., coordinates A, coordinates B, and coordinates C).

[0151] A single measurement may be affected by random noise or transient interference, resulting in accidental errors. Obtaining multiple sets of parallel data through repeated execution provides a statistical basis for subsequent consistency analysis, helps identify and eliminate accidental errors, and improves the reliability of the positioning results.

[0152] Step S500: Calculate the deviation values ​​between multiple sets of leak point coordinates.

[0153] This step is a data consistency analysis step. The system quantitatively assesses how far apart these independently calculated leak locations are from each other.

[0154] The system performs mathematical operations on the multiple sets of coordinates obtained in step S400, calculating the maximum difference, standard deviation, or deviation relative to the mean between them. For example, it calculates the distance difference between each pair of the three measurement results to obtain a specific value, namely the "deviation value" (e.g., 0.1m or 0.5m), which reflects the stability or dispersion of the system's measurements.

[0155] By quantifying the deviation, the system can objectively determine whether the current measurement results are stable. If the deviation is small, it indicates good consistency of the measurement results; if the deviation is large, it indicates interference or improper parameter settings.

[0156] Step S600: Determine whether the deviation value is not greater than the first preset deviation threshold.

[0157] This step is a logical decision step. The system compares the calculated deviation value with a pre-set pass / fail standard (threshold).

[0158] The system reads the preset "first preset deviation threshold" (for example, it can be 0.2m), and compares the deviation value obtained in step 500 with the threshold to obtain a Boolean judgment result: "yes" (deviation is qualified) or "no" (deviation exceeds the standard).

[0159] This step establishes a clear quality control standard to ensure that only high-precision positioning results are accepted by the system, preventing data with excessive errors from misleading subsequent maintenance work.

[0160] Step S700: If yes, then the average value of the multiple sets of leak point coordinates or any one set of coordinates is confirmed as the final leak point location.

[0161] This step is a confirmation output step when the conditions are met. When multiple sets of data are very close, the system considers the measurement successful. When the judgment deviation is ≤ the first preset deviation threshold (e.g., 0.2m), the system directly outputs the current calculation result. You can choose one set as the final result, or calculate the average of multiple sets of coordinates as the final result.

[0162] This step outputs the final confirmed location of the leak point, ending the system process and entering the early warning stage. This ensures the accuracy and reliability of the output results and confirms that the current parameter settings and calculation model are suitable for the current operating conditions.

[0163] Step S800: If not, adjust the peak recognition threshold using the AI ​​parameter adjustment module, and recalculate the leakage point coordinates using the adjusted peak recognition threshold until the deviation value meets the first preset deviation threshold.

[0164] This step is an automatic error correction and optimization loop when the conditions are not met. When the deviation is too large, the system does not directly report an error, but instead attempts to find the correct result by adjusting the internal parameters of the algorithm.

[0165] Specifically, parameters can be adjusted. When the deviation exceeds the first preset deviation threshold, the AI ​​parameter adjustment module is activated. This module automatically modifies the key parameter, the "peak recognition threshold." Then, using the adjusted threshold, the pressure wave data is reprocessed, and the leak point coordinates are recalculated. This is an iterative process ("until"), where the system continuously repeats the adjustment-calculation-comparison process until the deviation value is less than or equal to the first preset deviation threshold.

[0166] This step ultimately yields a set of leak point coordinates that meet accuracy requirements (deviation acceptable). This endows the system with strong adaptability and robustness. Under complex operating conditions, a fixed threshold may lead to misjudgments (e.g., misjudging noise as echo peaks, resulting in large positioning deviations). Through AI-automated iterative parameter adjustment, the system can "self-calibrate," eliminating errors without manual intervention and ensuring reliable positioning results under various operating conditions.

[0167] Furthermore, after calculating the deviation values ​​between multiple sets of leak point coordinates in step S500, the method further includes: Step S500-1: Determine whether the deviation value is greater than a second preset deviation threshold; wherein the second preset deviation threshold is greater than the first preset deviation threshold.

[0168] This step is a graded fault diagnosis step. Having already fine-tuned the AI ​​parameters for "general deviations" (greater than the first threshold, such as 0.2m), this step further identifies whether there are "serious deviations" or "extreme anomalies." It defines a second line of defense for the severity of deviations.

[0169] Specifically, the system can compare the deviation values ​​between the previously calculated coordinates of multiple leak points with the "second preset deviation threshold".

[0170] The first preset deviation threshold (used to trigger AI adjustment) can be set to 0.2m, while the second preset deviation threshold (used to trigger redundancy check) can be set to 0.5m. The system determines whether the deviation value exceeds this larger limit.

[0171] The above judgment leads to a logical conclusion: if the deviation exceeds the threshold, it indicates that the current single calculation or parameter fine-tuning can no longer meet the positioning accuracy requirements, or there is serious signal interference, requiring the activation of a higher-level verification mechanism.

[0172] This step implements a tiered response for fault handling. It prevents the system from blindly fine-tuning AI parameters and failing to converge even when errors are extremely large (potentially caused by sensor malfunction or strong interference). By setting higher thresholds, the system can promptly identify complex situations requiring additional data assistance.

[0173] Step S500-2: If yes, then initiate redundant sensor data verification; retrieve historical data from at least three pressure sensors around the leak point, and determine the leak location range through spatiotemporal correlation analysis.

[0174] The redundant sensor data verification step is a system operating mode switching step. When the positioning deviation is determined to be too large, the system can switch from "dual-end precise positioning mode" to "multi-end redundant verification mode".

[0175] Specifically, the main control analysis unit can change its processing logic, no longer relying solely on the set of data that calculated the deviation, but instead activating a redundant verification subroutine to prepare for calling more data sources for comprehensive analysis. This step enhances the system's robustness. It provides a backup plan when the conventional calculation path fails, preventing the system from outputting incorrect location results or falling into an infinite loop.

[0176] The aforementioned retrieval of historical data from at least three pressure sensors around the leak point is a step in expanding the data source. To address the issue of inaccurate calculations based on data from a single sensor pair (or local area), the system broadens its scope by incorporating data from more sensors for joint diagnosis.

[0177] Specifically, the system can search for at least three pressure sensors closest to the leak point in the pipeline topology based on the initially calculated location. Then, it retrieves historical pressure records from these sensors before and after the leak occurred from the database or cache.

[0178] This resulted in a multidimensional dataset containing multiple spatial points (more than 3 sensor locations) and time series (historical data).

[0179] This step utilizes multi-point data to introduce spatial redundancy information. Even if poor signal quality from a single sensor leads to significant calculation errors, data from other surrounding sensors can provide corroborating evidence, helping to correct or verify the authenticity of the leak event.

[0180] The steps described above for determining the leak location range through spatiotemporal correlation analysis are based on a comprehensive analysis of multi-source data. By utilizing the temporal and spatial correlations of multiple sensors, the approximate leak area is determined, serving as a backup method after high-precision location analysis fails.

[0181] Specifically, the system performs spatiotemporal correlation analysis on historical data from three or more sensors. Specifically, it analyzes the time sequence of pressure wave propagation to these sensors and the signal attenuation characteristics to verify whether they conform to physical laws (e.g., the closer to the leak point, the earlier the pressure wave arrives, and the more significant the amplitude change), thereby determining a credible "leak location range." While it may not be accurate to specific meter-level coordinates (e.g., ±1m), it can narrow down and confirm the effective pipe section area where the leak occurred.

[0182] In this step, even when extreme operating conditions or severe interference make it impossible to accurately calculate coordinates, a reliable fault range can be provided at least, reducing the area for manual troubleshooting and ensuring the basic availability and reliability of the system under harsh conditions.

[0183] Furthermore, in the step of determining whether the deviation value is greater than the second preset deviation threshold (e.g., 0.5m), if it is determined that the deviation value is not greater than the second preset deviation threshold (i.e., the deviation value is between the first and second preset deviation thresholds, e.g., 0.2m < deviation value ≤ 0.5m), it can be determined that the current positioning error mainly originates from a slight drift in the wave velocity calculation parameter or peak identification parameter, and has not yet reached the fault level requiring the activation of redundant verification. At this time, the system will maintain the current active monitoring process and can return to the step of adjusting the peak identification threshold using the AI ​​parameter adjustment module. Specifically, the peak identification threshold is fine-tuned based on the current fluid concentration and temperature data using a random forest-LSTM hybrid algorithm, and the adjusted threshold is used to re-extract feature points, calculate wave velocity and leak point coordinates, and then recalculate the deviation value of a new set of coordinates. This adjustment-calculation-verification process will be executed cyclically until the deviation value is less than or equal to the first preset deviation threshold, thereby outputting the finally confirmed leak point location.

[0184] Example 5 Reference Figure 7 Based on the foregoing embodiments, this embodiment provides a method for monitoring and locating leaks in filled pipelines, the method further comprising: Step S900-1: Calculate the leakage orifice diameter and leakage amount based on the pressure data collected by the pressure sensing unit.

[0185] The above steps refer to the system's use of collected pressure change characteristics to quantitatively assess the severity of the leak. It converts the abstract pressure signal into specific physical quantitative indicators: the size of the leak (orifice) and the volume lost per unit time (leakage).

[0186] Specifically, the main control analysis unit can perform inversion calculations based on the data collected by the pressure sensing unit (especially the magnitude and rate of pressure drops), combined with the fluid dynamics model inside the pipeline, to estimate the equivalent leakage orifice size (unit: mm) and the corresponding fluid leakage rate (unit: m³) required to cause the current pressure change. 3 / h), thus obtaining two specific numerical indicators: leakage orifice diameter and leakage rate.

[0187] In this embodiment, the leakage event is upgraded from a qualitative "existence / absence" judgment to a quantitative "major / minor" assessment, which provides data support for subsequent hierarchical management and avoids the problems of overreacting to minor leaks or lagging in response to serious leaks.

[0188] Step S900-2, when the leakage orifice diameter is ≥20mm, or the leakage amount is ≥1m 3 / hour, triggering a high-risk warning and controlling the pipeline valve to shut off or shut off within the first preset time; The above steps represent the highest level of emergency response for serious leaks. The criteria for determining "high risk" and the corresponding emergency response measures are defined.

[0189] The system will compare the value calculated in step one with the high-risk threshold (20mm or 1m). 3 The system compares the values ​​of / h. Once either condition is met, the system immediately performs two operations: first, it triggers a high-intensity audible and visual alarm (decibels > 85dB as stated in the handover document); second, it sends an emergency shut-off command to the pipeline valve through the switch output module, requiring the valve to complete the action within a very short time (i.e., the first preset time, which can specifically correspond to ≤10s).

[0190] The system enables rapid shut-off and high-intensity warnings, minimizing material loss and environmental pollution. It ensures that in the event of a large-diameter pipe rupture or massive leak, the system can cut off the source with the highest priority and fastest speed (e.g., within 10 seconds), safeguarding industrial safety.

[0191] Step S900-3, when 20mm > the leakage orifice diameter ≥ 5mm, or 1m 3 / hour > Leakage amount ≥ 0.1m 3 / hour, triggering a medium-risk warning and controlling the pipeline valve to shut off or shut off within a second preset time; wherein, the first preset time is not greater than the second preset time; The above steps are for the control of moderate-level leaks. The criteria for determining "medium risk" and the corresponding response strategies are defined.

[0192] Specifically, when the calculated values ​​fall within the medium range (orifice diameter 5-20 mm or flow rate 0.1-1 m³), 3When the risk level reaches 0.65 m / h, the system determines it to be medium risk. The system triggers the corresponding level of warning and controls the valve to shut off. At this time, the requirement for the shutdown response time (i.e., the second preset time, which corresponds to ≤15s in the embodiment of the disclosure document) is slightly relaxed compared to high risk.

[0193] This step can trigger a medium-risk warning signal and orderly close the valves to stop the delivery. It achieves a tiered response. Although the valves still need to be shut off, the allowed response time (e.g., 15 seconds) is slightly longer than in high-risk situations, reflecting the distinction in the urgency of equipment action at different risk levels.

[0194] Step S900-4: When the leakage orifice diameter is <5mm, or the leakage amount is <0.1 m³ 3 / h triggers a low-risk warning.

[0195] This step is a suggestive procedure for minor leaks. It defines the criteria for determining "low risk" and the non-blocking approach.

[0196] Specifically, when the leakage is very small (orifice diameter less than 5 mm or flow rate less than 0.1 m³), 3 When the valve shuts off ( / h), the system can trigger only an audible and visual alarm to alert maintenance personnel, without sending a valve shut-off command. Alternatively, other processes can be triggered under an investigation procedure acceptable to this method.

[0197] The above steps, without interrupting production and transportation, alerted staff to equipment malfunctions. This prevented a complete shutdown from being triggered by a tiny leak or slight seepage, ensuring production continuity while prompting personnel to perform timely inspections and maintenance, thus balancing safety monitoring with production efficiency.

[0198] refer to Figure 8 In this embodiment of the application, a leak monitoring and locating device for filling pipelines is also provided, comprising: The data identification module 10 is used to collect data on the pressure change in the pipeline over time through the pressure sensing unit and to identify leakage triggering characteristics. The velocity calculation module 20 is used to transmit a pressure pulse wave at the beginning of the pipeline and receive the echo signal, and calculate the pressure wave propagation velocity under the current working condition based on the echo signal. The coordinate calculation module 30 is used to extract the arrival time of the pressure wave to each sensor, and calculate the coordinates of the leak point based on the propagation speed of the pressure wave and the time difference of the pressure wave arrival.

[0199] It is understood that the device in this embodiment corresponds to the filling pipeline leakage monitoring and location method in the above embodiment, and the options in the above embodiment are also applicable to this embodiment, so they will not be described again here.

[0200] In this embodiment of the application, a computer device is also provided, the computer device including a processor and a memory, the memory storing a computer program, and the processor being used to execute the computer program to implement the filling pipeline leakage monitoring and location method described in any of the foregoing embodiments.

[0201] The pressure wave analysis-based filling pipeline leakage monitoring and location system consists of a high-precision pressure sensing unit, a pressure pulse transmitter, a data acquisition unit, a main control and analysis unit, and a display and early warning unit.

[0202] The processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, including at least one of a Central Processing Unit (CPU), Graphics Processing Unit (GPU), Network Processor (NP), Digital Signal Processor (DSP), Application-Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor or any conventional processor, capable of implementing or executing the methods, steps, and logic block diagrams disclosed in the embodiments of this application.

[0203] The memory can be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), etc. The memory is used to store computer programs, and the processor can execute the computer programs accordingly after receiving execution instructions.

[0204] This application embodiment also provides a filling pipeline leakage monitoring and location system, including: A high-precision pressure sensing unit is used to be installed on the filling pipeline to collect data on the pressure change in the pipeline over time. A pressure pulse transmitting device is installed at the beginning of the filling pipe to transmit pressure pulse waves into the pipe; A data acquisition unit, connected to the high-precision pressure sensing unit, is used to receive and process the pressure change data over time. The display and early warning unit is used to display monitoring results and issue early warnings. The main control and analysis unit is connected to the pressure pulse transmitter, the data acquisition unit, and the display and warning unit, respectively. The main control analysis unit is used to execute the filling pipeline leakage monitoring and location method as described in the foregoing embodiments.

[0205] Furthermore, the high-precision pressure sensing unit includes multiple bidirectional precision digital pressure sensors; the bidirectional precision digital pressure sensors are arranged along the filling pipe, and the spacing between them meets the following rules: in the straight sections of the filling pipe, the spacing is 50m-100m (for example, it can be 50m, 60m, 70m, 80m, 90m, 100m, etc.); at the bends of the filling pipe, the spacing is 20m-50m (for example, it can be 20m, 30m, 40m, 50m, etc.).

[0206] Furthermore, the spacing between the branch pipe openings of the filling pipeline is 5m-10m.

[0207] Furthermore, the high-precision pressure sensing unit also includes a temperature compensation module, which contains a built-in thermocouple for real-time monitoring of ambient temperature; the built-in thermocouple has a measurement range of -20℃ to 80℃ and a measurement accuracy of ±0.5℃.

[0208] Furthermore, the data acquisition unit includes: The signal amplification module has an amplification factor configured to be 100x-500x (e.g., 100x, 200x, 300x, 400x, 500x, etc.); the filtering module uses a low-pass filter circuit with a cutoff frequency of 500Hz; and the switching output module is connected to the pipeline valve on the filling pipeline and is used to output control signals to drive the pipeline valve to operate.

[0209] Furthermore, the display warning unit includes an audible and visual alarm and a display screen; The alarm decibel level of the audible and visual alarm is greater than 85 dB; the display screen is used to display the coordinates of the leak point and the risk level.

[0210] Furthermore, the main control analysis unit also integrates a pipeline digital twin module, which is configured to construct a virtual model of the filling pipeline based on Unity3D and map the pressure distribution, pressure wave propagation trajectory and leakage point location in real time.

[0211] This application also provides a computer storage medium storing a computer program, which, when executed on a processor, implements the filling pipeline leakage monitoring and location method according to any one of the foregoing embodiments.

[0212] The computer storage medium can be a readable storage medium, a non-volatile storage medium, or a volatile storage medium. For example, the computer storage medium may include, but is not limited to, various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0213] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that, in alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0214] In addition, the functional modules or units in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0215] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a smartphone, personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.

[0216] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A method for monitoring and locating leaks in a filling pipeline, characterized in that, include: The pressure sensing unit collects data on the pressure change in the pipeline over time to identify leakage triggering characteristics. A pressure pulse wave is emitted at the beginning of the pipeline and the echo signal is received. The pressure wave propagation speed under the current operating condition is calculated based on the echo signal. The arrival time of the pressure wave to each sensor is extracted, and the coordinates of the leak point are calculated based on the propagation speed of the pressure wave and the time difference of arrival of the pressure wave.

2. The method for monitoring and locating leaks in a filled pipeline as described in claim 1, characterized in that, The method of collecting pressure change data within the pipeline over time through a pressure sensing unit to identify leakage triggering characteristics includes: The pressure sensing unit is controlled to collect pressure data in the pipeline and generate a pressure curve showing the change of pressure over time. A basic pressure model for pipelines is established based on the pressure fluctuation equation. Analyzing the pressure curve, when a sudden drop in pressure is detected in the pressure curve, it is determined that a leakage trigger feature has been identified.

3. The method for monitoring and locating leaks in a filling pipeline as described in claim 2, characterized in that, The pressure fundamental model of the pipeline established based on the pressure fluctuation equation includes: The ambient temperature of the pipeline is monitored in real time, and the elastic modulus in the pressure fluctuation equation is corrected according to the temperature-elastic coefficient correlation model; the expression of the temperature-elastic coefficient correlation model is: E=E0[1+α(T-T0)]; where E represents the elastic modulus at the real-time monitored temperature T; E0 represents the elastic modulus at the reference temperature; α represents the temperature coefficient; T represents the real-time monitored ambient temperature; T0 represents the reference temperature; and / or, The control of the pressure sensing unit to acquire pressure data within the pipeline includes: controlling the pressure sensing unit to acquire data at a sampling frequency of not less than 10 kHz to capture the instantaneous characteristics of a sudden pressure drop; and / or, The method of controlling the pressure sensing unit to collect pressure data in the pipeline further includes: performing signal preprocessing on the collected pressure data; the signal preprocessing includes: performing signal amplification processing on the collected pressure data by 100 times to 500 times; and / or, using a low-pass filter module with a cutoff frequency of 500Hz to filter the pressure data.

4. The method for monitoring and locating leaks in a filled pipeline as described in claim 1, characterized in that, The step of emitting a pressure pulse wave at the beginning of the pipeline and receiving the echo signal, and calculating the pressure wave propagation speed under the current operating conditions based on the echo signal, includes: At least two sets of pressure pulse waves of different frequencies are emitted at the beginning of the pipeline, with each set of pressure pulse waves lasting from 0.5 ms to 2.0 ms. The received echo signal is converted into a frequency domain signal by performing a fast Fourier transform. Identify the first feature point corresponding to the first peak and the second feature point corresponding to the second peak in the frequency domain signal, and calculate the time difference between the first feature point and the second feature point; The pressure wave propagation speed under the current operating condition is calculated based on the time difference.

5. The method for monitoring and locating leaks in a filled pipeline as described in claim 4, characterized in that, After calculating the pressure wave propagation speed under the current operating condition based on the time difference, the method further includes: acquiring real-time fluid concentration and temperature data within the pipeline; and using an AI parameter adjustment module to fine-tune the calculated pressure wave propagation speed based on the real-time fluid concentration and temperature data; wherein the AI ​​parameter adjustment module employs a random forest-LSTM hybrid algorithm, trained based on historical leakage data containing different operating conditions; and / or, After performing a Fast Fourier Transform on the received echo signal to convert it into a frequency domain signal, the method further includes: performing a smoothing filter on the converted frequency domain signal to eliminate spurious peaks in the frequency domain signal; and / or, The calculation of the time difference between the first feature point and the second feature point includes: obtaining the sampling period of the pressure sensing unit; and calculating the time difference based on the following formula: Where Δt represents the time difference; k1 represents the sampling point ordinal number corresponding to the first feature point; and k2 represents the sampling point ordinal number corresponding to the second feature point. Represents the sampling period of the pressure sensing unit; and / or, The expression for calculating the propagation speed of the pressure wave is: Where V represents the propagation speed of the pressure wave; Δt represents the time difference.

6. The method for monitoring and locating leaks in a filled pipeline as described in claim 1, characterized in that, After transmitting a pressure pulse wave and receiving the echo signal at the beginning of the pipeline, the process further includes: The echo signal is verified to meet the following conditions: Wherein, S(t) represents the echo signal; P represents the pulse intensity; R(t) represents the original echo; a represents the attenuation factor; n represents the number of time points; and / or, After obtaining the coordinates of the leak point through calculation, the process also includes: Repeat the steps of collecting pressure change data in the pipeline over time through the pressure sensing unit, calculating the pressure wave propagation speed under the current operating conditions, and calculating the coordinates of the leak point until multiple sets of parallel leak point coordinates are obtained. Calculate the deviation between multiple sets of leak point coordinates; Determine whether the deviation value is not greater than a first preset deviation threshold; If so, the average value of the multiple sets of leak point coordinates or any one set of coordinates will be determined as the final leak point location; If not, the peak recognition threshold is adjusted using the AI ​​parameter adjustment module, and the leak point coordinates are recalculated using the adjusted peak recognition threshold until the deviation value meets the first preset deviation threshold.

7. The method for monitoring and locating leaks in a filled pipeline as described in claim 6, characterized in that, After calculating the deviation values ​​between multiple sets of leak point coordinates, the method further includes: Determine whether the deviation value is greater than a second preset deviation threshold; wherein the second preset deviation threshold is greater than the first preset deviation threshold; If so, then initiate redundant sensor data verification; retrieve historical data from at least three pressure sensors around the leak point, and determine the leak location range through spatiotemporal correlation analysis.

8. The method for monitoring and locating leaks in a filled pipeline as described in claim 1, characterized in that, The method for monitoring and locating leaks in filled pipelines also includes: Based on the pressure data collected by the pressure sensing unit, the leakage orifice diameter and leakage amount are calculated. When the leakage orifice diameter is ≥20mm, or the leakage amount is ≥1m 3 / hour, triggering a high-risk warning and controlling the pipeline valve to shut off or shut off within the first preset time; When 20mm > the leakage orifice diameter ≥ 5mm, or 1m 3 / hour > Leakage amount ≥ 0.1m 3 / hour, triggering a medium-risk warning and controlling the pipeline valve to shut off or shut off within a second preset time; wherein, the first preset time is not greater than the second preset time; A low-risk warning is triggered when the leakage orifice diameter is less than 5 mm or the leakage rate is less than 0.1 m³ / hour.

9. A device for monitoring and locating leaks in a filling pipeline, characterized in that, include: The data identification module is used to collect data on the pressure change in the pipeline over time through the pressure sensing unit and to identify leakage triggering characteristics. The velocity calculation module is used to transmit pressure pulse waves at the beginning of the pipeline and receive echo signals, and calculate the pressure wave propagation velocity under the current operating conditions based on the echo signals. The coordinate calculation module is used to extract the arrival time of the pressure wave to each sensor, and calculate the coordinates of the leak point based on the propagation speed of the pressure wave and the time difference of the pressure wave arrival.

10. A computer device, characterized in that, The computer device includes a processor and a memory, the memory storing a computer program, and the processor executing the computer program to implement the filling pipeline leakage monitoring and location method according to any one of claims 1-8.

11. A leak monitoring and location system for filling pipelines, characterized in that, include: A high-precision pressure sensing unit is used to be installed on the filling pipeline to collect data on the pressure change in the pipeline over time. A pressure pulse transmitting device is installed at the beginning of the filling pipe to transmit pressure pulse waves into the pipe; A data acquisition unit, connected to the high-precision pressure sensing unit, is used to receive and process the pressure change data over time. The display and early warning unit is used to display monitoring results and issue early warnings. The main control and analysis unit is connected to the pressure pulse transmitter, the data acquisition unit, and the display and warning unit, respectively. The main control analysis unit is used to execute the filling pipeline leakage monitoring and location method as described in any one of claims 1-8.

12. A computer storage medium, characterized in that, It stores a computer program, which, when executed on a processor, implements the method for monitoring and locating leaks in filling pipelines according to any one of claims 1-8.

Images