Pipe network leakage sound detection circuit

Abstract

The utility model is suitable for the technical field of pipe network leakage detection, and relates to a pipe network leakage sound detection circuit which comprises a sound acquisition probe, a hardware amplification filtering module, a sound acquisition module, a DSP data processing module, a temperature acquisition module, an FPGA / NPU neural network training module, an MCU main control module, a remote transmission module and a storage module. The sound acquisition probe, the hardware amplification filtering module, the sound acquisition module, the DSP data processing module and the FPGA / NPU neural network training module are sequentially in communication connection, and the sound acquisition probe, the hardware amplification filtering module, the sound acquisition module, the DSP data processing module, the temperature acquisition module, the FPGA / NPU neural network training module and the remote transmission module are respectively in communication connection with the MCU main control module. The pipe network leakage sound detection device is simple in structure and convenient to work, and improves the accuracy of pipe network leakage sound detection.

Description

Technical Field

[0001] This utility model belongs to the field of pipeline leakage detection technology, and in particular relates to a pipeline leakage sound detection circuit. Background Technology

[0002] In pipeline leakage detection, sound detection is a commonly used method. Traditional sound detection methods mainly use listening rods or noise leak detectors to capture sound changes in the pipeline to determine the location of the leak. This method relies on manual listening and is greatly affected by environmental noise and the operator's experience. In addition, it is also greatly affected by ambient temperature. Temperature changes affect the speed of sound propagation and attenuation characteristics in the medium, thus affecting the accuracy of leak sound signal detection.

[0003] Patent application CN218153673U discloses an IoT-based water supply network leakage detection device, including a first pipe and a second pipe. The first and second pipes are connected at their closest points via a flange. A detection component is installed on the outer wall of the flange, and an adjustment component is installed on the outer wall of the first pipe. This device uses the detection component to monitor the flange connecting the first and second pipes in real time, facilitating timely detection of leaks and their condition. Leaks are detected using IoT technologies such as cameras, humidity sensors, and pressure sensors. However, this patent application also uses a leak detector to monitor network leakage, which has low accuracy and does not describe a technical solution for compensating for temperature changes, exhibiting the same drawbacks as existing technologies.

[0004] Therefore, how to compensate for temperature changes to improve the accuracy of leakage sound detection is a problem that urgently needs to be solved by those in this technical field. Utility Model Content

[0005] To address the shortcomings of existing technologies, the purpose of this invention is to provide a pipeline leakage sound detection circuit to solve the problem that existing pipeline detection methods do not compensate for temperature changes, resulting in low accuracy of leakage sound detection.

[0006] To solve the above-mentioned technical problems, the present invention adopts the following technical solution:

[0007] This utility model provides a pipeline leakage sound detection circuit, including:

[0008] The system comprises a sound acquisition probe, a hardware amplification and filtering module, a sound acquisition module, a DSP data processing module, a temperature acquisition module, an FPGA / NPU neural network training module, an MCU main control module, a remote transmission module, and a storage module. These components are sequentially and communicatively connected. The sound acquisition probe, hardware amplification and filtering module, sound acquisition module, DSP data processing module, and FPGA / NPU neural network training module are also communicatively connected to the MCU main control module. The temperature acquisition module is also communicatively connected to the DSP data processing module, and the DSP data processing module is also communicatively connected to the storage module.

[0009] Furthermore, the circuit of the hardware amplification and filtering module includes a resistor R1, a capacitor C1, an amplifier U11, an amplifier U12, an amplifier U14, and an amplifier U15. One end of the resistor R1 is connected to one end of the capacitor C1 and the third pin of the amplifier U14, respectively. The other end of the resistor R1 is connected to the control power supply VCC1 of the MCU main control module. The other end of the capacitor C1 is grounded. The first pin of the amplifier U14 is connected to the third pin of the amplifier U15. The first pin of the amplifier U15 is connected to the third pin of the amplifier U11. The first pin of the amplifier U11 is connected to the third pin of the amplifier U12.

[0010] Furthermore, the circuit composed of the sound acquisition module, DSP data processing module, storage module, temperature detection module, FPGA / NPU neural network training module, remote transmission module, and MCU main control module includes chips U1, U2, U3, U18B, U18N, U18L, U19, U20, crystal oscillator Y1, crystal oscillator Y2, transistor Q1, and transistor Q2. Chip U1 is connected to chip U2. Chip U2 is also connected to chip U20, chip U18B, switch XS1, and crystal oscillator Y1 respectively. Chip U18B is also connected to chip U19. Chip U18N is connected to crystal oscillator Y2. Chip U18L is connected to chip U3. Chip U19 is also connected to transistor Q1, transistor Q2, and chip U20 respectively.

[0011] Furthermore, the FPGA / NPU neural network training module uses an FPGA chip, model EP4CE6E22C8.

[0012] Furthermore, the model of the MCU main control module is HC32L190JCTA.

[0013] Furthermore, the sound acquisition module is model ADC4696.

[0014] Furthermore, the DSP data processing module is model TMS320C6713.

[0015] Compared with the prior art, the pipeline leakage sound detection circuit provided by this utility model has at least the following advantages:

[0016] Traditional sound detection methods primarily rely on listening rods or noise leak detectors to capture sound changes within pipes to pinpoint leak locations. This method depends on manual listening and is significantly affected by environmental noise, operator experience, and ambient temperature. Temperature variations influence the speed of sound propagation and attenuation characteristics within the medium, thus impacting the accuracy of leak detection. This invention presents a simple and convenient pipe network leak sound detection circuit based on a temperature compensation mechanism. By compensating for the impact of ambient temperature on sound frequency and other characteristics, it effectively eliminates the influence of temperature changes on the sound signal. Furthermore, the introduction of an FPGA-based NPU model significantly improves the accuracy and reliability of pipe network leak sound detection. Attached Figure Description

[0017] To more clearly illustrate the solution of this utility model, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this utility model. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1 A schematic diagram of a pipeline leakage sound detection circuit provided in this embodiment of the present invention;

[0019] Figure 2 A partial circuit diagram of a pipeline leakage sound detection circuit provided in this embodiment of the present utility model;

[0020] Figure 3 Another part of the circuit diagram of a pipeline leakage sound detection circuit provided for an embodiment of this utility model. Detailed Implementation

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. For example, terms such as “length,” “width,” “upper,” “lower,” “left,” “right,” “front,” “rear,” “vertical,” “horizontal,” “top,” “bottom,” “inner,” and “outer,” etc., indicate orientations or positions based on the accompanying drawings and are for ease of description only, and should not be construed as limiting the technical solution. The terms “comprising” and “having,” and any variations thereof, in the specification, claims, and accompanying drawings of this invention, are intended to cover non-exclusive inclusion. The terms “first,” “second,” etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a particular order. In the specification, claims, and accompanying drawings of this invention, when an element is referred to as “fixed to,” “mounted to,” “set on,” or “connected to” another element, it may be directly or indirectly located on that other element. For example, when an element is referred to as being "connected to" another element, it can be directly or indirectly connected to that other element. Furthermore, the reference herein to "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the present invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0022] This utility model provides a pipeline leakage sound detection circuit, applied in the pipeline leakage detection process. The pipeline leakage sound detection circuit includes:

[0023] The system comprises a sound acquisition probe, a hardware amplification and filtering module, a sound acquisition module, a DSP data processing module, a temperature acquisition module, an FPGA / NPU neural network training module, an MCU main control module, a remote transmission module, and a storage module. The sound acquisition probe, hardware amplification and filtering module, sound acquisition module, DSP data processing module, and FPGA / NPU neural network training module are sequentially and communicatively connected. The sound acquisition probe, hardware amplification and filtering module, sound acquisition module, DSP data processing module, temperature acquisition module, FPGA / NPU neural network training module, and remote transmission module are all communicatively connected to the MCU main control module.

[0024] This invention has a simple structure, is easy to operate, and improves the accuracy of sound detection for pipeline leakage.

[0025] To enable those skilled in the art to better understand the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings.

[0026] This utility model provides a sound detection circuit for pipeline leakage, which is applied in the process of pipeline leakage detection, combined with... Figures 1 to 3 In this embodiment, the pipeline leakage sound detection circuit includes:

[0027] The system comprises a sound acquisition probe, a hardware amplification and filtering module, a sound acquisition module, a DSP data processing module, a temperature acquisition module, an FPGA / NPU neural network training module, an MCU main control module, a remote transmission module, and a storage module. These components are sequentially connected in communication. The sound acquisition probe, hardware amplification and filtering module, sound acquisition module, DSP data processing module, and FPGA / NPU neural network training module are also connected in communication with the MCU main control module. The temperature acquisition module is also connected in communication with the DSP data processing module, which in turn is connected in communication with the storage module.

[0028] Specifically, in this embodiment, the sound acquisition probe mainly acquires sound; the hardware amplification and filtering module uses impedance matching and a preamplifier, amplifies the sound, and then performs bandpass filtering to obtain useful sound signals; the sound acquisition module uses ADI's SARADC chip, which can acquire sound at high speed, and the chip used is ADC4696 with 16-bit resolution; the DSP data processing module performs sound filtering and noise reduction processing, then extracts feature values ​​from the time and frequency domains, and establishes a temperature compensation model for sound, and the DSP used is TI's TMS320C6713; the temperature acquisition module uses a digital temperature acquisition chip, which exchanges data with the DSP via I2C; the FPGA / NPU neural network training module uses an FPGA chip of model EP4CE6E22C8, performs Verilog programming to form an NPU training model, and builds the NPU model through the FPGA; the MCU main control module is responsible for controlling the power supply of each module to control whether it works and coordinate the normal operation of each module, and uses the Xiaohua platform HC32L190JCTA. The remote transmission module uses a LoRa module, which can transmit data to the system via LoRa when pipeline leakage occurs.

[0029] Furthermore, in this embodiment, the circuit of the hardware amplification and filtering module includes a resistor R1, a capacitor C1, amplifiers U11, U12, U14, and U15. One end of the resistor R1 is connected to one end of the capacitor C1 and the third pin of the amplifier U14, respectively. The other end of the resistor R1 is connected to the control power supply VCC1 of the MCU main control module. The other end of the capacitor C1 is grounded. The first pin of the amplifier U14 is connected to the third pin of the amplifier U15. The first pin of the amplifier U15 is connected to the third pin of the amplifier U11. The first pin of the amplifier U11 is connected to the third pin of the amplifier U12. VCC1 controls the power supply through the MCU main control module. R1 and C1 form a passive filtering network. Amplifier U14 performs impedance matching. Amplifier U15 performs amplification. Amplifiers U11 and U12 form a bandpass filter.

[0030] Furthermore, in this embodiment, the circuit composed of the sound acquisition module, DSP data processing module, storage module, temperature detection module, FPGA / NPU neural network training module, remote transmission module, and MCU main control module includes chips U1, U2, U3, U18B, U18N, U18L, U19, U20, crystal oscillator Y1, crystal oscillator Y2, transistor Q1, and transistor Q2. Chip U1 is connected to chip U2, and chip U2 is also connected to chip U20, chip U18B, switch XS1, and crystal oscillator Y1 respectively. Chip U18B is also connected to chip U19, chip U18N is connected to crystal oscillator Y2, chip U18L is connected to chip U3, and chip U19 is also connected to transistor Q1, transistor Q2, and chip U20 respectively.

[0031] Specifically, in this embodiment, the sound acquisition module is chip U1, model ADC4696; the DSP data processing module is chip U2, model DSP617; the minimum system includes crystal oscillator Y1, clock VJ24MH3S, a 24MHz clock signal, and a reset circuit; the temperature detection module is switch XS1, using a digital thermometer and communicating via I2C; the storage module includes 16MB of FLASH memory and communicates with the DSP data processing module via SPI; the DSP data processing module communicates with the FPGA / NPU neural network training module via UART; and the FPGA / NPU neural network training module is implemented using Verilog programming. The current hardware NPU model includes three chips: U18N, U18B, and U18L, all model EP4CE6E22C8. Chip U3 outputs 1.2V, which is the core voltage of the FPGA. It communicates with the MCU main control module via UART, model NAP1P2S. The remote transmission module is chip U20, model W25Q64BV, which uses LoRa and communicates with the MCU main control module via SPI. The storage module communicates with the DSP data processing module via SPI. The MCU main control module controls P-MOS transistors, transistors Q1 and Q2 to power each module. All transistors are model IRLML5203.

[0032] The following describes the working process of the pipe network leakage sound detection circuit provided in this embodiment of the utility model:

[0033] Step 1: Install several sound sensors and temperature sensors at key locations in the pipeline network to collect sound and temperature signals in real time during pipeline operation.

[0034] Step 2: Preprocess the collected sound and temperature signals to remove interference signals and retain valid feature information;

[0035] Step 3: Extract time-domain features, frequency-domain features, and time-frequency-domain features from the acquired audio signal;

[0036] Step 4: Establish a model of the relationship between temperature and sound signal characteristic parameters, perform temperature compensation, and determine the influence of temperature changes on sound signal characteristic parameters by collecting and analyzing leakage sound signals at different temperatures, and establish a corresponding mathematical model.

[0037] Step 5: Collect known leaked sound signals and comprehensive feature vectors under normal operating conditions as training data to build a deep learning model;

[0038] Step 6: By inputting the data processed in Step 4 into the deep learning model in Step 5, the probability of the output sound signal being a missing sound signal is determined.

[0039] Compared with existing technologies, the traditional sound detection circuit for pipeline leaks described in the above embodiments mainly uses a listening rod or noise leak detector to capture sound changes in the pipeline to determine the location of the leak. This method relies on manual listening and is greatly affected by environmental noise and the operator's experience. Furthermore, it is significantly affected by ambient temperature, as temperature changes affect the speed of sound propagation and attenuation characteristics in the medium, thus impacting the accuracy of leak sound signal detection. This invention features a simple structure and convenient operation. It proposes a pipeline leak sound detection circuit based on a temperature compensation mechanism. By compensating for the frequency and other characteristics of sound based on ambient temperature, it effectively eliminates the influence of temperature changes on the sound signal. Furthermore, it introduces an FPGA-based NPU model, effectively improving the accuracy and reliability of pipeline leak sound detection.

[0040] Obviously, the embodiments described above are merely preferred embodiments of this utility model, and not all embodiments. The accompanying drawings show preferred embodiments of this utility model, but do not limit the patent scope of this utility model. This utility model can be implemented in many different forms; rather, the purpose of providing these embodiments is to provide a more thorough and comprehensive understanding of the disclosure of this utility model. Although this utility model has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing specific embodiments, or make equivalent substitutions for some of the technical features. Any equivalent structures made using the content of this utility model specification and drawings, directly or indirectly applied to other related technical fields, are similarly within the patent protection scope of this utility model.

Claims

1. A pipe network leak sound detection circuit, characterized by, include: The system comprises a sound acquisition probe, a hardware amplification and filtering module, a sound acquisition module, a DSP data processing module, a temperature acquisition module, an FPGA / NPU neural network training module, an MCU main control module, a remote transmission module, and a storage module. These components are sequentially and communicatively connected. The sound acquisition probe, hardware amplification and filtering module, sound acquisition module, DSP data processing module, and FPGA / NPU neural network training module are also communicatively connected to the MCU main control module. The temperature acquisition module is also communicatively connected to the DSP data processing module, and the DSP data processing module is also communicatively connected to the storage module.

2. A leak sound detection circuit for a pipe network according to claim 1, characterised in that, The circuit of the hardware amplification and filtering module includes a resistor R1, a capacitor C1, amplifiers U11, U12, U14, and U15. One end of the resistor R1 is connected to one end of the capacitor C1 and the third pin of the amplifier U14, respectively. The other end of the resistor R1 is connected to the control power supply VCC1 of the MCU main control module. The other end of the capacitor C1 is grounded. The first pin of the amplifier U14 is connected to the third pin of the amplifier U15. The first pin of the amplifier U15 is connected to the third pin of the amplifier U11. The first pin of the amplifier U11 is connected to the third pin of the amplifier U12.

3. A leak sound detection circuit for a pipe network according to claim 2, characterised in that, The circuit comprising the sound acquisition module, DSP data processing module, storage module, temperature detection module, FPGA / NPU neural network training module, remote transmission module, and MCU main control module includes chips U1, U2, U3, U18B, U18N, U18L, U19, U20, crystal oscillator Y1, crystal oscillator Y2, transistor Q1, and transistor Q2. Chip U1 is connected to chip U2. Chip U2 is also connected to chip U20, chip U18B, switch XS1, and crystal oscillator Y1 respectively. Chip U18B is also connected to chip U19. Chip U18N is connected to crystal oscillator Y2. Chip U18L is connected to chip U3. Chip U19 is also connected to transistor Q1, transistor Q2, and chip U20 respectively.

4. The leak sound detection circuit for pipe network according to claim 1, wherein The FPGA / NPU neural network training module uses an FPGA chip, model EP4CE6E22C8.

5. The leak sound detection circuit for pipe network according to claim 1, wherein The MCU main control module is model HC32L190JCTA.

6. The leak sound detection circuit for pipe network according to claim 1, wherein The sound acquisition module is model ADC4696.

7. The leak sound detection circuit for pipe network according to claim 1, wherein The DSP data processing module is model TMS320C6713.

Images