On-line abnormal sound monitoring device and safety monitoring method for valve cooling external cold water cooling tower based on sound sensor

Abstract

The invention relates to the technical field of safety protection, in particular to a valve cooling external cold water cooling tower abnormal sound online monitoring device and safety monitoring method based on a sound sensor, and the device comprises a microphone collection module which is arranged on a target valve cooling external cold water cooling tower and is used for obtaining acoustic signals generated in the operation process of the cooling tower in real time, the acoustic signal is converted into digital audio data; the MCU mainboard module is connected with the microphone acquisition module and is used for receiving the audio data of the microphone acquisition module and realizing feature extraction, model reasoning and logic control; the communication module is used for transmitting processing information of the MCU mainboard module to a mobile terminal to realize online early warning of abnormal sound of the valve cooling external cold water cooling tower, and the device realizes real-time sound monitoring of the cooling tower, judges equipment of which the sound exceeds a normal range, and sends an alarm signal at the terminal to ensure that equipment defects are found as early as possible and treated in advance; defect deterioration is avoided.

Description

Technical Field

[0001] This invention relates to the field of safety protection technology, specifically to an online monitoring device and safety monitoring method for abnormal noises in valve-cooled external cooling water towers based on sound sensors. Background Technology

[0002] The converter valve, a core component of the DC converter station, can remove a large amount of heat through the valve cooling system, thus ensuring its normal operation. The external cooling water tower is a major component of the valve cooling system. It dissipates heat by spraying internal cooling water pipes, and the heat exchanged between the external and internal cooling water is dissipated by a fan. Statistical data from a DC station since its commissioning in 2014 shows that during long-term operation, due to vibration, scaling, rust, or disassembly and assembly during power outages, when the matching belts show abnormal noise or age, maintenance personnel need to tighten and adjust the belts or replace them with spare parts to prevent the belts from falling off or breaking.

[0003] Currently, abnormal defects in cooling towers are discovered through operator inspections, which carries a significant element of chance. Firstly, maintenance requirements dictate that the valve-cooling system be inspected every four days, leaving a four-day gap in inspection time. Secondly, individual inspection standards vary slightly, leading to subjectivity in judging abnormal noises and a lack of quantitative standards. Furthermore, the cooling tower fan speed is automatically adjusted based on the cooling water inlet valve temperature, which is highly dependent on the DC load and ambient temperature. Abnormal noises from the cooling tower can change with the fan speed, making defects even harder to detect. Therefore, defect discovery is somewhat unpredictable. If defects are not detected promptly, the optimal time for intervention may be missed, impacting the cooling effect of the valve-cooling system and potentially affecting the safe and stable operation of high-voltage direct current transmission. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of the prior art by providing an online monitoring device and safety monitoring method for abnormal noises in valve-cooled external cooling water towers based on sound sensors. It collects and analyzes the sound signals of the cooling tower to achieve real-time sound monitoring of the cooling tower, judges equipment whose sound exceeds the normal range, and sends alarm signals to the terminal to ensure early detection of equipment defects, early handling, and prevention of defects from worsening.

[0005] To achieve one of the above objectives, the present invention provides the following technical solution: An online monitoring device for abnormal noise in valve-cooled external cooling water towers based on sound sensors is provided. include A microphone acquisition module is installed on the target valve-cooled external cooling water tower to acquire acoustic signals generated during the operation of the cooling tower in real time and convert the acoustic signals into digital audio data. The MCU motherboard module is connected to the microphone acquisition module and is used to receive audio data from the microphone acquisition module to realize feature extraction, model inference and logic control. The communication module transmits the processing information from the MCU motherboard module to the mobile terminal, enabling online early warning of abnormal noises from the valve-cooled external cooling water tower.

[0006] In some implementations, the microphone acquisition module converts the acquired acoustic signals into digital audio data at a sampling frequency of 10-20 kHz.

[0007] In some implementations, the microphone acquisition module converts the acquired acoustic signals into digital audio data at a sampling frequency of 16 kHz.

[0008] In some implementations, the communication module is a 4G communication module.

[0009] In some implementations, a power module is also included, which provides power to the microphone acquisition module and the MCU motherboard module.

[0010] In some implementations, the power module includes a solar panel and a lithium battery. The solar panel provides power to the microphone acquisition module and the MCU motherboard module during the day and charges the lithium battery.

[0011] The beneficial effects of the present invention, a sound sensor-based online monitoring device for abnormal noise in valve-cooled external cooling water towers, are as follows:

[0012] The present invention relates to an online monitoring device for abnormal noise of valve-cooled external cooling water towers based on sound sensors. It uses a microphone acquisition module to acquire acoustic signals generated during the operation of the target valve-cooled external cooling water tower in real time. The MCU main board module analyzes and judges the acoustic signals to determine whether there is abnormal noise, and feeds back the results in real time, thereby achieving real-time monitoring. This avoids the problems of delay and heavy workload of traditional manual monitoring and is suitable for large-scale applications.

[0013] To achieve the second objective mentioned above, the present invention provides the following technical solution: A safety monitoring method for valve-cooled external cooling water towers is provided, employing the aforementioned online monitoring device for abnormal noise in valve-cooled external cooling water towers based on sound sensors, comprising the following steps: The microphone acquisition module acquires the acoustic signals generated during the operation of the cooling tower in real time and converts the acoustic signals into digital audio data at a set sampling frequency of 16. The MCU motherboard module receives audio data from the microphone acquisition module and simultaneously completes MFCC feature extraction, model inference, and logic control, including: processing the collected audio data for feature processing, inferring a suitable model based on the obtained features, performing logic calculations based on the inferred model, and outputting a classification result, wherein the classification result is that the valve-cooled external cooling water tower is operating normally or that the valve-cooled external cooling water tower is not operating normally. When the classification result indicates that the valve-cooled external cooling water tower is not operating normally, the classification result is transmitted to the mobile terminal and an abnormal noise alarm signal is sent.

[0014] In some implementations, the MCU motherboard module is also connected to an external coordination module and / or decision module, and the MCU motherboard module makes decisions through the external coordination module and / or decision module.

[0015] In some implementations, the model is an AI model.

[0016] The beneficial effects of the safety monitoring method for valve-cooled external cooling water towers of the present invention are as follows:

[0017] The present invention discloses a safety monitoring method for valve-cooled external cooling water towers. It uses a microphone acquisition module to collect abnormal noises generated by the cooling tower and transmits the abnormal noise information to an MCU motherboard module to determine whether the cooling tower is aging or operating abnormally. If there is an abnormal noise problem, it transmits the information to a mobile terminal to trigger an alarm. No manual monitoring is required, and the feedback is timely, ensuring that equipment defects are detected early and dealt with in advance to prevent the defects from worsening. Attached Figure Description

[0018] Figure 1 This is a first-view image of the online monitoring device for abnormal noise of valve-cooled external cooling water tower based on sound sensor in this embodiment.

[0019] Figure 2 This is a second visual view of the online monitoring device for abnormal noises in a valve-cooled external cooling water tower based on a sound sensor, as described in this embodiment.

[0020] Figure 3 This is a flowchart of the safety monitoring method for valve-cooled external cooling water towers in this embodiment.

[0021] Figure Labels

[0022] 1. MCU motherboard module; 2. Communication module; 3. Solar panel; 4. Lithium battery. Detailed Implementation

[0023] Preferred embodiments of the invention will now be described in more detail. While preferred embodiments of the invention have been shown, it should be understood that the invention can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that the invention will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0024] The terminology used in this invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The singular forms “a” and “the” as used in this invention and the appended claims are intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0025] It should be understood that although the terms "first," "second," "third," etc., may be used in this invention to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this invention, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Thus, features defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0026] Currently, the DC converter station is not equipped with an online monitoring system for monitoring abnormal noises from the external cooling water tower. The abnormal noise defects are mainly discovered by operators during inspections, which results in delays and subjectivity in defect discovery.

[0027] To solve the above-mentioned technical problems, the following embodiments are disclosed: Example 1

[0028] This embodiment discloses an online monitoring device for abnormal noise in valve-cooled external cooling water towers based on sound sensors. Please refer to [link to relevant documentation]. Figures 1-2 It includes a microphone acquisition module, which is installed on the target valve-cooled external cooling water tower to acquire acoustic signals generated during the operation of the cooling tower in real time and convert the acoustic signals into digital audio data; Specifically, the microphone acquisition module is installed on the valve-cooled external cooling tower to be monitored, for example, on the surface of the tower body. This allows it to directly acquire the acoustic signal of any abnormal noise from the cooling tower. The microphone acquisition module converts this acoustic signal into digital audio data, which is then used for subsequent calculations and analysis. In practical applications, locations directly impacted by strong airflow should be avoided. Windshields can be installed to reduce wind noise interference, and multiple microphones (such as two diagonally positioned microphones) can be considered for placement. Signal comparison can then improve the signal-to-noise ratio.

[0029] MCU motherboard module 1 is connected to the microphone acquisition module and is used to receive audio data from the microphone acquisition module to realize feature extraction, model inference and logic control; Specifically, the MCU motherboard module 1, as the computing center, can perform calculations on digital audio data to make judgments. Therefore, it can extract features from digital audio data to obtain data features for subsequent identification. Then, it performs model reasoning to obtain a computing model to calculate feature data. Finally, it performs logic control to output results and determine whether there is any abnormal noise.

[0030] For example, raw digital audio signals, such as noise data collected by a microphone, are received and preliminarily processed.

[0031] Filter out environmental noise, such as high-frequency / low-frequency interference, to improve the signal-to-noise ratio. Segment the continuous audio stream into short frames (e.g., 20ms / frame) to facilitate subsequent feature extraction. Enhance high-frequency components and balance the spectrum using a high-pass filter (e.g., coefficient 0.97). Transform high-dimensional audio data into low-dimensional, highly discriminative feature vectors.

[0032] Simulates the characteristics of human hearing, extracts 13-40 dimensional features, and is suitable for mechanical abnormal noises (such as the periodic impact of bearing wear).

[0033] Each frame of audio corresponds to a multi-dimensional feature vector, such as a 40-dimensional MFCC, forming a time series feature matrix.

[0034] A lightweight AI model detects unusual noises that deviate from normal patterns through anomaly scoring. Anomaly probability (e.g., 0.87) or classification results guide the decision-making process.

[0035] Communication module 2 transmits the processing information of the MCU motherboard module 1 to the mobile terminal to realize online early warning of abnormal noises from the valve-cooled external cooling water tower.

[0036] Specifically, the MCU motherboard module 1 transmits the processed information to the mobile terminal, which then provides feedback on the warning information, thereby indicating whether the cooling tower is experiencing operational abnormalities or unusual noises.

[0037] The microphone acquisition module converts the acquired acoustic signals into digital audio data at a sampling frequency of 10~20kHz.

[0038] Preferably, the microphone acquisition module converts the acquired acoustic signal into digital audio data at a sampling frequency of 16kHz, thereby realizing the conversion of the acoustic signal acquired by the microphone acquisition module into digital audio data.

[0039] In this embodiment, the communication module 2 is a 4G communication module 2. In a specific implementation, other communication modules 2 may also be used. This communication module 2 primarily transmits signals from the MCU motherboard module 1 to the mobile terminal for computation.

[0040] In this embodiment, a power module is also included, which provides power to the microphone acquisition module and the MCU motherboard module 1. The power module mainly provides power to the MCU motherboard module 1 and the microphone acquisition module.

[0041] In this embodiment, the power module includes a solar panel 3 and a lithium battery 4. During the day, the solar panel 3 provides power to the microphone acquisition module and the MCU motherboard module 1, and also charges the lithium battery 4.

[0042] Specifically, the power module includes a solar panel 3 and a lithium battery 4. The solar panel 3 can be used during the day and charges the lithium battery 4, which is used at night.

[0043] The aforementioned device consists of an abnormal noise monitoring device and an alarm receiving device. The monitoring device is packaged as follows: a power module, a communication antenna, a microphone acquisition module, a solar main control board, a main control processing module, a solar panel, and a 4G communication module; the alarm receiving device is a personal mobile phone terminal.

[0044] Working principle: The monitoring device module includes: a microphone acquisition module (not shown in the figure), an MCU motherboard module 1, a 4G communication module 2, a solar panel 3, a battery module, and a mobile terminal.

[0045] The microphone acquisition module is responsible for acquiring the acoustic signals generated during the operation of the cooling tower in real time and converting the sound into digital audio data at a sampling frequency of 16kHz.

[0046] MCU mainboard module 1 is the core control unit of the system, responsible for receiving audio data from the microphone, and simultaneously performing MFCC (Mel Frequency Cepstral Coefficients) feature extraction, model inference, and logic control. This chip can handle audio signal processing and real-time operation of the AI ​​model, ultimately outputting a "normal / abnormal" classification result for real-time status monitoring and alarms. The main controller is also responsible for scheduling other peripheral modules, realizing the overall coordination and decision-making functions of the system.

[0047] The power module adopts a hybrid power supply scheme of "3 solar panels + 4 lithium batteries", which powers the device with solar energy and charges the batteries during the day to achieve long-term stable operation. The system adopts a low-power control strategy to make the overall energy consumption of microphone acquisition, MCU inference and communication processes controllable, ensuring that the device can achieve continuous power supply for many years in complex outdoor environments.

[0048] The mobile terminal is used to receive the "abnormal noise" alarm signal sent by the monitoring device to realize real-time monitoring of the cooling tower. If a defect is confirmed on site, the signal can be blocked, and the monitoring device will not send an alarm signal again when monitoring the same audio.

[0049] By diagnosing the operating sound of the cooling tower in the valve cooling system of the DC converter station, the operating status of the cooling tower fan can be monitored in real time. This allows for the early detection and handling of defects, preventing them from worsening. This technology can also be used in similar sound monitoring scenarios. Example 2

[0050] To further illustrate the monitoring method of the valve-cooled external cooling water tower abnormal noise online monitoring device, this embodiment uses the sound sensor-based valve-cooled external cooling water tower abnormal noise online monitoring device described in Embodiment 1. Please refer to [link to Embodiment 1]. Figure 3 The monitoring method includes the following steps: The microphone acquisition module acquires the acoustic signals generated during the operation of the cooling tower in real time and converts the acoustic signals into digital audio data at a set sampling frequency of 16. The MCU motherboard module 1 receives audio data from the microphone acquisition module and simultaneously completes MFCC feature extraction, model inference, and logic control, including: processing the collected audio data for feature processing, inferring a suitable model based on the obtained features, performing logic calculations based on the inferred model, and outputting a classification result, wherein the classification result is that the valve-cooled external cooling water tower is operating normally or the valve-cooled external cooling water tower is not operating normally. When the classification result indicates that the valve-cooled external cooling water tower is not operating normally, the classification result is transmitted to the mobile terminal and an abnormal noise alarm signal is sent.

[0051] In this embodiment, the MCU motherboard module 1 is also connected to an external coordination module and / or a decision module, and the MCU motherboard module 1 makes decisions through the external coordination module and / or decision module.

[0052] In this embodiment, the model is an AI model.

[0053] This embodiment describes a digital device for real-time online monitoring of the cooling tower in the valve-cooled system of a DC converter station. It can monitor the cooling tower's sound in real time, enabling early detection and intervention of equipment defects to prevent escalation. This achieves real-time monitoring of the cooling tower's operation, avoiding delays in defect detection due to gaps in maintenance personnel's inspections or subjective reasons, thus preventing further deterioration. It offers advantages in cost reduction, improved safety, and enhanced environmental friendliness. Utilizing digital methods for real-time monitoring of the cooling tower reduces the workload of maintenance personnel. It transforms the subjective judgment of maintenance personnel regarding defects into quantitative judgment of acoustic signals, improving the accuracy of defect identification.

[0054] For example, to obtain more accurate sound signals, one monitoring device can be installed on each cooling tower; if one sound monitoring device covers three cooling towers, it should be installed on the middle cooling tower to collect as complete a sound signal as possible. The monitoring device has three power supply modes: battery, solar panel, and more. It should be installed in a location exposed to direct sunlight and does not require rain protection. If installed indoors, it can be set to battery or wired power supply. The device can be configured to send relevant alarm signals to multiple mobile terminals simultaneously. The device has an IP5 moisture-proof rating.

[0055] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

[0056] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. An online monitoring device for abnormal noise in a valve-cooled external cooling water tower based on a sound sensor, characterized in that, include A microphone acquisition module is installed on the target valve-cooled external cooling water tower to acquire acoustic signals generated during the operation of the cooling tower in real time and convert the acoustic signals into digital audio data. The MCU motherboard module is connected to the microphone acquisition module and is used to receive audio data from the microphone acquisition module and perform feature extraction, model inference and logic control. The communication module transmits the abnormal noise information of the MCU motherboard module to the mobile terminal.

2. The online monitoring device for abnormal noise of valve-cooled external cooling water tower based on sound sensor according to claim 1, characterized in that, The microphone acquisition module converts the acquired acoustic signals into digital audio data at a sampling frequency of 10~20kHz.

3. The online monitoring device for abnormal noise of valve-cooled external cooling water tower based on sound sensor according to claim 1, characterized in that, The mobile terminal provides online early warnings for abnormal noise information.

4. The online monitoring device for abnormal noise of valve-cooled external cooling water tower based on sound sensor according to claim 1, characterized in that, The communication module is a 4G communication module.

5. The online monitoring device for abnormal noise of valve-cooled external cooling water tower based on sound sensor according to claim 1, characterized in that, It also includes a power module that provides power to the microphone acquisition module and the MCU motherboard module.

6. The online monitoring device for abnormal noise of valve-cooled external cooling water tower based on sound sensor according to claim 5, characterized in that, The power module includes a solar panel and a lithium battery. During the day, the solar panel provides power to the microphone acquisition module and the MCU motherboard module, and also charges the lithium battery.

7. A safety monitoring method for valve-cooled external cooling water towers, characterized in that, The online monitoring device for abnormal noise of valve-cooled external cooling water tower based on sound sensors as described in any one of claims 1 to 6 includes the following steps: The microphone acquisition module acquires the acoustic signals generated during the operation of the cooling tower in real time and converts the acoustic signals into digital audio data at a set sampling frequency of 16. The MCU motherboard module receives audio data from the microphone acquisition module and simultaneously completes MFCC feature extraction, model inference, and logic control, including: processing the collected audio data for feature processing, inferring a suitable model based on the obtained features, performing logic calculations based on the inferred model, and outputting a classification result, wherein the classification result is that the valve-cooled external cooling water tower is operating normally or that the valve-cooled external cooling water tower is not operating normally. When the classification result indicates that the valve-cooled external cooling water tower is not operating normally, the classification result is transmitted to the mobile terminal and an abnormal noise alarm signal is sent.

8. The safety monitoring method for valve-cooled external cooling water towers according to claim 7, characterized in that, The MCU motherboard module is also connected to an external coordination module and / or decision module, and the MCU motherboard module makes decisions through the external coordination module and / or decision module.

9. The safety monitoring method for valve-cooled external cooling water towers according to claim 8, characterized in that, The model is an AI model.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the method as described in any one of claims 7 to 9.

Images