Gas extraction water ring vacuum pump fouling degree on-line detection system and method

Abstract

The application discloses a gas extraction water ring vacuum pump fouling degree online detection system and method, relates to the technical field of vacuum pump fouling degree detection, and comprises a sound signal acquisition module, an excitation control module, a parameter sensing module, a signal processing module, a feature compensation module, a fouling inversion module and a model calibration module; the sound signal acquisition module is arranged on the outer wall of the pump body and is used for acquiring structural vibration signals generated in the operation process and outputting original vibration data; the excitation control module is connected with a piezoelectric excitation device and receives the operation state feedback of the sound signal acquisition module, is used for triggering the piezoelectric excitation device to apply high-frequency pulse signals to the pump shell when the suction negative pressure fluctuation is stable and continuously meets the steady-state condition, and synchronously starts the sound signal acquisition module to collect response signals; and the parameter sensing module is used for monitoring the cooling water inlet / outlet temperature and motor current waveform and outputting environmental and operation parameters.

Description

Technical Field

[0001] This invention relates to the field of vacuum pump scaling degree detection technology, and in particular to an online detection system and method for scaling degree of gas extraction water ring vacuum pumps. Background Technology

[0002] Scaling detection technology for gas extraction water ring vacuum pumps refers to a non-invasive method that, without interrupting equipment operation, obtains quantitative indicators reflecting the thickness and distribution of carbonate deposits on the heat exchange surfaces inside the pump chamber and on the impeller surface, and uses these indicators to assess their impact on pump efficiency, safety, and energy consumption. Therefore, improving the intelligence and safety of vacuum pump scaling detection using advanced technologies is one of the urgent problems to be solved.

[0003] In the field of vacuum pump scaling detection, existing systems attempt to infer scaling trends by monitoring indirect parameters such as motor current, power consumption, and inlet / outlet pressure difference. However, these parameters are affected by various factors such as load fluctuations, voltage instability, and gas volume changes, and have no clear correlation with scaling. This easily leads to false alarms or missed alarms, resulting in low diagnostic confidence. At the same time, the cooling water temperature changes significantly during the operation of water ring vacuum pumps, and the propagation characteristics of sound waves are extremely sensitive to temperature. Most existing acoustic detection methods have not established a temperature compensation mechanism, resulting in large differences in the signals measured at different water temperatures under the same scaling condition, leading to unstable measurement results and poor repeatability. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides an online detection system for the scaling degree of a gas extraction water ring vacuum pump. This addresses the problem that existing systems attempt to infer scaling trends by monitoring indirect parameters such as motor current, power consumption, and inlet / outlet pressure difference. However, these parameters are affected by various factors such as load fluctuations, voltage instability, and gas volume changes, and have no clear correlation with scaling, easily leading to false alarms or missed alarms and low diagnostic confidence. Furthermore, the cooling water temperature changes significantly during the operation of the water ring vacuum pump, and the propagation characteristics of sound waves are extremely sensitive to temperature. Most existing acoustic detection methods lack a temperature compensation mechanism, resulting in large differences in signals measured at different water temperatures under the same scaling condition, leading to unstable measurement results and poor repeatability.

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

[0007] In a first aspect, the present invention provides an online detection system and method for the scaling degree of a gas extraction water ring vacuum pump, comprising:

[0008] The system includes an acoustic signal acquisition module, an excitation control module, a parameter sensing module, a signal processing module, a feature compensation module, a scale inversion module, and a model calibration module.

[0009] The acoustic signal acquisition module is installed on the outer wall of the pump body and is used to acquire the structural vibration signals generated during operation and output the raw vibration data.

[0010] The excitation control module is connected to the piezoelectric excitation device and receives the operating status feedback from the acoustic signal acquisition module. When the suction negative pressure fluctuation is stable and the steady-state condition is continuously met, the piezoelectric excitation device is triggered to apply a high-frequency pulse signal to the pump casing, and the acoustic signal acquisition module is simultaneously started to acquire the response signal.

[0011] The parameter sensing module is used to monitor the inlet / outlet temperature of cooling water and the waveform of motor current, and output environmental and operating parameters.

[0012] The signal processing module receives the raw vibration data output by the acoustic signal acquisition module, combines it with the trigger timing information of the excitation control module, performs filtering and framing processing on the signal, extracts the energy ratio of a specific frequency band and the sound wave propagation attenuation characteristics, and generates primary feature quantities.

[0013] The feature compensation module receives the primary feature quantity output by the signal processing module and the temperature parameter output by the parameter sensing module, dynamically corrects the primary feature quantity according to the influence law of temperature on the sound wave propagation characteristics, and outputs the compensated feature quantity.

[0014] The scaling inversion module receives the compensated feature quantity output by the feature compensation module, calls the built-in scaling thickness mapping model, and calculates and outputs the average scaling thickness of the pump cavity inner wall by combining the model parameters corresponding to the current water temperature range.

[0015] The model calibration module receives the actual scale thickness value input from the outside during system downtime, retrieves the compensated feature quantity sequence used by the scale inversion module in the near period, and adjusts the parameters in the scale thickness mapping model based on the deviation between the actual scale thickness value and the calculation result.

[0016] As a preferred embodiment of the online scaling degree detection system for the gas extraction water ring vacuum pump of the present invention, wherein: the excitation control module determines that the suction negative pressure fluctuation is stable and continuously meets the steady-state condition, the specific steps are as follows:

[0017] Acquire the continuous pressure signal output by the inhalation negative pressure sensor;

[0018] The pressure signal is divided into sliding time windows, each with a length of T;

[0019] Calculate the standard deviation of the pressure signal within each time window;

[0020] When the standard deviation is less than the set threshold for N consecutive windows and the cooling water temperature change rate is lower than the preset limit, the pump body is determined to have entered a steady-state operation state.

[0021] An excitation trigger command is generated and sent to the piezoelectric excitation device.

[0022] As a preferred embodiment of the online detection system for scaling degree of the gas extraction water ring vacuum pump of the present invention, wherein: the piezoelectric excitation device applies a high-frequency pulse signal, specifically in the following process:

[0023] Upon receiving the excitation trigger command, the piezoelectric ceramic sheet is driven to generate mechanical vibration;

[0024] The vibration waveform is a linear frequency modulated signal with a starting frequency of The termination frequency is ;

[0025] The signal duration is This forms a single pulse;

[0026] The pulse is transmitted M times, with an interval of time between each transmission. ;

[0027] All pulses constitute an excitation sequence, which acts on the pump casing surface and excites a structural response.

[0028] As a preferred embodiment of the online scaling degree detection system for the gas extraction water ring vacuum pump of the present invention, wherein: the signal processing module performs coherent averaging processing on the response signal, the specific process being:

[0029] The acoustic signal acquisition module synchronously acquires the response signals corresponding to M excitations, denoted as... ;

[0030] Align all signals according to the excitation start time;

[0031] After alignment, the average response signal is obtained by performing an arithmetic mean at the same time points, and the expression is:

[0032] ;

[0033] in, Indicates the first The response signal of the secondary stimulus, Total number of incentives;

[0034] As input for subsequent feature extraction, it effectively suppresses random noise.

[0035] As a preferred embodiment of the online scaling degree detection system for the gas extraction water ring vacuum pump of the present invention, wherein: the signal processing module extracts the energy ratio of a specific frequency band, and the specific process is as follows:

[0036] right Perform a Fast Fourier Transform to obtain the frequency domain signal. ;

[0037] Divide the frequency domain into two bands, namely the low-frequency band. and high frequency band ;

[0038] The energy integrals within the two frequency bands are calculated separately, and the expressions are as follows:

[0039] ;

[0040] in, Low-frequency energy, High-frequency energy;

[0041] Calculate the energy ratio The expression is:

[0042] ;

[0043] Among them, energy ratio As one of the primary characteristic quantities reflecting the enhancement of low-frequency energy caused by scaling.

[0044] As a preferred embodiment of the online scaling degree detection system for the gas extraction water ring vacuum pump of the present invention, wherein: the signal processing module extracts the sound wave propagation attenuation characteristics, the specific process of which is as follows:

[0045] Simultaneous data acquisition using two AE sensors arranged axially on the pump casing , respectively denoted as and ;

[0046] Measure the amplitude of the main peak of the signal at the positions of the two sensors, and record it as... and ;

[0047] The known distance between the two sensors is ;

[0048] Calculate the sound wave attenuation coefficient per unit distance The expression is:

[0049] ;

[0050] in, The amplitude is measured by the upstream sensor. The amplitude is measured by the downstream sensor. The distance between the two sensors is the straight-line distance.

[0051] As a preferred embodiment of the online scaling degree detection system for the gas extraction water ring vacuum pump of the present invention, wherein: the feature compensation module dynamically corrects the primary feature quantity, and the specific process is as follows:

[0052] The cooling water inlet / outlet temperature is obtained from the parameter sensing module. and ;

[0053] The average water temperature is calculated using the following expression:

[0054] ;

[0055] Based on the interval to which T belongs, the corresponding compensation function is invoked to perform an exponential correction on the energy ratio R, as expressed in the following expression:

[0056] ;

[0057] For attenuation coefficient To perform linear correction, the expression is:

[0058] ;

[0059] in, and For the compensated characteristic quantity, and The temperature sensitivity coefficient was calibrated in the experiment. This is a reference temperature.

[0060] As a preferred embodiment of the online detection system for scaling degree of the gas extraction water ring vacuum pump described in this invention, the model calibration module adjusts the scaling thickness mapping model parameters, specifically as follows:

[0061] During system downtime for maintenance, receive externally input measurements of actual scale thickness. ;

[0062] The retrieved scale inversion module uses the compensated feature sequence in the immediate vicinity, including... and ;

[0063] The inversion model is established, and the expression is:

[0064] ;

[0065] in, To calculate the scale thickness, and Parameters to be updated;

[0066] by To achieve the objective, the weighted least squares method is used to solve for the optimal parameters. and The expression is:

[0067] ;

[0068] in, Time-weighted data is assigned a higher weight.

[0069] In a second aspect, the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein when the computer program is executed by the processor, it implements any step of the online detection system for scaling degree of gas extraction water ring vacuum pump as described in the first aspect of the present invention.

[0070] Thirdly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the online detection system for scaling degree of gas extraction water ring vacuum pump as described in the first aspect of the present invention.

[0071] The beneficial effects of this invention are as follows: By constructing an online detection system integrating acoustic signal acquisition, active excitation control, multi-parameter sensing, feature extraction, temperature compensation, dynamic inversion, and model self-calibration, high-precision, anti-interference, and adaptive monitoring of scaling degree of gas extraction water ring vacuum pumps is achieved. The system triggers high-frequency pulse excitation under steady-state conditions, combines coherent averaging technology to improve the signal-to-noise ratio, extracts specific frequency band energy ratio and acoustic attenuation characteristics as scaling-sensitive indicators, and introduces a dynamic temperature compensation mechanism to eliminate the influence of water temperature drift and improve detection stability. At the same time, the measured scale thickness data during shutdown drives model parameter updates, forming a closed-loop learning mechanism of perception-computation-verification-optimization, enabling the system to have self-correction capability under long-term operation. This effectively solves the problems of misjudgment and missed reporting caused by environmental interference, signal weakening, and model degradation in traditional methods, and improves the safety and intelligent operation and maintenance level of coal mine gas extraction systems. Attached Figure Description

[0072] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0073] Figure 1 This is a schematic diagram of the online detection system and method for scaling degree of gas extraction water ring vacuum pump in Example 1.

[0074] Figure 2 This is a schematic diagram of the module connection architecture of the online detection system for scaling degree of the gas extraction water ring vacuum pump in Example 1. Detailed Implementation

[0075] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0076] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0077] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0078] Example, refer to Figure 1 and Figure 2 As an embodiment of the present invention, this embodiment provides an online detection system and method for the scaling degree of a gas extraction water ring vacuum pump, including:

[0079] The system includes an acoustic signal acquisition module, an excitation control module, a parameter sensing module, a signal processing module, a feature compensation module, a scale inversion module, and a model calibration module.

[0080] The acoustic signal acquisition module is located on the outer wall of the pump body and is used to acquire the structural vibration signals generated during operation and output the raw vibration data.

[0081] Furthermore, the acoustic signal acquisition module includes at least two AE sensors, which are symmetrically arranged on both sides of the impeller cavity along the pump casing axis. The sensor installation positions avoid the flange connection and the reinforcing rib area to reduce the interference of structural discontinuities on the propagation of sound waves.

[0082] The sensor is fixed with a magnetic or welded base to ensure tight coupling with the metal surface of the pump body;

[0083] The acquisition frequency band covers 50kHz to 500kHz, meeting the complete acquisition requirements of high-frequency structural noise and active excitation response signals;

[0084] The acquired raw vibration data is transmitted to the signal processing module via a shielded cable, with a sampling rate of no less than 100 kS / s;

[0085] It should be noted that by symmetrically arranging the AE sensors along the pump casing axis on both sides of the impeller cavity and avoiding the discontinuous areas of the flange and reinforcing rib structure, the reflection, scattering, and attenuation distortion of the sound waves during propagation are effectively reduced, improving the spatial representativeness of the signal and the predictability of the propagation path. The use of magnetic or welded bases to achieve good coupling ensures the efficient transmission of high-frequency vibration signals and avoids signal loss due to poor contact. The high sampling rate and shielded transmission design further ensure the integrity and authenticity of the original vibration data, providing high-quality input for subsequent feature extraction.

[0086] The excitation control module is connected to the piezoelectric excitation device and receives the operating status feedback from the acoustic signal acquisition module. When the suction negative pressure fluctuation is stable and the steady-state condition is continuously met, the piezoelectric excitation device is triggered to apply a high-frequency pulse signal to the pump casing, and the acoustic signal acquisition module is started to acquire the response signal simultaneously.

[0087] Furthermore, the excitation control module determines that the intake negative pressure fluctuation is stable and continuously meets the steady-state conditions. The specific steps are as follows:

[0088] Acquire the continuous pressure signal output by the inhalation negative pressure sensor;

[0089] The pressure signal is divided into sliding time windows, each with a length of T;

[0090] Calculate the standard deviation of the pressure signal within each time window;

[0091] When the standard deviation is less than the set threshold for N consecutive windows and the cooling water temperature change rate is lower than the preset limit, the pump body is determined to have entered a steady-state operation state.

[0092] Generate an excitation trigger command and send it to the piezoelectric excitation device;

[0093] The piezoelectric excitation device applies a high-frequency pulse signal, and the specific process is as follows:

[0094] Upon receiving the excitation trigger command, the piezoelectric ceramic sheet is driven to generate mechanical vibration;

[0095] The vibration waveform is a linear frequency modulated signal with a starting frequency of The termination frequency is ;

[0096] The signal duration is This forms a single pulse;

[0097] The pulse is transmitted M times, with an interval of time between each transmission. ;

[0098] All pulses constitute an excitation sequence, which acts on the pump casing surface to excite the structural response;

[0099] It should be noted that by triggering active excitation only when the suction negative pressure fluctuation is stable and the steady-state condition is continuously met, measurements are avoided during severe disturbances in pump operation or during start-up and shutdown, effectively preventing misjudgments and invalid data acquisition. This control logic, combined with the sliding time window and standard deviation determination method, achieves dynamic and quantitative identification of the operating status, improving the system's adaptive capability. The piezoelectric excitation device and the acoustic signal acquisition module work together to form a one-to-one or multi-to-one detection structure, enhancing the penetrating detection capability of the scale layer on the inner wall of the pump cavity, making the acquired response signal more physically meaningful and analytically valuable.

[0100] The parameter sensing module is used to monitor the inlet / outlet temperature of cooling water and the waveform of motor current, and outputs environmental and operating parameters.

[0101] Furthermore, the temperature sensor in the parameter sensing module uses a PT100 platinum resistance thermometer, which is installed on the straight sections of the cooling water inlet and outlet pipes respectively. The distance between the measuring point and the pump body interface is not less than 3 times the pipe diameter to avoid local eddy currents affecting the accuracy of temperature measurement.

[0102] The temperature signal is converted into a standard 4–20mA signal by an isolation transmitter and then connected to the edge computing unit.

[0103] The motor current signal is acquired through a high-precision current transformer with a sampling frequency of not less than 10kS / s, and the current harmonic components are recorded simultaneously.

[0104] All parameter data are kept in time synchronization with the vibration signal to form a multi-source sensor data sequence, providing an environmental correlation basis for subsequent feature compensation and model calibration.

[0105] It should be noted that using a PT100 platinum resistance thermometer as a temperature sensor and installing it in a straight pipe section far from the pump body interface can accurately reflect the actual cooling water temperature entering and leaving the pump body, avoiding temperature measurement lag and deviation caused by local eddy currents or thermal inertia. The isolation transmitter effectively suppresses electromagnetic interference in the industrial field, ensuring signal transmission stability. It simultaneously acquires high sampling rate motor current signals and records harmonic components, which not only provides a basis for energy consumption analysis, but also serves as an auxiliary parameter to verify the load change trend caused by scaling, realizing cross-verification of multi-source information and improving the overall diagnostic confidence.

[0106] The signal processing module receives the raw vibration data output by the acoustic signal acquisition module, combines it with the trigger timing information of the excitation control module, performs filtering and framing processing on the signal, extracts the energy ratio of a specific frequency band and the sound wave propagation attenuation characteristics, and generates primary characteristic quantities.

[0107] Furthermore, the signal processing module performs coherent averaging on the response signal, the specific process of which is as follows:

[0108] The acoustic signal acquisition module synchronously acquires the response signals corresponding to M excitations, denoted as... ;

[0109] Align all signals according to the excitation start time;

[0110] After alignment, the average response signal is obtained by performing an arithmetic mean at the same time points, and the expression is:

[0111] ;

[0112] in, Indicates the first The response signal of the secondary stimulus, Total number of incentives;

[0113] As input for subsequent feature extraction, it effectively suppresses random noise;

[0114] The signal processing module extracts the energy ratio of a specific frequency band. The specific process is as follows:

[0115] right Perform a Fast Fourier Transform to obtain the frequency domain signal. ;

[0116] Divide the frequency domain into two bands, namely the low-frequency band. and high frequency band ;

[0117] The energy integrals within the two frequency bands are calculated separately, and the expressions are as follows:

[0118] ;

[0119] in, Low-frequency energy, High-frequency energy;

[0120] Calculate the energy ratio The expression is:

[0121] ;

[0122] Among them, energy ratio As one of the primary characteristic quantities reflecting the enhancement of low-frequency energy caused by scaling;

[0123] The signal processing module extracts the sound wave propagation attenuation features. The specific process is as follows:

[0124] Simultaneous data acquisition using two AE sensors arranged axially on the pump casing , respectively denoted as and ;

[0125] Measure the amplitude of the main peak of the signal at the positions of the two sensors, and record it as... and ;

[0126] The known distance between the two sensors is ;

[0127] Calculate the sound wave attenuation coefficient per unit distance The expression is:

[0128] ;

[0129] in, The amplitude is measured by the upstream sensor. The amplitude is measured by the downstream sensor. The straight-line distance between the two sensors;

[0130] It should be noted that the coherent averaging technique, by performing time alignment and arithmetic averaging on multiple repeated excitation response signals, suppresses the incoherent components of environmental noise, electrical interference, and random vibrations, highlighting the inherent response characteristics of the pump body structure to excitation, and improving the discernibility of weak acoustic signals. The frequency band division is determined based on a large amount of experimental data. The energy enhancement in the low-frequency band is closely related to the stiffness change caused by scaling, while the high-frequency band reflects the background level under clean conditions. The ratio of the two constitutes a characteristic parameter that is sensitive to and stable to scaling. The attenuation coefficient is calculated based on the dual-sensor time difference method, which can quantify the energy loss of sound waves in the propagation path, directly correlate with the thickness of the scaling layer, and enhance the physical interpretability of the inversion model.

[0131] The feature compensation module receives the primary feature quantity output by the signal processing module and the temperature parameter output by the parameter sensing module. Based on the influence of temperature on the sound wave propagation characteristics, it dynamically corrects the primary feature quantity and outputs the compensated feature quantity.

[0132] Furthermore, the feature compensation module dynamically corrects the initial feature values. The specific process is as follows:

[0133] The cooling water inlet / outlet temperature is obtained from the parameter sensing module. and ;

[0134] The average water temperature is calculated using the following expression:

[0135] ;

[0136] Based on the interval to which T belongs, the corresponding compensation function is invoked to perform an exponential correction on the energy ratio R, as expressed in the following expression:

[0137] ;

[0138] For attenuation coefficient To perform linear correction, the expression is:

[0139] ;

[0140] in, and For the compensated characteristic quantity, and The temperature sensitivity coefficient was calibrated in the experiment. For reference temperature;

[0141] It should be noted that by dynamically correcting the primary characteristic quantities with temperature, the measurement deviation caused by the drift of sound wave propagation speed and the fluctuation of material elastic modulus due to changes in cooling water temperature is effectively eliminated. A piecewise compensation strategy is adopted and exponential and linear functions are introduced to correct the energy ratio and attenuation coefficient respectively, taking into account the nonlinear differences in the temperature response of different characteristics. The compensation mechanism enables the system to maintain consistent detection accuracy under different seasons and different mining area water temperature conditions, thereby improving the system's environmental adaptability and long-term stability.

[0142] The scaling inversion module receives the compensated feature quantity output by the feature compensation module, calls the built-in scaling thickness mapping model, and calculates and outputs the average scaling thickness of the pump cavity inner wall by combining the model parameters corresponding to the current water temperature range.

[0143] Furthermore, the scale thickness mapping model divides the water temperature range into multiple ranges based on historical calibration data, with each range configured with an independent set of inversion parameters;

[0144] The model input consists of the energy ratio and acoustic attenuation coefficient after temperature compensation, and the output is a continuous numerical estimate of the fouling thickness.

[0145] The inversion process adopts a weighted fusion strategy. When the harmonic content of the motor current increases synchronously, the acoustic features are given higher weights to improve the confidence level of the judgment.

[0146] The output results are uploaded to the monitoring system in both digital and analog formats, along with the water temperature range identifier and model version number on which the calculation was based, to ensure the traceability of the detection process.

[0147] It should be noted that the scale thickness mapping model is configured with independent parameters according to the water temperature range, which realizes refined modeling of complex operating conditions. During the inversion process, a weighted fusion strategy is implemented in combination with the changes in motor current harmonics. When the trends of electrical characteristics and acoustic characteristics are consistent, the output confidence is increased; otherwise, an early warning mechanism is triggered, which enhances the robustness of the judgment. The output results are accompanied by water temperature range identifiers and model version numbers, which facilitates the tracing of historical data and the analysis of model evolution trends. It supports the integration of remote operation and maintenance with intelligent diagnostic platforms, thereby improving the manageability of the system.

[0148] The model calibration module receives the actual scale thickness value from external input during system downtime, retrieves the compensated feature quantity sequence used by the scale inversion module in the near period, and adjusts the parameters in the scale thickness mapping model based on the deviation between the actual scale thickness value and the calculation result.

[0149] Furthermore, the model calibration module adjusts the scaling thickness mapping model parameters, specifically as follows:

[0150] During system downtime for maintenance, receive externally input measurements of actual scale thickness. ;

[0151] The retrieved scale inversion module uses the compensated feature sequence in the immediate vicinity, including... and ;

[0152] The inversion model is established, and the expression is:

[0153] ;

[0154] in, To calculate the scale thickness, and Parameters to be updated;

[0155] by To achieve the objective, the weighted least squares method is used to solve for the optimal parameters. and The expression is:

[0156] ;

[0157] in, Time-weighted data is assigned a higher weight.

[0158] It should be noted that the model calibration module updates the inversion parameters using the weighted least squares method, giving higher weight to recent data. This enables the model to quickly respond to changes in water quality and the effects of long-term aging pumps, achieving self-learning and self-adaptation. The parameter update process is driven by real maintenance data, ensuring that the model always closely reflects the actual physical state. This mechanism breaks through the limitations of traditional static models that are prone to degradation, extends the system's calibration-free operation cycle, reduces maintenance costs, and improves the intelligence level and long-term reliability of the online monitoring system.

[0159] This embodiment also provides a computer device suitable for an online detection system for the scaling degree of a gas extraction water ring vacuum pump, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize the online detection system for the scaling degree of a gas extraction water ring vacuum pump as proposed in the above embodiment.

[0160] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0161] This embodiment also provides a storage medium on which a computer program is stored. When executed by a processor, the program implements the online detection system for scaling degree of a gas extraction water ring vacuum pump as proposed in the above embodiment. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0162] In summary, this invention constructs an online detection system integrating acoustic signal acquisition, active excitation control, multi-parameter sensing, feature extraction, temperature compensation, dynamic inversion, and model self-calibration. This system achieves high-precision, anti-interference, and adaptive monitoring of scaling on gas extraction water-ring vacuum pumps. Under steady-state conditions, the system triggers high-frequency pulse excitation, combines coherent averaging technology to improve the signal-to-noise ratio, extracts specific frequency band energy ratios and acoustic attenuation characteristics as scaling-sensitive indicators, and introduces a dynamic temperature compensation mechanism to eliminate the influence of water temperature drift, improving detection stability. Simultaneously, by using measured scale thickness data during downtime to drive model parameter updates, a closed-loop learning mechanism of perception-computation-verification-optimization is formed, enabling the system to possess self-calibration capabilities under long-term operation. This effectively solves the problems of misjudgment and missed reporting caused by environmental interference, signal weakening, and model degradation in traditional methods, thereby improving the safety and intelligent operation and maintenance level of coal mine gas extraction systems.

[0163] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A gas extraction water ring vacuum pump fouling degree on-line detection system, characterized in that: The application relates to a pump scale thickness inversion method and device. The application comprises an acoustic signal acquisition module, an excitation control module, a parameter sensing module, a signal processing module, a feature compensation module, a scale inversion module and a model calibration module. The acoustic signal acquisition module is arranged on the outer wall of a pump body and is used for acquiring structural vibration signals generated in the running process and outputting original vibration data. The excitation control module is connected with a piezoelectric excitation device and receives the running state feedback of the acoustic signal acquisition module, is used for triggering the piezoelectric excitation device to apply high-frequency pulse signals to the pump shell when the suction negative pressure fluctuation is stable and continuously meets the steady-state condition, and synchronously starts the acoustic signal acquisition module to collect response signals. The parameter sensing module is used for monitoring the cooling water inlet / outlet temperature and motor current waveform and outputting environmental and running parameters. The signal processing module receives the original vibration data output by the acoustic signal acquisition module, combines the trigger timing information of the excitation control module, filters and frames processes the signals, extracts specific frequency band energy ratios and sound wave propagation attenuation features, and generates primary feature quantities. The feature compensation module receives the primary feature quantities output by the signal processing module and the temperature parameters output by the parameter sensing module, dynamically corrects the primary feature quantities according to the influence law of temperature on the sound wave propagation characteristics, and outputs compensated feature quantities. The scale inversion module receives the compensated feature quantities output by the feature compensation module, calls a built-in scale thickness mapping model, combines the model parameters corresponding to the current water temperature interval, calculates the average scale thickness of the inner wall of the pump cavity and outputs the average scale thickness. The model calibration module receives the actual scale thickness value input from outside during system shutdown, retrieves the compensated feature quantity sequence used by the scale inversion module in the adjacent period, adjusts the parameters in the scale thickness mapping model based on the deviation between the actual scale thickness value and the calculation result.

2. The gas extraction water ring vacuum pump fouling degree online detection system of claim 1, wherein: The excitation control module judges whether the suction negative pressure fluctuation is stable and continuously meets the steady-state condition, and the specific steps are as follows: A continuous pressure signal output by a suction negative pressure sensor is acquired. The pressure signal is divided by a sliding time window, and the window length is T. The standard deviation of the pressure signal in each time window is calculated. When the standard deviation is less than a set threshold value for N consecutive windows and the cooling water temperature change rate is lower than a preset limit value, it is determined that the pump body enters a steady-state running state. An excitation trigger instruction is generated and sent to the piezoelectric excitation device.

3. The gas extraction water ring vacuum pump fouling degree on-line detection system of claim 2, wherein: The piezoelectric excitation device applies high-frequency pulse signals, and the specific process is as follows: After receiving the excitation trigger instruction, a piezoelectric ceramic piece is driven to generate mechanical vibration. The vibration waveform is a linear frequency modulation signal, the initial frequency is , and the terminal frequency is ; The signal duration is , forming a single pulse; The pulse is repeated M times, each time separated by a time interval of ; All pulses constitute an excitation sequence and act on the surface of the pump shell to excite structural response.

4. The gas extraction water ring vacuum pump fouling degree online detection system of claim 3, wherein: The signal processing module performs coherent average processing on the response signal, and the specific process is as follows: The sound signal collecting module synchronously collects the response signals corresponding to the M excitations, denoted as ; All signals are aligned according to the excitation starting time. After alignment, arithmetic average is performed on the same time points to obtain an average response signal, and the expression is as follows: ； wherein, represents the response signal of the excitation, is the total number of excitations; suppresses random noise as input for subsequent feature extraction.

5. The gas extraction water ring vacuum pump fouling degree online detection system of claim 4, wherein: The signal processing module extracts the specific frequency band energy ratio, and the specific process is as follows: ;​​ Two frequency bands are divided in the frequency domain, respectively, low frequency band and high frequency band ; The energy integrals in the two frequency bands are calculated respectively, and the expression is as follows: ； wherein, is low band energy, is high band energy; Computing the energy ratio , the expression is: ； wherein the energy ratio as one of the primary features reflecting the low-frequency energy enhancement due to fouling.

6. The gas extraction water ring vacuum pump fouling degree online detection system of claim 5, wherein: The signal processing module extracts the sound wave propagation attenuation feature, and the specific process is as follows: Two AE sensors are arranged axially on the pump shell to collect simultaneously , respectively denoted and ; The amplitudes of the main peaks of the signals at the positions of the two sensors are measured, denoted as and ; The known two-sensor spacing is ; Computing an acoustic attenuation coefficient within a unit distance , the expression is: ； wherein, is the amplitude measured by the upstream sensor, is the amplitude measured by the downstream sensor, is the straight-line distance between the two sensors.

7. The gas extraction water ring vacuum pump fouling degree online detection system of claim 6, wherein: The feature compensation module dynamically corrects the primary feature quantities, and the specific process is as follows: acquiring the inlet / outlet temperature of the cooling water output by the parameter sensor module with ; The average water temperature is calculated, and the expression is as follows: ； According to the corresponding compensation function called according to the interval of T, the energy ratio R is exponentially modified, and the expression is: ； to the attenuation coefficient linear correction is made, the expression being: ； wherein, and is a compensated feature quantity, and is a temperature sensitivity coefficient calibrated by experiment, is a reference temperature.

8. The gas extraction water ring vacuum pump fouling degree online detection system of claim 7, wherein: The model calibration module adjusts the fouling thickness mapping model parameters, and the specific process is: During system shutdown for maintenance, receiving an actual scale thickness measurement value from an external input ; The search scaling inversion module searches for a sequence of compensated feature quantities used by the scaling inversion module in a proximate time period, including and ; An inversion model is established, and the expression is: ； wherein, to calculate the scale thickness, and is the parameter to be updated; To this end, the weighted least squares method is used to solve the optimal parameters The expression is and ​ ； wherein, is a time weight, giving higher weight to more recent data.

9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that: The processor executes the computer program to realize the steps of the gas extraction water ring vacuum pump fouling degree online detection system of any one of claims 1-8.

10. A computer readable storage medium having stored thereon a computer program, characterized in that: The computer program is executed by the processor to realize the steps of the gas extraction water ring vacuum pump fouling degree online detection system of any one of claims 1-8.

Images