Method, device and system for acoustic monitoring of the operating state of a column internal

Abstract

This invention provides a method, apparatus, and system for acoustic monitoring of the operating status of internal components of a tower, belonging to the field of acoustic monitoring technology. The method includes: acquiring acoustic signals of the internal components of the tower during a certain operating time; obtaining acoustic waveform data and contour maps of the internal components during that operating time based on the acoustic signals; determining whether there are any abnormal points in the internal components during that operating time based on the acoustic waveform data or the contour maps; if abnormal points are determined to exist, determining the operating status of the internal components during that operating time based on the contour maps, wherein the operating status includes normal operation and abnormal operation. This invention has the advantage of accurately monitoring abnormalities occurring within the internal components of a tower and identifying changes in the operating status of the internal components caused by these abnormalities, thereby scientifically assessing the operating status of the internal components and ensuring safe production of the internal components.

Description

Technical Field

[0001] This invention relates to the field of acoustic monitoring technology, specifically to an acoustic monitoring method for the operating status of internal components of a tower, an acoustic monitoring device for the operating status of internal components of a tower, an acoustic monitoring system for the operating status of internal components of a tower, an electronic device, and a readable storage medium. Background Technology

[0002] The operational quality of tower equipment directly impacts the economic benefits of petrochemical enterprises. Current technologies for diagnosing tower equipment malfunctions primarily include process simulation and online measurement of process parameters. Process simulation enables optimized control and operation of chemical processes, but its successful application presupposes that the tower equipment's structure is "normal." When unpredictable mechanical failures occur in the tower due to scaling, corrosion, vibration, overload, or other reasons, or when operating conditions exceed the model's prediction range, it becomes difficult to accurately determine whether the tower's operating status is normal. Online testing technologies using process parameters such as temperature, pressure, flow rate, and composition can only provide superficial observations of the tower equipment's operating status. Once mechanical or operational malfunctions occur, these conventional detection methods struggle to pinpoint the root cause. While gamma-ray fault scanning technology, used for "seeing through" equipment, can diagnose internal structural faults in tower equipment, determining the location and extent of the fault, and serving as a tool for process optimization and online maintenance, it cannot be used for real-time monitoring of the tower's internal components due to radiation effects.

[0003] Therefore, there is a lack of effective online real-time monitoring technology in the existing technology to detect the operating status of tower equipment. Summary of the Invention

[0004] The purpose of this invention is to provide an acoustic monitoring method, device, and system for the operating status of internal components of a tower, so as to at least solve the problem of the lack of effective online real-time monitoring technology in the prior art for detecting the operating status of internal components of a tower.

[0005] To achieve the above objectives, a first aspect of the present invention provides an acoustic monitoring method for the operating status of internal components of a tower, the method comprising:

[0006] Acquire acoustic signals from the internal components of the tower over a period of time during operation;

[0007] Based on the acoustic signals, acoustic waveform data and contour maps of the internal components of the tower during the operating time of that period are obtained.

[0008] Based on the acoustic waveform data or the contour map, determine whether there are any abnormal points in the internal components of the tower during the operating period.

[0009] If it is determined that there are abnormal points in the internal components of the tower during the operating period, the operating status of the internal components of the tower during the operating period is determined based on the contour map. The operating status includes normal operation and abnormal operation.

[0010] Optionally, based on the acoustic signal, a contour map is obtained for the duration of the operation, including:

[0011] The total duration of a single signal is obtained based on the sampling rate and sampling length of the acoustic signal;

[0012] The total duration of a single signal is divided into frames and transformed by time and frequency to obtain the frame frequency, the time point for spectrum analysis, and the energy spectral density.

[0013] Based on the frame frequency, spectral analysis time point, and energy spectral density, the distribution of contour maps of the corresponding areas of the time-frequency intensity cloud map is extracted to obtain the contour maps of the internal components of the tower during the operating time of that period.

[0014] Optionally, based on the acoustic waveform data or the contour map, determine whether there are any anomalies during the specified operating time, including:

[0015] The acoustic waveform data is used as input to the first anomaly detection model to determine the anomaly detection result, or

[0016] The contour map is used as input to the second anomaly detection model to determine the anomaly detection result.

[0017] Optionally, the method further includes:

[0018] Obtain a first training dataset, which includes historical acoustic waveform data;

[0019] Based on the first training dataset and the autoencoder, a first anomaly detection model is trained.

[0020] Obtain a second training dataset, which includes historical contour maps;

[0021] Based on the second training dataset and the autoencoder, a second anomaly detection model is trained.

[0022] Optionally, if it is determined that there are abnormal points in the internal components of the tower during this operating period, the operating status of the internal components of the tower during this operating period is determined based on the contour map, including:

[0023] If the contour map after the anomaly point is not in a steady state, then the internal components of the tower are determined to be in an abnormal operating state.

[0024] Optionally, if it is determined that there are abnormal points in the internal components of the tower during this operating period, the operating status of the internal components of the tower during this operating period is determined based on the contour map, including:

[0025] If the contour map after the anomaly point is in a steady state, the operating status of the internal components of the tower can be determined based on the degree of deviation between the contour map before the anomaly point and the contour map after the anomaly point.

[0026] Optionally, based on the degree of deviation between the contour maps before and after the anomaly point, the operating status of the tower's internal components can be determined, including:

[0027] If the deviation is less than or equal to the preset threshold, the operating status of the internal components of the tower is determined to be normal operation;

[0028] If the deviation exceeds the preset threshold, the internal components of the tower are determined to be in an abnormal operating state.

[0029] Optionally, the degree of deviation is calculated using the following formula:

[0030]

[0031] Where MSE represents the degree of deviation; Y i A contour map showing the area in front of the anomaly points; This is a contour map following the outlier points.

[0032] A second aspect of the present invention provides an acoustic monitoring device for the operating status of internal components of a tower, the device comprising:

[0033] The data acquisition module is used to acquire acoustic signals of the internal components of the tower over a certain period of time.

[0034] The data conversion module is used to obtain acoustic waveform data and contour maps for the specified operating time based on the acoustic signal.

[0035] The anomaly detection module is used to determine whether there are any anomalies in the internal components of the tower during the operating time period, based on the acoustic waveform data or the contour map.

[0036] The operating status determination module is used to determine the operating status of the internal components of the tower during the operating period based on the contour map when it is determined that there are abnormal points in the internal components of the tower during the operating period. The operating status includes normal operation and abnormal operation.

[0037] A third aspect of the present invention provides an acoustic monitoring system for the operating status of internal components of a tower, the system comprising:

[0038] Multiple acoustic sensors are spaced apart on the wall of the tower.

[0039] The aforementioned acoustic monitoring device for the operating status of internal components of the tower is electrically connected to the acoustic sensor.

[0040] A fourth aspect of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described method for acoustic monitoring of the operating status of internal components of a tower.

[0041] On the other hand, the present invention provides a readable storage medium storing instructions for causing a machine to perform the above-described acoustic monitoring method for the operating status of tower internal components.

[0042] This technical solution obtains acoustic waveform data and contour maps of the internal components of the tower during a certain operating time by using acoustic signals from the internal components. Based on the acoustic waveform data or contour maps, it determines whether there are any abnormal points in the internal components during that operating time. Furthermore, if abnormal points are found, the operating status of the internal components during that operating time is determined based on the contour maps. This enables accurate real-time monitoring of abnormalities occurring within the internal components and identification of changes in the operating status of the internal components caused by these abnormalities, thereby scientifically assessing the operating status of the internal components and ensuring their safe production.

[0043] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description section. Attached Figure Description

[0044] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings:

[0045] Figure 1 This is a flowchart of the acoustic monitoring method for the operating status of internal components of a tower provided by the present invention;

[0046] Figure 2 This is a flowchart of determining contour maps based on acoustic signals provided by the present invention;

[0047] Figure 3 This is a schematic diagram of the acoustic monitoring device for the operating status of internal components of a tower provided by the present invention;

[0048] Figure 4 This is a structural schematic diagram of the acoustic monitoring system for the operating status of internal components of a tower provided by the present invention.

[0049] Explanation of reference numerals in the attached figures

[0050] 10 - Data acquisition module; 20 - Data conversion module;

[0051] 30 - Anomaly detection module; 40 - Running status determination module;

[0052] 51-Tower device; 52-Acoustic sensor;

[0053] 53-Acoustic monitoring device for the operating status of internal components of tower. Detailed Implementation

[0054] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0055] In the embodiments of the present invention, unless otherwise stated, directional terms such as "up," "down," "left," and "right" generally refer to the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship in which the product of the invention is usually placed when in use.

[0056] The terms “first”, “second”, etc., are used only to distinguish descriptions and should not be interpreted as indicating or implying relative importance.

[0057] The terms "parallel" and "perpendicular" do not mean that the components must be absolutely parallel or perpendicular, but rather that they can be slightly tilted. For example, "parallel" simply means that its direction is more parallel than "perpendicular," not that the structure must be completely parallel, but that it can be slightly tilted.

[0058] The terms "horizontal," "vertical," and "sag" do not imply that a component must be absolutely horizontal, vertical, or sagging, but rather that it can be slightly tilted. For example, "horizontal" simply means that its direction is more horizontal than "vertical," not that the structure must be completely horizontal, but can be slightly tilted.

[0059] Furthermore, terms like "roughly" and "basically" are used to indicate that the content does not require absolute precision, but rather allows for a certain degree of deviation. For example, "roughly equal" does not simply mean absolute equality; in actual production and operation, achieving absolute "equality" is difficult, and a certain degree of deviation is generally present. Therefore, besides absolute equality, "roughly equal to" also includes the aforementioned situation where a certain degree of deviation exists. Using this as an example, in other cases, unless otherwise specified, terms like "roughly" and "basically" have similar meanings.

[0060] In the description of this invention, it should also be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0061] Figure 1 This is a flowchart of the acoustic monitoring method for the operating status of internal components of a tower provided by the present invention; Figure 2 This is a flowchart of determining contour maps based on acoustic signals provided by the present invention; Figure 3 This is a schematic diagram of the acoustic monitoring device for the operating status of internal components of a tower provided by the present invention; Figure 4 This is a structural schematic diagram of the acoustic monitoring system for the operating status of internal components of a tower provided by the present invention.

[0062] Example 1

[0063] like Figure 1 As shown, this invention provides an acoustic monitoring method for the operating status of internal components of a tower, the method comprising:

[0064] Step 1: Acquire acoustic signals from the internal components of the tower over a period of time during operation;

[0065] Specifically, in this embodiment, the acoustic signal is acquired by an acoustic sensor.

[0066] Step 2: Based on the acoustic signal, obtain the acoustic waveform data and contour map of the internal components of the tower during this operating period;

[0067] Specifically, the internal components of the tower include a tray or a floating valve; the acoustic waveform data is a graphical representation of the amplitude of sound, which is obtained by superimposing simple sine waves of different amplitudes and phases at various frequencies. The horizontal axis of the waveform graph is time, and the vertical axis is amplitude, representing the change of the total amplitude of the superimposed sine waves of all frequencies over time.

[0068] Furthermore, in step two, as Figure 2 As shown, based on the acoustic signal, a contour map of the operating time segment is obtained, including:

[0069] Step 201: Based on the sampling rate and sampling length of the acoustic signal, obtain the total duration of a single signal;

[0070] Step 202: Perform frame processing and time-frequency transformation on the total duration of a single signal to obtain the frame frequency, the time point for spectrum analysis, and the energy spectral density;

[0071] Step 203: Based on the frame frequency, the time point of the spectrum analysis, and the energy spectral density, extract the distribution of contour maps of the corresponding areas of the time-frequency intensity cloud map to obtain the contour maps of the internal components of the tower during the operating time of that period.

[0072] Specifically, the acoustic signature distribution feature extraction is performed by dividing and calculating the total duration of a single signal based on the acoustic signal sampling rate and sampling length. Statistical analysis of the signal is used to determine the sampling locations of stationary signals, followed by frame segmentation. Through time-frequency transformation, the frame frequency, spectral analysis time points, and energy spectral density are calculated. Then, the calculation results are used to extract the distribution of contour maps of the corresponding areas in the time-frequency intensity cloud map, ultimately obtaining the contour maps of the tower's internal components during that operating period.

[0073] Step 3: Based on the acoustic waveform data or the contour map, determine whether there are any abnormal points in the internal components of the tower during this operating period;

[0074] Furthermore, based on the acoustic waveform data or the contour map, determine whether there are any anomalies during this operating time period, including:

[0075] The acoustic waveform data is used as input to the first anomaly detection model to determine the anomaly detection result, or

[0076] The contour map is used as input to the second anomaly detection model to determine the anomaly detection result.

[0077] Specifically, by using a pre-trained first anomaly detection model to determine the anomaly detection result, or by using a pre-trained second anomaly detection model to determine the anomaly detection result, the accuracy of the detection result can be guaranteed.

[0078] Furthermore, the method also includes:

[0079] Obtain a first training dataset, which includes historical acoustic waveform data;

[0080] Based on the first training dataset and the autoencoder, a first anomaly detection model is trained.

[0081] Obtain a second training dataset, which includes historical contour maps;

[0082] Based on the second training dataset and the autoencoder, a second anomaly detection model is trained.

[0083] Specifically, the first training dataset includes historical acoustic waveform data obtained from historical acoustic signals and a second training dataset. Obtaining historical acoustic waveform data from historical acoustic signals is prior art known to those skilled in the art and will not be elaborated here. The second training dataset includes historical contour maps obtained from historical acoustic signals. The steps for obtaining historical contour maps from historical acoustic signals are the same as described above and will not be elaborated here. Sliding window sampling is performed on the data obtained from the first and second training datasets. The window size is S, and the overlap between windows is A. The dataset is divided into training and test sets, with the training set accounting for 50%-80%.

[0084] This autoencoder learns the encoding format of "normal data," so when a dataset is provided to it, it encodes and decodes it according to this format. If the error between the decoded dataset and the input dataset is within a certain range, the input dataset is considered "normal"; otherwise, it is considered "abnormal." After determining a threshold, it can be assumed that if the error after decoding a new dataset exceeds that threshold, it is considered abnormal data.

[0085] In step three, when determining whether there are any abnormal points in the internal components of the tower during the operating time, the start time of the abnormal point can also be determined simultaneously.

[0086] Step 4: If it is determined that there are abnormal points in the internal components of the tower during this operating period, then based on the contour map, determine the operating status of the internal components of the tower during this operating period, including normal operation and abnormal operation.

[0087] In this embodiment, after the sudden abnormal event ends, the airflow state inside the tower will change, causing a change in the airflow acoustic signal. That is, the sudden abnormal event leads to a change in the operating state (abnormal response) inside the tower, but the change in the airflow acoustic signal is weak, and the subtle abnormal change is difficult to identify. To address this problem, a soundprint distribution feature extraction method is used to enhance the signal features and improve the accuracy.

[0088] Furthermore, if it is determined that there are abnormal points in the internal components of the tower during this operating period, then based on the contour map, the operating status of the internal components of the tower during this operating period is determined, including:

[0089] If the contour map after the anomaly point is not in a steady state, then the internal components of the tower are determined to be in an abnormal operating state.

[0090] Specifically, in this embodiment, after the sudden abnormal event ends, the airflow state inside the tower will change, causing a change in the airflow acoustic signal. That is, the sudden abnormal event leads to a change in the operating state (abnormal response) inside the tower, but the change in the airflow acoustic signal is weak, and the subtle abnormal change is difficult to identify. To address this problem, a sound signature distribution feature extraction method is used to enhance the signal features and improve accuracy. Specifically, the steady state after the abnormal point is determined as follows: the difference between several consecutive signals located at the abnormal point is judged. If the difference between several consecutive signals is less than a preset difference, it proves that the operating state of the internal components of the tower has reached a new steady state after the abnormal point. If there is a difference between signals that is not less than the preset difference, it proves that the operating state of the internal components of the tower is not in a steady state after the abnormal point. Therefore, it can be determined that there is an abnormality in the internal components of the tower.

[0091] Furthermore, if it is determined that there are abnormal points in the internal components of the tower during this operating period, then based on the contour map, the operating status of the internal components of the tower during this operating period is determined, including:

[0092] If the contour map after the anomaly point is in a steady state, the operating status of the internal components of the tower can be determined based on the degree of deviation between the contour map before the anomaly point and the contour map after the anomaly point.

[0093] Furthermore, based on the degree of deviation between the contour maps before and after the anomaly points, the operating status of the tower's internal components is determined, including:

[0094] If the deviation is less than or equal to the preset threshold, the operating status of the internal components of the tower is determined to be normal operation;

[0095] If the deviation exceeds the preset threshold, the internal components of the tower are determined to be in an abnormal operating state.

[0096] Specifically, in this embodiment, when an abnormal signal is detected, the current time t1 is recorded, where t1 is the point where the abnormal event occurs. From the current time t1, after a preset time, when the change in the MSE value of the signal within N consecutive windows is less than the threshold D, it is considered to have reached the second steady state. At this time, the time t2 of the first window signal within the N windows is recorded, where t2 is the end point of the abnormal event. The value of N is determined based on the sampling rate, signal processing capability, and processing effect. After obtaining time t2, the signal difference before t1 and after t2 is compared. The comparison method is as follows: if the signal after t2 is an abnormal signal, K consecutive samples are collected from both before t1 and after t2. Following the time sequence, the samples before t1 and after t2 are paired, and the difference between the corresponding two sets of signal acoustic signatures is calculated. If the signal after t2 is a normal signal, it indicates that the signals before t1 and after t2 are the same, and the operating state of the tower internal components is determined to be normal. If the signals before t1 and after t2 are different, the operating state of the tower internal components is determined to be abnormal.

[0097] Furthermore, the degree of deviation is calculated using the following formula:

[0098]

[0099] Where MSE represents the degree of deviation; Y i A contour map showing the area in front of the anomaly points; This is a contour map following the outlier points.

[0100] In another implementation, if the acoustic signal generating component is the same as the working principle of the tray or float valve, the above-mentioned scheme can also be used for fault analysis, identification and diagnosis, so as to obtain the operating status of the component with the same working principle as the tray or float valve.

[0101] Example 2

[0102] like Figure 1-2 As shown, this invention provides an acoustic monitoring method for the operating status of internal components of a tower, the method comprising:

[0103] Step 1: Acquire acoustic signals from the internal components of the tower over a period of time during operation;

[0104] Specifically, in this embodiment, the acoustic signal is acquired by an acoustic sensor.

[0105] Step 2: Based on the acoustic signal, obtain the acoustic waveform data and contour map of the internal components of the tower during this operating period;

[0106] Specifically, acoustic waveform data is a graphical representation of the amplitude of sound. It is obtained by superimposing simple sine waves of different amplitudes and phases at various frequencies. The horizontal axis of the waveform graph is time, and the vertical axis is amplitude, which represents the change of the total amplitude of the superimposed sine waves of all frequencies over time.

[0107] Further, in step two, based on the acoustic signal, a contour map is obtained for that segment of the operating time, including:

[0108] Step 201: Based on the sampling rate and sampling length of the acoustic signal, obtain the total duration of a single signal;

[0109] Step 202: Perform frame processing and time-frequency transformation on the total duration of a single signal to obtain the frame frequency, the time point for spectrum analysis, and the energy spectral density;

[0110] Step 203: Based on the frame frequency, the time point of the spectrum analysis, and the energy spectral density, extract the distribution of contour maps of the corresponding areas of the time-frequency intensity cloud map to obtain the contour maps of the internal components of the tower during the operating time of that period.

[0111] Specifically, the acoustic signature distribution feature extraction is performed by dividing and calculating the total duration of a single signal based on the acoustic signal sampling rate and sampling length. Statistical analysis of the signal is used to determine the sampling locations of stationary signals, followed by frame segmentation. Through time-frequency transformation, the frame frequency, spectral analysis time points, and energy spectral density are calculated. Then, the calculation results are used to extract the distribution of contour maps of the corresponding areas in the time-frequency intensity cloud map, ultimately obtaining the contour maps of the tower's internal components during that operating period.

[0112] Step 3: Based on the acoustic waveform data or the contour map, determine whether there are any abnormal points in the internal components of the tower during the operating period. This also includes: the start time of the abnormal point; and determining the cause of the abnormal point. The cause of the abnormal point in the internal components of the tower during the operating period may be the overturning of the tower tray in the internal components of the tower and the detachment of the float valve in the internal components of the tower, thereby achieving more detailed monitoring of other operating states.

[0113] Furthermore, based on the acoustic waveform data or the contour map, determine whether there are any anomalies during this operating time period, including:

[0114] The acoustic waveform data is used as input to the first anomaly detection model to determine the anomaly detection result, or

[0115] The contour map is used as input to the second anomaly detection model to determine the anomaly detection result.

[0116] Specifically, by using a pre-trained first anomaly detection model to determine the anomaly detection result, or by using a pre-trained second anomaly detection model to determine the anomaly detection result, the accuracy of the detection result can be guaranteed.

[0117] Furthermore, the method also includes:

[0118] Obtain a first training dataset, which includes historical acoustic waveform data;

[0119] Based on the first training dataset and the autoencoder, a first anomaly detection model is trained.

[0120] Obtain a second training dataset, which includes historical contour maps;

[0121] Based on the second training dataset and the autoencoder, a second anomaly detection model is trained.

[0122] Specifically, the first training dataset contains historical acoustic waveform data obtained based on historical acoustic signals. These historical acoustic signals include acoustic signals generated by airflow friction before and after tray overturning and float valve detachment within the tower. Using this first training dataset and an autoencoder, a first anomaly detection model is trained. This model can not only identify whether there are anomalies in the tower's internal components during operation but also determine the cause of the anomalies, i.e., anomalies caused by tray overturning or float valve detachment. The second training dataset contains historical contour maps obtained based on historical acoustic signals. These historical acoustic signals include acoustic signals generated by airflow friction before and after tray overturning and float valve detachment within the tower. Using this second training dataset and an autoencoder, a second anomaly detection model is trained. This model can not only identify whether there are anomalies in the tower's internal components during operation but also determine the cause of the anomalies, i.e., anomalies caused by tray overturning or float valve detachment. The steps for obtaining historical contour maps from historical acoustic signals are the same as described above and will not be repeated here. Sliding window sampling is performed on the data obtained from the first and second training datasets. The window size is S and the overlap between windows is A. The dataset is divided into training and test sets, with the proportion of the training set being 50%-80%.

[0123] This autoencoder learns the encoding format of "normal data," so when a dataset is provided to it, it encodes and decodes it according to this format. If the error between the decoded dataset and the input dataset is within a certain range, the input dataset is considered "normal"; otherwise, it is considered "abnormal." After determining a threshold, it can be assumed that if the error after decoding a new dataset exceeds that threshold, it is considered abnormal data.

[0124] Step 4: If it is determined that there are abnormal points in the internal components of the tower during this operating period, then based on the contour map, determine the operating status of the internal components of the tower during this operating period, including normal operation and abnormal operation.

[0125] In this embodiment, after the sudden abnormal event ends, the airflow state inside the tower will change, causing a change in the airflow acoustic signal. That is, the sudden abnormal event leads to a change in the operating state (abnormal response) inside the tower, but the change in the airflow acoustic signal is weak, and the subtle abnormal change is difficult to identify. To address this problem, a soundprint distribution feature extraction method is used to enhance the signal features and improve the accuracy.

[0126] Furthermore, if it is determined that there are abnormal points in the internal components of the tower during this operating period, then based on the contour map, the operating status of the internal components of the tower during this operating period is determined, including:

[0127] If the contour map after the anomaly point is not in a steady state, then the internal components of the tower are determined to be in an abnormal operating state.

[0128] Specifically, in this embodiment, after the sudden abnormal event ends, the airflow state inside the tower will change, causing a change in the airflow acoustic signal. That is, the sudden abnormal event leads to a change in the operating state (abnormal response) inside the tower, but the change in the airflow acoustic signal is weak, and the subtle abnormal change is difficult to identify. To address this problem, a sound signature distribution feature extraction method is used to enhance the signal features and improve accuracy. Specifically, the steady state after the abnormal point is determined as follows: the difference between several consecutive signals located at the abnormal point is judged. If the difference between several consecutive signals is less than a preset difference, it proves that the operating state of the internal components of the tower has reached a new steady state after the abnormal point. If there is a difference between signals that is not less than the preset difference, it proves that the operating state of the internal components of the tower is not in a steady state after the abnormal point. Therefore, it can be determined that there is an abnormality in the internal components of the tower.

[0129] Furthermore, if it is determined that there are abnormal points in the internal components of the tower during this operating period, then based on the contour map, the operating status of the internal components of the tower during this operating period is determined, including:

[0130] If the contour map after the anomaly point is in a steady state, the operating status of the internal components of the tower can be determined based on the degree of deviation between the contour map before the anomaly point and the contour map after the anomaly point.

[0131] Furthermore, based on the degree of deviation between the contour maps before and after the anomaly points, the operating status of the tower's internal components is determined, including:

[0132] If the deviation is less than or equal to the preset threshold, the operating status of the internal components of the tower is determined to be normal operation;

[0133] If the deviation exceeds the preset threshold, the internal components of the tower are determined to be in an abnormal operating state.

[0134] Specifically, in this embodiment, when an abnormal signal is detected, the current time t1 is recorded, where t1 is the point where the abnormal event occurs. From the current time t1, after a preset time, when the change in the MSE value of the signal within N consecutive windows is less than the threshold D, it is considered to have reached the second steady state. At this time, the time t2 of the first window signal within the N windows is recorded, where t2 is the end point of the abnormal event. The value of N is determined based on the sampling rate, signal processing capability, and processing effect. After obtaining time t2, the signal difference before t1 and after t2 is compared. The comparison method is as follows: if the signal after t2 is an abnormal signal, K consecutive samples are collected from both before t1 and after t2. Following the time sequence, the samples before t1 and after t2 are paired, and the difference between the corresponding two sets of signal acoustic signatures is calculated. If the signal after t2 is a normal signal, it indicates that the signals before t1 and after t2 are the same, and the operating state of the tower internal components is determined to be normal. If the signals before t1 and after t2 are different, the operating state of the tower internal components is determined to be abnormal.

[0135] Furthermore, the degree of deviation is calculated using the following formula:

[0136]

[0137] Where MSE represents the degree of deviation; Y i A contour map showing the area in front of the anomaly points; This is a contour map following the outlier points.

[0138] In another implementation, if the acoustic signal generating component is the same as the working principle of the tray or float valve, the above-mentioned scheme can also be used for fault analysis, identification and diagnosis, so as to obtain the operating status of the component with the same working principle as the tray or float valve.

[0139] Example 3

[0140] This invention also provides an acoustic monitoring device for the operating status of internal components of a tower, such as... Figure 3 As shown, the device includes:

[0141] Data acquisition module 10 is used to acquire acoustic signals of the internal components of the tower during a certain operating time;

[0142] Data conversion module 20 is used to obtain acoustic waveform data and contour maps for the specified operating time based on the acoustic signal.

[0143] The anomaly detection module 30 is used to determine whether there are any anomalies in the internal components of the tower during the operating time period based on the acoustic waveform data or the contour map.

[0144] The operating status determination module 40 is used to determine the operating status of the internal components of the tower during the operating period based on the contour map when it is determined that there are abnormal points in the internal components of the tower during the operating period. The operating status includes normal operation and abnormal operation.

[0145] Furthermore, the data conversion module 20 is specifically used for:

[0146] The total duration of a single signal is obtained based on the sampling rate and sampling length of the acoustic signal;

[0147] The total duration of a single signal is divided into frames and transformed by time and frequency to obtain the frame frequency, the time point for spectrum analysis, and the energy spectral density.

[0148] Based on the frame frequency, spectral analysis time point, and energy spectral density, the distribution of contour maps of the corresponding areas of the time-frequency intensity cloud map is extracted to obtain the contour maps of the internal components of the tower during the operating time of that period.

[0149] The anomaly detection module 30 is specifically used for:

[0150] The acoustic waveform data is used as input to the first anomaly detection model to determine the anomaly detection result, or

[0151] The contour map is used as input to the second anomaly detection model to determine the anomaly detection result.

[0152] Furthermore, the device further includes: a model training module, which is specifically used for:

[0153] Obtain a first training dataset, which includes historical acoustic waveform data;

[0154] Based on the first training dataset and the autoencoder, a first anomaly detection model is trained.

[0155] Obtain a second training dataset, which includes historical contour maps;

[0156] Based on the second training dataset and the autoencoder, a second anomaly detection model is trained.

[0157] Furthermore, the operating status determination module 40 is specifically used for:

[0158] If the contour map after the anomaly point is not in a steady state, it is determined that the operating state of the internal components of the tower is abnormal.

[0159] Furthermore, the operating status determination module 40 is also specifically used for:

[0160] If it is determined that there are abnormal points in the internal components of the tower during the operating period, and the contour map after the abnormal point is in a steady state, the operating status of the internal components of the tower can be determined based on the degree of deviation between the contour map before the abnormal point and the contour map after the abnormal point.

[0161] More specifically, the degree of deviation is calculated using the following formula:

[0162]

[0163] Where MSE represents the degree of deviation; Y i A contour map showing the area in front of the anomaly points; This is a contour map following the outlier points.

[0164] Among them, the operating status of the tower's internal components is determined based on the degree of deviation between the contour maps before and after the anomaly points, including:

[0165] If the deviation is less than or equal to the preset threshold, the operating status of the internal components of the tower is determined to be normal operation;

[0166] If the deviation exceeds the preset threshold, the internal components of the tower are determined to be in an abnormal operating state.

[0167] Example 4

[0168] This invention provides an acoustic monitoring system for the operating status of internal components of a tower, such as... Figure 4 As shown, the system includes:

[0169] Multiple acoustic sensors 52 are spaced apart on the wall of the tower 51;

[0170] The aforementioned acoustic monitoring device 53 for the operating status of internal components of the tower is electrically connected to the acoustic sensor 52.

[0171] Specifically, the number of acoustic sensors 52 can be determined based on the external volume of the tower. If the tower is large, more acoustic sensors 52 should be installed; if the tower is small, fewer acoustic sensors 52 should be installed. Furthermore, the acoustic sensors 52 can be arranged symmetrically or installed according to the relative positions of the trays and float valves within the tower, ensuring the acoustic sensors 52 are as close as possible to the trays and float valves, thereby guaranteeing better quality acoustic signals. The acoustic sensors 52 can be located on the outer surface of the tower or inside the tower.

[0172] Example 5

[0173] This invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-described method for acoustic monitoring of the operating status of internal components of a tower.

[0174] Example 6

[0175] This invention provides a readable storage medium storing instructions that cause a machine to execute the above-described acoustic monitoring method for the operating status of tower internal components.

[0176] Example 7

[0177] To verify the monitoring effectiveness of trays or float valves, 1000 sets of acoustic signals were collected. This scheme and conventional recognition models were used to identify tray tipping (250 sets), float valve detachment (250 sets), airflow changes (250 sets), and noise interference (250 sets). Compared to conventional recognition models, such as the CNN model (73.20% accuracy) and the empirical database matching model (82.50% accuracy), the model in this scheme achieved an accuracy of 98.1%.

[0178] Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing related hardware. This program is stored in a storage medium and includes several instructions to cause a microcontroller, chip, or processor to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0179] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application.

[0180] The optional embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the embodiments of the present invention are not limited to the specific details described above. Within the scope of the technical concept of the embodiments of the present invention, various simple modifications can be made to the technical solutions of the embodiments of the present invention, and these simple modifications all fall within the protection scope of the embodiments of the present invention. It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, the embodiments of the present invention will not further describe the various possible combinations.

[0181] Furthermore, various different embodiments of the present invention can be combined in any way, as long as they do not violate the spirit of the embodiments of the present invention, they should also be regarded as the content disclosed by the embodiments of the present invention.

Claims

1. An acoustic monitoring method for the operating status of internal components of a tower, characterized in that, The method includes: Acquire acoustic signals from the internal components of the tower over a period of time during operation; Based on the acoustic signals, acoustic waveform data and contour maps of the internal components of the tower during the operating time of that period are obtained. Based on the acoustic waveform data or the contour map, determine whether there are any abnormal points in the internal components of the tower during the operating period. If it is determined that there are abnormal points in the internal components of the tower during the operating period, the operating status of the internal components of the tower during the operating period is determined based on the contour map. The operating status includes normal operation and abnormal operation.

2. The method according to claim 1, characterized in that, Based on the acoustic signal, a contour map of the operating time segment is obtained, including: The total duration of a single signal is obtained based on the sampling rate and sampling length of the acoustic signal; The total duration of a single signal is divided into frames and transformed by time and frequency to obtain the frame frequency, the time point for spectrum analysis, and the energy spectral density. Based on the frame frequency, spectral analysis time point, and energy spectral density, the distribution of contour maps of the corresponding areas of the time-frequency intensity cloud map is extracted to obtain the contour maps of the internal components of the tower during the operating time of that period.

3. The method according to claim 1, characterized in that, Based on the acoustic waveform data or the contour map, determine whether there are any anomalies during the specified operating time, including: The acoustic waveform data is used as input to the first anomaly detection model to determine the anomaly detection result, or The contour map is used as input to the second anomaly detection model to determine the anomaly detection result.

4. The method according to claim 3, characterized in that, The method further includes: Obtain a first training dataset, which includes historical acoustic waveform data; Based on the first training dataset and the autoencoder, a first anomaly detection model is trained. Obtain a second training dataset, which includes historical contour maps; Based on the second training dataset and the autoencoder, a second anomaly detection model is trained.

5. The method according to claim 1, characterized in that, If anomalies are identified in the internal components of the tower during this operating period, the operating status of the internal components during this period is determined based on the contour map, including: If the contour map after the anomaly point is not in a steady state, then the internal components of the tower are determined to be in an abnormal operating state.

6. The method according to claim 1, characterized in that, If anomalies are identified in the internal components of the tower during this operating period, the operating status of the internal components during this period is determined based on the contour map, including: If the contour map after the anomaly point is in a steady state, the operating status of the internal components of the tower can be determined based on the degree of deviation between the contour map before the anomaly point and the contour map after the anomaly point.

7. The method according to claim 6, characterized in that, Based on the degree of deviation between the contour maps before and after anomalies, the operating status of the tower's internal components is determined, including: If the deviation is less than or equal to the preset threshold, the operating status of the internal components of the tower is determined to be normal operation; If the deviation exceeds the preset threshold, the internal components of the tower are determined to be in an abnormal operating state.

8. The method according to claim 6, characterized in that, The degree of deviation is calculated using the following formula: Where MSE represents the degree of deviation; Y i A contour map showing the area in front of the outlier. This is a contour map following the outlier points.

9. An acoustic monitoring device for the operating status of internal components of a tower, characterized in that, The device includes: The data acquisition module is used to acquire acoustic signals of the internal components of the tower over a certain period of time. The data conversion module is used to obtain acoustic waveform data and contour maps for the specified operating time based on the acoustic signal. The anomaly detection module is used to determine whether there are any anomalies in the internal components of the tower during the operating time period, based on the acoustic waveform data or the contour map. The operating status determination module is used to determine the operating status of the internal components of the tower during the operating period based on the contour map when it is determined that there are abnormal points in the internal components of the tower during the operating period. The operating status includes normal operation and abnormal operation.

10. An acoustic monitoring system for the operating status of internal components of a tower, characterized in that, The system includes: Multiple acoustic sensors are spaced apart on the wall of the tower. The acoustic monitoring device for the operating status of internal components of a tower as described in claim 9, wherein the acoustic monitoring device for the operating status of internal components of a tower is electrically connected to the acoustic sensor.

11. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the acoustic monitoring method for the operating status of tower internal components as described in any one of claims 1-8.

12. A readable storage medium storing instructions, characterized in that, This instruction is used to cause the machine to perform the acoustic monitoring method for the operating status of tower internal components as described in any one of claims 1-8.

Images