Wireless telemetry and edge diagnostic method and system based on compression lightweight perception

Abstract

The application belongs to the technical field of mechanical fault diagnosis, and specifically discloses a wireless telemetry and edge diagnosis method and system based on compressed lightweight sensing, which comprises the following steps: collecting vibration and temperature signals of equipment, and pre-processing original signals; performing envelope detection on the pre-processed vibration data at the edge end, calculating the kurtosis values of the temperature data and the vibration data, and performing abnormality detection using the pre-set kurtosis values, and outputting fault information if there is abnormality; using discrete cosine Huffman dual-mode coding to compress and encode the pre-processed vibration data, and sending the encoded data by the telemetry node; and decoding and reconstructing the encoded data by the data receiving end through Huffman decoding and discrete cosine inverse transformation, and using a neural network to recognize faults. By using the technical scheme, the amount of transmission data is significantly reduced through data compression technology, thereby reducing the bandwidth requirement and transmission delay, and the fault diagnosis can be more efficiently performed.

Description

Technical Field

[0001] This invention belongs to the field of mechanical fault diagnosis technology, and relates to a wireless telemetry and edge diagnosis method and system based on compressed lightweight sensing. Background Technology

[0002] Mechanical fault diagnosis is of great significance in modern industrial production. With the increasing complexity and automation of industrial equipment and production lines, the reliability and operating efficiency of equipment directly affect the safety and economic benefits of production.

[0003] During the operation of mechanical equipment, a large number of physical signals such as vibration and temperature are generated. Real-time monitoring and analysis of these signals are crucial for ensuring normal equipment operation and preventing malfunctions. However, traditional detection methods suffer from problems such as slow transmission and poor timeliness due to large data volumes. Summary of the Invention

[0004] The purpose of this invention is to provide a wireless telemetry and edge diagnosis method and system based on compressed lightweight sensing, so as to solve the problems of large data volume, slow transmission, poor timeliness and high power consumption in traditional fault diagnosis.

[0005] To achieve the above objectives, the basic solution of this invention is: a wireless telemetry and edge diagnosis method based on compressed lightweight sensing, comprising the following steps:

[0006] The vibration and temperature signals of the acquisition equipment are collected, and the raw signals are preprocessed.

[0007] Envelope detection is performed on the preprocessed vibration data at the edge, the kurtosis values ​​of temperature data and vibration data are calculated, and anomaly detection is performed using empirically preset kurtosis values. If anomalies are found, fault information is output.

[0008] Discrete cosine Huffman dual-mode coding is used to compress and encode the preprocessed vibration data, and the telemetry node transmits the encoded data.

[0009] The data receiving end decodes and reconstructs the encoded data through Huffman inverse coding and discrete cosine transform, and uses neural networks to identify equipment faults. By constructing and training a convolutional neural network (CNN), different types of faults can be effectively identified and classified, thereby enabling real-time monitoring and predictive maintenance of equipment status.

[0010] The working principle and beneficial effects of this basic solution are as follows: This technical solution is based on compressed lightweight sensing, which significantly reduces the amount of data transmitted through data compression technology, thereby reducing bandwidth requirements and transmission latency. Simultaneously, lightweight sensing technology can effectively reduce data processing complexity and energy consumption without affecting diagnostic accuracy. Edge computing nodes can perform fault diagnosis more efficiently, extend battery life, and reduce maintenance frequency, thereby improving the reliability and economic efficiency of the entire system.

[0011] Furthermore, the method for preprocessing the original signal is as follows:

[0012] The DC component is removed by calculating and subtracting the mean of the original signal. The mean is:

[0013]

[0014] in, It is the mean of the signal, N is the number of signal samples, and x is the mean of the signal. i It is the value of the i-th sample;

[0015] The original signal is smoothed using a weighted moving average method. Different weights are assigned to data points to calculate the average value, preserving the characteristics of the data and achieving a better smoothing effect.

[0016]

[0017] Among them, WMH t The weighted moving average at time point t, x t-i w is the value of the i-th data point within the window. i These are the weights of the corresponding data points, and A is the window size.

[0018] Denoising based on a block thresholding strategy: Visushrink calculates the threshold λ used for wavelet block thresholding denoising.

[0019]

[0020] Where σ represents the standard deviation of the noise;

[0021] The signal is decomposed into multi-scale detail components A using Haar wavelets. i AA i ADA i With approximate component D i ,DA i DDA i Block thresholding is used to process the different components obtained from the decomposition:

[0022]

[0023] Among them, (w j,k ) represents the original wavelet packet decomposition coefficients, (w j,k ) ⊥ These are the coefficients after thresholding.

[0024] Coefficients (w) after block thresholding j,k ) ⊥ By performing an inverse wavelet packet transform, the original denoised signal can be recovered.

[0025] The original signal is preprocessed, and the wavelet packet thresholding method is used to denoise and optimize the data.

[0026] Furthermore, the steps for anomaly detection in the preprocessed temperature data are as follows:

[0027] Calculate the kurtosis value of the temperature data:

[0028]

[0029] Where E[] represents the expected value, X is the original signal, and μ is the mean of the original signal X;

[0030] The kurtosis value of the temperature data is compared with the preset value. If the kurtosis value of the temperature data exceeds the preset value, a temperature fault message is output.

[0031] Anomaly detection is performed on the preprocessed temperature data to obtain corresponding temperature fault information.

[0032] Furthermore, the steps for anomaly detection of the preprocessed vibration data are as follows:

[0033] Envelope detection is performed on the preprocessed vibration signal to extract the envelope of the original signal. The envelope spectrum Envelope(t) is obtained using the Hilbert function.

[0034]

[0035] Where x(t) is the original signal, It is the Hilbert transform;

[0036] Kurtosis value calculated based on envelope spectrum:

[0037]

[0038] Where m is the number of samples, x i It is the i-th sample value. s is the sample mean, and s is the sample standard deviation; the empirical threshold is compared with the kurtosis value, and if it exceeds the empirical threshold, vibration fault information is sent.

[0039] Anomaly detection is performed on the preprocessed vibration data to obtain corresponding vibration fault information.

[0040] Furthermore, the steps for compressing and encoding the preprocessed vibration data using discrete cosine Huffman dual-mode coding are as follows:

[0041] By combining discrete cosine transform with Huffman coding, the original signal is compressed into a coded bitstream and an element dictionary:

[0042]

[0043] Where X(k) is the k-th frequency domain coefficient, x(n) is the n-th sample value of the original time domain signal, N is the number of samples of the input signal, n is the index of the signal, and k is the index of the transformed frequency domain coefficient.

[0044] The encoded bitstream, after efficient compression, has a significantly improved transmission efficiency.

[0045] Furthermore, the data receiver decodes and reconstructs the encoded data using Huffman inverse coding and discrete cosine transform, resulting in:

[0046]

[0047] Where X(k) is the k-th frequency domain coefficient, x(n) is the n-th sample value of the original time domain signal, k is the index of the transformed frequency domain coefficient, N is the number of signal samples, and n is the signal index.

[0048] High-precision reconstruction of data is achieved through Huffman inverse coding and discrete cosine transform, which facilitates fault identification.

[0049] The present invention also provides a wireless telemetry and edge diagnostic system based on compressed lightweight sensing, including a vibration sensor, a temperature sensor, a dual-channel acquisition module, a transmission module and an edge processing module;

[0050] The vibration sensor and temperature sensor are simultaneously connected to the dual-channel acquisition module, which is used to synchronously acquire the vibration and temperature signals of the equipment.

[0051] The edge processing module receives signals acquired by the dual-channel acquisition module through the transmission module and executes the method described in this invention to identify equipment faults.

[0052] This system utilizes sensors and various modules to achieve edge diagnosis of rolling elements.

[0053] Furthermore, it also includes a remote terminal, which is connected to the output of the edge processing module via a wireless communication module.

[0054] Receive data remotely for easy viewing.

[0055] Furthermore, it also includes a power supply module, which is connected to the power supply terminals of the vibration sensor, temperature sensor, dual-channel acquisition module, transmission module and edge processing module, respectively.

[0056] A power supply module is installed to ensure power supply for all components. Attached Figure Description

[0057] Figure 1 This is a flowchart illustrating the wireless telemetry and edge diagnosis method based on compressed lightweight sensing of the present invention.

[0058] Figure 2 This is a schematic diagram of the preprocessing process of the original signal in the wireless telemetry and edge diagnosis method based on compressed lightweight sensing of the present invention.

[0059] Figure 3 This is a flowchart illustrating the anomaly detection process of preprocessed temperature and vibration data using the wireless telemetry and edge diagnosis method based on compressed lightweight sensing of the present invention.

[0060] Figure 4 This is a schematic diagram of the compressed sensing process based on discrete cosine Huffman dual-mode coding for the wireless telemetry and edge diagnosis method based on compressed lightweight sensing of the present invention. Detailed Implementation

[0061] Embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0062] In the description of this invention, it should be understood that the terms "longitudinal", "lateral", "up", "down", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0063] In the description of this invention, unless otherwise specified and limited, it should be noted that the terms "installation", "connection" and "linking" should be interpreted broadly. For example, they can refer to mechanical or electrical connections, or internal connections between two components. They can be direct connections or indirect connections through an intermediate medium. Those skilled in the art can understand the specific meaning of the above terms according to the specific circumstances.

[0064] This invention discloses a wireless telemetry and edge diagnostic method based on compressed lightweight sensing. Addressing the problem that traditional manual inspections cannot provide real-time information on equipment operating status and issue early warnings and alarms, this method monitors vibration and temperature data during equipment operation in real time and achieves real-time monitoring of the equipment based on envelope detection anomaly detection technology. Data compression technology significantly reduces the amount of data transmitted, thereby lowering bandwidth requirements and transmission latency. Figure 1 As shown, the wireless telemetry and edge diagnostics method includes the following steps:

[0065] The vibration and temperature signals of the acquisition equipment are collected, and the raw signals are preprocessed.

[0066] Envelope detection is performed on the preprocessed vibration data at the edge, the kurtosis values ​​of temperature data and vibration data are calculated, and anomaly detection is performed using empirically preset kurtosis values. If anomalies are found, fault information is output.

[0067] The preprocessed vibration data is compressed and encoded using Discrete Cosine Hoffman Dual-mode Coding (DHDMC), and the telemetry node transmits the encoded data.

[0068] The data receiving end decodes and reconstructs the encoded data through Huffman inverse coding and discrete cosine transform, and uses neural networks (such as CNN) to identify equipment faults (identifying bearing and gear faults, such as bearing inner ring, outer ring, rolling element, and cage faults, and gear tooth breakage, wear, and misalignment). Convolutional neural networks (CNN) are constructed and trained to effectively identify and classify different types of faults, thereby enabling real-time monitoring and predictive maintenance of equipment status.

[0069] In a preferred embodiment of the present invention, such as Figure 2 As shown, the original signal often contains noise due to limitations of sensors and circuits. Based on traditional preprocessing methods and wavelet packet thresholding, the method for preprocessing the original signal is as follows:

[0070] The DC component is removed by calculating and subtracting the mean of the original signal. The mean is:

[0071]

[0072] in, It is the mean of the signal, N is the number of signal samples, and x is the mean of the signal. i It is the value of the i-th sample;

[0073] The original signal is smoothed using a weighted moving average method. Different weights are assigned to data points to calculate the average value, preserving the characteristics of the data and achieving a better smoothing effect.

[0074]

[0075] Among them, WMH t The weighted moving average at time point t, x t-i w is the value of the i-th data point within the window. i is the weight of the corresponding data point, and A is the window size, with a preferred window size of 5;

[0076] Wavelet packet decomposition is performed on the original data after removing the DC component and filtering and smoothing, and the decomposition results are denoised using a block thresholding strategy. The threshold λ used for wavelet block thresholding denoising is calculated by Visushrink visualization.

[0077]

[0078] Where σ represents the standard deviation of the noise;

[0079] Using Haar wavelets to perform multi-level (e.g., 4-level) decomposition of the signal, the original signal is decomposed into multi-scale detail components A. i AA i ADA i With approximate component D i ,DA i DDA i Block thresholding is used to process the different components obtained from the decomposition:

[0080]

[0081] Among them, (w j,k ) represents the original wavelet packet decomposition coefficients, (w j,k ) ⊥ These are the coefficients after thresholding.

[0082] Coefficients (w) after block thresholding j,k ) ⊥ By performing an inverse wavelet packet transform, the original denoised signal can be recovered.

[0083] In a preferred embodiment of the present invention, such as Figure 3 As shown, the steps for anomaly detection in the preprocessed temperature data are as follows:

[0084] Calculate the kurtosis value of the temperature data:

[0085]

[0086] Where E[] represents the expected value, X is the original signal, and μ is the mean of the original signal X;

[0087] The kurtosis value of the temperature data is compared with the preset value. If the kurtosis value of the temperature data exceeds the preset value, a temperature fault message is output.

[0088] In a preferred embodiment of the present invention, the step of anomaly detection of the preprocessed vibration data is as follows:

[0089] Envelope detection is performed on the preprocessed vibration signal to extract the envelope of the original signal. The envelope spectrum Envelope(t) is obtained using the Hilbert function.

[0090]

[0091] Where x(t) is the original signal, It is the Hilbert transform;

[0092] Kurtosis value calculated based on envelope spectrum:

[0093]

[0094] Where m is the number of samples, x i It is the i-th sample value. s is the sample mean, and s is the sample standard deviation; the empirical threshold is compared with the kurtosis value, and if it exceeds the empirical threshold, vibration fault information is sent.

[0095] In a preferred embodiment of the present invention, such as Figure 4 As shown, the steps for compressing and encoding the preprocessed vibration data using Discrete Cosine Hoffman Dual-mode Coding (DHDMC) are as follows:

[0096] By combining discrete cosine transform with Huffman coding, the original signal is compressed into a coded bitstream and an element dictionary:

[0097]

[0098] Where X(k) is the k-th frequency domain coefficient, x(n) is the n-th sample value of the original time domain signal, N is the number of samples of the input signal, n is the index of the signal, and k is the index of the transformed frequency domain coefficient.

[0099] Discrete cosine transform can convert the original signal into a sparse representation in the frequency domain, greatly reducing data complexity. Then, Huffman coding is a lossless coding method that can encode long data into a bit stream and an element dictionary. The memory occupied by the bit stream and the element dictionary is much smaller than the memory occupied by the original signal.

[0100] In this invention, the Discrete Cosine Transform (DCT) is combined with Huffman coding, and the DCT-Huffman dual-mode coding can efficiently compress the space occupied by the original data.

[0101] Based on this, the data uploaded by telemetry is no longer the original signal that occupies a huge amount of space, but a coded bit stream that has been efficiently compressed, which greatly improves the transmission efficiency.

[0102] In a preferred embodiment of the present invention, after transmission is completed, the data receiving end decodes and reconstructs the encoded data using Huffman inverse coding and discrete cosine transform, as follows:

[0103]

[0104] Where X(k) is the k-th frequency domain coefficient, x(n) is the n-th sample value of the original time domain signal, k is the index of the transformed frequency domain coefficient, and n is the index of the signal.

[0105] This invention also provides a wireless telemetry and edge diagnostic system based on compressed lightweight sensing, including a vibration sensor (such as a MEMS vibration sensor, which accurately captures the vibration amplitude and frequency of mechanical equipment), a temperature sensor (such as a DS18B20 temperature sensor, which accurately measures temperature changes during equipment operation), a dual-channel acquisition module (which synchronously acquires vibration and temperature signals to ensure data integrity and consistency), a transmission module, and an edge processing module. The vibration sensor and temperature sensor are electrically connected to the dual-channel acquisition module, which is used to synchronously acquire the vibration and temperature signals of the equipment. The vibration sensor, temperature sensor, and dual-channel acquisition module are installed at the edge of the equipment to capture key data such as vibration and temperature of the mechanical equipment in real time.

[0106] The edge processing module receives signals acquired by the dual-channel acquisition module via the transmission module and executes the method described in this invention to identify equipment faults. This system utilizes sensors and various modules in cooperation to achieve rolling element edge diagnosis.

[0107] Preferably, the vibration sensor, temperature sensor, dual-channel acquisition module, transmission module, and edge processing module are all housed within the housing, facilitating centralized installation and providing protection. The exterior of the housing can be fitted with a raised threaded structure (such as a screw-like structure) for connection to the equipment (i.e., screw connection), ensuring a secure connection.

[0108] In a preferred embodiment of the present invention, the wireless telemetry and edge diagnostic system further includes a remote terminal, which is electrically connected to the output of the edge processing module via a wireless communication module (such as WiFi, Bluetooth, 5G network, etc.). The remote terminal can be a smart display, computer, etc., to remotely receive data for easy viewing.

[0109] In a preferred embodiment of the present invention, the wireless telemetry and edge diagnostic system further includes a power supply module (such as a battery), which is electrically connected to the power supply terminals of the vibration sensor, temperature sensor, dual-channel acquisition module, transmission module, and edge processing module. The power supply module ensures power supply to all devices.

[0110] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0111] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

Claims

1. A wireless telemetry and edge diagnosis method based on compressed lightweight sensing, characterized in that, Includes the following steps: The vibration and temperature signals of the acquisition equipment are collected, and the raw signals are preprocessed. Envelope detection is performed on the preprocessed vibration data at the edge, the kurtosis values ​​of temperature data and vibration data are calculated, and anomaly detection is performed using empirically preset kurtosis values. If anomalies are found, fault information is output. Discrete cosine Huffman dual-mode coding is used to compress and encode the preprocessed vibration data, and the telemetry node transmits the encoded data. The data receiving end decodes and reconstructs the encoded data through Huffman inverse coding and discrete cosine transform, and uses neural networks to identify equipment faults. The method for preprocessing the original signal is as follows: The DC component is removed by calculating and subtracting the mean of the original signal. The mean is: in, It is the mean of the signal, N is the number of signal samples, and x is the mean of the signal. i It is the value of the i-th sample; The original signal is smoothed using a weighted moving average method. Different weights are assigned to data points to calculate the average value, preserving the characteristics of the data and achieving a better smoothing effect. Among them, WMA t The weighted moving average at time point t, x t-i w is the value of the i-th data point within the window. i These are the weights of the corresponding data points, and A is the window size. Denoising based on a block thresholding strategy: Visushrink calculates the threshold λ used for wavelet block thresholding denoising. Where σ represents the standard deviation of the noise; The signal is decomposed into multi-scale detail components A using Haar wavelets. i AA i ADA i With approximate component D i ,DA i DDA i Block thresholding is used to process the different components obtained from the decomposition: Among them, (w j,k ) represents the original wavelet packet decomposition coefficients, (w j,k ) ⊥ These are the coefficients after thresholding. The coefficients (w) after block thresholding j,k ) ⊥ By performing wavelet packet inverse transform, the original denoised signal can be recovered; The steps for anomaly detection of preprocessed temperature data are as follows: Calculate the kurtosis value of the temperature data: Where E[] represents the expected value, X is the original signal, and μ is the mean of the original signal X; The kurtosis value of the temperature data is compared with the preset value. If the kurtosis value of the temperature data exceeds the preset value, a temperature fault message is output. The steps for anomaly detection of preprocessed vibration data are as follows: Envelope detection is performed on the preprocessed vibration signal to extract the envelope of the original signal. The envelope spectrum Envelope(t) is obtained using the Hilbert function. Where x(t) is the original signal, It is the Hilbert transform; Kurtosis value calculated based on envelope spectrum: Where m is the number of samples, x i It is the i-th sample value. is the sample mean, and s is the sample standard deviation; the empirical threshold is compared with the kurtosis value, and if it exceeds the empirical threshold, vibration fault information is sent. The steps for compressing and encoding the preprocessed vibration data using discrete cosine Huffman dual-mode coding are as follows: By combining discrete cosine transform with Huffman coding, the original signal is compressed into a coded bitstream and an element dictionary: Where X(k) is the k-th frequency domain coefficient, x(n) is the n-th sample value of the original time domain signal, N is the number of samples of the input signal, n is the index of the signal, and k is the index of the transformed frequency domain coefficient; The data receiver decodes and reconstructs the encoded data using Huffman inverse coding and inverse discrete cosine transform, resulting in: Where X(k) is the k-th frequency domain coefficient, x(n) is the n-th sample value of the original time domain signal, k is the index of the transformed frequency domain coefficient, and n is the index of the signal.

2. A wireless telemetry and edge diagnostic system based on compressed lightweight sensing, characterized in that, It includes a vibration sensor, a temperature sensor, a dual-channel acquisition module, a transmission module, and an edge processing module; The vibration sensor and temperature sensor are simultaneously connected to the dual-channel acquisition module, which is used to synchronously acquire the vibration and temperature signals of the equipment. The edge processing module receives signals acquired by the dual-channel acquisition module through the transmission module and executes the method described in claim 1 to identify equipment faults.

3. The wireless telemetry and edge diagnostic system based on compressed lightweight sensing as described in claim 2, characterized in that, It also includes a remote terminal, which is connected to the output of the edge processing module via a wireless communication module.

4. The wireless telemetry and edge diagnostic system based on compressed lightweight sensing as described in claim 2, characterized in that, It also includes a power supply module, which is connected to the power supply terminals of the vibration sensor, temperature sensor, dual-channel acquisition module, transmission module and edge processing module respectively.

Images