Methods, devices and non-volatile storage media for monitoring the condition of moving equipment

Abstract

This application discloses a method, apparatus, and non-volatile storage medium for detecting the condition of moving equipment. The method includes: collecting vibration data from the moving equipment, wherein the vibration data includes at least one of the following: a vibration signal sequence and raw vibration acceleration data, and the moving equipment is a rotating type of moving equipment; determining a first trend sequence of the moving equipment based on the vibration data; determining the values ​​of development trend indicators corresponding to each first trend sequence based on the first trend sequence; determining a health metric value based on the development trend indicators and preset weights corresponding to the development trend indicators; and uploading the first trend sequence, development trend indicators, and health metric value to a server used to determine the condition of the moving equipment. This application solves the technical problems of low efficiency, poor stability, and incomplete health status assessment of moving equipment caused by the large data transmission volume, high latency, and single fault diagnosis indicators of traditional wireless vibration sensors.

Description

Technical Field

[0001] This application relates to the field of rotating equipment condition monitoring technology, and more specifically, to a method, apparatus and non-volatile storage medium for monitoring the condition of rotating equipment. Background Technology

[0002] Currently, vibration monitoring generates a massive amount of data, requiring large-scale transmission to local servers for processing and evaluation. This can easily lead to bandwidth congestion and data transmission delays, and significantly reduces the timeliness of data evaluation for the equipment itself. Furthermore, in terms of vibration characteristic calculation, only a single feature in the time and frequency domain is typically considered to assess the equipment's operating status, resulting in a relatively simplistic evaluation metric.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This application provides a method, apparatus, and non-volatile storage medium for detecting the condition of moving equipment, in order to at least solve the technical problems of low efficiency, poor stability, and incomplete health status assessment of moving equipment caused by the large data transmission volume, high latency, and single fault diagnosis indicators of traditional wireless vibration sensors.

[0005] According to one aspect of the embodiments of this application, a method for detecting the state of moving equipment is provided, comprising: collecting vibration data of the moving equipment, wherein the vibration data includes at least one of the following: a vibration signal sequence and raw vibration acceleration data, and the moving equipment is a rotating moving equipment; determining a first trend sequence of the moving equipment based on the vibration data, wherein the first trend sequence includes at least one of the following: a historical trend sequence of frequency domain features, a historical trend sequence of rolling bearing characteristic frequencies, a historical trend sequence of gearbox characteristic frequencies, a historical trend sequence of vibration intensity, and a historical trend sequence of time domain dimensionless features; determining the values ​​of development trend indicators corresponding to each first trend sequence based on the first trend sequence; determining a health measure value based on the development trend indicators and preset weights corresponding to the development trend indicators; and uploading the first trend sequence, the development trend indicators, and the health measure value to a server for determining the state of the moving equipment.

[0006] Optionally, determining the first trend sequence of the moving equipment based on vibration data includes: performing a fast Fourier transform on the vibration signal sequence to obtain a first frequency value sequence and a first amplitude sequence corresponding to the first frequency value sequence; screening peak points in the first amplitude sequence whose relative height is greater than a preset threshold, and adding the frequency values ​​corresponding to the peak points to a second frequency value sequence, wherein the relative height is the difference between the peak value and the valley value within a preset interval; determining multiple candidate frequency points in the second frequency value sequence according to a preset interval and a preset distance; determining a target frequency point from the candidate frequency points, and using the frequency corresponding to the target frequency point as the rotational frequency of the moving equipment; and determining the historical trend sequence of the frequency domain characteristics of the moving equipment, the historical trend sequence of the rolling bearing characteristic frequency, and the historical trend sequence of the gearbox characteristic frequency based on the rotational frequency.

[0007] Optionally, determining the target frequency point from the candidate frequency points includes: determining multiple harmonic frequency values ​​corresponding to the candidate frequency points; determining the frequency value with the smallest difference from each harmonic frequency value in the second frequency value sequence as an approximate frequency value that corresponds one-to-one with each harmonic frequency value; determining the sum of the differences between each harmonic frequency value and the approximate frequency value corresponding to the harmonic frequency value as the sum of the differences of the candidate frequency points; and determining the candidate frequency point with the smallest sum of differences as the target frequency point.

[0008] Optionally, determining the values ​​of the development trend indicators corresponding to each first trend sequence based on the first trend sequence includes: filtering the first trend sequence; determining the second trend sequence based on the filtered first trend sequence; and determining the values ​​of the development trend indicators based on the second trend sequence.

[0009] Alternatively, the second trend sequence can be determined according to the following formula:

[0010] Where Y = {y1, y2, ..., yn} is the second trend sequence, X = {x1, x2, ..., xn} is the first trend sequence, t is the sampling time corresponding to each sampling point in the first trend sequence, and λ is the preset regularization parameter.

[0011] Alternatively, the value of the development trend indicator can be determined according to the following formula: Where Y = {y1, y2, ..., yn} is the second trend sequence, and Δt is the time difference between adjacent sampling points in the second trend sequence.

[0012] Optionally, vibration data is collected by sensors, which are also used to locally determine a first trend sequence, a development trend indicator, and a health measure, and store the first trend sequence, the development trend indicator, and the health measure.

[0013] According to another aspect of the embodiments of this application, a moving equipment status detection device is also provided, comprising: a data acquisition module for acquiring vibration data of the moving equipment, wherein the vibration data includes at least one of the following: a vibration signal sequence and raw vibration acceleration data, and the moving equipment is a rotating moving equipment; a first determination module for determining a first trend sequence of the moving equipment based on the vibration data, wherein the first trend sequence includes at least one of the following: a historical trend sequence of frequency domain features, a historical trend sequence of rolling bearing characteristic frequencies, a historical trend sequence of gearbox characteristic frequencies, a historical trend sequence of vibration intensity, and a historical trend sequence of time domain dimensionless features; a second determination module for determining the values ​​of development trend indicators corresponding to each first trend sequence based on the first trend sequence; a third determination module for determining a health measurement value based on the development trend indicators and preset weights corresponding to the development trend indicators; and an upload module for uploading the first trend sequence, the development trend indicators, and the health measurement value to a server for determining the status of the moving equipment.

[0014] According to another aspect of the embodiments of this application, a non-volatile storage medium is also provided, wherein a program is stored in the non-volatile storage medium, and the program controls the device where the non-volatile storage medium is located to execute a device state detection method when it runs.

[0015] According to another aspect of the embodiments of this application, an electronic device is also provided, including: a memory and a processor, the processor being configured to run a program stored in the memory, wherein the program executes an electronic device state detection method during runtime.

[0016] According to another aspect of the embodiments of this application, a computer program product is also provided, including a computer program that, when executed by a processor, implements a method for detecting the state of a moving device.

[0017] In this embodiment, vibration data of a rotating device is collected. The vibration data includes at least one of the following: vibration signal sequence and raw vibration acceleration data. The rotating device is a rotating device. A first trend sequence of the device is determined based on the vibration data. The first trend sequence includes at least one of the following: historical trend sequence of frequency domain features, historical trend sequence of rolling bearing characteristic frequency, historical trend sequence of gearbox characteristic frequency, historical trend sequence of vibration intensity, and historical trend sequence of time domain dimensionless features. The values ​​of development trend indicators corresponding to each first trend sequence are determined based on the first trend sequence. A health metric is determined based on the development trend indicators and the preset weights corresponding to the development trend indicators. The first trend sequence, development trend indicators, and health metric are uploaded to a server used to determine the status of the rotating device. By analyzing multiple feature indicators through edge computing, the purpose of real-time monitoring and rapid fault diagnosis is achieved. This achieves the technical effects of reducing data transmission volume, reducing latency, and comprehensively assessing the health status of the device. This solves the technical problems of low efficiency, poor stability, and incomplete health status assessment of rotating devices caused by the large data transmission volume, high latency, and single fault diagnosis indicators of traditional wireless vibration sensors. Attached Figure Description

[0018] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0019] Figure 1 This is a schematic diagram of the structure of a computer terminal according to an embodiment of this application;

[0020] Figure 2 This is a flowchart illustrating a method for detecting the condition of moving equipment according to an embodiment of this application;

[0021] Figure 3 This is a schematic diagram of the various parts of an optional sensor provided according to an embodiment of this application;

[0022] Figure 4 This is a schematic diagram of an optional process for collecting vibration data of a moving device according to an embodiment of this application;

[0023] Figure 5 This is a schematic diagram of an optional feature value calculation process provided according to an embodiment of this application;

[0024] Figure 6 This is a schematic diagram of the structure of a dynamic equipment status detection device provided according to an embodiment of the present invention. Detailed Implementation

[0025] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0026] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0027] To better understand the embodiments of this application, the technical terms involved in the embodiments of this application are explained below:

[0028] Currently, most vibration monitoring relies on handheld inspection devices by maintenance workers, which is difficult to perform in complex environments. Among known wireless vibration sensors of this type, only a small portion of data processing functionality is integrated, transmitting raw waveform data to a server. This transmission may result in data loss, affecting the server's data analysis and equipment diagnostics.

[0029] Currently, vibration monitoring generates a massive amount of data, requiring large-scale transmission to local servers for processing and evaluation. This can easily lead to bandwidth congestion and data transmission delays, and significantly reduces the timeliness of data evaluation for the equipment itself. Furthermore, in terms of vibration characteristic calculation, only a single feature in the time and frequency domain is typically considered to assess the equipment's operating status, resulting in a relatively simplistic evaluation metric.

[0030] To address the aforementioned issues, this application provides relevant solutions, which are detailed below.

[0031] According to an embodiment of this application, a method embodiment for detecting the state of moving equipment is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0032] The methods and embodiments provided in this application can be executed on mobile terminals, computer terminals, or similar computing devices. Figure 1 A hardware block diagram of a computer terminal for implementing a method for detecting the state of moving equipment is shown. Figure 1 As shown, the computer terminal 10 may include one or more processors 102 (shown as 102a, 102b, ..., 102n in the figure) 102 (processor 102 may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0033] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10. As involved in the embodiments of this application, the data processing circuits serve as a form of processor control (e.g., selection of a variable resistor termination path connected to an interface).

[0034] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the moving equipment status detection method in this embodiment. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the above-mentioned moving equipment status detection method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0035] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0036] The display may be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10.

[0037] Under the above operating environment, embodiments of this application provide a method for detecting the state of moving equipment, such as... Figure 2 As shown, the method includes the following steps:

[0038] Step S202: Collect vibration data of the moving equipment, wherein the vibration data includes at least one of the following: vibration signal sequence and raw vibration acceleration data, and the moving equipment is a rotating moving equipment.

[0039] Optionally, vibration data is collected by sensors, which are also used to locally determine a first trend sequence, a development trend indicator, and a health measure, and store the first trend sequence, the development trend indicator, and the health measure.

[0040] Optionally, the sensor possesses sophisticated edge computing capabilities. After performing a series of calculations on the acquired waveform, it only sends the calculated results to the server, saving transmission time and energy, reducing the amount of data transmitted, and lowering the packet loss rate during data transmission. A wireless vibration sensor is a device that combines wireless communication technology and vibration sensing technology to monitor and measure the vibration status of motor equipment. It typically includes components such as an accelerometer module, a microcontroller, a communication module, and a power management unit. Figure 3 A schematic diagram of the various parts of the sensor is shown, such as... Figure 3 As shown, according to their functions, sensors include a sensing module, a data acquisition section, a data processing section, a data storage section, a communication transmission section, and an energy management section.

[0041] Sensor module: Uses a high-sensitivity accelerometer or vibration sensor to detect vibration signals and convert them into voltage signals.

[0042] Data acquisition module: Acquires voltage signals output by sensors and converts them into digital signals.

[0043] Data Processing Module: The embedded processor receives sensor data and performs real-time data processing and analysis, determining the primary trend sequence, development trend indicators, and health metrics locally. Utilizing edge computing technology, data processing can be performed at the device level (i.e., within the sensor), reducing data transmission and latency. Data processing algorithms include spectral analysis of vibration signals, time-domain analysis, and feature extraction. Online firmware upgrades are supported, allowing for future updates to the data processing algorithms.

[0044] Data storage module: Stores waveform data and edge computing module data.

[0045] Communication transmission module: Enables data transmission between sensors and the server.

[0046] Energy Management Module: The integrated high-efficiency energy management module features low power consumption design and energy-saving sleep mode, extending the service life of the equipment.

[0047] Optionally, Figure 4 This illustrates a process for collecting vibration data from moving equipment, such as... Figure 4 As shown, the vibration data collected from the moving equipment includes:

[0048] (1) Turn on the power supply of the ADC (Analog-to-Digital Converter, i.e., data acquisition module) and the power supply of the sensor module.

[0049] (2) Vibration data acquisition. Vibration data is acquired in real time, and the sampling rate and number of sampling points are configurable. Simultaneous sampling of XYZ axes is supported, and the three-axis data can be analyzed in a linked manner.

[0050] (3) After the data acquisition is completed, turn off the ADC power supply and the sensor module power supply. No further data acquisition will be performed during subsequent calculations to reduce the power consumption of the module and achieve a low-power system design.

[0051] Step S204: Determine the first trend sequence of the moving equipment based on the vibration data, wherein the first trend sequence includes at least one of the following: historical trend sequence of frequency domain characteristics, historical trend sequence of rolling bearing characteristic frequency, historical trend sequence of gearbox characteristic frequency, historical trend sequence of vibration intensity, and historical trend sequence of time domain dimensionless characteristics.

[0052] In the technical solution provided in step S204, determining the first trend sequence of the moving equipment based on vibration data includes: performing a fast Fourier transform on the vibration signal sequence to obtain a first frequency value sequence and a first amplitude sequence corresponding to the first frequency value sequence; screening peak points in the first amplitude sequence whose relative height is greater than a preset threshold, and adding the frequency value corresponding to the peak point to the second frequency value sequence, wherein the relative height is the difference between the peak value and the valley value within a preset interval; determining multiple candidate frequency points in the second frequency value sequence based on a preset interval and a preset distance; determining a target frequency point from the candidate frequency points, and using the frequency corresponding to the target frequency point as the rotational frequency of the moving equipment; and determining the historical trend sequence of the frequency domain characteristics of the moving equipment, the historical trend sequence of the rolling bearing characteristic frequency, and the historical trend sequence of the gearbox characteristic frequency based on the rotational frequency.

[0053] Optionally, determining the target frequency point from the candidate frequency points includes: determining multiple harmonic frequency values ​​corresponding to the candidate frequency points; determining the frequency value with the smallest difference from each harmonic frequency value in the second frequency value sequence as an approximate frequency value that corresponds one-to-one with each harmonic frequency value; determining the sum of the differences between each harmonic frequency value and the approximate frequency value corresponding to the harmonic frequency value as the sum of the differences of the candidate frequency points; and determining the candidate frequency point with the smallest sum of differences as the target frequency point.

[0054] Optionally, time-domain feature values ​​are calculated, and 10 types of feature data, such as mean, peak value, effective value, standard deviation, root square amplitude, skewness, kurtosis, peak factor, waveform factor, and margin factor, are calculated based on the original vibration data.

[0055] Optionally, the rotational speed of the equipment can be estimated based on vibration data, and the calculation method is as follows:

[0056] 1) Perform FFT (Fast Fourier Transform) on the vibration signal sequence to obtain its frequency value sequence F (first frequency value sequence) and its corresponding amplitude sequence A (first amplitude sequence);

[0057] 2) Calculate the median of the amplitude sequence A, denoted as Am;

[0058] 3) For the amplitude sequence A, perform relative height difference peak search where the relative peak is greater than 0.1*Am (i.e., the preset threshold), and denote it as the amplitude sequence Ap and the frequency sequence Fp. The specific steps are as follows: 1. Select the point in A whose value is higher than the values ​​at the left and right ends (i.e., the peak point) as the peak sequence A1; 2. Place a mark on the peak and denote it as A11; 3. Extend a horizontal line from the peak to the left and right until the line passes through the signal or reaches the left and right ends; 4. Find the minimum signal value in each of the two intervals defined in step 3. This point is one of the troughs or signal endpoints; 5. Among the minimum values ​​of the two intervals, the higher one is the reference level Ao (i.e., the trough value). If A11-Ao>0.1*Am, then the amplitude value of this point is placed in the Ap sequence, and the frequency value of this point is placed in the Fp sequence (the second frequency value sequence);

[0059] 4) Determine the frequency search interval for rotational speed search, denoted as [r1, r2, s], where r1 is the starting value, r2 is the ending value, and s is the interval value.

[0060] 5) Starting from r1, search at intervals of s. For each search frequency, denoted as Fi (i.e., the frequency value corresponding to the candidate frequency point), find the corresponding harmonic frequencies Fi2-Fi6. For each value in Fi1-Fi6, find the value closest to it in the Fp sequence (i.e., the approximate frequency value), record each difference Ei1-Ei6, and sum them up to Ei.

[0061] 6) The point with the lowest sum of differences (i.e., the sum of differences) among all points within the search interval is taken as the device's frequency Fr.

[0062] Optionally, based on the calculated rotational frequency Fr, the frequencies of its 1st to 12th harmonics and their corresponding amplitudes are calculated, resulting in historical trend sequences F1-F12 of 12 frequency domain features: The frequency values ​​of its 1st to 12th harmonics are calculated based on Fr, these frequency points corresponding to 1, 2, 3, up to 12 times the device's fundamental frequency, respectively. The purpose of this step is to identify characteristic frequencies closely related to the device's operating state. Subsequently, for each calculated characteristic frequency, the closest peak frequency is found from the amplitude sequence Ap calculated from the sensor edge, thereby extracting the corresponding amplitude. By combining these amplitudes with the time series, historical trend sequences F1 to F12 of 12 frequency domain features are constructed, each sequence representing the vibration energy change of the device at a specific harmonic frequency.

[0063] The construction of historical trend sequences F1 to F12 helps monitor the changes in vibration energy of equipment over time at different octave frequencies, enabling the timely detection of early signs of equipment failure, such as bearing wear and gear damage, as these failures typically cause a significant increase in vibration energy at specific octave frequencies. By analyzing these sequences, the health status of the equipment can be more accurately assessed, potential failures predicted, and corresponding preventative maintenance measures taken to reduce downtime and improve equipment reliability and production efficiency. This historical trend analysis method based on frequency domain characteristics significantly enhances the fault diagnosis capabilities of wireless vibration sensors in edge computing and the comprehensiveness of equipment health status assessment.

[0064] Optionally, based on the calculated rotational frequency Fr and the bearing parameters set by the host computer, the bearing fault characteristic frequencies are calculated, and the characteristic frequencies and amplitudes of the bearings are searched to obtain the historical trend sequence FB of the rolling bearing characteristic frequencies. First, the bearing parameters of the device where the wireless vibration sensor is located are obtained. These parameters typically include information such as the bearing type (e.g., deep groove ball bearing, tapered roller bearing), inner and outer diameters, number of rollers, and bearing cage structure. Using these parameters, the bearing fault frequency calculation formula can be applied, with the rotational frequency Fr as input, to calculate a series of bearing fault characteristic frequencies, such as ball rotational frequency and inner / outer ring fault frequencies. These frequencies are typical frequency points appearing in the vibration signal during bearing faults and can reflect abnormal conditions in the internal structure of the bearing.

[0065] Next, based on the spectral analysis results from edge computing using wireless vibration sensors, the calculated bearing fault characteristic frequencies are searched to identify the vibration amplitude at each characteristic frequency point. This process essentially compares the spectral data with the theoretical fault characteristic frequencies, finds the peak frequency in the actual vibration signal that is closest to the theoretical frequency, and records its amplitude. Over time, this amplitude data will be continuously collected and stored as part of the historical trend sequence (FB) of rolling bearing characteristic frequencies, providing time-series data on bearing health status.

[0066] Optionally, based on the calculated rotational frequency Fr, the gear meshing frequency is calculated according to the gear parameters set by the host computer, and the frequency and amplitude of the gear meshing frequency are searched to obtain the historical trend sequence FG of the gearbox characteristic frequency. First, relevant parameters of the gearbox are obtained from the host computer, including key information such as gear module, number of teeth, gear center distance, and gear speed. These parameters are crucial for calculating the gear meshing frequency, which is directly related to the number of teeth and the speed of the gear. Using the rotational frequency Fr, combined with the gear parameters, the gear meshing frequency calculation formula is applied to calculate the theoretical meshing frequency of the gear under normal operating conditions.

[0067] Subsequently, the calculated gear meshing frequency is finely searched using the spectrum analysis results from the edge computing module of the wireless vibration sensor. Spectrum analysis provides the intensity distribution of the vibration signal at various frequency points. This search process identifies the frequency point closest to the theoretical value by comparing the theoretical frequency with the actual spectrum data, and records the vibration intensity at that point.

[0068] Over time, these vibration intensity data at gear meshing frequencies will be continuously recorded, forming a historical trend sequence FG of gearbox characteristic frequencies.

[0069] Optionally, based on the real-time intensity I of the sensor Ins and intensity historical data sequence I InsTrend Six types of time-domain dimensionless features (skewness factor historical trend sequence I) SkewTrend Historical trend sequence of kurtosis factor I KurtTrend Waveform Factor Historical Trend Sequence I ShapeTrend Peak Factor Historical Trend Sequence I CresTrend Historical trend sequence of pulse factor I ImpTrend Margin Factor Historical Trend Series I ClearTrend The overall health index of the equipment is calculated. The above sequence factors are calculated using the following formula:

[0070]

[0071] I Cres =x p / x RMS (4)

[0072]

[0073] In the formula, x(n) represents the vibration data waveform collected by the sensor, and N represents the number of points in the data waveform. σ represents the mean of the waveform data. x The standard deviation of waveform data, x RMS x represents the root mean square value of the waveform data. p This indicates the peak value of the waveform data.

[0074] Step S206: Determine the values ​​of the development trend indicators corresponding to each first trend sequence based on the first trend sequence.

[0075] In the technical solution provided in step S206, determining the values ​​of the development trend indicators corresponding to each first trend sequence based on the first trend sequence includes: filtering the first trend sequence; determining the second trend sequence based on the filtered first trend sequence; and determining the values ​​of the development trend indicators based on the second trend sequence.

[0076] Alternatively, the second trend sequence can be determined according to the following formula: Where Y = {y1, y2, ..., yn} is the second trend sequence, X = {x1, x2, ..., xn} is the first trend sequence, t is the sampling time corresponding to each sampling point in the first trend sequence, and λ is the preset regularization parameter.

[0077] Alternatively, the value of the development trend indicator can be determined according to the following formula: Where Y = {y1, y2, ..., yn} is the second trend sequence, and Δt is the time difference between adjacent sampling points in the second trend sequence.

[0078] Optionally, determining the second trend sequence includes:

[0079] 1) The ratio f1 of real-time intensity to intensity threshold is used as the severity level exceeding the intensity level 1 / 2 / 3 threshold;

[0080] 2) The slope of the intensity interval and f2 are used as measures of the degree of intensity development trend. The calculation method is as follows:

[0081] 1. Obtain the historical trend sequence of intensity X = {x1, x2, ..., xn};

[0082] 2. Filter X and extract its overall trend to obtain Y = {y1, y2, ..., yn}, as shown in the following formula. The minimization optimization method is a general method and will not be elaborated further:

[0083]

[0084] 3. Calculate the interval slope of Y and f2, as follows:

[0085]

[0086] Where Δt is the time difference between adjacent sampling points in the Y sequence.

[0087] The interval slopes of the six dimensionless indicators and f3, f4, f5, f6, f7, f8, as well as the historical trend sequences of frequency domain characteristics, the historical trend sequences of rolling bearing characteristic frequencies, and the interval slopes of gearbox characteristic frequency historical trend sequences and f9(1-12), f10, f11 are used as measures of the degree of development trend of time domain indicators. The corresponding relationships are shown in the table below, and the calculation method is the same as above.

[0088]

[0089] Step S208: Determine the health metric value based on the development trend indicator and the preset weight corresponding to the development trend indicator.

[0090] Optionally, the health metric of the motor can be obtained by weighted summation based on the above indicators. Where wi represents the weight of each indicator in measuring health.

[0091] Step S210: Upload the first trend sequence, development trend indicators, and health measurement values ​​to the server used to determine the status of the moving equipment.

[0092] Optionally, wireless vibration sensors can perform data processing and filtering locally on the device, transmitting only important data results (first trend sequence, development trend indicators, health measurement values) to the cloud or central server. This reduces the amount of data transmitted and network bandwidth usage, better protects the privacy and security of sensor data, reduces the data transmission frequency and energy consumption of wireless vibration sensors, and extends the battery life of sensor devices.

[0093] Optionally, Figure 5 An eigenvalue calculation process is shown, such as Figure 5 As shown, time-domain characteristics, frequency-domain amplitude, vibration intensity, vibration intensity trend, gear meshing frequency amplitude, bearing characteristic frequency amplitude, and harmonic characteristics are calculated using the original waveform data. Then, the equipment health is calculated, and the calculation results are transmitted to the server via communication.

[0094] Through the above steps, data transmission latency and bandwidth consumption can be reduced, enabling real-time processing and response to vibration data, thus improving the efficiency and performance of the sensor system. In terms of edge feature calculation, by integrating time-frequency domain features and impact features, the system effectively monitors and assesses the condition and health of rotating equipment. Edge computing wireless vibration sensors can be used to monitor and analyze equipment vibration, enabling health monitoring, preventative maintenance, and fault diagnosis, thereby improving equipment reliability and production efficiency. Specifically, this application has the following advantages:

[0095] (1) Edge computing functionality is added to wireless vibration sensors. Real-time data processing and analysis of collected vibration data reduces the fault assessment cycle of motor equipment and quickly characterizes the current operational stability of the motor equipment. With edge computing, wireless vibration sensors can process and filter data locally on the device, transmitting only important data results to the cloud or central server. This reduces the amount of data transmitted and network bandwidth usage, better protects the privacy and security of sensor data, reduces the data transmission frequency and energy consumption of wireless vibration sensors, and extends the battery life of sensor equipment. Multi-feature value extraction of vibration waveforms at the sensor edge, including the characteristic frequency amplitudes of key components such as bearings and gears, not only accurately identifies mechanical fault types but also significantly reduces data transmission volume, improving the transmission stability of wireless sensors. The multi-feature values ​​calculated by edge computing are more intuitive and easier to use, and the amount of data transmitted is smaller. It eliminates the need for multi-layer data forwarding and manual judgment of equipment conditions, resulting in more stable wireless communication, reduced packet loss, and more reliable use of wireless vibration sensors in industrial scenarios.

[0096] Multi-indicator feature calculation and joint evaluation function. In addition to vibration waveform filtering, time-domain feature calculation, and frequency-domain feature calculation, it also takes into account bearing feature value calculation, gear meshing feature value calculation, and equipment health assessment. It can analyze the equipment's fault status from multiple perspectives. The time-frequency domain features calculated by the edge computing and the frequency amplitude of key components such as bearings and gears can effectively reflect the presence and type of equipment faults. The health value will effectively assess the overall operating status of the current equipment. In addition to conventional vibration waveform filtering, time-domain feature calculation, and frequency-domain feature calculation, it also takes into account bearing feature value calculation, gear meshing feature value, and equipment health assessment, enabling a comprehensive multi-dimensional evaluation of the equipment.

[0097] A method for assessing equipment health based on multi-feature thresholds and trend changes. Equipment health can be used to evaluate the real-time operating status of equipment. This patent considers multiple feature values ​​and constructs a comprehensive equipment health assessment system based on threshold values ​​and trend changes. This system can comprehensively reflect the health status of the equipment. It comprehensively assesses the operating status of the equipment by weighting the trend changes of six categories of time-domain dimensionless feature values, such as vibration intensity thresholds and trend changes, and waveform factors. This facilitates real-time judgment of the equipment's health status by personnel. Equipment health can be used to assess the real-time operating status of equipment. The method embodiment of this application constructs a comprehensive equipment health assessment system based on intensity threshold values ​​and multi-feature trend changes, which can comprehensively reflect the health status of the equipment.

[0098] This application provides a moving equipment condition detection device. Figure 6 This is a schematic diagram of the device, as shown below. Figure 6As shown, the device includes: a data acquisition module 60 for acquiring vibration data of a moving device, wherein the vibration data includes at least one of the following: a vibration signal sequence and raw vibration acceleration data, and the moving device is a rotating moving device; a first determination module 62 for determining a first trend sequence of the moving device based on the vibration data, wherein the first trend sequence includes at least one of the following: a historical trend sequence of frequency domain characteristics, a historical trend sequence of rolling bearing characteristic frequencies, a historical trend sequence of gearbox characteristic frequencies, a historical trend sequence of vibration intensity, and a historical trend sequence of time domain dimensionless characteristics; a second determination module 64 for determining the values ​​of development trend indicators corresponding to each first trend sequence based on the first trend sequence; a third determination module 66 for determining a health measurement value based on the development trend indicators and preset weights corresponding to the development trend indicators; and an upload module 68 for uploading the first trend sequence, development trend indicators, and health measurement value to a server for determining the status of the moving device.

[0099] In some embodiments of this application, the first determining module 62 determines the first trend sequence of the moving equipment based on vibration data, including: performing a fast Fourier transform on the vibration signal sequence to obtain a first frequency value sequence and a first amplitude sequence corresponding to the first frequency value sequence; screening peak points in the first amplitude sequence whose relative height is greater than a preset threshold, and adding the frequency value corresponding to the peak point to a second frequency value sequence, wherein the relative height is the difference between the peak value and the valley value within a preset interval; determining multiple candidate frequency points in the second frequency value sequence according to a preset interval and a preset distance; determining a target frequency point from the candidate frequency points, and using the frequency corresponding to the target frequency point as the rotational frequency of the moving equipment; and determining the historical trend sequence of the frequency domain characteristics of the moving equipment, the historical trend sequence of the rolling bearing characteristic frequency, and the historical trend sequence of the gearbox characteristic frequency based on the rotational frequency.

[0100] In some embodiments of this application, the first determining module 62 determines the target frequency point from the candidate frequency points by: determining a plurality of harmonic frequency values ​​corresponding to the candidate frequency points; determining the frequency value with the smallest difference from each harmonic frequency value in the second frequency value sequence as an approximate frequency value that corresponds one-to-one with each harmonic frequency value; determining the sum of the differences between each harmonic frequency value and the approximate frequency value corresponding to the harmonic frequency value as the sum of the differences of the candidate frequency points; and determining the candidate frequency point with the smallest sum of differences as the target frequency point.

[0101] In some embodiments of this application, the second determining module 64 determines the value of the development trend indicator corresponding to each first trend sequence based on the first trend sequence, including: filtering the first trend sequence; determining the second trend sequence based on the filtered first trend sequence; and determining the value of the development trend indicator based on the second trend sequence.

[0102] In some embodiments of this application, the second determining module 64 determines the second trend sequence according to the following formula: Where Y = {y1, y2, ..., yn} is the second trend sequence, X = {x1, x2, ..., xn} is the first trend sequence, t is the sampling time corresponding to each sampling point in the first trend sequence, and λ is the preset regularization parameter.

[0103] In some embodiments of this application, the second determining module 64 determines the value of the development trend indicator based on the following formula: Where Y = {y1, y2, ..., yn} is the second trend sequence, and Δt is the time difference between adjacent sampling points in the second trend sequence.

[0104] In some embodiments of this application, vibration data is collected by a sensor, which is also used to locally determine a first trend sequence, a development trend index, and a health measure, and to store the first trend sequence, the development trend index, and the health measure.

[0105] It should be noted that each module in the above-mentioned moving equipment status detection device can be a program module (for example, a set of program instructions to implement a certain function) or a hardware module. For the latter, it can be manifested in the following forms, but is not limited to them: each of the above modules is manifested as a processor, or the functions of each of the above modules are implemented by a processor.

[0106] This application provides a non-volatile storage medium storing a program. During program execution, the program controls the device containing the non-volatile storage medium to perform the following moving equipment status detection method: collecting vibration data of the moving equipment, wherein the vibration data includes at least one of the following: a vibration signal sequence and raw vibration acceleration data, and the moving equipment is a rotating moving equipment; determining a first trend sequence of the moving equipment based on the vibration data, wherein the first trend sequence includes at least one of the following: a historical trend sequence of frequency domain characteristics, a historical trend sequence of rolling bearing characteristic frequencies, a historical trend sequence of gearbox characteristic frequencies, a historical trend sequence of vibration intensity, and a historical trend sequence of time-domain dimensionless characteristics; determining the values ​​of development trend indicators corresponding to each first trend sequence based on the first trend sequence; determining a health measurement value based on the development trend indicators and preset weights corresponding to the development trend indicators; and uploading the first trend sequence, development trend indicators, and health measurement value to a server used to determine the status of the moving equipment.

[0107] This application provides an electronic device, including a memory and a processor. The processor is used to run a program stored in the memory. During program execution, the following method for detecting the state of a moving device is performed: collecting vibration data of the moving device, wherein the vibration data includes at least one of the following: a vibration signal sequence and raw vibration acceleration data, and the moving device is a rotating moving device; determining a first trend sequence of the moving device based on the vibration data, wherein the first trend sequence includes at least one of the following: a historical trend sequence of frequency domain characteristics, a historical trend sequence of rolling bearing characteristic frequencies, a historical trend sequence of gearbox characteristic frequencies, a historical trend sequence of vibration intensity, and a historical trend sequence of time-domain dimensionless characteristics; determining the values ​​of development trend indicators corresponding to each first trend sequence based on the first trend sequence; determining a health measurement value based on the development trend indicators and preset weights corresponding to the development trend indicators; and uploading the first trend sequence, development trend indicators, and health measurement value to a server used to determine the state of the moving device.

[0108] This application provides a computer program product, including a computer program that, when executed by a processor, implements the following method for detecting the state of a moving device: collecting vibration data of the moving device, wherein the vibration data includes at least one of the following: a vibration signal sequence and raw vibration acceleration data, and the moving device is a rotating moving device; determining a first trend sequence of the moving device based on the vibration data, wherein the first trend sequence includes at least one of the following: a historical trend sequence of frequency domain characteristics, a historical trend sequence of rolling bearing characteristic frequencies, a historical trend sequence of gearbox characteristic frequencies, a historical trend sequence of vibration intensity, and a historical trend sequence of time domain dimensionless characteristics; determining the values ​​of development trend indicators corresponding to each first trend sequence based on the first trend sequence; determining a health measurement value based on the development trend indicators and preset weights corresponding to the development trend indicators; and uploading the first trend sequence, development trend indicators, and health measurement value to a server used to determine the state of the moving device.

[0109] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0110] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0111] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0112] Furthermore, the functional units in the various embodiments of this application 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.

[0113] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to related technologies, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0114] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for detecting the condition of moving equipment, characterized in that, include: Vibration data of a moving device is collected, wherein the vibration data includes at least one of the following: a vibration signal sequence and raw vibration acceleration data, and the moving device is a rotating moving device; Determining a first trend sequence of the moving equipment based on the vibration data includes: performing a fast Fourier transform on the vibration signal sequence to obtain a first frequency value sequence and a first amplitude sequence corresponding to the first frequency value sequence; filtering peak points in the first amplitude sequence whose relative height is greater than a preset threshold, and adding the frequency value corresponding to the peak point to a second frequency value sequence, wherein the relative height is the difference between the peak value and the valley value within a preset interval; determining multiple candidate frequency points in the second frequency value sequence according to a preset interval and a preset distance; determining multiple harmonic frequency values ​​corresponding to the candidate frequency points; and determining the frequency value with the smallest difference from each harmonic frequency value in the second frequency value sequence as a one-to-one match with each harmonic frequency value. The approximate frequency value is determined; the sum of the differences between each of the harmonic frequency values ​​and the approximate frequency value corresponding to the harmonic frequency value is used as the sum of differences of the candidate frequency points; the candidate frequency point with the smallest sum of differences is determined as the target frequency point, and the frequency corresponding to the target frequency point is used as the rotational frequency of the moving equipment; based on the rotational frequency, the historical trend sequence of the frequency domain characteristics of the moving equipment, the historical trend sequence of the rolling bearing characteristic frequency, and the historical trend sequence of the gearbox characteristic frequency are determined, wherein the first trend sequence includes at least one of the following: the historical trend sequence of frequency domain characteristics, the historical trend sequence of rolling bearing characteristic frequency, the historical trend sequence of gearbox characteristic frequency, the historical trend sequence of vibration intensity, and the historical trend sequence of time domain dimensionless characteristics; The values ​​of the development trend indicators corresponding to each of the first trend sequences are determined based on the first trend sequences; The health metric is determined based on the development trend indicators and the preset weights corresponding to the development trend indicators; The first trend sequence, development trend indicators, and health measurement values ​​are uploaded to a server used to determine the status of the moving equipment.

2. The method for detecting the condition of moving equipment according to claim 1, characterized in that, Determining the values ​​of the development trend indicators corresponding to each of the first trend sequences based on the first trend sequences includes: The first trend sequence is filtered. The second trend sequence is determined based on the filtered first trend sequence; The value of the development trend indicator is determined based on the second trend sequence.

3. The method for detecting the condition of moving equipment according to claim 2, characterized in that, The second trend sequence is determined using the following formula: ; in, This is the second trend sequence. Let t be the first trend sequence, and t be the sampling time corresponding to each sampling point in the first trend sequence. These are the preset regularization parameters.

4. The method for detecting the condition of moving equipment according to claim 2, characterized in that, The value of the development trend indicator is determined according to the following formula: ; in, This is the second trend sequence. is the time difference between each adjacent sampling point in the second trend sequence.

5. The method for detecting the condition of moving equipment according to claim 1, characterized in that, The vibration data is collected by a sensor, which is also used to locally determine the first trend sequence, the development trend index, and the health measure, and to store the first trend sequence, the development trend index, and the health measure.

6. A device for detecting the condition of moving equipment, characterized in that, include: The acquisition module is used to acquire vibration data of the moving equipment, wherein the vibration data includes at least one of the following: vibration signal sequence and raw vibration acceleration data, and the moving equipment is a rotating moving equipment; A first determining module is configured to determine a first trend sequence of the moving equipment based on the vibration data, comprising: performing a fast Fourier transform on the vibration signal sequence to obtain a first frequency value sequence and a first amplitude sequence corresponding to the first frequency value sequence; filtering peak points in the first amplitude sequence whose relative height is greater than a preset threshold, and adding the frequency value corresponding to the peak point to a second frequency value sequence, wherein the relative height is the difference between the peak value and a valley value within a preset interval; determining multiple candidate frequency points in the second frequency value sequence based on a preset interval and a preset distance; determining multiple harmonic frequency values ​​corresponding to the candidate frequency points; and determining the frequency value with the smallest difference from each harmonic frequency value in the second frequency value sequence as the harmonic frequency value. The approximate frequency value corresponding to each value is determined; the sum of the differences between each of the harmonic frequency values ​​and the approximate frequency value corresponding to the harmonic frequency value is determined as the sum of the differences of the candidate frequency points; the candidate frequency point with the smallest sum of differences is determined as the target frequency point, and the frequency corresponding to the target frequency point is determined as the rotational frequency of the moving equipment; based on the rotational frequency, the historical trend sequence of the frequency domain characteristics of the moving equipment, the historical trend sequence of the rolling bearing characteristic frequency, and the historical trend sequence of the gearbox characteristic frequency are determined, wherein the first trend sequence includes at least one of the following: the historical trend sequence of frequency domain characteristics, the historical trend sequence of rolling bearing characteristic frequency, the historical trend sequence of gearbox characteristic frequency, the historical trend sequence of vibration intensity, and the historical trend sequence of time domain dimensionless characteristics; The second determining module is used to determine the values ​​of the development trend indicators corresponding to each of the first trend sequences based on the first trend sequences; The third determining module is used to determine the health measurement value based on the development trend indicator and the preset weight corresponding to the development trend indicator; The upload module is used to upload the first trend sequence, development trend indicators, and health measurement values ​​to a server used to determine the status of the moving equipment.

7. A non-volatile storage medium, characterized in that, The non-volatile storage medium stores a program, wherein when the program is executed, it controls the device where the non-volatile storage medium is located to execute the moving equipment state detection method according to any one of claims 1 to 5.

8. An electronic device, characterized in that, include: A memory and a processor, the processor being configured to run a program stored in the memory, wherein the program, when running, executes the moving equipment state detection method according to any one of claims 1 to 5.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the moving equipment state detection method according to any one of claims 1 to 5.

Images