Mechanical health early warning method and system based on Internet of Things

Abstract

The invention relates to a mechanical health early warning method and system based on the Internet of Things. Communication networking is performed through network access information of each vibration sensor, communication connection is performed based on the network access information of all the vibration sensors, and a multi-dimensional detection histogram data matrix is constructed based on feedback information of all the vibration sensors. Simple, three-dimensional feedback information is analyzed based on feedback information of all vibration sensors so as to determine working positions and three-dimensional virtual space positions of all the vibration sensors. And constructing a multi-dimensional detection rectangular data matrix by using a three-dimensional virtual space position. And receiving a vibration signal of each vibration sensor, and based on the real-time vibration signal, performing data filling of the multi-dimensional detection rectangular data matrix to form a rectangular data matrix with a timestamp.

Description

Technical Field

[0001] This application relates to the technical field of mechanical vibration detection, and particularly to a mechanical health warning method and system based on the Internet of Things. Background Art

[0002] An important indicator of mechanical health is the damage index of mechanical fatigue. Mechanical fatigue refers to the process in which materials and components gradually produce local permanent cumulative damage at one or several places under cyclic stress or cyclic strain, and cracks are generated after a certain number of cycles or sudden complete fracture occurs. When materials and structures are subjected to repeatedly changing loads, although the stress value never exceeds the strength limit of the material, and even is lower than the elastic limit, failure may still occur. This phenomenon of material and structure failure under repeated action of alternating loads is the fatigue failure of machinery.

[0003] In practical engineering applications, it is difficult to detect the mechanical fatigue of mechanical structures, and the mechanical fatigue of mechanical structures will affect the working continuity of the entire mechanical system. Therefore, it is necessary to propose a mechanical health warning method and system based on the Internet of Things for the defect that it is difficult to detect the mechanical fatigue of mechanical structures. Summary of the Invention

[0004] Based on this, it is necessary to propose a mechanical health warning method and system based on the Internet of Things for the defect that it is difficult to detect the mechanical fatigue of mechanical structures.

[0005] This application provides a mechanical health warning method based on the Internet of Things, including: Receiving the network access information of each vibration sensor; Based on the network access information of all vibration sensors, constructing a multi-dimensional detection histogram data array; Receiving the vibration signals of each vibration sensor; Based on the real-time vibration signals, forming a histogram data array with time stamps; Using the system time, forming multiple histogram data arrays with time stamps; Feeding back the information of replacing the detection target, and returning to the step of receiving the network access information of each vibration sensor until N groups of histogram data arrays are received to form a sample of the warning method; one group of histogram data arrays includes multiple histogram data arrays with time stamps of the same detection target at the system time; N is a positive integer; Using the N groups of histogram data arrays to train the mechanical health warning model to be trained; Obtaining the trained mechanical health warning model; Incorporating the received real-time vibration sensor data into the trained mechanical health warning model to obtain the mechanical health conclusion of the mechanical system monitored by the vibration sensor; Based on the mechanical health conclusion, feedback the maintenance plan of the mechanical system.

[0006] Preferably, the receiving the network access information of each vibration sensor includes: Select the network access information of one vibration sensor; Based on the network access information of the vibration sensor, determine the device serial number of the vibration sensor; Using the device serial number of the vibration sensor, determine the network access communication method of the vibration sensor; Return the network access information of the selected one vibration sensor until all vibration sensors are selected.

[0007] Preferably, the constructing the multi-dimensional detection histogram data array based on the network access information of all vibration sensors includes: Establish a virtual three-dimensional position coordinate system for the multi-dimensional detection histogram data array; Based on the virtual three-dimensional position coordinate system, set the position points of the vibration sensors; Select one vibration sensor; Based on the network access communication method of the selected vibration sensor, receive the position information of the vibration sensor; Using the position information of the vibration sensor, incorporate the position information of the selected vibration sensor into the position points of the vibration sensors; Return the selected one vibration sensor until all vibration sensors are selected.

[0008] Preferably, the constructing the multi-dimensional detection histogram data array based on the network access information of all vibration sensors further includes: Save the three-dimensional data coordinates of the position points of the vibration sensors in the virtual three-dimensional position coordinate system; Call one three-dimensional data coordinate; Based on the called three-dimensional data coordinate, establish vector parameters; Return the called one three-dimensional data coordinate until all the three-dimensional data coordinates of the position points of the vibration sensors in the virtual three-dimensional position coordinate system are called.

[0009] Preferably, after receiving the vibration signal of each vibration sensor, it includes: Select the vibration signal of one vibration sensor; Analyze the vibration signal of the selected vibration sensor; Obtain the vibration intensity of the vibration sensor and the spatial direction of the vibration; Take the vibration intensity of the vibration sensor and the spatial direction of the vibration as vector parameters; Return the vibration signal of the selected one vibration sensor until all vibration sensors are selected.

[0010] Preferably, before forming the histogram data array with timestamps based on the real-time vibration signal, it includes: Calling the initial vibration waveform of the initial vibration source; Determining the first-order vibration frequency of the detection target; Sequentially connecting the ends of the vector parameters of the virtual three-dimensional position coordinate system; Obtaining the actual resonance three-dimensional curve graph; Judging whether the initial vibration waveform is consistent with the actual resonance three-dimensional curve graph; If the initial vibration waveform is consistent with the actual resonance three-dimensional curve Figure 1 Then determine that the mechanical health of the mechanical system meets the threshold; If the initial vibration waveform is inconsistent with the actual resonance three-dimensional curve graph, then judge whether the actual resonance three-dimensional curve graph is consistent with the first-order vibration frequency of the detection target.

[0011] Preferably, judging whether the actual resonance three-dimensional curve graph is consistent with the first-order vibration frequency of the detection target includes: If the actual resonance three-dimensional curve graph is consistent with the first-order vibration frequency of the detection target, then determine that the mechanical system is damaged; If the actual resonance three-dimensional curve graph is inconsistent with the first-order vibration frequency of the detection target, then feedback the instruction feedback for executing the analysis program; the analysis program is the actual resonance three-dimensional curve graph analysis program.

[0012] Preferably, the analysis program includes: Calling the first-order vibration graph generated by the first-order vibration frequency of the detection target; Using the timestamp to match the first-order vibration graph and the actual resonance three-dimensional curve graph corresponding to the first-order vibration graph; Determining the same-frequency points and asynchronous points; Including the timestamp, the same-frequency points and the asynchronous points into the data set of the histogram data array with timestamps.

[0013] Preferably, forming the histogram data array with timestamps based on the real-time vibration signal includes: Calling the data set including the timestamp, the same-frequency points and the asynchronous points into the histogram data array with timestamps; Replacing the same-frequency points and asynchronous points of the multi-dimensional detection histogram data array based on the timestamp of the data set; Forming the histogram data array with timestamps.

[0014] This application also provides an IoT-based mechanical health warning system, including: A host computer for executing the IoT-based mechanical health warning method described above; Vibration sensors, all communicatively connected to the host computer.

[0015] The present application relates to a mechanical health warning method and system based on the Internet of Things. Through the network access information of each vibration sensor, communication networking is carried out. Based on the network access information of all vibration sensors, communication connections are established. Based on the feedback information of all vibration sensors, a multi-dimensional detection histogram data array is constructed. Briefly, based on the feedback information of all vibration sensors, the three-dimensional feedback information is analyzed to determine the working positions and three-dimensional virtual space positions of all vibration sensors. Using the three-dimensional virtual space positions, a multi-dimensional detection histogram data array is constructed. The vibration signals of each vibration sensor are received, and based on the real-time vibration signals, the data filling of the multi-dimensional detection histogram data array is carried out to form a histogram data array with a time stamp. The information of replacing the detection target is fed back, and the network access information of each vibration sensor is received again until N groups of histogram data arrays are received. Using the system time, multiple histogram data arrays with time stamps are formed.

[0016] A group of histogram data arrays includes multiple histogram data arrays with time stamps of the same detection target under the system time. Using the N groups of histogram data arrays, the mechanical health warning model to be trained is trained. The trained mechanical health warning model is obtained. The received real-time vibration sensor data is incorporated into the trained mechanical health warning model to obtain the mechanical health conclusion of the mechanical system monitored by the vibration sensor. Based on the mechanical health conclusion, the maintenance plan of the mechanical system is fed back. This realizes the technology of effective detection of mechanical fatigue of mechanical structures. Description of the Drawings

[0017] Figure 1 It is a schematic flowchart of a mechanical health warning method based on the Internet of Things provided by an embodiment of the present application.

[0018] Figure 2 It is a structural connection diagram of a mechanical health warning system based on the Internet of Things provided by an embodiment of the present application.

[0019] Reference Signs: 100 - host computer; 200 - vibration sensor. Detailed Embodiments

[0020] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0021] The present application provides a mechanical health warning method based on the Internet of Things.

[0022] As Figure 1 shown, in an embodiment of the present application, a mechanical health warning method based on the Internet of Things includes: S100, receive the network access information of each vibration sensor; S200, based on the network access information of all vibration sensors, construct a multi-dimensional detection histogram data array; S300, receive the vibration signals of each vibration sensor; S400, based on the real-time vibration signals, form a histogram data array with timestamps; S500, use the system time to form multiple histogram data arrays with timestamps; S600, feedback the information of replacing the detection target, and return to the step of receiving the network access information of each vibration sensor until N groups of histogram data arrays are received to form a sample of the early warning method; one group of histogram data arrays includes multiple histogram data arrays with timestamps of the same detection target under the system time; N is a positive integer; S700, use N groups of histogram data arrays to train the mechanical health early warning model to be trained; Specifically, the step of using N groups of histogram data arrays to train the mechanical health early warning model to be trained includes the following steps: Based on the multi-dimensional axes of the multi-dimensional detection histogram data array, that is, the recognition row factor groups of each dimension axis; the factors of the vibration intensity dimension axis to be analyzed can be determined through the vibration signals of the vibration sensors. For example, in product quality analysis, it may include factors such as the function, performance, and appearance of the product, and these factors will be used as the vibration intensity dimension axis. It can be understood that the recognition column factor groups: determine the factors of the second dimension axis related to the row factor groups. For example, for the above product quality analysis example, the column factors can be production processes, raw materials, personnel operations, etc. that affect product quality. These second dimension axes can be used as influencing factors for the maintenance plan of the mechanical system during mechanical health early warning.

[0023] Actually, during the construction of the mechanical health early warning model, the matrix diagram type can be selected as the L-type matrix diagram, T-type matrix diagram, Y-type matrix diagram, or C-type matrix diagram.

[0024] Simply put, the T-type matrix diagram is suitable for representing the relationship or correlation size between two sets of paired factors and is the most basic matrix diagram. For example, to analyze the relationship between employees' work efficiency and work quality, the L-type matrix diagram can be used, with employee names or numbers as row factors and work efficiency and work quality as column factors.

[0025] Due to the real-time nature of timestamps, during the maintenance process, the detection time interval often determines the adaptability of the maintenance plan for this detection cycle. Simple real-time monitoring often results in strong short-term correlation, while the long-term maintenance cost is too high.

[0026] Therefore, the L-shaped matrix diagram is suitable for representing the relationship or correlation size between two sets of paired factors and is the most basic matrix diagram. For example, to analyze the relationship between employees' work efficiency and work quality, an L-shaped matrix diagram can be used, with employee names or numbers as row factors and work efficiency and work quality as column factors. Compared with the L-shaped matrix diagram, the T-shaped matrix diagram is a combined matrix diagram of the L-shaped matrix of factors A and B and the L-shaped matrix diagram of factors A and C, which can analyze the relationship between "defect phenomenon - cause - process" in quality problems, or analyze the relationship between material composition, properties and uses, etc.

[0027] This multi-dimensional detection histogram data array composed of such rectangular diagrams is often an efficient solution for simple maintenance and a feasible solution for maintenance costs.

[0028] S800, obtain the trained mechanical health warning model; S900, incorporate the data of the received real-time vibration sensor into the trained mechanical health warning model to obtain the mechanical health conclusion of the mechanical system monitored by the vibration sensor; S910, based on the mechanical health conclusion, feedback the maintenance plan of the mechanical system.

[0029] This embodiment relates to a mechanical health warning method and system based on the Internet of Things. Through the network access information of each vibration sensor, communication networking is carried out. Based on the network access information of all vibration sensors, communication connection is carried out. Based on the feedback information of all vibration sensors, a multi-dimensional detection histogram data array is constructed. Simply, based on the feedback information of all vibration sensors, the three-dimensional feedback information is analyzed to determine the working positions and three-dimensional virtual space positions of all vibration sensors. Using the three-dimensional virtual space positions, a multi-dimensional detection histogram data array is constructed. Receive the vibration signals of each vibration sensor, and based on the real-time vibration signals, fill the data of the multi-dimensional detection histogram data array to form a histogram data array with a timestamp. Feedback the information of replacing the detection target, and return to receive the network access information of each vibration sensor until N groups of histogram data arrays are received. Using the system time, form multiple histogram data arrays with timestamps.

[0030] A group of histogram data arrays includes multiple histogram data arrays with timestamps of the same detection target at the system time. Use the N groups of histogram data arrays to train the mechanical health warning model to be trained. Obtain the trained mechanical health warning model. Incorporate the data of the received real-time vibration sensor into the trained mechanical health warning model to obtain the mechanical health conclusion of the mechanical system monitored by the vibration sensor. Based on the mechanical health conclusion, feedback the maintenance plan of the mechanical system. This realizes the technology of effective detection of mechanical fatigue of mechanical structures.

[0031] In an embodiment of the present application, S100 includes: S110, select the network access information of a vibration sensor; Specifically, based on the computer networking of a host computer, connecting multiple computers or other network devices to achieve the complex process of data exchange and resource sharing; Briefly, clarify the scale of the network, whether it is a small office, home network, or large enterprise network, etc. Determine the network coverage area. For example, a local area network (LAN) is suitable for a smaller geographical area, while a wide area network (WAN) is used for cross-regional connections; Select the network topology, such as bus topology, star topology, ring topology, tree topology, and mesh topology. In bus topology, all devices are connected through a main line, with a simple structure but relatively low reliability. A node failure may affect the entire network and is often used in small networks. Star topology uses a switch or hub as the central node, and other devices are connected to it through network cables, which is easy to manage and maintain and has strong scalability, being one of the most common networking methods. Ring topology connects devices in sequence to form a closed loop, and signals are transmitted unidirectionally in the loop, with stable data transmission but poor reliability. A node failure may cause the entire network to collapse. Tree topology combines the characteristics of bus topology and star topology, has a hierarchical structure, is suitable for large networks, has good scalability, but is relatively complex to maintain. Mesh topology directly connects each device to multiple other devices, with extremely high reliability and redundancy, but high cost, and is often used in occasions with extremely high requirements for network reliability; S120, based on the network access information of the vibration sensor, determine the device serial number of the vibration sensor; Specifically, as a complete device, the vibration sensor can, based on a modem, achieve the parsing of the network access information of the vibration sensor to realize the complex process of data exchange and resource sharing; The device serial number of the vibration sensor after parsing can be used as the network access identifier of the vibration sensor; S130, use the device serial number of the vibration sensor to determine the network access communication method of the vibration sensor.

[0032] Specifically, in fact, different types of vibration sensors have different working processes. For the vibration sensors for mechanical health warning in the Internet of Things, when the complete device vibration sensor is installed, it often affects the vibration damping of the entire mechanical system; When the installation of the vibration sensor of the complete device does not affect the vibration damping of the entire mechanical system, the factors of the vibration intensity dimension axis to be analyzed can be determined through the vibration signals of the vibration sensors. For example, in product quality analysis, the factors may include aspects such as the function, performance, and appearance of the product, and these factors will serve as the vibration intensity dimension axis. It can be understood that identifying the column factor group: determining the factors of the second dimension axis related to the row factor group. For example, in the above example of product quality analysis, the column factors can be production processes, raw materials, personnel operations, etc. that affect product quality. These second dimension axes can be used as influencing factors for the maintenance plan of the mechanical system during mechanical health warning.

[0033] S140, return the network access information of the selected vibration sensor until all vibration sensors are selected.

[0034] Specifically, computer networking is a systematic project, and this networking process meets the long-term monitoring needs. When considering multiple factors, computer networking should be based on the specific usage requirements of the mechanical equipment, such as usage time, installation level, working intensity, etc. Just from the factor of working intensity, select the appropriate networking method and technical means to ensure the high efficiency of network communication, the reliability and security of detection and warning; Simply put, when the vibration sensor fails, long-term monitoring data can have a high warning effect.

[0035] In an embodiment of the present application, S200 includes: S210, establish a virtual three-dimensional position coordinate system for the multi-dimensional detection histogram data array; S220, based on the virtual three-dimensional position coordinate system, set the position points of the vibration sensors; S230, select a vibration sensor; S240, based on the network access communication method of the selected vibration sensor, receive the position information of the vibration sensor; S250, use the position information of the vibration sensor to incorporate the position information of the selected vibration sensor into the position points of the vibration sensors; S260, return the selected vibration sensor until all vibration sensors are selected; Specifically, determine the types of vibration sensors, such as vibration intensity sensors, vibration vector sensors, and vibration variance sensors. Different virtual space application scenarios have different requirements for the coordinate system. For example, if it is used for virtual game development, a coordinate system that can adapt to various terrains and game mechanisms may be required. When the mechanical structure is used to simulate the virtual vibration environment of game development, for the vibration vector sensor, based on the vibration intensity sensor and the vibration variance sensor, it can be used for mechanical health warning based on the Internet of Things.

[0036] Simple, real-time monitoring data of mechanical structures can relatively simply depict and simulate the virtual vibration environment in game development. By using the Internet of Things networking, the data redundancy of the upper computer is relatively large, and the data processing of redundant data can be simplified relying on a multi-dimensional detection histogram data array to simplify the environmental deployment issues such as the size, proportion, and spatial relationship of mechanical structures. Environmental structure deployment is relatively important for mechanical systems. In fact, corrosion, oil film, etc. of mechanical systems will affect the transmission of vibration. By using data simulation, simulation, and early warning, the accuracy of real-time monitoring and early warning can be relatively simply improved.

[0037] In an embodiment of the present application, S200 further includes: S270, saving the three-dimensional data coordinates of the position points of the vibration sensors in the virtual three-dimensional position coordinate system; S280, calling a three-dimensional data coordinate; S290, establishing vector parameters based on the called three-dimensional data coordinates; S281, returning the called three-dimensional data coordinate until all the three-dimensional data coordinates of the position points of the vibration sensors in the virtual three-dimensional position coordinate system are called.

[0038] Specifically, by introducing additional coordinates, points in n-dimensional space are represented as (n + 1)-dimensional vectors. Homogeneous coordinates are often used in computer graphics to represent two-dimensional and three-dimensional points for various transformations such as translation, rotation, and scaling. For virtual space scenarios that require complex graphic transformations, such as animation production and object manipulation in virtual reality, homogeneous coordinate systems can provide a more concise and unified mathematical description.

[0039] In an embodiment of the present application, after S100, it includes: S150, selecting the vibration signal of a vibration sensor; S160, analyzing the selected vibration signal of the vibration sensor; S170, obtaining the vibration intensity and the spatial direction of vibration of the vibration sensor; S180, using the vibration intensity and the spatial direction of vibration of the vibration sensor as vector parameters; S190, returning the selected vibration signal of a vibration sensor until all the vibration sensors are selected.

[0040] The spatial direction of vibration is a concept that describes the performance and propagation characteristics of vibration in a specific direction. It is of great significance for understanding vibration phenomena and analyzing vibration systems. The spatial direction of vibration refers to the directivity of vibration in three-dimensional space, that is, the distribution and propagation of vibration energy in different directions. It can be described by the components of physical quantities such as displacement, velocity, or acceleration of vibration in each direction of space. Usually, in a three-dimensional rectangular coordinate system, the components of vibration along the x, y, and z axes are analyzed. The x-axis direction generally represents the horizontal direction or the front-back direction, the y-axis direction represents the vertical direction or the left-right direction, and the z-axis direction represents the up-down direction. By measuring the changes in displacement, velocity, or acceleration of an object in these coordinate axis directions, the spatial direction characteristics of vibration can be determined. Different vibration sources will generate vibrations with different spatial directions. For example, due to its structural characteristics and motion mode, a rotating machine may generate more significant vibrations in certain specific directions.

[0041] In an embodiment of the present application, before S400, it includes: S410, calling the initial vibration waveform of the initial vibration source; S420, determining the first-order vibration frequency of the detection target; S430, sequentially connecting the ends of the vector parameters of the virtual three-dimensional position coordinate system; S440, obtaining the actual resonance three-dimensional curve graph.

[0042] In an embodiment of the present application, S400 includes: S450, determining whether the initial vibration waveform is consistent with the actual resonance three-dimensional curve graph; S460, if the initial vibration waveform is Figure 1 consistent with the actual resonance three-dimensional curve, then determining that the mechanical health of the mechanical system meets the threshold; S470, if the initial vibration waveform is inconsistent with the actual resonance three-dimensional curve graph, then determining whether the actual resonance three-dimensional curve graph is consistent with the first-order vibration frequency of the detection target; S480, if the actual resonance three-dimensional curve graph is consistent with the first-order vibration frequency of the detection target, then determining that the mechanical system is damaged; S490, if the actual resonance three-dimensional curve graph is inconsistent with the first-order vibration frequency of the detection target, then feeding back an instruction feedback for executing the analysis program; the analysis program is the actual resonance three-dimensional curve graph analysis program; S491, calling the first-order vibration graph generated by the first-order vibration frequency of the detection target; S492, using the time stamp to match the first-order vibration graph and the actual resonance three-dimensional curve graph corresponding to the first-order vibration graph; S493, determining the frequency synchronization points and asynchronous points; S494, incorporate the timestamp, co-frequency points, and asynchronous points into the dataset of the histogram data array with timestamps.

[0043] In an embodiment of the present application, S400 further includes: K100, call to incorporate the timestamp, co-frequency points, and asynchronous points into the dataset of the histogram data array with timestamps; K200, replace the co-frequency points and asynchronous points of the multi-dimensional detection histogram data array based on the timestamps of the dataset; K300, form a histogram data array with timestamps.

[0044] Specifically, the timestamp, co-frequency points, and asynchronous points can form different time periods, thereby simply dividing the monitoring interval. It can also improve the accuracy of early warning.

[0045] The present application provides a mechanical health early warning system based on the Internet of Things.

[0046] As Figure 2 shown, in an embodiment of the present application, a mechanical health early warning system based on the Internet of Things includes a host computer 100 and vibration sensors 200. The host computer 100 is used to execute the mechanical health early warning method based on the Internet of Things, and the vibration sensors 200 are all communicatively connected to the host computer 100.

[0047] This embodiment relates to a mechanical health early warning system based on the Internet of Things. The host computer 100 performs communication networking through the network access information of each vibration sensor 200. Based on the network access information of all vibration sensors 200, communication connections are made. Based on the feedback information of all vibration sensors 200, a multi-dimensional detection histogram data array is constructed. Briefly, based on the feedback information of all vibration sensors 200, the three-dimensional feedback information is analyzed to determine the working positions and three-dimensional virtual space positions of all vibration sensors 200. Using the three-dimensional virtual space positions, a multi-dimensional detection histogram data array is constructed. Receive the vibration signals of each vibration sensor 200, and based on the real-time vibration signals, fill the data of the multi-dimensional detection histogram data array to form a histogram data array with timestamps. Feedback the information of replacing the detection target, and return to receive the network access information of each vibration sensor 200 until N groups of histogram data arrays are received. Using the system time, multiple histogram data arrays with timestamps are formed.

[0048] A set of histogram data arrays includes multiple timestamped histogram data arrays of the same detection target at system time. Using N sets of histogram data arrays, train the mechanical health warning model to be trained. Obtain the trained mechanical health warning model. Incorporate the data of the received real-time vibration sensor into the trained mechanical health warning model to obtain the mechanical health conclusion of the mechanical system monitored by the vibration sensor. Based on the mechanical health conclusion, feedback the maintenance plan of the mechanical system. This realizes the technology of effective detection of mechanical fatigue of mechanical structures.

[0049] The technical features of the above-described embodiments can be combined arbitrarily, and there is no limitation on the execution order of each method step. For the sake of brevity of description, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0050] The above-described embodiments only represent several implementation manners of the present application, and the description is relatively specific and detailed, but it should not be understood as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. An Internet of Things-based mechanical health warning method, characterized in that, Including: Receiving the network access information of each vibration sensor; Based on the network access information of all vibration sensors, constructing a multi-dimensional detection histogram data array; Receiving the vibration signals of each vibration sensor; Based on the real-time vibration signals, forming a histogram data array with timestamps; Using the system time, forming multiple histogram data arrays with timestamps; Feeding back the information of replacing the detection target, and returning to the step of receiving the network access information of each vibration sensor until N groups of histogram data arrays are received to form a sample of the early warning method; One group of histogram data arrays includes multiple histogram data arrays with timestamps of the same detection target under the system time; N is a positive integer; Using N groups of histogram data arrays to train the mechanical health early warning model to be trained; Obtaining the trained mechanical health early warning model; Incorporating the received real-time vibration sensor data into the trained mechanical health early warning model to obtain the mechanical health conclusion of the mechanical system monitored by the vibration sensor; Based on the mechanical health conclusion, feeding back the maintenance plan of the mechanical system.

2. The mechanical health warning method based on the Internet of Things according to claim 1, wherein, The step of receiving the network access information of each vibration sensor includes: Selecting the network access information of one vibration sensor; Based on the network access information of the vibration sensor, determining the device serial number of the vibration sensor; Using the device serial number of the vibration sensor to determine the network access communication method of the vibration sensor; Returning the selected network access information of one vibration sensor until all vibration sensors are selected.

3. The mechanical health warning method based on the Internet of Things according to claim 2, wherein The step of constructing a multi-dimensional detection histogram data array based on the network access information of all vibration sensors includes: Establishing a virtual three-dimensional position coordinate system for the multi-dimensional detection histogram data array; Based on the virtual three-dimensional position coordinate system, setting the position points of the vibration sensors; Selecting one vibration sensor; Based on the network access communication method of the selected vibration sensor, receiving the position information of the vibration sensor; Using the position information of the vibration sensor to incorporate the position information of the selected vibration sensor into the position points of the vibration sensors; Returning to the step of selecting one vibration sensor until all vibration sensors are selected.

4. The method for mechanical health warning based on the Internet of Things according to claim 3, wherein The step of constructing a multi-dimensional detection histogram data array based on the network access information of all vibration sensors further includes: Saving the three-dimensional data coordinates of the position points of the vibration sensors in the virtual three-dimensional position coordinate system; Invoking one three-dimensional data coordinate; Based on the invoked three-dimensional data coordinate, establishing vector parameters; Returning to the step of invoking one three-dimensional data coordinate until all three-dimensional data coordinates of the position points of the vibration sensors in the virtual three-dimensional position coordinate system are invoked.

5. The mechanical health warning method based on the Internet of Things according to claim 4, characterized in that, After receiving the vibration signals of each vibration sensor, it includes: Selecting the vibration signal of one vibration sensor; Analyzing the selected vibration signal of the vibration sensor; Obtaining the vibration intensity and the spatial direction of vibration of the vibration sensor; Taking the vibration intensity and the spatial direction of vibration of the vibration sensor as vector parameters; Returning to the step of selecting the vibration signal of one vibration sensor until all vibration sensors are selected.

6. The method for mechanical health warning based on the Internet of Things according to claim 5, wherein, Before forming a histogram data array with timestamps based on the real-time vibration signals, it includes: Invoking the initial vibration waveform of the initial vibration source; Determining the first-order vibration frequency of the detection target; Connect the ends of the vector parameters of the virtual three-dimensional position coordinate system in sequence; Obtain the actual resonance three-dimensional curve graph; Judge whether the initial vibration waveform is consistent with the actual resonance three-dimensional curve graph; If the initial vibration waveform is consistent with the actual resonance three-dimensional curve graph, determine that the mechanical health of the mechanical system meets the threshold; If the initial vibration waveform is inconsistent with the actual resonance three-dimensional curve graph, judge whether the actual resonance three-dimensional curve graph is consistent with the first-order vibration frequency of the detection target.

7. The method for mechanical health warning based on the Internet of Things according to claim 6, characterized in that, The judgment of whether the actual resonance three-dimensional curve graph is consistent with the first-order vibration frequency of the detection target includes: If the actual resonance three-dimensional curve graph is consistent with the first-order vibration frequency of the detection target, determine that the mechanical system is damaged; If the actual resonance three-dimensional curve graph is inconsistent with the first-order vibration frequency of the detection target, feedback the instruction feedback for executing the analysis program; the analysis program is the actual resonance three-dimensional curve graph analysis program.

8. The mechanical health warning method based on the Internet of Things according to claim 7, characterized in that The analysis program includes: Call the first-order vibration graph generated by the first-order vibration frequency of the detection target; Use the time stamp to match the first-order vibration graph and the actual resonance three-dimensional curve graph corresponding to the first-order vibration graph; Determine the same-frequency points and asynchronous points; Incorporate the time stamp, same-frequency points and asynchronous points into the data set of the time-stamped histogram data array.

9. The mechanical health warning method based on the Internet of Things according to claim 8, characterized in that, The formation of the time-stamped histogram data array based on the real-time vibration signal includes: Call the data set that incorporates the time stamp, same-frequency points and asynchronous points into the time-stamped histogram data array; Replace the same-frequency points and asynchronous points of the multi-dimensional detection histogram data array based on the time stamp of the data set; Form a time-stamped histogram data array.

10. An Internet of Things-based mechanical health warning system, characterized in that, It includes: A host computer for executing the mechanical health warning method based on the Internet of Things according to any one of claims 1 to 9; Vibration sensors, all of which are communicatively connected to the host computer.

Images