CN114444536A - Equipment production condition monitoring method and system based on vibration detection and storage medium - Google Patents

Abstract

The application provides an equipment condition monitoring method, system and computer medium based on vibration detection. Specifically, the vibration measurement data in the equipment production process is obtained; the equipment production status is predicted according to the vibration measurement data; through the trained equipment status model, Predict the equipment status data corresponding to the equipment production status; compare the equipment status data and the vibration measurement data to obtain a data comparison result, and determine whether the equipment is abnormal according to the data comparison result. In this application, a vibration detection device is installed in the paper packaging cutting equipment, and the production and operation of the equipment are analyzed in real time through the deep learning model; at the same time, the production efficiency of the enterprise is promoted through the production capacity estimation, and the production and labor costs of the enterprise are reduced.

Description

Method, system and storage medium for monitoring equipment production status based on vibration detection

technical field

The present application belongs to the technical field of equipment detection, and in particular, relates to a method, system and storage medium for equipment condition monitoring based on vibration detection.

Background technique

At present, the paper packaging industry has experienced a stage of rapid development, and has now formed a considerable production scale, becoming an important part of the manufacturing field. With the development of informatization, the introduction of informatization and intelligence into the paper packaging industry is the key to future market industry competition. For example, improving the production efficiency in the production process of paper packaging by making machinery and equipment intelligent is an industry problem that needs to be solved urgently.

However, the production equipment and production models in the paper packaging industry are still dominated by traditional models. The production status of most paper packaging cutting equipment is still monitored manually, which is inefficient and unreliable. Therefore, in the case of no intelligent monitoring of the paper packaging cutting equipment during the production process, it is difficult to detect in time when an abnormality or failure occurs, which will lead to serious consequences such as production stoppage. Other problems include non-uniform and non-transparent data interfaces between different equipment, lack of common technical means to monitor all equipment, and decision-makers unable to obtain the overall production data of the factory in a timely manner, which affects the overall arrangement of production tasks.

SUMMARY OF THE INVENTION

The present invention proposes an equipment condition monitoring method system and storage medium based on vibration detection, aiming to solve the problem that the current paper packaging industry cannot monitor the equipment production condition intelligently and effectively, and consumes manpower and material resources.

According to a first aspect of the embodiments of the present application, a method for monitoring equipment condition based on vibration detection is provided, which specifically includes the following steps:

Obtain vibration measurement data during equipment production;

Predict equipment production status based on vibration measurement data;

Through the trained equipment status model, the equipment status data corresponding to the equipment production status is predicted;

The data comparison result is obtained by comparing the equipment status data and the vibration measurement data, and whether the equipment is abnormal is determined according to the data comparison result.

In some embodiments of the present application, predicting the production state of the equipment according to the vibration measurement data includes:

Fit the vibration measurement data to obtain the vibration fitting curve;

According to the vibration fitting curve, by counting the vibration peaks, the cutting times of the equipment are calculated;

Predict equipment capacity based on the number of equipment cuts.

In some embodiments of the present application, the vibration measurement data is fitted to obtain a vibration fitting curve, which specifically includes:

Perform spectrum conversion and denoising processing on the vibration sample data to obtain vibration spectrum data;

The vertical component of the vibration spectrum data is subtracted from the current value and the absolute value is obtained, and then after Hilbert transform, Fourier transform and normalization, the maximum value of the left edge of the vibration spectrum data is removed to obtain the frequency data to be selected;

The vibration fitting curve is obtained by low-pass filtering according to the frequency data to be selected.

In some embodiments of the present application, the production state of the equipment is predicted according to the vibration measurement data, which specifically includes:

Obtain vibration sample data during equipment production;

The vibration sample data is clustered by k-means algorithm, and the data characteristic samples of different equipment production states are obtained;

Compare and analyze the vibration measurement data and data characteristic samples to predict the current equipment production status.

In some embodiments of the present application, the equipment production state includes a power-on state, an equipment idling state, and a cutting state.

In some embodiments of the present application, before predicting the equipment status data corresponding to the equipment production status through the trained equipment status model, the method further includes:

Obtain vibration sample data during equipment production;

Perform spectrum conversion and denoising processing on the vibration sample data to obtain vibration spectrum data;

The vibration spectrum data is input into the LSTM model for training, and the trained equipment state model is obtained.

In some embodiments of the present application, spectrum conversion and denoising processing are performed on the vibration sample data to obtain vibration spectrum data, which specifically includes:

Perform spectrum conversion on the vibration sample data to obtain the vibration spectrum, and determine whether there is a unique maximum value in the vibration spectrum;

If there is a unique maximum value, directly perform spectrum fitting in simple mode to obtain the fitted vibration spectrum data;

If there is no unique maximum value, and it is judged that the vibration spectrum does not contain time parameters, and there is a unique maximum value after inputting the time parameters, directly perform the spectrum fitting in the simple mode to obtain the fitted vibration spectrum data; otherwise, use The genetic algorithm automatically estimates the detection spectrum parameters, and obtains the vibration spectrum data under the minimum loss function through repeated estimation.

According to a second aspect of the embodiments of the present application, a system for monitoring equipment conditions based on vibration detection is provided, which specifically includes:

Data acquisition module: used to acquire vibration measurement data during equipment production;

Production status prediction module: used to predict the production status of equipment based on vibration measurement data;

Equipment status model module: used to predict the equipment status data corresponding to the equipment production status through the trained equipment status model;

Equipment status monitoring unit: used to compare equipment status data and vibration measurement data to obtain a data comparison result, and determine whether the equipment is abnormal according to the data comparison result.

According to a third aspect of the embodiments of the present application, a device condition monitoring device based on vibration detection is provided, including:

memory: used to store executable instructions; and

Processor: used to connect with the memory to execute executable instructions to complete the equipment condition monitoring method based on vibration detection.

According to a fourth aspect of the embodiments of the present application, there is provided a computer-readable storage medium on which a computer program is stored; the computer program is executed by a processor to implement a method for monitoring equipment condition based on vibration detection.

Adopt the equipment condition monitoring method, system and computer medium based on vibration detection in the embodiment of the present application, specifically, obtain the vibration measurement data in the equipment production process; predict the equipment production status according to the vibration measurement data; pass the trained equipment status model , predict the equipment status data corresponding to the equipment production status; compare the equipment status data and the vibration measurement data to obtain a data comparison result, and determine whether the equipment is abnormal according to the data comparison result. In this application, a vibration detection device is installed on the paper packaging cutting equipment, and the production and operation of the equipment are analyzed in real time through the deep learning model; at the same time, the production efficiency of the enterprise is promoted through the production capacity estimation, and the production and labor costs of the enterprise are reduced.

Description of drawings

The drawings described herein are used to provide further understanding of the present application and constitute a part of the present application. The schematic embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation of the present application. In the attached image:

FIG. 1 shows a schematic diagram of steps of a method for monitoring equipment condition based on vibration detection according to an embodiment of the present application;

FIG. 2 shows a schematic diagram of a fitting curve obtained by fitting according to vibration measurement data according to an embodiment of the present application;

FIG. 3 shows a schematic flowchart of spectrum conversion and denoising processing of vibration sample data according to an embodiment of the present application;

FIG. 4 shows a schematic structural diagram of a device condition monitoring system based on vibration detection according to an embodiment of the present application;

FIG. 5 shows a schematic structural diagram of a device condition monitoring device based on vibration detection according to an embodiment of the present application.

Detailed ways

In the process of realizing the present application, the inventor found that the current production equipment and production mode in the paper packaging industry are still dominated by the traditional mode. The production status of most paper packaging cutting equipment is still monitored manually, which is inefficient and unreliable. In the case of no intelligent monitoring of the paper packaging cutting equipment in the production process, it is difficult to detect in time when an abnormality or failure occurs, which will lead to serious consequences such as shutdown.

In order to solve this problem, the present application designs a method for monitoring the production status of equipment in the paper packaging industry and estimating capacity based on vibration detection, which has the following beneficial effects:

1. High detection accuracy: the detection accuracy of the paper packaging switching equipment cutting through the vibration detection device can reach more than 90%; 2. Real-time monitoring: the use of the vibration detection device can monitor the production status of the equipment in real time, save manpower and improve monitoring efficiency; 3. Abnormal Alarm: use deep learning algorithm to train vibration data during normal operation, and automatically alarm when abnormality is found, reducing the probability of equipment failure; 4. Strong versatility: based on unsupervised learning algorithm, the device of this application can automatically adapt to different production equipment and environments , without any configuration for the scene; 5. Simple deployment: the device of the application only needs to scan the code to distribute the network and install the power supply, which has no impact on the production equipment; 6. The device is lightweight: the device of the application is light in weight, small in size, and does not take up space , easy to transport and install.

Specifically, the present application is an equipment condition monitoring method, system and computer medium based on vibration detection, which acquires vibration measurement data in the equipment production process; predicts the equipment production status according to the vibration measurement data; Equipment status data corresponding to the equipment production status; compare the equipment status data and vibration measurement data to obtain a data comparison result, and determine whether the equipment is abnormal according to the data comparison result.

In order to make the technical solutions and advantages of the embodiments of the present application more clear, the exemplary embodiments of the present application will be described in further detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, and Not all embodiments are exhaustive. It should be noted that the embodiments in the present application and the features of the embodiments may be combined with each other in the case of no conflict.

Example 1

FIG. 1 shows a schematic diagram of steps of a method for monitoring equipment condition based on vibration detection according to an embodiment of the present application. As shown in FIG. 1 , the vibration detection-based equipment condition monitoring method according to the embodiment of the present application specifically includes the following steps:

S101: Acquire vibration measurement data during the production process of the equipment.

First of all, it is necessary to install a vibration detection device. The vibration detection device can be installed in the place where the vibration of the paper packaging cutting equipment is more obvious by means of magnetic adsorption. Specifically, install a wired power supply or use its own rechargeable battery; use a mobile phone to scan the QR code to set up a wifi network to connect to the server testing center.

When collecting data through the vibration detection device, the vibration detection device uses the built-in acceleration sensor of the embedded hardware to collect the vibration data of various production states of the paper packaging cutting equipment, such as the acceleration data generated by the vibration of the equipment. Then convert the analog signal to digital signal and send it to the server testing center through wifi.

Further, the vibration measurement data during the production process of the equipment is obtained.

The detection method and a series of algorithms of the present application can be completed in the server-side detection center.

S102: Predict the production state of the equipment according to the vibration measurement data.

Specifically, first, the vibration sample data in the production process of the equipment is obtained; the vibration sample data is clustered by the k-means algorithm to obtain the data characteristic samples under different equipment production states;

Then, compare and analyze the vibration measurement data and data feature samples to predict the current equipment production status.

Specifically, the production status of the equipment includes a power-on status, an idling status of the equipment, a cutting status, and the like.

S103: Predict the equipment status data corresponding to the equipment production status through the trained equipment status model.

Specifically, before predicting the equipment status data corresponding to the equipment production status through the trained equipment status model, a process of training the equipment status model is also included.

First, obtain the vibration sample data in the production process of the equipment; then, perform spectrum conversion and denoising on the vibration sample data to obtain the vibration spectrum data; finally, input the vibration spectrum data into the LSTM model for training to obtain the trained equipment state model.

S104: Comparing the equipment state data and the vibration measurement data to obtain a data comparison result, and determining whether the equipment is abnormal according to the data comparison result.

Finally, when monitoring the production status of the paper packaging cutting equipment, when the difference between the equipment status data predicted by the model and the actual vibration measurement data exceeds the threshold, the system determines that the production equipment is abnormal; at the same time, the system will send a message to the detection device for real-time alarms .

In a preferred embodiment, the server receives the vibration data, and calculates the production capacity of the device according to the number of times of cutting by counting the times of cutting by the paper packaging cutting equipment for a period of time in the cutting state, so as to estimate the capacity.

After obtaining the vibration measurement data in the production process of the equipment, predicting the production state of the equipment according to the vibration measurement data also includes the process of predicting the production capacity of the equipment, specifically:

First, as shown in Figure 2, the vibration measurement data is fitted to obtain a vibration fitting curve C.

Specifically, the vibration measurement data is fitted to obtain a vibration fitting curve. The specific fitting process includes:

Perform spectrum conversion and denoising processing on the vibration sample data to obtain the vibration spectrum data; subtract the current value from the vertical component of the vibration spectrum data and take the absolute value, and then pass the Hilbert transform, Fourier transform and normalization, Selecting and removing the maximum value of the left edge of the vibration spectrum data to obtain the frequency data to be selected; performing low-pass filtering according to the frequency data to be selected to obtain the vibration fitting curve.

Secondly, according to the vibration fitting curve, by counting the vibration wave peaks A, the number of cutting times of the equipment is calculated.

Finally, the equipment capacity is predicted based on the number of equipment cuts.

FIG. 3 shows a schematic flowchart of spectrum conversion and denoising processing for vibration sample data according to an embodiment of the present application.

In the process of training the equipment state model and the process of predicting equipment production capacity, it includes: spectrum conversion and denoising processing of vibration sample data to obtain vibration spectrum data.

Specifically, it includes: 1) performing spectrum conversion on the vibration sample data to obtain the vibration spectrum, and judging whether there is a unique maximum value in the vibration spectrum; 2) if there is a unique maximum value, directly perform the spectrum fitting in the simple mode to obtain the approximate The combined vibration spectrum data; 3) If there is no unique maximum value, and it is judged that the vibration spectrum does not contain time parameters, when there is a unique maximum value after inputting the time parameters, directly perform the spectrum fitting in the simple mode to obtain the fitting Otherwise, use the genetic algorithm to automatically estimate the detection spectrum parameters, and obtain the vibration spectrum data under the minimum loss function through repeated estimation.

As shown in Figure 3, for specific description, first, the input equipment vibration data is subjected to spectrum conversion, and it is judged whether there is a unique maximum value in the frequency spectrum, if there is a simple mode calculation model parameter directly; Whether the vibration data contains time parameters or not, you need to input time parameters without time parameters, and continue to judge whether there is a unique maximum value in the frequency spectrum interval. If there is no unique maximum value, go to complex mode configuration parameters; if there is, go to simple mode configuration parameters.

Among them, in the simple mode, the maximum value of the removed left edge of the spectrum is selected as the frequency to be selected, and the wavelet threshold transformation threshold, bandpass filter parameters, the length of the smoothing filter window, and the order of the polynomial used to fit the sample are calculated.

Among them, in the complex mode, the genetic algorithm is used to automatically estimate the detection parameters, and by repeatedly calculating the loss function, the wavelet threshold transformation threshold, bandpass filter parameters, and the length of the smoothing filter window under the minimum loss function are obtained. The order of the polynomial for the sample.

The equipment condition monitoring method based on vibration detection in the embodiment of the present application, specifically, obtains vibration measurement data in the equipment production process; predicts the equipment production status according to the vibration measurement data; and predicts the corresponding equipment production status through the trained equipment status model. equipment status data; compare the equipment status data and vibration measurement data to obtain a data comparison result, and determine whether the equipment is abnormal according to the data comparison result. In this application, a vibration detection device is installed on the paper packaging cutting equipment, and the production and operation of the equipment are analyzed in real time through the deep learning model; at the same time, the production efficiency of the enterprise is promoted through the production capacity estimation, and the production and labor costs of the enterprise are reduced.

Example 2

This embodiment provides an equipment condition monitoring system based on vibration detection. For details not disclosed in the equipment condition monitoring system based on vibration detection in this embodiment, please refer to the equipment condition monitoring methods based on vibration detection in other embodiments. specific implementation content.

FIG. 4 shows a schematic structural diagram of an equipment condition monitoring system based on vibration detection according to an embodiment of the present application.

As shown in FIG. 4 , the equipment condition monitoring system based on vibration detection according to the embodiment of the present application specifically includes a data acquisition module 10 , a production status prediction module 20 , an equipment status model module 30 and an equipment condition monitoring unit 40 .

specific,

Data acquisition module 10: used to acquire vibration measurement data in the production process of the equipment.

First of all, it is necessary to install a vibration detection device. The vibration detection device can be installed in the place where the vibration of the paper packaging cutting equipment is more obvious by means of magnetic adsorption. Specifically, install a wired power supply or use its own rechargeable battery; use a mobile phone to scan the QR code to set up a wifi network to connect to the server testing center.

When collecting data through the vibration detection device, the vibration detection device uses the built-in acceleration sensor of the embedded hardware to collect the vibration data of various production states of the paper packaging cutting equipment, such as the acceleration data generated by the vibration of the equipment. Then convert the analog signal to digital signal and send it to the server testing center through wifi.

Further, the vibration measurement data during the production process of the equipment is obtained.

The detection method and a series of algorithms of the present application can be completed in the server-side detection center.

Production state prediction module 20: used to predict the production state of the equipment according to the vibration measurement data.

Specifically, first, the vibration sample data in the production process of the equipment is obtained; the vibration sample data is clustered by the k-means algorithm to obtain the data characteristic samples under different equipment production states;

Then, compare and analyze the vibration measurement data and data feature samples to predict the current equipment production status.

Specifically, the production status of the equipment includes a power-on status, an idling status of the equipment, a cutting status, and the like.

The equipment state model module 30 is used for predicting the equipment state data corresponding to the equipment production state through the trained equipment state model.

Specifically, before predicting the equipment state data corresponding to the equipment production state through the trained equipment state model, a process of training the equipment state model is also included.

First, obtain the vibration sample data in the production process of the equipment; then, perform spectrum conversion and denoising on the vibration sample data to obtain the vibration spectrum data; finally, input the vibration spectrum data into the LSTM model for training to obtain the trained equipment state model.

Equipment condition monitoring unit 40: used to compare equipment status data and vibration measurement data to obtain a data comparison result, and determine whether the equipment is abnormal according to the data comparison result.

Finally, when monitoring the production status of the paper packaging cutting equipment, when the difference between the equipment status data predicted by the model and the actual vibration measurement data exceeds the threshold, the system determines that the production equipment is abnormal; at the same time, the system will send a message to the detection device for real-time alarms .

In a preferred embodiment, the server receives the vibration data, and calculates the production capacity of the device according to the number of times of cutting by counting the times of cutting by the paper packaging cutting equipment for a period of time in the cutting state, so as to estimate the capacity.

After acquiring the vibration measurement data in the production process of the equipment, the present application also includes the process of predicting the production capacity of the equipment, specifically:

First, fit the vibration measurement data to obtain the vibration fitting curve C.

Specifically, the vibration measurement data is fitted to obtain a vibration fitting curve. The specific fitting process includes:

Perform spectrum conversion and denoising processing on the vibration sample data to obtain the vibration spectrum data; subtract the current value from the vertical component of the vibration spectrum data and take the absolute value, and then pass the Hilbert transform, Fourier transform and normalization, Selecting and removing the maximum value of the left edge of the vibration spectrum data to obtain the frequency data to be selected; performing low-pass filtering according to the frequency data to be selected to obtain the vibration fitting curve.

Secondly, according to the vibration fitting curve, by counting the vibration wave peaks A, the number of cutting times of the equipment is calculated.

Finally, the equipment capacity is predicted based on the number of equipment cuts.

Through the equipment condition monitoring system based on vibration detection in the embodiment of the present application, the data acquisition module 10 acquires vibration measurement data in the equipment production process; the production status prediction module 20 predicts the equipment production status according to the vibration measurement data; the equipment status model module 30 passes The trained equipment status model predicts equipment status data corresponding to the equipment production status; the equipment status monitoring unit 40 compares the equipment status data and the vibration measurement data to obtain a data comparison result, and determines whether the equipment is abnormal according to the data comparison result. In this application, a vibration detection device is installed on the paper packaging cutting equipment, and the production and operation of the equipment are analyzed in real time through the deep learning model; at the same time, the production efficiency of the enterprise is promoted through the production capacity estimation, and the production and labor costs of the enterprise are reduced.

Example 3

This embodiment provides a device condition monitoring device based on vibration detection. For details that are not disclosed in the device state monitoring device based on vibration detection in this embodiment, please refer to the device state monitoring method based on vibration detection in other embodiments. Or system specific implementation content.

FIG. 5 shows a schematic structural diagram of a device condition monitoring device 400 based on vibration detection according to an embodiment of the present application.

As shown in FIG. 5 , the device condition monitoring device 400 includes:

memory 402: for storing executable instructions; and

Processor 401: for connecting with the memory 402 to execute executable instructions to complete the motion vector prediction method.

Those skilled in the art can understand that the schematic diagram 5 is only an example of the equipment condition monitoring apparatus 400, and does not constitute a limitation on the equipment condition monitoring apparatus 400. Or different components, such as the device condition monitoring device 400, may also include input and output devices, network access devices, buses, and the like.

The so-called processor 401 (Central Processing Unit, CPU) may also be other general-purpose processors, digital signal processors (Digital Signal Processors, DSPs), application specific integrated circuits (Application Specific Integrated Circuits, ASICs), field programmable gate arrays ( Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor 401 can also be any conventional processor, etc. The processor 401 is the control center of the equipment condition monitoring device 400, and uses various interfaces and lines to connect the entire equipment condition monitoring equipment 400. various parts.

The memory 402 can be used to store computer-readable instructions, and the processor 401 implements various functions of the equipment condition monitoring device 400 by running or executing the computer-readable instructions or modules stored in the memory 402 and calling the data stored in the memory 402. . The memory 402 may mainly include a stored program area and a stored data area, wherein the stored program area may store an operating system, an application program (such as a sound playback function, an image playback function, etc.) required for at least one function, and the like; The device condition monitoring device 400 uses the created data or the like. In addition, the memory 402 may include a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card (Flash Card), at least one disk storage device, a flash memory device , Read-Only Memory (Read-Only Memory, ROM), Random Access Memory (Random Access Memory, RAM) or other non-volatile/volatile storage devices.

If the modules integrated in the device condition monitoring device 400 are implemented in the form of software function modules and sold or used as independent products, they may be stored in a computer-readable storage medium. Based on this understanding, the present invention realizes all or part of the processes in the methods of the above embodiments, and can also be completed by instructing relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium, The computer-readable instructions, when executed by the processor, can implement the steps of the above-mentioned various method embodiments.

Example 4

This embodiment provides a computer-readable storage medium on which a computer program is stored; the computer program is executed by a processor to implement the vibration detection-based equipment condition monitoring methods in other embodiments.

The equipment condition monitoring equipment and computer storage medium based on vibration detection in the embodiments of the present application obtain vibration measurement data in the production process of the equipment; predict the equipment production status according to the vibration measurement data; predict the equipment production status through the trained equipment status model Corresponding equipment status data; compare equipment status data and vibration measurement data to obtain a data comparison result, and determine whether the equipment is abnormal according to the data comparison result. In this application, a vibration detection device is installed on the paper packaging cutting equipment, and the production and operation of the equipment are analyzed in real time through the deep learning model; at the same time, the production efficiency of the enterprise is promoted through the production capacity estimation, and the production and labor costs of the enterprise are reduced.

As will be appreciated by those skilled in the art, the embodiments of the present application may be provided as a method, a system, or a computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It will be understood that each process and/or block in the flowchart illustrations and/or block diagrams, and combinations of processes and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device produce Means for implementing the functions specified in a flow or flow of a flowchart and/or a block or blocks of a block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions The apparatus implements the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.

These computer program instructions can also be loaded on a computer or other programmable data processing device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process such that The instructions provide steps for implementing the functions specified in the flow or blocks of the flowcharts and/or the block or blocks of the block diagrams.

The terminology used in the present invention is for the purpose of describing particular embodiments only and is not intended to limit the present invention. As used in this specification and the appended claims, the singular forms "a," "the," and "the" are intended to include the plural forms as well, unless the context clearly dictates otherwise. It will also be understood that the term "and/or" as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

It should be understood that although the terms first, second, third, etc. may be used in the present invention to describe various information, such information should not be limited by these terms. These terms are only used to distinguish the same type of information from each other. For example, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information, without departing from the scope of the present invention. Depending on the context, the word "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determining."

Although the preferred embodiments of the present application have been described, additional changes and modifications to these embodiments may occur to those skilled in the art once the basic inventive concepts are known. Therefore, the appended claims are intended to be construed to include the preferred embodiment and all changes and modifications that fall within the scope of this application.

Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims (10)

1. a device condition monitoring method based on vibration detection, is characterized in that, comprises the following steps: Obtain vibration measurement data during equipment production; Predict the production state of the equipment according to the vibration measurement data; Predict the equipment status data corresponding to the equipment production status through the trained equipment status model; A data comparison result is obtained by comparing the equipment state data and the vibration measurement data, and whether the equipment is abnormal is determined according to the data comparison result. 2. The equipment condition monitoring method according to claim 1, wherein the predicting the equipment production status according to the vibration measurement data comprises: Fitting the vibration measurement data to obtain a vibration fitting curve; According to the vibration fitting curve, the number of times of equipment cutting is calculated by counting the vibration peaks; The capacity of the equipment is estimated according to the number of cuts of the equipment. 3. The equipment condition monitoring method according to claim 2, wherein the said vibration measurement data is fitted to obtain a vibration fitting curve, specifically comprising: Perform spectrum conversion and denoising processing on the vibration sample data to obtain vibration spectrum data; Take the absolute value after subtracting the current value from the vertical component of the vibration spectrum data, then after Hilbert transform, Fourier transform and normalization, select and remove the maximum value of the left edge of the vibration spectrum data, and obtain the maximum value of the left edge of the vibration spectrum data. select frequency data; A vibration fitting curve is obtained by performing low-pass filtering according to the candidate frequency data. 4. The equipment condition monitoring method according to claim 1, wherein the predicting the equipment production status according to the vibration measurement data specifically comprises: Obtain vibration sample data during equipment production; Clustering the vibration sample data through the k-means algorithm to obtain data characteristic samples under different equipment production states; The vibration measurement data and the data characteristic samples are compared and analyzed to predict the current equipment production state. 5 . The equipment condition monitoring method according to claim 4 , wherein the equipment production status includes a power-on status, an equipment idling status and a cutting status. 6 . 6 . The equipment condition monitoring method according to claim 1 , wherein, before predicting the equipment status data corresponding to the equipment production status through the trained equipment status model, the method further comprises: 6 . Obtain vibration sample data during equipment production; Perform spectrum conversion and denoising processing on the vibration sample data to obtain vibration spectrum data; The vibration spectrum data is input into the LSTM model for training to obtain a trained equipment state model. 7. The equipment condition monitoring method according to claim 3 or 6, wherein the vibration sample data is subjected to spectrum conversion and denoising processing to obtain vibration spectrum data, specifically comprising: The vibration sample data is subjected to spectrum conversion to obtain a vibration spectrum, and it is judged whether there is a unique maximum value in the vibration spectrum; If there is a unique maximum value, directly perform spectrum fitting in simple mode to obtain the fitted vibration spectrum data; If there is no unique maximum value, and it is judged that the vibration spectrum does not contain time parameters, and there is a unique maximum value after inputting the time parameter, directly perform spectrum fitting in the simple mode to obtain the fitted vibration spectrum data; otherwise , using the genetic algorithm to automatically estimate the detection spectrum parameters, and obtain the vibration spectrum data under the minimum loss function through repeated estimation. 8. The equipment condition monitoring method based on vibration detection according to any one of claims 1-7, the system comprising: Data acquisition module: used to acquire vibration measurement data during equipment production; Production state prediction module: used to predict the production state of the equipment according to the vibration measurement data; Equipment status model module: used to predict the equipment status data corresponding to the equipment production status through the trained equipment status model; Equipment status monitoring unit: used to compare the equipment status data and the vibration measurement data to obtain a data comparison result, and determine whether the equipment is abnormal according to the data comparison result. 9. A device condition monitoring device based on vibration detection is characterized in that, comprising: memory: used to store executable instructions; and Processor: used to connect with the memory to execute the executable instructions to complete the vibration detection-based equipment condition monitoring method according to any one of claims 1-7. 10. A computer-readable storage medium, characterized in that a computer program is stored thereon; the computer program is executed by a processor to implement the vibration detection-based equipment condition monitoring method according to any one of claims 1-7.

Images