Damping method and device, storage medium and electronic equipment

Abstract

The invention discloses a damping method and device, a storage medium and electronic equipment. The method relates to the field of financial science and technology and other related technical fields, and comprises the following steps: when detecting that target equipment vibrates, collecting target data of the target equipment; processing the target data to obtain target feature information corresponding to the target data; predicting the target equipment based on the target feature information through the target convolutional neural network model to obtain vibration information corresponding to the target equipment; and determining a target damping strategy corresponding to the target equipment based on the vibration information through the target decision tree model. Through the method and the device, the problem that the efficiency of determining the damping strategy is relatively low due to the fact that the vibration condition of the storage equipment is evaluated manually and the damping strategy of the storage equipment is determined based on experience when vibration of the storage equipment is detected in related technologies is solved.

Description

Technical Field

[0001] The present application relates to the field of financial technology and other related technical fields, and specifically, to a shock absorption method and device, a storage medium and an electronic device. Background Art

[0002] When the storage device performs read and write operations, the magnetic head keeps jumping rapidly between sectors on the disk surface, and the distance between the magnetic head and the disk is only 0.1 to 0.3 microns. Sudden vibrations will cause severe vibrations of the magnetic head and the mechanical arm, and it is very likely that the magnetic head and the disk surface will contact, causing partial or complete damage to the storage device. In the computer room of a financial institution, a large-scale storage device cluster is deployed, which is placed in a dedicated cabinet to store and protect critical business data. However, when encountering force majeure factors such as earthquakes or manual movement, these storage devices are very likely to suffer serious physical damage, which in turn leads to the risk of data loss.

[0003] Currently, there are relatively few shockproof technologies for storage devices. The traditional method is mainly to manually evaluate the vibration of the storage device when the vibration of the storage device is detected, and determine the shock reduction strategy of the storage device based on experience, and use shock absorbers or buffering materials to reduce the vibration of the storage device. However, this method cannot prevent vibration damage before it occurs, so it cannot fundamentally avoid the damage caused by vibration to the storage device. At the same time, buffering materials are usually wrapped around the storage device to provide additional physical protection. This design limits the heat dissipation performance of the device, which in turn affects the stability and reliability of the storage device.

[0004] Currently, no effective solution has been proposed to the problem that when vibration of a storage device is detected, the vibration condition of the storage device is manually evaluated and a shock reduction strategy of the storage device is determined based on experience, which results in low efficiency in determining the shock reduction strategy. Summary of the invention

[0005] The main purpose of the present application is to provide a shock absorption method and device, a storage medium and an electronic device, so as to solve the problem in the related art that when vibration of the storage device is detected, the vibration condition of the storage device is manually evaluated, and the shock absorption strategy of the storage device is determined based on experience, resulting in low efficiency in determining the shock absorption strategy.

[0006] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a shock reduction method is provided. The method comprises: when a vibration of a target device is detected, collecting target data of the target device, wherein the target data at least includes: acceleration, angular velocity and vibration waveform of the target device when the vibration occurs; processing the target data to obtain target feature information corresponding to the target data; predicting the target device based on the target feature information through a target convolutional neural network model to obtain vibration information corresponding to the target device, wherein the vibration information at least includes: vibration intensity and vibration damage degree corresponding to the target device; determining a target shock reduction strategy corresponding to the target device based on the vibration information through a target decision tree model, wherein the target shock reduction strategy is used to perform shock reduction processing on the target device when vibration of the target device is detected.

[0007] Furthermore, collecting target data of the target device includes: collecting first data of the target device through a target sensor; correcting abnormal values ​​in the first data to obtain second data; filling missing values ​​in the second data to obtain third data; and filtering the third data to obtain the target data.

[0008] Furthermore, collecting the first data of the target device through the target sensor includes: collecting the initial acceleration of the target device when vibrating through the accelerometer in the three-axis sensor in the target sensor; collecting the initial angular velocity of the target device when vibrating through the gyroscope in the three-axis sensor in the target sensor; collecting the initial vibration waveform of the target device when vibrating through the piezoelectric sensor in the target sensor; and determining the first data based on the initial acceleration, the initial angular velocity and the initial vibration waveform.

[0009] Furthermore, processing the target data to obtain target feature information corresponding to the target data includes: calculating the target data to obtain first feature information corresponding to the target data, wherein the first feature information at least includes: mean, variance, maximum value and minimum value; performing frequency domain analysis on the target data to obtain second feature information corresponding to the target data; performing time domain analysis on the target data to obtain third feature information corresponding to the target data; and determining the target feature information based on the first feature information, the second feature information and the third feature information.

[0010] Furthermore, performing frequency domain analysis on the target data to obtain second characteristic information corresponding to the target data includes: discretizing the target data to obtain discretized target data; performing Fourier transform on the discretized target data to obtain transformed target data; performing spectrum analysis on the transformed target data to obtain the second characteristic information.

[0011] Furthermore, performing time domain analysis on the target data to obtain third characteristic information corresponding to the target data includes: determining a time domain graph corresponding to the target data; performing calculations based on the time domain graph to obtain time domain characteristic information corresponding to the target data; and performing calculations based on the time domain characteristic information to obtain the third characteristic information.

[0012] Furthermore, determining a target shock reduction strategy corresponding to the target device based on the vibration information through a target decision tree model includes: acquiring multiple shock reduction strategies in a strategy database; calculating according to preset weight values ​​and the vibration information to obtain a vibration level corresponding to the target device; and determining the target shock reduction strategy from the multiple shock reduction strategies based on the vibration level through the target decision tree model.

[0013] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a shock absorption device is provided. The device includes: a collection unit, which is used to collect target data of the target device when vibration is detected in the target device, wherein the target data at least includes: acceleration, angular velocity and vibration waveform of the target device when vibration occurs; a processing unit, which is used to process the target data to obtain target feature information corresponding to the target data; a prediction unit, which is used to predict the target device based on the target feature information through a target convolutional neural network model to obtain vibration information corresponding to the target device, wherein the vibration information at least includes: vibration intensity and vibration damage degree corresponding to the target device; a determination unit, which is used to determine the target shock absorption strategy corresponding to the target device based on the vibration information through a target decision tree model, wherein the target shock absorption strategy is used to perform shock absorption processing on the target device when vibration is detected in the target device.

[0014] Furthermore, the acquisition unit includes: an acquisition module, used to collect first data of the target device through a target sensor; a correction module, used to correct abnormal values ​​in the first data to obtain second data; a filling module, used to fill missing values ​​in the second data to obtain third data; and a filtering module, used to filter the third data to obtain the target data.

[0015] Furthermore, the acquisition module includes: a first acquisition submodule, used to acquire the initial acceleration of the target device when it vibrates through the accelerometer in the three-axis sensor in the target sensor; a second acquisition submodule, used to acquire the initial angular velocity of the target device when it vibrates through the gyroscope in the three-axis sensor in the target sensor; a third acquisition submodule, used to acquire the initial vibration waveform of the target device when it vibrates through the piezoelectric sensor in the target sensor; a first determination submodule, used to determine the first data based on the initial acceleration, the initial angular velocity and the initial vibration waveform.

[0016] Furthermore, the processing unit includes: a first calculation module, used to calculate the target data to obtain first feature information corresponding to the target data, wherein the first feature information at least includes: mean, variance, maximum value and minimum value; a first analysis module, used to perform frequency domain analysis on the target data to obtain second feature information corresponding to the target data; a second analysis module, used to perform time domain analysis on the target data to obtain third feature information corresponding to the target data; a first determination module, used to determine the target feature information based on the first feature information, the second feature information and the third feature information.

[0017] Furthermore, the first analysis module includes: a discrete submodule, used to discretize the target data to obtain discretized target data; a transformation submodule, used to perform Fourier transform on the discretized target data to obtain transformed target data; and an analysis submodule, used to perform spectral analysis on the transformed target data to obtain the second feature information.

[0018] Furthermore, the second analysis module includes: a second determination submodule, used to determine the time domain graph corresponding to the target data; a first calculation submodule, used to perform calculations based on the time domain graph to obtain the time domain feature information corresponding to the target data; and a second calculation submodule, used to perform calculations based on the time domain feature information to obtain the third feature information.

[0019] Furthermore, the determination unit includes: an acquisition module, used to acquire multiple shock reduction strategies in a strategy database; a second calculation module, used to calculate according to a preset weight value and the vibration information to obtain a vibration level corresponding to the target device; and a second determination module, used to determine the target shock reduction strategy among the multiple shock reduction strategies based on the vibration level through the target decision tree model.

[0020] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a computer-readable storage medium is provided, wherein the storage medium stores a program, wherein when the program is running, the device where the storage medium is located is controlled to execute any one of the above-mentioned shock absorption methods.

[0021] In order to achieve the above-mentioned purpose, according to another aspect of the present application, an electronic device is further provided, the electronic device includes one or more processors and a memory, and the memory is used to store the one or more processors to implement any one of the above-mentioned shock reduction methods.

[0022] Through the present application, the following steps are adopted: when vibration of the target device is detected, target data of the target device is collected, wherein the target data includes at least: acceleration, angular velocity and vibration waveform of the target device when vibration occurs; the target data is processed to obtain target feature information corresponding to the target data; the target device is predicted based on the target feature information by a target convolutional neural network model to obtain vibration information corresponding to the target device, wherein the vibration information includes at least: vibration intensity and vibration damage degree corresponding to the target device; based on the vibration information, a target shock reduction strategy corresponding to the target device is determined by a target decision tree model, wherein the target shock reduction strategy is used to perform shock reduction processing on the target device when vibration of the target device is detected. Through the present application, the problem of low efficiency in determining the shock reduction strategy is solved in the related art that when vibration of the storage device is detected, the vibration condition of the storage device is manually evaluated, and the shock reduction strategy of the storage device is determined based on experience.

[0023] In this scheme, when the target device is detected to be vibrating, target data such as acceleration, angular velocity, and vibration waveform of the target device are collected. Then, the target data is subjected to various analyses and calculations to obtain the target feature information corresponding to the target device. The target convolutional neural network model is used to predict the target device based on the target feature information to obtain vibration information such as the vibration intensity, damage degree, and whether there is rotation and tipping of the target device. Finally, the target decision tree model is used to determine the target shock reduction strategy that best suits the target device based on the vibration information to perform shock reduction processing on the target device.

[0024] By analyzing and calculating the collected target data, the target feature information can be accurately obtained. The target convolutional neural network model and the target decision tree model are used to predict and make decisions on the target equipment to obtain the most suitable shock reduction strategy for the target equipment, effectively reducing the damage risk of the target equipment and extending the service life of the target equipment. At the same time, through automated shock reduction processing, the stability and reliability of the equipment are improved, the maintenance cost and the risk of production interruption are reduced, thereby improving work efficiency and production benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0026] Figure 1 is a flow chart of a shock absorption method provided according to an embodiment of the present application;

[0027] Figure 2 is a schematic diagram of a shock absorption method provided according to an embodiment of the present application;

[0028] Figure 3 is a schematic diagram of shockproofing a storage device according to an embodiment of the present application;

[0029] Figure 4 is a schematic diagram of a shock absorbing device provided according to an embodiment of the present application;

[0030] Figure 5 is a schematic diagram of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0031] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0032] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0033] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0034] For the convenience of description, some nouns or terms involved in the embodiments of the present application are explained below:

[0035] Convolutional Neural Network (CNN): It is a deep feedforward neural network with characteristics such as local connection and weight sharing. It is one of the representative algorithms of deep learning.

[0036] ID3 algorithm: It is a greedy algorithm used to construct decision trees. The ID3 algorithm originated from the concept learning system. It uses the rate of decrease of information entropy as the criterion for selecting test attributes. That is, at each node, the attribute with the highest information gain that has not been used for partitioning is selected as the partitioning criterion, and then this process is continued until the generated decision tree can perfectly classify the training samples.

[0037] Decision tree: It is a decision analysis method that uses a decision tree to construct a decision tree based on the known probabilities of various situations to obtain the probability that the expected value of the net present value is greater than or equal to zero, evaluate project risks, and judge its feasibility. It is a graphical method that intuitively uses probability analysis.

[0038] Storage devices: refers to hardware devices used to store, manage and protect data. In the computer rooms of financial institutions, in order to meet the needs of high capacity, high performance and high reliability of financial institutions' key business data, large-scale storage device clusters are usually deployed. These storage device clusters are placed in dedicated cabinets. Through these storage devices, financial institutions can ensure the integrity, availability and recoverability of key business data, thereby ensuring the continuity and stability of financial institutions' business.

[0039] Active shock protection: It means using machine learning to quickly predict and respond to sudden vibration shocks, performing corresponding protective actions before damage actually occurs, and significantly reducing the risk of storage device damage and data loss.

[0040] It should be noted that the collected information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this application are information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data are in compliance with relevant laws, regulations and standards, necessary confidentiality measures are taken, and public order and good customs are not violated, and corresponding operation entrances are provided for users to choose to authorize or refuse. For example, an interface is set up between this system and relevant users or institutions to provide users with corresponding operation entrances for users to choose to agree or refuse the results of automated decision-making; if the user chooses to refuse, the expert decision-making process will be entered.

[0041] The present invention is described below in conjunction with preferred implementation steps. Figure 1 is a flow chart of a shock absorption method provided according to an embodiment of the present application, such as Figure 1 As shown, the method comprises the following steps:

[0042] Step S101, when it is detected that the target device is vibrating, target data of the target device is collected, wherein the target data at least includes: acceleration, angular velocity and vibration waveform of the target device when it is vibrating.

[0043] Optionally, the embedded device is usually in a sleeping state. When vibration of the target device is detected, the embedded device is awakened through an interruption and collects the vibration signal (ie, target data) uploaded by the sensor in real time.

[0044] It should be noted that the sensor is a fusion of a three-axis sensor and a piezoelectric sensor.

[0045] Step S102, processing the target data to obtain target feature information corresponding to the target data.

[0046] Optionally, meaningful features are extracted from the target data, including but not limited to: statistical features, frequency domain features, time domain features, etc., to obtain target feature information.

[0047] It should be noted that the target feature information includes but is not limited to: mean, variance, maximum value, minimum value, two-dimensional feature map, amplitude, period, acceleration and angular velocity in each direction of the three-axis sensor, etc.

[0048] Step S103, predicting the target device based on the target feature information through the target convolutional neural network model to obtain vibration information corresponding to the target device, wherein the vibration information at least includes: vibration intensity and vibration damage degree corresponding to the target device.

[0049] Optionally, a target convolutional neural network model is built through deep learning technology, and the vibration information of the target device is predicted by training and learning a large amount of target feature information.

[0050] It should be noted that vibration information includes but is not limited to: vibration intensity, severity of damage that vibration may cause to equipment (i.e., degree of vibration damage), whether the cabinet rotates, tips over, etc., and process information when the cabinet rotates, tips over, etc.

[0051] Step S104, determining a target vibration reduction strategy corresponding to the target device based on the vibration information through a target decision tree model, wherein the target vibration reduction strategy is used to perform vibration reduction processing on the target device when vibration of the target device is detected.

[0052] Optionally, a decision tree is constructed by using an ID3 algorithm (ie, a target decision tree model), and based on the vibration information, an emergency treatment strategy (ie, a target vibration reduction strategy) corresponding to the storage device is output.

[0053] It should be noted that the decision tree is a commonly used machine learning algorithm that uses a tree structure to model and predict data.

[0054] In summary, when the target device is detected to be vibrating, target data such as acceleration, angular velocity, and vibration waveform of the target device are collected. Then, the target data is subjected to various analyses and calculations to obtain the target feature information corresponding to the target device. The target convolutional neural network model is used to predict the target device based on the target feature information to obtain vibration information such as the vibration intensity, damage degree, and whether there is rotation and tipping of the target device. Finally, the target decision tree model is used to determine the target shock reduction strategy that best suits the target device based on the vibration information to perform shock reduction processing on the target device.

[0055] By analyzing and calculating the collected target data, the target feature information can be accurately obtained. The target convolutional neural network model and the target decision tree model are used to predict and make decisions on the target equipment to obtain the most suitable shock reduction strategy for the target equipment, effectively reducing the damage risk of the target equipment and extending the service life of the target equipment. At the same time, through automated shock reduction processing, the stability and reliability of the equipment are improved, the maintenance cost and the risk of production interruption are reduced, thereby improving work efficiency and production benefits.

[0056] Optionally, in the shock absorption method provided in the embodiment of the present application, collecting target data of the target device includes: collecting first data of the target device through a target sensor; correcting abnormal values ​​in the first data to obtain second data; filling missing values ​​in the second data to obtain third data; filtering the third data to obtain target data.

[0057] In an optional embodiment, after the target sensor formed by the fusion of the three-axis sensor and the piezoelectric sensor collects the first data of the target device, the abnormal values ​​of the first data (the abnormal values ​​may be caused by sensor failure or other external factors) are corrected or eliminated to obtain the second data. The missing values ​​in the second data (the missing values ​​may be caused by sensor failure or data recording error) are interpolated or filled to obtain the third data. The third data is filtered by the sliding window averaging technology to remove noise and smooth the data to obtain the target data.

[0058] By correcting or removing outliers from the first data and interpolating or filling the second data, the accuracy and integrity of the data can be improved, ensuring the reliability of subsequent analysis and processing. By filtering the third data through the sliding window averaging technology, noise can be effectively removed and data can be smoothed, making the final target data more stable and reliable.

[0059] Optionally, in the shock reduction method provided in the embodiment of the present application, collecting the first data of the target device through the target sensor includes: collecting the initial acceleration of the target device when vibration occurs through the accelerometer in the three-axis sensor in the target sensor; collecting the initial angular velocity of the target device when vibration occurs through the gyroscope in the three-axis sensor in the target sensor; collecting the initial vibration waveform of the target device when vibration occurs through the piezoelectric sensor in the target sensor; and determining the first data based on the initial acceleration, initial angular velocity and initial vibration waveform.

[0060] In an optional embodiment, the three-axis sensor is a device that integrates two different types of sensors, an accelerometer and a gyroscope. The accelerometer is mainly used to measure the acceleration information (i.e., initial acceleration) of the cabinet on three spatial axes. By measuring the change in the acceleration of the cabinet, the acceleration vector of the cabinet can be obtained, and then its velocity and displacement changes can be calculated. The gyroscope is used to measure the angular velocity information (i.e., initial angular velocity) of the cabinet, that is, the speed at which the cabinet rotates around the three spatial axes. By measuring the change in the angular velocity of the cabinet, its angular velocity vector can be obtained, thereby calculating the rotation angle and rotation state of the cabinet. The measurement results of the accelerometer and the gyroscope provide key information such as the position, velocity, rotation angle direction, etc. of the object in space, providing data support for analyzing the intensity of the vibration and determining whether the cabinet has tipped over.

[0061] Piezoelectric sensors convert mechanical energy into electrical energy based on the positive piezoelectric effect, realizing the conversion of force and electricity. When certain materials are deformed under the action of external forces in a specific direction, they will show equal amounts of positive and negative charges on two opposite surfaces at the same time, and the amount of charge is proportional to the magnitude of the applied external force. After the external force is eliminated, it will return to an uncharged state. This phenomenon is called the positive piezoelectric effect, this material is called a piezoelectric material, and the parts made of piezoelectric materials are called piezoelectric sensitive parts. When external vibrations (i.e., periodic changes in external forces) are sensed, the surface charge of the piezoelectric sensitive element also shows periodic changes, and the frequency of the change is consistent with the vibration frequency. The purpose of vibration measurement can be achieved by collecting and measuring the surface charge signals of piezoelectric sensitive elements. The complete cabinet vibration waveform data (i.e., the initial vibration waveform) is collected by the piezoelectric vibration sensor.

[0062] Through the accelerometer, gyroscope and piezoelectric sensor in the three-axis sensor, the first data of the target device when vibration occurs can be quickly and accurately collected.

[0063] Optionally, in the shock absorption method provided in the embodiment of the present application, processing the target data to obtain target characteristic information corresponding to the target data includes: calculating the target data to obtain first characteristic information corresponding to the target data, wherein the first characteristic information includes at least: mean, variance, maximum value and minimum value; performing frequency domain analysis on the target data to obtain second characteristic information corresponding to the target data; performing time domain analysis on the target data to obtain third characteristic information corresponding to the target data; and determining the target characteristic information based on the first characteristic information, the second characteristic information and the third characteristic information.

[0064] In an optional embodiment, the position, displacement, velocity change, and rotation angle of the cabinet in space are calculated based on the acceleration and angular velocity in the target data, and the mean, variance, maximum, and minimum of the target data are calculated to obtain the first characteristic information. The target data is decomposed using a continuous Morlet wavelet transform (scaling factor is 256) to obtain the second characteristic information. The amplitude and time domain characteristics of the target data are extracted through peak analysis and envelope analysis to obtain the third characteristic information.

[0065] By performing calculations, frequency domain analysis, and time domain analysis on target data, target feature information can be obtained quickly and accurately.

[0066] Optionally, in the shock absorption method provided in the embodiment of the present application, frequency domain analysis is performed on the target data to obtain second characteristic information corresponding to the target data, including: discretizing the target data to obtain discretized target data; performing Fourier transform on the discretized target data to obtain transformed target data; performing spectral analysis on the transformed target data to obtain second characteristic information.

[0067] In an optional embodiment, continuous target data is processed in segments by sampling or other methods, and converted into discrete data to obtain discrete target data. The discrete target data is subjected to Fourier transform (FFT) and converted into the frequency domain to obtain the amplitude and phase information of the frequency domain signal (i.e., the transformed target data). By performing spectrum analysis on the Fourier transformed data, the frequency components and energy distribution of the signal in the frequency domain can be obtained, and the characteristics of the target data in the frequency domain can be further understood, including but not limited to: frequency range, frequency intensity and other information, thereby obtaining the second characteristic information.

[0068] Through the above steps, more information about the frequency characteristics of the data can be accurately obtained, which is helpful for in-depth analysis of the frequency domain characteristics of the target data and provides more references for subsequent signal processing and analysis.

[0069] Optionally, in the shock absorption method provided in the embodiment of the present application, time domain analysis is performed on the target data to obtain third characteristic information corresponding to the target data, including: determining a time domain graph corresponding to the target data; performing calculations based on the time domain graph to obtain time domain characteristic information corresponding to the target data; and performing calculations based on the time domain characteristic information to obtain third characteristic information.

[0070] In an optional embodiment, a corresponding time domain graph is drawn according to the time series of the target data, that is, a curve image of the data changing over time. In the time domain graph, various statistical features are calculated, including but not limited to: time domain feature information such as mean, variance, peak value and waveform factor. Based on the time domain feature information, the time domain characteristics of the data are further analyzed, including but not limited to: periodicity and trend, etc., and feature extraction and data processing are performed according to requirements to obtain third feature information.

[0071] By performing time domain analysis on the target data, the changing trend, periodicity and vibration characteristics of the data can be obtained quickly and accurately, which helps to deeply understand the actual meaning and regularity of the data.

[0072] Optionally, in the shock reduction method provided in the embodiment of the present application, determining a target shock reduction strategy corresponding to the target device based on vibration information through a target decision tree model includes: obtaining multiple shock reduction strategies in a strategy database; calculating according to preset weight values ​​and vibration information to obtain a vibration level corresponding to the target device; and determining a target shock reduction strategy from multiple shock reduction strategies based on the vibration level through a target decision tree model.

[0073] In an optional embodiment, multiple defined shock reduction strategies (i.e., multiple shock reduction strategies) are obtained from a strategy database, and these strategies include different shock reduction schemes, shock reduction measures, or shock reduction parameter settings. According to the preset weight value and the data extracted from the vibration information, the vibration level of the target device (divided into high, medium, and low levels) is calculated to evaluate the current vibration state of the target device. And using the target decision tree model, the vibration level is used as an input feature, combined with multiple defined shock reduction strategies as decision conditions, to determine the shock reduction strategy (i.e., the target shock reduction strategy) that is most suitable for the target device to protect the target device from vibration damage.

[0074] Through the above steps, the decision tree model can be used to intelligently determine the most appropriate shock absorption scheme based on the vibration level of the target equipment and the defined shock absorption strategy, thereby improving the stability and reliability of the equipment, reducing the risk of damage, and ensuring the normal operation of the equipment.

[0075] It should be noted that after determining the target shock reduction strategy, emergency processing instructions can be sent to the agent software running in the storage device through the TCP / IP protocol or USB protocol, including but not limited to: stop working or health scan instructions. For example: the agent software sends an immediate instruction to the storage device to stop the head from working and retract the head from the working state to the head stop area, thereby reducing the damage to the storage device caused by vibration and protecting the storage device and the data in the storage device; when receiving the recovery work instruction, the agent software will send a signal again to restore the storage device to the working state. And the SQLite lightweight embedded database records the time, level, whether the storage device has tipped over, rotated, and the emergency processing actions that have been executed. At the same time, with the help of the storage server's own network, the abnormal information is pushed to the relevant management personnel in real time through the agent software.

[0076] It should be noted that Figure 2 Schematic diagram of a shock absorption method according to an embodiment of the present application. Figure 2 As shown, the shock reduction method includes: a data acquisition module, a data preprocessing module, a machine learning module and an emergency processing module. First, the target data of the storage device when vibration occurs is collected by the three-axis sensor and the piezoelectric sensor (i.e., the vibration sensor) in the data acquisition module. Then, the target data is processed and filtered for abnormal values ​​and missing values ​​by the data preprocessing module, and the processed data is operated and feature extracted to obtain the target feature information corresponding to the storage device. At the same time, the target convolutional neural network model in the machine learning module is used to predict the storage device based on the target feature information to obtain the vibration information corresponding to the target device. And the target decision tree model in the machine learning module is used to determine the target shock reduction strategy corresponding to the target device based on the vibration information. Finally, the storage device is subjected to shock reduction processing based on the target shock reduction strategy, and the time, level, whether the storage device has tipped over, rotated, and the emergency processing actions that have been executed are recorded. At the same time, with the help of the storage server's own network, the abnormal information is pushed to the relevant management personnel in real time through the agent software.

[0077] It should be noted that Figure 3 Schematic diagram of shockproofing a storage device according to an embodiment of the present application. Figure 3As shown in the figure, the shockproof system for storage devices mainly consists of four parts: sensors, main controllers, switches, and agent software pre-installed in the storage devices. The sensor is a fusion of a three-axis sensor and a piezoelectric sensor. A three-axis sensor is a device that integrates two different types of sensors: an accelerometer and a gyroscope. The accelerometer is mainly used to measure the acceleration of the cabinet on three spatial axes. By measuring the change in the acceleration of the cabinet, the acceleration vector of the cabinet can be obtained, and then its velocity and displacement changes can be calculated. The gyroscope is used to measure the angular velocity of the cabinet, that is, the speed at which the cabinet rotates around the three spatial axes. By measuring the change in the angular velocity of the cabinet, its angular velocity vector can be obtained, and the rotation angle and rotation state of the cabinet can be calculated. The measurement results of the accelerometer and gyroscope provide key information such as the position, velocity, and rotation angle direction of the object in space, providing data support for analyzing the intensity of the vibration and determining whether the cabinet has tipped over. Based on the positive piezoelectric effect, the piezoelectric sensor converts mechanical energy into electrical energy to achieve the conversion of force and electricity. When certain materials are deformed under the action of external forces in a specific direction, they will show equal amounts of positive and negative charges on two opposite surfaces at the same time, and the amount of charge is proportional to the magnitude of the applied external force. After the external force is eliminated, it will return to an uncharged state. This phenomenon is called the positive piezoelectric effect, the material is called a piezoelectric material, and the parts made of piezoelectric materials are called piezoelectric sensitive parts. When external vibrations (i.e., periodic changes in external forces) are sensed, the surface charge of the piezoelectric sensitive element also shows periodic changes, and the frequency of the change is consistent with the vibration frequency. The purpose of vibration measurement can be achieved by collecting and measuring the surface charge signals of piezoelectric sensitive elements. The complete cabinet vibration waveform data is collected through the piezoelectric vibration sensor.

[0078] The main controller refers to a chip with strong computing power in terms of hardware configuration, ensuring that more complex machine learning models can run smoothly, while only relying on network interface peripherals to meet instruction transmission requirements. It includes four core modules: data acquisition, data preprocessing, machine learning, and diagnosis and processing. These four modules work together to proactively and quickly predict and respond to sudden vibration and impact events. Through efficient analysis of machine learning models, the system can send early warning instructions to the agent software before damage actually occurs, thereby significantly reducing the risk of damage to storage devices and effectively preventing the loss of important data.

[0079] By deploying lightweight agent software on the original storage device, efficient read and write control, full disk scanning and other functions of the storage device are realized. In the normal state of the device without vibration, the software runs in the background for continuous monitoring to ensure the effective use of system resources. Only when the network port data upload is detected, the software will quickly start and perform the corresponding work tasks, such as read and write control, full disk scanning, etc. This process has little impact on the performance of the storage device, thus ensuring the stability and reliability of the system.

[0080] The shock reduction method provided in the embodiment of the present application collects target data of the target device when vibration is detected in the target device, wherein the target data includes at least: acceleration, angular velocity and vibration waveform of the target device when vibration occurs; processes the target data to obtain target feature information corresponding to the target data; predicts the target device based on the target feature information through a target convolutional neural network model to obtain vibration information corresponding to the target device, wherein the vibration information includes at least: vibration intensity and vibration damage degree corresponding to the target device; determines a target shock reduction strategy corresponding to the target device based on the vibration information through a target decision tree model, wherein the target shock reduction strategy is used to perform shock reduction processing on the target device when vibration is detected in the target device, thereby solving the problem in the related art that when vibration of the storage device is detected, the vibration condition of the storage device is manually evaluated, and the shock reduction strategy of the storage device is determined based on experience, resulting in low efficiency in determining the shock reduction strategy.

[0081] In summary, in this solution, when the target device is detected to be vibrating, target data such as acceleration, angular velocity, and vibration waveform of the target device are collected. Then, the target data is subjected to various analyses and calculations to obtain the target feature information corresponding to the target device. The target convolutional neural network model is used to predict the target device based on the target feature information to obtain vibration information such as the vibration intensity, damage degree, and whether there is rotation and tipping of the target device. Finally, the target decision tree model is used to determine the target shock reduction strategy that best suits the target device based on the vibration information to perform shock reduction processing on the target device.

[0082] By analyzing and calculating the collected target data, the target feature information can be accurately obtained. The target convolutional neural network model and the target decision tree model are used to predict and make decisions on the target equipment to obtain the most suitable shock reduction strategy for the target equipment, effectively reducing the damage risk of the target equipment and extending the service life of the target equipment. At the same time, through automated shock reduction processing, the stability and reliability of the equipment are improved, the maintenance cost and the risk of production interruption are reduced, thereby improving work efficiency and production benefits.

[0083] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0084] The embodiment of the present application also provides a shock absorbing device. It should be noted that the shock absorbing device of the embodiment of the present application can be used to execute the shock absorbing method provided in the embodiment of the present application. The shock absorbing device provided in the embodiment of the present application is introduced below.

[0085] Figure 4 Schematic diagram of a shock absorbing device according to an embodiment of the present application. Figure 4 As shown, the device includes: a collection unit 401, a processing unit 402, a prediction unit 403, and a determination unit 404.

[0086] The acquisition unit 401 is used to acquire target data of the target device when the target device is detected to be vibrating, wherein the target data at least includes: acceleration, angular velocity and vibration waveform of the target device when the target device is vibrating;

[0087] The processing unit 402 is used to process the target data to obtain target feature information corresponding to the target data;

[0088] The prediction unit 403 is used to predict the target device based on the target feature information through the target convolution neural network model to obtain vibration information corresponding to the target device, wherein the vibration information at least includes: vibration intensity and vibration damage degree corresponding to the target device;

[0089] The determination unit 404 is used to determine a target vibration reduction strategy corresponding to the target device based on the vibration information through a target decision tree model, wherein the target vibration reduction strategy is used to perform vibration reduction processing on the target device when vibration of the target device is detected.

[0090] In the shock absorption device provided by the embodiment of the present application, the acquisition unit 401 acquires target data of the target device when the target device is detected to be vibrating, wherein the target data at least includes: the acceleration, angular velocity and vibration waveform of the target device when the vibration occurs; the processing unit 402 processes the target data to obtain target feature information corresponding to the target data; the prediction unit 403 predicts the target device based on the target feature information through a target convolutional neural network model to obtain vibration information corresponding to the target device, wherein the vibration information at least includes: the vibration intensity and the degree of vibration damage corresponding to the target device; the determination unit 404 determines the target shock absorption strategy corresponding to the target device based on the vibration information through a target decision tree model, wherein the target shock absorption strategy is used to perform shock absorption processing on the target device when the vibration of the target device is detected, which solves the problem in the related art that when the vibration of the storage device is detected, the vibration condition of the storage device is manually evaluated, and the shock absorption strategy of the storage device is determined based on experience, resulting in low efficiency in determining the shock absorption strategy.

[0091] In this scheme, when the target device is detected to be vibrating, target data such as acceleration, angular velocity, and vibration waveform of the target device are collected. Then, the target data is subjected to various analyses and calculations to obtain the target feature information corresponding to the target device. The target convolutional neural network model is used to predict the target device based on the target feature information to obtain vibration information such as the vibration intensity, damage degree, and whether there is rotation and tipping of the target device. Finally, the target decision tree model is used to determine the target shock reduction strategy that best suits the target device based on the vibration information to perform shock reduction processing on the target device.

[0092] By analyzing and calculating the collected target data, the target feature information can be accurately obtained. The target convolutional neural network model and the target decision tree model are used to predict and make decisions on the target equipment to obtain the most suitable shock reduction strategy for the target equipment, effectively reducing the damage risk of the target equipment and extending the service life of the target equipment. At the same time, through automated shock reduction processing, the stability and reliability of the equipment are improved, the maintenance cost and the risk of production interruption are reduced, thereby improving work efficiency and production benefits.

[0093] Optionally, in the shock absorbing device provided in the embodiment of the present application, the acquisition unit includes: an acquisition module, used to acquire first data of the target device through a target sensor; a correction module, used to correct abnormal values ​​in the first data to obtain second data; a filling module, used to fill missing values ​​in the second data to obtain third data; and a filtering module, used to filter the third data to obtain target data.

[0094] Optionally, in the shock absorption device provided in the embodiment of the present application, the acquisition module includes: a first acquisition submodule, used to acquire the initial acceleration of the target device when vibration occurs through the accelerometer in the three-axis sensor in the target sensor; a second acquisition submodule, used to acquire the initial angular velocity of the target device when vibration occurs through the gyroscope in the three-axis sensor in the target sensor; a third acquisition submodule, used to acquire the initial vibration waveform of the target device when vibration occurs through the piezoelectric sensor in the target sensor; a first determination submodule, used to determine the first data based on the initial acceleration, initial angular velocity and initial vibration waveform.

[0095] Optionally, in the shock absorbing device provided in the embodiment of the present application, the processing unit includes: a first calculation module, used to calculate the target data to obtain first characteristic information corresponding to the target data, wherein the first characteristic information includes at least: mean, variance, maximum value and minimum value; a first analysis module, used to perform frequency domain analysis on the target data to obtain second characteristic information corresponding to the target data; a second analysis module, used to perform time domain analysis on the target data to obtain third characteristic information corresponding to the target data; a first determination module, used to determine the target characteristic information based on the first characteristic information, the second characteristic information and the third characteristic information.

[0096] Optionally, in the shock absorbing device provided in the embodiment of the present application, the first analysis module includes: a discrete sub-module, used to discretize the target data to obtain discretized target data; a transformation sub-module, used to perform Fourier transform on the discretized target data to obtain transformed target data; and an analysis sub-module, used to perform spectral analysis on the transformed target data to obtain second characteristic information.

[0097] Optionally, in the shock absorbing device provided in the embodiment of the present application, the second analysis module includes: a second determination submodule, used to determine the time domain graph corresponding to the target data; a first calculation submodule, used to perform calculations based on the time domain graph to obtain time domain feature information corresponding to the target data; and a second calculation submodule, used to perform calculations based on the time domain feature information to obtain third feature information.

[0098] Optionally, in the shock absorption device provided in the embodiment of the present application, the determination unit includes: an acquisition module, used to acquire multiple shock absorption strategies in a strategy database; a second calculation module, used to perform calculations based on preset weight values ​​and vibration information to obtain a vibration level corresponding to a target device; and a second determination module, used to determine a target shock absorption strategy among multiple shock absorption strategies based on the vibration level through a target decision tree model.

[0099] The shock absorption device includes a processor and a memory. The above-mentioned acquisition unit 401, processing unit 402, prediction unit 403, determination unit 404, etc. are all stored in the memory as program units. The processor executes the above-mentioned program units stored in the memory to achieve efficient shock absorption of the storage device.

[0100] The processor includes a kernel, which calls the corresponding program unit from the memory. One or more kernels can be set, and efficient shock absorption of the storage device can be achieved by adjusting the kernel parameters.

[0101] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0102] An embodiment of the present invention provides a computer-readable storage medium on which a program is stored. When the program is executed by a processor, a vibration reduction method is implemented.

[0103] An embodiment of the present invention provides a processor, which is used to run a program, wherein the vibration reduction method is executed when the program is running.

[0104] like Figure 5 As shown, an embodiment of the present invention provides an electronic device, the device includes a processor, a memory, and a program stored in the memory and executable on the processor, and the processor implements the following steps when executing the program: when vibration of the target device is detected, target data of the target device is collected, wherein the target data at least includes: acceleration, angular velocity and vibration waveform of the target device when vibration occurs; the target data is processed to obtain target feature information corresponding to the target data; the target device is predicted based on the target feature information by a target convolutional neural network model to obtain vibration information corresponding to the target device, wherein the vibration information at least includes: vibration intensity and vibration damage degree corresponding to the target device; and a target shock reduction strategy corresponding to the target device is determined based on the vibration information by a target decision tree model, wherein the target shock reduction strategy is used to perform shock reduction processing on the target device when vibration of the target device is detected.

[0105] Optionally, collecting target data of the target device includes: collecting first data of the target device through a target sensor; correcting abnormal values ​​in the first data to obtain second data; filling missing values ​​in the second data to obtain third data; and filtering the third data to obtain target data.

[0106] Optionally, collecting the first data of the target device through the target sensor includes: collecting the initial acceleration of the target device when vibrating through the accelerometer in the three-axis sensor in the target sensor; collecting the initial angular velocity of the target device when vibrating through the gyroscope in the three-axis sensor in the target sensor; collecting the initial vibration waveform of the target device when vibrating through the piezoelectric sensor in the target sensor; and determining the first data based on the initial acceleration, initial angular velocity and initial vibration waveform.

[0107] Optionally, processing the target data to obtain target feature information corresponding to the target data includes: calculating the target data to obtain first feature information corresponding to the target data, wherein the first feature information includes at least: mean, variance, maximum value and minimum value; performing frequency domain analysis on the target data to obtain second feature information corresponding to the target data; performing time domain analysis on the target data to obtain third feature information corresponding to the target data; and determining the target feature information based on the first feature information, the second feature information and the third feature information.

[0108] Optionally, performing frequency domain analysis on the target data to obtain second feature information corresponding to the target data includes: discretizing the target data to obtain discretized target data; performing Fourier transform on the discretized target data to obtain transformed target data; and performing spectrum analysis on the transformed target data to obtain second feature information.

[0109] Optionally, performing time domain analysis on the target data to obtain third characteristic information corresponding to the target data includes: determining a time domain graph corresponding to the target data; performing calculations based on the time domain graph to obtain time domain characteristic information corresponding to the target data; and performing calculations based on the time domain characteristic information to obtain third characteristic information.

[0110] Optionally, determining a target shock reduction strategy corresponding to a target device based on vibration information through a target decision tree model includes: acquiring multiple shock reduction strategies in a strategy database; calculating according to preset weight values ​​and vibration information to obtain a vibration level corresponding to the target device; and determining a target shock reduction strategy from multiple shock reduction strategies based on the vibration level through a target decision tree model.

[0111] The devices in this article can be servers, PCs, PADs, mobile phones, etc.

[0112] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that is initialized with the following method steps: when vibration of a target device is detected, target data of the target device is collected, wherein the target data at least includes: the acceleration, angular velocity and vibration waveform of the target device when vibration occurs; the target data is processed to obtain target feature information corresponding to the target data; the target device is predicted based on the target feature information by a target convolutional neural network model to obtain vibration information corresponding to the target device, wherein the vibration information at least includes: the vibration intensity and vibration damage degree corresponding to the target device; and a target shock reduction strategy corresponding to the target device is determined based on the vibration information by a target decision tree model, wherein the target shock reduction strategy is used to perform shock reduction processing on the target device when vibration of the target device is detected.

[0113] Optionally, collecting target data of the target device includes: collecting first data of the target device through a target sensor; correcting abnormal values ​​in the first data to obtain second data; filling missing values ​​in the second data to obtain third data; and filtering the third data to obtain target data.

[0114] Optionally, collecting the first data of the target device through the target sensor includes: collecting the initial acceleration of the target device when vibrating through the accelerometer in the three-axis sensor in the target sensor; collecting the initial angular velocity of the target device when vibrating through the gyroscope in the three-axis sensor in the target sensor; collecting the initial vibration waveform of the target device when vibrating through the piezoelectric sensor in the target sensor; and determining the first data based on the initial acceleration, initial angular velocity and initial vibration waveform.

[0115] Optionally, processing the target data to obtain target feature information corresponding to the target data includes: calculating the target data to obtain first feature information corresponding to the target data, wherein the first feature information includes at least: mean, variance, maximum value and minimum value; performing frequency domain analysis on the target data to obtain second feature information corresponding to the target data; performing time domain analysis on the target data to obtain third feature information corresponding to the target data; and determining the target feature information based on the first feature information, the second feature information and the third feature information.

[0116] Optionally, performing frequency domain analysis on the target data to obtain second feature information corresponding to the target data includes: discretizing the target data to obtain discretized target data; performing Fourier transform on the discretized target data to obtain transformed target data; and performing spectrum analysis on the transformed target data to obtain second feature information.

[0117] Optionally, performing time domain analysis on the target data to obtain third characteristic information corresponding to the target data includes: determining a time domain graph corresponding to the target data; performing calculations based on the time domain graph to obtain time domain characteristic information corresponding to the target data; and performing calculations based on the time domain characteristic information to obtain third characteristic information.

[0118] Optionally, determining a target shock reduction strategy corresponding to a target device based on vibration information through a target decision tree model includes: acquiring multiple shock reduction strategies in a strategy database; calculating according to preset weight values ​​and vibration information to obtain a vibration level corresponding to the target device; and determining a target shock reduction strategy from multiple shock reduction strategies based on the vibration level through a target decision tree model.

[0119] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0120] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0121] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0122] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0123] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0124] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0125] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0126] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0127] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0128] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A shock reduction method, characterized in that: include: When the target device is detected to be vibrating, target data of the target device is collected, wherein the target data at least includes: acceleration, angular velocity and vibration waveform of the target device when the vibration occurs; Processing the target data to obtain target feature information corresponding to the target data; Predicting the target device based on the target feature information through a target convolutional neural network model to obtain vibration information corresponding to the target device, wherein the vibration information at least includes: vibration intensity and vibration damage degree corresponding to the target device; A target shock reduction strategy corresponding to the target device is determined based on the shock information through a target decision tree model, wherein the target shock reduction strategy is used to perform shock reduction processing on the target device when vibration of the target device is detected.

2. The method according to claim 1, characterized in that Collecting the target data of the target device includes: Collecting first data of the target device through a target sensor; Correcting abnormal values ​​in the first data to obtain second data; Filling missing values ​​in the second data to obtain third data; The third data is filtered to obtain the target data.

3. The method according to claim 2, characterized in that Collecting the first data of the target device by the target sensor includes: Collecting the initial acceleration of the target device when vibration occurs by using an accelerometer in a three-axis sensor in the target sensor; Collecting the initial angular velocity of the target device when vibration occurs by using a gyroscope in a three-axis sensor in the target sensor; Collecting an initial vibration waveform of the target device when it vibrates by means of a piezoelectric sensor in the target sensor; The first data is determined according to the initial acceleration, the initial angular velocity and the initial vibration waveform.

4. The method according to claim 1, characterized in that: Processing the target data to obtain target feature information corresponding to the target data includes: Calculating the target data to obtain first feature information corresponding to the target data, wherein the first feature information at least includes: mean, variance, maximum value and minimum value; Performing frequency domain analysis on the target data to obtain second feature information corresponding to the target data; Performing time domain analysis on the target data to obtain third feature information corresponding to the target data; The target characteristic information is determined based on the first characteristic information, the second characteristic information and the third characteristic information.

5. The method according to claim 4, characterized in that Performing frequency domain analysis on the target data to obtain second feature information corresponding to the target data includes: Discretizing the target data to obtain discrete target data; Performing Fourier transform on the discretized target data to obtain transformed target data; Performing spectrum analysis on the transformed target data to obtain the second feature information.

6. The method according to claim 4, characterized in that Performing time domain analysis on the target data to obtain third feature information corresponding to the target data includes: Determine a time domain graph corresponding to the target data; Calculating according to the time domain graph to obtain time domain feature information corresponding to the target data; Calculation is performed based on the time domain feature information to obtain the third feature information.

7. The method according to claim 1, characterized in that Determining a target vibration reduction strategy corresponding to the target device based on the vibration information through a target decision tree model includes: Obtain multiple shock absorption strategies from a strategy database; Calculating according to a preset weight value and the vibration information to obtain a vibration level corresponding to the target device; The target damping strategy is determined among the plurality of damping strategies based on the vibration level by the target decision tree model.

8. A shock absorbing device, characterized in that: include: A collection unit, configured to collect target data of the target device when vibration of the target device is detected, wherein the target data at least includes: acceleration, angular velocity and vibration waveform of the target device when vibration occurs; A processing unit, used to process the target data to obtain target feature information corresponding to the target data; A prediction unit, configured to predict the target device based on the target feature information through a target convolutional neural network model to obtain vibration information corresponding to the target device, wherein the vibration information at least includes: vibration intensity and vibration damage degree corresponding to the target device; A determination unit is used to determine a target vibration reduction strategy corresponding to the target device based on the vibration information through a target decision tree model, wherein the target vibration reduction strategy is used to perform vibration reduction processing on the target device when vibration of the target device is detected.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the storage medium is controlled to execute the vibration reduction method according to any one of claims 1 to 7 on a device.

10. An electronic device, characterized in that: It comprises one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the shock absorption method described in any one of claims 1 to 7.

Images