Dry vacuum pump vibration data analysis system and method based on big data

Abstract

The invention discloses a dry vacuum pump vibration data analysis system and method based on big data, and belongs to the technical field of data analysis. The system comprises a vacuum pump control module, a data acquisition and transmission module, a database, a model management and analysis module, an intelligent judgment module, an early warning module and a display module, the vacuum pump control module is used for starting and closing the dry vacuum pump; the data acquisition and transmission module is used for acquiring parameter data and vibration amplitude data; the database is used for storing historical data; the model management and analysis module is used for establishing a vibration analysis model and analyzing the influence of different parameter data on the vibration amplitude in the process of extracting the gas in the container by the dry vacuum pump; the intelligent judgment module is used for judging whether the current dry vacuum pump has a fault risk or not; the early warning module is used for carrying out fault alarm; and the display module is used for providing an interaction platform and carrying out digital display.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and particularly to a vibration data analysis system and method for a dry vacuum pump based on big data. Background Technique

[0002] With the development of industrial automation and Internet of Things technologies, dry vacuum pumps, as oil-free and pollution-free vacuum extraction devices, are widely used in many fields; when a dry vacuum pump operates, as the internal screw of the pump starts, a negative pressure is formed inside the pump cavity, and under the action of the pressure difference, the gas in the system to be pumped is inhaled and discharged, thus creating a vacuum environment in the system to be pumped; by installing monitoring devices in the dry vacuum pump, abnormalities can be detected at the initial stage of equipment failure, and measures can be taken in a timely manner for maintenance to reduce the occurrence of safety risks; in the prior art, the fault judgment of dry vacuum pumps mostly relies on manual experience and preset rules, lacking intelligent automatic diagnosis functions and having limitations; it is difficult to further analyze the vibration signals of dry vacuum pumps under different working conditions, which easily leads to failure to identify faults or misjudgment of the system. Summary of the Invention

[0003] The purpose of the present invention is to provide a vibration data analysis system and method for a dry vacuum pump based on big data to solve the problems raised in the above background technique.

[0004] To solve the above technical problems, the present invention provides the following technical solution: A vibration data analysis method for a dry vacuum pump based on big data, the method includes the following steps: Step S1: Start the dry vacuum pump to extract the gas in the container, install a pressure acquisition device at the air inlet of the dry vacuum pump, and collect the parameter data during the process of extracting the gas in the container; the parameter data includes the volume of the container and the change in the gas pressure at the air inlet of the dry vacuum pump. Step S2: Determine the vibration data acquisition points of the dry vacuum pump, and collect the vibration amplitude data at the vibration data acquisition points when the dry vacuum pump is operating. Step S3: Store the parameter data collected in Step S1 and the vibration amplitude data collected in Step S2 as historical data in the database, and establish a vibration analysis model based on the historical data stored in the database to analyze the influence of different parameter data on the vibration amplitude during the process of the dry vacuum pump extracting the gas in the container. Step S4: Analyze the real-time parameter data collected in Step S1 and the real-time vibration amplitude data collected in Step S2, and judge whether there is a fault risk for the current dry vacuum pump according to the analysis result of the vibration analysis model in Step S3; if there is no fault risk, continue to judge; if there is a fault risk, give a fault alarm and send an alarm message to the management personnel.

[0005] A vibration data analysis system for a dry vacuum pump based on big data, the system includes a vacuum pump control module, a data acquisition and transmission module, a database, a model management and analysis module, an intelligent judgment module, an early warning module and a display module; The vacuum pump control module is used to start and stop the dry vacuum pump; when the dry vacuum pump starts, it controls the dry vacuum pump to extract the gas in the container; The data acquisition and transmission module is used to install a pressure acquisition device at the inlet of the dry vacuum pump to acquire the parameter data during the gas extraction process in the container; the parameter data includes the volume of the container and the change in gas pressure at the inlet of the dry vacuum pump; determine the vibration data acquisition points of the dry vacuum pump, and acquire the vibration amplitude data at the vibration data acquisition points; send the acquired parameter data and vibration amplitude data to the database and the intelligent judgment module; The database is used to store the acquired parameter data and vibration amplitude data as historical data and continuously update them; The model management and analysis module is used to establish a vibration analysis model based on the historical data stored in the database, and analyze the influence of different parameter data on the vibration amplitude during the process of the dry vacuum pump extracting the gas in the container; The intelligent judgment module is used to analyze the real-time parameter data and real-time vibration amplitude data acquired, and judge whether there is a fault risk for the current dry vacuum pump according to the analysis result of the vibration analysis model in the model management and analysis module; if there is no fault risk, continue to judge; if there is a fault risk, send a signal to the early warning module; The early warning module is used to give a fault alarm and send an alarm message to the management personnel; The display module is used to provide an interactive platform for digital display.

[0006] An electronic device, including: a processor and a memory, wherein, a computer program that can be called by the processor is stored in the memory; The processor executes the above-mentioned vibration data analysis method for a dry vacuum pump based on big data by calling the computer program stored in the memory.

[0007] A computer-readable storage medium stores instructions, and when the instructions run on a computer, the computer is made to execute the above-mentioned vibration data analysis method for a dry vacuum pump based on big data.

[0008] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: By analyzing the influence of different parameter data on the vibration amplitude, the fault diagnosis range of the vacuum pump is narrowed, and the accuracy of the vibration data analysis of the dry vacuum pump is improved; By calculating the deviation value of the current vibration amplitude of the dry vacuum pump, it is judged whether there is a fault risk in the current dry vacuum pump, reducing the interference of the instability of gas flow on the vibration data of the vacuum pump during the process of the dry vacuum pump extracting the gas in the container, thereby improving the fault diagnosis ability of the vacuum pump and reducing the occurrence of safety risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 is a schematic diagram of the steps of a method for analyzing the vibration data of a dry vacuum pump based on big data according to the present invention; Figure 2 is a schematic diagram of the structure of a system for analyzing the vibration data of a dry vacuum pump based on big data according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0010] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0011] When the dry vacuum pump extracts the gas in the container, at a high gas extraction rate, the flow rate of the gas increases, the impact force of the gas flow increases, and the contact force between the rotor and the pump housing increases, especially at the outer edge part of the rotor. If the balance of the rotor is not good, these contact forces will generate great vibrations; in addition, when the gas pressure in the container decreases, the rarefaction degree of the gas increases, which will also cause the movement of the rotor to become unstable, thereby causing rotor vibration.

[0012] Please refer to Figure 1 - Figure 2 , the present invention provides the following technical solutions:

[0013] Please refer to Figure 1 , in the first embodiment: A method for analyzing the vibration data of a dry vacuum pump based on big data is provided, and the method includes the following steps: Step S1: Start the dry vacuum pump to extract the gas in the container, and install a pressure acquisition device at the inlet of the dry vacuum pump to collect the parameter data during the process of extracting the gas in the container; the parameter data includes the volume of the container and the change in the gas pressure at the inlet of the dry vacuum pump.

[0014] Further, connect the gas outlet of the container to the gas inlet of the dry vacuum pump. Before the dry vacuum pump operates, determine the target pressure required for the gas in the container. When the dry vacuum pump extracts the gas in the container, monitor the gas pressure at the gas inlet of the dry vacuum pump through a pressure acquisition device. When the gas pressure at the gas inlet of the dry vacuum pump reaches the target pressure, turn off the vacuum pump and disconnect the connection between the gas outlet of the container and the gas inlet of the dry vacuum pump.

[0015] In this embodiment, the pressure acquisition device is a pressure sensor for acquiring the change in gas pressure at the gas inlet of the dry vacuum pump. Since the change in gas pressure in the container will cause instability in the gas flow in the dry vacuum pump, thereby affecting the vibration amplitude of the vacuum pump, by acquiring the change in gas pressure in the container and analyzing the influence of different gas extraction processes of the dry vacuum pump on the vibration data, the accuracy of the system's judgment of the vibration data is improved.

[0016] Step S2: Determine the vibration data acquisition points of the dry vacuum pump. When the dry vacuum pump operates, acquire the vibration amplitude data at the vibration data acquisition points. It should be noted that by analyzing the vibration data, the early judgment of whether there is a fault in the dry vacuum pump can be made. Since the parts prone to failure in the dry vacuum pump are the rotor and the cavity, in this embodiment, the vibration data acquisition points are arranged at the position near the rotor at the gas inlet of the dry vacuum pump to reflect the vibration induced by gas pulsation, and the vibration amplitude data near the gas inlet of the dry vacuum pump is acquired through a vibration sensor.

[0017] Step S3: Store the parameter data acquired in Step S1 and the vibration amplitude data acquired in Step S2 as historical data in the database. According to the historical data stored in the database, establish a vibration analysis model to analyze the influence of different parameter data on the vibration amplitude during the process of the dry vacuum pump extracting the gas in the container. Specifically, the method steps are as follows: Step S31: Store the acquired parameter data and vibration amplitude data as historical data in the database and update the database. Retrieve the historical parameter data and historical vibration amplitude data during the normal operation of the dry vacuum pump from the database for analysis. According to the historical parameter data, determine the volume of the container and determine the gas pressure at the gas inlet of the dry vacuum pump at different timestamps ; According to the historical vibration amplitude data, determine the vibration amplitude at the vibration data acquisition points at different timestamps ; ; Step S32: According to the analysis results of the historical parameter data in Step S31, calculate the gas extraction rate in the container at different timestamps ​ : ; Among them, represents the timestamp the gas pressure at the inlet of the down-dry vacuum pump; represents to the time step; represents the natural logarithm; Step S33. According to the analysis result of the historical vibration amplitude data in Step S31, calculate the change amplitude of the vibration amplitude at the vibration data acquisition point at different timestamps : : ; Among them, represents the timestamp the vibration amplitude at the vibration data acquisition point; Step S34. Establish a vibration analysis model, take the extraction rate of the gas in the container and the gas pressure at the inlet of the dry vacuum pump as influencing factors, and take the change amplitude of the vibration amplitude at the vibration data acquisition point as the influence value. Analyze the influence of different parameter data on the vibration amplitude during the process of the dry vacuum pump extracting the gas in the container. According to the calculation formula: ; Among them, represents the extraction rate of the gas in the container; represents the gas pressure at the inlet of the dry vacuum pump; represents the influence degree of the extraction rate of the gas in the container on the vibration amplitude at the vibration data acquisition point; and both represent the influence degree of the gas pressure at the inlet of the dry vacuum pump on the vibration amplitude at the vibration data acquisition point; represents a constant; represents the base of the natural logarithm; represents the natural logarithm.

[0018] In this embodiment, the working state of the dry vacuum pump is divided into normal operation and failure; the normal operation means that the vibration amplitude at the vibration data acquisition point of the dry vacuum pump is within the normal range, and the dry vacuum pump continues to operate; the failure means that the vibration amplitude at the vibration data acquisition point of the dry vacuum pump exceeds the normal range, and the dry vacuum pump stops working.

[0019] It should be noted that during the process of a dry vacuum pump extracting the gas in a container, when the gas extraction rate is too high, the vibration amplitude of the vacuum pump will increase, while the low gas extraction rate is relatively stable; when analyzing the influence of the gas pressure change in the container on the vibration amplitude of the dry vacuum pump, when the gas pressure in the container is high, the density of gas molecules is large, and when the gas in the container is extracted, the force acting on the vacuum pump increases, resulting in an increase in the vibration amplitude near the rotor position of the vacuum pump inlet; in this embodiment, by establishing a vibration analysis model, as the training parameters of as the training parameters of as the training parameters of, substitute them into the calculation formula in step S34 for fitting, determine and values, and according to the fitting results, analyze the influence of different parameter data on the vibration amplitude during the process of the dry vacuum pump extracting the gas in the container, so as to improve the accuracy of the vibration data analysis of the dry vacuum pump; among them, the fitting methods include but are not limited to the gradient descent method, the least squares method, and ridge regression; by analyzing the influence of different parameter data on the vibration amplitude, the fault diagnosis range of the vacuum pump is narrowed, the misjudgment of faults caused by the instability of the gas during the process of the vacuum pump extracting the gas in the container is avoided, and the accuracy of the vibration data analysis of the dry vacuum pump is improved.

[0020] Step S4: Analyze the real-time parameter data collected in step S1 and the real-time vibration amplitude data collected in step S2, and judge whether there is a fault risk for the current dry vacuum pump according to the analysis result of the vibration analysis model in step S3; if there is no fault risk, continue to judge; if there is a fault risk, give a fault alarm and send an alarm message to the management personnel.

[0021] Specifically, the method steps are as follows: Step S41: Analyze the collected real-time parameter data to determine the gas pressure at the inlet of the current dry vacuum pump, and determine the gas extraction rate of the gas in the current container; analyze the collected real-time vibration amplitude data to determine the amplitude change value at the current vibration data collection point, and calculate the deviation value of the vibration amplitude of the current dry vacuum pump: ; Step S42: Retrieve the historical parameter data and historical vibration amplitude data of the dry vacuum pump during a fault from the database for analysis; based on the historical parameter data, determine the gas pressure at the inlet of the dry vacuum pump and the gas extraction rate of the gas in the container during the fault of the dry vacuum pump; based on the historical vibration amplitude data, determine the amplitude change value of the vibration at the vibration data acquisition point during the fault of the dry vacuum pump; based on the analysis results of the retrieved historical data of the dry vacuum pump during a fault, determine the deviation values for different vibration amplitudes ; where represents the amount of data of the dry vacuum pump during a fault retrieved and analyzed from the database; construct a BP neural network, and divide into a training set and a validation set , input the training set into the BP neural network for training, train the network weights and thresholds through the backpropagation algorithm, and perform cross-validation on the validation set and the trained BP neural network to determine the maximum deviation threshold of the vibration amplitude during the fault of the dry vacuum pump ; Step S43: Compare with to determine whether there is a risk of failure for the current dry vacuum pump; when , there is no risk of failure for the current dry vacuum pump, and continue to judge; when , there is a risk of failure for the current dry vacuum pump, perform a fault alarm, and send an alarm signal to the management personnel.

[0022] It should be noted that by calculating the deviation value of the vibration amplitude of the current dry vacuum pump and comparing the calculated deviation value with the maximum deviation threshold of the vibration amplitude during the fault of the dry vacuum pump, the interference of the instability of gas flow on the vibration data of the vacuum pump during the process of the dry vacuum pump extracting the gas in the container is reduced, thereby improving the fault diagnosis ability of the vacuum pump and reducing the occurrence of safety risks.

[0023] Please refer to Figure 2 , in the second embodiment: A vibration data analysis system for a dry vacuum pump based on big data is provided, and this system includes a vacuum pump control module, a data acquisition and transmission module, a database, a model management and analysis module, an intelligent judgment module, an early warning module, and a display module; The vacuum pump control module is used to start and stop the dry vacuum pump; when the dry vacuum pump is started, control the dry vacuum pump to extract the gas in the container; The data acquisition and transmission module is used to install a pressure acquisition device at the inlet of the dry vacuum pump to collect parameter data during the process of extracting gas from the container; the parameter data includes the volume of the container and the change in gas pressure at the inlet of the dry vacuum pump; determine the vibration data acquisition points of the dry vacuum pump, and collect the vibration amplitude data at the vibration data acquisition points; send the collected parameter data and vibration amplitude data to the database and the intelligent judgment module; The database is used to store the collected parameter data and vibration amplitude data as historical data and continuously update them; The model management and analysis module is used to establish a vibration analysis model based on the historical data stored in the database, and analyze the influence of different parameter data on the vibration amplitude during the process of the dry vacuum pump extracting gas from the container; The intelligent judgment module is used to analyze the real-time parameter data and real-time vibration amplitude data collected, and judge whether there is a fault risk for the current dry vacuum pump according to the analysis result of the vibration analysis model in the model management and analysis module; if there is no fault risk, continue to judge; if there is a fault risk, send a signal to the warning module; The warning module is used to give a fault alarm and send an alarm message to the management personnel; The display module is used to provide an interactive platform for digital display.

[0024] Further, the model management and analysis module includes a historical data analysis unit and a model training unit; The historical data analysis unit is used to retrieve and analyze the historical parameter data and historical vibration amplitude data of the dry vacuum pump during normal operation from the database, determine the volume of the container according to the historical parameter data, and determine the gas pressure at the inlet of the dry vacuum pump at different timestamps. According to the analysis result of the historical parameter data, calculate the gas extraction rate in the container at different timestamps; according to the historical vibration amplitude data, determine the vibration amplitude at the vibration data acquisition points at different timestamps, and calculate the amplitude change amplitude of the vibration amplitude at the vibration data acquisition points at different timestamps according to the analysis result of the historical vibration amplitude data; The model training unit is used to establish a vibration analysis model, take the gas extraction rate in the container and the gas pressure at the inlet of the dry vacuum pump as influencing factors, and take the amplitude change amplitude of the vibration amplitude at the vibration data acquisition points as the influencing value, and analyze the influence of different parameter data on the vibration amplitude during the process of the dry vacuum pump extracting gas from the container.

[0025] Further, the intelligent judgment module includes a real-time data analysis unit, a threshold determination unit and a judgment unit; The real-time data analysis unit is used to analyze the collected real-time parameter data to determine the gas pressure at the inlet of the current dry vacuum pump and the gas extraction rate of the gas in the current container; analyze the collected real-time vibration amplitude data to determine the amplitude change amplitude at the current vibration data acquisition point, and calculate the deviation value of the vibration amplitude of the current dry vacuum pump; The threshold determination unit is used to retrieve and analyze the historical parameter data and historical vibration amplitude data when the dry vacuum pump fails from the database; determine the gas pressure at the inlet and the gas extraction rate of the gas in the container when the dry vacuum pump fails according to the historical parameter data; determine the amplitude change amplitude at the vibration data acquisition point when the dry vacuum pump fails according to the historical vibration amplitude data; determine the deviation values of different vibration amplitudes according to the analysis results of the retrieved historical data when the dry vacuum pump fails; construct a BP neural network, divide the deviation values of different vibration amplitudes into a training set and a validation set, input the training set into the BP neural network for training, train the network weights and thresholds through the backpropagation algorithm, and perform cross-validation on the validation set and the trained BP neural network to determine the maximum deviation threshold of the vibration amplitude when the dry vacuum pump fails; The judgment unit is used to judge whether there is a risk of failure of the current dry vacuum pump according to the deviation value of the vibration amplitude of the current dry vacuum pump and the maximum deviation threshold of the vibration amplitude when the dry vacuum pump fails; when there is no risk of failure of the current dry vacuum pump, continue to judge; when there is a risk of failure of the current dry vacuum pump, send a signal to the warning module.

[0026] Furthermore, the provided interaction platform is used to display the gas pressure at the inlet of the current dry vacuum pump, the gas extraction rate of the gas in the current container, the amplitude change amplitude at the current vibration data acquisition point, and the deviation value of the vibration amplitude of the current dry vacuum pump.

[0027] In this embodiment: This system is a vibration data analysis and fault warning system for a dry vacuum pump. When the vacuum pump control module starts the dry vacuum pump, it controls the dry vacuum pump to extract the gas in the container; The data acquisition and transmission module collects the parameter data during the gas extraction process in the container and the vibration amplitude data at the vibration data acquisition point; sends the collected parameter data and vibration amplitude data to the database and the intelligent judgment module; The database stores the collected parameter data and vibration amplitude data as historical data and continuously updates them; The historical data analysis unit in the model management and analysis module retrieves the historical parameter data and historical vibration amplitude data of the dry vacuum pump during normal operation from the database for analysis, and sends the analysis results to the model training unit; the model training unit establishes a vibration analysis model to analyze the influence of different parameter data on the vibration amplitude during the process of the dry vacuum pump extracting the gas in the container. The real-time data analysis unit in the intelligent judgment module analyzes the collected real-time parameter data and real-time vibration amplitude data, and sends the analysis results to the threshold determination unit; the threshold determination unit retrieves the historical parameter data and historical vibration amplitude data of the dry vacuum pump during a fault from the database for analysis, and determines the maximum deviation threshold of the vibration amplitude when the dry vacuum pump fails; the judgment unit determines whether there is a fault risk for the current dry vacuum pump based on the deviation value of the current vibration amplitude of the dry vacuum pump and the maximum deviation threshold of the vibration amplitude when the dry vacuum pump fails; when there is a fault risk for the current dry vacuum pump, a signal is sent to the warning module. After receiving the signal sent by the intelligent judgment module, the warning module issues a fault alarm and sends an alarm message to the management personnel. The display module provides an interaction platform to digitally display the gas pressure at the inlet of the current dry vacuum pump, the extraction rate of the gas in the current container, the change amplitude of the vibration amplitude at the current vibration data acquisition point, and the deviation value of the current vibration amplitude of the dry vacuum pump.

[0028] In the third embodiment: An electronic device is provided, including a processor and a memory, wherein a computer program that can be called by the processor is stored in the memory. The processor executes the steps of implementing the above-mentioned method for analyzing the vibration data of a dry vacuum pump based on big data by calling the computer program stored in the memory.

[0029] In the fourth embodiment: A computer-readable storage medium is provided, storing instructions that, when run on a computer, cause the computer to execute the steps of the above-mentioned method for analyzing the vibration data of a dry vacuum pump based on big data to achieve the following functions: determining the target pressure that the gas in the container needs to reach; collecting parameter data during the process of extracting the gas in the container; collecting vibration amplitude data at the vibration data acquisition point; establishing a vibration analysis model to analyze the influence of different parameter data on the vibration amplitude during the process of the dry vacuum pump extracting the gas in the container; determining whether there is a fault risk for the current dry vacuum pump.

[0030] The computer-readable storage medium includes various media for storing program codes, such as USB flash drives, mobile hard disks, read-only memories, random access memories, magnetic disks, or optical discs.

[0031] Finally, it should be noted that the above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions recorded in the foregoing embodiments or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A dry vacuum pump vibration data analysis method based on big data, characterized in that: The method comprises the following steps: Step S1, starting a dry vacuum pump to extract gas from a container, installing a pressure collection device at an air inlet of the dry vacuum pump, and collecting parameter data during the gas extraction process in the container; the parameter data includes the volume of the container and the change in gas pressure at the air inlet of the dry vacuum pump; Step S2, determining a vibration data collection point of the dry vacuum pump, and collecting vibration amplitude data at the vibration data collection point when the dry vacuum pump is operating; Step S3, storing the parameter data collected in step S1 and the vibration amplitude data collected in step S2 as historical data in a database, establishing a vibration analysis model based on the historical data stored in the database, and analyzing the influence of different parameter data on the vibration amplitude during the process of the dry vacuum pump extracting gas in the container; Step S4, analyze the real-time parameter data collected in step S1 and the real-time vibration amplitude data collected in step S2, and judge whether there is a failure risk in the current dry vacuum pump according to the analysis result of the vibration analysis model in step S3; if there is no failure risk, continue to judge; if there is a failure risk, issue a failure alarm and send an alarm message to the management personnel.

2. The dry vacuum pump vibration data analysis method based on big data according to claim 1, characterized in that: The gas outlet of the container is connected to the gas inlet of the dry vacuum pump. Before the dry vacuum pump is operated, the target pressure that the gas in the container needs to reach is determined; when the dry vacuum pump extracts the gas in the container, the gas pressure at the gas inlet of the dry vacuum pump is monitored by a pressure acquisition device. When the gas pressure at the gas inlet of the dry vacuum pump reaches the target pressure, the vacuum pump is turned off and the connection between the gas outlet of the container and the gas inlet of the dry vacuum pump is disconnected.

3. The dry vacuum pump vibration data analysis method based on big data according to claim 2 is characterized in that: The method steps of step S3 are: Step S31, storing the collected parameter data and vibration amplitude data as historical data in a database, and updating the database; retrieving the historical parameter data and historical vibration amplitude data of the dry vacuum pump during normal operation from the database for analysis, and determining the volume of the container based on the historical parameter data , and determine different timestamps The gas pressure at the inlet of the dry vacuum pump is ; Determine different timestamps based on historical vibration amplitude data The vibration amplitude at the vibration data collection point is ; Step S32: Calculate different timestamps based on the historical parameter data analysis results in step S31 The extraction rate of gas in the container is : ;in, Indicates timestamp The gas pressure at the inlet of the lower dry vacuum pump; express arrive The time step; represents the natural logarithm; Step S33: Calculate different timestamps according to the historical vibration amplitude data analysis results in step S31 The vibration amplitude change amplitude at the vibration data collection point is : ;in, Indicates timestamp The vibration amplitude at the vibration data collection point; Step S34, establish a vibration analysis model, take the extraction rate of gas in the container and the gas pressure at the air inlet of the dry vacuum pump as influencing factors, take the vibration amplitude change amplitude at the vibration data collection point as the influencing value, analyze the influence of different parameter data on the vibration amplitude during the process of the dry vacuum pump extracting gas in the container, according to the calculation formula: ； in, Indicates the extraction rate of gas in the container; Indicates the gas pressure at the inlet of the dry vacuum pump; Indicates the degree of influence of the extraction rate of gas in the container on the vibration amplitude at the vibration data collection point; and Both represent the influence of the gas pressure at the air inlet of the dry vacuum pump on the vibration amplitude at the vibration data collection point; represents a constant; represents the base of natural logarithms; Represents the natural logarithm.

4. The dry vacuum pump vibration data analysis method based on big data according to claim 3 is characterized by: The method steps of step S4 are: Step S41: Analyze the collected real-time parameter data to determine the current gas pressure at the air inlet of the dry vacuum pump. , and determine the extraction rate of the gas in the current container ; Analyze the collected real-time vibration amplitude data to determine the vibration amplitude change amplitude at the current vibration data collection point , calculate the deviation value of the current dry vacuum pump vibration amplitude : ； Step S42, retrieve the historical parameter data and historical vibration amplitude data when the dry vacuum pump fails from the database for analysis; determine the gas pressure at the air inlet and the extraction rate of the gas in the container when the dry vacuum pump fails based on the historical parameter data; determine the vibration amplitude change amplitude at the vibration data collection point when the dry vacuum pump fails based on the historical vibration amplitude data; determine the deviation values ​​of different vibration amplitudes based on the retrieved historical data analysis results when the dry vacuum pump fails ;in, represents the amount of data retrieved from the database for analysis of dry vacuum pump failures; constructing a BP neural network, Divide into training set and validation set , the training set Input into BP neural network for training, train network weights and thresholds through back propagation algorithm, and use the validation set Cross-validation with the trained BP neural network to determine the maximum deviation threshold of the vibration amplitude when the dry vacuum pump fails ; Step S43: and Compare and judge whether the current dry vacuum pump has the risk of failure; When the dry vacuum pump does not have a failure risk, continue to judge; when When the dry vacuum pump is at risk of failure, a fault alarm is issued and an alarm signal is sent to the management personnel.

5. A dry vacuum pump vibration data analysis system based on big data, characterized in that: The system includes a vacuum pump control module, a data acquisition and transmission module, a database, a model management and analysis module, an intelligent judgment module, an early warning module and a display module; The vacuum pump control module is used to start and shut down the dry vacuum pump; when the dry vacuum pump is started, the dry vacuum pump is controlled to extract gas from the container; The data acquisition and transmission module is used to install a pressure acquisition device at the air inlet of the dry vacuum pump to collect parameter data during the gas extraction process in the container; the parameter data includes the volume of the container and the change in gas pressure at the air inlet of the dry vacuum pump; determine the vibration data acquisition point of the dry vacuum pump, and collect the vibration amplitude data at the vibration data acquisition point; send the collected parameter data and vibration amplitude data to the database and the intelligent judgment module; The database is used to store the collected parameter data and vibration amplitude data as historical data and continuously update them; The model management and analysis module is used to establish a vibration analysis model based on the historical data stored in the database, and analyze the influence of different parameter data on the vibration amplitude during the process of the dry vacuum pump extracting gas in the container; The intelligent judgment module is used to analyze the collected real-time parameter data and real-time vibration amplitude data, and judge whether the current dry vacuum pump has a failure risk according to the analysis results of the vibration analysis model in the model management and analysis module; if there is no failure risk, continue to judge; if there is a failure risk, send a signal to the early warning module; The early warning module is used to generate fault alarms and send alarm information to management personnel; The display module is used to provide an interactive platform for digital display.

6. The dry vacuum pump vibration data analysis system based on big data according to claim 5, characterized in that: The model management and analysis module includes a historical data analysis unit and a model training unit; The historical data analysis unit is used to retrieve historical parameter data and historical vibration amplitude data of the dry vacuum pump during normal operation from the database for analysis, determine the volume of the container according to the historical parameter data, and determine the gas pressure at the air inlet of the dry vacuum pump at different time stamps, and calculate the extraction rate of the gas in the container at different time stamps according to the historical parameter data analysis results; According to the historical vibration amplitude data, the vibration amplitude at the vibration data collection point at different time stamps is determined, and according to the historical vibration amplitude data analysis results, the vibration amplitude change amplitude at the vibration data collection point at different time stamps is calculated; The model training unit is used to establish a vibration analysis model, taking the extraction rate of gas in the container and the gas pressure at the air inlet of the dry vacuum pump as influencing factors, and taking the vibration amplitude change amplitude at the vibration data collection point as the influencing value, to analyze the influence of different parameter data on the vibration amplitude during the process of the dry vacuum pump extracting gas in the container.

7. The dry vacuum pump vibration data analysis system based on big data according to claim 6, characterized in that: The intelligent judgment module includes a real-time data analysis unit, a threshold determination unit and a judgment unit; The real-time data analysis unit is used to analyze the collected real-time parameter data, determine the gas pressure at the current air inlet of the dry vacuum pump, and determine the extraction rate of the gas in the current container; Analyze the collected real-time vibration amplitude data, determine the vibration amplitude change amplitude at the current vibration data collection point, and calculate the deviation value of the current dry vacuum pump vibration amplitude; The threshold determination unit is used to retrieve historical parameter data and historical vibration amplitude data when the dry vacuum pump fails from a database for analysis; determine the gas pressure at the air inlet and the extraction rate of the gas in the container when the dry vacuum pump fails based on the historical parameter data; determine the vibration amplitude change amplitude at the vibration data collection point when the dry vacuum pump fails based on the historical vibration amplitude data; determine the deviation values ​​of different vibration amplitudes based on the retrieved historical data analysis results when the dry vacuum pump fails; construct a BP neural network, divide the deviation values ​​of different vibration amplitudes into a training set and a validation set, input the training set into the BP neural network for training, train the network weights and thresholds through a back propagation algorithm, cross-validate the validation set with the trained BP neural network, and determine the maximum deviation threshold of the vibration amplitude when the dry vacuum pump fails; The judgment unit is used to judge whether the current dry vacuum pump has a failure risk based on the deviation value of the vibration amplitude of the current dry vacuum pump and the maximum deviation threshold of the vibration amplitude when the dry vacuum pump fails; when the current dry vacuum pump does not have a failure risk, continue to judge; when the current dry vacuum pump has a failure risk, send a signal to the early warning module.

8. The dry vacuum pump vibration data analysis system based on big data according to claim 7, characterized in that: The interactive platform provided is used to display the gas pressure at the current dry vacuum pump inlet, the extraction rate of the gas in the current container, the vibration amplitude change amplitude at the current vibration data collection point and the deviation value of the current dry vacuum pump vibration amplitude.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; The processor executes the dry vacuum pump vibration data analysis method based on big data as described in any one of claims 1 to 4 by calling the computer program stored in the memory.

10. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer executes a dry vacuum pump vibration data analysis method based on big data as described in any one of claims 1 to 4.

Images