CN-122016034-A - Intelligent inspection-based self-diagnosis management system for faults of chemical production mechanical equipment

CN122016034ACN 122016034 ACN122016034 ACN 122016034ACN-122016034-A

Abstract

The application discloses a self-diagnosis management system for faults of chemical production machinery equipment based on intelligent inspection, which relates to the technical field of diagnosis management of production machinery equipment, a vibration signal self-adaptive acquisition module of the scheme carries out self-adaptive acquisition on vibration signals of the chemical production machinery equipment, vibration spectrum data is obtained based on the vibration signals of the chemical production equipment, whether to implement vibration spectrum data rechecking is judged, a vibration spectrum data transmission analysis module is used for carrying out vibration spectrum data transmission analysis after the self-adaptive acquisition process is finished, the self-adaptive threshold judging module is used for carrying out self-adaptive threshold judgment on the vibration spectrum data after the vibration spectrum data transmission analysis flow is finished, and deciding whether to carry out self-diagnosis management on the faults of the chemical equipment or not based on the obtained judging result, so that the problem that intelligent inspection is difficult to realize accurate identification and advanced early warning on the early faults of the chemical production mechanical equipment is solved.

Inventors

GUO HUAN
SONG YACHAO
YUAN HUAN
ZHANG SHIBO
WANG XIAOYU
LU YUAN

Assignees

河南省豫冠安全发展有限公司

Dates

Publication Date: 20260512
Application Date: 20260227

Claims (10)

1. The intelligent inspection-based self-diagnosis management system for the faults of the chemical production mechanical equipment is characterized by comprising a vibration signal self-adaptation acquisition module, a vibration spectrum data transmission analysis module and a self-adaptation threshold judgment module; the vibration signal self-adaptive acquisition module is used for carrying out self-adaptive acquisition on the vibration signals of the chemical equipment, obtaining corresponding vibration spectrum data based on the vibration signals of the chemical equipment, and judging whether to implement vibration spectrum data rechecking operation according to the vibration spectrum data; the vibration spectrum data transmission analysis module is used for carrying out vibration spectrum data transmission analysis on the transmitted vibration spectrum data after the self-adaptive acquisition process is finished, obtaining a corresponding transmission analysis result, and deciding whether to implement dynamic transmission of the vibration spectrum data or not based on the transmission analysis result; the self-adaptive threshold judging module is used for carrying out self-adaptive threshold judgment on the vibration spectrum data after the vibration spectrum data transmission analysis flow is finished, and judging whether to carry out self-diagnosis management on the faults of the chemical equipment or not based on the obtained judging result.
2. The intelligent inspection-based self-diagnosis management system for faults of chemical production mechanical equipment, as set forth in claim 1, is characterized in that the specific process of performing self-adaptive acquisition on the vibration signals of the chemical equipment is as follows: collecting chemical equipment vibration signals in a preset time period in a self-adaptive collection time period; the ratio of the fourth-order central moment of the vibration signal to the square of the amplitude variance of the vibration signal is expressed as the kurtosis of the vibration signal of the chemical equipment; The fourth-order central moment of the vibration signal is represented by an average value after four times of arithmetic through a difference value between the amplitude of the vibration signal and the average value of the amplitude of the vibration signal at each moment in a preset time period; the ratio of the total amplitude of the modulation side frequency bands in the vibration signals of the chemical equipment to the amplitude of the fundamental wave is expressed as the amplitude ratio of the vibration signals of the chemical equipment; Judging whether the amplitude ratio of the vibration signal of the chemical equipment is smaller than or equal to the amplitude ratio of the vibration signal of the preset chemical equipment while judging whether the kurtosis of the vibration signal of the chemical equipment is within the range of the kurtosis of the vibration signal of the preset chemical equipment; When the kurtosis of the vibration signals of the chemical equipment is in the range of the kurtosis of the vibration signals of the preset chemical equipment, and the amplitude ratio of the vibration signals of the chemical equipment is smaller than or equal to the amplitude ratio of the vibration signals of the preset chemical equipment, marking the corresponding vibration spectrum data as three-level vibration spectrum data, storing the three-level vibration spectrum data into an edge computing node, and uploading the three-level vibration spectrum data to a central server according to the preset three-level frequency; If there are two cases: in the first case, the chemical equipment vibration signal kurtosis is in a preset chemical equipment vibration signal kurtosis range, and the chemical equipment vibration signal amplitude ratio is larger than the preset chemical equipment vibration signal amplitude ratio; In the second case, the chemical equipment vibration signal kurtosis is not in the preset chemical equipment vibration signal kurtosis range, and the chemical equipment vibration signal amplitude ratio is smaller than or equal to the preset chemical equipment vibration signal amplitude ratio; marking the corresponding vibration spectrum data as secondary vibration spectrum data, and implementing vibration spectrum data rechecking operation at the edge computing node; when the chemical equipment vibration signal kurtosis is not in the range of the preset chemical equipment vibration signal kurtosis, the chemical equipment vibration signal amplitude ratio is larger than the preset chemical equipment vibration signal amplitude ratio, the corresponding vibration spectrum data are marked as primary vibration spectrum data, the primary vibration spectrum data are directly transmitted to a central server, and primary early warning prompt is sent to preset personnel to stop the operation of the chemical mechanical equipment.
3. The intelligent inspection-based self-diagnosis management system for faults of chemical production mechanical equipment, as set forth in claim 2, is characterized in that the specific process of the vibration spectrum data rechecking operation is as follows: dividing chemical equipment vibration signals corresponding to the secondary vibration spectrum data into chemical equipment vibration segmentation signals with preset segments, and randomly extracting the chemical equipment vibration segmentation signals; Obtaining chemical equipment vibration signal kurtosis and chemical equipment vibration signal amplitude ratio corresponding to different chemical equipment vibration sectional signals; taking the ratio of the standard deviation of the kurtosis of the obtained chemical equipment vibration signal to the average value of the kurtosis of the chemical equipment vibration signal as the fluctuation value of the vibration kurtosis; sequencing the amplitude ratio of the obtained vibration signals of the chemical equipment according to the magnitude of the numerical value; Taking the ratio of the difference value of the maximum value of the vibration signal amplitude ratio of the chemical equipment to the minimum value of the vibration signal amplitude ratio of the chemical equipment to the average value of the vibration signal amplitude ratio of the chemical equipment as a vibration amplitude ratio stabilizing value; the maximum value of the amplitude ratio of the vibration signals of the chemical equipment is the maximum value of the amplitude ratio of the vibration signals of the chemical equipment obtained in the operation of rechecking the vibration spectrum data; The minimum value of the amplitude ratio of the vibration signals of the chemical equipment is the minimum value of the amplitude ratio of the vibration signals of the chemical equipment obtained in the operation of rechecking the vibration spectrum data; if the following two results occur: The first result is that the vibration amplitude ratio stable value does not exceed the amplitude ratio stable critical value while the vibration kurtosis fluctuation value exceeds the kurtosis fluctuation critical value; The second result is that the vibration kurtosis fluctuation value does not exceed the kurtosis fluctuation critical value while the vibration amplitude ratio stable value exceeds the amplitude ratio stable critical value; The wavelet packet decomposition treatment of the vibration spectrum signal is required to be implemented; If the vibration kurtosis fluctuation value does not exceed the kurtosis fluctuation critical value and the vibration amplitude ratio stability value does not exceed the amplitude ratio stability critical value, directly entering into vibration spectrum data transmission analysis; If the vibration kurtosis fluctuation value exceeds the kurtosis fluctuation critical value and the vibration amplitude ratio stable value exceeds the amplitude ratio stable critical value, marking the corresponding vibration spectrum data as primary vibration spectrum data, directly transmitting the primary vibration spectrum data to a central server, and sending primary early warning prompt to preset personnel to stop the operation of chemical mechanical equipment.
4. The intelligent inspection-based self-diagnosis management system for faults of chemical production mechanical equipment, as set forth in claim 3, is characterized in that the specific process of the vibration spectrum signal wavelet packet decomposition processing is as follows: decomposing the vibration signal of the chemical equipment into vibration frequency bands with preset signal division numbers based on the frequency interval of the vibration signal of the chemical equipment; acquiring the frequency of each vibration frequency band; the proportion of each vibration frequency band frequency to the vibration signal frequency of the chemical equipment is expressed as the vibration signal frequency ratio; judging whether the frequency ratio of the vibration signal is in the reference range of the vibration frequency band or not; If the vibration signal frequency ratio is not in the vibration frequency band reference range, judging the corresponding vibration frequency band as a fault sensitive frequency band; if the vibration signal frequency ratio is in the vibration frequency band reference range, judging the corresponding vibration frequency band as a normal operation frequency band; Counting the number of fault sensitive frequency bands and the number of normal operation frequency bands; if the number of the fault sensitive frequency bands is greater than or equal to the number of the normal operation frequency bands, marking the corresponding chemical equipment vibration signals as fault characteristic signals, and reconstructing the fault characteristic signals; If the number of the fault sensitive frequency bands is smaller than that of the normal operation frequency bands, marking the corresponding vibration signals of the chemical equipment as normal operation characteristic signals, directly marking the corresponding vibration spectrum data as secondary vibration spectrum data, and executing vibration spectrum data transmission analysis.
5. The intelligent patrol-based self-diagnosis and management system for faults of chemical production mechanical equipment as claimed in claim 4, wherein the specific process of reconstructing the fault characteristic signals is as follows: firstly, screening amplitude threshold values of the amplitude values of time domain signals of fault sensitive frequency bands; reserving time domain signals corresponding to the time domain signals with the amplitude greater than or equal to the amplitude threshold value of the fault sensitive frequency band, and eliminating time domain signals corresponding to the time domain signals with the amplitude smaller than the amplitude threshold value of the fault sensitive frequency band; And sequencing and overlapping the time domain signals of the reserved fault sensitive frequency bands according to the frequency of each vibration frequency band from large to small to form time domain signals of the fault sensitive frequency bands, performing fast Fourier transform, converting the time domain signals of the fault sensitive frequency bands into vibration spectrum data, updating the vibration spectrum data into secondary vibration spectrum data, and performing vibration spectrum data transmission analysis.
6. The intelligent patrol-based self-diagnosis and management system for faults of chemical production machinery equipment according to claim 5 is characterized in that the specific process of vibration spectrum data transmission analysis is as follows: Acquiring vibration spectrum data quantity and real-time occupancy rate of network bandwidth; Judging whether the vibration spectrum data amount is smaller than or equal to a preset vibration spectrum data amount; if the vibration spectrum data volume is smaller than or equal to the preset vibration spectrum data volume, further judging whether the real-time occupancy rate of the network bandwidth is smaller than a real-time occupancy threshold value of the network bandwidth; if not, sending a network bandwidth abnormality prompt to a preset person; If yes, transmitting the vibration spectrum data to a central server according to the emergency degree of the vibration spectrum data and the corresponding preset transmission frequency, and executing self-adaptive threshold judgment, specifically: If the vibration spectrum data is primary vibration spectrum data, transmitting the primary vibration spectrum data to a central server in real time according to a preset primary transmission frequency, and immediately triggering the self-adaptive threshold judgment after the transmission is completed; if the vibration spectrum data is the secondary vibration spectrum data, transmitting the secondary vibration spectrum data to a central server at an edge computing node according to a preset secondary transmission frequency; if the vibration spectrum data are three-level vibration spectrum data, uploading the three-level vibration spectrum data from the edge computing node to a central server according to preset three-level transmission frequency; if not, sending a network bandwidth abnormality prompt to a preset person; If the vibration spectrum data amount is greater than the preset vibration spectrum data amount, judging the delay condition of the vibration spectrum data transmission, specifically: The time interval between the starting time of the edge computing node for transmitting the low-level vibration spectrum data and the ending time of the central server for successfully receiving the batch of data is expressed as the transmission time of the vibration data; the low-level vibration spectrum data comprises secondary vibration spectrum data and tertiary vibration spectrum data; The ratio of the vibration data transmission time length to the preset vibration data transmission time length is expressed as a vibration data transmission delay result; comparing the vibration data transmission delay result with a vibration data transmission threshold value to obtain a corresponding comparison result; if the comparison result is that the vibration data transmission delay result is larger than or equal to the vibration data transmission threshold value, the vibration spectrum data is dynamically transmitted, and the self-adaptive threshold value judgment is carried out after the dynamic transmission of the vibration spectrum data is finished; And if the comparison result is that the vibration data transmission delay result is smaller than the vibration data transmission threshold value, performing adaptive threshold value judgment.
7. The intelligent patrol-based self-diagnosis and management system for faults of chemical production machinery equipment according to claim 6 is characterized in that the specific process of dynamic transmission of vibration spectrum data is as follows: dividing the low-level vibration spectrum data volume into a preset number of data fragments, and monitoring the network bandwidth occupation fluctuation rate in real time; the low-level vibration spectrum data amount refers to the total data amount of the secondary vibration spectrum data and the tertiary vibration spectrum data; if the network bandwidth occupation fluctuation rate is larger than the preset network bandwidth occupation fluctuation rate, adjusting the data slicing transmission rate, otherwise, continuously transmitting the data slicing to the central server; the specific process of adjusting the data slicing transmission rate is as follows: Monitoring the data slicing transmission rate in real time; If the data slicing transmission rate is larger than the first transmission rate standard value, reducing the data slicing transmission rate to the first transmission rate standard value, and simultaneously suspending the three-level vibration spectrum data slicing transmission; if the data slicing transmission rate is lower than the first transmission rate standard value, enabling a standby network link to transmit the second-level vibration spectrum data slicing; judging whether the bandwidth occupation fluctuation rate is still larger than the preset network bandwidth occupation fluctuation rate or not again; if yes, sending a bandwidth occupation abnormality prompt to a preset person, otherwise, executing self-adaptive threshold judgment.
8. The intelligent patrol-based self-diagnosis and management system for faults of chemical production machinery equipment according to claim 7 is characterized in that the specific process of judging the self-adaptive threshold value is as follows: the ratio of the frequency band energy corresponding to the fault characteristic to the total energy of the vibration signal is expressed as the frequency band energy duty ratio of the fault characteristic; The ratio of the real-time material viscosity to the common material viscosity is expressed as a viscosity working condition adaptation coefficient; dividing the viscosity working condition adaptation coefficient into a preset number of continuous intervals, and acquiring a working condition adaptation energy duty ratio reference value when the chemical production mechanical equipment operates according to each interval to serve as a working condition adaptation energy duty ratio reference value corresponding to the interval; If the working condition adaptive energy duty ratio reference value is within the preset energy duty ratio threshold value range, sending a self-diagnosis qualification prompt of the chemical production mechanical equipment to preset personnel; and otherwise, developing a self-diagnosis management link of the faults of the chemical equipment.
9. The intelligent patrol-based self-diagnosis and management system for the faults of the chemical production mechanical equipment, as set forth in claim 8, is characterized in that the specific process of the self-diagnosis and management for the faults of the chemical production mechanical equipment is as follows: Acquiring a real-time vibration spectrum based on the vibration spectrum data; counting the number of fault characteristic frequency bands corresponding to the energy ratio of the fault characteristic frequency bands in the reference range of the energy ratio of the fault characteristic frequency bands, and taking the ratio of the number of the fault characteristic frequency bands to the total number of the reference fault characteristic frequency bands as the characteristic frequency similarity; If the characteristic frequency similarity is greater than or equal to the primary fault similarity threshold, triggering a primary early warning prompt immediately until a preset person stops the operation of the chemical mechanical equipment; if the feature frequency similarity is larger than or equal to the secondary fault similarity threshold and smaller than the primary fault similarity threshold, triggering a secondary early warning prompt preset operation and maintenance personnel to push the fault early warning information of the chemical mechanical equipment; If the feature frequency similarity is smaller than the secondary fault similarity threshold, obtaining feature frequency similarity of the preset similarity dividing number; in the process of developing the self-diagnosis management of the faults of the chemical equipment, taking the ratio of the difference value of the randomly extracted characteristic frequency similarity and the characteristic frequency similarity average value to the characteristic frequency similarity average value as the similarity change rate: If the similarity change rate is larger than the similarity change threshold, the fault characteristics of the chemical production mechanical equipment are continuously enhanced, and a first-level early warning prompt is triggered to stop the operation of the chemical mechanical equipment for a preset person; Otherwise, the normal operation of the chemical production mechanical equipment is described, and a self-diagnosis qualification prompt of the chemical production mechanical equipment is sent to preset personnel.
10. The intelligent patrol-based self-diagnosis and management system for faults of chemical production machinery equipment according to claim 7 is characterized in that the specific process of judging the self-adaptive threshold value is as follows: continuously monitoring the running rotating speed of chemical production mechanical equipment through a rotating speed sensor, and taking the average rotating speed in a preset acquisition time period as a real-time rotating speed parameter of the working condition of the current chemical production mechanical equipment; Defining the ratio of the average rotating speed of the chemical production mechanical equipment to the rated rotating speed of the chemical production mechanical equipment as a rotating speed difference coefficient; when the rotation speed difference coefficient is greater than 1, marking the interval corresponding to the rotation speed of the current chemical production mechanical equipment as a high rated rotation speed interval; When the rotation speed difference coefficient is smaller than 1, marking the interval corresponding to the rotation speed of the current chemical production mechanical equipment as a low rated rotation speed interval; When the rotation speed difference coefficient is equal to 1, marking the interval corresponding to the rotation speed of the current chemical production mechanical equipment as an equal rotation speed interval; and (3) counting key index data of the chemical production mechanical equipment in three continuous intervals, wherein the key index data comprise reference thresholds of fault characteristic frequency band energy duty ratio, vibration signal kurtosis and vibration signal amplitude ratio.

Description

Intelligent inspection-based self-diagnosis management system for faults of chemical production mechanical equipment Technical Field The invention relates to the technical field of production mechanical equipment diagnosis management, in particular to a chemical production mechanical equipment fault self-diagnosis management system based on intelligent inspection. Background With the increasing and miniaturization of industrial intelligent surge and chemical industry, the intelligent inspection technology is applied in various industrial fields, and becomes a core path for breaking equipment operation and maintenance problems and building a safe and defensive line, especially, intelligent inspection of machines in chemical production is particularly important, a core carrier in chemical production is various types of chemical production machines, and from a reaction kettle and a compressor which bear high temperature and high pressure for a long time, to a pump valve and a heat exchanger which are responsible for medium conveying, stable operation of the equipment directly determines production continuity, is tightly bound with electrical equipment such as an explosion-proof motor and a control cabinet, and management and control of dangerous materials such as inflammable and explosive solvents and reaction intermediates, and forms a safe closed loop of chemical production together. Under the background, the chemical industry field provides a strict standard for core indexes such as abnormal identification precision, early warning response speed, cross-equipment cooperative capacity and the like of intelligent inspection, so that the faults of chemical production machinery and related links are ensured to be captured in time and accurately diagnosed, and the method is more important in ensuring production safety. However, the traditional chemical production machinery fault diagnosis and inspection management mode relies on manual experience judgment or single parameter monitoring, lacks intelligent research and judgment capability of systematic data fusion analysis and precision, faces the complex requirements of mass equipment collaborative operation and multi-type risk cross superposition on the modern chemical production line, is difficult to adapt to fault characteristics under different working conditions, easily causes problems of fault missed judgment, misjudgment, early warning lag and the like, reduces operation and maintenance efficiency, causes equipment to stop in an unplanned manner, and possibly causes important safety accidents such as leakage, explosion, fire and the like due to untimely fault disposal, so that the precision and timeliness of fault self diagnosis under an intelligent inspection system are improved, and the method becomes a core problem to be solved in the current chemical production industry. In order to realize intelligent inspection of chemical production mechanical equipment (such as a reaction kettle), the chemical production machinery is subjected to global temperature scanning and temperature acquisition by a non-contact thermal infrared imager to acquire temperature distribution data of key parts of the equipment; detecting gas leakage and electric partial discharge conditions in the operation process of the chemical production machinery through an ultrasonic leak detector; monitoring vibration conditions of chemical production machinery equipment by means of a high-frequency piezoelectric acceleration sensor, wherein vibration signals are continuously collected by the high-frequency piezoelectric acceleration sensor and converted into vibration spectrum data by means of fast Fourier transform, wherein the vibration spectrum data are obtained by converting time-varying time domain signals collected by the vibration sensor of the equipment into frequency domain patterns showing how vibration energy is distributed on different frequencies through mathematical transform (such as fast Fourier transform), covering vibration frequencies, vibration amplitude and the like, transmitting the collected vibration spectrum data to a central server or an edge computing node through industrial Ethernet and a wireless network, then triggering primary alarm on data exceeding a threshold value or abnormal change rate by a rule engine, wherein the rule engine is a configurable logic processing core embedded in diagnostic software, and automatically executing judgment logic by a computer through expert experience knowledge and industry standard coding by means of a rule form of 'if-then', for example, if a stirring rod temperature of a reaction kettle is triggered, then accurately recognizing failure characteristics of a rotor, such as failure in a high-temperature reaction kettle is accurately matched with the vibration spectrum data, and the failure characteristics of the reaction kettle are accurately recognized by the fact that the vibration spectrum data are not matched with the hig