Engineering machinery fault analysis early warning system

Abstract

The embodiment of the invention discloses an engineering machinery fault analysis and early warning system, which belongs to the technical field of mechanical fault early warning, and comprises a hardware monitoring module used for carrying out state monitoring and signal acquisition on data during operation of target equipment; and the software management module is used for establishing a platform architecture, setting up a plurality of functional modules and carrying out fault early warning processing on the collected signals. According to the embodiment of the invention, feature vectors of various signal types can be obtained, and the purpose of intelligently judging the health state of equipment is achieved by taking data acquisition by a sensor system as a basis and empirical knowledge accumulation by machine learning as a way; reliability of operation of mechanical equipment is guaranteed, fault diagnosis of multi-source data fusion is realized, and a diagnosis effect is improved.

Description

Technical Field

[0001] The present application belongs to the technical field of mechanical failure early warning, and specifically, relates to an engineering machinery failure analysis and early warning system. Background Art

[0002] The camshaft is an important component of the engine. It controls the engine's valve timing with the help of the cam. It is specifically used to control the opening and closing time of the engine's intake and exhaust valves. The rotation speed of the camshaft is only half of the engine's crankshaft. It will continuously accelerate and decelerate during operation. Its idling speed is only a few hundred revolutions per minute, and when it accelerates or runs under heavy load, its speed can reach more than 2,000 revolutions per minute. Such a high rotation speed requires the engine camshaft to have good toughness, and the camshaft must not have more serious and more metallurgical defects, such as loose structure, internal inclusions and cracks.

[0003] However, the structural characteristics and working principles of the engine determine that the camshaft vibration signal has vibration characteristics different from those of general rotating machinery. The periodic vibration is closely related to the principle of alternating operation of its multiple cylinders. During the operation, the unstable fluctuations between each working cycle ultimately cause the camshaft vibration to exhibit cyclic fluctuation characteristics. Under the same working environment and working load conditions, the vibration signal is affected by the complex effects of various working conditions such as unstable injection volume, fluctuations in injection pressure, and unstable engine speed, resulting in different cyclic fluctuations in time, frequency, and vibration intensity, making it impossible to generate an accurate digital fault diagnosis report. Summary of the invention

[0004] In order to solve the above problems and technical defects, the embodiment of the present application adopts the following technical solution, a construction machinery fault analysis and early warning system, comprising:

[0005] Hardware monitoring module, used for status monitoring and signal collection of data during the operation of the target device;

[0006] The software management module is used to establish the platform architecture, set up multiple functional modules, and perform fault warning processing on the collected signals.

[0007] Preferably, the hardware monitoring module includes a perception layer and a collection layer. The perception layer adopts a sensor integrated module, and the collection layer adopts a high-precision collector. The sensor integrated module is installed on the target device to perform signal monitoring. The high-precision collector collects, processes and forwards the monitored signals.

[0008] Preferably, the platform architecture of the software management module adopts a microservice architecture for distributed cluster deployment, and module-based development ensures the independence of each module service. When problems occur in the architecture nodes or the platform performance reaches a bottleneck, the platform performance is improved through cluster deployment, and the data is managed in an integrated and unified manner.

[0009] Furthermore, the functional modules within the software management module include an online monitoring module, an AI fault diagnosis module, a defect management module, a maintenance management module, a lubrication management module, a spot inspection management module, an online management module, an intelligent diagnosis module, a work ticket management module and an inventory management module.

[0010] Furthermore, the software management module realizes integrated deployment management through cross-platform deployment and containerized deployment, adopts microservice technology for platform construction, plans and designs the overall technical architecture based on the microservice architecture, supports multi-tenant mode, and strictly isolates the data between tenants. Each tenant uses an independent database, and the dynamic data source class provided by spring realizes dynamic addition of databases and data source switching.

[0011] Preferably, the software management module can diagnose a single piece of vibration monitoring data, and can also perform comprehensive diagnosis using data over a period of time, and then intelligently determine the engine operating status, and provide maintenance advice and maintenance plans. The software management module has complete abnormal data tracking and processing capabilities. Abnormal data can automatically generate message reminders, push abnormal data in the form of messages, and directly convert alarm equipment into abnormal processing work orders, which can be queried through special software and message centers.

[0012] Furthermore, the software management module has an automatic diagnosis function. The camshaft fault diagnosis method based on the mechanism model takes the vibration data spectrum analysis as the core, combines the equipment mechanical parameters and process operation parameters, automatically identifies the fault frequency, timely discovers the fault type and locates the fault range, and realizes automatic diagnosis of typical equipment faults by configuring the equipment component parameters or creating the mechanism model of the equipment;

[0013] By obtaining equipment component parameters and process operation parameters, calculating component failure frequencies, and establishing a mechanism model for the target equipment, users can view equipment monitoring type distribution, diagnostic model distribution, and component distribution.

[0014] Furthermore, a bearing database is established in the software management module, which can perform fuzzy search according to the bearing model or name, view the key parameters of the bearing, and provide a bearing characteristic frequency calculation tool to automatically calculate the bearing characteristic frequency according to the bearing model.

[0015] Furthermore, the software management module can automatically generate a digital fault diagnosis report, completely recording all fault information without manual reporting, including: key monitoring values, waveforms, spectrum diagrams and digital diagnosis reports;

[0016] By integrating industry standards and customized warnings based on expert experience, multiple warning categories are set. By establishing a fault characteristic frequency library, software integration, filtering, and envelope analysis are performed on the vibration data. The carrier frequency is removed, the sidebands are retained, and the energy of the sideband attachments is extracted to determine whether to issue an alarm.

[0017] Furthermore, the software management module displays the characteristics of non-stationary operating conditions and identifies faults by performing non-stationary analysis on the vibration signal under variable speed conditions, using time-frequency domain characteristics to perform wavelet transform spectrum and Hilbert-Huang transform spectrum, displaying the signal frequency distribution, performing multi-layer wavelet packet decomposition on the signal to obtain independent frequency bands, solving and normalizing the signal energy of each frequency band, constructing energy characteristics, and finally extracting signal fault characteristics.

[0018] Compared with the prior art, the beneficial effects of the embodiments of the present application are:

[0019] (1) The present application adopts the wavelet packet analysis method to decompose the signal in the entire frequency band, which can effectively reflect the time-frequency characteristics of the signal and extract the characteristics of the fault. The collected signal is divided into multiple parts according to the frequency range for each type, and each part of the signal is decomposed by multi-layer wavelet packets. The decomposed signal is reconstructed to obtain the characteristic vectors of various signal types;

[0020] (2) This application applies artificial intelligence algorithms such as classification and clustering to camshaft fault diagnosis, conducts knowledge mining on equipment fault information, obtains diagnostic rules related to faults, and then identifies equipment fault states in order to formulate maintenance strategies. The science of using big data to identify the health status of mechanical equipment is based on data acquisition by sensor systems, using machine learning to accumulate experience and knowledge, and intelligently identifying the health status of equipment to ensure the reliability of mechanical equipment operation;

[0021] (3) The fault model library of this application contains a variety of data types. The system can define different weights for different data types in the fault database based on the customer's prior knowledge, thereby realizing fault diagnosis by fusion of multi-source data and improving the diagnosis effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In the attached picture:

[0023] Figure 1 A schematic diagram of the system structure of an embodiment of the present application;

[0024] Figure 2 A schematic diagram of the platform architecture of an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions 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 part of the embodiments of the present application, not all of the embodiments. Generally, the components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0026] Example 1

[0027] like Figure 1 and Figure 2 As shown, a construction machinery fault analysis and early warning system comprises:

[0028] Hardware monitoring module, used for status monitoring and signal collection of data during the operation of the target device;

[0029] The software management module is used to establish the platform architecture, set up multiple functional modules, and perform fault warning processing on the collected signals.

[0030] The hardware monitoring module includes a perception layer and a collection layer. The perception layer adopts a sensor integrated module, and the collection layer adopts a high-precision collector. The sensor integrated module is installed on the target device for signal monitoring. The high-precision collector collects, processes and forwards the monitored signals.

[0031] The platform architecture of the software management module adopts a microservice architecture for distributed cluster deployment. Module-based development ensures the independence of each module's services. When problems occur in architecture nodes or platform performance reaches a bottleneck, cluster deployment is used to improve platform performance and integrate and unify data management.

[0032] The functional modules within the software management module include online monitoring module, AI fault diagnosis module, defect management module, maintenance management module, lubrication management module, inspection management module, online management module, intelligent diagnosis module, work ticket management module and inventory management module.

[0033] The software management module achieves integrated deployment management through cross-platform deployment and containerized deployment, adopts microservice technology for platform construction, and plans and designs the overall technical architecture based on the microservice architecture. It supports multi-tenant mode, strictly isolates the data between tenants, and uses an independent database for each tenant. The dynamic data source class provided by spring is used to dynamically add databases and switch data sources.

[0034] The software management module integrates industry standards and customized warnings based on expert experience to set up multiple warning categories. It establishes a fault characteristic frequency library to perform software integration, filtering, and envelope analysis on the vibration data, remove the carrier frequency, retain the sidebands, and extract the energy of the sideband attachments to determine whether to issue an alarm.

[0035] The software management module can diagnose a single piece of vibration monitoring data, and can also perform comprehensive diagnosis using data over a period of time, and then intelligently determine the engine operating status and provide maintenance advice and maintenance plans.

[0036] The software management module has complete abnormal data tracking and processing capabilities. Abnormal data can automatically generate message reminders and push abnormal data in the form of messages. It can also directly convert alarm devices into abnormal processing work orders and query them through special software and message center.

[0037] The software management module has an automatic diagnosis function. The camshaft fault diagnosis method based on the mechanism model takes vibration data spectrum analysis as the core, combines the equipment mechanical parameters and process operation parameters, automatically identifies the fault frequency, promptly finds the fault type and locates the fault range, and realizes automatic diagnosis of typical equipment faults by configuring the equipment component parameters or creating the mechanism model of the equipment.

[0038] By obtaining equipment component parameters and process operation parameters, calculating component failure frequencies, and establishing a mechanism model for the target equipment, users can view equipment monitoring type distribution, diagnostic model distribution, and component distribution.

[0039] A common bearing database is established in the software management module, which can perform fuzzy search based on bearing model or name, view key parameters of bearings, and provide a bearing characteristic frequency calculation tool to automatically calculate the bearing characteristic frequency based on the bearing model.

[0040] The software management module can automatically generate digital fault diagnosis reports, completely recording all fault information without manual reporting, including: key monitoring values, waveform diagrams, spectrum diagrams and digital diagnosis reports.

[0041] The software management module displays the characteristics of non-stationary working conditions and identifies faults by performing non-stationary analysis on the vibration signal under variable speed conditions, using the time-frequency domain characteristics to perform wavelet transform spectrum and Hilbert-Huang transform spectrum, displaying the signal frequency distribution, performing multi-layer wavelet packet decomposition on the signal to obtain independent frequency bands, solving and normalizing the signal energy of each frequency band, constructing energy characteristics, and finally extracting the signal fault characteristics.

[0042] The above-mentioned embodiments only express the preferred implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for ordinary technicians in this field, several modifications, improvements and substitutions can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application.

Claims

1. A construction machinery fault analysis and early warning system, characterized in that: include: Hardware monitoring module, used for status monitoring and signal collection of data during the operation of the target device; The software management module is used to establish the platform architecture, set up multiple functional modules, and perform fault warning processing on the collected signals.

2. The engineering machinery fault analysis and early warning system according to claim 1 is characterized in that: The hardware monitoring module includes a perception layer and a collection layer. The perception layer adopts a sensor integrated module, and the collection layer adopts a high-precision collector. The sensor integrated module is installed on the target device to perform signal monitoring. The high-precision collector collects, processes and forwards the monitored signals.

3. The engineering machinery fault analysis and early warning system according to claim 1 is characterized in that: The platform architecture of the software management module adopts a microservice architecture for distributed cluster deployment, and module-based development ensures the independence of each module service. When problems occur in the architecture nodes or the platform performance reaches a bottleneck, the platform performance is improved through cluster deployment, and the data is managed in a unified and integrated manner.

4. The engineering machinery fault analysis and early warning system according to claim 3 is characterized in that: The functional modules within the software management module include an online monitoring module, an AI fault diagnosis module, a defect management module, a maintenance management module, a lubrication management module, a spot inspection management module, an online management module, an intelligent diagnosis module, a work ticket management module and an inventory management module.

5. The engineering machinery fault analysis and early warning system according to claim 4 is characterized in that: The software management module realizes integrated deployment management through cross-platform deployment and containerized deployment, adopts microservice technology for platform construction, plans and designs the overall technical architecture based on the microservice architecture, supports multi-tenant mode, strictly isolates the data between tenants, and uses an independent database for each tenant. The dynamic data source class provided by spring is used to dynamically add databases and switch data sources.

6. The engineering machinery fault analysis and early warning system according to claim 1 is characterized in that: The software management module can diagnose a single piece of vibration monitoring data, and can also perform comprehensive diagnosis using data over a period of time, and then intelligently judge the engine operating status and provide maintenance advice and maintenance plans. The software management module has complete abnormal data tracking and processing capabilities. Abnormal data can automatically generate message reminders and push abnormal data in the form of messages. It can also directly convert alarm equipment into abnormal processing work orders, which can be queried through special software and message center.

7. The engineering machinery fault analysis and early warning system according to claim 6 is characterized in that: The software management module has an automatic diagnosis function. The camshaft fault diagnosis method based on the mechanism model takes the vibration data spectrum analysis as the core, combines the equipment mechanical parameters and process operation parameters, automatically identifies the fault frequency, promptly finds the fault type and locates the fault range, and realizes automatic diagnosis of typical equipment faults by configuring the equipment component parameters or creating the mechanism model of the equipment. By obtaining equipment component parameters and process operation parameters, calculating component failure frequencies, and establishing a mechanism model for the target equipment, users can view equipment monitoring type distribution, diagnostic model distribution, and component distribution.

8. The engineering machinery fault analysis and early warning system according to claim 7 is characterized in that: The software management module establishes a bearing database, which can perform fuzzy search according to the bearing model or name, view the key parameters of the bearing, and provide a bearing characteristic frequency calculation tool to automatically calculate the bearing characteristic frequency according to the bearing model.

9. The engineering machinery fault analysis and early warning system according to claim 8, characterized in that: The software management module can automatically generate a digital fault diagnosis report, completely recording all fault information without manual reporting, including: key monitoring values, waveforms, spectrum diagrams and digital diagnosis reports; By integrating industry standards and customized warnings based on expert experience, multiple warning categories are set. By establishing a fault characteristic frequency library, software integration, filtering, and envelope analysis are performed on the vibration data. The carrier frequency is removed, the sidebands are retained, and the energy of the sideband attachments is extracted to determine whether to issue an alarm.

10. The engineering machinery fault analysis and early warning system according to claim 9, characterized in that: The software management module displays the characteristics of non-stationary working conditions and identifies faults by performing non-stationary analysis on the vibration signal under variable speed conditions, using time-frequency domain characteristics to perform wavelet transform spectrum and Hilbert-Huang transform spectrum, displaying the signal frequency distribution, performing multi-layer wavelet packet decomposition on the signal to obtain independent frequency bands, solving and normalizing the signal energy of each frequency band, constructing energy characteristics, and finally extracting signal fault characteristics.

Images