Essay: Fault prognosis of rotating machine

Vibration monitoring is the most widely and cost-effective monitoring technique. It is to detect, locate and distinguish faults [1]. Vibration signal didn’t benefit before analysis, because the signal was random and complex. Also different parts of rotating machine are generated various signals components. Analyzing different features extracted from these signal components generated by several of rotating parts has been proven to be an exceptionally effective way for solving the issue of fault detection or fault diagnosis of rotary machines. Usually, the vibration signal based analysis is commonly and potently used to perceive fault prognosis for rotary machine system, because that vibration signal is measured by sensors installed in the appropriate component of the rotary machine carry information about working conditions [2].
Monitoring and vibration analysis techniques are the main features of a successful predictive and proactive maintenance programs. Whether it is applied in structural health monitoring (SHM) or monitoring the case of machines, and these techniques have proved to be effective for the management and maintenance scheduling programs, prevent catastrophic failure, and reduce downtime, reduce maintenance costs and enhance productivity.
1-2 Fault Diagnosis
Machine fault diagnosis (MFD) is the ability to detect fault, isolate failed component, and estimate the influence of potential impacts of the failed component on the machinery health. Due to the costs of executing, only critical machine components, whose failures drastically affect the breakdown, are frequently examined. The faults of any part may not only cause interruption of product operation, but also increase costs, decrease product quality and effect safety of operators. Consequently, fault diagnosis in machine has been the subject of serious studies in the recent years.
1-3 Fault Prognosis
Machine prognosis (MP) is an important component that owns the ability to predict accurately and precisely the future condition and remaining useful life (RUL) of a failing component or subsystem [3]
A reliable predictor is important and useful to industries to forecast the upcoming states of a dynamic system or to predict damage propagation trend in machines. Therefore, the forecasting information can be used to provide an accurate alarm level before a fault reaches a critical levels so as to prevent machinery performance degradation, malfunction or catastrophic failure. It can also be used for scheduling of repairs and predictive and preventive maintenance and predictive fault-tolerant control of engineering assets, also MP is an estimate of the remaining useful life of a monitored parts, While diagnostics alone can support condition based maintenance practices, prognostics facilitates changes to logistics which can greatly reduce cost or increase readiness and availability [4] these two major properties will be discussed with great attention later.
1-4 Online Machine Multi-sensing
The adopted practice of conventional vibration based condition monitoring of rotating machines uses a number of sensors to identify any fault, the effective methods for machine online health prognosis are still needed now due to Equipment subjects to high levels of uncertainty and unpredictability [5], A variety of faults can occur within machine, during normal operation. Several faults, such as unbalanced, broken rotor bars, rotor eccentricity, can result in a complete breakdown of the machine, if the progress of the fault is not detected [6], the fault progress can be detected online during machine operation. Online based fault diagnosis method is beneficial to find out machine faults and make maintenance plan in time.
1-5 Vibration Analysis
Raw vibration data can be accumulated by an instrument such as accelerometer. These data include the state of rotating machine. These data still didn’t service any indication about the state of machine, before any analysis can be done on it. So vibration analysis is used to detect early precursors to machine failure, allowing machinery to be repaired or replaced before an expensive failure occurs. Also vibration analysis can identify improper maintenance or repair practices. These can include improper bearing installation and replacement, inaccurate shaft alignment or imprecise rotor balancing. As almost 80% of common rotating equipment problems are related to misalignment and unbalance, vibration analysis is an important tool that can be used to reduce or eliminate recurring machine problems. Trending vibration levels can also identify improper production practices, such as using equipment beyond their design specifications (higher temperatures, speeds or loads). These trends can also be used to compare similar machines from different manufacturers in order to determine if design benefits or flaws are reflected in increased or decreased performance. Ultimately, vibration analysis can be used as part of an overall program to significantly improve equipment reliability. This can include more precise alignment and balancing, better quality installations and repairs, and continuously lowering the average vibration levels of equipment in the plant [7].
1-6 Predictive or condition-based maintenance
This philosophy consists of scheduling maintenance activities only when a functional failure is detected as detailed in chapter three. Mechanical and operational conditions are periodically monitored, and when unhealthy trends are detected, the troublesome parts in the machine are identified and scheduled for maintenance. The machine would then be shut down at a time when it is most convenient, and the damaged components would be replaced. If left unattended, these failures could result in costly secondary failures. One of the advantages of this approach is that the maintenance events can be scheduled in an orderly fashion. It allows for some lead-time to purchase parts for the necessary repair work and thus reducing the need for a large inventory of spares. Since maintenance work is only performed when needed, there is also a possible increase in production capacity.
1-7 Aim of the Thesis
The goals of this thesis are to develop and construct an actual currently fault prognosis of rotating machine based on vibration signal using intelligent approaches. The system should be able to acquire acceleration data from specified points on a vibrating machine and transmit it to processing unit, waveform data is to be filtered so that monitored variables can be calculated such as peak frequencies. The monitored variables will then be compared against the baseline profile, monitored variables that deviate from the baseline profile would be indictors of undesired operation or machine faults. Users will specify tolerance threshold on the monitored variables and algorithm are used to determine when a fault has occurred. Good monitoring of the deterioration in rotating machinery based on intelligent approaches applied to forecast the rate of machine deterioration. In order to construct online multi sensing intelligent fault prognosis system need the following steps:
1. Collect sufficient historical vibration data from local industrial.
2. Suggest Intelligent approach method to deal these data, The specific approaches are summarized as follows:
‘ To develop a more reliable signal processing technique for machine fault detection. The emphasis is placed on feature extraction and the analysis of non-stationary signatures that are generated, for example, by the faults on the rolling elements and rotating rings of bearings etc.
‘ To develop an enhanced diagnostic (ED) scheme for automatic diagnostic decision making. The suggested ED scheme consists of two modules:
‘ A novel classifier is proposed to effectively integrate the strengths of several signal processing techniques for a more accurate assessment of the health condition of machine.
‘ A new multi-step predictor is developed and integrated into the ED scheme to forecast the future states of the machine health condition, and to further enhance the diagnostic reliability
3. Construct rig to verify the suggested approaches,
A vibration analysis system usually consists of four basic parts:
‘ Signal pickup(s), also called a transducer
‘ A signal analyzer
‘ Analysis software
‘ A computer for data analysis and storage.
These basic parts can be configured to form a continuous online system, a periodic analysis system using portable equipment, or a multiplexed system that samples a series of transducers at predetermined time intervals. Hard-wired and multiplexed systems are more expensive per measurement position. The determination of which configuration would be more practical and suitable depends on the critical nature of the equipment, and also on the importance of continuous or semi continuous measurement data for that particular application.
1-8 Thesis Outline
This thesis is presented in eight chapters and two appendices. Definitions the faults prognosis and diagnosis is introduce as read above in chapter one.
The literature review is presented in chapter two where several works on faults prognosis and diagnosis methods with the intelligent method used for this issue. Also vibration analysis techniques are reviewed.
In chapter three outline and briefly discuss two different types of maintenance strategies associated with our research.
Vibration Signal Analysis and Features Extraction Techniques are study in galore detail in chapter four.
The two intelligent method used for faults prognosis are studied in chapter five.
In Chapter six has been described experiments that have been used to investigate the methods which proposed to detect faults in rotating machines. It’s also in this chapter describe the types of faults.
Chapter seven has been discussing the results obtained and marked the best intelligent method used to detect faults.
Finally, in chapter eight the conclusion and future work recommendations are presented.