Special Issue on Machine Fault Diagnostics and Prognostics

Machine components and systems, such as gears, bearings, pipes, cutting tools and turbines, may experience various types of faults, such as breakage, crack, pitting, wear, corrosion. If not being properly monitored and treated, such faults can propagate and lead to machinery perfor- mance degradation, malfunction, or even severe compo- nent/system failure. It is significant to reliably detect machinery defects, evaluate their severity, predict the fault propagation trends, and schedule optimized maintenance and inspection activities to prevent unexpected failures. Advances in these areas will support ensuring equipment and production reliability, safety, quality and productivity.

Sparse Autoencoder-based Multi-head Deep Neural Networks for Machinery Fault Diagnostics with Detection of Novelties

Supervised fault diagnosis typically assumes that all the types of machinery failures are known.However,in practice unknown types of defect,i.e.,novelties,may occur,whose detection is a challenging task.In this paper,a novel fault diagnostic method is developed for both diagnostics and detection of novelties.To this end,a sparse autoencoder-based multi-head Deep Neural Network(DNN)is presented to jointly learn a shared encoding representation for both unsupervised reconstruction and supervised classification of the monitoring data.The detection of novelties is based on the reconstruction error.Moreover,the computational burden is reduced by directly training the multi-head DNN with rectified linear unit activation function,instead of performing the pre-training and fine-tuning phases required for classical DNNs.The addressed method is applied to a benchmark bearing case study and to experimental data acquired from a delta 3D printer.The results show that its performance is satisfactory both in detection of novelties and fault diagnosis,outperforming other state-of-the-art methods.This research proposes a novel fault diagnostics method which can not only diagnose the known type of defect,but also detect unknown types of defects.

Aircraft Engine Sensor Fault Diagnostics Based on Estimation of Engine's Health Degradation

A duty in development of an on-line fault detection algorithm is to make it associate with estimation of engine s health degradation. For this purpose,an on-line diagnostic algorithm is put forward. Using a tracking filter to estimate the engine s health condition over its lifetime,can be reconstructed an onboard model,which is then made to match a real aircraft gas turbine engine. Finally,a bank of Kalman filters is applied in fault detection and isola-tion (FDI) of sensors for the engine. Through the bank...

The Implementation of Fault Diagnostic Expert System for Personal Computer

In this paper a PC fault diagnostic expert system (PCDGES) is introduced, which can be run under CCDOS and encoded by English Prolog and C. In the system, a method of combining logic with production rules is applied to represent knowledge. The expert system program is separated from knowledge base. Inference computation is mainly carried backward, and the forward is regarded as an auxiliary inference. The knowledge base can be easily updated, deleted and added in operation time. It has a supporting machanism for the acquisition of knowledge and by means of “telling method”, knowledge can be acquisited. The system also has “why” explanation function and an interface with DOS, full screen editor, and hardware dignostic program. For Chinese users, all the prompt information and selection menus are displayed in color Chinese.

DISTRIBUTED OPTICAL FIBER SENSOR FOR LONG-DISTANCE OIL PIPELINE HEALTH

A fully distributed optical fiber sensor （DOFS） for monitoring long-distance oil pipeline health is proposed based on optical time domain reflectometry （OTDR）. A smart and sensitive optical fiber cable is installed along the pipeline acting as a sensor, The experiments show that the cable swells when exposed to oil and induced additional bending losses inside the fiber, and the optical attenuation of the fiber coated by a thin skin with periodical hardness is sensitive to deformation and vibration caused by oil leakage, tampering, or mechanical impact. The region where the additional attenuation occurred is detected and located by DOFS based on OTDR, the types of pipeline accidents are identified according to the characteristics of transmitted optical power received by an optical power meter, Another prototype of DOFS based on a forward traveling frequency-modulated continuous-wave （FMCW） is also proposed to monitor pipeline. The advantages and disadvantages of DOFSs based on OTDR and FMCW are discussed. The experiments show that DOFSs are capable of detecting and locating distant oil pipeline leakages and damages in real time with an estimated precision of ten meters over tens of kilometers.

Evaluate the impact of sensor accuracy on model performance in data-driven building fault detection and diagnostics using Monte Carlo simulation

The performance of data-driven fault detection and diagnostics(FDD)is heavily dependent on sensors.However,sensor inaccuracy and sensor faults are pervasive in building operation:inaccurate and missing sensor readings deteriorate FDD performance;sensor inaccuracy will also affect the selection of sensor for data-driven FDD in the model training process,which is another key factor of data-driven FDD performance.Sensor accuracy and sensor selection individually are well-studied research topics in this field,but the impact of sensor accuracy on sensor selection and its further impact on FDD performance has not been evaluated and quantified.In this paper,we developed a novel analysis methodology that comprehensively evaluates sensor fault on sensor selection and FDD accuracy.Monte Carlo simulation is applied to deal with multiple stochastic sensor inaccuracy and provide probabilistic analysis results of the impact of sensor inaccuracy on sensor selection and FDD accuracy.This methodology focuses on the net impact of fault states across a full sensor set.The developed methodology can be used for the early-stage sensor design and operation-stage sensor maintenance.A case study is conducted to demonstrate the analysis methodology using a commercial building model crated to Flexible Research Platform located at Oak Ridge National Laboratory,USA.

Semi-Supervised Machine Learning for Fault Detection and Diagnosis of a Rooftop Unit

Most heating,ventilation,and air-conditioning(HVAC)systems operate with one or more faults that result in increased energy consumption and that could lead to system failure over time.Today,most building owners are performing reactive maintenance only and may be less concerned or less able to assess the health of the system until catastrophic failure occurs.This is mainly because the building owners do not previously have good tools to detect and diagnose these faults,determine their impact,and act on findings.Commercially available fault detection and diagnostics(FDD)tools have been developed to address this issue and have the potential to reduce equipment downtime,energy costs,maintenance costs,and improve occupant comfort and system reliability.However,many of these tools require an in-depth knowledge of system behavior and thermodynamic principles to interpret the results.In this paper,supervised and semi-supervised machine learning(ML)approaches are applied to datasets collected from an operating system in the field to develop new FDD methods and to help building owners see the value proposition of performing proactive maintenance.The study data was collected from one packaged rooftop unit(RTU)HVAC system running under normal operating conditions at an industrial facility in Connecticut.This paper compares three different approaches for fault classification for a real-time operating RTU using semi-supervised learning,achieving accuracies as high as 95.7%using few-shot learning.