scholarly journals International Journal of Prognostics and Health Management, ISSN 2153-2648, 2017 019 1 A Condition Based Maintenance Implementation for an Automated People Mover Gearbox

2020 ◽  
Vol 8 (3) ◽  
Author(s):  
Ali Ashasi-Sorkhabi ◽  
Stanley Fong ◽  
Guru Prakash ◽  
Sriram Narasimhan
Keyword(s):  
Fault Detection ◽  
Real Time ◽  
Health Management ◽  
Industrial Applications ◽  
Remaining Useful Life ◽  
Condition Based Maintenance ◽  
Vibration Data ◽  
Condition Indicators ◽  
Failure Data ◽  
Wide Range

Data-driven condition-based maintenance (CBM) can be an effective predictive maintenance strategy for components within complex systems with unknown dynamics, nonstationary vibration signatures or a lack of historical failure data. CBM strategies allow operators to maintain components based on their condition in lieu of traditional alternatives such as preventive or corrective strategies. In this paper, the authors present an outline of the CBM program and a field pilot study being conducted on the gearbox, a critical component in an automated cable-driven people mover (APM) system at Toronto’s Pearson airport. This CBM program utilizes a paired server-client “two-tier” configuration for fault detection and prognosis. At the first level, fault detection is performed in real-time using vibration data collected from accelerometers mounted on the APM gearbox. Time-domain condition indicators are extracted from the signals to establish the baseline condition of the system to detect faults in real-time. All tier one tasks are handled autonomously using a controller located on-site. In the second level pertaining to prognostics, these condition indicators are utilized for degradation modeling and subsequent remaining useful life (RUL) estimation using random coefficient and stochastic degradation models. Parameter estimation is undertaken using a hierarchical Bayesian approach. Degradation parameters and the RUL model are updated in a feedback loop using the collected degradation data. While the case study presented will primarily focus on a cable-driven APM gearbox, the underlying theory and the tools developed to undertake diagnostics and prognostics tasks are broadly applicable to a wide range of other civil and industrial applications.

scholarly journals Development of a Novel Methodology for Remaining Useful Life Prediction of Industrial Slurry Pumps in the Absence of Run to Failure Data

Sensors ◽  
2021 ◽  
Vol 21 (24) ◽  
pp. 8420
Author(s):  
Muhammad Mohsin Khan ◽  
Peter W. Tse ◽  
Amy J.C. Trappey
Keyword(s):  
Life Prediction ◽  
Prediction Models ◽  
Remaining Useful Life ◽  
Condition Based Maintenance ◽  
Vibration Signals ◽  
The Core ◽  
Failure Data ◽  
Periodic Maintenance ◽  
Useful Life ◽  
Nonlinear Autoregressive

Smart remaining useful life (RUL) prognosis methods for condition-based maintenance (CBM) of engineering equipment are getting high popularity nowadays. Current RUL prediction models in the literature are developed with an ideal database, i.e., a combination of a huge “run to failure” and “run to prior failure” data. However, in real-world, run to failure data for rotary machines is difficult to exist since periodic maintenance is continuously practiced to the running machines in industry, to save any production downtime. In such a situation, the maintenance staff only have run to prior failure data of an in operation machine for implementing CBM. In this study, a unique strategy for the RUL prediction of two identical and in-process slurry pumps, having only real-time run to prior failure data, is proposed. The obtained vibration signals from slurry pumps were utilized for generating degradation trends while a hybrid nonlinear autoregressive (NAR)-LSTM-BiLSTM model was developed for RUL prediction. The core of the developed strategy was the usage of the NAR prediction results as the “path to be followed” for the designed LSTM-BiLSTM model. The proposed methodology was also applied on publically available NASA’s C-MAPSS dataset for validating its applicability, and in return, satisfactory results were achieved.

scholarly journals Deep Learning with Dynamically Weighted Loss Function for Sensor-Based Prognostics and Health Management

Sensors ◽  
2020 ◽  
Vol 20 (3) ◽  
pp. 723 ◽  
Author(s):  
Divish Rengasamy ◽  
Mina Jafari ◽  
Benjamin Rothwell ◽  
Xin Chen ◽  
Grazziela P. Figueredo
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Loss Function ◽  
Short Term Memory ◽  
Health Management ◽  
Remaining Useful Life ◽  
Loss Functions ◽  
Pressure System ◽  
Failure Data ◽  
Prognostic And Health Management

Deep learning has been employed to prognostic and health management of automotive and aerospace with promising results. Literature in this area has revealed that most contributions regarding deep learning is largely focused on the model’s architecture. However, contributions regarding improvement of different aspects in deep learning, such as custom loss function for prognostic and health management are scarce. There is therefore an opportunity to improve upon the effectiveness of deep learning for the system’s prognostics and diagnostics without modifying the models’ architecture. To address this gap, the use of two different dynamically weighted loss functions, a newly proposed weighting mechanism and a focal loss function for prognostics and diagnostics task are investigated. A dynamically weighted loss function is expected to modify the learning process by augmenting the loss function with a weight value corresponding to the learning error of each data instance. The objective is to force deep learning models to focus on those instances where larger learning errors occur in order to improve their performance. The two loss functions used are evaluated using four popular deep learning architectures, namely, deep feedforward neural network, one-dimensional convolutional neural network, bidirectional gated recurrent unit and bidirectional long short-term memory on the commercial modular aero-propulsion system simulation data from NASA and air pressure system failure data for Scania trucks. Experimental results show that dynamically-weighted loss functions helps us achieve significant improvement for remaining useful life prediction and fault detection rate over non-weighted loss function predictions.

Fault detection of gearboxes using synchro-squeezing transform

2016 ◽  
Vol 23 (19) ◽  
pp. 3108-3127 ◽  
Author(s):  
B Hazra ◽  
A Sadhu ◽  
S Narasimhan
Keyword(s):  
Fault Detection ◽  
Mathematical Structure ◽  
Intrinsic Mode Functions ◽  
Robust Detection ◽  
Time Frequency ◽  
Vibration Data ◽  
Condition Indicators ◽  
Mode Decomposition ◽  
Gearbox Vibration ◽  
The Individual

This paper presents a novel fault detection method for gearbox vibration signatures using the synchro-squeezing transform (SST). Premised upon the concept of time-frequency (TF) reassignment, the SST provides a sharp representation of signals in the TF plane compared to many popular TF methods. Additionally, it can also extract the individual components, called intrinsic mode functions or IMFs, of a nonstationary multi-component signal, akin to empirical mode decomposition. The rich mathematical structure based on the continuous wavelet transform makes synchro-squeezing a promising candidate for gearbox diagnosis, as such signals are frequently constituted out of multiple amplitude and frequency modulated signals embedded in noise. This work utilizes the decomposing power of the SST to extract the IMFs from gearbox signals, followed by the application of both condition indicators and fault detection to gearbox vibration data. For robust detection of faults in gear-motors, a fault detection technique based on time-varying auto-regressive coefficients of IMFs as features is utilized. The sequential Karhunen–Loeve transform is employed on the condition indicators to select the appropriate window sizes on which the SST can be applied. This approach promises improved fault detection capability compared to applying condition indicators directly to the raw data. Laboratory experimental data obtained from a drivetrain diagnostics simulator and seeded fault tests from a helicopter gearbox provide test beds to demonstrate the robustness of the proposed algorithm.

Data Driven Prognostics for Rotating Machinery

2013 ◽  
pp. 120-133 ◽  
Author(s):  
Eric Bechhoefer
Keyword(s):  
Detection Threshold ◽  
Remaining Useful Life ◽  
Condition Based Maintenance ◽  
Data Driven ◽  
Health Indicator ◽  
Damage State ◽  
Condition Indicators ◽  
Gear Fault ◽  
Useful Life ◽  
Threshold Setting

A prognostic is an estimate of the remaining useful life of a monitored part. While diagnostics alone can support condition based maintenance practices, prognostics facilitates changes to logistics which can greatly reduce cost or increase readiness and availability. A successful prognostic requires four processes: 1) feature extraction of measured data to estimate damage; 2) a threshold for the feature, which, when exceeded, indicates that it is appropriate to perform maintenance; 3) given a future load profile, a model that can estimate the remaining useful life of the component based on the current damage state; and 4) an estimate of the confidence in the prognostic. This chapter outlines a process for data-driven prognostics by: describing appropriate condition indicators (CIs) for gear fault detection; threshold setting for those CIs through fusion into a component health indicator (HI); using a state space process to estimate the remaining useful life given the current component health; and a state estimate to quantify the confidence in the estimate of the remaining useful life.

Using Prognostics and Health Monitoring Data in Load Distribution Optimization Problems

2020 ◽  
Author(s):  
Leonardo R. Rodrigues ◽  
Vandilberto Pereira Pinto
Keyword(s):  
Load Distribution ◽  
Optimization Problems ◽  
Health Management ◽  
Short Interval ◽  
Decision Support Tool ◽  
Industrial Applications ◽  
Remaining Useful Life ◽  
Support Tool ◽  
Multidimensional Knapsack ◽  
Proposed Model

The use of Remaining Useful Life (RUL) predictions as a decision support tool has increased in recent years. The RUL predictions can be obtained from Prognostics and Health Management (PHM) systems that monitor the health status and estimate the failure instant of components and systems. An example of a decision-making problem that can benet from RUL predictions is the load distribution problem, which is a common problem that appears in many industrial applications. It consists in dening how to distribute a task among a set of components. In this paper, a model to solve load distribution optimization problems is proposed. The proposed model considers the RUL prediction of each component in its formulation. Also, the proposed model assumes that the predicted RUL of each component is a function of the load assigned to that component. Thus, it is possible to distribute the load to avoid multiplecomponents to fail in a short interval. An approach based on the MMKP (Multiple-choice Multidimensional Knapsack Problem) is adopted. The proposed model nds a load distribution that minimizes the operational cost subject to a maintenance personnel capacity constraint, i.e. there is a maximum number of components that can be simultaneously on repair. A numerical case study considering a gas compressor station is presented to illustrate the application of theproposed model.

Prognostics and Health Monitoring of Electro-Hydraulic Systems

2017 ◽  
Author(s):  
Damoon Soudbakhsh ◽  
Anuradha M. Annaswamy
Keyword(s):  
Fault Detection ◽  
Health Monitoring ◽  
Industrial Applications ◽  
Remaining Useful Life ◽  
Maintenance Cost ◽  
Hydraulic Systems ◽  
Multiple Sources ◽  
Redundant Actuators ◽  
Component Failures ◽  
Prognostics And Health Monitoring

Electro-Hydraulic Systems (EHS) are commonly used in many industrial applications. Prediction and timely fault detection of EHS can significantly reduce their maintenance cost, and eliminate the need for redundant actuators. Current practice to detect faults in the actuators can miss failures with combination of multiple sources. Missed faults can result in sudden, unforeseen failures. We propose a fault detection technique based on Multiple Regressor Adaptive Observers (MRAO). The results were evaluated using a two-stage servo-valve model. The proposed MRAO can be used for on-line fault detection. Therefore, we propose a health monitoring approach based on the trend of the identified parameters of the system. Using the history of identified parameters, normal tear and wear of the actuator can be distinguished from the component failures to more accurately estimate the remaining useful life of the actuator.

Physics-based integrated vehicle health management system for predicting the remaining useful life of an aircraft planetary gear transmission

2017 ◽  
Vol 8 (4) ◽  
pp. 484-495 ◽  
Author(s):  
Adrian Cubillo ◽  
Jeroen Vermeulen ◽  
Marcos Rodriguez de la Peña ◽  
Ignacio Collantes Casanova ◽  
Suresh Perinpanayagam
Keyword(s):  
Real Time ◽  
Management System ◽  
Health Management ◽  
Remaining Useful Life ◽  
Metal Contact ◽  
Content Type ◽  
Metal Metal ◽  
Useful Life ◽  
Aircraft System ◽  
Planetary Transmission

Purpose Integrated vehicle health management has been developed for several years in different industries, to be able to provide the required inputs to determine the optimal maintenance operations depending on the actual health status of the system. The purpose of this paper is to demonstrate the potential of a physics-based model (PbM) for prognostics with a real case study, based on the detection of incipient faults and estimate the remaining useful life of a planetary transmission of an aircraft system. Design/methodology/approach Most of the research in the area of health assessment algorithms has been focused on data-driven approaches that are not based on the knowledge of the physics of the system, while PbM approaches rely on the understanding of the system and the degradation mechanisms. A physics-based modelling approach to represent metal-metal contact and fatigue in the gears of the planetary transmission of an aircraft system is applied. Findings Both the failure mode caused by metal-metal contact as caused by fatigue in the gears is described. Furthermore, the real-time application that retrieves the results from the simulations to assess the health of the system is described. Finally the decision making that can be executed during flight in the aircraft is incorporated. Originality/value The paper proposes an innovative prognostics health management system that assesses two important failure modes of the planetary transmission that regulates the speed of the generators of an aircraft. The results from the models have been integrated in an application that emulates a real system in the aircraft and computes the remaining useful life in real time.

scholarly journals A User Programmable General Purpose Microprocessor Control System

1980 ◽  
Author(s):  
D. E. Mann
Keyword(s):  
Real Time ◽  
Gas Turbine ◽  
Diesel Engines ◽  
Industrial Applications ◽  
General Purpose ◽  
Real Time System ◽  
Authority Control ◽  
Wide Range ◽  
Structure And Design ◽  
Hardware Structure

This paper describes the hardware structure and design of a general-purpose microprocessor based controller intended for the full authority control of gas turbine and diesel engines in ground based vehicle and industrial applications. Particular attention is paid to the digital processor and how it’s design was influenced by the user requirements of a general purpose, real-time system. The system is currently being manufactured in production form. An accompanying paper describes the supporting software and user program facilities (Ref 1). Such systems based on the use of microprocessors must not only provide general purpose hardware, but also software structured so that a wide range of control algorithms may be programmed and performed within strict limits of real-time. This paper describes the development of the Type C4E87 General Purpose Controller (REF Fig. 1) with particular reference to its hardware structure and design within a system intended primarily for application as a full authority control of gas turbine and diesel engines etc.

Fault Detection and Diagnostics in an Ocean Turbine Using Vibration Analysis

2010 ◽  
Author(s):  
Mustapha Mjit ◽  
Pierre-Philippe J. Beaujean ◽  
David J. Vendittis
Keyword(s):  
Fault Detection ◽  
Diagnostic Techniques ◽  
Fault Detection And Diagnosis ◽  
Vibration Data ◽  
Wide Range ◽  
Detection And Diagnosis ◽  
Early Fault Detection ◽  
Monitoring And Diagnostics ◽  
Machine Speed ◽  
Diagnostics System

This paper describes the approach, procedure and techniques developed to evaluate the health of ocean turbines, based on vibration measurements and analyses. A LabVIEW model for on-line vibration condition monitoring, implemented with advanced diagnostic techniques features, was developed. In order to distinguish between a vibration amplitude change due to a developing fault and that due to a change in operating condition, this program includes the use of an ordering technique in the frequency domain, which relates the vibration to the machine speed. Some experiments were first performed on a commercial fan to illustrate and demonstrate the fault detection capability of the monitoring and diagnostics system. To increase the reliability of the monitoring system, and to demonstrate that it can be used for monitoring a wide range of machines, a second series of vibration data collection and monitoring events was performed on a small boat with different combination (on/off status) of the engine, hydraulic pump, generator and air conditioning. This allowed for the detection of the frequency components associated with each subsystem, alone and together, and enabled the detection of mechanical faults, such as imbalance and misalignment, if they existed. For long term monitoring, the model allow for the automatic storing of raw data either periodically and/or after any deviations from normal conditions, i.e., when alerts are on. This makes it possible to follow the progress (towards an alarm condition) of any faults without saving data continuously. In this way, measurements of unexpected events may be made without the vibration engineer’s physical presence, hopefully, early fault detection and diagnosis will avoid catastrophic failure from occurring. This enables the economic and efficient health monitoring of ocean turbines as they become operational.

Sign in / Sign up

Export Citation Format

Share Document