Sheraz Ali Khan

Dr. Sheraz Ali Khan

orcid

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 April 2019 in Reliability Engineering & System Safety
Verified
Journal Article
Closed access
WAWasim Ahmad
Wasim Ahmad
SKSheraz Ali Khan
Sheraz Ali Khan
M M Manjurul IslamM M Manjurul Islam
M M Manjurul Islam
Jong-Myon KimJong-Myon Kim
Jong-Myon Kim

28 July 2017 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
WAWasim Ahmad
Wasim Ahmad
SKSheraz Ali Khan
Sheraz Ali Khan
Jong-Myon KimJong-Myon Kim
Jong-Myon Kim
Rolling element bearings cause the largest number of failures in induction motors. Predicting an impending failure and estimating the remaining useful life (RUL) of a bearing is essential for scheduling maintenance and avoiding abrupt shutdowns of critical systems. This paper presents a hybrid technique for bearing prognostics that utilizes regression-based adaptive predictive models to learn the evolving trend in a bearing's health indicator. These models are then used to project forward in time and estimate the RUL of a bearing. The proposed algorithm addresses some key issues in existing methods for bearing health prognosis that affect their prognostic performance, specifically determining the time to start prediction (TSP), handling random fluctuations in a bearing's health indicator, and setting a dynamic failure threshold. The proposed algorithm is validated on publicly available bearing prognostics data from the Center for Intelligent Maintenance Systems. Experimental results show that the proposed approach is effective in determining an accurate TSP and failure threshold, as well as handling random fluctuations. Moreover, this approach achieves excellent prognostic performance and estimates the RUL of bearings within the specified error bounds, even at points very close to the TSP, where traditional methods yield relatively poor RUL estimates.

9 September 2020 in IEEE Access
Verified
Journal Article
Open access
ANAbdullah Nawaz
Abdullah Nawaz
Ghulam HafeezGhulam Hafeez
Ghulam Hafeez
IKImran Khan
Imran Khan
KJKhadim Ullah Jan
Khadim Ullah Jan
HLHui Li
Hui Li
ZWZahid Wadud
Zahid Wadud
The development of advanced metering infrastructure (AMI) in smart grid (SG) had enabled consumers to participate in demand-side management (DSM) using the price-based demand response (DR) programs offered by the distribution companies (DISCO). This way, not only the consumers minimize their electricity bills and discomfort, but also the DISCOs can handle peak power demand and reduce the carbon (CO2) emissions in a controlled manner. Building an optimization framework that will minimize cost, peak demand, waiting time, and CO2 emission is not only a challenging task but also a concern of DSM. Most analyses are based on cost and peak-to-average ratio (PAR) minimization, but the effectiveness of the DSM framework is equally determined by user comfort and CO2 emission. Considering only one objective (cost) or two objectives (cost and PAR) is not sufficient. Thus, for DSM framework to achieve these four relatively independent objectives at the same time, minimized cost, PAR, CO2 emission, and user discomfort, an energy management controller (EMC) based on our proposed algorithm hybrid bacterial foraging and particle swarm optimization (HBFPSO) is employed that return optimal power usage schedule for consumers. A novel DSM framework consists of four units: (i) DISCO, (ii) multi-layer perceptron (MLP) based forecast engine, (iii) AMI, and (iv) demand-side energy management modules is successfully developed in this work. To validate the proposed model, extensive simulations are conducted and results are compared with the benchmark models like genetic algorithm (GA), bacterial foraging optimization algorithm (BFOA), binary particle swarm optimization (BPSO), and a hybrid combination of genetic and binary particle swarm optimization (GBPSO) in terms of electricity cost, PAR, user comfort, and CO2 emissions. The simulation results demonstrate effectiveness of our proposed model to outperform all the benchmark models in optimizing the consumer and DISCO objectives. The proposed scheme has reduced electricity cost, user discomfort, PAR, and CO2 emission for the residential sector by 15.14%, 4.6%, 61.6%, and 52.86% in scenario 1, 62.60%, 4.56%, 60.77%, and 27.77% in scenario 2, and 26.03%, 4.54%, 63.78%, and 23.02% in scenario 3, as compared to without an EMC. Similarly, for commercial sector the proposed HBFPSO algorithm reduces electricity cost, user discomfort, PAR, and CO2 emission by 11.31%, 5.5%, 60.9%, and 38.18% in scenario 1, 64.9%, 5.56%, 44.08%, and 58.8% in scenario 2, 15.31%, 5.26%, 78.22%, and 15.58% in scenario 3. Likewise, the proposed algorithm also has superior performance for the industrial sector for all the three scenarios.

2 November 2018 in Sensors
Verified
Journal Article
Open access
PDF file
BACH PHI DUONGBACH PHI DUONG
BACH PHI DUONG
SKSheraz Ali Khan
Sheraz Ali Khan
DSDongkoo Shon
Dongkoo Shon
KIKichang Im
Kichang Im
JPJeongho Park
Jeongho Park
Jong-Myon KimJong-Myon Kim
Jong-Myon Kim
Estimation of the remaining useful life (RUL) of bearings is important to avoid abrupt shutdowns in rotary machines. An important task in RUL estimation is the construction of a suitable health indicator (HI) to infer the bearing condition. Conventional health indicators rely on features of the vibration acceleration signal and are predominantly calculated without considering its non-stationary nature. This often results in an HI with a trend that is difficult to model, as well as random fluctuations and poor correlation with bearing degradation. Therefore, this paper presents a method for constructing a bearing’s HI by considering the non-stationarity of the vibration acceleration signals. The proposed method employs the discrete wavelet packet transform (DWPT) to decompose the raw signal into different sub-bands. The HI is extracted from each sub-band signal, smoothened using locally weighted regression, and evaluated using a gradient-based method. The HIs showing the best trends among all the sub-bands are iteratively accumulated to construct an HI with the best trend over the entire life of the bearing. The proposed method is tested on two benchmark bearing datasets. The results show that the proposed method yields an HI that correlates well with bearing degradation and is relatively easy to model.

6 December 2017 in Sensors
Verified
Journal Article
Open access
PDF file
Viet TraViet Tra
Viet Tra
JKJaeyoung Kim
Jaeyoung Kim
SKSheraz Ali Khan
Sheraz Ali Khan
Jong-Myon KimJong-Myon Kim
Jong-Myon Kim
This paper presents a novel method for diagnosing incipient bearing defects under variable operating speeds using convolutional neural networks (CNNs) trained via the stochastic diagonal Levenberg-Marquardt (S-DLM) algorithm. The CNNs utilize the spectral energy maps (SEMs) of the acoustic emission (AE) signals as inputs and automatically learn the optimal features, which yield the best discriminative models for diagnosing incipient bearing defects under variable operating speeds. The SEMs are two-dimensional maps that show the distribution of energy across different bands of the AE spectrum. It is hypothesized that the variation of a bearing’s speed would not alter the overall shape of the AE spectrum rather, it may only scale and translate it. Thus, at different speeds, the same defect would yield SEMs that are scaled and shifted versions of each other. This hypothesis is confirmed by the experimental results, where CNNs trained using the S-DLM algorithm yield significantly better diagnostic performance under variable operating speeds compared to existing methods. In this work, the performance of different training algorithms is also evaluated to select the best training algorithm for the CNNs. The proposed method is used to diagnose both single and compound defects at six different operating speeds.

1 December 2017 in Information Sciences
Verified
Journal Article
Closed access
DADileep K. Appana
Dileep K. Appana
RIRashedul Islam
Rashedul Islam
SKSheraz Ali Khan
Sheraz Ali Khan
JKJong-Myon Kim
Jong-Myon Kim