Assistant Professor @ UET Mardan

Dr. Muhammad Farooq Siddique

Pioneering AI-Driven Industrial Intelligence through deep learning, signal processing, fault diagnosis, and predictive maintenance for next-generation smart manufacturing systems.

40+ Publications

932+ Citations

23 i10-Index

19 H-Index

View Publications Download CV

Academic Profile

Profile

Dr. Muhammad Farooq Siddique is an Assistant Professor in the Department of Mechanical Engineering at the University of Engineering and Technology (UET), Mardan, Khyber Pakhtunkhwa, Pakistan. He completed his Ph.D. in Artificial Intelligence and Computer Engineering at the University of Ulsan, South Korea, with the degree officially awarded on 13 February 2026. His research combines artificial intelligence, machine learning, deep learning, advanced signal processing, and intelligent condition monitoring to develop reliable frameworks for fault diagnosis, prognostics, quality monitoring, and predictive maintenance in industrial systems. By integrating time-frequency analysis with hybrid neural architectures, explainable AI, and multi-sensor learning, his work aims to improve the robustness and interpretability of vibration- and acoustic-emission-based monitoring under real-world operating conditions. He has extensive experience with Python, PyTorch, MATLAB, experimental testbeds, industrial sensing, and AI-enabled smart manufacturing. His current interests include intelligent fault diagnosis, predictive maintenance, explainable AI, digital twins, Industry 4.0, and autonomous industrial systems. He also holds internationally recognized occupational health and safety certifications, including NEBOSH, IOSH, and OSHA.

Current PositionAssistant Professor, UET Mardan

Highest DegreePh.D. in AI & Computer Engineering

Emailfarooqsiddique.mech@gmail.com

ORCID0009-0005-5807-7056

My Research

Research Excellence

At the intersection of AI and industrial systems, developing trustworthy models that translate multi-sensor signals into actionable insights.

Research Interests

Deep Learning for Industrial AI
Fault Diagnosis & Predictive Maintenance
Signal Processing & Analysis
Physics-Informed Machine Learning
Explainable AI & Uncertainty
Vision Transformers

Current Projects

Physics-Guided RUL Prediction
Causal Inference for Diagnosis
Graph Neural Networks
Acoustic Emission Analysis
Healthcare AI Applications
Smart City Monitoring

Key Achievements

Best Paper Award — FICTA 2025 (UK)
Best Paper Award — IHCI 2023 (Korea)
40+ Publications in Peer-Reviewed Venues
932+ Citations | H-Index: 19 | i10-Index: 23
NEBOSH, IOSH, OSHA Certified
Active Reviewer for IEEE, Elsevier

Academic Background

Education

A comprehensive journey spanning mechanical engineering and AI research

Ph.D. in AI & Computer Engineering

2022 – 2026 University of Ulsan, South Korea

Thesis: "Condition Monitoring of Flow-Based Industrial and Mechanical Equipment Based on Advanced Signal Processing and Deep Learning"
Advisor: Prof. Jong-Myon Kim
Status: Defense completed November 2025. BK21 Graduate Research Assistant. Degree awarded February 13, 2026.

M.S. in Mechanical Engineering

2018 – 2020 UET Peshawar, Pakistan

Specialized in thermal systems and energy management. University of Arizona Funded (USAID) Scholarship recipient.

Bachelor in Mechanical Engineering

2013 – 2017 NUST, Islamabad, Pakistan

Senior Alumni Scholarship recipient. Strong foundation in mechanical systems design, analysis, and CAD/CAM applications.

Career Journey

Professional Experience

Academic, research, engineering, and industrial leadership experience.

Assistant Professor

April 2026 – Present UET Mardan, Pakistan

Department of Mechanical Engineering. Teaching and research in industrial AI, intelligent condition monitoring, predictive maintenance, and smart manufacturing.

Graduate Research Assistant

September 2022 – February 2026 University of Ulsan, South Korea

Developed advanced condition-monitoring and fault-diagnosis frameworks using acoustic emission, vibration sensing, signal processing, deep learning, and real-world industrial datasets.

Manager, CAD/CAM & Configuration Cell

September 2019 – August 2022 Aircraft Manufacturing Factory, PAC Kamra

Led CAD/CAM and configuration activities supporting aircraft manufacturing and engineering operations.

Mechanical Design Engineer

March 2018 – September 2018 Pakistan Air Force, 3D Laboratory, 109 AED

Worked on mechanical design, 3D modeling, engineering analysis, and manufacturing-support activities.

Research Output

Complete Publications

All listed works are displayed below without search, filtering, or pagination. Citation counts follow the supplied Google Scholar snapshot.

Journal Articles

27 items

JournalIF: 4.0Q22023

A Hybrid Deep Learning Approach: Integrating Short-Time Fourier Transform and Continuous Wavelet Transform for Improved Pipeline Leak Detection

MF Siddique, Z Ahmad, N Ullah, J Kim

Sensors 23 (19), 8079 107 citations

Dr. Muhammad Farooq Siddique

Profile

Research Excellence

Research Interests

Current Projects

Key Achievements

Education

Ph.D. in AI & Computer Engineering

M.S. in Mechanical Engineering

Bachelor in Mechanical Engineering

Professional Experience

Assistant Professor

Graduate Research Assistant

Manager, CAD/CAM & Configuration Cell

Mechanical Design Engineer

Complete Publications

Journal Articles

A Hybrid Deep Learning Approach: Integrating Short-Time Fourier Transform and Continuous Wavelet Transform for Improved Pipeline Leak Detection

Pipeline leak diagnosis based on leak-augmented scalograms and deep learning

A hybrid deep learning approach for bearing fault diagnosis using continuous wavelet transform and attention-enhanced spatiotemporal feature extraction

Pipeline Leak Detection: A Comprehensive Deep Learning Model Using CWT Image Analysis and an Optimized DBN-GA-LSSVM Framework

A new dual-input CNN for multimodal fault classification using acoustic emission and vibration signals

Pipeline Leak Detection System for a Smart City: Leveraging Acoustic Emission Sensing and Sequential Deep Learning

Milling Machine Fault Diagnosis Using Acoustic Emission and Hybrid Deep Learning with Feature Optimization

Centrifugal Pump Fault Diagnosis Based on a Novel SobelEdge Scalogram and CNN

Acoustic Emission-Based Pipeline Leak Detection and Size Identification Using a Customized One-Dimensional DenseNet

Hybrid Deep Learning Model for Fault Diagnosis in Centrifugal Pumps: A Comparative Study of VGG16, ResNet50, and Wavelet Coherence Analysis

A Hybrid Deep Learning Framework for Fault Diagnosis in Milling Machines

Advanced Bearing-Fault Diagnosis and Classification Using Mel-Scalograms and FOX-Optimized ANN

An Intelligent Framework for Fault Diagnosis of Centrifugal Pump Leveraging Wavelet Coherence Analysis and Deep Learning

Spatio-Temporal Feature Extraction for Pipeline Leak Detection in Smart Cities Using Acoustic Emission Signals: A One-Dimensional Hybrid Convolutional Neural Network–Long Short-Term Memory Approach

Advanced Fault Diagnosis in Milling Machines Using Acoustic Emission and Transfer Learning

A Deep Learning Approach for Fault Diagnosis in Centrifugal Pumps through Wavelet Coherent Analysis and S-Transform Scalograms with CNN-KAN

Burst-informed acoustic emission framework for explainable failure diagnosis in milling machines

Application of membrane technology in the treatment of waste liquid containing radioactive materials

Advanced fault diagnosis in milling cutting tools using vision transformers with semi-supervised learning and uncertainty quantification

Multi-sensor observer-based residual learning with Auto-Permutation Feature Importance for fault diagnosis of multistage centrifugal pumps under variable pressures

Smart Predictive Maintenance: A TCN-Based System for Early Fault Detection in Industrial Machinery

Early-warning industrial fault detection based on physics-guided residual learning and calibrated CRNNs

A multistage transfer learning framework for intelligent fault diagnosis of rotating machinery under variable operating conditions

Advanced Fault Diagnosis in Rotary Machines Using Optimized Transfer Learning

Fabrication Challenges in Synthesizing Porous Ceramic Membrane to Effective Flue Gas Treatment

A distribution-level statistical framework for reliable pipeline leak detection using multi-domain signal analysis

Calibrated Deep-Learning Risk Indexing and Latent Behavioural Profiling for Occupational Mental-Health Risk Assessment

Conferences & Book Chapters

An Interpretable Lightweight CNN Framework for Fault Diagnosis in Centrifugal Pumps Using Time-Frequency Scalograms

Advanced Fault Diagnosis in Milling Machines Using CQ-NSGT and Deep Learning

Centrifugal Pump Fault Detection with Hybrid Feature Pool and Deep Learning

Pipeline Leak Detection: Leveraging Acoustic Emission Signal Processing and Machine Learning

Design of Double Integral Sliding Mode Controller for Energy Storage System of a Novel Multisource Hybrid Electric Vehicle

Comprehensive Pipeline Leak Detection Using Induced-Leak Enhanced Scalogram Analysis and Deep Learning

A Hybrid Classification Framework of Centrifugal Pumps Using Wavelet Coherence Visuals and Principal Component Analysis

Fabrication and Characterization of porous alumina and fly ash based filtering membrane through appending pore forming agent technique

Centrifugal Pump Health Condition Identification Based on Novel Multi-filter Processed Scalograms and CNN

A Framework for Centrifugal Pump Diagnosis Using Health Sensitivity Ratio Based Feature Selection and KNN

Bearing Fault Diagnosis: Class-Conditional Deep Domain Adaptation for Generalization Across Machines

Local and Global Feature Extraction Using Convolutional Autoencoders and Convolution Neural Networks for Diagnosing Milling Machine Faults

Analysis of dual booster mirrors box type solar cooker integrated with thermal storage

Solar Thermal Water and Space Heating: Comparative Analysis of Charging and Discharging Behavior of Phase Change Materials

Under Review & In Preparation

Advanced Bearing Fault Diagnostics Based on Physics-Guided Vision Transformer and Band-Aware Attention

Layer-Wise Domain Discrepancy-Guided Transfer Learning with ScaloNet for Fault Diagnosis in Rotating Machines

Physics-Informed Neural Differential Modelling for Continuous Tool Wear and Uncertainty-Aware Remaining Useful Life Prediction

Research Gallery

Contact

Email

Phone

Profiles