Faculty

Dr. Akhand Rai received his PhD from Indian Institute of Technology Roorkee, Roorkee. He has a working experience of more than 5 years in various reputed academic and industrial institutions across the country as well as outside. His areas of interest include rotating machinery dynamics, vibration analysis, data-driven condition monitoring, diagnosis and prognosis of rolling element bearings and gears, application of signal processing and artificial intelligence methods for reducing maintenance costs and preventing failures, pipeline fault detection and biomdedical fields such as mental stress diagnosis. He has published 16 research papers in various SCI indexed international journals and 5 papers in national-international conferences with total citations of 864, h-index and i-10 index of 10. Some of his contributions are in well-recognized journals such as Mechanical Systems and Signal processing, Measurement, Tribology International, Applied Soft Computing and IEEE Transactions on Instrumentation and Measurement. He is also a reviewer of various international journals such as IEEE transactions on Industrial Electronics, IEEE Transactions on Circuits and Systems, Mechanism and Machine Theory, IEEE Access, and Measurement. During his research career, he has developed various signal processing techniques to process the sensor signals such as vibration and acoustic emission signals acquired from rotating machines and pipelines to detect faults. Besides, he has successfully developed various fault-diagnosis methods based on AI techniques and machine learning algorithms. Recently, he has been awarded by DRDO, Government of India for demonstrating technology on early fault detection and remaining useful life prediction in aeroengine bearings. He has also been featured in the world top 2% scientist list for the year 2021 prepared by Stanford University for his research contribution in the condition monitoring field. He has established successful research collaborations with foreign scientists and insitutions. His recent collaboration is with Ulsan Industrial Artificial intelligence Laboratory, University of Ulsan, South Korea for developing tehcnology for pipeline mangement and predictive maintennace.

He began his career with General Electric, Aviation, Bangalore. There, he worked on high and low cycle fatigue analyses of jet engine externals and fuel-supply systems. Subsequently, he joined Jaypee University of Engineering and Technology, Guna and worked there as an Assistant Professor for 2.5 years. Afterwards, he finished his PhD from IIT Roorkee and worked with Thapar Institute of Engineering and Technology as a Visiting Assistant Professor for approximately 1 year. He was employed as a Postdoctoral Professional Researcher at University of Ulsan, South Korea, prior to joining Ahmedabad University. There, he developed technology for fault detection in fluid filled mechanical components such as pipelines and boiler tubes. 

Condition monitoring of rotating machinery: The rotating machinery finds extensive application in a variety of industries such as aerospace industry, electric power industry, textile industry, automotive industry, mining industry and energy industry, etc. A few examples of the rotating machinery used in these industries are electrical motors, electrical generators, turbines, compressors, rotary machine tools, and gearboxes, etc. It’s just a matter of the past few decades, that the industries have realized the importance of maintenance of these rotating machines that are actually installed in huge numbers on the production shop floor. A failure of a single rotating machinery leads to huge economic losses because of higher production downtimes and increased maintenance activities. In addition, the chances of human casualties are tremendously increased. My research work therefore focuses on providing efficacious condition-monitoring tools and solutions with an aim to eradicate the catastrophic failures in roto-mechanical equipments before it occurs and thus prevent the related damaging consequences. Through my research, I have developed several diagnostics and prognostics approaches based on different signal porcessing and AI algorithms to monitor the condition of rolling bearings. 

Condition monitoring of pipleines: Pipelines have extensive applications in industries for the transportation of liquids and gases over certain distances. The presence of various defects such as fatigue cracks, stress corrosion cracks, geometrical discontinuities, and corrosion can cause premature failure of pipelines in the form of leaks. This leads to an interruption in the fluid supply, increase in downtime, undue maintenance expenses, and a hazardous atmosphere. Therefore, the detection of leaks becomes important to avoid these unwanted situations. In this regard, my current research interests deal with the application of AI techniques to enable real-time leak detection and prevent associated harmful effects.

Battery management and maintenance: Lithium-ion batteries find huge application in our day-to-day life such as electric vehicles, electronic devices, solar and energy storage devices, and various machines. The performance of battery may deteriorate over extended periods of time due to repeated charge and discharge cycles that cause electrolytic decomposition, temperature rise, and growth in internal resistance, etc. Thus, the prediction of battery remaining useful life becomes important to guarantee an uninterrupted operation of the devices and prevent sudden accidents. We are focusing on developing different data-driven AI approaches that can successfully predict the battery failures in advance.

Mental Stress and Emotion Detection: Mental stress is the body's response to a change that requires a physical, mental, or emotional adjustment. Stress-related mental illness harms both the body and the mind equally. It has a detrimental effect on people's emotional behavior, productivity at work and overall quality of life. In addition, prolonged stress condition may result in depression, stroke, heart attack, obesity, diabetes, and many other health disorders. Over the past few decades, EEG has emerged as an effective biological marker for recognizing stress. The brain activities change with changes in emotional states, which are finally reflected into the EEG signals. In our research, we are attempting to develop signal porcessing and machin learning techniques for EEG analysis and stress detection.

International SCI Journals:

Publications at Ahmedabad University (2020 onwards):

1. Prasad, A., Dantreliya, C., Chande, M., Chauhan, V., & Rai, A. (2022). An intelligent fault diagnosis framework based on piecewise aggregate approximation, statistical moments, and sparse autoencoder. Proceedings of the Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability, 1748006X221108598. https://doi.org/10.1177/1748006X2211085. 
2. Gandhi, C. P., Kumar, A., Vashist, G., Tang, H., Rai, A., & Xiang, J. (2022). Maximal overlap discrete wavelet packet transforms and variants of neutrosophic cubic cross-entropy-based identification of rotor defects. Measurement Science and Technology, 33(8), 085107.
3. Rai, A., & Kim, J. M. (2021). A novel health indicator for pipeline leak detection independent of prior failure information. Measurement, 167, 108284. DOI: 10.1016/j.measurement.2020.108284
4. Rai, A., Ahmad, Z., Hasan, M. J., & Kim, J. M. (2021). A Novel Pipeline Leak Detection Technique Based on Acoustic Emission Features and Two-Sample Kolmogorov–Smirnov Test. Sensors, 21(24), 8247.
5. Ahmad, Z., Rai, A., Hasan, M. J., Kim, C. H., & Kim, J. M. (2021). A Novel Framework for Centrifugal Pump Fault Diagnosis by Selecting Fault Characteristic Coefficients of Walsh Transform and Cosine Linear Discriminant Analysis. IEEE Access, 9, 150128-150141.
6. Hasan, M. J., Rai, A., Ahmad, Z., & Kim, J. M. (2021). A Fault Diagnosis Framework for Centrifugal Pumps by Scalogram-Based Imaging and Deep Learning. IEEE Access, 9, 58052-58066.
7. Ahmad, Z., Rai, A., Maliuk, A. S., & Kim, J. M. (2020). Discriminant feature extraction for centrifugal pump fault diagnosis. IEEE Access, 8, 165512-165528.

Publications Before:

1. Rai, A., & Kim, J. M. (2020). A novel health indicator based on information theory features for assessing rotating machinery performance degradation. IEEE Transactions on Instrumentation and Measurement, 69(9), 6982-6994. DOI: 10.1109/TIM.2020.2978966.
2. Rai, A., & Kim, J. M. (2020). A novel health indicator based on the Lyapunov exponent, a probabilistic self-organizing map, and the Gini-Simpson index for calculating the RUL of bearings. Measurement, 164, 108002. DOI: 10.1016/j.measurement.2020.108002.
3. Habib, M. A., Rai, A., & Kim, J. M. (2020). Performance degradation assessment of concrete beams based on acoustic emission burst features and Mahalanobis—Taguchi system. Sensors, 20(12), 3402.                         
4. Rai, A., & Upadhyay, S. H. (2019). The application of semi- nonnegative matrix factorization for detection of incipient faults in bearings. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 233(13), 4543- 4555.
5. Rai, A., & Upadhyay, S. H. (2018). An integrated approach to bearing prognostics based on EEMD-multi feature extraction, Gaussian mixture models and Jensen-Rényi divergence. Applied Soft Computing, 71, 36-50.
6. Rai, A., & Upadhyay, S. H. (2018). Intelligent bearing performance degradation assessment and remaining useful life prediction based on self-organising map and support vector regression. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 232(6), 1118-1132.
7. Rai, A., & Upadhyay, S. H. (2017). The use of MD-CUMSUM and NARX neural network for anticipating the remaining useful life of bearings. Measurement, 111, 397-410.
8. Rai, A., & Upadhyay, S. H. (2017). Bearing performance degradation assessment based on a combination of empirical mode decomposition and k-medoids clustering. Mechanical Systems and Signal Processing, 93, 16-29.
9. Rai, A., & Upadhyay, S. H. (2016). A review on signal processing techniques utilized in the fault diagnosis of rolling element bearings. Tribology International, 96, 289-306.

Conferences (Presented/Proceedings):

Publications at Ahmedabad University (2020 onwards):

1. Rai,  A., &  Verma,  D. Remaining Useful Life Prediction of Lithium-Ion Batteries using Artificial Intelligence, In International Conference on Sustainable Energy and Clean Technologies, PDEU, Gandhinagar, September, 2-4, 2022. [Received Best Paper Award].

Publications before

1. Rai,  A., &  Upadhyay,  S. H. Estimating the performance degradation of bearings based on multiscale-entropy and Support vector data description”, In National Symposium on Rotor Dynamics, 2017 - NSRD 2017, IIT Patna, India, Dec., 12-13, 2017.
2. Rai, A., & Upadhyay, S. H., “Bearing degradation process prediction based on PCA and regression trees”, In National Tribology Conference 2016 -NTC 2016, IIT (BHU) Varanasi, India, Dec., 08-10, 2016.
3. Rai, A., & Upadhyay, S. H., "A neural network approach for calculating the remaining useful life of bearings", In Proceedings of 60th Congress of ISTAM, MNIT, Jaipur, Rajasthan, India, Dec. 16-19, 2015.

• Awarded  DRDO Dare to Dream Innovation contest 2.0 prize under the category “innovative technologies for early fault detection in aero-engines.” by Defence Research and Development Organization, Government of India.

• Featured in the world top 2% scientist list prepared by Stanford University under the single year category for the year 2021.

• Awarded IIT BHU-Varanasi Gold medal for standing first in Mechanical Engineering at the M. Tech Examination 2012.

Monsoon 2020

1. Fluid Mechanics (CHE 201)
2. Automobile Engineering (MEC442)

Winter 2021

1. Kinematics and Structures of Machines (MEC 200)

Monsoon 2021

1. Dynamics of Machines (MEC450)
2. Dynamics of Machines and Vibrations (MEC301)

Winter 2022

1. Kinematics and Structures of Machines (MEC 200)

Monsoon 2022

1. Kinematics and Structures of Machines (MEC 200)
2. Dynamics of Machines and Vibrations (MEC301)

Project-based learning is an important component of the courses and provide a practical understanding of the subject concepts. Few interesting projects done in my courses are briefly described below. 

Project 1: Design and Development of a Monowheel

Course Name: Dynamics of Machines and Vibrations (MEC 301)
Description: A Monowheel is a one-wheeled single-track vehicle. The rider sits either within the wheel or next to it. The wheel is a ring, usually driven by smaller wheels pressing against its inner rim. A monowheel can have several issues. There are four key problem statements that can be defined for a monowheel. 1. Static and dynamic force analysis of monowheel. 2. Balancing of monowheel. 3. Gyroscope effect on the monowheel. 4. Vibration of monowheel. The students were asked to work on each of these problems, conduct a design analysis and fabricate the monowheel based on the obtained results.

References: Motorized Monowheel. US 2008/0105473 A1 Patent Document.

Project 2: Development of a sine-wave glasss cutter

Course Name: Kinematics and Strutures of Machines (MEC 200)

Description: The students were asked to construct a sine-wave glass cutter using the concepts of mechanism synthesis. The sine-wave galss cutter cuts the glass-material along a sine curve. The cutter design is based on the principles of path generation and motion generation in mechanisms.

Project 3: Development of an agricultural robot using four-bar mechanism

Course Name: Kinematics and Strutures of Machines (MEC 200)

Description: In this project, an agricultural robot was designed and fabricated by students using a combination of four-bar and slider-crank mechanisms. The students used the agricultural robot to perform seeding operation.

Project 4: Development of a quick-return conveyor using gear trains

Course Name: Kinematics and Strutures of Machines (MEC 200)

Description: In this project, the students were asked to design and fabricate a quick-return mechanism based on gear trains for transporting small objects from one place to another. A quick-return mechanism is one where the return stroke is shorter than the forward stroke and helpful in increasing machine efficiency.

Academic Year 2020-2021

# Faculty Incharge for Annual Tech-festival, Ingenium 2021.
# Member for Mechanical Workshop committee.
# Member for PhD admission committee for entrance examination and interview
# Facilitator for Peer Tutoring

Academic Year 2021-2022

# School Academic Committee, Role: MajorAdvisor
# Ingenium 2022 - Annual tech fest, FacultyIncharge
# Admission Outreach Committee, Member
# PhD Admissions Committee, Convener (Major in Mechanical Engineering)
# Fabrication Shop Committee, Member
# Student Affairs Committee, Member

1. A talk delivered on "Sessions on Industrial expectations and readiness" at National Institute of technology Uttarakhand, Uttarakhand; February 04-05.
2. A research talk delivered on "Vibration condition monitoring for industrial machines" in SERB sponsored High-end International Workshop - Karyashala, NITRourkela, Rourkela; December 20-24.