A proximal policy optimization framework for bearing condition monitoring using low-dimensional time-domain features Waqar Ahmad, Syed Humayoon Shah, Naeem Ul Islam, Said Ghani Khan, Kamran Shah JVC Journal of Vibration and Control, 2026 Bearings are essential elements of rotating machinery and their malfunction may result in considerable operational interruptions and financial detriment. This paper investigates Proximal Policy Optimization (PPO), a reinforcement learning (RL) technique, to formulate data-driven policies for bearing maintenance. A custom OpenAI Gym environment was developed to replicate the decision-making process employing experimental vibration data from normal bearings, as well as bearings with ball, inner-race, and outer-race faults. The RL agent was trained to determine the appropriate maintenance policies such as inspection, repair, and replacement to reduce total costs and prevent breakdowns. In addition, training performance was evaluated using essential measures such as cumulative rewards, loss, KL divergence, and value loss. The experimental findings demonstrate that the PPO agent achieved 94.2% accuracy in decision making in 10 epochs with limited improvement from additional training. Furthermore, the method shows instability in policy updates, value loss, and sensitivity to sparse-reward structure. These findings demonstrate that PPO holds considerable potential for vibration-based CBM; however, its performance in real-world operational environments remains highly dependent on reward design and hyperparameter tuning. This research showcases a balanced evaluation of PPO’s strengths and limitations in bearing maintenance and provides a foundation for future studies on hybrid and alternative reinforcement learning strategies.
Finite Element Analysis of Custom Designed and Additive Manufactured Total Surface Bearing Prosthesis for Trans-Tibial Amputees Kamran Shah, Mustafa Ur Rehman Applied Sciences Switzerland, 2025 Our limb prostheses aim to restore Activities of Daily Living (ADLs) for amputees, with the socket being a critical component of trans-tibial prostheses influencing both comfort and functionality. Despite technological advancements, challenges such as fit, weight, and durability remain. This study investigates an additive manufacturing method for Total Surface Bearing (TSB) sockets, leveraging CT scans to create a Computer-Aided Design (CAD) and finite element (FE) model. Biomechanical behavior under static loading conditions were analyzed using FE analysis and resistive-based pressure sensors. The study found consistent pressure distribution across the residual limb, with deviations of 8.53 kPa and 4.46 kPa between FE analysis and experimental measurements. Mean pressures of 44.6 kPa and 22.11 kPa were observed under Full Body Weight (FBW) and Half Body Weight (HBW) conditions, respectively. The FE analysis demonstrated a uniform stress distribution in the prosthetic socket, with a maximum stress of 0.15 MPa and a deformation of 0.008 mm, highlighting the effectiveness of this approach in enhancing socket design.
Design, Analysis, and Development of Low-Cost State-of-the-Art Magnetorheological-Based Microprocessor Prosthetic Knee Muhammad Usman Qadir, Izhar Ul Haq, Muhammad Awais Khan, Kamran Shah, Houssam Chouikhi, Mohamed A. Ismail Sensors, 2024 For amputees, amputation is a devastating experience. Transfemoral amputees require an artificial lower limb prosthesis as a replacement for regaining their gait functions after amputation. Microprocessor-based transfemoral prosthesis has gained significant importance in the last two decades for the rehabilitation of lower limb amputees by assisting them in performing activities of daily living. Commercially available microprocessor-based knee joints have the needed features but are costly, making them beyond the reach of most amputees. The excessive cost of these devices can be attributed to custom sensing and actuating mechanisms, which require significant development cost, making them beyond the reach of most amputees. This research contributes to developing a cost-effective microprocessor-based transfemoral prosthesis by integrating off-the-shelf sensing and actuating mechanisms. Accordingly, a three-level control architecture consisting of top, middle, and low-level controllers was developed for the proposed prosthesis. The top-level controller is responsible for identifying the amputee intent and mode of activity. The mid-level controller determines distinct phases in the activity mode, and the low-level controller was designed to modulate the damping across distinct phases. The developed prosthesis was evaluated on unilateral transfemoral amputees. Since off-the-shelf sensors and actuators are used in i-Inspire, various trials were conducted to evaluate the repeatability of the sensory data. Accordingly, the mean coefficients of correlation for knee angle, force, and inclination were computed at slow and medium walking speeds. The obtained values were, respectively, 0.982 and 0.946 for knee angle, 0.942 and 0.928 for knee force, and 0.825 and 0.758 for knee inclination. These results confirmed that the data are highly correlated with minimum covariance. Accordingly, the sensors provide reliable and repeatable data to the controller for mode detection and intent recognition. Furthermore, the knee angles at self-selected walking speeds were recorded, and it was observed that the i-Inspire Knee maintains a maximum flexion angle between 50° and 60°, which is in accordance with state-of-the-art microprocessor-based transfemoral prosthesis.
A Wearable Force Myography-Based Armband for Recognition of Upper Limb Gestures Mustafa Ur Rehman, Kamran Shah, Izhar Ul Haq, Sajid Iqbal, Mohamed A. Ismail Sensors, 2023 Force myography (FMG) represents a promising alternative to surface electromyography (EMG) in the context of controlling bio-robotic hands. In this study, we built upon our prior research by introducing a novel wearable armband based on FMG technology, which integrates force-sensitive resistor (FSR) sensors housed in newly designed casings. We evaluated the sensors’ characteristics, including their load–voltage relationship and signal stability during the execution of gestures over time. Two sensor arrangements were evaluated: arrangement A, featuring sensors spaced at 4.5 cm intervals, and arrangement B, with sensors distributed evenly along the forearm. The data collection involved six participants, including three individuals with trans-radial amputations, who performed nine upper limb gestures. The prediction performance was assessed using support vector machines (SVMs) and k-nearest neighbor (KNN) algorithms for both sensor arrangments. The results revealed that the developed sensor exhibited non-linear behavior, and its sensitivity varied with the applied force. Notably, arrangement B outperformed arrangement A in classifying the nine gestures, with an average accuracy of 95.4 ± 2.1% compared to arrangement A’s 91.3 ± 2.3%. The utilization of the arrangement B armband led to a substantial increase in the average prediction accuracy, demonstrating an improvement of up to 4.5%.
Assessment of Low-Density Force Myography Armband for Classification of Upper Limb Gestures Mustafa Ur Rehman, Kamran Shah, Izhar Ul Haq, Sajid Iqbal, Mohamed A. Ismail, Fatih Selimefendigil Sensors, 2023 Using force myography (FMG) to monitor volumetric changes in limb muscles is a promising and effective alternative for controlling bio-robotic prosthetic devices. In recent years, there has been a focus on developing new methods to improve the performance of FMG technology in the control of bio-robotic devices. This study aimed to design and evaluate a novel low-density FMG (LD-FMG) armband for controlling upper limb prostheses. The study investigated the number of sensors and sampling rate for the newly developed LD-FMG band. The performance of the band was evaluated by detecting nine gestures of the hand, wrist, and forearm at varying elbow and shoulder positions. Six subjects, including both fit and amputated individuals, participated in this study and completed two experimental protocols: static and dynamic. The static protocol measured volumetric changes in forearm muscles at the fixed elbow and shoulder positions. In contrast, the dynamic protocol included continuous motion of the elbow and shoulder joints. The results showed that the number of sensors significantly impacts gesture prediction accuracy, with the best accuracy achieved on the 7-sensor FMG band arrangement. Compared to the number of sensors, the sampling rate had a lower influence on prediction accuracy. Additionally, variations in limb position greatly affect the classification accuracy of gestures. The static protocol shows an accuracy above 90% when considering nine gestures. Among dynamic results, shoulder movement shows the least classification error compared to elbow and elbow–shoulder (ES) movements.
Effect of Tine Shaped Furrow Opener on Dry Soil Using Discrete Element Modelling Abdul Mohiz, Fazal E Nasir, Kamran Shah 2023 International Conference on Robotics and Automation in Industry Icrai 2023, 2023 Tillage of the soil is the most important consideration when it comes to the implementation of agricultural practices. Increases in crop yield has been achieved through a variety of agricultural practices thanks to the discoveries of various agricultural experts. The planting process is the one that has the greatest impact on the crop's overall health. The hull can be more precisely prepared for the seed-planting trench with the assistance of furrows. A variety of furrow openers are currently undergoing the implantation process. Studying dynamic systems that are discontinuous in nature can be done with the help of discrete element modelling. The simulation of a tine-shaped furrow opener using the EDEM package software was carried out for three different speeds. When the speed of an object increases, so does the force it exerts on it. Additionally, the length of an object has an effect on the force it exerts. Additionally, taken into consideration were the profiles that were generated in the soil. To carry out statistical validation of the results analysis of variation (ANOVA) was done. The results provided a basis for calculating a confidence level of 95%. For the furrow openers, it was suggested that a speed of 0.495 meters per second, which is equivalent to 1.76 kilometers per hour, be used.
Control Simulation of Proportional-Integral and Sliding Mode Control for Precision Seed Planters Yasir Nawaz, Muhammad Usman Qadir, Muhammad Awais Khan, Izhar Ul Haq, Kamran Shah, Tahir Khan 2023 International Conference on Robotics and Automation in Industry Icrai 2023, 2023 The desired development and design of an electric control system (ECS) for a precision planter is one of the most crucial elements in evaluating the efficacy of applicators for plant production. The seeds would be sown using this approach. Years have been invested in the continuous development of a range of application methods and metering systems, each of which offers specific advantages for applying the required system with a high degree of precision. Researchers worldwide have been trying to make electric-driven seed meters (EDSM) for planters, but they haven't succeeded. This study looks into the current state of installing seed metering systems for precision planters. Proportional-integral (PI) and sliding mode control (SMC) designs of the control system have been implemented to improve the planting quality of the planters. We want to highlight the electrically driven control system (EDCS) using these designs. An overview of the noteworthy features and limitations of past research is given. We also discuss several future directions for future research, concentrating on the knowledge gaps in this area.
Deep Learning with a Novel Concoction Loss Function for Identification of Ophthalmic Disease Sayyid Kamran Hussain, Ali Haider Khan, Malek Alrashidi, Sajid Iqbal, Qazi Mudassar Ilyas, Kamran Shah Computers Materials and Continua, 2023 As ocular computer-aided diagnostic (CAD) tools become more widely accessible, many researchers are developing deep learning (DL) methods to aid in ocular disease (OHD) diagnosis. Common eye diseases like cataracts (CATR), glaucoma (GLU), and age-related macular degeneration (AMD) are the focus of this study, which uses DL to examine their identification. Data imbalance and outliers are widespread in fundus images, which can make it difficult to apply many DL algorithms to accomplish this analytical assignment. The creation of effcient and reliable DL algorithms is seen to be the key to further enhancing detection performance. Using the analysis of images of the color of the retinal fundus, this study offers a DL model that is combined with a one-of-a-kind concoction loss function (CLF) for the automated identification of OHD. This study presents a combination of focal loss (FL) and correntropy-induced loss functions (CILF) in the proposed DL model to improve the recognition performance of classification performance of the DL model with our proposed loss function is compared to that of the baseline models using accuracy (ACU), recall (REC), specificity (SPF), Kappa, and area under the receiver operating characteristic curve (AUC) as the evaluation metrics. The testing shows that the method is reliable and effcient.
Machine learning techniques to evaluate the ultrasonic pulse velocity of hybrid fiber-reinforced concrete modified with nano-silica Kaffayatullah Khan, Muhammad Nasir Amin, Umbreen Us Sahar, Waqas Ahmad, Kamran Shah, Abdullah Mohamed Frontiers in Materials, 2022 It is evident that preparing materials, casting samples, curing, and testing all need time and money. The construction sector will benefit if these problems can be handled using cutting-edge techniques like machine learning. Also, a material’s ultrasonic pulse velocity (UPV) is affected by various variables, and it is difficult to study their combined effect experimentally. This research used machine learning to assess the UPV and SHapley Additive ExPlanations techniques to study the impact of input parameters of hybrid fiber-reinforced concrete modified with nano-silica (HFRNSC). Three ML algorithms were employed, i.e., gradient boosting regressor, adaptive boosting regressor, and extreme gradient boosting, for ultrasonic pulse velocity evaluation. The accuracy of machine learning models was measured via the coefficient of determination (R2), k-fold analysis, statistical tests, and comparing the predicted and actual ultrasonic pulse velocity. This study determined that the gradient boosting and adaptive boosting models had a good level of accuracy for ultrasonic pulse velocity, but the extreme gradient boosting method estimated the ultrasonic pulse velocity of HFRNSCs with a greater degree of precision. Also, from the statistical checks and k-fold approach, it was discovered that the extreme gradient boosting method is more exact in estimating the ultrasonic pulse velocity of HFRNSCs. The SHapley Additive ExPlanations analysis revealed that the age of the specimen and nano-silica had a greater positive impact on the ultrasonic pulse velocity of HFRNSCs, whereas the coarse aggregate to fine aggregate ratio had a negative impact. In addition, fiber volume was found to have both positive and negative effects. By aiding the development of rapid and low-cost methods for determining material properties and the influence of input parameters, the construction industry may profit from the use of such technologies.
Design and Analysis of Knee Joint for Transfemoral Amputees Muhammad Usman Qadir, Muhammad Awais Khan, Muzammal Hussain, Izhar ul Haq, Nizar Akhtar, Kmaran Shah Aims 2021 International Conference on Artificial Intelligence and Mechatronics Systems, 2021
Laser micro processing of carbide tool insert Ashfaq Khan, Muhammad Alam Zaib Khan, Kamran Shah, Aftab Khan, Mushtaq Khan, Syed Husain Imran, Mohammad A. Sheikh, Lin Li ASME 2014 International Manufacturing Science and Engineering Conference Msec 2014 Collocated with the JSME 2014 International Conference on Materials and Processing and the 42nd North American Manufacturing Research Conference, 2014
