Research Title: Online Model-Free Reinforcement Learning for Output Feedback Tracking Control of a Class of Discrete-time Systems with Input Saturation

Author: Ahmad Jobran Al-Mahasneh, Published Year: 2022

IEEE Access, 10

Faculty: Engineering and Technology

Abstract: In this paper, a new model-free Model-Actor (MA) reinforcement learning controller is developed for output feedback control of a class of discrete-time systems with input saturation constraints. The proposed controller is composed of two neural networks, namely a model-network and an actor network. The model-network is utilized to predict the output of the plant when a certain control action is applied to it. The actor network is utilized to estimate the optimal control action that is required to drive the output to the desired trajectory. The main advantages of the proposed controller over the previously proposed controllers are its ability to control systems in the absence of explicit knowledge of these systems’ dynamics and its ability to start learning from scratch without any offline training. Also, it can explicitly handle the control constraints in the controller design. Comparison results with a previously published reinforcement learning output feedback controller and other controllers confirm the superiority of the proposed controller.

Keywords: Reinforcement learning, adaptive control, nonlinear control, optimal control.

Research Title: Guidance, Navigation and Control System for Multi-Robot Network in Monitoring and Inspection Operations

Author: Ahmad Jobran Al-Mahasneh, Published Year: 2022

Drones , 6

Faculty: Engineering and Technology

Abstract: This work focuses on the challenges associated with autonomous robot guidance, navigation, and control in multi-robot systems. This study provides an affordable solution by utilizing a group of small unmanned ground vehicles and quadrotors that collaborate on monitoring and inspection missions. The proposed system utilizes a potential fields path planning algorithm to allow a robot to track a moving target while avoiding obstacles in a dynamic environment. To achieve the required performance and provide robust tracking against wind disturbances, a backstepping controller is used to solve the essential stability problem and ensure that each robot follows the specified path asymptotically. Furthermore, the performance is also compared with a proportional- integral-derivative (PID) controller to ensure the superiority of the control system. The system combines a low-cost inertial measurement unit (IMU), a GNSS receiver, and a barometer for UAVs to generate a navigation solution (position, velocity, and attitude estimations), which is then used in the guidance and control algorithms. A similar solution is used for UGVs by integrating the IMU, a GNSS receiver, and encoders. Non-linear complementary filters integrate the measurements in the navigation system to produce high bandwidth estimates of the state of each robotic platform. Experimental results of several scenarios are discussed to prove the effectiveness of the approach.

Keywords: backstepping controller; complementary filters; motion planner; navigation system; ground robot; aerial robot; inspection and monitoring

Research Title: A three-stage PSO-based methodology for tuning an optimal PD-controller for robotic arm manipulators

Author: Mustafa Awwad Al Khawaldeh, Published Year: 2022

Evolutionary Intelligence, 15

Faculty: Engineering and Technology

Abstract: Six degrees-of-freedom (DoF) robot manipulators are dynamically coupled and highly nonlinear multi-variable systems. Calculating the optimal joint angles from the operational space (i.e. inverse kinematics) and designing the optimal joint controller parameters are two important research topics. This paper proposes a 3-stage Particle Swarm Optimization (PSO)-based methodology for solving the inverse kinematics and optimizing the controller parameters. In the first stage, a PSO algorithm solves the inverse kinematics problem by minimizing a multi-objective cost function in the operational space (i.e. the error in the end-effector’s pose) and therefore finds the optimal joint angles. In the second stage, polynomial functions generate the desired trajectory between the initial and final poses in the joint space. Finally, a second PSO algorithm tunes six proportional-derivative (PD) controllers, one for each joint, to track the desired trajectory by minimizing another multi-objective cost function in the joint space. Two case studies, based on six DoF Puma 560, validate the performance of the proposed methodology. Simulation results show that the proposed 3-stage methodology provides fast and accurate results as the PSO algorithms are effective in solving the inverse kinematics problem and tuning the optimal PD parameters.

Keywords: Robot manipulator; Nonlinear dynamics; Optimization, PSO algorithm, Inverse kinematics, Trajectory tracking, PD-control, PUMA 560

Research Title: Macro-engineering Design for an Artificial Lake in Southeastern Jordan

Author: Mustafa Awwad Al Khawaldeh, Published Year: 2022

WSEAS TRANSACTIONS on ENVIRONMENT and DEVELOPMENT, 18

Faculty: Engineering and Technology

Abstract: Water situation in Jordan has become very critical. A feasible solution is to desalinate water drawn from Gulf of Aqaba (GoA). Another problem that Jordan faces is the very short coastline. These two problems can be solved by developing an artificial lake in south Jordan. The water from the lake can be desalinated while the lake itself provides a badly needed coastline. This work presents a macro-engineering design for the proposed lake; The proposed project is named "Red Sea-Jafer Basin Conduit (RSJBC)"; it involves a pipeline connecting GoA at the Red Sea with Jafer Basin (JB) in the south-eastern desert, where the topography of the region is exploited to develop an artificial Lake. Using multiple pumping stations, seawater will be pumped from GoA to JB though a 220 km long pipeline. After constructing the project, it will take three years to fill-up the Lake. Once it is filled, the pumping rate is reduced from 51 to 30 m3/s. However, based on fresh water needs, a volume of up to 21 m3/s can be desalinated. The suggested pipeline route has a curved path (CP) to avoid the mountains if it were to go straight path (SP). A comparison is conducted between CP and SP, where it was found that CP offers the lowest development cost for RSJBC, given fabric pipe is used. More specifically,a pipe diameter of 6 m enables total development cost of 2.74 B$, with corresponding annual operating cost of 306 M$.

Keywords: Artificial Lake, Jordan desert, Gulf of Aqaba, Jafer Basin, Water transport, Pumping station, Gravity flow, Seawater pipeline, Seawater pumping, Tourist attraction development.

Research Title: Obstacles Avoidance for Mobile Robot Using Type-2 Fuzzy Logic Controller

Author: Mustafa Awwad Al Khawaldeh, Published Year: 2022

Robotics, 11(6)

Faculty: Engineering and Technology

Abstract: Intelligent mobile robots need to deal with different kinds of uncertainties in order to perform their tasks, such as tracking predefined paths and avoiding static and dynamic obstacles until reaching their destination. In this research, a Robotino® from Festo Company was used to reach a predefined target in different scenarios, autonomously, in a static and dynamic environment. A Type-2 fuzzy logic controller was used to guide and help Robotino® reach its predefined destination safely. The Robotino® collects data from the environment. The rules of the Type-2 fuzzy logic controller were built from human experience. They controlled the Robotino® movement, guiding it toward its goal by controlling its linear and angular velocities, preventing it from colliding obstacles at the same time, as well. The Takagi–Sugeno–Kang (TSK) algorithm was implemented. Real-time and simulation experimental results showed the capability and effectiveness of the proposed controller, especially in dealing with uncertainty problems.

Keywords: mobile robot; Robotino®; static and dynamic obstacle-avoidance environment; Type-2 fuzzy logic controller; wireless sensor network

Research Title: Evaluating social sustainability in Jordanian residential neighborhoods: a combined expert-user approach

Author: Alaa Saleh Al Shdiefat, Published Year: 2022

Faculty: Engineering and Technology

Abstract: Neighborhood sustainability has assumed a pole position as a topic of interest in the past years, addressed through dedicated strands of most of the globally adopted sustainability rating tools, such as LEED and BREEAM. Considering sustainability assessment, the social sustainability of neighborhoods assumes a certain particularity, not only in terms of its high context dependence pertaining to its locality, but in its means of assessment as well, with people as a key potential evaluator for matters that are not bound to quantitative aspects. This research focused on developing a framework for rating social sustainability in neighborhoods, utilizing a quantitative approach that builds upon insights obtained by an extended group of experts and end users. It combines the Delphi and AHP techniques along with the case study approach to develop a framework that suits the Jordanian local context, where a particular neighborhood, Dahiyat Al Hussein in Amman, is used for validation. The research revealed that rating the social sustainability of neighborhoods is not only highly guided by the local context it addresses, but is also reliant on the level of understanding and adoption of the concept itself as attained by the people.

Keywords: Social sustainability, Neighborhood, Rating system, Delphi technique, AHP, Local context

Research Title: Experimental and numerical study of strengthening and repairing heat-damaged RC circular column using hybrid system of CFRP

Author: Ala Taleb Obaidat, Published Year: 2022

Case Studies in Construction Materials,

Faculty: Engineering and Technology

Abstract: This study aims to investigate the behavior of heat damaged reinforced concrete RC circular column considering effect of heat and repair technique. Six RC circular column with diameter of 185 mm and 800 mm in height were cast, heated at 400 °C and 600 °C for 3 h, strengthened and repaired with hybrid system of CFRP and then tested under concentric load. Also, four RC circular columns from Obaidat et al. (2020) [3] were used for comparison. Complementary to the experimental investigation, a finite element modeling (FEM) was developed to simulate the compression behavior of heat damaged RC circular column. The result showed that specimens strengthened and repaired with hybrid system SC-H23-COMP and (DC-H400-COM and DC-H600-COM) exhibited the higher improvement in compression capacity about 100.4% and (86.7% and 53%), receptively, more than the control specimens. It was concluded that as the temperature increases the strength of the specimen decreases. Moreover, the strength in repaired specimens by hybrid system increased by 64.9% and 48.85% more than unheated control RC column specimen CC-COM. Finally, the FEM results provides a good agreement with experimental results and the model capable to predict the compression behavior of the RC circular column.

Keywords: Heat damagedStrengtheningRepairingCarbon fiber reinforced polymers CFRPHybrid systemStress-strainRC circular columnFinite element model

Research Title: BehaviBehaviour of heat damaged repaired reinforced SCC cantilever beam using carbon fiber reinforced polymer rope

Author: Ala Taleb Obaidat, Published Year: 2022

Faculty: Engineering and Technology

Abstract: This study investigated the behaviour of self-compacted cantilever concrete (SCCC) beams exposed to high temperature and repaired using near surface mounted carbon fibre (NSM-CFRP) rope. Nine (SCCC) beam specimens with cross sectional area of (150 mm × 150 mm) and 750 mm in length were constructed and tested. Seven beam specimens were exposed to 400 °C and 500 °C for two hours and then repaired using NSM-CFRP rope. The tested SCCC specimens were divided into four groups to study the effect of temperature, location and number of NSM rope. Results showed that using NSM-CFRP rope as retrofitting or strengthening techniques at the sides of cantilever beam had a significant effect on load-deflection behaviour compared to other techniques. It was concluded that using NSM-CFRP rope as retrofitting or strengthening techniques depend on the number of rope and position of ropes. Moreover, increasing the number of ropes to two at top of the beam had a limited impact upon load capacity. On the other hand, rehabilitated (SCC) beams specimens damaged by heat up to 500 °C for 2 h with two CFRP ropes at sides and top surface exhibited load capacity about 197% and 101%, respectively, as control specimen.

Keywords: Heat damagedstrengtheningrepairingcarbon fibre reinforced polymers (CFRP)stress-strainself-compacted cantilever concrete (SCC)

Research Title: Experimental and analytical investigation of using externally bonded, hybrid, fiber-reinforced polymers to repair and strengthen heated, damaged RC beams in flexure

Author: Ala Taleb Obaidat, Published Year: 2022

Faculty: Engineering and Technology

Abstract: Purpose – This study aims to conduct an experimental study and finite element model (FEM) to investigate the flexural behavior of heat-damaged beams strengthened/repaired by hybrid fiber-reinforced polymers (HFRP). Design/methodology/approach – Two groups of beams of (150 3 250 3 1,200) mm were cast, strengthened and repaired using different configurations of HFRP and tested under four-point loadings. The first group was kept at room temperature, while the second group was exposed to a temperature of 4008C. Findings – It was found that using multiple layers of carbon fiber-reinforced polymer (CFRP) and glass fiberreinforced polymer (GFRP) enhanced the strength more than a single layer. Also, the order of two layers of FRP showed no effect on flexural behavior of beams. Using a three-layer scheme (attaching the GFRP first and followed by two layers of CFRP) exhibited increase in ultimate load more than the scheme attached by CFRP first. Furthermore, the scheme HGC (heated beam repaired with glass and carbon, in sequence) allowed to achieve residual flexural capacity of specimen exposed to 4008C. Typical flexural failure was observed in control and heat-damaged beams, whereas the strengthened/repaired beams failed by cover separation and FRP debonding, however, specimen repaired with two layers of GFRP failed by FRP rupture. The FEM results showed good agreement with experimental results. Originality/value – Few researchers have studied the effects of HFRP on strengthening and repair of heated, damaged reinforced concrete (RC) beams. This paper investigates, both experimentally and analytically, the performance of externally strengthened and repaired RC beams, in flexure, with different FRP configurations of CFRP and GFRP.

Keywords: Hybrid fiber-reinforced polymers, Heat, Repairing, Strengthening, RC beams, Flexure, Glass FRP, Carbon FRP

Research Title: Modeling of confined circular RC columns using artificial neural network and finite element method

Author: Ala Taleb Obaidat, Published Year: 2022

Structures, 40

Faculty: Engineering and Technology

Abstract: A Finite Element (FE) and an Artificial Neural Network (ANN) model were developed to investigate the effect of different parameters, such as the space between stirrups and the diameter of longitudinal steel, on the behavior of circular Reinforced-Concrete (RC) columns confined with fiber reinforced polymer (FRP) sheets using the actual hoop rupture strain of the FRP. The FE model was accomplished using the FE software ABAQUS 6.13 which incorporates the nonlinear behavior of concrete material, the bilinear stress–strain curve of steel, and the linear elastic behavior of FRP. It was found that there is a good agreement between the FE model (FEM) results and the experiments. The ANNs were trained and tested on an experimental database from the literature. The database contains the experimental ultimate FRP strain, and the ultimate load results of 92 FRP confined circular RC columns. The ANN results agreed well with the FEM results. The neural network results were carried out to develop empirical equations to predict the effective rupture FRP strain and the ultimate load for circular confined RC columns with R2 of 0.912 and 0.932, respectively. The proposed equations estimate the ultimate strain from experimental works of the FRP with a small error up to 20%. In addition, the predicted results from the proposed equations exhibited good accuracy compared with previous guidelines and experimental and FE results from the literature, and it can be easily used in engineering designs as well.

Keywords: Fiber reinforced polymer (FRP)ConcreteColumnConfinementFinite element analysis (FEA)Artificial neural network (ANN)