S. B. Mohd Noor

Intelligent Modeling and Control of a Conveyor Belt Grain Dryer Using a Simplified Type 2 Neuro-Fuzzy Controller

In this article, a nonlinear autoregressive with exogenous input (NARX) network was utilized to model a conveyor belt grain dryer using a set of input–output data collected during an experiment to dry paddy grains. The resulting NARX model has achieved a remarkable modeling accuracy compared to other previously reported modeling techniques. To control the considered dryer, a simplified type 2 adaptive neuro-fuzzy inference system (ANFIS) controller was proposed. The effectiveness of this controller was demonstrated by several performance tests conducted by computer simulations. Moreover, a comparative study with other related controllers further confirmed the superiority of the proposed dryer controller.

Broadly tunable multiwavelength fiber laser with bismuth-oxide EDF using large effective area fiber

A multiwavelength laser comb using 2.49 m Bismuth-oxide erbium-doped fiber (Bi-EDF) with different lengths of large effective area fiber (LEAF) in a ring cavity configuration is realized. The Bi-EDF is used as the linear gain medium and LEAF is used as the non-linear gain medium for stimulated Brillouin scattering. Out of the four different lengths, the longest length of 25 km LEAF exhibits the widest tuning range of 44 nm (1576 to 1620 nm) in the L-band at 264 mW pump power and 5 mW Brillouin pump power. In addition, a total of 15 output channels are achieved with total average output power of −8 dBm from this laser structure. All Brillouin Stokes signals exhibit high peak power of above −20 dBm per signal and their optical signal-to-noise ratio of greater than 15 dB.

Non-linear modelling and control of a conveyor-belt grain dryer utilizing neuro-fuzzy systems

The grain drying process is characterized by its complex and non-linear nature. As a result, conventional control system design cannot handle this process appropriately. This work presents an intelligent control system for the grain drying process, utilizing the capabilities of the adaptive neuro-fuzzy inference system (ANFIS) to model and control this process. In this context, a laboratory-scale conveyor-belt grain dryer was specifically designed and constructed for this study. Utilizing this dryer, a real-time experiment was conducted to dry paddy (rough rice) grains. Then, the input–output data collected from this experiment were presented to an ANFIS network to develop a control-oriented dryer model. As the main controller, a simplified proportional–integral–derivative (PID)-like ANFIS controller is utilized to control the drying process. A real-coded genetic algorithm (GA) is used to train this controller and to find its scaling factors. From the robustness tests and a comparative study with a genetically tuned conventional PID controller, the simplified ANFIS controller has proved its remarkable ability in controlling the grain drying process represented by the developed ANFIS model.

Modelling of a conveyor-belt grain dryer utilizing a sigmoid network

Post-harvest techniques play an important role in modern agricultural industry. One of these essential post-harvest techniques is the grain drying process. However, this process is characterized by its high complexity and nonlinearity due to the effects of several drying parameters. Therefore, conventional modelling approaches cannot produce accurate modelling results to describe the dynamics of this challenging process. This paper presents a nonlinear modelling technique to develop a highly accurate model for a laboratory-scale conveyor-belt grain drying system. In particular, this modelling technique is based on utilizing the sigmoid network as a nonlinearity estimator in a nonlinear autoregressive with exogenous input (NARX) model. As the training samples, a set of experimental input-output data was used in the model development process. This data set was collected from the conveyor-belt grain dryer during a real-time experiment to dry paddy (rough rice) grains. Compared to other previously reported modelling techniques which were applied for the same drying process, the proposed sigmoid-based NARX model has achieved the best modelling accuracy in describing the grain drying process. More precisely, the proposed model has achieved a root mean squared error (RMSE) of 2.776 × 10-17. It is worth to highlight that, unlike previous efforts which aimed at modelling conveyor-belt grain drying systems, the advantage of the proposed modelling technique is that it can be directly applied to model the drying system regardless of the dryer shape, and moreover regardless of the size and physical properties of the grains to be dried. In addition, the resulting model can be readily employed in control applications to design suitable dryer controllers.

Wavelet network based online sequential extreme learning machine for dynamic system modeling

Wavelet network (WN) has been introduced in many applications of dynamic systems modeling with different learning algorithms. In this paper an online sequential extreme learning machine (OSELM) algorithm adopted as training procedure for wavelet network based on serial-parallel nonlinear autoregressive exogenous (NARX) model. The proposed model used as system identification for nonlinear dynamic systems. The main advantage of OSELM over conventional algorithms is the ability of updating network weights sequentially through data sample-by-sample in a single learning step. This attains good performance at extremely fast learning. The initial kernel parameters of WN played a big role to ensure fast and better learning performance. Simulation of the proposed scheme applied to nonlinear dynamic systems validates that WN-OSELM is superior in terms of identification accuracy and fast learning ability compared to NN-OSELM.

A development of self-tuning quantitative feedback theory

This paper presents a development of self-tuning Quantitative Feedback Theory (QFT) for a non linear system. QFT is one type of robust controller which deals with plant uncertainty. The performance of robust controller for any uncertain plant is guaranteed based on pre-defined specifications. Meanwhile, self-tuning controller is one type of adaptive controller which also meant to solve the same control problem, however for slower plant drift. By combining both adaptive and robust controllers, both robust and adaptive performance can be achieved. The proposed algorithm is tested on a chosen case study, grain dryer plant. Grain dryer is a non linear plant with uncertainty as the characteristics of the plant can be affected by environmental changes, manufacturing tolerance and input/output disturbance. Based on the results obtained from this case study, the superiority of the proposed self-tuning QFT has been proven. From the comparison test conducted between self-tuning and standard QFT-based controllers, the proposed method produced more desirable response in terms of faster settling time, less percentage of overshoot with reduced ringing, smaller control effort required and wider leverage of uncertainty range.

Effectiveness of a Participatory Ergonomics Intervention to Improve Musculoskeletal Health: A Solomon Four-Group Study Among Manufacturing Industry Workers in Selangor, Malaysia

The aim of this Solomon four-group study was to evaluate the effectiveness of participatory ergonomics (PE) intervention to improve musculoskeletal health among manufacturing industry workers. A total of 436 workers were randomly assigned into four groups. Intervention groups went through PE intervention while control groups went through hearing conservation programme. The main outcome measures were the prevalence and intensity of musculoskeletal pain at 9 body sites, collected by questionnaires at baseline (pretested groups) and 3 months after PE intervention (all groups). The study found that lower back has the highest prevalence rate of musculoskeletal disorders (MSD). There was significant lower prevalence rate of MSD at upper back, lower back and knee for intervention group as compared to control group. There was a significant main effect of PE intervention on the overall pain intensity at different body parts whether they are pretested or non-pretested. In conclusion, PE intervention had effectively improved musculoskeletal health among the respondents.

Implementation of high-gain observer on low-cost fused IR-OS sensor embedded in UAV system

This paper presents discrete time implementation of a high gain observer (HGO) and extended term to estimate the state velocity and acceleration from the position measured by a low-cost sensor installed on-board the unmanned aerial vehicle (UAV). Owing to the low-cost sensor, the signal produced from fused IR–OS is noisy and therefore, additional filters are used to remove the noise. This study proposes an alternative to this standard and tedious procedure using HGO. The discrete time implementation of HGO and its extended term is presented and ground tests are conducted to verify the algorithm by inducing a dynamic motion on the UAV platform embedded with the fusion IR-OS onboard. A comparison study is conducted using standard numerical differentiation and ground truth measurement by OptiTrack. The results show that EHGO can produce a velocity signal with the same quality as that of differentiated signal from fused IR-OS using Kalman filter. The novelty of HGO lies in its simplicity and its minimal tuning of parameters.

Investigation on self energized automated multi levels car parking system

This work proposes a method to enhance the green power demands through providing an energy source which utilizes the kinetic green energy of the vehicles in multi-level car parking building, where vehicles are already climbing when the driver looking for space to park, and then climb down to go out the building with a kinetic energy due to ground gravity. A novel mechanism has been designed to generate electric power in each individual level from the car parking building, this individuality not only would generate more energy but also simplified the system and reduce the installation cost. The simulation result shows a significant energy value which could cover the demand of the parking place from the electricity, such as lighting, ventilation, barrier gate and CCTV.

Simulated real time controller using modified hill climbing algorithm on fixed wing airplane

In dynamic systems, it is very difficult to have models with good accuracy that are sufficient to predict the plant behavior in a way that an acceptably controlled performance can be produced. Sometimes even if mathematical models are sufficiently accurate in a way that a good controlled performance can be obtained, long term operation (or even short term in some cases) gradually increases the difference between the plant and its dynamical model. That, in turn, would lead to a degraded performance. It is a common task in industrial applications to recalibrate the control system periodically, as the plant parameters suffer various fluctuations from their original values that were used in designing the control system. The calibration procedure usually requires professional attendance, which adds up to more maintenance costs. Also, the experimental nature of the manual calibration often requires at least part of the plant operations to be halted. Adapted from MRAC framework using PID and fuzzy controller, a modified climbing algorithm was introduced in order to compensate the signal. This simulation was applied in fixed-wing airplane pitch angle in Simulink MATLAB. The result demonstrated that effectiveness of the proposed tuning algorithm and improvement over the initial non-tuned response of the process.