Vibration analysis is widely used as an efficient condition monitoring (CM) tool for rotating machines in various industries. Fault detection and diagnosis (FDD) models play an important role in the development of any CM system. The use of artificial intelligence (AI) has since gained recognition in the development of fault detection and diagnosis systems. In this paper, a combination of principal component analysis (PCA) which is used for reducing the data dimensionality, and support vector machine (SVM) which is adopted for classification to carry out fault detection and diagnosis of faults in bearings using vibrations. The diagnostic feature design and machine learning toolbox in MATLAB are used to develop features and train the models, respectively. Real data from the Mendeley data depository is used to test and evaluate the models. Model training is carried out using data with varying speeds representing different conditions of bearing making it different from similar approaches involving SVM. The choice of data used proves that SVM can be able to classify faults with consideration of the varying operating speeds. Results have shown that the combination of PCA and SVM is effective in fault diagnosis of bearing faults under varying speeds such that a 97.4% classification accuracy was achieved. The result implies that PCA and SVM can be implemented in various industrial setups where variable speeds can occur both intentionally or nonintentionally. Furthermore, the method was able to differentiate between compounding faults and faults that occur at different times. The confusion matrix further proves the quality and accuracy of the trained model. Future work will focus on the development of models that can carry out the prognosis of faults in bearings as well as to model for other faults other than bearing faults.

The most challenging issue in the design of wireless sensor networks for the application of localization in the underground environment, mostly for miner’s location, is the sensor nodes’ energy consumption, efficiency and communication. Underground Wireless Sensor Networks are active and promising area of application of Wireless Sensor Networks (WSNs), whereby sensor nodes perform sensing duties in the underground environment. Most of the communication techniques used in the underground environment experience a high path loss and hence, hinders the range needed for transmission. However, the available option to increase information transmission is to increase the transmission power which needs large size of apparatus which is also limited in the underground. To solve the mentioned problems, this paper proposed a Magnetic Induction based Pulse Power. Analytical results of the Magnetic Induction based Pulse Power with an ordinary magnetic induction communication technique show an improvement in Signal-to-Noise Ratio (SNR) and path loss with variation in distance between nodes and frequency of operation. This paper further formulates a nonlinear program to determine the optimal data (events) extraction in a grid based WUSNs.

This study evaluates different control algorithms used in a hydroponic farming system to improve the quality of farm produce and resource efficiency. It focuses on three key hydroponic control parameters(potential hydrogen (pH), water level, and temperature control). Mathematical models are derived from the literature to represent hydroponic environments. These models are used for simulation purposes in MATLAB software to implement various control algorithms to evaluate their performance against each other and the system requirements utilizing transient performance parameters. Transient performance parameters are overshoot, settling time, rise time ,and steady-state error. The various control algorithms are fuzzy logic (FL), Proportional Integral Derivative (PID), and Proportional Integral Derivative-Fuzzy logic controller (PID-FL). This paper examines the performance of the hybrid PID-FL controllers compared to the most commonly used fuzzy logic and PID controllers. The result of the work shows that PID-FL is generally better for all the system models, making it more applicable.

The practical near impossibility of empirical attempts in estimating optimal controller gains makes the use of metaheuristics strategies inevitable to automatically obtain these gains by an iterative, heuristic simulation procedure. The convergence of the gains values to the local or global solutions occur with ease. In designing controllers for the Twin-Rotor MIMO System (TRMS), Jumping Spider Optimization Algorithm (JSOA), a novel neoteric population-based bio-inspired metaheuristic approach is used to obtain optimum values for the Proportional, Integral and Derivative (PID) controllers. With the k,p,i controller gains as the decision variables, the JSOA solution to a nonlinear multi-objective optimization problem subject to some intrinsic constraints spawned optimal values for the controllers’ variables. Counter to other algorithms (deterministic and stochastic) that get caught in local minima, JSOA evolved a solution after searchingly rummaging the entire solution search space in a vectorized fashion for an optimal value. Compared with several other versatile controllers (using GA, PSO, Pattern Search and Simulated Annealing), statistical results obtained showed JSOA technique provided a unique solution and found the gains of the PID controllers, marginally in relation to the others like optimization methods.