Fault Diagnosis of Rotary Machines Using Deep Convolutional Neural Network with Wide Three Axis Vibration Signal Input.

Fault diagnosis is considered as an essential task in rotary machinery as possibility of an early detection and diagnosis of the faulty condition can save both time and money. This work presents developed and novel technique for deep-learning-based data-driven fault diagnosis for rotary machinery. The proposed technique input raw three axes accelerometer signal as high definition 1D image into deep learning layers which automatically extract signal features, enabling high classification accuracy.

PID controller auto-tuning based on process step response and damping optimum criterion.

This paper presents a novel method of PID controller tuning suitable for higher-order aperiodic processes and aimed at step response-based auto-tuning applications. The PID controller tuning is based on the identification of so-called n-th order lag (PTn) process model and application of damping optimum criterion, thus facilitating straightforward algebraic rules for the adjustment of both the closed-loop response speed and damping. The PTn model identification is based on the process step response, wherein the PTn model parameters are evaluated in a novel manner from the process step response equivalent dead-time and lag time constant.

Modeling and control of a pneumatically actuated inverted pendulum.

This paper presents the results of modeling of an inverted pendulum system driven by a linear pneumatic motor and equipped with relatively low-cost potentiometer-based position measurement system. Based on the nonlinear model of the overall pendulum system, which also includes notable friction effects, a linearized model is derived. The linearized model is used as a basis for the design of state feedback controller based on LQ and LQG optimization procedures.