Vibration-Based Smart Sensor for High-Flow Dust Measurement.

Asphalt mixes comprise aggregates, additives and bitumen. The aggregates are of varying sizes, and the finest category, referred to as sands, encompasses the so-called filler particles present in the mixture, which are smaller than 0.063 mm. As part of the H2020 CAPRI project, the authors present a prototype for measuring filler flow, through vibration analysis. The vibrations are generated by the filler particles crashing to a slim steel bar capable of withstanding the challenging conditions of temperature and pressure within the aspiration pipe of an industrial baghouse. This paper presents a prototype developed to address the need for quantifying the amount of filler in cold aggregates, considering the unavailability of commercially viable sensors suitable for the conditions encountered during asphalt mix production. In laboratory settings, the prototype simulates the aspiration process of a baghouse in an asphalt plant, accurately reproducing particle concentration and mass flow conditions. The experiments performed demonstrate that an accelerometer positioned outside the pipe can replicate the filler flow within the pipe, even when the filler aspiration conditions differ. The obtained results enable extrapolation from the laboratory model to a real-world baghouse model, making it applicable to various aspiration processes, particularly those involving baghouses. Moreover, this paper provides open access to all the data and results used, as part of our commitment to the CAPRI project, with the principles of open science.

An SVM-based solution for fault detection in wind turbines.

Research into fault diagnosis in machines with a wide range of variable loads and speeds, such as wind turbines, is of great industrial interest. Analysis of the power signals emitted by wind turbines for the diagnosis of mechanical faults in their mechanical transmission chain is insufficient. A successful diagnosis requires the inclusion of accelerometers to evaluate vibrations. This work presents a multi-sensory system for fault diagnosis in wind turbines, combined with a data-mining solution for the classification of the operational state of the turbine. The selected sensors are accelerometers, in which vibration signals are processed using angular resampling techniques and electrical, torque and speed measurements. Support vector machines (SVMs) are selected for the classification task, including two traditional and two promising new kernels. This multi-sensory system has been validated on a test-bed that simulates the real conditions of wind turbines with two fault typologies: misalignment and imbalance. Comparison of SVM performance with the results of artificial neural networks (ANNs) shows that linear kernel SVM outperforms other kernels and ANNs in terms of accuracy, training and tuning times. The suitability and superior performance of linear SVM is also experimentally analyzed, to conclude that this data acquisition technique generates linearly separable datasets.

A virtual sensor for online fault detection of multitooth-tools.

The installation of suitable sensors close to the tool tip on milling centres is not possible in industrial environments. It is therefore necessary to design virtual sensors for these machines to perform online fault detection in many industrial tasks. This paper presents a virtual sensor for online fault detection of multitooth tools based on a bayesian classifier. The device that performs this task applies mathematical models that function in conjunction with physical sensors. Only two experimental variables are collected from the milling centre that performs the machining operations: the electrical power consumption of the feed drive and the time required for machining each workpiece. The task of achieving reliable signals from a milling process is especially complex when multitooth tools are used, because each kind of cutting insert in the milling centre only works on each workpiece during a certain time window. Great effort has gone into designing a robust virtual sensor that can avoid re-calibration due to, e.g., maintenance operations. The virtual sensor developed as a result of this research is successfully validated under real conditions on a milling centre used for the mass production of automobile engine crankshafts. Recognition accuracy, calculated with a k-fold cross validation, had on average 0.957 of true positives and 0.986 of true negatives. Moreover, measured accuracy was 98%, which suggests that the virtual sensor correctly identifies new cases.