Machine Learning for Predictive Maintenance: A Multiple Classifiers Approach

In this paper a multiple classifier machine learning methodology for Predictive Maintenance (PdM) is presented. PdM is a prominent strategy for dealing with maintenance issues given the increasing need to minimize downtime and associated costs. One of the challenges with PdM is generating so called ’health factors’ or quantitative indicators of the status of a system associated with a given maintenance issue, and determining their relationship to operating costs and failure risk. The proposed PdM methodology allows dynamical decision rules to be adopted for maintenance management and can be used with high-dimensional and censored data problems. This is achieved by training multiple classification modules with different prediction horizons to provide different performance trade-offs in terms of frequency of unexpected breaks and unexploited lifetime and then employing this information in an operating cost based maintenance decision system to minimise expected costs. The effectiveness of the methodology is demonstrated using a simulated example and a benchmark semiconductor manufacturing maintenance problem.

COD and NH4-N Estimation in the Inflow of Wastewater Treatment Plants using Machine Learning Techniques

The in-line measurement of COD and NH4-N in the WWTP inflow is crucial for the timely monitoring of biological wastewater treatment processes and for the development of advanced control strategies for optimized WWTP operation. As a direct measurement of COD and NH4-N requires expensive and high maintenance in-line probes or analyzers, an approach estimating COD and NH4-N based on standard and spectroscopic in-line inflow measurement systems using Machine Learning Techniques is presented in this paper. The results show that COD estimation using Radom Forest Regression with a normalized MSE of 0.3, which is sufficiently accurate for practical applications, can be achieved using only standard in-line measurements. In the case of NH4-N, a good estimation using Partial Least Squares Regression with a normalized MSE of 0.16 is only possible based on a combination of standard and spectroscopic in-line measurements. Furthermore, the comparison of regression and classification methods shows that both methods perform equally well in most cases.

An Adaptive Machine Learning Decision System for Flexible Predictive Maintenance

Process monitoring and Predictive Maintenance (PdM) are gaining increasing attention in most manufacturing environments as a means of reducing maintenance related costs and downtime. This is especially true in industries that are data intensive such as semiconductor manufacturing. In this paper an adaptive PdM based flexible maintenance scheduling decision support system, which pays particular attention to associated opportunity and risk costs, is presented. The proposed system, which employs Machine Learning and regularized regression methods, exploits new information as it becomes available from newly processed components to refine remaining useful life estimates and associated costs and risks. The system has been validated on a real industrial dataset related to an Ion Beam Etching process for semiconductor manufacturing.

Levels of Arsenic and Other Trace Elements in Southern Libyan Agricultural Irrigated Soil and Non-irrigated Soil Projects

The levels of As and various other trace elements found in the irrigated agricultural soil (Tsoil) of southern Libya were compared with non-irrigated soil (Csoil) from the same sampling campaign collected between April and May 2008. The soil samples represented agronomic practice in the southern Libyan regions of Maknwessa (MAK), Aril (ARL) and Taswaa (TAS), and were analyzed by Inductively coupled plasma mass spectrometry (ICP-MS) for Co, Ni, Cu, Se, Mo, Zn, As, Pb, Cd and P. Concentrations of P and As in TAS and MAK were found to be higher in Tsoil compared to Csoil, while the opposite was true for ARL. In general, As concentrations in these areas were 2-3 times lower than the global average. In ARL, the average P concentrations of the Csoil samples were significantly higher than those of Tsoil samples: this site is composed mainly of pasture for animal production, where phosphate fertilizers are used regularly. Distance from the source of irrigation was found to be of an important influence on the heavy metal concentration of the soil, with greater concentrations found closer to the irrigation source. It can be concluded from the results that irrigation water contains elevated levels of As, which finds its way into the soil profile and can lead to accumulation of As in the soil over time.

DFIG Machine Design for Maximizing Power Output Based on Surrogate Optimization Algorithm

This paper presents a surrogate-model based optimization of a doubly-fed induction generator (DFIG) machine winding design for maximizing power yield. Based on site-specific wind profile data and the machine’s previous operational performance, the DFIG’s stator and rotor windings are optimized to match the maximum efficiency with operating conditions for rewinding purposes. The particle swarm optimization (PSO)-based surrogate optimization techniques are used in conjunction with the finite element method (FEM) to optimize the machine design utilizing the limited available information for the site-specific wind profile and generator operating conditions. A response surface method in the surrogate model is developed to formulate the design objectives and constraints. Besides, the machine tests and efficiency calculations follow IEEE standard 112-B. Numerical and experimental results validate the effectiveness of the proposed technologies.

Neoliberalism, the University, Public Goods, and Agricultural Innovation

After World War II, most industrialising nations adopted some form of welfare-state approach to balance the economic activities of self-interested agents and social welfare. In the realm of scientific research and innovation, this often meant that governments took primary responsibility for funding public research organisations, including research universities and government laboratories. Over the past four decades, however, the significance of private funding for agricultural research has increased, and academic scientists now often work in public-private partnerships. We argue that this trend needs to be carefully monitored because public goods are likely to be overlooked and undervalued in such arrangements. In the interest of developing indicators to monitor the trend, we document public and private funding for agricultural research and agricultural innovation in four countries: the USA, the UK, Ireland and Germany. Our results show that although neoliberalism is evident in each country, it is not homogeneous in its application and impacts, suggesting that national and institutional contexts matter. This article is directed at stimulating debates on the relationships between university research, agricultural innovation and public goods.