Application of logistic regression for fault analysis in an industrial printing process

A statistical technique for fault analysis in industrial printing is reported. The method specifically deals with binary data, for which the results of the production process fall into two categories, rejected or accepted. The method is referred to as logistic regression, and is capable of predicting future fault occurrences by the analysis of current measurements from machine parts sensors. Individual analysis of each type of fault can determine which parts of the plant have a significant influence on the occurrence of such faults; it is also possible to infer which measurable process parameters have no significant influence on the generation of these faults. Information derived from the analysis can be helpful in the operator's interpretation of the current state of the plant. Appropriate actions may then be taken to prevent potential faults from occurring. The algorithm is being implemented as part of an applied self-learning expert system.

Power transmission network simulation for fault diagnosis

The authors discuss an implementation of an object oriented (OO) fault simulator and its use within an adaptive fault diagnostic system. The simulator models the flow of faults around a power network, reporting switchgear indications and protection messages that would be expected in a real fault scenario. The simulator has been used to train an adaptive fault diagnostic system; results and implications are discussed.

Rheology of milk foams produced by steam injection

Rheology of milk foams generated by steam injection was studied during the transient destabilization process using steady flow and dynamic oscillatory techniques: yield stress (τ_y) values were obtained from a stress ramp (0.2 to 25 Pa) and from strain amplitude sweep (0.001 to 3 at 1 Hz of frequency); elastic (G') and viscous (G") moduli were measured by frequency sweep (0.1 to 150 Hz at 0.05 of strain); and the apparent viscosity (η_a) was obtained from the flow curves generated from the stress ramp. The effect of plate roughness and the sweep time on τ_y was also assessed. Yield stress was found to increase with plate roughness whereas it decreased with the sweep time. The values of yield stress and moduli—G' and G"—increased during foam destabilization as a consequence of the changes in foam properties, especially the gas volume fraction, φ, and bubble size, R_32 (Sauter mean bubble radius). Thus, a relationship between τ_y, φ, R_32, and σ (surface tension) was established. The changes in the apparent viscosity, η, showed that the foams behaved like a shear thinning fluid beyond the yield point, fitting the modified Cross model with the relaxation time parameter (λ) also depending on the gas volume fraction. Overall, it was concluded that the viscoelastic behavior of the foam below the yield point and liquid-like behavior thereafter both vary during destabilization due to changes in the foam characteristics.

Fault tolerant decentralised K-Means clustering for asynchronous large-scale networks

The K-Means algorithm for cluster analysis is one of the most influential and popular data mining methods. Its straightforward parallel formulation is well suited for distributed memory systems with reliable interconnection networks, such as massively parallel processors and clusters of workstations. However, in large-scale geographically distributed systems the straightforward parallel algorithm can be rendered useless by a single communication failure or high latency in communication paths. The lack of scalable and fault tolerant global communication and synchronisation methods in large-scale systems has hindered the adoption of the K-Means algorithm for applications in large networked systems such as wireless sensor networks, peer-to-peer systems and mobile ad hoc networks. This work proposes a fully distributed K-Means algorithm (EpidemicK-Means) which does not require global communication and is intrinsically fault tolerant. The proposed distributed K-Means algorithm provides a clustering solution which can approximate the solution of an ideal centralised algorithm over the aggregated data as closely as desired. A comparative performance analysis is carried out against the state of the art sampling methods and shows that the proposed method overcomes the limitations of the sampling-based approaches for skewed clusters distributions. The experimental analysis confirms that the proposed algorithm is very accurate and fault tolerant under unreliable network conditions (message loss and node failures) and is suitable for asynchronous networks of very large and extreme scale.

Classification and fault detection methods for fuel cell monitoring and quality control

In this paper, various types of fault detection methods for fuel cells are compared. For example, those that use a model based approach or a data driven approach or a combination of the two. The potential advantages and drawbacks of each method are discussed and comparisons between methods are made. In particular, classification algorithms are investigated, which separate a data set into classes or clusters based on some prior knowledge or measure of similarity. In particular, the application of classification methods to vectors of reconstructed currents by magnetic tomography or to vectors of magnetic field measurements directly is explored. Bases are simulated using the finite integration technique (FIT) and regularization techniques are employed to overcome ill-posedness. Fisher's linear discriminant is used to illustrate these concepts. Numerical experiments show that the ill-posedness of the magnetic tomography problem is a part of the classification problem on magnetic field measurements as well. This is independent of the particular working mode of the cell but influenced by the type of faulty behavior that is studied. The numerical results demonstrate the ill-posedness by the exponential decay behavior of the singular values for three examples of fault classes.

Chapter 4: Simulation of reaction injection moulding

Reaction Injection Moulding is a technology that enables the rapid production of complex plastic parts directly from a mixture of two reactive materials of low viscosity. The reactants are mixed in specific quantities and injected into a mould. This process allows large complex parts to be produced without the need for high clamping pressures. This chapter explores the simulation of the complex processes involved in reaction injection moulding. The reaction processes mean that the dynamics of the material in the mould are in constant evolution and an effective model which takes full account of these changing dynamics is introduced and incorporated in to finite element procedures, which are able to provide a complete simulation of the cycle of mould filling and subsequent curing.

Production of milk foams by steam injection: the effects of steam pressure and nozzle design

Foam properties depend on the physico-chemical characteristics of the continuous phase, the method of production and process conditions employed; however the preparation of barista-style milk foams in coffee shops by injection of steam uses milk as its main ingredient which limits the control of foam properties by changing the biochemical characteristics of the continuous phase. Therefore, the control of process conditions and nozzle design are the only ways available to produce foams with diverse properties. Milk foams were produced employing different steam pressures (100-280 kPa gauge) and nozzle designs (ejector, plunging-jet and confined-jet nozzles). The foamability of milk, and the stability, bubble size and texture of the foams were investigated. Variations in steam pressure and nozzle design changed the hydrodynamic conditions during foam production, resulting in foams having a range of properties. Steam pressure influenced foam characteristics, although the net effect depended on the nozzle design used. These results suggest that, in addition to the physicochemical determinants of milk, the foam properties can also be controlled by changing the steam pressure and nozzle design.