Statistical inference for the lifetime performance index based on generalised order statistics from exponential distribution

In manufacturing industries, the lifetime of an item is usually characterised by a random variable X and considered to be satisfactory if X exceeds a given lower lifetime limit L. The probability of a satisfactory item is then η_L := P(X ≥ L), called conforming rate. In industrial companies, however, the lifetime performance index, proposed by Montgomery and denoted by C_L, is widely used as a process capability index instead of the conforming rate. Assuming a parametric model for the random variable X, we show that there is a connection between the conforming rate and the lifetime performance index. Consequently, the statistical inferences about η_L and C_L are equivalent. Hence, we restrict ourselves to statistical inference for C_L based on generalised order statistics, which contains several ordered data models such as usual order statistics, progressively Type-II censored data and records. Various point and interval estimators for the parameter C_L are obtained and optimal critical regions for the hypothesis testing problems concerning C_L are proposed. Finally, two real data-sets on the lifetimes of insulating fluid and ball bearings, due to Nelson (1982) Nelson, W. (1982), Applied Life Data Analysis, New York: John Wiley &; Sons.[Crossref] , [Google Scholar] and Caroni (2002) Caroni, C. (2002), ‘The correct “ball bearings” data’, Lifetime Data Analysis, 8, 395–399.[Crossref], [PubMed], [Web of Science ®] , [Google Scholar], respectively, and a simulated sample are analysed.     

A survey: hybrid evolutionary algorithms for cluster analysis

Clustering is a popular data analysis and data mining technique. It is the unsupervised classification of patterns into groups. Many algorithms for large data sets have been proposed in the literature using different techniques. However, conventional algorithms have some shortcomings such as slowness of the convergence, sensitive to initial value and preset classed in large scale data set etc. and they still require much investigation to improve performance and efficiency. Over the last decade, clustering with ant-based and swarm-based algorithms are emerging as an alternative to more traditional clustering techniques. Many complex optimization problems still exist, and it is often very difficult to obtain the desired result with one of these algorithms alone. Thus, robust and flexible techniques of optimization are needed to generate good results for clustering data. Some algorithms that imitate certain natural principles, known as evolutionary algorithms have been used in a wide variety of real-world applications. Recently, much research has been proposed using hybrid evolutionary algorithms to solve the clustering problem. This paper provides a survey of hybrid evolutionary algorithms for cluster analysis.     

Simultaneous coordination of order quantity and reorder point in a two-stage supply chain

In this paper, we investigate the simultaneous coordination of order quantity and reorder point in a two-stage supply chain (SC). While coordination of order quantity has received much attention in the supply chain management literature, coordination of the reorder point has been less-studied. The retailer's reorder point has a direct impact on product availability and customer service level (CSL) and therefore has a great impact on SC profitability. Our proposed model adopts a two-stage SC with stochastic demand and lead times over multiple periods. The proposed coordination model assures global optimization of order quantity–reorder point decisions. Using a pricing scheme with a discount factor, we extract conditions in which both downstream and upstream members have sufficient motivation to participate in the coordination scheme. Numerical experiments demonstrate that the proposed model can achieve channel coordination. Results of the modeling and analyses show that coordination of both reorder point and order quantity can lead to increased SC profitability as well as CSL improvement.     

Multidisciplinary design of a small satellite launch vehicle using particle swarm optimization

In the present paper, particle swarm optimization, a relatively new population based optimization technique, is applied to optimize the multidisciplinary design of a solid propellant launch vehicle. Propulsion, structure, aerodynamic (geometry) and three-degree of freedom trajectory simulation disciplines are used in an appropriate combination and minimum launch weight is considered as an objective function. In order to reduce the high computational cost and improve the performance of particle swarm optimization, an enhancement technique called fitness inheritance is proposed. Firstly, the conducted experiments over a set of benchmark functions demonstrate that the proposed method can preserve the quality of solutions while decreasing the computational cost considerably. Then, a comparison of the proposed algorithm against the original version of particle swarm optimization, sequential quadratic programming, and method of centers carried out over multidisciplinary design optimization of the design problem. The obtained results show a very good performance of the enhancement technique to find the global optimum with considerable decrease in number of function evaluations.     

Visual domain adaptation via transfer feature learning

One of the serious challenges in computer vision and image classification is learning an accurate classifier for a new unlabeled image dataset, considering that there is no available labeled training data. Transfer learning and domain adaptation are two outstanding solutions that tackle this challenge by employing available datasets, even with significant difference in distribution and properties, and transfer the knowledge from a related domain to the target domain. The main difference between these two solutions is their primary assumption about change in marginal and conditional distributions where transfer learning emphasizes on problems with same marginal distribution and different conditional distribution, and domain adaptation deals with opposite conditions. Most prior works have exploited these two learning strategies separately for domain shift problem where training and test sets are drawn from different distributions. In this paper, we exploit joint transfer learning and domain adaptation to cope with domain shift problem in which the distribution difference is significantly large, particularly vision datasets. We therefore put forward a novel transfer learning and domain adaptation approach, referred to as visual domain adaptation (VDA). Specifically, VDA reduces the joint marginal and conditional distributions across domains in an unsupervised manner where no label is available in test set. Moreover, VDA constructs condensed domain invariant clusters in the embedding representation to separate various classes alongside the domain transfer. In this work, we employ pseudo target labels refinement to iteratively converge to final solution. Employing an iterative procedure along with a novel optimization problem creates a robust and effective representation for adaptation across domains. Extensive experiments on 16 real vision datasets with different difficulties verify that VDA can significantly outperform state-of-the-art methods in image classification problem.     

Robust adaptive actuator failure compensation for a class of uncertain nonlinear systems

This paper presents a robust adaptive state feedback control scheme for a class of parametric-strict-feedback nonlinear systems in the presence of time varying actuator failures. The designed adaptive controller compensates a general class of actuator failures without any need for explicit fault detection. The parameters, times, and patterns of the considered failures are completely unknown. The proposed controller is constructed based on a backstepping design method. The global boundedness of all the closed-loop signals is guaranteed and the tracking error is proved to converge to a small neighborhood of the origin. The proposed approach is employed for a two-axis positioning stage system as well as an aircraft wing system. The simulation results show the correctness and effectiveness of the proposed robust adaptive actuator failure compensation approach.     

Investigation on Effect of Magnetic Field Dependency Coefficient of Critical Current Density on the AC Magnetizing Loss in HTS Tapes Exposed to External Field

High-temperature superconducting (HTS) technology is the most promising, advanced, and beneficial technological developments of the last two decades in terms of fabricating more efficient, compact, and reliable electrical power apparatus. The second-generation HTS wires are now quite competitive with traditional conductors from the cost point of view. In addition, they are of high interest in electrical machine manufacturing due to their unique merits such as high current density, high magnetic field, and low loss. The most significant issue for any superconducting devices which work with alternating current or magnetic field is the AC loss of the HTS tapes. Since HTS tapes are always exposed to an external magnetic field in electrical machine applications, it is vital to consider the effect of this external field on their AC magnetizing (ACMG) loss. It is well-known that external magnetic field decreases the current carrying capability of the wire. In real life, critical current density of HTS tapes is dependent to magnetic field but this dependency sometime was not considered in modeling stage in order to make it faster and simple. In this paper, the electromagnetic properties of HTS tapes for use in superconducting electric machines have been investigated with a particular focus on the ACMG loss of YBCO tapes. For this purpose, a two-dimensional finite element model has been implemented based on the H formulation in order to study the effect of dependency of critical current density to magnetic field on the variation of ACMG loss. The modeling results will be helpful for electrical machine designers to have a better understanding about this effect and have a more accurate estimate of ACMG loss in design stage.     

Multiaxial fatigue of extruded ZK60 magnesium alloy

Multiaxial monotonic and cyclic behaviors of ZK60‐T5 magnesium extrusion are investigated. Strain‐controlled tests were performed at standard laboratory condition with fully reversed straining. Twinning‐detwinning deformation plays an important role in the cyclic axial behavior for tests that were performed under strain amplitudes higher than 0.4%. However, the hysteresis loop for the 0.4% was found symmetric and no sign of twinning‐detwinning deformation was observed. On the contrary, the cyclic shear behavior was found to be similar to conventional alloys and no significant asymmetric or twinning‐detwinning deformations were observed. The multiaxial fatigue tests suggest that multiaxiality and nonproportionality are not detrimental to fatigue life. Three multiaxial fatigue damage models were used: Smith‐Watson‐Topper, Fatemi‐Socie, and Jahed‐Varvani. While Fatemi‐Socie and Jahed‐Varvani models show comparable estimation, Smith‐Watson‐Topper overestimates shear and nonproportional lives.     

Robust nonlinear control of atomic force microscope via immersion and invariance

This paper reports an immersion and invariance (I&I)–based robust nonlinear controller for atomic force microscope (AFM) applications. The AFM dynamics is prone to chaos, which, in practice, leads to performance degradation and inaccurate measurements. Therefore, we design a nonlinear tracking controller that stabilizes the AFM dynamics around a desired periodic orbit. To this end, in the tracking error state space, we define a target invariant manifold, on which the system dynamics fulfills the control objective. First, considering a nominal case with full state measurement and no modeling uncertainty, we design an I&I controller to render the target manifold exponentially attractive. Next, we consider an uncertain AFM dynamics, in which only the displacement of the probe cantilever is measured. In the framework of the I&I method, we recast the robust output feedback control problem as the immersion of the output feedback closed‐loop system into the nominal full state one. For this purpose, we define another target invariant manifold that recovers the performance of the nominal control system. Moreover, to handle large uncertainty/disturbances, we incorporate the method of active disturbance rejection into the I&I output feedback control. Through Lyapunov‐based analysis of the closed‐loop stability and robustness, we show the semiglobal practical stability and convergence of the tracking error dynamics. Finally, we present a set of detailed, comparative software simulations to assess the effectiveness of the control method.