AbstractAccurate capacity estimation and degradation trajectory predictions are crucial part of effectively monitoring the current and future health status of lithium‐ion batteries, which ensures their optimal performance and longevity. However, it is hard to acquire precise predictions under various application conditions when relying on limited historical data. In this paper, we propose a novel deep time‐index framework based on meta‐learning to achieve online capacity estimation and degradation trajectory predictions with only a few monitoring data from early cycles. Highly correlated health feature from lithium‐ion battery degradation data is extracted for online capacity estimation. The deep time‐index framework consists of three parts, Implicit Neural Representations (INRs), Long Short‐Term Memory (LSTM) and Ridge regressor. Cycle numbers are selected as time feature and fed into the INRs to obtain informative representations. A LSTM module is employed to process the temporal representations and capture the long‐term dependencies to Ridge regressor to generate a direct multi‐step predictions. Three distinct lithium‐ion battery degradation datasets are applied to validate the efficacy of the proposed approach. The experimental results validate that within the deep time‐index framework, the short‐term predictions show remarkable performance. This high level of accuracy makes the proposed deep time‐index framework suitable for a wide range of real‐world scenarios, as it demonstrates precise predictions even under varying charging and discharging conditions with limited historical data.

AbstractThe Cognitive Reliability and Error Analysis Method (CREAM) represents one of the second‐generation approaches to human reliability assessment, taking into account the influence of environmental conditions on human error probability (HEP). In the context of CREAM, the Common Performance Conditions (CPCs) influence error probabilities. Since not all CPCs have equal impacts, this study employs the Bayesian Best Worst Method (BWM), a novel approach in group decision‐making, to assign weights to these factors. Subsequently, two techniques based on basic CREAM are proposed. The current control mode is determined in the first technique according to the experts' opinions. Then the probability of human error is calculated based on the amount of control. It is possible to provide solutions for improving control mode, based on obtained results. Therefore, in this study, the second method has been used to make suggestions to enhance human reliability. For this purpose, in the second technique, an optimization problem is formulated to select the best applicable programs for managers to enhance human reliability. The proposed bi‐objective model tries to increase the reliability of human resources by reducing human error and costs. The proposed bi‐objective model seeks to bolster the reliability of human resources by concurrently minimizing HEP and associated costs. The efficiency of the presented methods is verified through a case study in the control room of the cement factory. The results of the first technique reveal an opportunistic control mode with a corresponding HEP of 0.0198. On the other hand, the outcomes of our proposed model underscore the greater impact of improving CPC levels in reducing the probability of human error. Ultimately, the practical programs derived from our mathematical model provide decision‐makers with valuable insights to reduce the probability of human error to a mere 0.000172 through the transition from opportunistic to strategic control.

AbstractIn this paper, a novel approach to a Bayesian accelerated life testing model is presented. The Weibull distribution is used as the life distribution and the generalized Eyring model as the time transformation function. This is a model that allows for the use of more than one stressor, whereas other commonly used acceleration models, such as the Arrhenius and power law models, incorporate one stressor. The use of the generalized Eyring‐Weibull model developed in this paper is demonstrated in a case study, where Markov chain Monte Carlo methods are utilized to generate samples for posterior inference.

AbstractThis paper proposes a more computationally efficient approach for resilience assessment of rail transit system under disruptions. An improved linear programming model is developed to depict commuter flows and estimate system statuses. To address the computational challenge caused by the complexity of system, a four‐step approach is proposed based on the proposed commuter flow model. In the first step, Origin‐Destination (OD) pairs are divided into smaller groups and their flows under normal conditions are estimated by the proposed model separately, with the assumption that the railway capacity is sufficient relative to demand. Next, overall system statuses under normal conditions, including commuters on each train and spare capacities of each train are calculated by integrating results obtained in the first step. In the third step, system statuses under disruptions are estimated. In this step, we assume that unaffected commuters will not change their routes and flows of all affected commuters are estimated by a modified commuter model with given spare space of trains. Based on these outputs, several critical measures are introduced and calculated to quantify the resilience, resistance, and recovery ability of rail network systematically. We also demonstrate how our approach could be used to facilitate design and evaluation of bus bridging service. The proposed approach is demonstrated on the core part of Hangzhou rail transit network.

AbstractThe mission success probability (MSP) is a critical indicator for phased mission systems (PMSs). In the modern aerospace industry, redundancy techniques, including component/phase redundancy, are commonly seen to increase the MSP of the whole system. These component/phase redundancies make the reliability analysis more complex. Meanwhile, one or more components are required for normal working for different subsystems, called the K/N structure. In this article, a Markov‐process method is proposed for PMS with K/N subsystems and different redundancy strategies. Then, a universal system optimization model is proposed to optimize system structure and redundancy strategies for all subsystems at the same time. Then, an improved genetic algorithm (GA) is used to resolve the optimization problem. At last, a propulsion system is used as an engineering case, showing the proposed binary decision diagram‐based method.

AbstractRisk‐adjusted control charts have been widely used in monitoring surgical quality in detecting risks of surgical performance. Most of the previous approaches focus on shifts in the location parameter as well as the existence of the scale parameter, which cannot get the full measure of the scale parameter under different levels. Ignoring the magnitude of the scale parameter, the monitoring methods cannot detect different variations of surgical mortality that is measured by scale parameter and required to reflect surgical quality improvement. The method of detecting variations in surgical quality is of interest in surgical quality improvement. This paper uses a new weighted h‐likelihood method to obtain a weighted score test for the surgical risks from the logistic model. Then an exponentially weighted moving average chart can be constructed to monitor the changes in the variance of risks, which could be of interest in practical surgical monitoring programs. Simulation results indicate that the proposed approach performs more efficiently than existing methods under various magnitudes of shifts in scale parameters on top of different pre‐set threshold stability. In addition, the application of the proposed method to real surgical data from the Surgical Outcome Monitoring and Improvement Program in Hong Kong shows the improvement and deterioration in a hospital's outcomes.

AbstractDrive circuit is a critical part of instrumentation and control systems in nuclear reactors, and its performance directly influences the operation of nuclear reactors. However, comparing with the open circuit IGBT faults, soft faults caused by the degradation of electronic components present much slighter fluctuations to the performance of drive circuits. If the two fault modes co‐exist, traditional fault diagnosis models are prone to misclassify soft faults as the normal condition. To improve the accuracy of fault diagnosis of drive circuits, it necessitates to accurately locate the faults of drive circuits, while effectively extracting the distinguishable fault features is one of the critical factors for fault location. In this article, a fault location method combining the empirical modal decomposition (EMD) algorithm and sparse convolutional autoencoder (SCAE) is proposed. The EMD algorithm is applied to decompose the three‐phase current signals of drive circuits. An SCAE‐based feature extractor is constructed to capture high‐dimensional and sparse fault feature data with the aid of the powerful feature autonomic extraction capability of deep learning. A deep classifier is designed to locate faults in the driver circuit. A fault simulation model of the drive circuit is developed and the monitor data is collected. The effectiveness of the proposed method is validated via a real case of drive circuit in nuclear reactors.

AbstractThe probability life distributions usually describe the time to event or survival time. Therefore, these life distributions play a crucial role in the analysis and projection of the maximum life expectancy using the Laplace transform technique for nonparametric hypothesis testing. A flexible framework for monitoring randomized clinical trials utilizing prior knowledge of certain phenomena under uncertainty is provided by the Laplace transform. By considering the previous data, medical professionals can also utilize these estimators to calculate the chance of tumor recurrence, cardiovascular death, and AIDS for HIV patients. However, censoring occurs in clinical trials and medical studies when the precise event's time of occurrence is unknown. The present study aims to propose a new test for exponential better than used (EBU). The suggested statistical test's efficiency and critical values are computed and compared with those of previous classes. Furthermore, the suggested test statistic is provided in bivariate form as well. Finally, the methodology is then tested using medical data in order to provide evidence that it is applied efficiently.

AbstractA two‐sided nonparametric sequential probability ratio test (SPRT) control chart for process location is proposed. The mechanism of this chart is based on the SPRT for location based on the signs of the sequential observations that is extended for a two‐sided alternative hypothesis. Approximate expressions that relate the statistical performance measures of this chart with that of its corresponding one‐sided charts are obtained through a simulation study and are shown to be quite accurate. Furthermore, an approach to design the proposed chart is provided. The statistical performance of the proposed chart is numerically compared to that of the two‐sided Shewhart, cumulative sum, and exponentially weighted moving average sign charts for location and it is observed that in general the proposed chart significantly outperforms these charts for detecting a location shift of any size. An example is provided to illustrate the mechanism of the proposed chart. Also, the chart is extended for monitoring process dispersion.