A study on negative binomial inspection for imperfect production systems

Production systems continuously deteriorate with age and usage due to corrosion, fatigue, and cumulative wear in production processes, resulting in an increasing possibility of producing defective products. To prevent selling defective products, inspection is usually carried out to ensure that the performance of a sold product satisfies the customer requirements. Nevertheless, some defective products may still be sold in practice. In such a case, warranties are essential in marketing products and can improve the unfavorable image by applying higher product quality and better customer service. The purpose of this paper is to provide manufacturers with an effective inspection strategy in which the task of quality management is performed under the considerations of related costs for production, sampling, inventory, and warranty. A Weibull power law process is used to describe the imperfection of the production system, and a negative binomial sampling is adopted to learn the operational states of the production process. A free replacement warranty policy is assumed in this paper, and the reworking of defective products before shipment is also discussed. A numerical application is employed to demonstrate the usefulness of the proposed approach, and sensitivity analyses are performed to study the various effects of some influential factors.     

Intra-supply chain system with multiple sales locations and quality assurance

The emergence of the global economy has transformed the interdepartmental nature of a transnational enterprise into a highly collaborative oriented team. This transformation enables the enterprise to lower its transaction and coordination costs and increase its competitive advantage in the global market. This study investigates such a so-called intra-supply chain system that exists in present-day transnational firms, wherein a single production unit manufactures products to meet the demands of multiple regional sales offices and incorporates quality assurance in its production. The objective of the present study is to determine an optimal production quantity and shipment policy that minimizes the integrated production–inventory–delivery costs for the intra-supply chain system. In this study, considerations related to a product’s quality assurance include inspection for quality, rework of defective items and failure in rework. Delivery of the finished products starts when quality of the entire production lot is assured. Multi-shipment policy is used to synchronously transport finished items to multiple locations for satisfying customer demands in each cycle. Mathematical modeling along with Hessian matrix equations is employed to solve the proposed intra-supply chain system. A numerical example with a discussion and cost-benefit analysis of outsourcing work to an external distributor is presented to demonstrate the practical applicability of the obtained results.     

A dispatching rule for photolithography scheduling with an on-line rework strategy

Generally speaking, wafer fabrication factories define the photolithography area as the dispatching center of the entire factory. To establish a set of operative dispatching rules in the photolithography area while taking into consideration the rework of defective products would assist in coordinating and balancing the workload of the entire production line. Furthermore, it would help to enhance both the productivity and efficiency of the wafer fabrication, reduce the on-line WIP stock, shorten the production cycle time, and satisfy the requirements of customers regarding production due time and product quality. This research uses on-line rework as the basis for bringing the factor of reworking of a batch process into the dispatching rule for measurement. It then develops the dispatching rule (Rw-DR) which includes the rework strategy. In addition, this research focuses on the batch with high finished proportion in the photolithography area for finding a way to complete the manufacturing procedure faster, lighten the machine workload of the waiting line, and at the same time increase the output quantity.     

Multi-product production quantity model with repair failure and partial backordering

In this paper, a production quantity model with random defective items, service level constraints and repair failure is studied. The existence of only one machine results in limited production capacity and partial backordering. The aim of this research is to determine the optimal cycle length, optimal production quantity and optimal backordered quantity of each product such that the expected total cost (holding, shortage, production, setup, defective items and repair costs) is minimized. Two numerical examples and sensitivity analysis are provided to illustrate the practical usage of the proposed method.     

An improved collaborative movie recommendation system using computational intelligence

Recommendation systems have become prevalent in recent years as they dealing with the information overload problem by suggesting users the most relevant products from a massive amount of data. For media product, online collaborative movie recommendations make attempts to assist users to access their preferred movies by capturing precisely similar neighbors among users or movies from their historical common ratings. However, due to the data sparsely, neighbor selecting is getting more difficult with the fast increasing of movies and users. In this paper, a hybrid model-based movie recommendation system which utilizes the improved K-means clustering coupled with genetic algorithms (GAs) to partition transformed user space is proposed. It employs principal component analysis (PCA) data reduction technique to dense the movie population space which could reduce the computation complexity in intelligent movie recom-mendation as well. The experiment results on Movielens dataset indicate that the proposed approach can provide high performance in terms of accuracy, and generate more reliable and personalized movie recommendations when compared with the existing methods.     

Scalable prediction of non-functional properties in software product lines: Footprint and memory consumption

ContextA software product line is a family of related software products, typically created from a set of common assets. Users select features to derive a product that fulfills their needs. Users often expect a product to have specific non-functional properties, such as a small footprint or a bounded response time. Because a product line may have an exponential number of products with respect to its features, it is usually not feasible to generate and measure non-functional properties for each possible product.ObjectiveOur overall goal is to derive optimal products with respect to non-functional requirements by showing customers which features must be selected.MethodWe propose an approach to predict a product’s non-functional properties based on the product’s feature selection. We aggregate the influence of each selected feature on a non-functional property to predict a product’s properties. We generate and measure a small set of products and, by comparing measurements, we approximate each feature’s influence on the non-functional property in question. As a research method, we conducted controlled experiments and evaluated prediction accuracy for the non-functional properties footprint and main-memory consumption. But, in principle, our approach is applicable for all quantifiable non-functional properties.ResultsWith nine software product lines, we demonstrate that our approach predicts the footprint with an average accuracy of 94%, and an accuracy of over 99% on average if feature interactions are known. In a further series of experiments, we predicted main memory consumption of six customizable programs and achieved an accuracy of 89% on average.ConclusionOur experiments suggest that, with only few measurements, it is possible to accurately predict non-functional properties of products of a product line. Furthermore, we show how already little domain knowledge can improve predictions and discuss trade-offs between accuracy and required number of measurements. With this technique, we provide a basis for many reasoning and product-derivation approaches.     

A generative neural network model for the quality prediction of work in progress products

One of the key challenges in manufacturing processes is improving the accuracy of quality monitoring and prediction. This paper proposes a generative neural network model for automatically predicting work-in-progress product quality. Our approach combines an unsupervised feature-extraction step with a supervised learning method. An autoencoding neural network is trained using raw manufacturing process data to extract rich information from production line recordings. Then, the extracted features are reformed as time-series and are fed into a multi-layer perceptron for predicting product quality. Finally, the outputs are decoded into a forecast quality measure. We evaluate the performance of the generative model on a case study from a powder metallurgy process. Our experimental results suggest that our method can precisely capture the defective products.     

Discovering business intelligence from online product reviews: A rule-induction framework

Online product reviews are a major source of business intelligence (BI) that helps managers and marketers understand customers’ concerns and interests. The large volume of review data makes it difficult to manually analyze customers’ concerns. Automated tools have emerged to facilitate this analysis, however most lack the capability of extracting the relationships between the reviews’ rich expressions and the customer ratings. Managers and marketers often resort to manually read through voluminous reviews to find the relationships. To address these challenges, we propose the development of a new class of BI systems based on rough set theory, inductive rule learning, and information retrieval methods. We developed a new framework for designing BI systems that extract the relationship between the customer ratings and their reviews. Using reviews of different products from Amazon.com, we conducted both qualitative and quantitative experiments to evaluate the performance of a BI system developed based on the framework. The results indicate that the system achieved high accuracy and coverage related to rule quality, and produced interesting and informative rules with high support and confidence values. The findings have important implications for market sentiment analysis and e-commerce reputation management.     

High-efficient view planning for surface inspection based on parallel deep reinforcement learning

Machine vision, especially deep learning methods, has become a hot topic for product surface inspection. In practice, capturing high quality images is a base for defect detection. It turns out to be challenging for complex products as image quality suffers from occlusion, illumination, and other issues. Multiple images from different viewpoints are often required in this scenario to cover all the important areas of the products. Reducing the viewpoints while ensuring the coverage is the key to make the inspection system more efficient in production. This paper proposes a high-efficient view planning method based on deep reinforcement learning to solve this problem. First, visibility estimation method is developed so that the visible areas can be quickly identified for a given viewpoint. Then, a new reward function is designed, and the Asynchronous Advantage Actor-Critic method is applied to solve the view planning problem. The effectiveness and efficiency of the proposed method is verified with a set of experiments. The proposed method could also be potentially applied to other similar vision-based tasks.     

考虑元素烧损和仓储成本的特种铝合金配料优化

配料计算是特种铝合金熔炼的重要准备工序,直接影响产品的最终性能.为提高产品质量和配料效率,降低原料和仓储物流成本,建立考虑元素烧损和旧料循环利用等因素的特种铝合金配料优化模型.针对该模型的目标多样性和非线性等特点,设计以投料量和投料时间为决策变量的实数编码规则,提出一种基于第3代非支配遗传算法并融入分布式估计策略的多目标优化算法用于求解该模型.通过基于真实生产数据的仿真实验进行模型和算法验证.实验结果表明,所提出模型能够有效地解决特种铝合金配料优化问题,与传统的多目标优化算法相比,所提出求解算法能够获得更优的结果.     

Dispatching rule for non-identical parallel machines with sequence-dependent setups and quality restrictions

This paper proposes a dispatching rule that guarantees a predetermined minimum quality level for non-identical parallel machines with multiple product types. Manufacturers are focusing on improving the overall quality of their products, as the demand for top quality products is increasing. Such changes increase the possibility of neglecting another crucial factor in manufacturing schedules, namely due date. Traditionally, jobs are dispatched with the focus on meeting due dates. That is, jobs are assigned to machines without consideration of product quality. This approach opens the possibility of manufacturing poor quality products. Realizing the shortcomings of the existing dispatching rules, manufacturers are tempted to dispatch jobs with the objective of maximizing product quality. With such an attempt, jobs are likely to be assigned to high performance machines only. In turn, waiting times will increase and job delays are inevitable. This research proposes a dispatching rule that satisfies both criteria, reducing due date delays, while ensuring a predefined product quality level. A quality index is introduced to standardize various product qualities. The index is used to ensure a predetermined quality level, whilst minimizing product delays. Simulations compare various dispatch methods, evaluating them based on mean tardiness and product quality.     

Determining the production lot size with a heuristic inspection policy for controlling the quality of input materials and products

This study simultaneously determines the optimal production lot size and an inspection policy for input materials and products, where an unreliable process produces products with a discrete general shift distribution. This work proposes a heuristic inspection policy for materials and products, by first obtaining the inspection range for the input material without considering product inspection, and by further determining the product inspection range based on the obtained range of the input material inspection. The optimal inspection policy shows that common policies of no or full inspection are never optimal. This study includes the optimal production lot size based on the obtained inspection policy. Numerical examples demonstrate the impacts of input quality level, process reliability and unit nonconforming cost on the optimal solution, which adopts a discrete Weibull shift distribution to model the process failure time. Finally, this study addresses the conclusions.     

Mutual effects of defective components in assemblies

The focus of this study is a known and disturbing actual problem. The industry will soon celebrate a century of quality awareness and efforts. Still, according to field data, many new products exit the manufacturing systems defective. This study proposes mutual effects among assembly's components as an explanation to this phenomenon – many defective new products. While each item in a serial manufacturing process moves individually, items are joined to others in assemblies. There, a single defective component suffices to disqualify a whole assembled unit! Surprisingly, few studies have focused on the repercussions of defective items on production. Particularly, there appears to be no study that quantifies these mutual effects of components which arrive from different sources with different defect rates. Thus, this study is also a first attempt to analyze and quantify these mutual effects. Apparently, the mutual effects of their components amplify the defect rates of assemblies dramatically, to the extent that defects due to common or random causes become significant.     

Decision rules for distributed decision networks with uncertainties

The authors study distributed decision networks where uncertainties exist in the statistical environment. Specifically each decision maker (DM) has an unknown probability to be jammed or defective and an unknown probability to provide an incorrect decision when jammed or defective. Each DM in the network has the ability to process its input data consisting of external observations and decisions from preceding DMs, to produce a decision regarding an underlying binary hypothesis testing problem. The local observations are assumed conditionally independent given each hypothesis. The resulting binary hypothesis testing problem is solved using some simple concepts of Dempster-Shafer theory. The performance of the proposed decision rule is compared to that of the minimax decision rule and the decision rule that is optimum when there are no jammed or defective DMs for several distributed decision networks with different topologies. It is shown that the proposed decision rule has a very robust behavior     

Visual-GPS combined ‘follow-me’ tracking for selfie drones

ABSTRACT

The ‘follow-me’ mode, where the drone autonomously follows and captures the user or target, is a new and attractive feature for camera drones, especially selfie drones. For this purpose, today’s commercial drones use the difference between two GPS data in the drone and user-side mobile GCS, e.g. a smartphone, but the targeting performance is often not satisfactory due to the inaccuracy of the GPS data, ranging from a few to tens of meters. Visual tracking can be considered for a solution to this problem, but the reliability of visual tracking is still questionable for long-term tracking in un-expected operating environments. The paper proposes a hybrid approach that combines the high accuracy of a visual tracking algorithm in short-term tracking and the reliability of GPS-based one in long-term tracking. The experiment with our prototype drone system demonstrates that the proposed combined approach can accomplish the follow-me operation very successfully, capturing the target in the center of video contents over 50% higher accuracy than the GPS-based ones. Also, the extreme scenario experiments verify the system can recover vision tracking failure and Wi-Fi failure quickly in a short-term, e.g. 3–7?s.     

Intelligent monitoring and diagnosis of manufacturing processes using an integrated approach of KBANN and GA

In many manufacturing processes, some key process parameters (i.e., system inputs) have very strong relationship with the categories (e.g., normal or various faulty products) of finished products (i.e., system outputs). The abnormal changes of these process parameters could result in various categories of faulty products. In this paper, a hybrid learning-based model is developed for on-line intelligent monitoring and diagnosis of the manufacturing processes. In the proposed model, a knowledge-based artificial neural network (KBANN) is developed for monitoring the manufacturing process and recognizing faulty quality categories of the products being produced. In addition, a genetic algorithm (GA)-based rule extraction approach named GARule is developed to discover the causal relationship between manufacturing parameters and product quality. These extracted rules are applied for diagnosis of the manufacturing process, provide guidelines on improving the product quality, and are used to construct KBANN. Therefore, the seamless integration of GARule and KBANN provides abnormal warnings, reveals assignable cause(s), and helps operators optimally set the process parameters. The proposed model is successfully applied to a japing-line, which improves the product quality and saves manufacturing cost.     

Self-organizing neural network-based clustering and organization of production cells

Organizing and optimizing production in small and medium enterprises with small batch production and many different products can be very difficult. This paper presents an approach to organize the production cells by means of clustering-manufactured products into groups with similar product properties. Several clustering methods are compared, including the hierarchical clustering, k-means and self-organizing map (SOM) clustering. Clustering methods are applied to production data describing 252 products from a Slovenian company KGL. The best clustering result, evaluated by an average silhouette width for a total data set, is obtained by SOM clustering. In order to make clustering results applicable to the industrial production cell planning, an interpretation method is proposed. The method is based on percentile margins that reflect the requirements of each production cell and is further improved by incorporating the economic values of each product and consequently the economic impact of each production cell. Obtained results can be considered as a recommendation to the production floor planning that will optimize the production resources and minimize the work and material flow transfer between the production cells.

     

Reinforcement learning for combined production-maintenance and quality control of a manufacturing system with deterioration failures

This paper describes and examines thoroughly a stochastic production/inventory system that produces a single type of products. During the production process, the system is affected by several deterioration failures. It is restored to its initial and previous deterioration state by repair and maintenance activities. Both maintenance and repair duration are assumed as exponential random variables. Moreover, the quality of the manufactured products is assumed to be affected by the current deterioration level of the system. The aim of this paper is to find the optimal trade-off between conflicting performance metrics for the optimization of the total expected profit of the system. To tackle such optimization problems, researchers frequently employ Dynamic Programming. This method, though, is not appropriate for the addressed problem due to complexity reasons. To this end, a Reinforcement Learning-based approach is proposed in order to obtain the optimal joint production, maintenance and product quality control policies. To the authors’ knowledge, the proposed approach is novel and there are few examples of such implementation in the academic literature.     

Fault detection and prognosis of assembly locating systems using piezoelectric transducers

Fixture faults have been identified as a principal root cause of defective products in assembly lines; however, there exists a lack of fast and accurate monitoring tools to detect fixture fault damage. Locating fixture damage causes a decrease in product quality and production throughput due to the extensive work required to detect and diagnosis a faulty fixture. In this paper, a unique algorithm is proposed for fixture fault monitoring based on the use of autoregressive models and previously developed piezoelectric impedance fixture sensors. The monitoring method allows for the detection of changes within a system without the need for healthy references. The new method also has the capability to quantify deterioration with respect to a calibrated value. Deterioration prognosis can then be facilitated for structural integrity predictions and maintenance purposes based on the quantified deterioration and forecasting algorithms. The proposed robust methodology is proven to be effective on an experimental setup for monitoring damage in locating fixtures. Fixture wear and failure are successfully detected by the methodology, and fixture structural integrity prognosis is initiated.     

Two-echelon multi-product multi-constraint product returns inventory model with permissible delay in payments and variable lead time

Supply chain is not limited to delivering products to the end-costumers since the defective products that are returned back to the producers by the consumers. The producers should be superior knowledge to utilize the return products effectively so as to maintain our natural resources and to provide better service to customers. In this paper, a distributor and a warehouse consisting of a serviceable part and a recoverable part supply chain problem is considered in which there are several products, the distributor has limited space capacity and budget to purchase all products. In this supply chain, the defective products are returned back to the warehouse by the distributor and the warehouse recovered those defective products into perfect products having the same value as the procured products. The lead-time of receiving products from a warehouse to a distributor is a variable which is controllable by adding extra crashing cost. For each product, a fraction of the shortage is backordered and the rest are lost. A mathematical model is employed in this study for optimizing the order quantity, lead time and total number of deliveries with the objective of minimizing system total cost. We show that the model of this problem is a constrained non-linear programme and present a simple Lagrangian multiplier technique to solve it. Numerical and sensitivity analysis are given to show the applicability of the proposed model in real-world product returns inventory problems.