Automated product line test case selection: industrial case study and controlled experiment

Automated test case selection for a new product in a product line is challenging due to several reasons. First, the variability within the product line needs to be captured in a systematic way; second, the reusable test cases from the repository are required to be identified for testing a new product. The objective of such automated process is to reduce the overall effort for selection (e.g., selection time), while achieving an acceptable level of the coverage of testing functionalities. In this paper, we propose a systematic and automated methodology using a feature model for testing (FM_T) to capture commonalities and variabilities of a product line and a component family model for testing (CFM_T) to capture the overall structure of test cases in the repository. With our methodology, a test engineer does not need to manually go through the repository to select a relevant set of test cases for a new product. Instead, a test engineer only needs to select a set of relevant features using FM_T at a higher level of abstraction for a product and a set of relevant test cases will be selected automatically. We evaluated our methodology via three different ways: (1) We applied our methodology to a product line of video conferencing systems called Saturn developed by Cisco, and the results show that our methodology can reduce the selection effort significantly; (2) we conducted a questionnaire-based study to solicit the views of test engineers who were involved in developing FM_T and CFM_T. The results show that test engineers are positive about adapting our methodology and models (FM_T and CFM_T) in their current practice; (3) we conducted a controlled experiment with 20 graduate students to assess the performance (i.e., cost, effectiveness and efficiency) of our automated methodology as compared to the manual approach. The results showed that our methodology is cost-effective as compared to the manual approach, and at the same time, its efficiency is not affected by the increased complexity of products.     

Assessing software product line potential: an exploratory industrial case study

Corporate organizations sometimes offer similar software products in certain domains due to former company mergers or due to the complexity of the organization. The functional overlap of such products is an opportunity for future systematic reuse to reduce software development and maintenance costs. Therefore, we have tailored existing domain analysis methods to our organization to identify commonalities and variabilities among such products and to assess the potential for software product line (SPL) approaches. As an exploratory case study, we report on our experiences and lessons learned from conducting the domain analysis in four application cases with large-scale software products. We learned that the outcome of a domain analysis was often a smaller integration scenario instead of an SPL and that business case calculations were less relevant for the stakeholders and managers from the business units during this phase. We also learned that architecture reconstruction using a simple block diagram notation aids domain analysis and that large parts of our approach were reusable across application cases.     

Model predictive control of an industrial packed bed reactor using neural networks

This paper discusses an industrial application of a multivariable nonlinear feedforward/feedback model predictive control where the model is given by a dynamic neural network. A multi-pass packed bed reactor temperature profile is modelled via recurrent neural networks using the backpropagation through time training algorithm. This model is then used in conjunction with an optimizer to build a nonlinear model predictive controller. Results show that, compared with conventional control schemes, the neural network model based controller can achieve tighter temperature control for disturbance rejection     

Artificial neural networks in process estimation and control

In this contribution, the suitability of the artificial neural network methodology for solving some process engineering problems is discussed. First the concepts involved in the formulation of artificial neural networks are presented. Next the suitability of the technique to provide estimates of difficult to measure quality variables is demonstrated by application to industrial data. Measurements from established instruments are used as secondary variables for estimation of the “primary” quality variables. The advantage of using these estimates for feedback control is then demonstrated. The possibility of using neural network models directly within a model-based predictive control strategy is also considered, making use of an on-line optimization routine to determine the future inputs that will minimize the deviations between the desired and predicted outputs. Control is implemented in a receding horizon fashion. Application of the predictive controller to a nonlinear distillation system is used to indicate the potential of the neural network based control philosophy.     

Closed loop identification and control loop reconfiguration: an industrial case study

The results of a joint university–industry collaborative project for control loop reconfiguration using closed loop experimental data from a fuel gas pressure control system are described in this paper. The fuel gas pressure was being regulated using a butane stream. For economic reasons, it was necessary to switch control to the ethane stream. Previous attempts at effecting this changeover had proved unsuccessful. In this study, a powerful system identification technique namely Canonical Variate Analysis (CVA) was employed to obtain the empirical plant models. A PI controller was then designed using the direct synthesis method. Acceptable closed loop behavior was obtained with little online tuning.     

Distributed-information neural control: the case of dynamic routingin traffic networks

Large-scale traffic networks can be modeled as graphs in which a set of nodes are connected through a set of links that cannot be loaded above their traffic capacities. Traffic flows may vary over time. Then the nodes may be requested to modify the traffic flows to be sent to their neighboring nodes. In this case, a dynamic routing problem arises. The decision makers are realistically assumed 1) to generate their routing decisions on the basis of local information and possibly of some data received from other nodes, typically, the neighboring ones and 2) to cooperate on the accomplishment of a common goal, that is, the minimization of the total traffic cost. Therefore, they can be regarded as the cooperating members of informationally distributed organizations, which, in control engineering and economics, are called team organizations. Team optimal control problems cannot be solved analytically unless special assumptions on the team model are verified. In general, this is not the case with traffic networks. An approximate resolutive method is then proposed, in which each decision maker is assigned a fixed-structure routing function where some parameters have to be optimized. Among the various possible fixed-structure functions, feedforward neural networks have been chosen for their powerful approximation capabilities. The routing functions can also be computed (or adapted) locally at each node. Concerning traffic networks, we focus attention on store-and-forward packet switching networks, which exhibit the essential peculiarities and difficulties of other traffic networks. Simulations performed on complex communication networks point out the effectiveness of the proposed method.     

模块小波神经网络在工业产品质量控制中的应用

针对输入空间包含多种类型的数据时，以单一的神经网络为模型，其收敛很困难的问题，提出一种基于模块小波神经网络的建模方法。利用分而治之思想，模块神经网络通过一个门控网络进行分类和协调，可以将一个复杂任务分解成几个简单的子任务，每个子任务由一个局部专家网络学习，与传统的模块网络不同，这里的专家网络是小波网络而不是BP网络，将所提出的网络模型用于热连轧产品质量建模，并与单一的神经网络建模结果进行比较，建模结果表明，模块小波神经网络模型优于单一神经网络模型。     

A systematic test case selection methodology for product lines: results and insights from an industrial case study

In the context of product lines, test case selection aims at obtaining a set of relevant test cases for a product from the entire set of test cases available for a product line. While working on a research-based innovation project on automated testing of product lines of Video Conferencing Systems (VCSs) developed by Cisco, we felt the need to devise a cost-effective way of selecting relevant test cases for a product. To fulfill such need, we propose a systematic and automated test selection methodology using: 1) Feature Model for Testing (FM_T) to capture commonalities and variabilities of a product line; 2) Component Family Model for Testing (CFM_T) to model the structure of test case repository; 3) A tool to automatically build restrictions from CFM_T to FM_T and traces from CFM_T to the actual test cases. Using our methodology, a test engineer is only required to select relevant features through FM_T at a higher level of abstraction for a product and the corresponding test cases will be obtained automatically. We evaluate our methodology by applying it to a VCS product line called Saturn with seven commercial products and the results show that our methodology can significantly reduce cost measured as test selection time and at the same time achieves higher effectiveness (feature coverage, feature pairwise coverage and fault detection) as compared with the current manual process. Moreover, we conduct a questionnaire-based study to solicit the views of test engineers who are involved in developing FM_T and CFM_T. The results show that test engineers are positive about adapting our methodology in their current practice. Finally, we present a set of lessons learnt while applying product line engineering at Cisco for test case selection.     

Australian technology meets American manufacturing: A case study of industrial collaboration

This article examines some of the issues that surround the development and application of Australian computer software in the collaborative design of cellular manufacturing operations in an American manufacturing operation. In examining the dynamic relationship between a national research-based organization and a multinational corporation, a detailed case study is presented of the collaborative venture between the Australian Commonwealth Scientific and Industrial Research Organisation (CSIRO) and the Boeing Commercial Airplane Group. In 1988, the Wichita Division of Boeing applied Group Technology (GT) classification and coding to create a GT data base for 200,000 sheet metal parts. However, their aim to implement cellular work arrangements was constrained by the complexity of the manufacturing environment. In 1990, they became aware of some innovative cell-build software that had been developed in Australia. After some preliminary negotiations, a collaborative contract was signed between the CSIRO and Boeing. In charting the development of this joint project and consequent outcomes, the article draws out new insights on the practice of industrial collaboration in the development and implementation of cellular forms of work organization. © 1998 John Wiley & Sons, Inc.     

Integration of neural networks and genetic algorithms for an intelligent manufacturing controller

This paper addresses the development and implementation of a “controller” for a single manufacturing machine. This prototype will serve as an important tool to study the integration of several functions and the utilization of status data to evaluate scheduling and control decision alternatives. The emphasis is on creating a prediction capability to aid in assessing the long-term system performance impact resulting from decisions made and environmental changes. This prediction capability is implemented by using neural networks, simulation, and genetic algorithms. Neural networks predict the behavior of different sequencing policies available in the system. The contribution of the genetic algorithms to the decision-making process is the development of a “new” scheduling rule based on a “building blocks” procedure initiated by the neural networks     

Ensembles of ARTMAP-based neural networks: an experimental study

ARTMAP-based models are neural networks which use a match-based learning procedure. The main advantage of ARTMAP-based models over error-based models, such as Multi-Layer Perceptron, is the learning time, which is considered as significantly fast. This feature is extremely important in complex systems that require the use of several models, such as ensembles or committees, since they produce robust and fast classifiers. Subsequently, some extensions of the ARTMAP model have been proposed, such as: ARTMAP-IC, RePART, among others. Aiming to add an extra contribution to ARTMAP context, this paper presents an analysis of ARTMAP-based models in ensemble systems. As a result of this analysis, two main goals are aimed, which are: to analyze the influence of the RePART model in ensemble systems and to detect any relation between diversity and accuracy in ensemble systems in order to use this relation in the design of these systems.     

GAMLSS and neural networks in combat simulation metamodelling: A case study

The GAMLSS (Generalised Additive Models for Location, Scale and Shape) regression approach is compared to neural networks in the context of modelling the relationship between the inputs and outputs of the stochastic combat simulation model SIMBAT. The similarities and differences in these modelling approaches, and their advantages and disadvantages in this case, are discussed. Comparison of out-of-sample prediction suggests that some GAMLSS models are better able to cope with skewed data, but otherwise performance is broadly similar.     

Model predictive control of an activated sludge process: A case study

This paper details a case study application of model predictive control for a wastewater treatment process in Lancaster, North England. The control system was implemented in real time, together with a plant monitoring system for the purposes of process supervision. Following implementation, the model predictive control system provided significant benefits compared with the previously applied control system. These benefits included a reduction of over 25% in power usage and a similar increase in plant efficiency. The system therefore represents a useful tool in helping the water industry to reach its goal of significantly reducing its carbon footprint.     

An iterative learning scheme for motion control of robots using neural networks: A case study

In this paper, an iterative learning controller using neural networks has been studied for the motion control of robotic manipulators. Simulations of a two-link robot have demonstrated that the proposed control scheme for robotic manipulators can greatly reduce tracking errors after a few trials. Our modification of the original back-propagation algorithm is employed in the neural network, resulting in a much faster learning rate. The results of simulation have also shown that the proposed iterative learning controller has a faster rate of convergence and better robustness.     

Developing a digital transformation process in the manufacturing sector: Egyptian case study

Digital transformation is of crucial importance in the manufacturing industry, especially after the COVID-19 pandemic because of the increasing need for remote working and socially distanced workplaces. However, there is a lack of a clear and well-defined process to implement digital transformation in manufacturing. This paper aims to identify the most critical stages to implementing digital transformation in the manufacturing sector. Twenty-one structured interviews with experienced specialists in digitalisation in the manufacturing sector in the Egyptian economy were held and used the Best–Worst Method to analyse the data as an analysis tool for a multiple criteria decision making (MCDM) approach. The digital transformation process comprises eight stages covering technology, management, communications, and customer elements. The main contribution of this work stage is the balance between the different elements of digital transformation—digital technologies, leadership and strategy, people and business processes—to create an integrated 8-step process of digital transformation in the manufacturing sector of developing economies such as the Egyptian economy.

     

Acquisition of state transitions and concept formation in neural networks

Searching of state transitions is an important subject of problem solving in artificial intelligence, computer science, engineering and operations research. In artificial intelligence, a breadth-first search is optimal, with uniform cost, but it takes considerable time to obtain a solution. Neural networks process state transitions in parallel with learning ability. The authors have developed a search procedure for state transitions, that resembles a breadth-first search, using neural networks. First, the input pattern states are self-organized in the neural network, which consists of a Kohonen layer followed by a state-planning layer. The state-planning layer makes lateral connections between the cells of transitions. Then, the initial and the target states are given as a problem. The network shows an optimal transition pathway of states in the neuron firings. Next, the state-transition procedure is developed for the formation of a concept for action planning. Here, as the action planning, an integration between the symbols and the action pattern is carried out in the extended neural network.     

An investigation on the impact of product modularity level on supply chain performance metrics: an industrial case study

The benefit of integrating product design decisions and supply chain design decisions has been recognized by researchers. Such integration can facilitate better communication between design teams and operations groups. Consequently, potential supply chain risks can be highlighted and addressed before the launch of a new product. Modularization is one of the most critical elements for both product design and supply chain design decisions as it impacts the assembly sequence and hence the selection of component and module suppliers. However, the impact of modularity level on supply chain performance is still unclear, and thus is the focus of this study. The proposed analytical method incorporates both product design and supply chain design functions, and hence, enables simultaneous consideration of these decisions. The supply chain performances of all two-module and three-module design concepts are fully investigated in an effort to explore the impact of modularity level on supply chain performance. Results show that increased modularity is advantageous for the time-based performance of a supply chain network, whereas decreased modularity yields superiority in terms of cost performance.     

On-line identification and nonlinear control of an industrial pH process

The control of pH for industrial processes is a highly nonlinear and challenging problem, especially when the nonlinearity is unknown and time-varying. In this work, a controller is developed and implemented for an industrial pH process with unknown chemical composition. The method used is an application of a general algorithm for pH processes, which is based on a representation of the nonlinearity that leads to on-line identification of a small number of parameters. The results show good performance of the pH control algorithm under normal operating conditions and satisfactory performance during several unusual hardware or process problems.     

Plant-wide hierarchical optimization and control of an industrial hydrocracking process

Hydrocracking is a crucial refinery process in which heavy hydrocarbons are converted to more valuable, low-molecular weight products. Hydrocracking plants operate with large throughputs and varying feedstocks. In addition the product specifications change due to varying economic and market conditions. In such a dynamic operating environment, the potential gains of real-time optimization (RTO) and control are quite high. At the same time, real-time optimization of hydrocracking plants is a challenging task. A complex network of reactions, which are difficult to characterize, takes place in the hydrocracker. The reactor effluent affects the operation of the fractionator downstream and the properties of the final products. In this paper, a lumped first-principles reactor model and an empirical fractionation model are used to predict the product distribution and properties on-line. Both models have been built and validated using industrial data. A cascaded model predictive control (MPC) structure is developed in order to operate both the reactor and fractionation column at maximum profit. In this cascade structure, reactor and fractionation units are controlled by local decentralized MPC controllers whose set-points are manipulated by a supervisory MPC controller. The coordinating action of the supervisory MPC controller accomplishes the transition between different optimum operating conditions and helps to reject disturbances without violating any constraints. Simulations illustrate the applicability of the proposed method on the industrial process.     

An intelligent hybrid approach for industrial quality control combining neural networks, fuzzy logic and fractal theory

The application of type-2 fuzzy logic to the problem of automated quality control in sound speaker manufacturing is presented in this paper. Traditional quality control has been done by manually checking the quality of sound after production. This manual checking of the speakers is time consuming and occasionally was the cause of error in quality evaluation. For this reason, by applying type-2 fuzzy logic, an intelligent system for automated quality control in sound speaker manufacturing is developed. The intelligent system has a type-2 fuzzy rule base containing the knowledge of human experts in quality control. The parameters of the fuzzy system are tuned by applying neural networks using, as training data, a real time series of measured sounds produced by good sound speakers. The fractal dimension is used as a measure of the complexity of the sound signal.