Explore the vast range of titles available.

The book summarizes theory and applications of data-driven model-free adaptive control (MFAC) which is different from the traditional adaptive control. The traditional unmodeled dynamics do not exist in MFAC framework. In addition, MFAC is suitable for many practical applications since it is easily implemented and has strong robustness. By reading this book, readers become familiar with MFAC in a short time, and can quickly carry out their independent research and applications.

HighlightsAn interactive electronic system inspired by the temperature self-regulation of human skin.Heat stimulation therapy and temperature monitoring during dynamic wound healing.Mechanism of temperature self-regulation during dynamic wound healing.The thermoregulating function of skin that is capable of maintaining body temperature within a thermostatic state is critical. However, patients suffering from skin damage are struggling with the surrounding scene and situational awareness. Here, we report an interactive self-regulation electronic system by mimicking the human thermos-reception system. The skin-inspired self-adaptive system is composed of two highly sensitive thermistors (thermal-response composite materials), and a low-power temperature control unit (Laser-induced graphene array). The biomimetic skin can realize self-adjusting in the range of 35–42 °C, which is around physiological temperature. This thermoregulation system also contributed to skin barrier formation and wound healing. Across wound models, the treatment group healed ~ 10% more rapidly compared with the control group, and showed reduced inflammation, thus enhancing skin tissue regeneration. The skin-inspired self-adaptive system holds substantial promise for next-generation robotic and medical devices.

A self-adaptive system can automatically maintain its quality requirements in the presence of dynamic environment changes. Developing a self-adaptive system may be difficult due to design time uncertainty; e.g., anticipating all potential environment changes at design time is in most cases infeasible. To realize self-adaptive systems in the presence of design time uncertainty, online machine learning, i.e., machine learning at runtime, is increasingly used. In particular, online reinforcement learning is proposed, which learns suitable adaptation actions through interactions with the environment at runtime. To learn about its environment, online reinforcement learning has to select actions that were not selected before, which is known as exploration. How exploration happens impacts the performance of the learning process. We focus on two problems related to how adaptation actions are explored. First, existing solutions randomly explore adaptation actions and thus may exhibit slow learning if there are many possible adaptation actions. Second, they are unaware of system evolution, and thus may explore new adaptation actions introduced during evolution rather late. We propose novel exploration strategies that use feature models (from software product line engineering) to guide exploration in the presence of many adaptation actions and system evolution. Experimental results for two realistic self-adaptive systems indicate an average speed-up of the learning process of 33.7% in the presence of many adaptation actions, and of 50.6% in the presence of evolution.

The integration of machine learning (ML) into industrial automation is fundamentally reshaping how manufacturing systems are monitored, inspected, and optimized. By applying machine learning to real-time sensor data and operational histories, advanced models enable proactive fault prediction, intelligent inspection, and dynamic process control—directly enhancing system reliability, product quality, and efficiency. This review explores the transformative role of ML across three key domains: Predictive Maintenance (PdM), Quality Control (QC), and Process Optimization (PO). It also analyzes how Digital Twin (DT) and Edge AI technologies are expanding the practical impact of ML in these areas. Our analysis reveals a marked rise in deep learning, especially convolutional and recurrent architectures, with a growing shift toward real-time, edge-based deployment. The paper also catalogs the datasets used, the tools and sensors employed for data collection, and the industrial software platforms supporting ML deployment in practice. This review not only maps the current research terrain but also highlights emerging opportunities in self-learning systems, federated architectures, explainable AI, and themes such as self-adaptive control, collaborative intelligence, and autonomous defect diagnosis—indicating that ML is poised to become deeply embedded across the full spectrum of industrial operations in the coming years.

In order to improve the precision of fault diagnosis within distribution grids, this study introduces a novel framework for classifying faults. This framework integrates a Bidirectional Long Short-Term Memory (BiLSTM) network equipped with an Attention Mechanism (AM), which is optimized via a Self-Adaptive Chaotic Particle Swarm Optimization (SA-CPSO) algorithm. Firstly, a self-adaptive chaotic particle swarm optimization algorithm (SA-CPSO) is proposed. Building upon the standard Chaotic Particle Swarm Optimization (CPSO), we incorporate a self-adaptive tuning strategy. This modification is designed to balance the algorithm’s global exploration and local exploitation capabilities, thereby significantly boosting its optimization efficiency. Then, to enhance the ability of BiLSTM to extract key features of time series, an attention mechanism is introduced, and a fault identification model based on SA-CPSO-AM-BiLSTM is established. SA-CPSO is used to optimize the hyperparameters of AM-BiLSTM, thereby improving the identification accuracy of the model. Finally, a distribution network simulation model is constructed using PSCAD software to obtain node fault data, and the model is verified for performance. The instance analysis results show that, compared with other models, the fault identification accuracy of the model proposed in this paper reaches 99.86%. It also demonstrates good robustness under various interference factors and has good generalization performance.

The problem of mitigating uncertainty in self-adaptation has driven much of the research proposed in the area of software engineering for self-adaptive systems in the last decade. Although many solutions have already been proposed, most of them tend to tackle specific types, sources, and dimensions of uncertainty (e.g., in goals, resources, adaptation functions) in isolation. A special concern are the aspects associated with uncertainty modeling in an integrated fashion. Different uncertainties are rarely independent and often compound, affecting the satisfaction of goals and other system properties in subtle and often unpredictable ways. Hence, there is still limited understanding about the specific ways in which uncertainties from various sources interact and ultimately affect the properties of self-adaptive, software-intensive systems. In this SoSym expert voice, we introduce the Uncertainty Interaction Problem as a way to better qualify the scope of the challenges with respect to representing different types of uncertainty while capturing their interaction in models employed to reason about self-adaptation. We contribute a characterization of the problem and discuss its relevance in the context of case studies taken from two representative application domains. We posit that the Uncertainty Interaction Problem should drive future research in software engineering for autonomous and self-adaptive systems, and therefore, contribute to evolving uncertainty modeling towards holistic approaches that would enable the construction of more resilient self-adaptive systems.

Adaptive systems possess the remarkable capability to assess and modify their behavior in real-time, particularly when the software deviates from its programmed course or when opportunities for enhanced functionality or performance arise. This adaptability proves invaluable in highly dynamic environments, where rapid changes occur, and human oversight alone falls short in effectively managing applications. However, in certain system types, achieving optimal performance through adaptation may necessitate human input, be it as a sensor providing unique information beyond the system's reach, an actuator driving adaptation, or a fallback mechanism in contingency scenarios. In this context, the concept of 'human-in-the-loop' harnesses the innate capabilities of humans to execute tasks and make decisions with greater efficiency and precision, thereby ensuring the security and reliability of these systems. Our primary objective in this study is to present a comprehensive analysis of the key research and contributions in this field. Additionally, we aim to pinpoint potential research avenues and unresolved challenges within the realm of Human-in-the-loop.

An increasingly used method for the engineering of software systems with strict quality-of-service (QoS) requirements involves the synthesis and verification of probabilistic models for many alternative architectures and instantiations of system parameters. Using manual trial-and-error or simple heuristics for this task often produces suboptimal models, while the exhaustive synthesis of all possible models is typically intractable. The EvoChecker search-based software engineering approach presented in our paper addresses these limitations by employing evolutionary algorithms to automate the model synthesis process and to significantly improve its outcome. EvoChecker can be used to synthesise the Pareto-optimal set of probabilistic models associated with the QoS requirements of a system under design, and to support the selection of a suitable system architecture and configuration. EvoChecker can also be used at runtime, to drive the efficient reconfiguration of a self-adaptive software system. We evaluate EvoChecker on several variants of three systems from different application domains, and show its effectiveness and applicability.

Self-adaptive cuckoo search algorithm is used to optimize the design of water distribution system problems. It is proposed to dynamically adjust the two sensitive parameters of the algorithm, (i) step size control parameter ‘α’ and (ii) discovering probability parameter ‘Pa’ which largely govern the exploration and exploitation search strategies of the algorithm. These parameters are essential for enhancing the performance of the algorithm and normally the values of these parameters needs careful selection according to the type of problem. Single objective self-adaptive cuckoo search algorithm (SACSA) and multi-objective self-adaptive cuckoo search algorithm (SAMOSCA) are proposed in this study. Robustness and efficiency of these algorithms in single (minimization of cost) and multi-objective scenarios (minimization of cost and maximization of resilience) is validated using standard water distribution benchmark problems i.e. Two loop and Hanoi network. These are later applied to solve a medium size real-life water distribution system located at Pamapur, Telangana, India. A simulation-optimization based program combining the water distribution network simulation software EPANET 2.2 and MATLAB is used for computation. The proposed methodology has provided better results in terms of computational efficiency as well as found better solutions when compared to the previously reported results in both single and multi-objective scenarios. In the case of multi-objective problems, it has been observed that SAMOCSA has been able to find new points in pareto front when compared to the best-known pareto front reported in the literature. Self-adaptive cuckoo search algorithm has been found to be an attractive alternative in both exploration and exploitation of larger search spaces for finding better optimal solutions.

With the establishment of Cyber-physical Systems (CPS) and the Internet of Things, the virtual world of software and services and the physical world of objects and humans move closer together. Despite being a useful means for automation, BPM technologies and workflow systems are yet not fully capable of executing processes in CPS. The effects on and possible errors and inconsistencies in the physical world are not considered by “traditional” workflow engines. In this work we propose a framework for self-adaptive workflows in CPS based on the MAPE-K feedback loop. Within this loop monitoring and analysis of additional sensor and context data is used to check for unanticipated errors in the physical world. Planning and execution of compensation actions restores Cyber-physical Consistency , which leads to an increased resilience of the process execution environment. The framework facilitates the separation of CPS aspects from the “regular” workflow views. We show the feasibility of this approach in a smart home scenario and discuss the application of our approach for legacy BPM systems.