Though they can be traced back to different roots, both smart design and smart systems have to do with the recent developments of artificial intelligence. There are two major questions related to them: (i) What way are smart design and smart systems enabled by artificial narrow, general, or super intelligence? and (ii) How can smart design be used in the realization of smart systems? and How can smart systems contribute to smart designing? A difficulty is that there are no exact definitions for these novel concepts in the literature. The endeavor to analyze the current situation and to answer the above questions stimulated an exploratory research whose first findings are summarized in this paper. Its first part elaborates on a plausible interpretation of the concept of smartness and provides an overview of the characteristics of smart design as a creative problem solving methodology supported by artificial intelligence. The second part exposes the paradigmatic features and system engineering issues of smart systems, which are equipped with application-specific synthetic system knowledge and reasoning mechanisms. The third part presents and elaborates on a conceptual model of AI-based couplings of smart design and smart systems. The couplings may manifest in various concrete forms in real life that are referred to as “connectors” in this paper. The principal types of connectors are exemplified and discussed. It has been found that smart design tends to manifest as a methodology of blue-printing smart systems and that smart systems will be intellectualized the enablers of implementation of smart design. Understanding the affordances of and creating proper connectors between smart design and smart systems need further explorative research.

Early childhood education has long-lasting influences on people, and an appropriate companion toy can play an essential role in children's brain development. This paper establishes a complete framework to guide the design of intelligent companion toys for preschool children from 2 to 6 years old, which is child-centered and environment-oriented. The design process is divided into three steps: requirement confirmation, the smart design before the sale, and the iterative update after the sale. This framework considers the characteristics of children and highlights the integration of human and artificial intelligence in design. A case study is provided to prove the superiority of the new framework. In addition to enriching the research on intelligent toy design, this paper also guides for practitioners to design smart toys and helps in children's cognitive development.

Functional design is regarded as a design activity primarily aimed at clarifying customer needs, and developing the functional architecture and solution concepts for a system under development. Existing functional design approaches are mainly focused on how to assist designers in searching for solution principles for desired products, which, however, do not adequately take into account the interactions between a smart system under development and its environment, and cannot explicitly represent the complex functional logic of the system, resulting in that they cannot effectively assist designers in the functional design of smart systems. Therefore, this paper proposes a scenario-integrated approach for functional design of smart systems to address the above issues. Based on the concept of scenario in software engineering, the proposed approach explicitly elaborates how to employ scenarios to express subjective customer needs and how to generate the functional architectures and the corresponding solution concepts through a structured process. The functional design of the automated doors-unlocking system of a smart vehicle is employed to illustrate the proposed approach, which also demonstrates that the proposed approach is suitable for functional design of smart systems.

Automatic generation of high-quality meshes is a base of CAD/CAE systems. The element extraction is a major mesh generation method for its capabilities to generate high-quality meshes around the domain boundary and to control local mesh densities. However, its widespread applications have been inhibited by the difficulties in generating satisfactory meshes in the interior of a domain or even in generating a complete mesh. The element extraction method's primary challenge is to define element extraction rules for achieving high-quality meshes in both the boundary and the interior of a geometric domain with complex shapes. This paper presents a self-learning element extraction system, FreeMesh-S, that can automatically acquire robust and high-quality element extraction rules. Two central components enable the FreeMesh-S: (1) three primitive structures of element extraction rules, which are constructed according to boundary patterns of any geometric boundary shapes; (2) a novel self-learning schema, which is used to automatically define and refine the relationships between the parameters included in the element extraction rules, by combining an Advantage Actor-Critic (A2C) reinforcement learning network and a Feedforward Neural Network (FNN). The A2C network learns the mesh generation process through random mesh element extraction actions using element quality as a reward signal and produces high-quality elements over time. The FNN takes the mesh generated from the A2C as samples to train itself for the fast generation of high-quality elements. FreeMesh-S is demonstrated by its application to two-dimensional quad mesh generation. The meshing performance of FreeMesh-S is compared with three existing popular approaches on ten pre-defined domain boundaries. The experimental results show that even with much less domain knowledge required to develop the algorithm, FreeMesh-S outperforms those three approaches in essential indices. FreeMesh-S significantly reduces the time and expertise needed to create high-quality mesh generation algorithms.

Digital platform business models are disrupting traditional business processes and reveal a new way of creating value. Current validation processes for business models are designed to assess pipeline business models. They cannot grasp the logic of digital platforms, which increasingly integrate Artificial Intelligence (AI) to ensure success. This study developed a new validation process for early market validation of digital platform business models by following the Design Science Research methodology. The designed process, the Smart Platform Experiment Cycle (SPEC), is created by combining the Four-Step Iterative Cycle of business experiments, the Customer Development Process, and the Build-Measure-Learn feedback loop of the Lean Startup approach and enriching it with the knowledge of digital platforms. It consists of five iterative steps showing the startup how to design their platform business model and corresponding experiments and how to run, measure, analyze, and learn from the outcomes and results. To assess its efficacy, applicability, and validity, SPEC was applied in the German startup GassiAlarm, a service marketplace business model. The application of SPEC revealed shortcomings in the pricing strategy and highlighted to what extent their current business model would be successful. SPEC reduces the risk of building a product or service the market deems redundant and gives insights into its success rate. More applications of the SPEC are needed to validate its robustness further and to extend it to other types of digital platform business models for improved generalization.

In order to realize the online allocation of collaborative processing resource of smart workshop in the context of cloud manufacturing, a multi-objective optimization model of workshop collaborative resources (MOM-WCR) was proposed. Considering the optimization objectives of processing time, processing cost, product qualification rate, and resource utilization, MOM-WCR was constructed. Based on the time sequence of workshop processing tasks, the workshop collaborative manufacturing resource was integrated in MOM-WCR. Fuzzy analytic hierarchy process (FAHP) was adopted to simplified the multi-objective problem into the single-objective problem. Then, the improved firefly algorithm which integrated the particle swarm algorithm (IFA-PSA) was used to solve MOM-WCR. Finally, a group of connecting rod processing experiments were used to verify the model proposed in this paper. The results show that the model is feasible in the application of workshop-level resource allocation in the context of cloud manufacturing, and the improved firefly algorithm shows good performance in solving the multi-objective resource allocation problem.

The potential relationship between service demands and remanufacturing services (RMS) is essential to make the decision of a RMS plan accurately and improve the efficiency and benefit. In the traditional association rule mining methods, a large number of candidate sets affect the mining efficiency, and the results are not easy for customers to understand. Therefore, a mining method based on binary particle swarm optimization ant colony algorithm to discover service demands and remanufacture services association rules is proposed. This method preprocesses the RMS records, converts them into a binary matrix, and uses the improved ant colony algorithm to mine the maximum frequent itemset. Because the particle swarm algorithm determines the initial pheromone concentration of the ant colony, it avoids the blindness of the ant colony, effectively enhances the searchability of the algorithm, and makes association rule mining faster and more accurate. Finally, a set of historical RMS record data of straightening machine is used to test the validity and feasibility of this method by extracting valid association rules to guide the design of RMS scheme for straightening machine parts.

Machine learning components such as deep neural networks are used extensively in cyber-physical systems (CPS). However, such components may introduce new types of hazards that can have disastrous consequences and need to be addressed for engineering trustworthy systems. Although deep neural networks offer advanced capabilities, they must be complemented by engineering methods and practices that allow effective integration in CPS. In this paper, we proposed an approach for assurance monitoring of learning-enabled CPS based on the conformal prediction framework. In order to allow real-time assurance monitoring, the approach employs distance learning to transform high-dimensional inputs into lower size embedding representations. By leveraging conformal prediction, the approach provides well-calibrated confidence and ensures a bounded small error rate while limiting the number of inputs for which an accurate prediction cannot be made. We demonstrate the approach using three datasets of mobile robot following a wall, speaker recognition, and traffic sign recognition. The experimental results demonstrate that the error rates are well-calibrated while the number of alarms is very small. Furthermore, the method is computationally efficient and allows real-time assurance monitoring of CPS.