The fourth industrial revolution requires higher capabilities of changeability and reconfigurability (C–R) of the future factories (FoF), as well as a higher focus on business models that are based on total-cost-of-ownership (TCO) paradigm. Up to date, there are little scientific contributions to deploy C–R into TCO models, as well as to systematic plan and design manufacturing resources such as to facilitate FoF ecosystem. In order to address this issue, this paper introduces research results that show how to deploy C–R, connectivity, smartness and TCO requirements into the technical solutions of manufacturing resources of FoF. Contributions emerging from this research include an index to measure C–R capability of manufacturing resources, a model to assess economic feasibility of a FoF over its lifecycle, as well as a methodology and related tools to design smart connected manufacturing resources with embedded features to facilitate changeability and reconfigurability in a FoF. Theoretical contributions are explained through a case study of a fast reconfigurable robotic manufacturing cell. Preliminary results demonstrate that it is possible to rapid design smart connected manufacturing resources and integrate them into FoF architectures that support convertibility, integrability, modifiability, adaptability, serviceability, scalability, integration of resources from various producers, service clustering and cloud-based services.

Hepatocellular Carcinoma (HCC) is the most common malignant liver tumor, being present in 70% of liver cancer cases. It usually evolves on the top of the cirrhotic parenchyma. The most reliable method for HCC diagnosis is the needle biopsy, which is an invasive, dangerous method. In our research, specific techniques for non-invasive, computerized HCC diagnosis are developed, by exploiting the information from ultrasound images. In this work, the possibility of performing the automatic diagnosis of HCC within B-mode ultrasound and Contrast-Enhanced Ultrasound (CEUS) images, using advanced machine learning methods based on Convolutional Neural Networks (CNN), was assessed. The recognition performance was evaluated separately on B-mode ultrasound images and on CEUS images, respectively, as well as on combined B-mode ultrasound and CEUS images. For this purpose, we considered the possibility of combining the input images directly, performing feature level fusion, then providing the resulted data at the entrances of representative CNN classifiers. In addition, several multimodal combined classifiers were experimented, resulted by the fusion, at classifier, respectively, at the decision levels of two different branches based on the same CNN architecture, as well as on different CNN architectures. Various combination methods, and also the dimensionality reduction method of Kernel Principal Component Analysis (KPCA), were involved in this process. These results were compared with those obtained on the same dataset, when employing advanced texture analysis techniques in conjunction with conventional classification methods and also with equivalent state-of-the-art approaches. An accuracy above 97% was achieved when our new methodology was applied.

Capacity to remotely monitor and control systems for waste-water treatment and to provide real time and trustworthy data of system’s behavior to various stakeholders is of high relevance. SCADA systems are used to undertake this job. SCADA solutions are usually conceptualized and designed with a major focus on technological integrability and functionality. Very little contributions are brought to optimize these systems with respect to a mix of target functions, especially considering a lifecycle perspective. In this paper, we propose a structured methodology for optimizing SCADA systems from a lifecycle perspective for the specific case of waste-water treatment units. The methodology embeds techniques for handling entropy in the design process and to assist engineers in designing effective solutions in a space with multiple constrains and conflicts. Evolutionary multiple optimization algorithms are used to handle this challenge. After the foundation of the theoretical model calibrated for the specific case of waste-water treatment units, a practical example illustrates its applicability. It is shown how the model can lead to a disruptive solution, which integrates cloud computing, IoT, and data analytics in the SCADA system, with some competitive advantages in terms of flexibility, cost effectiveness, and increased value added for both integrators and beneficiaries.

The development of concepts for new generations of products that are located at the convergence of various cutting-edge technologies requires: integration of knowledge from different fields of science and technology; the management of non-linear interactions of technical, cognitive and organizational nature; the handling of multiple and inconsistent information; innovative solving of negative correlations between different system's characteristics, etc. Despite specialists’ experience, empirical approaches to the synthesis process for this category of products do not represent a reliable solution. An innovative tool for the systematic management of the synthesis process of complex innovative products is introduced in this paper. It is called the complex system design technique (CSDT) and incorporates a set of coefficients and a specific algorithm that take data from product performance planning process (e.g. data extracted from QFD-type matrices) for the formulation of a working scheme for system design (WSSD). This scheme represents a practical tool for the new product synthesis (design) process. It also allows systematic integration of innovation and analysis tools (e.g. TRIZ, AFD, Pugh, Design-FMEA, etc.) in the product synthesis process.

In the paradigm of industry 4.0, manufacturing enterprises need a high level of agility to adapt fast and with low costs to small batches of diversified products. They also need to reduce the environmental impact and adopt the paradigm of the circular economy. In the configuration space defined by this duality, manufacturing systems must embed a high level of reconfigurability at the level of their equipment. Finding the most appropriate concept of each reconfigurable equipment that composes an eco-smart manufacturing system is challenging because every system is unique in the context of an enterprise’s business model and technological focus. To reduce the entropy and to minimize the loss function in the design process of reconfigurable equipment, an evolutionary algorithm is proposed in this paper. It combines the particle swarm optimization (PSO) method with the theory of inventive problem-solving (TRIZ) to systematically guide the creative potential of design engineers towards the definition of the optimal concept over equipment’s lifecycle: what and when you need, no more, no less. The algorithm reduces the number of iterations in designing the optimal solution. An example for configuration design of a reconfigurable machine tool with adjustable functionality is included to demonstrate the effectiveness of the proposed algorithm.

Risk management is a key activity in every organization. The identification and evaluation of all risks in higher education institutions lead to the continuous monitoring of investments in people, high technology, and innovation. This paper evaluates the relative efficiency of study programs in Romanian higher education using the DEA method. This study is based on 38 study programs from a public university in Romania, using a traditional DEA approach: CRS-DEA and VRS-DEA models, with an output orientation for three academic years (2016–2019). To avoid distortions in the efficiency scores, we decided to implement the bootstrap method to correct DEA efficiencies. The results show that only four study programs were efficient during this period under the CRS-DEA approach, and eight study programs were efficient under the VRS-DEA model. According to scale efficiency and the bootstrap method, the results also showed that four study programs were efficient during the period analyzed. Finally, we observed that the inefficiency of study programs is relatively persistent (89%), compared with efficient DMUs (11%). Based on these findings, higher education institutions should consider the possibility of increasing the quality of study programs correlated with the degree of attractiveness of various programs in the current socio-economic environment.