The paper proposes a novel decomposition method aimed at supporting decision-making in manufacturing systems. The main goal of the presented technique is an adequate proposal for dividing the production process flow in the manufacturing system by delegating the selected activities to the outsourcing mode. In order to obtain such separated activities within a production process, the modelled system is decomposed into the set of components (sets of places) that are executed externally. The presented idea involves Petri net and hypergraph theories. In particular, the system is modelled by a Petri net and further decomposed with the use of hypergraph’s transversals. The key advantage of the proposed algorithm is many decomposition possibilities, since the activities performed as part of the production process in an outsourcing mode may be specified precisely, exactly conforming to the production strategy. It can be treated as a tool supporting decision-making by managers in the context of delegating tasks from the production process in an outsourcing mode. Such study complements the results of the analysis of cost and efficiency of the production process realized in a manufacturing enterprise.

The paper proposes a novel modelling and analysis technique of the system supporting implementation of additive manufacturing (AM) technologies specified by the interpreted Petri net. Nowadays, there is a need in a manufacturing enterprise to implement the new technologies supporting the realization of production, especially in terms of the possibility of unplanned crisis events. Managers expect such models to support their decisions in order to maintain or strengthen their competitive position thanks to the investments. Therefore, this paper proposes a system supporting the decision to implement AM technology, based on the interpreted Petri net, by utilizing its main advantages: the possibility of graphical modelling, and strong mathematical support of formal verification techniques. In particular, the proposed verification algorithm allows for detection of possible unbounded places. Contrary to the most popular analysis methods (which are bounded exponential in general case), it is proved that the presented technique is bounded by a cubic polynomial with the number of Petri net nodes. Finally, the presented modelling and analysis method is illustrated by a real-life case-study example of the decision-making model to support the implementation of AM technologies.Note to Practitioners—This paper is motivated by the limited performances in the existing modelling and analysis techniques of systems that support implementation of additive manufacturing (AM) technologies. In particular, the article proposes a system supporting the decision to implement AM technology, based on the interpreted Petri net. Existing approaches have important restrictions related to the exponential computational complexity of analysis methods. Therefore, verification of the model can be a real challenge to the designer. In contradistinction, the algorithm proposed in the paper permits the examination of the system in a polynomial time. The presented modelling and analysis ideas are illustrated by a real-life example of the decision-making system that utilizes implementation of AM technology. Managers of manufacturing enterprises, thanks to the use of the proposed approach, can assess the investment in AM technology in the following three unexpected situations: 1) delays in the delivery of materials and/or semi-finished products or the inability to receive materials and/or semi-finished products; 2) high employee turnover; 3) increasing costs of energy consumption. Thus, the application of this model allows for the harmonious conduct of manufacturing activities in conditions of unexpected situations.

This work deals with the verification of a decision-making system for additive manufacturing (AM) technology adoption specified by a Petri net. An innovative verification technique of a Petri net-based system is oriented toward practical applications, and can detect errors at the early design and modelling stage. The idea is illustrated by a real-life case study of supporting decision making in AM technology adoption affecting supply chain management (SCM). Two main issues are addressed. Firstly, making optimal decisions about AM technology requires models rarely possessed within a company. Therefore, this work proposes a model supporting the decision making related to the implementation of AM technology, based on a Petri net, by utilizing its main advantages: graphical modelling, and strong mathematical support of formal verification techniques. Contrary to the most popular analysis methods (which are bounded exponentially in a general case), it is proved that the presented method is bounded by a cubic polynomial with net size. Secondly, an investment in AM technology is often financially assessed and does not affect other processes, as in our SCM case. Hence, strong connectivity within the proposed Petri net-based model is examined.

Nowadays the sensor-based human activity recognition is a key issue in the field of the physical exercises’ recognition. The purpose of this paper is to recognise exercise sports, such as squats, pull-ups and dips, using a dataset based on three ultra-wideband (UWB) sensors with additional inertial data and a deep learning approach in order to achieve an appropriate rate of the recognition of sports exercises with reduced computational effort. Firstly, a dataset, containing 273 samples of dips, 215 samples of pull-ups and 956 samples of squats, plus an additional 2024 samples of the input signals acquired during breaks, was created. Next, an optimal set of hyperparameters of Convolutional Neural Network (CNN) architecture in order to balance the accuracy rate and computational effort was achieved. Finally, it was discovered that acceleration signals have the highest energy and therefore, a comparison of the accuracy rate between CNN, using all signals and CNN, using acceleration only, was carried out (97.5% vs. 97.7%). Moreover, much less computational effort, expressed in number of multiplications, (1.8e4 vs. 1.2e5) was achieved. The practical usefulness is presented, by facilitating the implementation of the presented UWB sensor-based system for recognising such physical exercises as squats, pull-ups and dips on smartphones and commonly available wearable sensor devices.

Integrating Additive Manufacturing (AM) technologies into manufacturing systems is regarded as a potential solution to improve the effectiveness of the production process flow in terms of the reduction of production costs, the involvement of human resources in the operation and the maximum use of materials. However, to date, the design of a model for the effectiveness of such integration is still an unresolved question. To find an answer to this question and help managers make decisions about AM technologies implementation, this paper applies Petri nets to the development of a formal model for the effectiveness of integrating AM technologies into manufacturing systems. The use of Petri nets in such context allows for modelling the correctness of the structure of the proposed production process improved by the AM technologies. The main novelty of the idea refers to the detailed description of the parameters of the production process integrating AM technologies. Moreover, new methods are proposed for boundedness and safeness verification of the Petri net-based manufacturing system (supported by an adequate algorithm, proposition, and proof). The presented model is illustrated through a real-life case study example of the production process with AM technology.

The paper deals with the modelling and analysis of physical resilient manufacturing systems (RMS) specified by the interpreted Petri net. Nowadays a need to improve manufacturing resilience is evident due to several unexpected situations currently on the market. The production strategy of mass customization application of RMS on the physical layer enables quick and cost-effective reaction to changing market and social conditions. Such systems should be capable of operating under any changes in production. Therefore, in this paper, a novel modelling concept of Petri net-based physical RMS for mass customisation production is proposed. The idea is based on the interpreted Petri net, which permits for additional specification of input and output signals of the system. Moreover, such a net ought to be live and bounded (or even safe), therefore a boundedness and safeness verification algorithm is developed. The proposed techniques are illustrated by the real-life case-study example of a RMS at the physical layer operating according to a mass customisation production strategy.

In the case of industrial solutions, in the context of Industry 4.0, Artificial Neural Networks (ANNs) currently dominate almost all tasks related to the optimisation of manufacturing processes. For manufacturing enterprises, a quick and precise response to customers needs is crucial for gaining a competitive advantage, therefore, managers should invest in new technologies, such as Additive Manufacturing (AM) technologies. However, these activities are very costly, so it seems that a good solution would be to encourage enterprises to cooperate with specialized research laboratories offering material research in the field of the AM technologies used. This paper proposes a new framework to determine the types and quantities of devices in the field of AM technologies, with which such a research laboratory should be equipped. The proposed AI-based Decision Support System (AI-DSS) integrates the results of a survey of 250 manufacturing companies in western Poland, the use of the Ensemble Neural Network (ENN) Model and the use of a Genetic Algorithm (GA) to determine the profitability of investing in research laboratories, especially in AM technologies. Firstly, in order to reduce variance and thus improve generalization of the proposed model, the combination of outputs of several networks forming ENN was proposed. For this purpose, the bootstrap technique was used, resulting in a model with 75% accuracy being obtained. Next, using the fitness function in a GA algorithm, the research laboratory optimal configuration was determined. Finally, its practicality is presented by applying AI-DSS in the design of the current and future workload of devices, in order to find the optimal configuration in the research laboratory.

Managers are looking for solutions that will be helpful when deciding on the purchase of new technologies, in order to adapt the enterprise to the Industry 4.0 concept. Nowadays, many approaches suitable for smart manufacturing systems involving maintenance workers are based on Artificial Neural Networks (ANN). This paper presents an approach to measuring the effectiveness of the use of an IT system supporting the realisation of business processes in the maintenance department and describes the empirical research results of maintenance workers (121) within Polish manufacturing companies with automotive branches. Finally, this paper seeks to integrate the first two main research results and ANN, into a novel, decision-making model regarding the implementation of activities and investments aimed at increasing the level of a company’s automation. The architecture of ANN classifier was chosen in a series of experiments. The Levenberg-Marquardt method and genetic algorithms were used in training process. The performance of the classifier was measured using the sum of squared errors and the error function with the regularisation term in the form of the sum of squared norms of Jacobian matrices. The best performing classifier achieved 95.8% accuracy on the test dataset.