Predictive maintenance in a manufacturing company is strategic, in order to maintain high production quality and to avoid unexpected production downtimes. In this scenario, the prediction of future machineries health status is necessary in order to plan maintenance cycles and to optimize the production. The proposed approach relies on the use of Electronic Design Automation (EDA) techniques mapped from the electronic domain to the production line domain. This paper proposes a general framework based on the EDA approach that allows to set-up a maintenance strategy by analyzing data retrieved from sensors. An MSM, is associated to each observable measurement, while a Supervisor monitors the current state of each Monitoring State Machine (MSM) by raising alerts when the monitored equipment is deviating from its normal behavior. This framework is the Digital-Twin of the plant devoted to its monitoring. It has some execution modalities ranging from online monitoring to predictive maintenance. The methodology has been applied to a mechanical transmission system showing its effectiveness.
We present a toolehain based on Docker and KubeEdge that enables containerization and orchestration of ROS-based robotic SW applications on heterogeneous and hierarchical HW architectures. The toolchain allows for verification of functional and real-time constraints through HW-in-the-loop simulation, and for automatic mapping exploration of the SW across Cloud-Server-Edge architectures. We present the results obtained for the deployment of a real case of study composed by an ORB-SLAM application combined to local/global planners with obstacle avoidance for a mobile robot navigation.Continua a leggere
The advent of Industry 4.0 is making production processes every day more complicated. As such, early process validation is becoming crucial to avoid production errors thus decreasing costs. In this paper, we present an approach to validate production recipes. Initially, the recipe is specified according to the ISA-95 standard, while the production plant is described using AutomationML. These specifications are formalized into a hierarchy of assume-guarantee contracts. Each contract specifies a set of temporal behaviors, characterizing the different machines composing the production line, their actions and interaction. Then, the formal specifications provided by the contracts are systematically synthesized to automatically generate a digital twin for the production line. Finally, the digital twin is used to evaluate, and validate, both the functional and the extra-functional characteristics of the system.The methodology has been applied to validate the production of a product requiring additive manufacturing, robotic assembling and transportation.Continua a leggere
Today's factory machines are ever more connected with SCADA, MES, ERP applications as well as external systems for data analysis. Different types of network architectures must be used for this purpose. For instance, control applications at the lowest level are susceptible to delays and errors while data analysis with machine learning procedures requires to move a large amount of data without real-time constraints. Standard data formats, like Automation Markup Language (AML), have been established to document factory environment, machine placement and network deployment, however, no automatic technique is currently available in the context of Industry 4.0 to choose the best mix of network architectures according to spacial constraints, cost, and performance. We propose to fill this gap by formulating an optimization problem. First of all, spatial and communication requirements are extracted from the AML description. Then, the optimal interconnection of wired or wireless channels is obtained according to application objectives. Finally, this result is back-annotated to AML to be used in the life cycle of the production system. The proposed methodology is described through a small, but complete, smart production plant.Continua a leggere
This paper analyzes a set of languages and standard used when designing industrial plants. It focuses on AutomationML and B2MML to specify respectively the architecture and the intended production of the system being designed. It also relies on the DIN 8580 standard to describe the actions performed by each machine composing the production line. Then, it outlines a methodology starting by mapping the information expressed by the analyzed languages and standards into the Assume-Guarantee Contracts formalism. It exploits contract-based design concepts to tackle the increase automation of the industrial plant design process and to enable the generation of digital twins. The approach is outlined by showing its applicability to a concrete manufacturing scenario.Continua a leggere
The approach we present in this paper exploits assume-guarantee reasoning through contracts to model a production line, and to generate its virtual prototype for efficient and correct plant simulation. Contracts are used to model the different parts composing the line; the modeling is guided by a well-known taxonomy associating industrial machines to manufacturing processes and their elementary actions, each represented by a contract. The composition of contracts representing the actions of a machine specifies each possible manufacturing process implemented by the machine. Then, automatic synthesis from contracts is used to generate an executable model of the machines composing the plant. The generated models are finally integrated into a state-of-the-practice industrial plant simulation software to validate the execution of the production line.The entire methodology is presented by showing its step-by-step application to a concrete scenario.Continua a leggere