Evidence-Based and Explainable Smart Decision Support for Quality Improvement in Stainless Steel Manufacturing

This article demonstrates the use of data mining methods for evidence-based smart decision support in quality control. The data were collected in a measurement campaign which provided a new and potential quality measurement approach for manufacturing process planning and control. In this study, the machine learning prediction models and Explainable AI methods (XAI) serve as a base for the decision support system for smart manufacturing. The discovered information about the root causes behind the predicted failure can be used to improve the quality, and it also enables the definition of suitable security boundaries for better settings of the production parameters. The user’s need defines the given type of information. The developed method is applied to the monitoring of the surface roughness of the stainless steel strip, but the framework is not application dependent. The modeling analysis reveals that the parameters of the annealing and pickling line (RAP) have the best potential for real-time roughness improvement.

Design for Manufacturing: geometric manufacturability evaluation for 5-axis milling

The geometric manufacturability of a part design is an important decision factor for various manufacturing applications and is especially critical for the machining process. In machining, the geometric manufacturability is primarily determined by the geometric accessibility, which has a direct impact on decisions such as setup planning, tool selection, tool orientation selection/adjustment, and the tool path strategies. These planning decisions can have significant impact on cycle time and cost. Thus, it can be justified that geometric manufacturability is one of the essential product design aspects that must be evaluated for machining processes. Being able to evaluate the geometric manufacturability will not only provide a part design metric but also offer a new approach for manufacturing process planning and optimization. This research proposes a new method for determining the geometric manufacturability of a part designed for 5-axis milling. In this work, the part design is input as polygon mesh boundary represented models, the 3D tool geometry is sampled to line segments, the 3D geometric accessibility of the part design is calculated, and a new metric for 5-axis milling manufacturability evaluation is developed. Case studies on complex mechanical component design examples are conducted to validate the method.

How to Establish Digital Thread Using 3D Factory

In a manufacturing assembly line scenario, factory layout is one of the most crucial information used by manufacturing, facility and factory automation engineers for planning purposes. It is important for manufacturing, facility and operations team to work with most up-to-date layout when product, process and operational information on the shop-floor is constantly changing. There are four elements which governs availability of a real-time layout, these are nothing but Product Design, Manufacturing Process Planning, Layout Planning and Shop-floor. The layout must accommodate these changes coming from product design, process updates and shop-floor modifications on real-time basis so that there is no confusion amongst the stakeholders while referring layout data for their planning purpose. If we talk about the impact on the layout because of product design and process design, it is hardly managed real-time due to the isolated systems to manage these data. The integration of product, process and plant (PPP) is becoming crucial to facilitate collaboration and shrink new product introduction lead time where as real-time update from the shop-floor changes is expected in the era of digital transformation. One of the reasons why the integration of product, process and plant (PPP) does not happen is multiple isolated systems used to maintain this data, there are also challenges to feed data back from the shop-floor because of the non-availability of the thread between these objects. The paper is about how factory layout can be developed integrating product, process and plant (PPP) in a single dynamic environment and establish a digital thread between the product design, manufacturing process planning and factory layout to trigger real-time changes and facilitate digital twin of the factory. The methodology adopted here is to develop bill of material for manufacturing resources and align it with the product data management. This approach not only provides ability to maintain change control over resource objects but also helps in configuration management of the resource bill of material. The resources are grouped together as layout structure for the plant with each object required to manufacture the product. The detailed layout developed for the plant while integrating with product and process is used to establish connection with objects on the shop-floor through sensors and IOT (Internet of Things) devices to form digital twin. Such details added in layout which is So far there are no efforts to digitalize every information on the factory floor and able to generate Digital Twin of the factory by connecting physical objects with the digital objects. Paper will elaborate the approach to establish digital thread between PPP and how this can become foundation to drive digital twin of the factory.

LEAN MANUFACTURING PROCESS PLANNING FOR 5 AXES CNC DRIVEN MILLING MACHINE

The aim of this publication is to determine the OEE (Overall Equipment Efficiency) indicator for 5 axes milling machine found at Diehl Aircabin Hungary Ltd. for the present and future state. Based on this value, the utilization of the machine for the given production amount can be calculated. With the optimal choice of the right production parameters (the number of cuts, feeding, depth of cut, etc.) greater productivity can be achieved i.e. the machine main time (time of cutting) will be less. The possibilities of the reduction of the machine time will be analysed and calculated. Setting of the appropriate technological parameters the machine main time could be decreased. The calculation of the machine main time will be determined for the most frequent manufacturing technologies.

Direct Solid Element Slicing in Topology Optimization for Additive Manufacturing

The traditional input to almost all commercially available Additive Manufacturing (AM) systems is in STL (Standard Tessellation Language) format, which represents a solid model by its tessellated surfaces. This does not allow transferring the entire information of a solid model to the additive manufacturing preprocessing system. However, in some recent applications such as additive manufacturing preprocessing simulation, closed-loop of topology optimization and additive manufacturing process planning, and AM-based design optimization the full access to the solid model information is necessary. Slicing of the finite element model directly is introduced in this paper. The presented approach enables access to the entire solid model information during the AM preprocessing tasks with a focus on coupling the topology optimization in the design process with the actual manufacturing constraints.