In the quest to enhance the efficiency of gas turbines, there is a growing demand for innovative solutions to optimize high-pressure turbine blade cooling. However, the traditional methods for achieving this optimization are known for their complexity and time-consuming nature. We present an automation framework to streamline the design, meshing, and structural analysis of cooling channels, achieving design automation at both the morphological and topological levels. This framework offers a comprehensive approach for evaluating turbine blade lifetime and enabling multidisciplinary design analyses, emphasizing flexibility in turbine cooling design through high-level CAD templates and knowledge-based engineering. The streamlined automation process, supported by a knowledge base, ensures continuity in both the mesh and structural simulation automations, contributing significantly to advancements in gas turbine technology.

Fixture layout is a complex task that significantly impacts manufacturing costs and requires the expertise of well-trained engineers. While most research approaches to automating the fixture layout process use optimization or rule-based frameworks, this paper presents a novel approach using supervised learning. The proposed framework replicates the 3-2-1 locating principle to layout fixtures for sheet metal designs. This principle ensures the correct fixing of an object by restricting its degrees of freedom. One main novelty of the proposed framework is the use of topographic maps generated from sheet metal design data as input for a convolutional neural network (CNN). These maps are created by projecting the geometry onto a plane and converting the Z coordinate into gray-scale pixel values. The framework is also novel in its ability to reuse knowledge about fixturing to lay out new workpieces and in its integration with a CAD environment as an add-in. The results of the hyperparameter-tuned CNN for regression show high accuracy and fast convergence, demonstrating the usability of the model for industrial applications. The framework was first tested using automotive b-pillar designs and was found to have high accuracy (approximate to 100%) in classifying these designs. The proposed framework offers a promising approach for automating the complex task of fixture layout in sheet metal design.

Implementation of Machine Learning (ML) to improve product and production development processes poses a significant opportunity for manufacturing industries. ML has the capability to calibrate models with considerable adaptability and high accuracy. This capability is specifically promising for applications where classical production automation is too expensive, e.g., for mass customization cases where the production environment is uncertain and unstructured. To cope with the diversity in production systems and working environments, Reinforcement Learning (RL) in combination with lightweight game engines can be used from initial stages of a product and production development process. However, there are multiple challenges such as collecting observations in a virtual environment which can interact similar to a physical environment. This project focuses on setting up RL methodologies to perform path-finding and collision detection in varying environments. One case study is human assembly evaluation method in the automobile industry which is currently manual intensive to investigate digitally. For this case, a mannequin is trained to perform pick and place operations in varying environments and thus automating assembly validation process in early design phases. The next application is path-finding of mobile robots including an articulated arm to perform pick and place operations. This application is expensive to setup with classical methods and thus RL enables an automated approach for this task as well.

Selecting an appropriate machine learning model architecture for manufacturing tasks requires expertise in both computer science and manufacturing. However, integrating state-of-the-art machine learning models and manufacturing processes is often challenging due to the distance between these fields. OpenAI’s popular language model, ChatGPT, has the potential to bridge this gap.

This paper proposes guidelines and questions to explore model architecture options and extract valuable information from ChatGPT’s natural language processing capabilities. While ChatGPT is a powerful tool, it is important to verify any answers obtained against reliable sources before making any decisions. The guidelines compose a flowchart with four queries to give ChatGPT enough context and exisiting input data information. ChatGPT suggestions will be directed towards input processing, output, and architecture proposals. The last query produces keywords based on the chat for a background study on the topic.

A manufacturing case study was conducted to demonstrate the effectiveness of these guidelines. The study involved creating a model to forecast fixturing locations for welding processes in the automotive sector. After conducting four separate interviews with ChatGPT, the authors discuss the selection of architecture based on ChatGPT suggestions and contrast it with previous literature.

The proposed guidelines are expected to be useful in a variety of manufacturing contexts, as they offer a structured approach to exploring model architecture options using ChatGPT’s capabilities, ultimately leading to new and innovative applications of machine learning in this field.

Introduction: Digitization is a crucial step towards achieving automation in production quality control for mechanical products. Engineering drawings are essential carriers of information for production, but their complexity poses a challenge for computer vision. To enable automated quality control, seamless data transfer between analog drawings and CAD/CAM software is necessary.

Methods: This paper focuses on autonomous text detection and recognition in engineering drawings. The methodology is divided into five stages. First, image processing techniques are used to classify and identify key elements in the drawing. The output is divided into three elements: information blocks and tables, feature control frames, and the rest of the image. For each element, an OCR pipeline is proposed. The last stage is output generation of the information in table format.

Results: The proposed tool, called eDOCr, achieved a precision and recall of 90% in detection, an F1-score of 94% in recognition, and a character error rate of 8%. The tool enables seamless integration between engineering drawings and quality control.

Discussion: Most OCR algorithms have limitations when applied to mechanical drawings due to their inherent complexity, including measurements, orientation, tolerances, and special symbols such as geometric dimensioning and tolerancing (GD&T). The eDOCr tool overcomes these limitations and provides a solution for automated quality control.

Conclusion: The eDOCr tool provides an effective solution for automated text detection and recognition in engineering drawings. The tool's success demonstrates that automated quality control for mechanical products can be achieved through digitization. The tool is shared with the research community through Github.

This paper presents a framework to develop the automated design of fixtures using the combination ofdesign automation (DA), multidisciplinary optimization and robotic simulation. MDO necessitates the useof concurrent and parametric designs which are created by DA and knowledge-based engineering tools. Thisapproach is designed to decrease the time and cost of the fixture design process by increasing the degree ofautomation. AutoFix provides methods and tools for automatically optimizing resource-intensive fixturedesign utilizing digital tools from different disciplines.

This paper describes a methodology for automation of measurements in Computer-Aided Design (CAD) software by enabling the use of supervised learning algorithms. The paper presents a proof of concept of how dimensions are placed automatically in the drawing at predicted positions. The framework consists of two trained neural networks and a rule-based system. Four steps compound the methodology. 1. Create a data set of labeled images for training a pre-built convolutional neural network (YOLOv5) using CAD automatic procedures. 2. Train the model to make predictions on 2D drawing imagery, identifying their relevant features. 3. Reuse the information extracted from YOLOv5 in a new neural network to produce measurement data. The output of this model is a matrix containing measurement location and size data. 4. Convert the final data output into actual measurements of an unseen geometry using a rule-based system for automatic dimension generation. Although the rule-based system is highly dependent on the problem and the CAD software, both supervised learning models exhibit high performance and reusability. Future work aims to make the framework suitable for more complex products. The methodology presented is promising and shows potential for minimizing human resources in repetitive CAD work, particularly in the task of creating engineering drawings.

Cable and hose routing is a complex and time-consuming process that often involves several conflicting objectives. Complexity increases further when routes of multiple components are to be considered through the same space. Extensive work has been done in the area of automatic routing where few proposals optimize multiple hoses together. This paper proposes a framework for the routing of multiple pre-formed hoses in an assembly using a unique permutation process where several alternatives for each hose are generated. A combinatorial optimization process is then used to find Pareto-optimal solutions for the multi-route assembly. This is coupled with a scoring model that predicts the overall fitness of a solution based on designs previously scored by the engineer as well as an evaluation system where the engineer can score new designs found through the use of the framework to update the scoring model. The framework is evaluated using a testcase from a car manufacturer showing a severalfold time reduction compared to a strictly manual process. Considering the time savings, the proposed framework has the potential to greatly reduce the overall routing processes of hoses and cables.

Maintaining high product quality while reducing cost is essential for mass-customised products, requiring continuous improvement of the product development process. To this end, design automation should be utilised in all stages of a product’s develop process and lay the foundation for automation of repetitive tasks throughout the process from interaction with the customer to design and production in order to mitigate errors and minimise costs. In this paper, a design automation and production preparation framework is proposed that can facilitate automation from initial stages via CAD to production. Examples of the framework are shown in the shape of proof-of-concepts systems developed by master students in the context of a course in design automation at Linköping University. Included disciplines such as automated planning of robot assembly paths, CNC manufacturing files and production drawings are described, based on design automation, Knowledge-Based Engineering, and design optimisation. Additionally, variations of the framework are implemented at three SMEs, and the results thereof are presented. The proposed frameworks enable interaction and connection between the "softer", human centred, aspects of customer interaction within sales, with more traditional "harder" engineering disciplines in design and manufacturing.

Companies manufacturing customized engineer-to-order (ETO) products are decelerated by repetitive work, misinterpretations and uncoordinated processes which prohibits the achievement of mass customization. Being able to deliver customized product with low costs and fast delivery times, the concept of mass customization, is a prerequisite for maintained competitiveness with the demands from the market today. This paper presents a product configuration system (PCS) for customized products using design automation enabled by knowledge-based engineering (KBE) and enterprise-wide optimization (EWO). With this approach, the process from sales to delivery of customized products can be extensively rationalized. The PCS consists of two modules. The first being a configurator for use in the sales quotation stage. Here, customer requirements are captured, and used to generate alternatives feasible for the customer context. Thereby, correct quotations can be generated at the sales instance. The second module is the enterprise-wide configurator where accepted orders are concurrently optimized for their detailed and final design, considering the current state of the production and concurrent sales cases in the company. In other terms, instead of adapting the supply chain according to the design of the products in the order entry, the design of the products in the order entry are adapted according to the state of the supply chain. Thereby, resources can be efficiently utilized to the benefit of both the customer and the company, with reduced costs and delivery times. An implementation of the PCS in a case concerning spiral staircases, an ETO product, has shown potential of substantially reducing resources and errors and enable a reliable process supporting achievement of mass customization.