Computer-Aided Engineering (CAE) enables simulation experts to optimize complex models, but faces challenges in user experience (UX) that limit efficiency and accessibility. While artificial intelligence (AI) has demonstrated potential to enhance CAE processes, research integrating these fields with a focus on UX remains fragmented. This paper presents a multivocal literature review (MLR) examining how AI enhances UX in CAE software across both academic research and industry implementations. Our analysis reveals significant gaps between academic explorations and industry applications, with companies actively implementing LLMs, adaptive UIs, and recommender systems while academic research focuses primarily on technical capabilities without UX validation. Key findings demonstrate opportunities in AI-powered guidance, adaptive interfaces, and workflow automation that remain underexplored in current research. By mapping the intersection of these domains, this study provides a foundation for future work to address the identified research gaps and advance the integration of AI to improve CAE user experience.

Federated Learning (FL) and Reinforcement Learning (RL) show significant potential for industrial embedded systems, but their application is hindered by challenges like hardware constraints, data heterogeneity, and safety requirements, creating a research-practice gap. This systematic literature review synthesizes the state-of-the-art deployment of FL and RL on such systems, structuring findings across four challenge categories to identify research gaps. Our analysis of 61 studies reveals a dominance of simulation (66%), and FL (62%), with scarce hardware deployments (18%). The key barriers to industrial adoption are a lack of large-scale, real-world validation and unaddressed scalability challenges.

This systematic literature review analyzes how Generative AI (GenAI), specifically Large Language Models (LLMs), impacts Software Product Management (SPM). Based on recent studies, our analysis reveals that current research is in a nascent, experimental phase, focusing on task-level applications like requirements engineering and user persona generation, which show potential for efficiency gains. However, the field suffers from critical limitations, including a lack of methodological standardization, an over-reliance on a narrow range of LLMs like ChatGPT, and a focus on superficial efficiency metrics over measures of product success. We conclude that while LLMs show promise for discrete PM tasks, their true transformative potential lies in integrated, workflow-centric systems. This paper provides a baseline of the current research and calls for a more rigorous, impact-focused agenda for future studies.

The extraction of structured metadata from Piping and Instrumentation Diagrams (P&IDs) is a major bottleneck for digitalization in the process industries. Existing methods, based on Optical Character Recognition (OCR), stop at raw text extraction, failing to interpret critical engineering information encoded within variable-format identifiers like pipeline numbers. This paper bridges this semantic gap by introducing a system for the format-aware interpretation of P&ID pipeline metadata. Our hybrid system architecture integrates deep learning for text recognition with domain interpretation rules that allow the system to adapt to new project formats without model retraining. These rules perform validation, error correction, and semantic mapping of raw text to structured data. We validated our system on a challenging dataset of real-world P&IDs from four distinct industrial projects, each with a unique and complex pipeline number format. Our method achieved 91.1% end-to-end accuracy, demonstrating a significant leap in performance over standard OCR tools, which proved insufficient for the task. This work presents a robust solution that unlocks valuable data from non-standardized engineering documents, providing a practical pathway for creating reliable digital twins and supporting plant lifecycle management in the chemical engineering sector.

There are few technologies, if any, that have the potential to change the software-intensive industry to the extent that artificial intelligence (AI) is currently doing. Across industries, companies are adopting these technologies to improve productivity, to increase efficiency and to automate tasks. In products, AI is used for optimization and mass-customization. However, there are few examples of companies that use AI to reinvent and fundamentally change their existing practices. In this paper, we present results from an expert interview study in which we explore how AI is affecting the ways in which companies operate and what steps companies evolve through when advancing their use of AI in their development processes, in their products and in their business processes. The contribution of the paper is two-fold. First, we present the interview results that reflect the adoption and use of AI technologies. As part of our interviews, we also identify a set of key challenges that companies experience. Second, we present an inductively derived three-pronged maturity model that describes how companies transition from traditional towards AI-driven organizations.

Obtaining labels for supervised learning is time-consuming, and practitioners seek to minimize manual labeling. Semi-supervised learning allows practitioners to eliminate manual labeling by including unlabeled data in the training process. With many deep semi-supervised algorithms and applications available, practitioners need guidelines to select the optimal labeling algorithm for their problem. The performance of new algorithms is rarely compared against existing algorithms on real-world data. This study empirically evaluates 16 deep semi-supervised learning algorithms to fill the research gap. To investigate whether the algorithms perform differently in different scenarios, the algorithms are run on 15 commonly known datasets of three datatypes (image, text and sound). Since manual data labeling is expensive, practitioners must know how many manually labeled instances are needed to achieve the lowest error rates. Therefore, this study utilizes different configurations for the number of available labels to study the manual effort required for optimal error rate. Additionally, to study how different algorithms perform on real-world datasets, the researchers add noise to the datasets to mirror real-world datasets. The study utilizes the Bradley-Terry model to rank the algorithms based on error rates and the Binomial model to investigate the probability of achieving an error rate lower than 10%. The results demonstrate that utilizing unlabeled data with semi-supervised learning may improve classification accuracy over supervised learning. Based on the results, the authors recommend FreeMatch, SimMatch, and SoftMatch since they provide the lowest error rate and have a high probability of achieving an error rate below 10% on noisy datasets.

Context: Machine Learning Operations (MLOps) has become a top priority for companies. However, its adoption has become challenging due to the need for proper guidance and awareness. Most of the MLOps solutions available in the market are designed to fit the specific platform, tools and culture of the providers. Objective: The objective is to develop a structured approach to adopting, assessing and advancing MLOps adoption. Methods: The study was conducted based on a multi-case study across fourteen companies. Results: We provide a comprehensive analysis that highlights the similarities and differences in the adoption of MLOps practices among companies. We have also empirically validated the developed MLOps framework and MLOps maturity model. Furthermore, we carefully reviewed the feedback received from practitioners and revised the MLOps framework and maturity model to confirm its effectiveness. Additionally, we develop an MLOps taxonomy for classifying ML use cases based on their context and requirements into the desired stage of the MLOps framework and maturity model. Conclusion: The findings provide companies with a structured approach to adopt, assess, and further advance the adoption of MLOps practices regardless of their current status.

Within the Engineering, Procurement, and Construction (EPC) industry, engineers manually create documents based on engineering drawings, which can be time-consuming and prone to human error. For example, the expansion of typical assemblies of instrument items (Instrument Typicals) in Piping and Instrumentation Diagrams (P&IDs) is a labor-intensive task. Each Instrument Typical assembly is depicted in the P&IDs via a simplified representation showing only a subset of the utilized instruments. The expansion activity involves recording all utilized instruments to create an instrument item list document based on the P&IDs for a particular EPC project. Fortunately, Artificial Intelligence (AI) could help automate this process. In this paper, we propose the first method for automating the process of Instrument Typical expansion in P&IDs. The method utilizes computer vision techniques and domain knowledge rules to extract information about the Instrument Typicals from a project's P&IDs and legend sheets. Subsequently, the extracted information is used to automatically generate the listing of all utilized instruments. The effectiveness of our method is evaluated on P&IDs from large industrial EPC projects, resulting in precision rates exceeding 98% and recall rates surpassing 99%. These results demonstrate the suitability of our method for industrial deployment. The successful application of our method has the potential to reduce engineering costs and increase the efficiency of EPC projects. Furthermore, the method could be adapted for additional applications in the EPC industry, which highlights the method's industrial value.

The application of Vision Language Models (VLMs) to industrial automation, specifically engineering blueprint analysis, is severely hampered by the absence of domain-specific evaluation tools. Existing benchmarks fail to replicate the critical visual challenges of this domain, such as high symbol density, occlusion, and visual similarity. Furthermore, they assume reliable pre-trained knowledge or standardized symbology, which rarely hold in real-world industrial settings. To address these critical gaps, we introduce BlueprintSymVL, the first benchmark explicitly designed to evaluate VLM symbol recognition in engineering blueprints. BlueprintSymVL is engineered as a strong discriminator, with test cases that systematically introduce challenges to differentiate model capabilities. A key innovation is our robust evaluation method, centered on a one-shot visual in-context querying strategy. At query time, the model is provided with a visual exemplar of a symbol. This approach eliminates reliance on unreliable pre-existing knowledge and is paired with a strict evaluation criterion demanding correctness on both symbol counts and their labels, setting a rigorous standard for quality assurance in high-stakes applications. We conducted a comprehensive benchmark of four leading VLMs (GPT-4o, Gemini 2.5 Pro, InternVL 2.5 78B, and Qwen 2.5 VL 72B). Our analysis provides the first baseline on their readiness, revealing that BlueprintSymVL is highly discriminative. We pinpoint specific failure modes, including a notable degradation in cluttered environments, confusion when faced with visually similar distractors, and a concerning propensity to hallucinate symbols. These insights demonstrate that current VLMs are not yet suitable for autonomous deployment in blueprint analysis and are best integrated into human-in-the-loop workflows.

Manual analysis of diagrams and legend sheets in engineering projects is time consuming and needs automation. The lack of standardized legend formats complicates creating a general method for automated information extraction. Existing approaches require training and custom rules for each project. This study proposes a novel solution combining optical character recognition with vision language models and multimodal prompt engineering to automate information extraction from diverse legend sheets without training. It integrates legend information with information extracted from diagrams, unlike studies that only focus on diagrams. Our study shows that VLMs, guided by multimodal prompts, can accurately extract information from diverse legend sheets, enabling automatic information extraction in diagrams across engineering projects. We validate our method through a case study involving the extraction of instruments from piping and instrumentation diagrams (P&IDs) and their legends across three projects with varied formats and standards. The proposed method achieved 100% accuracy in legend classification and information extraction, and 99.68% precision and 95.91% recall in generating instrument listings. The results demonstrate the effectiveness of our approach, significantly enhancing the accuracy and efficiency of information extraction from diagrams. This method can be adapted to different legend formats and diagrams, providing a versatile solution for various industries.