Literature Review Data for a Multimodal Framework in SME Process Planning

This dataset contains a comprehensive collection of literature and evaluation data in support of the study, 'Knowledge-Infused Sequence Generation: A Multimodal Framework for Validated Process Planning in SMEs'. The data provides an empirical basis for systematically deriving and evaluating three distinct architectural patterns designed for automated process planning in SMEs. Within the associated study, these patterns (Practicality, Validity and Adaptability) are synthesised using the Architecture Trade-off Analysis Method (ATAM). Content of this dataset: - Literature source list: A curated list of scientific publications referenced in Table 2 of the paper, covering computer vision (CNN, ViT and OCR), sequence generation (RNN, LSTM and transformers) and knowledge infusion (ontologies and neuro-symbolic AI). - Technology assessment: A comparative ranking of the identified technologies based on SME-specific requirements, such as data sovereignty, hardware efficiency and system adaptability. - Detailed Technology Justification Matrix: A granular assessment and reasoning for the selection of specific technologies (e.g., CNN vs. ViT, LSTM vs. GRU) against the primary evaluation criteria: o Data Scarcity Resilience: Performance and stability in "small data" environments. o Hardware Efficiency: Suitability for deployment on low-power industrial edge devices. o Technological Validity: Ability to enforce manufacturing constraints through knowledge integration. o Maintenance Effort: Complexity of implementation and updates without specialized AI staff. Usage Note: This dataset is intended for researchers and engineers in the field of Computer-Aided Process Planning (CAPP) and Industrial AI who wish to replicate the technology selection process or extend the framework to other manufacturing domains.