Mission

Engineering Intelligence and Innovation (EII) is a peer-reviewed English journal dedicated to practice-oriented engineering intelligence—work that is usable, deployable, and sustainable under real-world constraints. We welcome end-to-end contributions spanning problem formulation, data acquisition & governance, model design, simulation/optimization, and system integration—along with monitoring and continuous improvement after deployment. EII serves a broad range of engineering domains including manufacturing, infrastructure, energy, transportation, and the built environment, and values transferable insights from practice-based training and project-driven engineering. Beyond benchmark metrics, EII emphasizes measurable field impact, reliability, maintainability, and honest reporting of limitations and trade-offs.

Scope & principles

EII spans the full spectrum “from lightweight techniques to foundation models,” including rule-based systems, statistics, classical ML, small models, deep and reinforcement learning, knowledge-informed approaches, digital twins, and multimodal/generative foundation models engineered for practice. We focus not only on models, but also on systems: data lineage and labeling strategy, simulation-to-field feedback loops, integration with existing software and operational controls, post-deployment monitoring and rollback, and human-in-the-loop collaboration and workflow design. We encourage reproducible evaluation and auditable data governance, and welcome robust solutions that remain stable under constrained resources, messy operating conditions, and high-reliability requirements— including lessons learned from failures and boundary conditions.

Audience & value

EII is for readers who want to use intelligence in practice: engineers, researchers, system builders, operations teams, and practice-based training or project-driven groups. We welcome interdisciplinary work, but prioritize engineering deliverables—so readers can reproduce key steps, judge suitability under constraints, and embed methods into real systems and workflows.

What we expect in submissions

To keep papers genuinely useful, EII encourages authors to provide (as applicable): context and constraints, data provenance and quality control, comparison to practical baselines, offline and in-field evaluation, deployment and maintenance details, safety and reliability considerations, and reproducibility materials (code/configuration/data documentation). Not every item is required for every paper, but readers should be able to understand why design choices were made, how the solution works in practice, and where it may fail.

• Problem & constraints — objectives, KPIs, operating conditions, resource limits (latency/compute/cost), and operational rules.
• Data & governance — provenance, missing/noisy data handling, labeling strategy, versioning, and auditability.
• Method choice & baselines — rationale for the chosen complexity and comparisons to practical “just-enough” baselines.
• Evaluation — beyond offline metrics, report field KPIs, robustness, regression risk, and performance under varying conditions.
• Deployment & maintenance — architecture, integration interfaces, monitoring/alerting, updates/rollback, and observability.
• Reliability, safety & responsibility — failure handling, cost of errors, explainability needs, safety boundaries, and human oversight.

Editorial focus

EII takes an “engineering-first” approach: papers should help readers make better decisions under real constraints and embed intelligence into systems and workflows in a maintainable way. We pay particular attention to the following types of contributions:

• Runnable engineering AI systems — end-to-end pipelines from problem framing to operations, with constraints, integration details, and verifiable outcomes.
• Lightweight solutions & field craft — “just-enough” intelligence and practical tips that improve robustness and maintainability.
• Foundation models for engineering — LLM/multimodal applications for documentation, diagnosis copilots, parameter recommendation, and automation, with reliability and safety boundaries.
• Data, simulation & digital twins — data governance, labeling, simulation assets, twin building methods, and integration with optimization/control/decision-making.
• Systems, platforms & toolchains — edge–cloud patterns, deployment monitoring, online updates, rollback, observability, and compliance practices.
• People, workflows & capability building — human-in-the-loop collaboration, workflow redesign, and transferable experiences from practice-based training and project learning.

What we publish

• Research Articles — original research on real engineering problems with clear validation and measurable value (beyond offline metrics).
• Engineering AI in Action — end-to-end deployment case studies: context, data, design choices, integration, operational outcomes, and lessons learned.
• Lightweight Intelligence — “just-enough” solutions (rules, statistics, classical ML) and practical engineering tips for stable operation.
• Methods & Tools — engineering-ready methods, implementations, datasets/benchmarks, toolchains, and best practices.
• Data, Simulation & Digital Twins — datasets, benchmarks, simulation assets, digital twin methodologies, and their integration with intelligent decision-making.
• Systems & Toolchains — architectures, deployment & monitoring, edge–cloud patterns, online updates, observability, and safety practice.
• Reviews & Roadmaps — surveys, benchmarking analyses, and forward-looking roadmaps with actionable guidance.
• Perspectives & Practice Notes — short articles and practitioner viewpoints, including “what went wrong” and how to fix it.

Topics (non-exhaustive)