Established proof domain LMD / DED Exafuse-linked

AI for Laser Metal Deposition and Directed Energy Deposition

The established technical proof domain behind Manish Sharma Lab.

This hub keeps the LMD/DED authority layer easy to navigate without duplicating the detailed pages. It connects process monitoring, machine vision, robotic deposition, industrial repair, RFQ intelligence, and inspection-aware decision support.

Scope

What this domain includes

Laser Metal Deposition
Directed Energy Deposition
Laser cladding
Industrial repair
Robotic deposition
Process monitoring
Machine vision
RFQ intelligence
Inspection evidence

Decision system

LMD / DED is not just a process label

This page is the personal decision layer around a wider industrial additive manufacturing landscape: LMD, DED, DED-LB/M, laser cladding, SLM/LPBF, hybrid manufacturing, machining, repair, and replacement.

Why LMD/DED is a decision-system problem

A useful LMD decision combines material compatibility, geometry, damage state, access, heat input, post-machining, inspection, economics, and service risk. No single signal should become a final recommendation by itself.

Connection to repairability

Local damage on a large or valuable part can be a strong LMD signal, but only after material, damage depth, crack context, tolerance recovery, and inspection needs are visible.

Connection to quality evidence

Process monitoring and AI flags can guide review. Final confidence still depends on the inspection and validation evidence required by the part risk.

Connection to Exafuse public proof

Commercial manufacturing, repair, case details, and RFQs belong on Exafuse. This page interprets public LMD/DED proof through AI, evidence, repairability, and decision-system language.

What AI can help with

Useful decision support

structure RFQ facts, gaps, assumptions, risks, and next questions
compare LMD/DED, SLM/LPBF, cladding, machining, replacement, and hybrid routes
flag monitoring anomalies or drift candidates for human review
connect process signals to inspection planning and evidence levels
summarize repeat jobs, parameter history, photos, logs, and operator feedback
make uncertainty and missing information visible before a recommendation hardens

What AI cannot prove alone

Explicit limits

AI cannot certify material properties from process signals alone.
AI cannot turn melt-pool monitoring into final quality proof.
AI cannot approve safety-critical repair without inspection, testing, qualification, and expert review.
AI cannot recover missing material grade, damage depth, geometry, service load, or acceptance criteria.
AI cannot guarantee a repair, coating, or build outcome.

What changes the decision

The route can change when risk or evidence changes

Use this block before treating LMD, DED, SLM/LPBF, cladding, repair, or replacement as an obvious answer.

Unknown material
Crack depth or damage beyond visible wear
Tight tolerance and no post-machining route
Internal channels or fine geometry
No inspection path
Safety-critical service
Qualification or certification requirement
Missing operating conditions

Exafuse canonical pages

Company-owned commercial and case-study context

Use these Exafuse routes according to the current link mode. Manish Sharma Lab links to company-owned service, RFQ, quality, technology, and public proof context instead of duplicating service pages.

Writing and definitions

Short notes and glossary pages

Use these pages when terminology, monitoring limits, RFQ structure, or process selection needs to stay precise.

Industrial services

Manish Sharma Lab is a public technical site. For industrial LMD/SLM services, company capabilities, case studies, or RFQs, use Exafuse as the industrial-service context.

Visit Exafuse