Industrial AI & Decision Systems LMD / DED proof domain Decision support only

Manish Sharma Lab

AI for Laser Metal Deposition decisions you can verify.

I build inspection-aware AI frameworks, RFQ tools, and process-monitoring notes for LMD/DED, repair, cladding, and metal additive manufacturing - grounded in public Exafuse work and bounded by engineering evidence.

Decision support only. Not final engineering approval.

Start LMD Decision Cockpit Open Decision Map Open Workbench Read Thesis Request Exafuse review

Who

Manish Sharma

Builds

inspection-aware AI tools

Proof

public Exafuse LMD/DED context

One compact operating loop

Sense -> Model -> Decide -> Verify

Signal, assumption, bounded decision, verification evidence. The detailed doctrine lives in the thesis.

Open thesis

Flagship assets

Start with the three LMD decision assets

These are the shortest route from a vague LMD/DED question to a structured decision-support workflow.

LMD Quality Evidence Ladder

Problem: Monitoring data is often treated as release proof.
Helps decide: Which evidence level is needed for a claim.
Cannot prove: Final part quality without inspection/testing.

Open framework

LMD Repairability Index

Problem: Repair requests arrive before material, damage, access, and inspection facts are clear.
Helps decide: Whether a repair candidate is worth expert review.
Cannot prove: Repair feasibility, release, or service safety.

Open index

LMD RFQ Toolkit

Problem: Vague RFQs hide missing facts and risk flags.
Helps decide: How to structure known facts, gaps, assumptions, and next questions.
Cannot prove: Replace Exafuse commercial review or engineering approval.

Open toolkit

Public proof

Public proof that anchors the LMD/DED domain

Company-owned case details and RFQs belong to Exafuse. Manish Sharma Lab uses these only as public context for frameworks, monitoring, repairability, RFQ structure, and evidence boundaries.

Open proof map Open claim ledger

CS15 Public Exafuse source

Duisburg Bridge Components

750 kg+ components6 structural nodes219 h single-node buildapprox. 38 km robot path1M+ melt-pool imagesKIT validation context

Decision it helps: Helps decide how much evidence is needed before large-part LMD monitoring data becomes a defensible engineering discussion.
Source status: Source link pending until Exafuse production migration
What it proves: Public context for large-part LMD scale, monitoring, validation, and inspection planning in one documented Exafuse case.
What it does not prove: It does not prove that monitoring alone certifies quality or that this site can approve structural parts.
Related framework: LMD Quality Evidence Ladder
Decision pattern extracted: Large-scale LMD requires evidence planning, monitoring context, and an inspection boundary.

This is a pattern, not a transfer of feasibility.

Start a brief from this pattern Contact Exafuse

CS01 Public Exafuse source

Forging Hammer Repair

local wear repair

Decision it helps: Helps decide whether local wear repair should move into expert review instead of becoming an automatic repair claim.
Source status: Source link pending until Exafuse production migration
What it proves: Public context for local wear repair, material strategy, finishing, and release-evidence planning.
What it does not prove: It does not prove every hammer or safety-critical part is repairable.
Related framework: LMD Repairability Index
Decision pattern extracted: Local repair needs material, damage depth, machining route, and inspection plan.

This is a pattern, not a transfer of feasibility.

Start a brief from this pattern Contact Exafuse

CS10 Public Exafuse source

Nobufil Extrusion Screw Repair

local crack context

Decision it helps: Helps decide which missing RFQ facts block a repairability conversation.
Source status: Source link pending until Exafuse production migration
What it proves: Public context for RFQ intelligence around local damage, downtime pressure, drawings, machining, and inspection needs.
What it does not prove: It does not prove feasibility without part-specific material, damage, geometry, and service context.
Related framework: LMD RFQ Toolkit
Decision pattern extracted: Repair/RFQ quality depends on complete facts, downtime context, and service context.

This is a pattern, not a transfer of feasibility.

Start a brief from this pattern Contact Exafuse

CS13 Public Exafuse source

130 mm Build-and-Coat Drill

130 mm build-and-coat drill

Decision it helps: Helps decide when build-up and surface function must be planned as one route.
Source status: Source link pending until Exafuse production migration
What it proves: Public context for combining build-up, coating function, material choice, and finishing strategy.
What it does not prove: It does not prove surface performance without application-specific validation.
Related framework: LMD Quality Evidence Ladder
Decision pattern extracted: Build-and-coat routes need geometry, surface function, material, finishing, and validation.

This is a pattern, not a transfer of feasibility.

Start a brief from this pattern Contact Exafuse

AI for Laser Metal Deposition decisions you can verify.

Start with a rough LMD question. Leave with a brief.

A signal is not proof.

Sense -> Model -> Decide -> Verify

Choose the path that matches your question

Start with the three LMD decision assets

LMD Quality Evidence Ladder

LMD Repairability Index

LMD RFQ Toolkit

Public proof that anchors the LMD/DED domain

Duisburg Bridge Components

Forging Hammer Repair

Nobufil Extrusion Screw Repair

130 mm Build-and-Coat Drill

Use this site for public frameworks and AI-readable guidance.

For services, RFQs, and company claims, use Exafuse.