See inside every part without cutting a single one open
X-ray inspection reveals what surface inspection never will: internal voids and porosity, foreign material inside sealed packages, missing internal components, and fill levels in opaque containers. It removes destructive sampling — the cut-and-scrap audits that check a fraction of production and destroy the parts they check.
Willowark integrates proven X-ray sources and digital detectors into production lines rather than reinventing the physics. Our work is the system engineering around them: specifying energy and geometry for your material, automating the image analysis, handling the material flow, and making sure the radiation safety story is airtight.
Vision & Advanced SensingHow the work gets done
The same way every time: scope, build, hand over.
Specification starts with penetration physics: source voltage and power matched to your material thickness and density, detector pixel pitch and geometry set by the smallest defect that matters, and magnification arranged so that defect spans enough pixels to detect reliably. Around the imaging core sits the machinery of a real line — conveyance through the shielded cabinet, safety-interlocked shielding with documented survey results, and coordination with your radiation safety officer on state registration requirements. Automated defect recognition software then does what human screeners cannot at line speed: consistent detection of voids, inclusions, and foreign objects, image after image.
Validation uses seeded samples: parts and packages with known, characterized defects run through the system to establish detection probability by defect size and type, alongside false-reject rate and throughput. In production, every image can be archived against a part or lot identifier — a traceability record that matters enormously in food safety programs, weld documentation, and customer quality audits.
Feasibility is a set of scans, not a conversation. We arrange for your parts or packages — including samples with known internal defects — to be imaged on candidate equipment at a range of energies and geometries, and we review the images to agree on what is visible at what size. That session also settles the analysis approach: classical contrast and morphology tools work well for voids and dense foreign material against a uniform background, while learned models earn their place on products with variable internal structure, such as packaged food, where foreign material resists a written rule. Either way the acceptance criteria are recorded before equipment is specified.
Integration into the line is mostly material handling and timing. Product must enter and leave the shielded cabinet through tunnels sized to block scatter, arrive at the detector at a steady speed matched to the exposure, and reach the reject device with the decision still attached to the right item. Detector gain and offset calibrations, source warm-up routines, and periodic test-piece checks are automated so the system verifies itself at shift start and refuses to run inspection if the check fails. Handover includes the software source, the calibration and test-piece procedures, and training for the operators and the radiation safety officer.
Scope it in writing
What we agree before work starts
- Feasibility study with sample scans of your parts or packages
- System specification: source, detector, geometry, and vendor selection
Build with checkpoints
Working results, not slide decks
- Automated defect recognition software configured to your defect classes
- Line integration: conveyance, controls, and reject handling
Hand over something you own
Documentation, source, and training
- Radiation safety documentation support and interlock verification
- Seeded-defect validation with documented detection performance
Sound familiar?
Where x-ray inspection integration earns its keep.
Foreign material detection in packaged food products
Porosity and void inspection in castings and welds
Fill level and component presence checks in sealed containers
Void and solder inspection in electronics assemblies
Ask about X-Ray Inspection Integration
Describe the problem. Get a straight answer.
One line is enough. An engineer replies within a business day.
Related work
Radar centering system for steel mills
Components:
- Radar sensors (strip position): Non-contact radar reading strip edge position in a hot, dusty, vibrating environment where optical sensors fail.
- Edge controller (signal processing): Turns raw radar returns into a clean lateral offset in real time.
- Mill PLC (centering actuators): The mill's existing controller: receives the offset and drives the centering actuators.
- Operator HMI (live position): Live strip position for the operator.
Connections:
- Radar sensors to Edge controller (raw returns)
- Edge controller to Mill PLC (offset)
- Edge controller to Operator HMI
A steel-mill systems provider · Steel manufacturing
Radar-based centering system for steel mills
End-to-end engineering of a radar sensing system that measures and centers material on steel mill lines — from equipment assessment through hardware selection, electrical engineering, software, installation, and commissioning.
Read the case study →Common questions
Asked before every x-ray inspection integration project.
Is X-ray inspection safe to run on our line?
Yes, when engineered properly. Industrial cabinet systems are shielded so external dose rates meet regulatory limits, with interlocks that kill the beam if a panel opens. We support the compliance side — radiation surveys, interlock verification, and coordination with your radiation safety officer and state registration — as part of the integration, not as an afterthought.
Do you build X-ray machines or integrate commercial ones?
We integrate and automate. Sources, detectors, and cabinets from established manufacturers are mature and certified; our value is selecting the right ones for your material and defect sizes, building the automated recognition software, and making the system a working part of your line and data systems.
How small a defect can X-ray detect?
It depends on the physics of your part: material density, thickness, defect contrast, and system geometry all matter, so any blanket number would be dishonest. The practical approach is a feasibility scan of your real parts with representative defects — that gives you measured detectability before you invest in equipment.
Will X-ray affect our product?
For the vast majority of industrial and food products, no. Inspection doses are very small and do not make anything radioactive; food X-ray inspection is widely used and addressed by existing food-safety regulation in most jurisdictions. A few product categories — some photographic films, certain sensitive electronics, and specific pharmaceutical materials — warrant a check, and we raise the question during feasibility rather than after installation.
What ongoing maintenance does an X-ray system need?
Less than people expect, but it is not zero. Sources have a finite life and are replaced on a schedule or when output drops; detectors need periodic gain and offset calibration, which we automate; test pieces are run at set intervals to prove detection is still working; and shielding surveys are repeated at intervals your state program specifies. We provide the maintenance schedule and procedures, and the system logs each check so your audit trail is complete.
Where this sits
X-Ray Inspection Integration, inside a vision & advanced sensing system.
The lit component is the part of the system this service delivers; the rest is what it has to work with.
Hover or focus a component to see what it is and what it talks to. Arrow keys move between them.
A part is presented under controlled lighting, a camera captures a frame per trigger, inspection compute decides, the PLC rejects, and every result lands in a database that feeds SPC dashboards.
Components:
- Part (on conveyor): Presentation is half the problem: fixturing, orientation and cycle time decide what is possible.
- Lighting (ring / backlight): Chosen for the defect, not the camera. Lighting is where most vision projects are won or lost.
- Camera (GigE, triggered): Machine vision camera, hardware-triggered per part.
- Inspection compute (edge PC): Runs the inspection — classical tools, a trained model, or both — within cycle time.
- Line PLC (reject / accept): Acts on the verdict: reject gate, line stop, or count.
- Results DB (every part): Every inspection result, with the image reference, for traceability and SPC.
- SPC dashboard (trends): Escape rate, false-reject rate and drift over time.
Connections:
- Part to Camera over digital I/O (trigger)
- Lighting to Camera
- Camera to Inspection compute over GigE
- Inspection compute to Line PLC over digital I/O
- Inspection compute to Results DB over SQL
- Results DB to SPC dashboard over REST
Strategy. Software. Systems.
Have a system that should exist?
Tell us what your operation is doing manually, what isn't connected, or what you're trying to build. We'll tell you plainly whether and how we can help.