Inspection Failure Mode Coverage Ratio (FMCR-M)

GMI-MIN-012MiningIntegration-Required

Definition

Proportion of known geotechnical failure modes that the drone and CV inspection system is capable of detecting, relative to the total failure mode catalog for the inspected structure type.

The Measurement Gap

The Measurement Gap

When operations deploy drone inspection programs, the typical success metrics focus on flight hours completed, area coverage per survey, and number of anomalies detected. These metrics measure activity and volume. They do not measure whether the technology can actually see everything that a trained geotechnical engineer walking the pit wall was looking for.

Manual inspection protocols are designed around comprehensive failure mode registers: tension cracks, planar sliding indicators, wedge failures, erosion rills, seepage points, bench crest deterioration, sulfide oxidation staining, and dozens of other conditions specific to each operation's geology and geometry. A human inspector uses multiple senses (visual, auditory, olfactory) and can probe ambiguous features up close. A drone with a camera at 30 meters altitude operates within a narrower detection envelope.

Legacy metrics for drone programs count detections without asking whether the detection space covers the requirement space. An operation may report "200 anomalies detected this quarter" without acknowledging that the entire category of subsurface tension cracking is invisible to the camera system. The result is a false sense of comprehensive monitoring when significant failure modes remain unmonitored.

Decision Supported:

Is the drone inspection program actually replacing the scope of manual inspections, or is it substituting frequency for depth, leaving failure modes undetected?

Formula

Plain Language

Build the complete list of failure modes that inspections are required to cover (from the geotechnical monitoring plan and regulatory requirements). For each failure mode, determine whether the drone/CV system has demonstrated the capability to detect it. Divide the number of detectable modes by the total required modes.

Notation

FMCR-M = Detectable_modes_CV / Total_required_modes

Variables

Variable Description Source
Detectable_modes_CV Count of failure modes where the drone/CV inspection system has demonstrated detection capability through validation testing or confirmed field detections Inspection technology team validation records
Total_required_modes Complete count of failure modes from the geotechnical monitoring plan, regulatory inspection scope requirements, and site-specific engineering standards Geotechnical monitoring plan; regulatory requirements

"Demonstrated capability" requires evidence: either controlled validation testing where known examples of the failure mode were presented to the CV system and correctly identified, or confirmed field detections where the CV system flagged a condition later verified by expert assessment. Theoretical capability based on sensor specifications alone is insufficient. A failure mode moves from "undetectable" to "detectable" only when evidence supports the claim.

The result is a ratio between 0 and 1. A value of 1.0 means the drone/CV system can detect every required failure mode. A value of 0.7 means 30% of the required failure modes fall outside the system's detection envelope.

Proposed formula, pending validation pilots.

At a Glance

Unit
Ratio (0 to 1)
Trend Direction
Toward 1.0
Reporting Frequency
Quarterly
Category
Inspection Fidelity & Anomaly Detection Quality
← Detection Confidence Accuracy Score (DCAS)Temporal Change Detection Rate (TCHDR) →

Assess Your Organization

The AI-GPS Assessment evaluates your AI governance maturity and recommends KPIs like this one for your implementation roadmap.

Take the Free AI-GPS Assessment