Conforming Capacitive Load Cells for Conical Pick Cutters.

Area of Science:

• Mining Engineering
• Sensor Technology
• Machine Safety

Background:

• Underground coal mining operators face risks when monitoring machinery near the cutting face.
• Improving operator safety and machine efficiency is crucial in mining operations.

Purpose of the Study:

• To develop and evaluate a novel cutting force sensor for underground coal mining applications.
• To enhance operator safety and efficiency by enabling remote monitoring of cutting forces.

Main Methods:

• A linear cutting machine simulated coal mining using concrete-cast coal samples and conical pick cutters.
• A cutting force sensor utilizing resonant frequency of capacitive cells was developed and tested.
• Linear and neural network regression models were employed to analyze sensor data from 100 test/train splits.

Main Results:

• The sensor accurately tracked normal force on conical picks, achieving a mean absolute error under 6 kN with linear regression (R2 > 0.60).
• A neural network model improved accuracy to a mean absolute error under 4 kN (R2 ≈ 0.80).
• The sensor demonstrated increased stiffness and sensitivity when integrated into the cutting tooling.

Conclusions:

• The developed cutting force sensor shows promise for improving safety and efficiency in underground coal mining.
• Objective force measurements can allow operators to assess tool wear and material type remotely.
• This technology can reduce operator proximity to hazardous cutting interfaces.