The research discussed in this thesis explores a new method for the detection of grinding burn temperature using a laser irradiation acoustic emission (AE) sensing technique. This method is applicable for the grinding process monitoring system, providing an early warning for burn detection on metal alloy based materials (specifically nickel alloy based materials: Inconel718 and MarM002). The novelty in this research is the laser irradiation induced thermal AE signal that represents the grinding thermal behaviour and can be used for grinding burn detection. A set of laser irradiation experiments were conducted to identify key process characteristics. By controlling the laser power, the required grinding temperatures were simulated on alloy test materials. The thermal features of the extracted AE signal were used to identify the high, medium and low temperature signatures in relation to the off-focal laser distances. Grinding experiments were also conducted to investigate burn conditions. The extracted AE data was used to identify grinding burn and no burn signatures in relation to the depth of cuts. A new approach using an artificial neural network (ANN) was chosen as the pattern recognition tool for classifying grinding burn detection and was used to classify grinding temperatures by extracting the mechanical-thermal grinding AE signal. The results demonstrated that the classification accuracy achieved was 66 % for Inconel718 and 63 % for MarM002 materials. The research established that the wheel wear has a large influence on the creation of burn within the workpiece surface. The results demonstrated that the AE signals in each grinding trial presents different levels of high, medium and low temperature scales. This type of information provides a foundation for a new method for monitoring of grinding burn and wheel wear.