Time： 9:00-11:30am,September 8, 2019

Location： Meeting room 1,on the second floor of School of Mechanical Engineering, Xingqing Campus

Lecture 1#：

Artificial Intelligence Enabled Manufacturing System Diagnosis and Prognosis

Lecturer：严如强教授（Prof. Ruqiang YAN）

Abstract：The new generation AI technology, especially deep learning, has shown great advantage in feature learning and knowledge mining, which provides a new way for intelligent diagnosis and prognosis in manufacturing. This talk first provides a brief overview of deep learning. Then applications of some typical deep network models in intelligent diagnosis and prognosis are discussed, followed by new trend of deep learning theory and development.

Lecture 2#：

The energy-absorbing capacity of composite reinforced structures for aerospace application

Lecturer：周晋教授（Prof. Jin ZHOU）

Abstract:This study investigates the crashworthiness characteristics of carbon fibre-reinforced plastic (CFRP) reinforced aluminium honeycomb core and PVC foam cores, for the use in lightweight energy-absorbing structures. Impact tests on individual CFRP tubes yielded specific energy absorption values as high as 110 kJ/kg. It was observed that the composite tubes efficiently absorbed large amounts of energy via a number of failure modes. Subsequently, a number of composite tubes inserted into square blocks of aluminium honeycomb and PCV foam. Low velocity crushing tests were carried out. It has been shown that embedding the tubes in a PVC foam and aluminium honeycomb panel serves to modify the failure process occurring within the composite tubes, greatly enhancing their ability to absorb energy, with values as high as 100 kJ/kg. Finally, it is shown that the energy-absorbing capability of tube-based foams is higher than many comparable core systems. Hence, this evidence suggests that composite tubes-reinforced aluminium honeycombs and PCV foam panels do offer great potential applications as energy absorbing structures for use under conditions of extreme crushing.

Lecture 3#：

Analysis of the Key Technologies for Battery Management System for Electric Driven Vehicles

Lecturer:Dr. Giovanni Violino

Abstract：The presentation introduces the key technologies for battery management systems of electric driven vehicles. The necessity of battery management is first introduced. Then, states estimation and fault detection methods are analyzed. Battery balancing/reconfiguration structures and control strategies are then reviewed and compared. Battery system thermal structure design and management are finally given.