Commissioning of P/PI-cascade controlled servo axes with flexible load can be quite time consuming, if the step response based setup procedures are applied for the velocity controller as indicated by the automation sy...Commissioning of P/PI-cascade controlled servo axes with flexible load can be quite time consuming, if the step response based setup procedures are applied for the velocity controller as indicated by the automation systems manufacturers. Based on the drive frequency response, suitable rules of thumb with optimum velocity control damping performance are derived in this contribution that turned out to be very efficient in several dozen machine tool servo axis applications of different industrial partners in Switzerland and southern Germany. Anyway, single feedback loop velocity control sometimes provides insufficient damping of structural vibrations, especially for high dynamic machine tools or robots. The axis performance can be improved significantly by state space control extensions that are meanwhile available for commercial machine tool control systems. This contribution explains the state space control extension application with effective commissioning rules of thumb for typical machine tool axes as well as robot joint drives. The achievable benefit is elucidated by exemplary machine tool axes.展开更多
Statistical dialogue management is the core of cognitive spoken dialogue systems （SDS） and has attracted great research interest. In recent years, SDS with the ability of evolution is of particular interest and beco...Statistical dialogue management is the core of cognitive spoken dialogue systems （SDS） and has attracted great research interest. In recent years, SDS with the ability of evolution is of particular interest and becomes the cuttingedge of SDS research. Dialogue state tracking （DST） is a process to estimate the distribution of the dialogue states at each dialogue turn, given the previous interaction history. It plays an important role in statistical dialogue management. To provide a common testbed for advancing the research of DST, international DST challenges （DSTC） have been organised and well-attended by major SDS groups in the world. This paper reviews recent progresses on rule-based and statistical approaches during the challenges. In particular, this paper is focused on evolvable DST approaches for dialogue domain extension. The two primary aspects for evolution, semantic parsing and tracker, are discussed. Semantic enhancement and a DST framework which bridges rule-based and statistical models are introduced in detail. By effectively incorporating prior knowledge of dialogue state transition and the ability of being data-driven, the new framework supports reliable domain extension with little data and can continuously improve with more data available. This makes it excellent candidate for DST evolution. Experiments show that the evolvable DST approaches can achieve the state-of-the-art performance and outperform all previously submitted trackers in the third DSTC.展开更多
文摘Commissioning of P/PI-cascade controlled servo axes with flexible load can be quite time consuming, if the step response based setup procedures are applied for the velocity controller as indicated by the automation systems manufacturers. Based on the drive frequency response, suitable rules of thumb with optimum velocity control damping performance are derived in this contribution that turned out to be very efficient in several dozen machine tool servo axis applications of different industrial partners in Switzerland and southern Germany. Anyway, single feedback loop velocity control sometimes provides insufficient damping of structural vibrations, especially for high dynamic machine tools or robots. The axis performance can be improved significantly by state space control extensions that are meanwhile available for commercial machine tool control systems. This contribution explains the state space control extension application with effective commissioning rules of thumb for typical machine tool axes as well as robot joint drives. The achievable benefit is elucidated by exemplary machine tool axes.
文摘Statistical dialogue management is the core of cognitive spoken dialogue systems （SDS） and has attracted great research interest. In recent years, SDS with the ability of evolution is of particular interest and becomes the cuttingedge of SDS research. Dialogue state tracking （DST） is a process to estimate the distribution of the dialogue states at each dialogue turn, given the previous interaction history. It plays an important role in statistical dialogue management. To provide a common testbed for advancing the research of DST, international DST challenges （DSTC） have been organised and well-attended by major SDS groups in the world. This paper reviews recent progresses on rule-based and statistical approaches during the challenges. In particular, this paper is focused on evolvable DST approaches for dialogue domain extension. The two primary aspects for evolution, semantic parsing and tracker, are discussed. Semantic enhancement and a DST framework which bridges rule-based and statistical models are introduced in detail. By effectively incorporating prior knowledge of dialogue state transition and the ability of being data-driven, the new framework supports reliable domain extension with little data and can continuously improve with more data available. This makes it excellent candidate for DST evolution. Experiments show that the evolvable DST approaches can achieve the state-of-the-art performance and outperform all previously submitted trackers in the third DSTC.
