Strong mechanical vibration and acoustical signals of grinding process contain useful information related to load parameters in ball mills. It is a challenge to extract latent features and construct soft sensor model ...Strong mechanical vibration and acoustical signals of grinding process contain useful information related to load parameters in ball mills. It is a challenge to extract latent features and construct soft sensor model with high dimensional frequency spectra of these signals. This paper aims to develop a selective ensemble modeling approach based on nonlinear latent frequency spectral feature extraction for accurate measurement of material to ball volume ratio. Latent features are first extracted from different vibrations and acoustic spectral segments by kernel partial least squares. Algorithms of bootstrap and least squares support vector machines are employed to produce candidate sub-models using these latent features as inputs. Ensemble sub-models are selected based on genetic algorithm optimization toolbox. Partial least squares regression is used to combine these sub-models to eliminate collinearity among their prediction outputs. Results indicate that the proposed modeling approach has better prediction performance than previous ones.展开更多
Nonlinear lumped-parameter force factor Bl(x), stiffness Kms(x) and inductance Le(x) of electrodynamic loudspeakers change frequency responses and generate some nonlinear effects for large stimulus: harmonic and inter...Nonlinear lumped-parameter force factor Bl(x), stiffness Kms(x) and inductance Le(x) of electrodynamic loudspeakers change frequency responses and generate some nonlinear effects for large stimulus: harmonic and intermodulation distortion, DC component in diaphragm displacement, instability of vibration and jumping effects. By modeling the nonlinear system under large-signal conditions, relationship between the nonlinear parameters and large-signal behavior can be revealed and help to provide guidance to diagnose loudspeakers. Agreement between the measured and predicted responses of a real loudspeaker validates the modeling and enables new methods for loudspeaker diagnosis.展开更多
With the combination of engine and two electric machines, the power split device allows higher efficiency of the engine. The operation modes of a power split HEV are analyzed, and the system dynamic model is establish...With the combination of engine and two electric machines, the power split device allows higher efficiency of the engine. The operation modes of a power split HEV are analyzed, and the system dynamic model is established for HEV forward simulation and controller design. Considering the fact that the operation modes of the HEV are event-driven and the system dynamics is continuous time-driven for each mode, the structure of the controller is built and described with the hybrid automaton control theory. In this control structure, the mode selection process is depicted by the finite state machine （FSM）. The multi-mode switch controller is designed to realize power distribution. Furthermore, the vehicle mode operations are optimized, and the nonlinear model predictive control （NMPC） strategy is applied by implementing dynamic programming （DP） in the finite pre- diction horizon. Comparative simulation results demonstrate that the hybrid control structure is effective and feasible for HEV energy management design. The NMPC optimal strategy is superior in improving fuel economy.展开更多
基金Supported partially by the Post Doctoral Natural Science Foundation of China(2013M532118,2015T81082)the National Natural Science Foundation of China(61573364,61273177,61503066)+2 种基金the State Key Laboratory of Synthetical Automation for Process Industriesthe National High Technology Research and Development Program of China(2015AA043802)the Scientific Research Fund of Liaoning Provincial Education Department(L2013272)
文摘Strong mechanical vibration and acoustical signals of grinding process contain useful information related to load parameters in ball mills. It is a challenge to extract latent features and construct soft sensor model with high dimensional frequency spectra of these signals. This paper aims to develop a selective ensemble modeling approach based on nonlinear latent frequency spectral feature extraction for accurate measurement of material to ball volume ratio. Latent features are first extracted from different vibrations and acoustic spectral segments by kernel partial least squares. Algorithms of bootstrap and least squares support vector machines are employed to produce candidate sub-models using these latent features as inputs. Ensemble sub-models are selected based on genetic algorithm optimization toolbox. Partial least squares regression is used to combine these sub-models to eliminate collinearity among their prediction outputs. Results indicate that the proposed modeling approach has better prediction performance than previous ones.
基金supported by the National Natural Science Foundation of China(Grant No. 11274172)
文摘Nonlinear lumped-parameter force factor Bl(x), stiffness Kms(x) and inductance Le(x) of electrodynamic loudspeakers change frequency responses and generate some nonlinear effects for large stimulus: harmonic and intermodulation distortion, DC component in diaphragm displacement, instability of vibration and jumping effects. By modeling the nonlinear system under large-signal conditions, relationship between the nonlinear parameters and large-signal behavior can be revealed and help to provide guidance to diagnose loudspeakers. Agreement between the measured and predicted responses of a real loudspeaker validates the modeling and enables new methods for loudspeaker diagnosis.
基金supported by the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD)the National Natural Science Foundation of China(Grant Nos.51475213&51305167)the Scientific Research Innovation Projects of Jiangsu Province(Grant No.KYLX_1022)
文摘With the combination of engine and two electric machines, the power split device allows higher efficiency of the engine. The operation modes of a power split HEV are analyzed, and the system dynamic model is established for HEV forward simulation and controller design. Considering the fact that the operation modes of the HEV are event-driven and the system dynamics is continuous time-driven for each mode, the structure of the controller is built and described with the hybrid automaton control theory. In this control structure, the mode selection process is depicted by the finite state machine （FSM）. The multi-mode switch controller is designed to realize power distribution. Furthermore, the vehicle mode operations are optimized, and the nonlinear model predictive control （NMPC） strategy is applied by implementing dynamic programming （DP） in the finite pre- diction horizon. Comparative simulation results demonstrate that the hybrid control structure is effective and feasible for HEV energy management design. The NMPC optimal strategy is superior in improving fuel economy.
