Nuclear norm subspace identification for continuous-time stochastic systems based on distribution theory method

Yu, Miao; Liu, Jianchang; Wang, Honghai

doi:10.1016/j.isatra.2018.08.014

Cited by 11 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It represents the logical step in complexity between the linear systems which are inadequate in the modeling of various dynamic processes and the difficult realm of nonlinear systems [24]. Therefore, to well capture the nonlinear dynamics of complex ironmaking process as well as consider the simplicity and easy-using of the model, the bilinear system model will be developed for the MIQ indices by subspace identification (SI) method, which is computationally efficient and can be applied to modeling of MIMO systems directly [5], [25], [26]. Different from the standard SI algorithms, such as CVA and N4SID [26], [27], this paper will establish an input-output bilinear model only by constructing the extended Hankel matrices to facilitate the calculation of the subspace matrices without explicitly computing the system matrices.Thus the method proposed in this paper can further improve the computational efficiency and ease to realize online learning.…”

Section: Online Learning Modeling and Data-driven Predictive Contmentioning

confidence: 99%

Recursive Learning-Based Bilinear Subspace Identification for Online Modeling and Predictive Control of a Complicated Industrial Process

2020

View full text Add to dashboard Cite

In this paper, a recursive learning based bilinear subspace identification (R-B-SI) algorithm is proposed for online modeling and data-driven predictive control of blast furnace (BF) ironmaking process with strong nonlinear time-varying dynamics. Different from the existing linear SI algorithms, the R-B-SI algorithm can make full use of the process data information by adding the Kronecker product term of input data and the Kronecker product term between input and output data into the data block Hankel matrices. Moreover, the parameters of the R-B-SI model can be updated online with the latest data using recursive learning. In order to adjust the sensitivity of the algorithm to the data at different sampling times, the forgetting factor is introduced into the involved recursive learning as well. Therefore, the nonlinear time-varying dynamics of process can be well captured and described by the R-B-SI model. As a result, the data-driven predictive controller designed by the R-B-SI prediction model with parameter adaption is always capable of achieving satisfactory control performances regardless of the variation in various process operating conditions. Data experiments using actual industrial data have verified the practicability and superiority of the proposed methods. INDEX TERMS Recursive bilinear subspace identification, online modeling, recursive learning, data-driven predictive control, blast furnace ironmaking process, nonlinear time-varying dynamics.

show abstract

Section: Online Learning Modeling and Data-driven Predictive Contmentioning

confidence: 99%

Recursive Learning-Based Bilinear Subspace Identification for Online Modeling and Predictive Control of a Complicated Industrial Process

2020

View full text Add to dashboard Cite

show abstract

“…More knowledge about identification of stochastic subspace can be seen is in Reference [40]. More knowledge about identification of closed-loop subspace can be seen is in Reference [41] or pages 55-78 of Reference [37].…”

Section: Conflicts Of Interestmentioning

confidence: 99%

A New Control Performance Evaluation Based on LQG Benchmark for the Heating Furnace Temperature Control System

2020

Processes

View full text Add to dashboard Cite

Temperature control systems are a series of processes with large time-delay and non-linear characteristics. Research shows that using fractional-order modeling and corresponding control strategies can better control these processes. At the same time, the existing studies for control performance assessment are almost committed to the integer order control systems, and the methods used in few literatures on performance assessment of fractional order systems are also one-sided. This paper applies the linear quadratic Gaussian (LQG) evaluation benchmark to the performance evaluation of fractional-order control systems for the first time, starting with the LQG evaluation benchmark considering the input and output performance. The LQG benchmark can be obtained by the analytical algorithm, which simplifies the complexity of LQG solution. Finally, taking the application of the fractional predictive function control (FO-PFC) controller in the experiment of industrial heating furnace temperature control as an example, the effectiveness of the LQG benchmark is verified.

show abstract

“…As a way to overcome the drawback of requiring physicalbased models, the process models obtained from subspace identification (SI) methods have gained attention in manufacturing systems management, since these methods directly deliver a state-space model of less complex implementation for the design of model-based control strategies [12]. As a consequence, SI models have had significant application to the modeling of complex, large-scale, and time-varying-parameter systems [13,14,15]. Then, due to the applicability of SI for obtaining models to be used in model-based control design (in particular for model predictive control -MPC -design), they have been widely used in manufacturing industries [16,17].…”

Section: Introductionmentioning

confidence: 99%

An optimization-based control strategy for energy efficiency of discrete manufacturing systems

et al. 2019

View full text Add to dashboard Cite

In order to reduce the global energy consumption and avoid highest power peaks during operation of manufacturing systems, an optimization-based controller for selective switching on/off of peripheral devices in a test bench that emulates the energy consumption of a periodic system is proposed. First, energy consumption models for the test-bench devices are obtained based on data and subspace identification methods. Next, a control strategy is designed based on both optimization and receding horizon approach, considering the energy consumption models, operating constraints, and the real processes performed by peripheral devices. Thus, a control policy based on dynamical models of peripheral devices is proposed to reduce the energy consumption of the manufacturing systems without sacrificing the productivity. Afterward, the proposed strategy is validated in the test bench and comparing to a typical rule-based control scheme commonly used for these manufacturing systems. Based on the obtained results, reductions near 7% could be achieved allowing improvements in energy efficiency via minimization of the energy costs related to nominal power purchased.

show abstract

Nuclear norm subspace identification for continuous-time stochastic systems based on distribution theory method

Cited by 11 publications

References 18 publications

Recursive Learning-Based Bilinear Subspace Identification for Online Modeling and Predictive Control of a Complicated Industrial Process

Recursive Learning-Based Bilinear Subspace Identification for Online Modeling and Predictive Control of a Complicated Industrial Process

A New Control Performance Evaluation Based on LQG Benchmark for the Heating Furnace Temperature Control System

An optimization-based control strategy for energy efficiency of discrete manufacturing systems

Contact Info

Product

Resources

About