Building energy consumption prediction plays an important role in improving the utilization rate through helping building managers to make better decisions. However, as a result of randomness and noisy disturbance, it is not easy task realize accurate consumption. In order obtain accuracy, extreme deep learning approach presented this paper. The proposed combines stacked autoencoders (SAEs) with machine (ELM) take advantage their respective characteristics. approach, SAE used extract...

This paper proposes a novel class of adaptive extended state observers (AESOs) that significantly expand the applications (ESOs) to nonlinear disturbed systems. An AESO is designed as linear time-varying form that, result, combines both advantages theoretical completeness in conventional ESO (LESO) and good practical performance (NESO). To tune observer gains, error dynamics first transformed into canonical (phase-variable) form. Then, PD-eigenvalues are assigned for system based on...

This article investigates the adaptive fuzzy tracking control design for uncertain nonstrict-feedback nonlinear systems with time-varying constraints and asymmetric input saturations. It is known that output constraint, error constraints, saturations are commonly seen issues in many practical engineering due to inherent physical limitations performance requirements. To deal these problems improve convergence rate of system, a novel fixed-time convergent scheme proposed considered via barrier...

A stable hierarchical sliding-mode control method for a class of second-order underactuated systems is presented. The ideas behind the are as follows. First, system divided into two subsystems. For each part first-level sliding surface defined. these surfaces, second-level law derived using Lyapunov law. can drive subsystems toward their surfaces and attain desired values, implement antidisturbance control. asymptotic stability all proved theoretically, simulation results show controller's...

This paper presents a novel fixed-time sliding mode disturbance observer (SMDO)-based robust backstepping cruise tracking control scheme with closed-loop finite-time convergence for flexible air-breathing hypersonic vehicles (FAHVs). In order to enhance the system's robustness, SMDO is designed compensate flexibility effects, model uncertainties, and external disturbances in FAHVs. consequence, fixed time of observation achieved independently initial estimation errors. Furthermore, velocity...

Abstract. Automated methods are important for automatically detecting mesoscale eddies in large volumes of altimeter data. While many algorithms have been proposed the past, this paper presents a new method, called hybrid detection (HD), to enhance eddy accuracy and capability recognizing multi-core structures from maps sea level anomaly (SLA). The HD method has integrated criteria Okubo–Weiss (OW) surface height-based (SSH-based) two commonly used algorithms. Evaluation shows that...

Uncertainty and measurement noise are main obstacles that limit the tracking control performances of flexible air-breathing hypersonic vehicles (FAHVs). In this article, we propose a novel fixed-time convergent nonsmooth backstepping scheme for FAHV via augmented sliding mode observers (ASMOs) to overcome these obstacles. The ASMOs first designed dynamics by employing measured states corrupted noises as inputs. On one hand, can simultaneously estimate uncertainties filter out noises. other...

Generating collision-free, time-efficient paths in an uncertain dynamic environment poses huge challenges for the formation control with collision avoidance (FCCA) problem a leader-follower structure. In particular, followers have to take both maintenance and into account simultaneously. Unfortunately, most of existing works are simple combinations methods dealing two problems separately. this article, new method based on deep reinforcement learning (RL) is proposed solve FCCA. Especially,...

This paper investigates the anti-disturbance control design for flexible air-breathing hypersonic vehicles (FAHVs) with appointed-time prescribed tracking performances. The challenging issues include multisource disturbances, cross-coupling effects of vehicle dynamics, and asymmetric amplitude rate saturations. To address these issues, we propose an performance scheme FAHVs via conditional disturbance negation technique. In contrast to existing rejection approaches, proposed not only...

Disturbances of the permanent magnet synchronous motor (PMSM) drive system are usually observed and fully compensated to improve robustness in existing two-degrees-of-freedom control schemes. However, these schemes neglect potential advantages disturbances that have not been well investigated yet. To this end, article proposes a new adaptive conditional disturbance negation (ACDN)-based scheme for PMSM enhance performance by exploiting disturbances. The proposed can utilize advantageous...

The single-input-rule-modules (SIRMs) connected fuzzy inference method can efficiently solve the rule explosion phenomenon, which usually occurs in multivariable modeling and/or control applications. However, performance of SIRMs system (SIRM-FIS) is limited due to its simple input-output mapping. In this paper, further enhance SIRM-FIS, a functionally weighted SIRM-FIS (FWSIRM-FIS), adopts functional weights measure important degrees SIRMs, presented. Then, order show fundamental...

A new output feedback control design for robust velocity and altitude tracking of an air-breathing hypersonic vehicle (AHSV) is presented in this paper. The scheme performed on the assumption that only partial states AHSV are measurable. key idea to employ immersion invariance approach globally asymptotically stable observers unmeasurable states. For controller design, whole architecture constructed using dynamic surface control, based decomposition longitudinal dynamics into subsystems....

It is commonly believed that uncertainties are obstacles to the tracking performances of flexible air-breathing hypersonic vehicles (FAHVs). In addition, estimation unmeasured states in an FAHV makes this issue much more complicated. To deal with these difficulties, article explores a novel adaptive fuzzy nonsmooth backstepping output-feedback control scheme for closed-loop finite-time convergence. First, approximate unknown dynamics FAHV, some function approximators constructed by utilizing...

Semi-active vehicle suspension with magnetorheological dampers is a promising technology for improving the ride comfort of ground vehicle. However, damper always exhibits nonlinear hysteresis between its output force and relative velocity, additional stiffness owing to state transition from liquid semi-solid or solid, so that semi-active features nonlinearity by nature. To control such dynamic systems subject random road roughness, in this paper we present neural network control, which...

On the basis of sliding-mode control, two controller models based on incremental hierarchical structure and aggregated for a class under-actuated systems are presented. The design steps types controllers principle choosing parameters given. At same time, to guarantee system's stability, determinant theorems Then, by theoretical analysis, proved be globally stable in sense that all signals involved bounded. simulation results show validity methods. Therefore an academic foundation development...

Qualitative knowledge is very useful for system modeling and control problems, especially when specific physical structure unavailable the number of training data points small. This paper studies incorporation one common qualitative knowledge-monotonicity into interval type-2 (IT2) fuzzy logic systems (FLSs). Sufficient conditions on antecedent consequent parts rules are derived to guarantee monotonicity between inputs outputs. We take account five type-reduction defuzzification methods (the...

To enhance the prediction performance for building energy consumption, this paper presents a modified deep belief network (DBN) based hybrid model. The proposed model combines outputs from DBN with energy-consuming pattern to yield final results. in study represents periodicity property of consumption and can be extracted observed historical data. residual data generated by removing original are utilized train training includes two steps, first one which adopts contrastive divergence (CD)...

This paper presents a novel robust adaptive tracking control method for hypersonic vehicle in cruise flight stage based on interval type-2 fuzzy-logic system (IT2-FLS) and small-gain approach. After the input-output linearization, model can be decomposed into two uncertain subsystems by considering matching disturbances parametric uncertainties. For each subsystem, an Takagi-Sugeno-Kang fuzzy logic (IT2-TSK-FLS) is then employed to approximate unavailable information. Following idea of...