Showing papers on "Filter design published in 2020"

Distributed Set-Membership Filtering for Multirate Systems Under the Round-Robin Scheduling Over Sensor Networks

Abstract: In this paper, the distributed set-membership filtering problem is dealt with for a class of time-varying multirate systems in sensor networks with the communication protocol. For relieving the communication burden, the round-Robin (RR) protocol is exploited to orchestrate the transmission order, under which each sensor node only broadcasts partial information to both the corresponding local filter and its neighboring nodes. In order to meet the practical transmission requirements as well as reduce communication cost, the multirate strategy is proposed to govern the sampling/update rate of the plant, the sensors, and the filters. By means of the lifting technique, the augmented filtering error system is established with a unified sampling rate. The main purpose of the addressed filtering problem is to design a set of distributed filters such that, in the simultaneous presence of the RR transmission protocol, the multirate mechanism, and the bounded noises, there exists a certain ellipsoid that includes all possible error states at each time instant. Then, the desired distributed filter gains are obtained by minimizing such an ellipsoid in the sense of the minimum trace of the weighted matrix. The proposed resource-efficient filtering algorithm is of a recursive form, thereby facilitating the online implementation. A numerical simulation example is given to demonstrate the effectiveness of the proposed protocol-based distributed filter design method.

Secure Distributed Finite-Time Filtering for Positive Systems Over Sensor Networks Under Deception Attacks

Abstract: This paper is concerned with secure ${\ell _{1}}$ -gain performance analysis and distributed finite-time filter design for a positive discrete-time linear system over a sensor network in the presence of deception attacks. A group of intercommunicating sensors is densely deployed to measure, gather, and process the output of the positive system. Each sensor is capable of sharing its measurement with its neighboring sensors in accordance with a prescribed network topology while suffering from random communication link failure. Meanwhile, the aggregated measurement on each sensor during network transmission is corrupted by stochastic deception attacks which compromise the sensor’s measurement integrity. First, a unified sensor measurement transmission model is put forward to account for the simultaneous presence of deception attacks and various network-induced constraints. Second, delicate secure distributed filters are constructed by admitting the corrupted sensor measurement. Third, theoretical analysis on finite-time ${\ell _{1}}$ -gain boundedness of the filtering error system and design of desired positive filters are carried out. The solution to the filter gain parameters is characterized by a set of linear programming inequalities. Finally, the effectiveness of the obtained results is verified through the secure monitoring of power distribution in the smart grid.

Protocol-Based Unscented Kalman Filtering in the Presence of Stochastic Uncertainties

Abstract: In this paper, the unscented Kalman filtering (UKF) problem is investigated for a class of general nonlinear systems with stochastic uncertainties under communication protocols. A modified unscented transformation is put forward to account for stochastic uncertainties caused by modeling errors. For preventing data collisions and mitigating communication burden, the round-robin protocol and the weighted try-once-discard protocol are, respectively, introduced to regulate the data transmission order from sensors to the filter. Then, by employing two kinds of data-holding strategies (i.e., zero-order holder and zero input) for those nodes without transmission privilege, two novel protocol-based measurement models are formulated. Subsequently, by resorting to the sigma point approximation method, two resource-saving UKF algorithms are developed, where the impact from the underlying protocols on the filter design is explicitly quantified. Finally, compared with the protocol-based extended Kalman filtering algorithms, a simulation example is presented to demonstrate the effectiveness of the proposed protocol-based UKF algorithms.

Reliable Filter Design of Takagi–Sugeno Fuzzy Switched Systems With Imprecise Modes

Abstract: This paper is concerned with the problem of asynchronous and reliable filter design with performance constraint for nonlinear Markovian jump systems which are modeled as a kind of Takagi–Sugeno fuzzy switched systems. The nonstationary Markov chain is adopted to represent the asynchronous situation between the designed filter and the considered system. By using the mode-dependent Lyapunov function approach and the relaxation matrix technique, a sufficient condition is proposed to ensure the filtering error system, which is a dual randomly switched system, is stochastically stable and satisfies a given ${{l}_{{2}}}{{-}}{{l}_{{\infty }}}$ performance index simultaneously. Two different approaches are developed to construct the asynchronous and reliable filter. Owing to the Finsler’s lemma, the second approach has fewer decision variables and less conservatism than the first one. Finally, two examples are provided to show the correctness and effectiveness of the proposed methods.

Event-triggered filter design for nonlinear cyber-physical systems subject to deception attacks.

Abstract: This paper is concerned with an event-triggered filter design for fuzzy-model-based cyber–physical systems with cyber-attacks. Spurious events may be triggered under the conventional event-triggered mechanism (ETM) when the sampling data has a rapid change arising from unpredicted external disturbance. To avoid spurious decisions on data releasing a new ETM is proposed. Furthermore, the communication network is vulnerable to attacks by malicious attackers. Under this scenario, a new resilient filter is designed to ensure the security. Sufficient conditions are established to make the filtering error system asymptotically stable. A numerical example is provided to show the effectiveness of the proposed results.

Robust fault detection filter design for a class of discrete-time conic-type non-linear Markov jump systems with jump fault signals

Abstract: This study investigates the robust fault detection filter design problem for a class of discrete-time conic-type non-linear Markov jump systems with jump fault signals. The conic-type non-linearities satisfy a restrictive condition that lies in an n-dimensional hyper-sphere with an uncertain centre. A crucial idea is to formulate the robust fault detection filter design problem of non-linear Markov jump systems as H ∞ filtering problem. The authors aim to design a fault detection filter such that the augmented Markov jump systems with conic-type non-linearities are stochastically stable and satisfy the given H ∞ performance against the external disturbances. By means of the appropriate mode-dependent Lyapunov functional method, sufficient conditions for the existence of the designed fault detection filter are presented in terms of linear matrix inequalities. Finally, a practical circuit model example is employed to demonstrate the availability of the main results.

RBFNN-Based Minimum Entropy Filtering for a Class of Stochastic Nonlinear Systems

Abstract: This paper presents a novel minimum entropy filter design for a class of stochastic nonlinear systems, which are subjected to non-Gaussian noises. Motivated by stochastic distribution control, an output entropy model is developed using a radial basis function neural network, while the parameters of the model can be identified by the collected data. Based upon the presented model, the filtering problem has been investigated, while the system dynamics have been represented. As the model output is the entropy of the estimation error, the optimal nonlinear filter is obtained based on the Lyapunov design, which makes the model output minimum. Moreover, the entropy assignment problem has been discussed as an extension of the presented approach. To verify the presented design procedure, a numerical example is given, which illustrates the effectiveness of the presented algorithm. The contributions of this paper can be summarized as follows: 1) an output entropy model is presented using a neural network; 2) a nonlinear filter design algorithm is developed as the main result; and 3) a solution of the entropy assignment problem is obtained, which is an extension of the presented framework.

Robust $\mathcal {H}_\infty$ Filtering for Vehicle Sideslip Angle With Quantization and Data Dropouts

Abstract: This paper studies the robust $\mathcal {H}_\infty$ filtering problem for the in-vehicle networked system with sensor failure, dynamic quantization and data dropouts. The nonlinear vehicle lateral dynamics is described as the Takagi-Sugeno fuzzy system. We assume that the sensor failure is adopted to present inaccurately work of the sensor, and both the measurement and performance output signals are quantized by the dynamic quantizers before being transmitted to the network channel. Moreover, the Bernoulli random binary distribution is considered to describe the data dropouts phenomenon both in the measurement and performance outputs. The proposed filter design method is given in the form of linear matrix inequalities which guarantee that the filtering error system is stochastically stable with $\mathcal {H}_\infty$ performance index. Finally, the co-simulation of the Matlab/Simulink and Carsim is used to validate the proposed filter design method.

Introducing Hypergraph Signal Processing: Theoretical Foundation and Practical Applications

Abstract: Signal processing over graphs has recently attracted significant attention for dealing with the structured data. Normal graphs, however, only model pairwise relationships between nodes and are not effective in representing and capturing some high-order relationships of data samples, which are common in many applications, such as Internet of Things (IoT). In this article, we propose a new framework of hypergraph signal processing (HGSP) based on the tensor representation to generalize the traditional graph signal processing (GSP) to tackle high-order interactions. We introduce the core concepts of HGSP and define the hypergraph Fourier space. We then study the spectrum properties of hypergraph Fourier transform (HGFT) and explain its connection to mainstream digital signal processing. We derive the novel hypergraph sampling theory and present the fundamentals of hypergraph filter design based on the tensor framework. We present HGSP-based methods for several signal processing and data analysis applications. Our experimental results demonstrate significant performance improvement using our HGSP framework over some traditional signal processing solutions.

Learning Low-Rank and Sparse Discriminative Correlation Filters for Coarse-to-Fine Visual Object Tracking

Abstract: Discriminative correlation filter (DCF) has achieved advanced performance in visual object tracking with remarkable efficiency guaranteed by its implementation in the frequency domain. However, the effect of the structural relationship of DCF and object features has not been adequately explored in the context of the filter design. To remedy this deficiency, this paper proposes a Low-rank and Sparse DCF (LSDCF) that improves the relevance of features used by discriminative filters. To be more specific, we extend the classical DCF paradigm from ridge regression to lasso regression, and constrain the estimate to be of low-rank across frames, thus identifying and retaining the informative filters distributed on a low-dimensional manifold. To this end, specific temporal-spatial-channel configurations are adaptively learned to achieve enhanced discrimination and interpretability. In addition, we analyse the complementary characteristics between hand-crafted features and deep features, and propose a coarse-to-fine heuristic tracking strategy to further improve the performance of our LSDCF. Last, the augmented Lagrange multiplier optimisation method is used to achieve efficient optimisation. The experimental results obtained on a number of well-known benchmarking datasets, including OTB2013, OTB50, OTB100, TC128, UAV123, VOT2016 and VOT2018, demonstrate the effectiveness and robustness of the proposed method, delivering outstanding performance compared to the state-of-the-art trackers.

Probabilistic-Constrained Distributed Filtering for a Class of Nonlinear Stochastic Systems Subject to Periodic DoS Attacks

Abstract: This paper investigates the probabilistic-constrained distributed filtering problem for a class of nonlinear stochastic systems with state constraints and cyber attacks. The considered cyber attacks are periodic denial-of-service (DoS) attacks which are modeled by a kind of periodic pulse-width-modulated (PWM) jamming signals. Different from some existing works, by using the proposed filter design method, the probability of the filtering error exceeding a threshold can be guaranteed below a certain level quantitatively. Furthermore, in order to economize the limited bandwidth resources, an event-triggered communication scheme (ETS) is designed for the data transmission. The aim of the problem addressed is to design a time-varying distributed filters such that: 1) the probability of the filtering error restricted to a given ellipsoid is larger than a specified value; and 2) the obtained ellipsoid threshold is minimized in the sense of matrix norm at each time point. To achieve this purpose, a recursive linear matrix inequality method is utilized and sufficient conditions are derived. Moreover, the filter parameters are explicitly determined in terms of the solution to certain matrix inequalities. Finally, the reliability and applicability of the proposed distributed filtering strategy are demonstrated by an illustrative example.

Estimation for a Class of Parameter-Controlled Tunnel Diode Circuits

Abstract: This paper studies the estimation problem for a class of nonlinear tunnel diode circuits with parameter perturbation. The dynamics of the nonlinear circuit is approximated by the Takagi–Sugeno fuzzy model with linear fractional parametric uncertainties. Considering the fuzzy filter with gain uncertainties, a filtering error system can be gotten naturally. The concentration of this paper lies in deriving the design conditions for the desired resilient filter such that the filtering error system preserves asymptotic stability as well as the $\boldsymbol {\mathcal {L}}_{\boldsymbol {\infty }}$ -norm of the transfer function from the external disturbance input to the filtering error output is below a specified bound. The filter design conditions for guaranteeing the prescribed peak-to-peak performance of the filtering error system are provided by a set of linear matrix inequalities. Finally, a simulation result is presented to illustrate the validity and effectiveness of the proposed filtering design for the parameter-controlled tunnel diode circuit.

Extended State Filter Based Disturbance and Uncertainty Mitigation for Nonlinear Uncertain Systems With Application to Fuel Cell Temperature Control

Abstract: The filter design for nonlinear uncertain systems is quite challenging since efficient estimation is required against stochastic noises, nonlinear uncertain dynamics as well as their concurrent effects. To this end, this article develops a novel filter algorithm by augmenting the disturbance as well as unknown nonlinear dynamics as an extended state and constructing consistent Kalman–Bucy algorithm. The proposed extended state based Kalman–Bucy filter (KBF) is shown to be of bounded estimation error, and the estimation accuracy can be online evaluated. More importantly, the estimation of asymptotic minimum variance is realized in condition that the changing rate of uncertainty approaches to zero. Therefore, the proposed extended state filter enables effective mitigation of disturbance and unknown nonlinear dynamics in real time by feedback control. The proposed algorithm is experimentally verified via a temperature control application in proton exchange membrane fuel cell, in which the thermocouple noise and the electrochemical uncertainty are seriously presented. The temperature variation of the extended state based KBF-based control is greatly reduced, in comparison with the conventional control. The results in this article depict a promising prospect of the proposed method for industrial control applications to handle both noises and nonlinear uncertain dynamics.

Novel ZVS S-TCM Modulation of Three-Phase AC/DC Converters

Abstract: For three-phase AC-DC power conversion, the widely-used continuous current mode (CCM) modulation scheme results in relatively high semiconductor losses from hard-switching each device during half of the mains cycle. Triangular current mode (TCM) modulation, where the inductor current reverses polarity before turn-off, achieves zero-voltage-switching (ZVS) but at the expense of a wide switching frequency variation (15× for the three-phase design considered here), complicating filter design and compliance with EMI regulations. In this paper, we propose a new modulation scheme, sinusoidal triangular current mode (S-TCM), that achieves soft-switching, keeps the maximum switching frequency below the 150 kHz EMI regulatory band, and limits the switching frequency variation to only 3×. Under S-TCM, three specific modulation schemes are analyzed, and a loss-optimized weighting of the current bands across load is identified. The 2.2 kW S-TCM phase-leg hardware demonstrator achieves 99.7% semiconductor efficiency, with the semiconductor losses accurately analytically estimated within 10% (0.3 W). Relative to a CCM design, the required filter inductance is 6× lower, the inductor volume is 37% smaller, and the semiconductor losses are 55% smaller for a simultaneous improvement in power density and efficiency.

Event-triggered finite-time H∞ filtering for networked systems under deception attacks

Abstract: This paper is concerned with event-triggered H∞ filter design for a networked system suffering stochastic deception attacks in the sense of finite-time boundedness. Firstly, a networked filtering error model is well constructed by taking the effect of deception attacks and event-triggered scheme into account. Then, two sufficient conditions are derived to ensure that the resultant filtering error system is finite-time bounded with a prescribed H∞ performance, where the feasible H∞ filter parameters and the event-triggered communication parameters can be obtained in a unified framework. Finally, the effectiveness of proposed method is demonstrated through a tunnel diode circuit system.

Homotopy Optimization of Microwave and Millimeter-Wave Filters Based on Neural Network Model

Abstract: High-performance microwave and millimeter-wave filters’ design is a challenging task because the filter characteristic is rather sensitive to the variation of geometric dimensions and electrical sizes. A common practice in filter design is to optimize the design variables starting from a set of initial values. However, if the initial values are not sufficiently close to the optimal solution, the optimization often fails to provide any satisfactory result. To deal with this problem, for the first time, the homotopy method is introduced to microwave and millimeter-wave filters’ optimization problems in this article. The homotopy method formulates a series of intermediate optimization problems, which can guide the optimizer to approach the optimal solution for the target filter design. In this article, the artificial neural network (ANN) is adopted as the surrogate model to the time-consuming electromagnetic model to speed up the homotopy filter optimization process. Two design examples are given to demonstrate the homotopy optimization technique based on the ANN model, including an all-pole filter and a generalized Chebyshev filter with a frequency-dependent coupling. Both filters with optimized geometric dimensions are simulated, and the all-pole filter is fabricated and measured. The simulation and measurement results verify the accuracy of the ANN model and validate the homotopy optimization method.

Finite-time memory fault detection filter design for nonlinear discrete systems with deception attacks

Abstract: In this paper, the finite-time memory fault detection filter (MFDF) is designed for nonlinear discrete systems with randomly occurring deception attacks, where the phenomenon of the randomly occurr...

From Static to Dynamic Anomaly Detection With Application to Power System Cyber Security

Abstract: Developing advanced diagnosis tools to detect cyber attacks is the key to security of power systems. It has been shown that multivariate data injection attacks can bypass bad data detection schemes typically built on static behavior of the systems, which misleads operators to disruptive decisions. In this article, we depart from the existing static viewpoint to develop a diagnosis filter that captures the dynamics signatures of such a multivariate intrusion. To this end, we introduce a dynamic residual generator approach formulated as robust optimization programs in order to detect a class of disruptive multivariate attacks that potentially remain stealthy in view of a static bad data detector. We investigate two possible desired features: (i) a non-zero transient and (ii) a non-zero steady-state behavior of the residual generator in the presence of an attack. In case (i), the problem is reformulated as a finite, but possibly non-convex, optimization program. We further develop a linear programming relaxation that improves the scalability, and as such practicality, of the diagnosis filter design. In case (ii), it turns out that the resulting robust program admits an exact convex reformulation, yielding a Nash equilibrium between the attacker and the residual generator. This assertion has an interesting implication: the proposed approach is not conservative in the sense that the additional knowledge of the worst-case attack does not improve the diagnosis performance. To illustrate our theoretical results, we implement the proposed diagnosis filter to detect multivariate attacks on the system measurements deployed to generate the so-called Automatic Generation Control signals in a three-area IEEE 39-bus system.

A Novel Approach in Filter Design for Grid-Connected Inverters Used in Renewable Energy Systems

Abstract: Renewable energy resources are utilized in distribution networks based on an active front end technology as a bidirectional power flow energy conversion system. Low and high frequency harmonics generated by switching pattern of the power electronics converter should be reduced by an appropriate output filter. According to international regulations, harmonics injected to the grid by pulsewidth modulated (PWM) power converters must be handled to maintain power quality indices within standard limits. LCL filters with passive damping resistors are the most reliable and renowned devices to fulfil the standards. The main objectives in the design of an efficient LCL filter are to reduce the cost and weight of the filter, as well as to increase the robustness and stability of the power electronics converter. In this paper, a comprehensive and mathematical approach is proposed to calculate the maximum current ripple of a PWM-based inverter, which helps to precisely calculate the size of the inverter-side inductors in the LCL filter. The mathematical approach to solve the problem of optimal damping is presented, which can be implemented analytically in different configurations of the LCL filters. The proposed method also works to solve an optimal damping problem for any type of filter.

Online Distributed Learning Over Graphs With Multitask Graph-Filter Models

Abstract: In this article, we are interested in adaptive and distributed estimation of graph filters from streaming data. We formulate this problem as a consensus estimation problem over graphs, which can be addressed with diffusion LMS strategies. Most popular graph-shift operators such as those based on the graph Laplacian matrix, or the adjacency matrix, are not energy preserving. This may result in an ill-conditioned estimation problem, and reduce the convergence speed of the distributed algorithms. To address this issue and improve the transient performance, we introduce a preconditioned graph diffusion LMS algorithm. We also propose a computationally efficient version of this algorithm by approximating the Hessian matrix with local information. Performance analyses in the mean and mean-square sense are provided. Finally, we consider a more general problem where the filter coefficients to estimate may vary over the graph. To avoid a large estimation bias, we introduce an unsupervised clustering method for splitting the global estimation problem into local ones. Numerical results show the effectiveness of the proposed algorithms and validate the theoretical results.

Resilient ${H_{\infty}}$ Filter Design For Continuous-Time Nonlinear Systems

Abstract: In this brief, the resilient ${H_{\infty}}$ filter design problem for continuous-time nonlinear systems is addressed. A Takagi-Sugeno (T-S) fuzzy model with norm-bounded uncertainties is used to represent the nonlinear plant. Meanwhile, the fuzzy filter to be designed is assumed to have gain variations. A useful matrix inequality decoupling approach is proposed to separate the product terms with different types of uncertainties. Then, the resulting design condition of the resilient ${H_{\infty}}$ filter is described by strict linear matrix inequalities (LMIs). Compared with the existing fuzzy resilient filtering results, the proposed design method shows a strong advantage of reducing design conservatism. Finally, a simulation example is provided to demonstrate the feasibility and the advantage of the proposed design method.

Window Selection of the Savitzky–Golay Filters for Signal Recovery From Noisy Measurements

Abstract: The Savitzky–Golay (SG) filtering is a widely used denoising method employed in different applications. The SG filter has two design parameters: the window length and the filter order. As the window length increases, the estimation variance is reduced, but at the same time, the bias error is increased. In this article, we obtain the optimal window length of an SG filter with an arbitrary order, based on minimizing the mean square error (mse), a well-known performance measure considering both the estimation bias and variance. To achieve the optimal window length, we propose an algorithm the performance of which is much better than the existing methods. In this article, we follow the viewpoint proposed by Persson and Strang and design the filter on the basis of the Chebyshev orthogonal polynomials.

Input–Output Finite-Time Generalized Dissipative Filter of Discrete Time-Varying Systems With Quantization and Adaptive Event-Triggered Mechanism

Abstract: This article discusses the issue of input–output finite-time generalized dissipative filter design for a class of discrete time-varying systems. First, an adaptive event-triggered mechanism (AETM) with an adaptive law is proposed to adjust the threshold in the AETM according to the error between the system states and the filter states. Such an AETM determines whether the measurement output should be transmitted or not, which is more effective to economize the communication resources comparing with the traditional event-triggered mechanism. Second, in view of network-induced delays, the quantization and the AETM, a time-varying filter error system (TV-FES) is modeled. Then, a new augmented time-varying Lyapunov functional containing triple sum terms is provided. Based on the new finite-sum inequality and improved reciprocally convex combination lemma, delay-dependent conditions are obtained, which can ensure the TV-FES to be input–output finite-time stable and satisfy the given generalized dissipative performance. Moreover, the recursive linear matrix inequalities are presented to obtain the desired filter gains. Finally, numerical examples demonstrate the superiority and feasibility of the proposed method in this article.

Attack-Resilient Event-Triggered Fuzzy Interval Type-2 Filter Design for Networked Nonlinear Systems Under Sporadic Denial-of-Service Jamming Attacks

Abstract: This paper is concerned with attack-resilient event-triggered $H_{\infty}$ filtering for a class of networked nonlinear systems described by an interval type-2 (IT2) fuzzy model. Suppose that data transmission from the plant to the filter is completed through a wireless sensor network subject to denial-of-service attacks (DoS). In order to save the limited network bandwidth and resist the effects of DoS attacks, a resilient event-triggered communication scheme is devised. Then, an attack-resilient IT2 filter model is introduced to estimate system states of the nonlinear plant. Based on a piecewise Lyapunov-Krasovskii functional, sufficient conditions are obtained to ensure that the filtering error system is exponentially stable and satisfies a certain $H_{\infty}$ performance level. Moreover, explicit expressions for the attack-resilient filter gain parameters and event-triggering parameters can be derived if a set of linear matrix inequalities are feasible. Finally, a practical example is provided to demonstrate the effectiveness of the proposed theoretical results.

Robust Finite-Horizon Filtering for 2-D Systems With Randomly Varying Sensor Delays

Abstract: This paper is concerned with the robust finite-horizon filter design problem for a class of two-dimensional (2-D) time-varying systems with norm-bounded parameter uncertainties and incomplete measurements. The incomplete measurements cover randomly occurring sensor delays and missing measurements that are presented in a unified form by resorting to a stochastic Kronecker delta function. The occurrences of the sensor delays and missing measurements are governed by stochastic variables with known probability distributions. The main aim of the addressed problem is to design a recursive filter with appropriate gain parameters that ensure the local minimum of certain upper bound on the estimation error variance at each time instant. With the aid of the inductive approach and the 2-D Riccati-like difference equations, one of the first few attempts is made to tackle the robust filter design problem for 2-D uncertain systems with random sensor delays over a finite horizon. Sufficient conditions are provided for the existence of an upper bound on the estimation error variance, an algorithm is then developed to derive such an upper bound, and finally the desired filter is designed to minimize the obtained upper bound. The filter design procedure is of a recursive form that facilitates the online calculation. A numerical simulation is carried out to show the effectiveness of the developed filtering scheme.

Inverse Modeling for Filters Using a Regularized Deep Neural Network Approach

Abstract: Extracting coupling matrix from given ${S}$ -parameters can be viewed as an inverse problem for microwave filters, which is of importance for filter design and tuning. In this letter, a regularized deep belief network (R-DBN) is proposed to handle this inverse modeling problem. The training of an R-DBN consists of two steps. First, in unsupervised training, to accommodate the characteristics of input data, this model is constructed with a series of traditional restricted Boltzmann machines (RBMs), which are equipped with a continuous version of transfer function for continuous data processing. In addition, this training can provide suitable weights and bias for the following step. Second, in supervised training, Bayesian regularization is employed to increase modeling ability and prevent overfitting. Two experiments with different simulation environments are illustrated, and the calibration results show high accuracy and robustness in a more intelligent way using this method.