Recording runtime status via logs is common for almost every computer system, and detecting anomalies in crucial timely identifying malfunctions of systems. However, manually time-consuming, error-prone, infeasible. Existing automatic log anomaly detection approaches, using indexes rather than semantics templates, tend to cause false alarms. In this work, we propose LogAnomaly, a framework model unstructured stream as natural language sequence. Empowered by template2vec, novel, simple yet...

Outliers may cause model deviation and then affect the monitoring performance hence it is a challenging problem for process monitoring. The robust principal component analysis (RPCA) approach, which describes outlier components with sparse matrix identifies these using recovery most commonly used method to solve problems caused by outliers. However, because existing mathematical tools can only obtain nonsparse small element values, RPCA performs poorly during In this paper, we propose novel...

Abstract The linear quadratic Gaussian (LQG) control for a quadrotor unmanned aerial vehicle (UAV) under false data injection attacks is studied. LQG depends on optimal state estimation, while this type of makes the estimation unimplementable in practice. To address problem, authors prose framework to detect and then augment information controller design. Based framework, designed sufficient condition security closed‐loop system given. Finally, applied UAV, some experiments are carried out...

Causal effect estimation of individual heterogeneity is a core issue in the field causal inference, and its application medicine poses an active challenging problem. In high-risk decision-making domain such as healthcare, inappropriate treatments can have serious negative impacts on patients. Recently, machine learning-based methods been proposed to improve accuracy results. However, many these concentrate estimating effects continuous outcome variables under binary intervention conditions,...

This article presents a novel singular value decomposition (SVD)-based robust distributed model predictive control (SVD-RDMPC) strategy for linear systems with additive uncertainties. The system is globally constrained and consists of multiple interrelated subsystems bounded disturbances, each whom has local constraints on states inputs. First, we integrate the steady-state target optimizer into MPC problem through offset cost function to formulate modified single optimization tracking...

To overcome the shortage of traditional temperature sensors, this paper adopts infrared thermal imaging technology for measurement. avoid spatial information loss issue during image data vectorization process, adopted relationship between pixels in principal component analysis (PCA) model training, which is called information-based PCA (SIPCA). Then, also used fault localization method to enhance location performance. Tested by an experimental tank system, proposed achieves better...

Deep learning methods have been rapidly developed in recent decades. In this work, they are extended to model spatial-temporal industrial processes. Instead of pure black-box data-driven modeling approaches, the proposed encodes domain knowledge and physical rules governing spatiotemporal system, called a dual-hierarchical recurrent neural network (DH-RNN). Both spatial temporal relationships modeled by multiple RNNs with diverse structures, which need correct specifications all interactions...

In this paper, a new sparse approximation technique is proposed for incremental power grid analysis. Our method motivated by the observation that when network locally updated during circuit design, its response changes and, hence, "change" of voltage almost zero at many internal nodes, resulting in unique pattern. An efficient Orthogonal Matching Pursuit (OMP) algorithm adopted to solve problem. addition, several numerical techniques are improve stability solver, while simultaneously...

Due to the pseudo-bipolar structure of flexible DC distribution network, short-circuit current caused by a pole-to-ground fault is weak. The characteristics, particularly steady-state are not prominent. Therefore, diagnosis and protection have become more challenging. This paper theoretically studies characteristics in derives analytical expression current, analyzes directional characteristics. Then, novel pilot scheme based on direction comparison proposed. compares positive negative...

Abstract Modelling is a basic and key requirement for model‐based controlling, monitoring, or other process strategies. In non‐linear model predictive control (NMPC), although data‐driven models can be more easily established than first‐principle ones, representative data may not adequately included in advance to train complete model, which an attractive research topic. An actively improved Gaussian (GP) building strategy developed, especially incomplete based on the idea of Bayesian...

An event-based consensus filtering control scheme for multi-agents with multiple mixing delays is proposed in the paper. Firstly, a piece-wise sampling model transmission delay defined from sensors to controllers built, and effect of time-varying on analyzed. Secondly, self-triggered take into consideration reducing redundant data complexity. Thirdly, fully utilize available information, by employing an improved generalized free-weighting matrix inequality, novel Lyapunov-Krasovskii...

This paper proposes a novel stabilizing decentralized model predictive control for nonlinear continuous systems. We extend the method proposed by [1] from discrete time systems to The key idea of this is adding contractive constraint optimal problem each subsystems. By whole system can be stabilizable within certain degree interaction. interaction also represented inequalities. Finally numerical simulation used prove effectiveness and applied four-tank benchmark problem.

Abstract Traditional multivariate statistical-based process monitoring (MSPM) methods are effective data-driven approaches for large-scale industrial processes, but have a shortcoming in handling the redundant correlations between variables. To address this shortcoming, study proposes new MSPM method called minimalist module analysis (MMA). MMA divides data into several different modules and one more independent module. All variables strongly correlated, no exist; therefore, extracted...

Gaussian process (GP) models based model predictive control (MPC) structure for cooperative motion planning of Unmanned Aerial and Ground Vehicle System (UAGVS) is proposed in this article. The GP are firstly trained to describe the dynamics UAVs UGVs with their uncertainties. Stochastic optimization problems designed controlling on models' probabilistic predictions. And necessary interactions among agents, predicted information also communicated each other, so that they can obtain others'...

A new data-driven system identification method, called KL-GP, is proposed for spatiotemporal system. It combines Karhunen-Loève (KL) decomposition and Gaussian process (GP) models. As the nonlinear spatial-temporal has strong characteristics, KL with good characteristics employed time/space separation dimension reduction. Then output expanded onto a low-dimensional space temporal coefficients. GP models are to build up relation using these In addition, healthy model that accuracy predictions...