In this paper, the problem of intelligent fault detection for switched systems is investigated based on SVM. In order to illustrate the ability of SVM in distinguishing normal and faulty systems, a model-based analysi...
详细信息
ISBN:
(纸本)9781665478977
In this paper, the problem of intelligent fault detection for switched systems is investigated based on SVM. In order to illustrate the ability of SVM in distinguishing normal and faulty systems, a model-based analysis method is introduced in this paper. Different from the existing methods, this paper considers the influence of disturbance on the output data. The theoretical model of SVM is given, which can realize the fuzzy distinction between normal and fault system data, and describe the indistinguishable region affected by disturbance. Finally, one numerical model of aeroengine is used to illustrate the effectiveness of the proposed analysis.
Group re-identification (GReID) is an important yet less-studied task. GReID focuses on associating the group images across non-overlapping cameras. The key challenges of GReID include layout variation, membership cha...
详细信息
ISBN:
(纸本)9781665476881
Group re-identification (GReID) is an important yet less-studied task. GReID focuses on associating the group images across non-overlapping cameras. The key challenges of GReID include layout variation, membership changes, and occlusion. Most existing methods focus on the group variation but ignore the occlusion that frequently occurs in the group. In practical scenarios, so many activities like conversing, queuing, or fighting consist of groups. To this end, we design a novel Transformer-based Siamese Network for GReID (TSN-GReID) for joint learning of classification and correspondence tasks to learn more robust group features for group layout and membership changes. Furthermore, we put forward an original regrouping random patch module(RRPM) which respectively regroups the member patch embedding and member-level local features to generate group features with improved discrimination ability and more diversified coverage to deal with occlusion. Experimental results demonstrate the effectiveness of our approach, which significantly outperforms state-of-the-art methods by 4.6 % Rank-1 on the CUHK-SYSU Group (CSG) dataset and by 7.1% Rank-1 on the DukeMTMC Group dataset.
Recent years have seen the emergence of non-cooperative objects in space, like failed satellites and space junk. These objects are usually operated or collected by free-float dual-arm space manipulators. Thanks to eli...
详细信息
This paper proposes a novel statistical parameters based data driven approach for passive islanding detection. The proposed scheme relies in the voltage data, measured at the point of common coupling, and is comprised...
详细信息
ISBN:
(纸本)9781665459310
This paper proposes a novel statistical parameters based data driven approach for passive islanding detection. The proposed scheme relies in the voltage data, measured at the point of common coupling, and is comprised of three stages. The Stage-1 quickly detects what is termed as coarse islanding, Stage-2 computes the decaying DC detector (DDCD), and 3) finally, the digital relay logic (DRL) is devised in Stage-3. The proposed scheme is tested as per the IEEE-1547, UL 1741 and IEC-62116 standards. Various tests are investigated on the modified IEEE-13 bus system, modeled in PSCAD/EMTDC, under stringent test scenarios such as power mismatch, induction motor starting effect, capacitor bank switching and various level of loads changes, considered for both single and multiple DG systems. The test results reveal that the proposed scheme can detect islanding in less than 2 cycles, and results in nearly zero non detection zone (NDZ). Also, the scheme can very well be used for single-phase microgrids too as it relies only on the single phase voltage information.
Automated Guided Vehicles (AGVs) are usual in industrial settings, with an increasing economic impact on processes. They move through numerous environments inside factories, commonly navigating long distances, while p...
详细信息
ISBN:
(数字)9781665462808
ISBN:
(纸本)9781665462815
Automated Guided Vehicles (AGVs) are usual in industrial settings, with an increasing economic impact on processes. They move through numerous environments inside factories, commonly navigating long distances, while performing several activities. The constant detection of such vehicles, especially in cases of maintenance and safety, is a main issue in an industry setting. Usually, this information could be provided by a supervisory system, but many applications are not so large as to make such a system viable. Thus, a solution via machine learning and computer vision is developed in this work, by using simple cameras, such as the factories' security cameras. As the industrial environment is a scenario with a lot of variation and noise, the Transfer Learning technique is used to improve the training step of the developed AGV detection system. Finally, a database with 1067 images is used to build and validate the model, achieving a result greater than 80% of F1-score for various confidence values.
Policy iteration is one of the classical frameworks of reinforcement learning, which requires a known initial stabilizing control. However, finding the initial stabilizing control depends on the known system model. To...
详细信息
In this paper, the $\mathcal{L}_{1}$ -gain based filtering problem for nonlinear positive semi-Markov jump systems is investigated by proposing a novel asynchronous design approach. More precisely, the mode-dependent...
详细信息
ISBN:
(数字)9789887581536
ISBN:
(纸本)9781665482561
In this paper, the $\mathcal{L}_{1}$ -gain based filtering problem for nonlinear positive semi-Markov jump systems is investigated by proposing a novel asynchronous design approach. More precisely, the mode-dependent filters are designed in terms of practical observed modes instead of true system modes, such that less conservatism can be achieved. In addition, the effect of time-varying delays is taken into account for more robustness and applicability. By selecting suitable stochastic Lyapunov-Krasovskii functions and applying the linear programming method, sufficient conditions are established to fulfill the desired $\mathcal{L}_{1}$ -gain performance. Eventually, the illustrative simulation is performed to verify the effectiveness of our developed control scheme.
The authors highlight the need for the development and industrial deployment of online monitoring systems for the elastic moment on the rolling mill stand spindles. An example of a 5000 plate mill was used to demonstr...
The authors highlight the need for the development and industrial deployment of online monitoring systems for the elastic moment on the rolling mill stand spindles. An example of a 5000 plate mill was used to demonstrate that these systems are made due to the need for a reliable moment assessment in dynamic modes. This problem is relevant for the development of control systems limiting the maximum (amplitude) values of moments when the workpieces enter the stand. The shock loading causes a multifold increase of the dynamic moment over the steady rolling moment. This results in the fatigue breakdown of spindle connections., as well as mill failures and emergency stops. The authors provide information on a telemetric elastic moment monitoring system installed on a 5000 mill. The data were validated in the industrial context. To achieve this, the authors propose a procedure where experimental research is carried out in two stages. During the first stage, the electromagnetic moment of the motor is compared to the spindle moment in the quasi-steady rolling mode when the elastic properties of the spindle are not manifested. During the second stage, the elastic moments of the upper and lower roll motors are assessed during 9 passes of reverse rolling. Some conclusions are made about the proportion of roll motor loads, spindle moment amplitudes, and the relevance of aligning rolling moments through the improvement of electric drive speed control algorithms.
Training of a Machine Learning model requires sufficient data. The sufficiency of the data is not always about the quantity, but about the relevancy and reduced redundancy. Data-generating processes create massive amo...
详细信息
In this paper, a multi-kernel principal component analysis (MKPCA) method for quality-related fault detection is proposed. The initial space is firstly mapped to a new space. The correlated information between the new...
详细信息
ISBN:
(纸本)9781665465373
In this paper, a multi-kernel principal component analysis (MKPCA) method for quality-related fault detection is proposed. The initial space is firstly mapped to a new space. The correlated information between the new space and output quality is then obtained by the kernel function. Meanwhile, with consideration of the advantage of global function and local function, a weight factor which combines them together is introduced to construct a multi-kernel function. In this way, the algorithm achieves better learning ability. The new space is projected to two mutually orthogonal subspaces, i.e., quality-related part and quality-unrelated part. In each subspace, fault information is expressed by different statistical indicators. The numerical example is presented to evaluate the performance of the MKPCA. The results show better reliability and high fault detection rate through proper spatial decomposition and kernel function construction.
暂无评论