Abnormal actions detection of robotic arm via 3D convolution neural network and support vector data description

Robotic arms are powerful assistants in many industrial production environments, and they run periodically in accordance with preset actions to complete specified operations. However, they may act abnormally when encountering unexpected situation and then lead to unnecessary loss. Recognizing the abnormal actions of robotic arms through surveillance video can automatically help us to understand their operating status and discover possible abnormalities in time. We designed a deep learning architecture based on 3D convolution for abnormal action recognition. The 3D convolutional layer can extract the spatial and temporal features of the robotic arm movements from the video frame difference sequence. The features are compressed and streamlined by the maximum pooling layer to obtain concise and effective robotic arm action features. Finally, the fully connected layer is used to classify the features to recognize the abnormal robotic arm tasks. Support vector data description (SVDD) model is employed to detect abnormal actions of the robotic arm, and the well-trained SVDD model can distinguish the normal actions from the three kinds of abnormal actions with the Area Under Curve (AUC) 99.17% .

Aging state detection of viscoelastic sandwich structure using redundant second generation wavelet packet transform and fuzzy support vector data description

Viscoelastic sandwich structure plays an important role in mechanical equipment, nevertheless viscoelastic material inevitably suffers from gradual aging. For guaranteeing the operation safety of mechanical equipment, it is urgent to perform the aging state detection of viscoelastic sandwich structure with vibration response signal analysis. However, the structural vibration response signal is non-stationary and its variation caused by the structural aging state change is very puny, and the abnormal state samples is lacking. The vibration-based structural aging state detection has become a challenging task. Therefore, a novel method based on redundant second generation wavelet packet transform (RSGWPT) and fuzzy support vector data description (FSVDD) is proposed for this task. For extracting sensitive aging feature information, RSGWPT is introduced to process the structural vibration response signal, and multiple energy features are extracted from the frequency-band signals to reflect structural aging state change. For accurate and automatic aging state identification, by fusing fuzzy theory, FSVDD only uses the normal state samples for training and can identify the abnormal severity degrees is developed to identify the structural aging states. The proposed method is applied on a viscoelastic sandwich structure to validate its effectiveness, and different structural aging states are created through the accelerated aging of viscoelastic material. The analysis results show the outstanding performance of the proposed method.

A Novel Hybrid Method for KPI Anomaly Detection Based on VAE and SVDD

Key performance indicator (KPI) anomaly detection is the underlying core technology in Artificial Intelligence for IT operations (AIOps). It has an important impact on subsequent anomaly location and root cause analysis. Variational auto-encoder (VAE) is a symmetry network structure composed of encoder and decoder, which has attracted extensive attention because of its ability to capture complex KPI data features and better detection results. However, VAE is not well applied to the modeling of KPI time series data and it is often necessary to set the threshold to obtain more accurate results. In response to these problems, this paper proposes a novel hybrid method for KPI anomaly detection based on VAE and support vector data description (SVDD). This method consists of two modules: a VAE reconstructor and SVDD anomaly detector. In the VAE reconstruction module, firstly, bi-directional long short-term memory (BiLSTM) is used to replace the traditional feedforward neural network in VAE to capture the time correlation of sequences; then, batch normalization is used at the output of the encoder to prevent the disappearance of KL (Kullback–Leibler) divergence, which prevents ignoring latent variables to reconstruct data directly. Finally, exponentially weighted moving average (EWMA) is used to smooth the reconstruction error, which reduces false positives and false negatives during the detection process. In the SVDD anomaly detection module, smoothed reconstruction errors are introduced into the SVDD for training to determine the threshold of adaptively anomaly detection. Experimental results on the public dataset show that this method has a better detection effect than baseline methods.

Abnormal Data Detection of Guidance Angle Based On SMP-SVDD For Seeker

The accuracy of the pitch angle deviation directly affects the guidance accuracy of the laser seeker. During the guidance process, the abnormal pitch angle deviation data will be produced when the seeker is affected by interference sources. In this paper, aiming to detect abnormal data in seeker pitch angle deviation data, a method based on Smooth Multi-Kernel Polarization Support Vector Data Description (SMP-SVDD) is proposed to detect abnormal data in guidance angle data. On the one hand, the polarization value is used to determine the weight of the multi-kernel combination coefficient to obtain the multi-kernel polarization function, and the particle swarm optimization is used to find the optimal kernel, which improves the detection accuracy. On the other hand, the constrained quadratic programming problem is smooth and differentiable, and the conjugate gradient method can be applied to reduce the complexity of problem solving. Through simulation experiments, it is verified that the SMP-SVDD method has higher detection accuracy and faster calculation speed compared with different detection methods in different guidance stages.

Weighted Decoding for the Competence Reliability Problem of ECOC Multiclass Classification

Error-Correcting Output Codes has become a well-known, established technique for multiclass classification due to its simplicity and efficiency. Each binary split contains different original classes. A noncompetent classifier emerges when it classifies an instance whose real class does not belong to the metasubclasses which is used to learn the classifier. How to reduce the error caused by the noncompetent classifiers under diversity big enough is urgent for ECOC classification. The weighted decoding strategy can be used to reduce the error caused by the noncompetence contradiction through relearning the weight coefficient matrix. To this end, a new weighted decoding strategy taking the classifier competence reliability into consideration is presented in this paper, which is suitable for any coding matrix. Support Vector Data Description is applied to compute the distance from an instance to the metasubclasses. The distance reflects the competence reliability and is fused as the weight in the base classifier combination. In so doing, the effect of the competent classifiers on classification is reinforced, while the bias induced by the noncompetent ones is decreased. Reflecting the competence reliability, the weights of classifiers for each instance change dynamically, which accords with the classification practice. The statistical simulations based on benchmark datasets indicate that our proposed algorithm outperforms other methods and provides new thought for solving the noncompetence problem.

Batch process monitoring based on global enhanced multiple neighborhoods preserving embedding

Batch process generally has varying dynamic characteristic that causes low fault detection rate and high false alarm rate, and it is necessary and urgent to monitor batch process. This paper proposes a global enhanced multiple neighborhoods preserving embedding based fault detection strategy for dynamic batch process. Firstly, the angle neighbor is defined and selected to compensate for the insufficient expression for the spatial similarity of samples only by using the distance neighbor, and the time neighbor is introduced to describe the time correlations between samples. These three types of neighbors can fully characterize the similarity of the samples in time and space. Secondly, considering the minimum reconstruction error and the order information of three types of neighbors, an enhanced objective function is constructed to prevent the loss of order information when neighborhood preserving embedding (NPE) calculates the reconstruction weights. Furthermore, the enhanced objective function and a global objective function are organically combined to extract both global and local features, to describe process dynamics and visualize process data in a low-dimensional space. Finally, a monitoring index based on support vector data description is constructed to eliminate adverse effects of non-Gaussian data for monitoring performance. The advantages of the proposed method over principal component analysis, neighborhood preserving embedding, dynamic principal component analysis and time NPE are demonstrated by a numerical example and the penicillin fermentation process simulation.