In this paper, a wind turbine anomaly detection method based on a generalized feature extraction is proposed. Firstly, wind turbine (WT) attributes collected from the Supervisory Control And Data Acquisition (SCADA) system are clustered with k-means, and the Silhouette Coefficient (SC) is adopted to judge the effectiveness of clustering. Correlation between attributes within a class becomes larger, correlation between classes becomes smaller by clustering. Then, dimensions of attributes within classes are reduced based on t-Distributed-Stochastic Neighbor Embedding (t-SNE) so that the low-dimensional attributes can be more full and more concise in reflecting the WT attributes. Finally, the detection model is trained and the normal or abnormal state is detected by the classification result 0 or 1 respectively. Experiments consists of three cases with SCADA data demonstrate the effectiveness of the proposed method.

Magnetic flux leakage (MFL) inspection is one of the most commonly used nondestructive evaluation (NDT) methods for detecting anomalies of ferromagnetic materials. Sizing of the defect with MFL signal is the key problem of inspection, which is important for evaluating the health condition of the material. However, it is an ill-posed inverse problem that is hard to solve and harder to be accurate. Forward models that give a highly accurate simulated signal with a corresponding depth profile are widely used in solving the inverse problem iteratively. Unfortunately, the policy which determines the iteration process is hard to design. In this article, a reinforcement learning (RL)-based algorithm is proposed to reconstruct the depth of defects with a complex depth profile. Instead of designing the policy, the iterative process of the classic iteration-based method is embedded into the learning process of the RL-based algorithm proposed in this article. The policy is learned from the data generated during the reconstructing iteration. By designing the states, actions, and rewards in the RL structure, the most computationally costly part of calling the forward model during iteration is avoided. An adaptive limited exploration process is given to balance the exploration and exploitation in the inverse problem of MFL inspection in this article. The effectiveness of the proposed algorithm is demonstrated with simulation results under different noise levels. The results demonstrate that the proposed algorithm is robust with good reconstruction accuracy.

Purpose: To establish an environment-induced dry eye model in rabbits using a controlled drying system (CDS). Methods: Rabbits were randomly divided into two groups. The rabbits in the dry group were housed in the CDS, in which the relative humidity, airflow, and temperature were controlled at 22% ± 4%, 3 to 4 m/s, and 23°C to 25°C for 14 days. The rabbits in the control group were housed in a normal environment at the same time. A Schirmer test, fluorescein staining, and lissamine green staining were performed. On day 14, the eyeballs and lacrimal glands were processed for evaluating the corneal epithelial thickness, inflammatory cell infiltration index, goblet cell density, and expression of the MUC5AC protein and caspase-3 protein. The mRNA expression of the involved inflammatory genes was analyzed. Results: The CDS was able to maintain a dry environment, in which the tear production decreased, and the ocular surface staining increased over time in the rabbits. In the dry group, the corneal epithelium became thinner, inflammatory cells were noted, goblet cells and MUC5AC proteins decreased, and the increased levels of caspase-3 proteins and inflammatory cytokines were observed in the ocular surface tissues and lacrimal glands. Conclusions: This CDS could create a dry environment, in which the rabbits exhibited a pathological change in dry eye similar to that in humans. Translational Relevance: This model would be helpful in offering a platform to identify and test candidate therapies for environment-induced dry eye and to explore its underlying mechanisms.

Pipeline inspection is important to ensure the safe operation of pipelines. Obtaining the location of an underground pipeline is a prerequisite for most inspection technologies. Existing pipeline location methods can find a pipeline’s location, but they require multiple measurements and cannot be used by automatic inspection robots. In this paper, a tunnel magnetoresistance (TMR)-sensor-array-based pipeline location method is proposed to solve this problem. Firstly, a detection probe is designed using a TMR sensor array. It is calibrated by the improved ellipsoid fitting method to measure the magnetic field around the pipeline accurately. Secondly, a relative pipeline-position-locating method is proposed by detecting the phases of the magnetic induction signals at different frequencies. Thirdly, a three-dimensional pipeline location method is proposed. The horizontal and vertical distances and the angle between the pipeline and the probe are calculated by measuring the magnetic induction amplitude. Finally, a simulation model and a test platform are established, and the experimental results illustrate that, by adopting the TMR array, the three-dimensional pipeline location method can locate a pipeline in real time in three dimensions with good accuracy.

Magnetic flux leakage (MFL) as an efficient method for pipeline flaw detection plays important role in pipeline safety. This nondestructive test technique assesses the health of the buried pipeline. The signal is gathered by an array of hall‐effect sensors disposed at the magnetic neutral plane of a pair of permanent magnet in the pipeline inspection gauge (PIG) clinging to the inner surface of the pipe wall. The magnetic flux measured by the sensors reflects the health condition of the pipe. The signal is influenced by not only the condition of the pipe, but also by the lift‐off value of the sensors and various properties of electronic component. The consistency of the position of the sensors is almost never satisfied and each sensor measures differently. In this paper, a new scheme of channel equalization is proposed for MFL signal in order to correct sensor misalignments, which eventually improves accuracy of defect characterization. The algorithm proposed in this paper is adaptive to the effects of error on the disposition of the sensor due to manufacturing imperfections and movements of the sensors. The algorithm is tested by data acquired from an experimental pipeline. The results show the effectiveness of the proposed algorithm.