Search

• This paper suggests a grating Moiré fringe-based error correction approach that uses an artificial neural network (ANN) and the quartile method (QM). • The approach uses QM for data cleaning operations to eliminate outliers and creates the ANN model with a structure of fully connected layer-normalization layer-fully connected layer for regression training in order to achieve lightweight and stability. • The proposed QM-ANN error correction model's mean absolute error (MAE) can reach 3.3 nm once the QM data has been cleaned and the ANN model has been trained. Many interference factors of the complex and changeable working environment of the grating sensor are the main factors affecting the accuracy; a grating Moiré fringe error correction model based on the quartile method (QM) and artificial neural network (ANN) is proposed in this paper. Firstly, the grating sensor's signals in the working process are collected, and three kinds of interference signals (temperature, humidity and vibration) from the grating sensor working environment are collected simultaneously. Secondly, the QM is used to detect outliers from the collected data and delete data outliers directly. Subsequently, the processed data are input into the ANN model for training. The model is lightweight and stable, because it adopts the cascaded structure of full connection layer-normalization layer-full connection layer, which does not need deploy the complex convolution layer module etc. Finally, the corrected data are output after being processed by the QM-ANN error correction model. The experimental results show that the mean absolute error (MAE) of the proposed QM-ANN error correction model is better than QM-convolutional neural network (CNN), QM-long short-term memory (LSTM) and ANN, CNN, LSTM models without QM. It shows that the proposed model has better robustness and practicability. [ABSTRACT FROM AUTHOR]

• This paper presents an error correction method for curved rail profile measurement based on selective focus, without adding additional hardware. • This paper proposes a method for solving the optimal auxiliary plane through the objective function of the overlap between virtual 3D rail and actual rail. Its advantage is that the optimal auxiliary plane can be solved through a single line laser. • Laboratory experiments have shown that the rail wear error has been reduced to 0.1 mm, while vehicle dynamic experiments have shown that the rail wear error has been reduced to within 0.2 mm. • This paper proposes a virtual 3D rail creation method based on the center of the light strip, providing a new insight into future work on rail profile measurement error correction. Rail profile detection is an important means of railway operation and maintenance. Currently, structured light profile measurement technology is mainly used for vehicle-mounted rail profile measurement. The body attitude of the vehicle will change as it passes by a curve, and the laser plane of the rail profile measurement device would be non-perpendicular to the rail in the local longitudinal direction, resulting in errors in rail profile measurement. To address this issue, an error correction method based on selective focus for curved rail profile measurement is proposed. The virtual 3D rail is generated with the section image of a single-beam laser and projected onto the image plane, which is then combined with the projection data of virtual 3D rail and the actual rail from the rail image to build the optimization function. The optimal auxiliary plane perpendicular to the rail's longitudinal direction is then determined. Finally, error correction is achieved by projecting the measured data onto the optimal auxiliary plane. The effectiveness and accuracy of the proposed method are validated through experiments, demonstrating that regardless of the laser plane's relative pitch or yaw motion with respect to the rail, the corrected profile wear measurement error was under 0.10 mm, satisfying the requirement for rail wear measurement accuracy. In this study, the plane perpendicular to the longitudinal direction of the rail was obtained through selective focus, thus providing a new insight into future work on rail profile measurement error correction. [ABSTRACT FROM AUTHOR]

Wind power forecasting can effectively improve the energy utilization efficiency of a power system and ensure its stable operation. In this study, a novel hybrid multistep prediction model, including the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), variational mode decomposition (VMD), the kernel principal component analysis (KPCA), an enhanced arithmetic optimization algorithm (ENAOA), a bidirectional long short-term memory (BILSTM) neural network, and error correction, was designed for short-term wind power forecasting. First, the collected original wind power data were decomposed into multiple intrinsic mode functions (IMFs) through a secondary decomposition composed of the CEEMDAN and VMD, which eliminated the interactions between different components to achieve denoising. Second, the KPCA was adopted to reduce the dimensionality of the multiple IMFs by extracting the principal components, effectively reducing the complexity of the multidimensional IMF data and improving the forecasting efficiency of the proposed prediction model. Subsequently, an ENAOA was proposed based on the Sobol sequence, adaptive T-distribution, and random walk strategy to optimize the BILSTM parameters. Finally, multiple preprocessed components were predicted by the optimized BILSTM, after which error correction was performed to obtain the final prediction results, which could further reduce the forecast error of the designed prediction model. Based on two sets of data collected from a wind farm in northwest China, the simulation results of 1-step, 4-step, 7-step, and 10-step forecasting revealed that compared with other incomplete models, the various algorithms adopted in the hybrid forecasting model reduced the prediction errors to different degrees, significantly enhanced the wind power prediction performance, and validated the effectiveness and feasibility of the proposed model. • Original wind power data is preprocessed through CEEMNAN and VMD. • KPCA is adopted to extract principal components of several IMFs. • Propose an improved ENAOA optimization algorithm through three improvements. • Error correction is employed to further increase the forecast accuracy. • The hybrid multi-step forecasting model greatly reduces the prediction error. [ABSTRACT FROM AUTHOR]