Electrical load forecasting is a vital process for balancing the electricity supply and demand sections. In order to make a precise prediction, many intelligent methods aiming at forecasting future load of different horizons have been proposed in recent years. Regardless of the great progress in this field, yet two major problems widely exist in the field of midterm load forecasting, which are pseudo midterm forecast and divergence of the forecasting error. This article proposes a multistep forecasting approach, mainly based on phase space reconstruction and support vector machine (SVM) methods, to solve these two problems. The relations between the forecasting step in the future and the historical data points that need to be fed into the SVM model are derived, which endue the model with the real ability to forecast adjustable steps of future load without the divergence of error and, therefore, have a notable engineering application significance. The proposed methodology is implemented on the European Network on Intelligent Technologies dataset. Compared with previous methods, the results show that the multistep implemented model is of more accurate prediction and stronger robustness. Moreover, the method is easy to implement and able to be combined with other intelligent methods to get better performance.

This paper reports the characterization of disbonds between a steel plate and a lead plate on the surface of the lead using lock-in thermography. Based on the photothermal model, the excitation frequency of the bonding specimen with the steel plate and the lead plate is optimized. A lock-in thermography testing system is established to inspect the specimen. The Fourier transform method is used to process the infrared image sequences. To improve the signal-to-noise ratio (SNR), a fuzzy c-means (FCM) algorithm is used to process the phase matrix. The influence of number of clusters on the processing results is researched, and the optimal value of clusters number is obtained. The shearing phase technique is used to evaluate the size of the disbonds quantitatively. The measurement results of the artificial disbonds in the specimen show good agreement with the actual values. The results prove that FCM is effective in enhancing the SNR of the phase image, which makes it feasible for the quantitative determination of defect size by the shearing phase technique.