The surface roughness of a machined metal surface is crucial to its appearance and performance. There are hardly any in‐situ methods for surface roughness measurement of moving surfaces. A study of the digital speckle patterns generated by rough surfaces illuminated by a laser is performed experimentally. Laser speckle phenomenon can be used to monitor the surface roughness in a non‐contact way. By investigating the effect of the surface roughness on the statistical and fractal parameters of the laser speckle pattern, an assessment method for evaluating surface roughness is discussed. The results show that some of the proposed statistical parameters have definite relationships with the surface roughness and can be explored to evaluate the surface roughness. Furthermore, the fractal parameters of the speckle pattern are sensitive to the type of machining process and therefore they can be used to classify the machined surface. The method can be a practical tool to achieve in‐situ surface roughness measurement of moving surfaces.

Camber is a typical asymmetrical defect of slabs in the hot-rolling process. The identification of camber plays a key role in improving the quality of the finished strip. To obtain the shape information of the camber, we select the derivative dynamic time warping (DDTW) distance as the measure of curve similarity. An iterative self-organizing data analysis clustering algorithm integrated with DDTW is proposed to divide the sample into different clusters. A curve template is generated via polynomial fitting in each cluster based on the dynamic mechanism of camber. Subsequently, the dynamic time warping (DTW) and DDTW distances are adopted as the input and a weighted random forest (WRF) algorithm is developed for the camber classification to address the sample imbalance problem. Comparative experiments are conducted on the camber sample collected in the actual factory to test the clustering and classification performances. The experimental results indicate that the error rates (ERRs) of four distance-based methods─Euclidean distance, Pearson distance, DTW, and DDTW are 32.7%, 28.5%, 19.1% and 12.3%, respectively, and ERRs of the four classification algorithms—DDTW-SVM, DDTW-KNN, DDTW-RF, and DDTW-WRF are 9.8%, 5.7%, 4.7%, and 2.1%, respectively, which verifies the superior performance of the proposed method in this article.