Engineering drawing numbering (DN) is one of the most essential procedures for seamless platform integration towards intelligent manufacturing. In spite of this, it is difficult to handle the numbering work in an appropriate and effective manner. This is due to the unpredictability of the names of the manufactured parts and the ineffable relationship between the number and the shape of the parts. This paper proposes a method for numbering items based on historical numbering records based on deep learning. First, name-number (NN) duplexes are generated by retrieving the records. [Formula: see text]-means[Formula: see text] is then used to cluster these NN duplexes. Second, it involves looking up the names of the newly designed items using KNN in order to generate an initial numbering system. Third, a modified multi-view convolutional neural network (MVCNN) is utilized for numbering in situations where the same name is different from the previous number (SNDN). Finally, the most recent sequence numbers are appended to complete the numbering. When the system based on the proposed scheme for authentic engineering application is implemented on a refrigerated compartment, the correctness obtained is over 95%, and the efficiency is increased by 5–6 times.

In this paper, we describe the use of threshold modulation to remove the visual artifacts contained in the variable-coefficient error-diffusion algorithm. To obtain a suitable parameter set for the threshold modulation, a cost function used for the search of optimal parameters is designed. An optimal diffusion parameter set, as well as the corresponding threshold modulation strength values, is thus obtained. Experiments over this new set of parameters show that, compared with the original variable-coefficient error-diffusion algorithm, threshold modulation can remove visual anomalies more effectively. The result of the new algorithm is an artifact-free halftoning in the full range of intensities. Fourier analysis of the experimental results further support this conclusion.