Continuous inkjet technology, as a key technology in the field of industrial printing, is favoured for its excellent printing speed, precision and versatility. In order to achieve the accurate generation of ideal droplets in continuous inkjet devices, this paper proposes a new parameter optimisation method, BO-GP, which combines the Bayesian optimisation algorithm with computer vision, and after 50 rounds of iterations, it can converge to the optimal values of the control parameters, and successfully constructs the Pareto frontier of the control parameters. In this paper, experiments were conducted on two different device droplet image datasets, a millimetre-scale inkjet device and a microfluidic device, respectively. Compared with the original BO in Loop method, the optimised minimum objective function value is reduced from 0.378 to 0.331 in the millimetre-scale device, and from 0.073 to 0.046 in the microfluidic device. Moreover, the Pareto solution of the 10 sets of predicted parameters output using the BO-GP method tends to be stable with fluctuations around 0.1, and it takes only 1 h to derive the control conditions for achieving high roundness, high yield and uniform size droplets.
1 February 2021 in Journal of Physics: Conference Series
In recent years, with the rapid development of NLP (Natural Language Processing) and deep learning, public opinion and public opinion on the Internet have decreased a lot compared to the past. Many Internet users have changed from mere "bystanders" to disseminators of Internet information. Movie review sentiment analysis technology is an emerging category in the field of information mining. More and more people have joined the "review army". The quality of a movie is closely related to movie reviews! The manual screening method not only consumes a lot of manpower and material resources, but also is inefficient. Therefore, the use of deep learning-based sentiment analysis has become the current general trend. Based on the principle of word mosaic (word vector) and deep learning, this paper proposes a movie review sentiment analysis technology based on deep learning and machine learning word mosaic. Experiments show that the method used in this article has reached the correct rate of emotional classification of movie reviews. 83.13%, the experimental results prove the practicability and scalability of this method and the effectiveness of this method.
With the advent of the 6G era, the number of IoT devices has experienced explosive growth, leading to the generation of massive amounts of data at the network edge. Semantic communication, as an innovative solution to handling this data deluge, can significantly enhance communication efficiency. However, the limited storage and computational resources of terminal devices constrain the widespread application of semantic communication in 6G networks. To address this issue, we propose a terminal-side-computing-driven intelligent semantic communication solution. Specifically, we introduce a semantic communication model based on Kolmogorov–Arnold Networks (KANs), named K-DeepSC. Using image-reconstruction tasks as an example, the proposed K-DeepSC reduces the number of model parameters by 44% compared to semantic communication models based on Multi-Layer Perceptrons (MLPs), while maintaining similar performance. Furthermore, to fully leverage idle terminal computing power for semantic tasks, we explore computation offloading in dynamic Terminal-Side Computing Power Networks. By optimizing task delay minimization, a deep reinforcement learning algorithm is employed to determine the optimal offloading strategy. Simulation results demonstrate that our proposed solution effectively reduces semantic task processing delay.
Satellite droplet are trailing droplets caused by improper voltage waveform control in the nozzles, which directly affect the quality of inkjet printing. Traditional empirical tuning methods struggle to effectively control and predict satellite droplet. In response, this paper establishes a simulation model of a ring-shaped piezoelectric ceramic device. establishes a simulation model of a ring-shaped piezoelectric ceramic nozzle through numerical analysis, collecting droplet behavior parameters for 13,650 different waveforms. It was found that the relative differential of the negative pressure peak at the nozzle is the primary cause of satellite droplet formation. Furthermore, the critical values of various behavior parameters leading to satellite droplet formation were investigated, resulting in the construction of a “Satellite droplet formation”. resulting in the construction of a “Satellite droplet threshold domain.” Based on this domain, an attention-based MLP algorithm, the Attentive Ink MLP Based on this domain, an attention-based MLP algorithm, the Attentive Ink MLP, was proposed to automatically predict whether a waveform will generate satellite droplet. algorithm reduces prediction time from 40 min to 5 min, with a validation accuracy of 0.988. The numerical analysis and algorithm were further validated through experiments with a droplet. The numerical analysis and algorithm were further validated through experiments with a droplet observation system.