Experiments have proven that traditional prediction research methods have limitations in practice. Proposing countermeasures for environmental changes is the key to optimal control of the cold chain environment and reducing the lag of control effects. In this paper, a cold chain transportation environment prediction method, combining k-means++ and a long short-term memory (LSTM) neural network, is proposed according to the characteristics of the cold chain transportation environment of agricultural products. The proposed prediction model can predict the trend of cold chain environment changes in the next ten minutes, which allows cold chain vehicle managers to issue control instructions to the environmental control equipment in advance. The fusion process for temperature and humidity data measured by multiple data sensors is performed with the k-means++ algorithm, and then the fused data are fed into an LSTM neural network for prediction based on time series. The prediction error of the prediction model proposed in this paper is very satisfactory, with a root-mean-square error (RMSE), mean absolute error (MAE), mean squared error (MSE), mean absolute percentage error (MAPE) and R-squared of 0.5707, 0.2484, 0.3258, 0.0312 and 0.9660, respectively, for temperature prediction, and with an RMSE, MAE, MSE, mean absolute percentage error and R-squared of 1.6015, 1.1770, 2.5648, 0.2736 and 0.9702, respectively, for humidity prediction. Finally, the LSTM neural network and back propagation (BP) neural network are compared in order to enhance the reliability of the results. In terms of the prediction effect of the temperature and humidity in cold chain vehicles transporting agricultural products, the proposed model has a higher prediction accuracy than that of existing models and can provide strategic support for the fine management and regulation of the cold chain transportation environment.

In order to overcome the shortcomings of existing electrowetting display defect detection models in terms of computational complexity, structural complexity, detection speed, and detection accuracy, this article proposes an improved YOLOv7-based electrowetting display defect detection model. The model effectively optimizes the detection performance of display defects, especially small target defects, by integrating GhostNetV2 modules, Acmix attention mechanisms, and NGWD (Normalized Gaussian Wasserstein Distance) Loss. At the same time, it reduces the parameter size of the network model and improves the inference efficiency of the network. This article evaluates the performance of an improved model using a self-constructed electrowetting display defect dataset. The experimental results show that the proposed improved model achieves an average detection rate (mAP) of 89.5% and an average inference time of 35.9 ms. Compared to the original network, the number of parameters and computational costs are reduced by 19.2% and 64.3%, respectively. Compared with current state-of-the-art detection network models, the proposed EW-YOLOv7 exhibits superior performance in detecting electrowetting display defects. This model helps to solve the problem of defect detection in industrial production of electrowetting display and assists the research team in quickly identifying the causes and locations of defects.

The electrowetting display (EWD) has obtained much attention as its readability in sunlight and flexible displays. Oil motion control is an important factor for the display performance of EWD. In this paper, we propose a low-cost drive and detection scheme for EWD. The dynamic drive and detection scheme for EWD consists of a low-cost camera, computer and graphical detection system, and portable driving control system. The proposed scheme can detect oil leaking, splitting, and non-recovered defects successfully. Moreover, surface defects such as the hydrophobic layer burned and scratch can also be captured and analyzed by the proposed scheme. We hope that this scheme can provide a drive and detection platform for other EWD researchers.

Traditional methods for reliability and lifetime testing of digital microfluidic systems heavily rely on real-time monitoring data. This often leads to evaluation lag and limits their application, especially for complex droplets. To address these issues, this study proposes a novel prediction model for digital microfluidic (DMF) devices. The model combines an attention-based bidirectional long short-term memory (BiLSTM) with eXtreme Gradient Boosting (XGBoost) using a Stacking approach. This integrated model efficiently identifies the health state and predicts the failure time of digital microfluidic devices. This approach overcomes the limitations of traditional methods, such as over-reliance on sensor feedback and detection hysteresis. Experimental results demonstrate high prediction accuracy. The model achieved a mean absolute percentage error (MAPE) of 1.6464, Root mean squared error (RMSE) of 0.3667, mean absolute error (MAE) of 0.2557, and a coefficient of determination (R-squared) of 0.9949. Compared to baseline methods, the proposed BiLSTM-XGBoost model achieves the highest prediction accuracy, enabling effective health monitoring, problem identification, and failure prediction. Ultimately, this improves system reliability and lifetime with greater timeliness and accuracy.

In practical applications of droplet actuation using digital microfluidic (DMF) systems based on electrowetting-on-dielectric (EWOD), various electrode failures can still arise due to diverse operational conditions. To improve droplet transport efficiency, this study proposes a heuristic-elite genetic algorithm (HEGA) for droplet path planning. We introduce a heuristic method and a bidirectional elite fragment recombination method to address the challenge of poor initialization quality in genetic algorithms, particularly in complex environments. These approaches aim to enhance the global search capability and accelerate the algorithm’s convergence. Simulations were performed using MATLAB, and the results indicate that compared to the basic ant colony algorithm, the proposed method reduces the average number of turning points by approximately 17.23% and the average search time by about 92.60%. In multi-droplet transport applications, the algorithm generates optimal paths for test droplets while maintaining fast convergence. Additionally, it effectively prevents droplets from accidentally contacting or merging in non-synthesis areas, ensuring improved testing outcomes for the chip.