Tool wear condition monitoring is an important component of mechanical processing automation, and accurately identifying the wear status of tools can improve processing quality and production efficiency. This paper studied a new deep learning model, to identify the wear status of tools. The force signal was transformed into a two-dimensional image using continuous wavelet transform (CWT), short-time Fourier transform (STFT), and Gramian angular summation field (GASF) methods. The generated images were then fed into the proposed convolutional neural network (CNN) model for further analysis. The calculation results show that the accuracy of tool wear state recognition proposed in this paper was above 90%, which was higher than the accuracy of AlexNet, ResNet, and other models. The accuracy of the images generated using the CWT method and identified with the CNN model was the highest, which is attributed to the fact that the CWT method can extract local features of an image and is less affected by noise. Comparing the precision and recall values of the model, it was verified that the image obtained by the CWT method had the highest accuracy in identifying tool wear state. These results demonstrate the potential advantages of using a force signal transformed into a two-dimensional image for tool wear state recognition and of applying CNN models in this area. They also indicate the wide application prospects of this method in industrial production.

This paper presents a study on surface roughness generated by high speed milling of high volume fraction (65%) silicon carbide particle-reinforced aluminum matrix (SiCp/Al) composites. Typical 2D (Ra and Rz) and 3D (Sa and Sq) surface roughness parameters were selected to evaluate the influence of the milling parameters on the surface quality in comparison with aluminum alloy. The 3D topography of the milled surface was studied as well. The results indicate that 3D parameters (Sa and Sq) are more capable to describe the influence of the milling parameters on the surface quality, and among them Sq is preferable due to its good sensitivity. Sq decreases with milling speed and increases with feed rate. The influence of axial depth of cut (ADOC) is negligible

The excessive pesticide residues in cereals, fruit and vegetables is a big threat to human health, and it is necessary to develop a portable, low-cost and high-precision pesticide residue detection scheme to replace the large-scale laboratory testing equipment for rapid detection of pesticide residues. In this study, a colorimetric device for rapid detection of organophosphorus pesticide residues with high precision based on a microfluidic mixer chip was proposed. The microchannel structure with high mixing efficiency was determined by fluid dynamics simulation, while the corresponding microfluidic mixer chip was designed. The microfluidic mixer chip was prepared by a self-developed liquid crystal display (LCD) mask photo-curing machine. The influence of printing parameters on the accuracy of the prepared chip was investigated. The light source with the optimal wavelength of the device was determined by absorption spectrum measurement, and the relationship between the liquid reservoir depth and detection limit was studied by experiments. The correspondence between pesticide concentration and induced voltage was derived. The minimum detection concentration of the device could reach 0.045 mg·L⁻¹ and the average detection time was reduced to 60 s. The results provide a theoretical and experimental basis for portable and high-precision detection of pesticide residues.

In tool wear monitoring, the efficient fusion of multi-source sensor signals poses significant challenges due to their inherent heterogeneous characteristics. In this paper, we propose a Multi-Sensor Multi-Domain feature fusion Transformer (MSMDT) model that achieves precise tool wear prediction through innovative feature engineering and cross-modal self-attention mechanisms. Specifically, we first develop a physics-aware feature extraction framework, where time-domain statistical features, frequency-domain energy features, and wavelet packet time–frequency features are systematically extracted for each sensor type. This approach constructs a unified feature matrix that effectively integrates the complementary characteristics of heterogeneous signals while preserving discriminative tool wear signatures. Then, a position-embedding-free Transformer architecture is constructed, which enables adaptive cross-domain feature fusion through joint global context modeling and local feature interaction analysis to predict tool wear values. Experimental results on the PHM2010 demonstrate the superior performance of MSMDT, outperforming state-of-the-art methods in prediction accuracy.

Tool condition monitoring technology is an indispensable part of intelligent manufacturing. Most current research focuses on complex signal processing techniques or advanced deep learning algorithms to improve prediction performance without fully leveraging the end-to-end advantages of deep learning. The challenge lies in transforming multi-sensor raw data into input data suitable for direct model feeding, all while minimizing data scale and preserving sufficient temporal interpretation of tool wear. However, there is no clear reference standard for this so far. In light of this, this paper innovatively explores the processing methods that transform raw data into input data for deep learning models, a process known as an input paradigm. This paper introduces three new input paradigms: the downsampling paradigm, the periodic paradigm, and the subsequence paradigm. Then an improved hybrid model that combines a convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) was employed to validate the model’s performance. The subsequence paradigm demonstrated considerable superiority in prediction results based on the PHM2010 dataset, as the newly generated time series maintained the integrity of the raw data. Further investigation revealed that, with 120 subsequences and the temporal indicator being the maximum value, the model’s mean absolute error (MAE) and root mean square error (RMSE) were the lowest after threefold cross-validation, outperforming several classical and contemporary methods. The methods explored in this paper provide references for designing input data for deep learning models, helping to enhance the end-to-end potential of deep learning models, and promoting the industrial deployment and practical application of tool condition monitoring systems.