Machine Tool Wear Prediction Technology Based on Multi-Sensor Information Fusion.

The intelligent monitoring of cutting tools used in the manufacturing industry is steadily becoming more convenient. To accurately predict the state of tools and tool breakages, this study proposes a tool wear prediction technique based on multi-sensor information fusion. First, the vibrational, current, and cutting force signals transmitted during the machining process were collected, and the features were extracted. Next, the Kalman filtering algorithm was used for feature fusion, and a predictive model for tool wear was constructed by combining the ResNet and long short-term memory (LSTM) models (called ResNet-LSTM). Experimental data for thin-walled parts obtained under various machining conditions were utilized to monitor the changes in tool conditions. A comparison between the ResNet and LSTM tool wear prediction models indicated that the proposed ResNet-LSTM model significantly improved the prediction accuracy compared to the individual LSTM and ResNet models. Moreover, ResNet-LSTM exhibited adaptive noise reduction capabilities at the front end of the network for signal feature extraction, thereby enhancing the signal feature extraction capability. The ResNet-LSTM model yielded an average prediction error of 0.0085 mm and a tool wear prediction accuracy of 98.25%. These results validate the feasibility of the tool wear prediction method proposed in this study.

Synthesis of the Key Intermediate of SM-406 (Xevinapant) and Its Analogues.

Efficient methods for the synthesis of three dipeptide mimetics with diazabicycloalkanone amino acid scaffolds were developed. Among them, compound 3, which contains a 1,5-diazabicyclo[6,3,0]dodecanone amino acid core structure, was used as the key intermediate of a clinical staged IAP inhibitor SM-406 (Xevinapant). Compared with the reported methods for the synthesis of compound 3 and its derivatives, our method is more efficient and more suitable for large scale preparation.

Synchronized time tagger for single-photon detection in one- and two-dimension quantum experiments.

We report a synchronized time tagger based on a field-programmable-gate-array chip for one- or two-dimensional quantum experiments that require precise single-photon detections. The time tagger has a 9.2 ps single-shot root-mean-square precision and is equipped with a 1 GB dynamic memory for data storage. Because the relationship between the control parameter and acquired data is guaranteed by using hardware synchronization, the experiment can be performed much faster than conventional schemes that are based on software synchronization. With this technique, an improvement of up to 61.3% in efficiency is observed in a typical nitrogen-vacancy center quantum experiment. We further show advanced optical features of the center using the detected high-resolution photon-arrival information and provide detailed electrical benchmarking of the device. This technique could be easily extended to other quantum control systems.

90% yield production of polymer nano-memristor for in-memory computing.

Polymer memristors with light weight and mechanical flexibility are preeminent candidates for low-power edge computing paradigms. However, the structural inhomogeneity of most polymers usually leads to random resistive switching characteristics, which lowers the production yield and reliability of nanoscale devices. In this contribution, we report that by adopting the two-dimensional conjugation strategy, a record high 90% production yield of polymer memristors has been achieved with miniaturization and low power potentials. By constructing coplanar macromolecules with 2D conjugated thiophene derivatives to enhance the π-π stacking and crystallinity of the thin film, homogeneous switching takes place across the entire polymer layer, with fast responses in 32 ns, D2D variation down to 3.16% ~ 8.29%, production yield approaching 90%, and scalability into 100 nm scale with tiny power consumption of ~ 10-15 J/bit. The polymer memristor array is capable of acting as both the arithmetic-logic element and multiply-accumulate accelerator for neuromorphic computing tasks.

[Design and Implementation of a Programmable Wireless Neural Stimulation System].

The paper proposes and realizes a programmable wireless neural stimulation system which can be used as a solution of functional electrical stimulation to treat neural diseases. The system is composed of two parts: controller and neural stimulator. The controller can transmit pulse parameters to the stimulator wirelessly, and the stimulator can generate bidirectional pulses with charge balance. The simulator takes use of ADCs to sample on the bidirectional pulse output, which compared with preset amplitude to the DAC output voltage to realize the voltage calibration. Through the test, the whole system works stably and the output of the biphasic charge balanced circuit is definite. The stimulator output ranges from 0 to 5 V ajustably, and the frequency ranges from 1 Hz to 200 Hz ajustably, while the pulse width ranges from 500 µs to 1500 µs ajustably. The duration of the stimulation can be set from 10 s to 10 min.