RESUMO
Accurately predicting the state of health (SOH) of lithium-ion batteries is fundamental in estimating their remaining lifespan. Various parameters such as voltage, current, and temperature significantly influence the battery's SOH. However, existing data-driven methods necessitate substantial data from the target domain for training, which hampers the assessment of lithium-ion battery health at the initial stage. To address these challenges, this paper introduces the multi-head attention-time convolution network (MHAT-TCN), amalgamating multi-head attention learning with random block dropout techniques. Additionally, it employs grey relational analysis (GRA) to select health indicators (HIs) highly correlated with battery capacity, thereby enhancing the accuracy of the model training. Employing leave-one-out crossvalidation (LOOCV), the MHAT-TCN network is pre-trained using data from batteries of the same model to facilitate comprehensive prediction of the target battery throughout its operational period. Results demonstrate that the MHAT-TCN network trained on HIs outperforms other models, enabling precise predictions across the entire operational period.
RESUMO
Five-axis working machines are applied in the high-precision machining of complex convex surfaces. Therefore, this study integrated a horizontal parallel three-axis motion platform and a three-axis machine tools to create a reconfigurable precision five-axis machine tools (RPFMT). A DELTA OPEN computer numerical control controller was used as the control system architecture. A human-machine interface and programmable controller were incorporated into the developed tool to achieve automatic online measurement. A suitable cutting tool was selected to calculate the five-axis NC machining code for a complex convex surface. The NC codes were input into the LabVIEW software for five-axis postprocessing conversion. A concave workpiece was cut through rough and finishing machining to verify the accuracy of the produced RPFMT.
RESUMO
OBJECTIVE: To evaluate the effect of placement of short iliac screw using Galveston technique in lumbosacral fusion. METHODS: From October 2003 to August 2007, 18 consecutive patients (mean age 46 years ranging from 25 to 62 years) received placement of short iliac screw in lumbosacral fusion. The patients were followed up for a mean of 18 months (12-23 months), and the effect of lumbosacral fusion was evaluated according to standing anterior-posterior and lateral plain films taken before and after the operation and at the follow-up and also on the basis of symptom relief. RESULTS: The mean time of surgery was 210 min (180-290 min). No complications occurred during and after the operation. According to the evaluation criteria of surgical treatment of low back pain formulated by the spine group of Chinese Orthopedic Association, excellent clinical outcome was achieved in 12 cases, good outcome in 3 cases, and tolerable outcome in 2 cases, with the excellent and good outcome rate of 83%. CONCLUSION: The Galveston technique for short iliac screw placement can obtain satisfactory outcome in the lumbosacral fusion.