Search

To address the lack of annotated data and insufficient performance in intent detection and slot filling in the domain of industrial equipment failure, a joint model based on BERT was proposed. BERT was utilized for text sequence encoding, while a bidirectional long short-term memory (Bi-LSTM) network was employed to capture the semantic relationships within the context. Max pooling and dense layers were used to extract key information, and a conditional random field (CRF) was incorporated to enhance the model's generalization capability. A question-and-answer corpus specifically tailored to the industrial domain of equipment failure was constructed, and a deployment framework for this domain was proposed. Experimental evaluations conducted on public datasets such as ATIS demonstrated that the proposed model outperforms baseline models by improving sentence-level accuracy, F1 score, and intent detection accuracy by 4. 4%, 2. 1%, and 0. 5% respectively. This research effectively enhances the performance of question-and-answer systems and provides a dataset and deployment framework for the field of industrial equipment failure, which lacks sufficient real-world data. [ABSTRACT FROM AUTHOR]

A new method for the rapid detection of cadmium (Cd), lead (Pb) and arsenic (As) elements in pig premixed feeds by energy dispersive X-ray fluorescence (EDXRF) spectroscopy was investigated. Samples were added to starch and water, pasted in a water bath at 94 ℃ and scanned by EDXRF spectroscopy, with copper spectral identification for characterisation and standard addition method for quantification. The results showed that the EDXRF spectral peaks of each element were interference-free and the method was well linear (R2 >0.998) in the concentration range examined; the limits of detection were 1.06 mg/kg, 1.68 mg/kg and 1.97 mg/kg for Cd, Pb and As, respectively. The overall recoveries were 93.72%-105.10% and the overall relative standard deviations were 2.30%-9.40%. The method is simple, rapid, accurate and reliable, and can meet the needs of rapid determination of Cd, Pb and As in pig premixed feeds. [ABSTRACT FROM AUTHOR]

A quartz crystal microbalance (QCM) systematic evolution of ligands by the exponential enrichment (SELEX) technique was developed to screen out aptamers with high affinity for arsenic (III). Α random single strand DNA library was designed and fixed on the mercaptoethylamine-modified crystal plate with arsenic (III) as the target, and the free aptamer was captured in the solution, and the QCMSELEX screening method was constructed. After 6 rounds of screening, the secondary library was sequenced with high throughput method, and the 6S1 dissociation coefficient Kd value was 0.36 µmol/L based on QCM resonance frequency. Using 6S1 as a probe, the QCM biosensor was constructed for the detection of arsenic (III). The sensor has a good linear relationship in the range of 0.01 µmol/L~0.2 µmol/L, and the detection limit of arsenic (III) is 5.2 nmol/L(30), indicatinggood selectivity. [ABSTRACT FROM AUTHOR]