Theoretical analysis in this paper indicates that the accuracy of a silicon piezoresistive pressure sensor is mainly affected by thermal drift, and varies nonlinearly with the temperature. Here, a smart temperature compensation system to reduce its effect on accuracy is proposed. Firstly, an effective conditioning circuit for signal processing and data acquisition is designed. The hardware to implement the system is fabricated. Then, a program is developed on LabVIEW which incorporates an extreme learning machine (ELM) as the calibration algorithm for the pressure drift. The implementation of the algorithm was ported to a micro-control unit (MCU) after calibration in the computer. Practical pressure measurement experiments are carried out to verify the system’s performance. The temperature compensation is solved in the interval from −40 to 85 °C. The compensated sensor is aimed at providing pressure measurement in oil-gas pipelines. Compared with other algorithms, ELM acquires higher accuracy and is more suitable for batch compensation because of its higher generalization and faster learning speed. The accuracy, linearity, zero temperature coefficient and sensitivity temperature coefficient of the tested sensor are 2.57% FS, 2.49% FS, 8.1 × 10−5/°C and 29.5 × 10−5/°C before compensation, and are improved to 0.13%FS, 0.15%FS, 1.17 × 10−5/°C and 2.1 × 10−5/°C respectively, after compensation. The experimental results demonstrate that the proposed system is valid for the temperature compensation and high accuracy requirement of the sensor.
This paper presents a high performance triaxial cutting force sensor with excellent accuracy, favorable natural frequency and acceptable cross-interference for high speed turning process. Octagonal ring is selected as sensitive element of the designed sensor, which is drawn inspiration from ring theory. A novel structure of two mutual-perpendicular octagonal rings is proposed and three Wheatstone full bridge circuits are specially organized in order to obtain triaxial cutting force components and restrain cross-interference. Firstly, the newly developed sensor is tested in static calibration; test results indicate that the sensor possesses outstanding accuracy in the range of 0.38%–0.83%. Secondly, impacting modal tests are conducted to identify the natural frequencies of the sensor in triaxial directions (i.e., 1147 Hz, 1122 Hz and 2035 Hz), which implies that the devised sensor can be used for cutting force measurement in a high speed lathe when the spindle speed does not exceed 17,205 rev/min in continuous cutting condition. Finally, an application of the sensor in turning process is operated to show its performance for real-time cutting force measurement; the measured cutting forces demonstrate a good accordance with the variation of cutting parameters. Thus, the developed sensor possesses perfect properties and it gains great potential for real-time cutting force measurement in turning.
Classification is an important task in data mining field. As the time of big data is coming, the traditional methods of classification cannot satisfy the requirements of real-time processing and storage for big data. This study firstly applies a machine learning technique called extreme learning machine (ELM) to classify for big data. Performances of ELM for big data are evaluated by using big data. The experimental results show that classification method based on ELM outperforms other methods based on BP neural networks and support vector machine (SVM). Secondly, the possibility of paralleling ELM based on MapReduce is analyzed and a paralleling ELM is designed.