Search

To realize the remote detection of the leak of a buried natural gas pipeline by an airborne laser,a helicopter-borne laser autonomous positioning method for the buried natural gas pipeline was presented.Based on the position and attitude of the carrier aircraft obtained by an airborne GPS and an inertial attitude measurement system,the laser autonomous positioning point of the pipeline was obtained based on the known location information and by the space vector method.Furthermore,the azimuth and pitch angles of the airborne laser were solved through the coordinate transformation.Finally,driven by the mechanism,the laser-guiding positioning of the pipeline was fulfilled.With application of the laser clamping alignment mechanism independently developed by ourselves,the ground point-fixed experiment proves that the proposed algorithm can offer the accuracy of the ground positioning by 6.9 m,and it will be more accurate when the precision of the carrier aircraft attitude and the position sensor is further improved.Experiments demonstrate that the algorithm is suitable for the remote detection of the buried natural gas pipeline by airborne lasers.

In the real world, the inputs of many complicated systems are time-varying functions or processes. In order to predict the outputs of these systems with high speed and accuracy, this paper proposes a time series prediction model based on the wavelet process neural network, and develops the corresponding learning algorithm based on the expansion of the orthogonal basis functions. The effectiveness of the proposed time series prediction model and its learning algorithm is proved by the Mackey–Glass time series prediction, and the comparative prediction results indicate that the proposed time series prediction model based on the wavelet process neural network seems to perform well and appears suitable for using as a good tool to predict the highly complex nonlinear time series.

Airbone optical detection system for monitoring the methane gas leak is developed. The measuring principle, concentration equation, measurement device, airborne clamping apparatus and tracking pointing control system is studied. Firstly, the absorbing and measuring mechanism is designed based on the principle of near-infrared tunable diode laser absorption spectrum, using a second derivative wavelength modulation technique, the gas concentration is deduced. Then, the detailed description of measurement device, airborne clamping apparatus and control system is given. The device is mounted on low-moving platform, simulation of the gas line leak experiment shows that this method has high accuracy to tracking and pointing the detected gas line, the detection sensitivity of the system for the buried pipeline leakage is about 50 ppm*m (in the case of methane) and the tracking and pointing accuracy of the detection laser for the pipeline is 1°. This system can be applied into the airborne remote sensing detection for the long-distance natural gas leak.

Vertical atmospheric steel storage tanks are important equipments in oilfield. During daily operation, corrosion defects such as perforation and fracture are often not detected in time due to the cost and difficulty in inspecting storage tanks. This compromises the safety in petrochemical plants as measures are usually not taken. The key lies in obtaining the principle of corrosion, and predicating and assessing the corrosion condition of the storage tank. However, the principle of the corrosion is very complex and the corrosion rate is affected by numerous factors. It is therefore difficult to obtain the corrosion rate accurately. This paper assessed the precision of an improved non-equidistance GM (1, 1) model, which has been set up to predict the corrosion rate of oil storage tanks. The results show that the precision of the prediction model is high and the corrosion rate evaluated via this model reconciles with the corrosion characteristic of the storage tank and can offer consults to maintenances of the storage tank.

Time series prediction methods based on conventional neural networks do not take into account the functional relations between the discrete observed values in the time series. This usually causes a low prediction accuracy. To solve this problem, a functional time series prediction model based on a process neural network is proposed in this paper. A Levenberg—Marquardt learning algorithm based on the expansion of the orthonormal basis functions is developed to train the proposed functional time series prediction model. The efficiency of the proposed functional time series prediction model and the corresponding learning algorithm is verified by the prediction of the monthly mean sunspot numbers. The comparative test results indicate that process neural network is a promising tool for functional time series prediction.