Research on compact propulsion system dynamic model based on deep neural network

Author(s):  
Juan Fang ◽  
Qiangang Zheng ◽  
Haibo Zhang

The on-board dynamic model is the basis of numerous advanced control technologies for modern aero-engine, and its accuracy and real-time performance are two crucial indicators. Since the simulation accuracy declines with the deviation from the ground point of the conventional compact propulsion system dynamic model (CPSDM), an improved CPSDM (ICPSDM) based on deep neural network is proposed in this paper. First, the K-means algorithm is utilized to get the sampling point, and the engine simulation data is collected in the cluster centers. Then, the batch normalize deep neural network (BN-DNN) is applied to build the ICPSDM, which can shorten the training time tremendously. The simulation results show that, in the same simulation environment, the accuracy of turbine inlet temperature T 4 , fan surge margin SMc, thrust F, and specific fuel consumption SFC calculated by ICPSDM are 11.04, 3.17, 1.89, and 1.98 times of CPSDM, respectively, at off-design point, and the real-time performance of ICPSDM is more than 30 times faster than the component-level model.

Author(s):  
Qiangang Zheng ◽  
Yong Wang ◽  
Chongwen Jin ◽  
Haibo Zhang

The modern advanced aero-engine control methods are onboard dynamic model–based algorithms. In this article, a novel aero-engine dynamic modeling method based on improved compact propulsion system dynamic model is proposed. The aero-engine model is divided into inlet, core engine, surge margin and nozzle models for establishing sub-model in the compact propulsion system dynamic model. The model of core engine is state variable model. The models of inlet, surge margin and nozzle are nonlinear models which are similar to the component level model. A new scheduling scheme for basepoint control vector, basepoint state vector and basepoint output vector which considers the change of engine total inlet temperature is proposed to improve engine model accuracy especially the steady. The online feedback correction of measurable parameters is adopted to improve the steady and dynamic accuracy of model. The modeling errors of improved compact propulsion system dynamic model remain unchanged when engine total inlet temperature of different conditions are the same or changes small. The model accuracy of compact propulsion system dynamic model, especially the measurable parameters, is improved by online feedback correction. Moreover, the real-time performance of compact propulsion system dynamic model and improved compact propulsion system dynamic model are much better than component level model.


2021 ◽  
Vol 336 ◽  
pp. 03002
Author(s):  
Yuanyuan Zheng ◽  
Jun Ge

In order to solve the problem that the deep neural network model is large in scale, the calculation time is too long, and the real-time performance is severely limited when combined with embedded devices, so studied the intelligent follower robot system based on YOLO-LITE algorithm combined with Raspberry Pi 3B+. The system mainly includes camera processing, target detection and other modules. Obtained the internal and external parameters of the camera through calibration, and according to these parameters to correct the binocular camera. Recognized and located the target in each frame of image, calculated the distance from the camera to the target and the center location error, and driven the car to move. The experimental results show that the following car has excellent real-time performance, the average detection frame rate can reach 20Fps, and the average detection accuracy can reach more than 80%.


Healthcare ◽  
2020 ◽  
Vol 8 (3) ◽  
pp. 234 ◽  
Author(s):  
Hyun Yoo ◽  
Soyoung Han ◽  
Kyungyong Chung

Recently, a massive amount of big data of bioinformation is collected by sensor-based IoT devices. The collected data are also classified into different types of health big data in various techniques. A personalized analysis technique is a basis for judging the risk factors of personal cardiovascular disorders in real-time. The objective of this paper is to provide the model for the personalized heart condition classification in combination with the fast and effective preprocessing technique and deep neural network in order to process the real-time accumulated biosensor input data. The model can be useful to learn input data and develop an approximation function, and it can help users recognize risk situations. For the analysis of the pulse frequency, a fast Fourier transform is applied in preprocessing work. With the use of the frequency-by-frequency ratio data of the extracted power spectrum, data reduction is performed. To analyze the meanings of preprocessed data, a neural network algorithm is applied. In particular, a deep neural network is used to analyze and evaluate linear data. A deep neural network can make multiple layers and can establish an operation model of nodes with the use of gradient descent. The completed model was trained by classifying the ECG signals collected in advance into normal, control, and noise groups. Thereafter, the ECG signal input in real time through the trained deep neural network system was classified into normal, control, and noise. To evaluate the performance of the proposed model, this study utilized a ratio of data operation cost reduction and F-measure. As a result, with the use of fast Fourier transform and cumulative frequency percentage, the size of ECG reduced to 1:32. According to the analysis on the F-measure of the deep neural network, the model had 83.83% accuracy. Given the results, the modified deep neural network technique can reduce the size of big data in terms of computing work, and it is an effective system to reduce operation time.


2021 ◽  
Vol 301 ◽  
pp. 126901
Author(s):  
Tsai-Chi Kuo ◽  
Ni-Ying Hsu ◽  
Reza Wattimena ◽  
I-Hsuan Hong ◽  
Chin-Jung Chao ◽  
...  

2021 ◽  
Vol 11 (15) ◽  
pp. 7148
Author(s):  
Bedada Endale ◽  
Abera Tullu ◽  
Hayoung Shi ◽  
Beom-Soo Kang

Unmanned aerial vehicles (UAVs) are being widely utilized for various missions: in both civilian and military sectors. Many of these missions demand UAVs to acquire artificial intelligence about the environments they are navigating in. This perception can be realized by training a computing machine to classify objects in the environment. One of the well known machine training approaches is supervised deep learning, which enables a machine to classify objects. However, supervised deep learning comes with huge sacrifice in terms of time and computational resources. Collecting big input data, pre-training processes, such as labeling training data, and the need for a high performance computer for training are some of the challenges that supervised deep learning poses. To address these setbacks, this study proposes mission specific input data augmentation techniques and the design of light-weight deep neural network architecture that is capable of real-time object classification. Semi-direct visual odometry (SVO) data of augmented images are used to train the network for object classification. Ten classes of 10,000 different images in each class were used as input data where 80% were for training the network and the remaining 20% were used for network validation. For the optimization of the designed deep neural network, a sequential gradient descent algorithm was implemented. This algorithm has the advantage of handling redundancy in the data more efficiently than other algorithms.


Sign in / Sign up

Export Citation Format

Share Document