In order to improve the operation efficiency of fire image recognition neural network, the FPGA hardware acceleration of fire image recognition neural network is studied and implemented. Firstly, with the help of fire image database and TensonFlow machine learning platform, a fire image recognition neural network is trained with VGG19 as the neural network model. Then the FPGA hardware design of convolution layer, pooling layer, full connection layer and activation function is carried out for the trained neural network through Vivado. Secondly, the designed VGG19 fire image recognition convolution neural network accelerator is debugged on the ZYNQ7020 development board. Finally, the acceleration performance of fire identification convolutional neural network accelerator system is tested in three aspects: acceleration efficiency, resource utilization and power consumption. The experimental results show that the accelerator can reduce the clock cycle required by each convolution layer of fire image recognition neural network from one million to ten thousand, the resource utilization meets the chip requirements, and the chip power consumption is reduced to 2.067w. While improving the operation efficiency of neural network, it realizes low power consumption.
Fiber Bragg Grating (FBG) sensor has attracted considerable attention for intelligent health monitoring system, owing to advantages including resistance to electromagnetic interference, durability under extreme temperature and pressures, light weight, high transmission rate, small size and flexibility. However, the intelligent health monitoring system based on FBG sensor may carry the risk of transmission or sensing optical fiber fracture in the engineering application, the safety and reliability of intelligent health monitoring system will be reduced. For improving the security and reliability, the self-healing implementation of the intelligent health monitoring 25system based on confidence probability cooperation technology is investigated. The self-healing model of multi-agent FBG intelligent health monitoring system based on confidence probability is constructed firstly. Secondly, the optical fiber sensing function agent and system cooperative decision making agent with self-learning ability is defined. The progress of cooperative means between agents based on confidence probability is studied. Thirdly, for the non-participants of the fiber sensing function because of the low confidence probability, dynamic model modification method is studied, and the evaluation results of optical sensing function are modified dynamically. Correspondingly, the system cooperative decision making model is modified on account of its confidence probability. Thus the self-healing ability of the multi-agent FBG intelligent health monitoring system is implemented. Finally, taking the plane wing box test panel as subject, the multi-agent FBG intelligent health monitoring system based on confidence probability is verified and analyzed by experiment and simulation. The results indicate that the multi-agent technology based on confidence probability cooperation not only improves the self-learning ability, but also improves the monitoring accuracy of the FBG intelligent health monitoring system.
In multi-agent systems, agents coordinate their behavior and work together to achieve a shared goal through collaboration. However, in multi-agent systems, selecting qualified participants to form effective collaboration communities is challenging. In this paper, we propose a minimum circle covering algorithm, as a solution for on-demand participant selection for collaboration in multi-agent systems. Furthermore, a twenty-one point FBG sensors are divided into four sensing function agent in Structural Health Monitoring (SHM) system is experimented in an aircraft wing box. Correspondingly, there are four intelligent evaluation agents and one system collaborative agent in the multi-agent intelligent health monitoring system. For the damage loading position prediction on the aircraft wing box, the collaborative participation selection strategy based on the minimum circle coverage is verified experimentally. The research result indicates that the minimum circle covering algorithm can be used to select the participation in multi-agent intelligent health monitoring system, of all the participations in the collaboration, it enables them to identify and select a qualified participants.
Due to some limitations of traditional methods about oil temperature and level monitoring in transformer conservators, an intelligent monitoring system based on fiber Bragg grating sensors to monitor the change of oil temperature and level in transformer is proposed in this paper. This system is composed of five parts: fiber Bragg grating sensors, sensor data processing and storage, intelligent evaluation of the characteristic information of the transformer, cooperation of the monitoring and evaluation results. The oil level sensor is composed of a fiber Bragg grating sensor and a C-type spring tube, and the oil level can be monitored by the relationship between pressure and height of the liquid pressure. This method can improve the stable operation reliability of the transformer without electricity detection. The experimental results show that the central wavelength of the fiber Bragg grating sensor changes linearly with the oil temperature and level in the transformer. The intelligent monitoring system can be achieved in high voltage, electromagnetic interference and other complex environments without electricity detection, which can greatly improve the safety and reliability of the transformer.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.