Accurate granularity estimation of ore images is vital in automatic geometric parameter detecting and composition analysis of ore dressing progress. Machine learning based methods have been widely used in multi-scenario ore granularity estimation. However, the adhesion of coal particles in the images usually results in lower segmentation accuracy. Because much powdery coal fills between blocky ones, making edge contrast between them is not distinct. Currently, the coal granularity estimation is still carried out empirical in nature. We propose a novel method for coal granularity estimation based on a deep neural network called Res-SSD to deal with the problem. Then, to further improve the detection performance, we propose an image enhancement layer for Res-SSD. Since the dust generated during production and transportation will seriously damage the image quality, we first propose an image denoising method based on dust modelling. By investigating imaging characteristics of coal, we second propose the optical balance transformation(OBT), by which the distinguishability of coal in dark zones can be increased. Meanwhile, OBT can also suppress overexposed spots in images. Experimental results show that the proposed method is better than classic and state-of-the-art methods in terms of accuracy while achieving a comparable speed performance.

For a large-scale palmprint identification system, it is necessary to speed up the identification process to reduce the response time and also to have a high rate of identification accuracy. In this paper, we propose a novel hashing-based technique called orientation field code hashing for fast palmprint identification. By investigating hashing-based algorithms, we first propose a double-orientation encoding method to eliminate the instability of orientation codes and make the orientation codes more reasonable. Secondly, we propose a window-based feature measurement for rapid searching of the target. We explore the influence of parameters related to hashing-based palmprint identification. We have carried out a number of experiments on the Hong Kong PolyU large-scale database and the CASIA palmprint database plus a synthetic database. The results show that on the Hong Kong PolyU large-scale database, the proposed method is about 1.5 times faster than the state-of-the-art ones, while achieves the comparable identification accuracy. On the CASIA database plus the synthetic database, the proposed method also achieves a better performance on identification speed.

Traditional methods are unable to effectively assess the health status of engine bleed air systems. To address the limitation, this paper proposes a methodology for constructing health indicators using multi-level feature extraction. First, this approach involves data-level feature extraction from Quick Access Recorder (QAR) data and employs a method of significance compensation to process the QAR data. Second, through unsupervised learning, the ResNet Deep Autoencoder (RDAE) is utilized to do the feature-level feature extraction from the processed data. This can solve the problem of lacking annotated data and obtain the health indicators of the engine bleed air system. Third, the method was experimented on one year of QAR data from a specific airline company. The results demonstrate that the RDAE approach achieves the best performance in constructing health indicators for the system. It achieves a miss rate of 0.0523 for the duct pressure of 5th stage bleed, reducing the miss rate by 0.2810 compared to Kernel Principal Component Analysis (KPCA). It also achieves a miss rate of 0 for the pre-cooler outlet temperature, reducing the miss rate by 0.0035 compared to the Deep Autoencoder (DAE). The results indicate that the proposed method provides a more effective assessment of the health status of the engine bleed air system.

The geometric model and performance criteria of a stereo camera sensor are proposed for the purpose of sensor performance optimization. In particular, the details of the geometric model is presented to characterize the configuration parameters of the stereo camera sensor. Six effective criteria are then synthesized to measure the sensor performance based on the geometric model, including depth resolution, permissible degree of orientation, visual resolution, field of view, focus, and occlusion. A sample optimization task is presented to show the effectiveness of the model and the performance criteria with the simulation validation using the gradient-ascent based algorithm and the improved genetic algorithm respectively.

As the synthesis, modularization, and integration of avionics systems increase, the interconnections between systems and equipment within subsystems become increasingly complex, posing risks to the safety and reliability of the integrated avionics system. To address the risk of fault propagation due to functional cascade failures in integrated avionics systems, this paper proposes a discrete dynamic fault propagation analysis method, which was applied to an all-electric braking system to assess its feasibility. First, the architectural features of the Distributed Integrated Modular Avionics system are summarized. Subsequently, the constructed system layer model is described, establishing the function–resource hierarchical architecture. Subsequently, the behavior of cascading failure propagation in discrete dynamic systems is analyzed by integrating the cascading failure analysis method from SAE ARP 4761A and considering the coupling characteristics between system properties and functions comprehensively. This approach facilitates the development of a cascading failure propagation model for DIMA based on discrete dynamic systems. Finally, by using the all-electric braking system under DIMA architecture as a case study, key Core Processing Modules and failure-prone functions are identified. The findings reveal that within this system, CPM2 and CPM6 are particularly susceptible to failure propagation, and the automatic brake function is notably vulnerable. Data show that the system’s failure rate escalates markedly after $2\times {10}^4$ h of operation. Performing maintenance before reaching this threshold can further mitigate risks. This practice aligns with current international aircraft maintenance time regulations. The method proposed in this paper can be applied early in the allocation of DIMA resources to enhance security and support DIMA design.

The electric propulsion system serves as the power source for multi-rotor drones, helping them complete various maneuvering actions. The reliability of this system directly affects whether the drone can successfully complete its mission. The multi-rotor drone propulsion system is a k-out-of-n system with functional dependence (FDEP). With the insufficient basis for selecting k-values, the problem of incalculable reliability caused by computational space explosion due to voting gates, and the uncertain impact of functional dependence on system reliability, we propose a reliability evaluation method based on controllability theory and BN (Bayesian network) reconstruction. The drone is dynamically modeled, and a control model is built, and k-values are selected through different failure combination controllability evaluations. We model the system with BN, use functional dependent components as BN node inputs, and reconstruct BN via an adder model to solve the problem of exponential growth in the conditional probability table. This paper analyzes system reliability, safety, and the impact of FDEP on the system, and conducts component importance analysis. The result provides important reference for the reliability, safety assessment, and dynamic maintenance processes of multi-rotor drone.