No abstract

Quality control in electronic system manufacturing is achieved mainly through system testing. Device miniaturization and multilayer Printed Circuit Boards have increased the electronic circuit test complexity considerably and processes based on manual inspections have become outdated and inefficient. The concept of Industry 4.0 has enabled the manufacturing of customized products based on customers’ demands, which demands a high degree of flexibility in production processes, with low cost and without placing numerous test points. In this paper, we propose two automated test solutions based on machine learning and thermographic analysis. We propose deploying autoencoders and random forest in two different manners to detect firmware or hardware anomalies based on the circuit board’s temperature signature. We validate our proposal using two firmware versions running independently on the test board. We obtained an anomaly detection rate above 98%. In the random forest approach, we require all data classes for training, whereas the autoencoder only requires the reference class, which is expected in real scenarios.

No abstract

The excessive exposure to certain kinds of acoustic noise can lead to health problems. To avoid this situation, the use of noise attenuation devices is a standard solution. Among those devices, the active noise control (ANC) systems have gained prominence over the years, mainly due to the technological development and costs reduction of electronic components. Despite good performance of ANC concerning low-frequency noise attenuation, the convergence speed for this kind of system is still an important issue when it deals with real-time applications in dynamic environments. This article presents an alternative solution to accelerate the active attenuation system response. This solution is based on the use of sets of coefficients, which are employed during the adaptive filter initialization and are obtained via a training process with particle swarm optimization (PSO). Two objective functions were tested: one based on the response time itself and the other one based on the magnitude reduction of the residual noise. The coefficients obtained through this process provided response time reductions up to 98.3% concerning adaptive filters initialized with null coefficients. The article is an extended version of the conference paper Accelerating the Convergence of Adaptive Filters for Active Noise Control Using Particle Swarm Optimization, published in LA-CCI 2017.