A Collaborative Platform for Advancing Automatic Interpretation in ECG Signals.

Numerous papers report the efficiency of the automatic interpretation capabilities of commercial algorithms. Unfortunately, these algorithms are proprietary, and academia has no means of directly contributing to these results. In fact, nothing at the same stage of development exists in academia. Despite the extensive research in ECG signal processing, from signal conditioning to expert systems, a cohesive single application for clinical use is not ready yet. This is due to a serious lack of coordination in the academic efforts, which involve not only algorithms for signal processing, but also the signal acquisition equipment itself. For instance, the different sampling rates and the different noise levels frequently found in the available signal databases can cause severe incompatibility problems when the integration of different algorithms is desired. Therefore, this work aims to solve this incompatibility problem by providing the academic community with a diagnostic-grade electrocardiograph. The intention is to create a new standardized ECG signals database in order to address the automatic interpretation problem and create an electrocardiography system that can fully assist clinical practitioners, as the proprietary systems do. Achieving this objective is expected through an open and coordinated collaboration platform for which a webpage has already been created.

Nonlinear modeling of industrial boiler NOx emissions.

Pollutant emissions into the atmosphere are recognized as a significant problem in fossil fuel combustion. The pollution emission measurement in industrial boilers is difficult and expensive but fundamental for monitoring and controlling. Frequently continuous emissions monitoring (CEM) system is out of service or useless due to obsolescence, high maintenance cost, and so on or simply is not installed. When a system for measuring pollutant emissions is not available, an alternative method must be employed to get the pollutant emission value. According to the black-box model approach, this article describes the nonlinear modeling of NOx emissions from a utility boiler. Bayesian-Gaussian (BG), multilayer perceptron (MLP), and Volterra polynomial basis functions (VPBF) neural networks are developed for model benchmarking. Experimental data from a utility boiler was acquired in order to model definition and evaluation. The models process three boiler variables oxygen excess, fuel mass flow and flue gas recirculation gates for NOx emission estimation. Models with BG show better performance than models with MLP and VPBF for NOx prediction.Implications: The technology to control NOx emissions generated by combustion operates under strict regulations. In order to reduce NOx emissions, theoretical models of NOx generation have been studied extensively, including nitrogen chemistry and the dynamic flow of gas particles which is very complex. The new technology trends would require the continuous measurement of high precision NOx emissions to achieve further reductions in NOx emissions. Currently, NOx emissions are measured by a Continuous Emission Monitoring system, which turns out to be extremely expensive and difficult to maintain, so alternative low-cost solutions are desirable. Our contribution shows how algorithms based on different artificial intelligence techniques are viable and quality alternatives for the measurement of continuous NOx emissions. The NOx emissions models based on IA algorithms are viable alternatives that have versatility and self-tuning capacity due to the fact that they are based on boiler operation parameters which have valuable information few explored nowadays.

Design and Validation of an Articulated Sensor Carrier to Improve the Automatic Pipeline Inspection.

Pipeline inspection gauges (PIGs) carry out automatic pipeline inspection with nondestructive testing (NDT) technologies like ultrasound, magnetic flux leakage, and eddy current. The ultrasonic straight beam allows technicians to determine the wall thickness of the pipeline through the time of flight diffraction (TOFD), providing the pipeline reconstruction and allowing the detection of several defects like dents or corrosion. If the pipeline is of a long distance, then the inspection process is automatic, and the fluid pressure pushes the PIG through the pipeline system. In this case, the PIG velocity and its axial alignment with the pipeline cannot be controlled. The PIG geometry, the pipeline deformations, and the girth welds cause a continuous chattering when the PIG is running, removing the transducers perpendicularity with the inspection points, which means that some echoes cannot be received. To reduce this problem, we propose a novel method to design a sensor carrier that takes into account the angularity and distance effects to acquire the straight beam echoes. The main advantage of our sensor carrier is that it can be used in concave and convex pipeline sections through geometric adjustments, which ensure that it is in contact with the inner pipe wall. Our improvement of the method is the characterization of the misalignment between the internal wall of the pipeline and the transducer. Later, we analyzed the conditions of the automatic pipeline inspection, the existing recommendations in state-of-the-art technology, and the different mechanical scenarios that may occur. For the mechanical design, we developed all the equations and rules. At the signal processing level, we set a fixed gain in the filtering step to obtain the echoes in a defined distance range without saturating the acquisition channels. For the validation, we compared through the mean squared error (MSE) our sensor carrier in a straight pipe section and a pipe elbow of steel versus other sensor carrier configurations. Finally, we present the design parameters for the development of the sensor carrier for different pipeline diameters.

Improvement of Ultrasonic Pulse Generator for Automatic Pipeline Inspection.

This paper presents the improvement of an ultrasonic pulse generator for a pipeline inspection gauge (PIG), which uses 64 transducers for inspecting distances up to 100 km with an axial resolution fixed at 3 mm and variable speeds between 0 and 2 m/s. An ultrasonic pulse generator is composed of a high-voltage (HV) MOSFETs, driver logic and an HV power supply. We used a DC-HV DC converter device as the HV power supply because it reduces the size of the ultrasound system considerably. However, pipeline geometry and inspection effects such as hammer and shock cause a variable pulse repetition frequency (PRF), producing voltage drops, poor quality of the HV pulse generated, failures in the dimensioning of defects and damage to devices by over-voltage. Our improvement is to implement a control scheme to maintain the high quality of the HV regardless of the variable PRF. To achieve this, we characterized three transfer functions of the DC-HV DC converter, varying the connected load to 10%, 45% and 80%. For the characterization, we used the least squares technique, considering an autoregressive exogenous (ARX) model. Later, we compared three control schemes: (1) proportional-integral-derivative (PID) tuned by simultaneous optimization of several responses (SOSR), (2) PID tuned by a neural network (NN) and (3) PI tuned by the analytical design method (ADM). The metrics used to compare the control schemes were the recovery time, the maximum over-voltage and the excess energy when the shock and hammer effects happen to occur. Finally, to verify the improvement of the HV pulser, we compared the ultrasonic pulses generated for various frequencies and amplitudes using the pulse generator with and without the control scheme.