Sensor Errors Research Articles

Spectrum characteristics and temperature measurement error of FBG sensor based on rotor temperature monitoring system

For real-time temperature monitoring of a generator or electric motor rotor, the effects of rotation on the reflection spectrum of a polyimide-coated Fibre Bragg Grating (FBG) were analyzed using formulas. The measurement error resulting from the low-speed operation was evaluated, combined with the finite element method. Secondly, the key design of the FBG sensors and the mating part of the fiber optic rotary joint (FORJ) were investigated. The temperature of a rotating shaft was monitored to test the reliability of the measurement system. With a resolution of 0.1℃, the system was able to achieve an error of 0.5℃ over a range of 30-180℃. Finally, the critical conditions for the application of polyimide-coated and metal-coated FBGs were discussed. The results show that the variation of the center wavelength is more sensitive to the radius of the small-sized rotor, and the rotation speed of the large-sized rotor. It is at higher speeds that the thickness of the coating has a more pronounced effect on error, demonstrating that the accuracy of FBGs used in high-speed rotors could be rapidly improved by reducing the thickness of the metal coating. The reported results provide a basis for the thermal monitoring performance of FBG sensors during rotation.

Impact of Motion-Dependent Errors on the Accuracy of an Unaided Strapdown Inertial Navigation System

The selection of an appropriate measurement system for an inertial navigation system requires an analysis of the impact of sensor errors on the position and orientation determination accuracy to ensure that the selected solution is cost-effective and complies with the requirements. In the current literature, this problem is solved based on the navigation duration only by considering the time-dependent errors due to sensor bias and random walk parameters or by conducting numerous simulations. In the former case, oversimplifying the analysis will not allow accurate values to be determined, while the latter method does not provide direct insight into the emerging dependencies. In contrast, this article introduces an analytic approach with a detailed model. This article presents general formulas, also written in detail for the measurement system model adopted and various manoeuvres. Although general equations are complicated, the use of piecewise constant motion variables allow us to discern fragments of equations corresponding to individual error sources. The results confirm the effect the carouseling has on the reduction of navigation errors. The general formulas presented extend the potential to analyse the influence of the entire host vehicle motion, while the detailed formulas make dependencies between motion and navigational errors evident.

A Sustainable Forage-Grass-Power Fuel Cell Solution for Edge-Computing Wireless Sensing Processing in Agriculture 4.0 Applications

Intelligent sensing systems based on the edge-computing paradigm are essential for the implementation of Internet of Things (IoT) and Agriculture 4.0 applications. The development of edge-computing wireless sensing systems is required to improve the sensor’s accuracy in soil and data interpretation. Therefore, measuring and processing data at the edge, rather than sending it back to a data center or the cloud, is still an important issue in wireless sensor networks (WSNs). The challenge under this paradigm is to achieve a sustainable operation of the wireless sensing system powered with alternative renewable energy sources, such as plant microbial fuel cells (PMFCs). Consequently, the motivation of this study is to develop a sustainable forage-grass-power fuel cell solution to power an IoT Long-Range (LoRa) network for soil monitoring. The stenotaphrum secundatum grass plant is used as a microbial fuel cell proof of concept, implemented in a 0.015 m3-chamber with carbon plates as electrodes. The BQ25570 integrated circuit is employed to harvest the energy in a 4 F supercapacitor, which achieves a maximum generation capacity of 1.8 mW. The low-cost pH SEN0169 and the SHT10 temperature and humidity sensors are deployed to analyze the soil parameters. Following the edge-computing paradigm, the inverse problem methodology fused with a system identification solution is conducted, correcting the sensor errors due to non-linear hysteresis responses. An energy power management strategy is also programmed in the MSP430FR5994 microcontroller unit, achieving average power consumption of 1.51 mW, ∼19% less than the energy generated by the forage-grass-power fuel cell. Experimental results also demonstrate the energy sustainability capacity achieving a total of 18 consecutive transmissions with the LoRa network without the system’s shutting down.

An Ultrasonic Target Detection System Based on Piezoelectric Micromachined Ultrasonic Transducers

In this paper, an ultrasonic target detection system based on Piezoelectric Micromachined Ultrasonic Transducers (PMUTs) is proposed, which consists of the PMUTs based ultrasonic sensor and the sensor system. Two pieces of 3 × 3 PMUTs arrays with the resonant frequency of 115 kHz are used as transmitter and receiver of the PMUTs-based ultrasonic sensor. Then, the sensor system can calculate the target's position through the signal received by the above receiver. The static and dynamic performance of the proposed prototype system are characterized on black, white, and transparent targets. The experiment results demonstrated that the proposed system can detect targets of different colors, transparencies, and motion states. In the static experiments, the static location errors of the proposed system in the range of 200 mm to 320 mm are 0.51 mm, 0.50 mm and 0.53 mm, whereas the errors of a commercial laser sensor are 2.89 mm, 0.62 mm, and N\A. In the dynamic experiments, the experimental materials are the targets with thicknesses of 1 mm, 1.5 mm, 2 mm and 2.5 mm, respectively. The proposed system can detect the above targets with a maximum detection error of 4.00%. Meanwhile, the minimum resolution of the proposed system is about 0.5 mm. Finally, in the comprehensive experiments, the proposed system successfully guides a robotic manipulator to realize the detecting, grasping, and moving of a transparent target with 1 mm. This ultrasonic target detection system has demonstrated a cost-effective method to detect targets, especially transparent targets, which can be widely used in the detection and transfer of glass substrates in automated production lines.

Multiphysical Field Analysis of a Temperature Sensor for Meteorological Observation

Due to the influence of solar radiation, the observed values of existing meteorological temperature sensors may differ from the free air temperatures up to the order of 1 °C. This article proposed a temperature sensor consisting of a sensor probe, an airflow deflector, and two aluminum plates. The airflow deflector can effectively guide the airflow to the sensor probe and reduce radiation error. The two silver-plated mirror aluminum plates have up to 98% reflectivity. They can effectively block direct solar radiation, reflected radiation, long-wave radiation, and so on. The radiation protection and airflow guiding ability of the sensor are analyzed by the computational fluid dynamics (CFD) method. Then, the CFD approach obtains the radiation errors of the sensor under different environmental conditions. Next, the neural network algorithm fits the simulation data to form a high-accuracy radiation error correction approach. Finally, the 076B artificially ventilated temperature sensor is used as the temperature reference during experiments. The experimental results show that the mean absolute error (MAE) and the root-mean-square error (RMSE) between the radiation errors provided by the experiments and the radiation errors given by the neural network are 0.031 °C and 0.026 °C, respectively. After correction, the maximum, minimum, and average radiation errors of the new sensor are 0.095 °C, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$-0.074\,\,^{\circ }\text{C}$ </tex-math></inline-formula> , and 0.01 °C, respectively. The correlation coefficient between the temperature results of the new sensor after correction and the reference temperature results is 0.999. These results show that this new sensor might reduce the measurement error to within 0.1 °C.

Feasibility of intraoperative continuous glucose monitoring: An observational study in general surgery patients

BackgroundPerioperative hyperglycemia is associated with adverse outcomes in surgical patients, and major societies recommend intraoperative monitoring and treatment targeting glucose <180–200 mg/dL. However, compliance with these recommendations is poor, in part due to fear of unrecognized hypoglycemia. Continuous Glucose Monitors (CGMs) measure interstitial glucose with a subcutaneous electrode and can display the results on a receiver or smartphone. Historically CGMs have not been utilized for surgical patients. We investigated the use of CGM in the perioperative setting compared to current standard practices. MethodThis study evaluated the use of Abbott Freestyle Libre 2.0 and/or Dexcom G6 CGMs in a prospective cohort of 94 participants with diabetes mellitus undergoing surgery of ≥3 h duration. CGMs were placed preoperatively and compared to point of care (POC) BG checks obtained by capillary samples analyzed with a NOVA glucometer. Frequency of intraoperative blood glucose measurement was at the discretion of the anesthesia care team, with a recommendation of once per hour targeting BG of 140–180 mg/dL. Of those consented, 18 were excluded due to lost sensor data, surgery cancellation, or rescheduling to a satellite campus resulting in 76 enrolled subjects. There were zero occurrences of failure with sensor application. Paired POC BG and contemporaneous CGM readings were compared with Pearson product-moment correlation coefficients, and Bland-Altman plots. ResultsData for use of CGM in perioperative period was analyzed for 50 participants with Freestyle Libre 2.0, 20 participants with Dexcom G6, and 6 participants with both devices worn simultaneously. Lost sensor data occurred in 3 participants (15%) wearing Dexcom G6, 10 participants wearing Freestyle Libre 2.0 (20%) and 2 of the participants wearing both devices simultaneously. The overall agreement of the two CGM's utilized had a Pearson correlation coefficient of 0.731 in combined groups with 0.573 in Dexcom arm evaluating 84 matched pairs and 0.771 in Libre arm with 239 matched pairs. Modified Bland-Altman plot of the difference of CGM and POC BG indicated for the overall dataset a bias of −18.27 (SD 32.10). ConclusionsBoth Dexcom G6 and Freestyle Libre 2.0 CGMs were able to be utilized and functioned well if no sensor error occurred at time of initial warmup. CGM provided more glycemic data and further characterized glycemic trends more than individual BG readings. Required time of CGM warm up was a barrier for intraoperative use as well as unexplained sensor failure. CGMs had a fixed warm of time, 1 h for Libre 2.0 and 2 h for Dexcom G6 CGM, before glycemic data obtainable. Sensor application issues did not occur. It is anticipated that this technology could be used to improve glycemic control in the perioperative setting. Additional studies are needed to evaluate use intraoperatively and assess further if any interference from electrocautery or grounding devices may contribute to initial sensor failure. It may be beneficial in future studies to place CGM during preoperative clinic evaluation the week prior to surgery. Use of CGMs in these settings is feasible and warrants further evaluation of this technology on perioperative glycemic management.

LSTM-Based Projectile Trajectory Estimation in a GNSS-Denied Environment.

This paper presents a deep learning approach to estimate a projectile trajectory in a GNSS-denied environment. For this purpose, Long-Short-Term-Memories (LSTMs) are trained on projectile fire simulations. The network inputs are the embedded Inertial Measurement Unit (IMU) data, the magnetic field reference, flight parameters specific to the projectile and a time vector. This paper focuses on the influence of LSTM input data pre-processing, i.e., normalization and navigation frame rotation, leading to rescale 3D projectile data over similar variation ranges. In addition, the effect of the sensor error model on the estimation accuracy is analyzed. LSTM estimates are compared to a classical Dead-Reckoning algorithm, and the estimation accuracy is evaluated via multiple error criteria and the position errors at the impact point. Results, presented for a finned projectile, clearly show the Artificial Intelligence (AI) contribution, especially for the projectile position and velocity estimations. Indeed, the LSTM estimation errors are reduced compared to a classical navigation algorithm as well as to GNSS-guided finned projectiles.

The Behavior of BpSi Stars in the Far UV—Paper II: HD 9996 (HR 465)

The analysis of IUE spectra of the B9 SiCrEu star HD 9996 recorded by the SWP and the LWP camera on board the International Ultraviolet Explorer collected at two phases of its very long rotational period (separated by Δϕ = 0.40), reveals large variations of the far and mid ultraviolet flux. The FUV flux seems to vary in opposition with the optical brightness recorded by the Fine Error Sensor near the V band. At ultraviolet maximum, the lines of Mg ii, Cr ii and Fe ii are definitely stronger than at minimum, which suggests that these elements are distributed in a non uniform manner on the stellar disk with large horizontal gradients. However, the changing aspect of the magnetic field between the two rotational phases observed could also cause part of the ultraviolet variability.

Sistem Monitoring Online Dan Analisis Perfomansi Plts Panel Surya Monocrystalline 100 Wp Berbasis Web

In this modern life, people's dependence on energy sources, especially electrical energy, has led to innovation in the use of cheap alternative energy sources that are environmentally friendly such as solar energy, one of which is PLTS. To support PLTS performance, a web-based monitoring system is needed for remote monitoring in monitoring PLTS performance, the data displayed is the result of measurements by voltage and current sensors installed in each solar panel on the PLTS performance detector. In this case, it is necessary to develop a Web-based monitoring system to help improve the efficiency of performance maintenance on 100 wp monocrystalline panels. By using the INA260 sensor in the form of a digital DC sensor that can measure a maximum current of 15 A, a maximum voltage of 36 v, and DC power and the DS18B20 sensor is a digital sensor that can measure the surface temperature of the panel. Sensor readings can be displayed offline via the HMI LCD while online readings can be displayed in the form of a Web which has a graphical display feature for each parameter and downloads data in the form of a .csv file as a feature that supports data analysis. The results of the sensor validation test or calibration using a measuring instrument have an average error sensor reading of 0.34 %. The average current sensor error is 0.63%, and the power sensor error average is 0.56%, while the average panel surface temperature sensor error is 0.34%

Leakage detection in water distribution networks via 1D CNN deep autoencoder for multivariate SCADA data

Leakages are undesirable events in water distribution networks (WDNs) with mostly unknown incident time making it extremely difficult to accurately label leaks in distribution systems. This study proposes a one-dimensional convolutional neural network (1D CNN) deep autoencoder (AE) that is trained in a semi-supervised fashion to detect and localize leaks using multivariate timeseries data in a bid to mitigate the adverse impact of random noise. A leakage identification framework based on Pruned Exact Linear Time (PELT) multiple change point detector and alarm correlation is proposed. Additionally, a novel localization framework is proposed based on the relative percentage deviation of 1D CNN deep AE reconstruction error of pressure sensors in a district metering area (DMA). The leak localization framework outputs a sensor priority list based on the proximity of the pressure sensor to the leaky pipe thereby significantly reducing the search area for a leakage. The proposed leakage identification and localization framework is validated on a benchmark WDN, the L-TOWN. The results indicate the ability of the proposed method to identify 16 of the 19 leaks in 2019 and accurately localize 13 of the 16 identified leaks within the maximum allowable leak search radius of 300 m without recourse to a hydraulic model. Minimal identification lag was recorded for abrupt leakages whiles incipient leaks require longer identification time due to gradual leak growth rate.

Redundant Parallel Beam Multiaxis Force Sensor—Stress Correlation Coefficient

The stress nonuniformity on the loading neck is an important factor that leads to the local force error of an individual multiaxis force sensor (MAFS) in a distributed multiaxis force sensing system (DMAFSS). The stress correlation coefficient is used to characterize the stress nonuniformity. The stress correlation coefficient decreases with the increase of the loading offset. A full-constrained high-relative-stiffness-ratio structure is important for an MAFS to obtain a good stress correlation coefficient on its loading neck under various external loads. An individual MAFS with two loading necks is employed in the sensing system to increase the relative stiffness ratio. A thin loading neck, a long loading neck distance, and a high stiffness loading frame are important for the high-relative-stiffness-ratio structure. A local high-relative-stiffness-ratio structure is valuable for a large-scale DMAFSS. The mechanical hinge on the loading neck is useful to realize a large-scale lightweight DMAFSS. The extreme load including the load outside the reference loading zone and the concentrated torque affects the stress correlation coefficient apparently which should be specified in future standards.

An Adaptive Multiple Backtracking UKF Method Based on Krein Space Theory for Marine Vehicles Alignment Process

The large misalignment errors of horizontal and azimuthal angle cannot be converged rapidly on the sea surface due to extra disturbance of linear and angular motions caused by wind and waves, which increases the time cost of marine vehicles alignment process and ultimately limits the SINS quick working capability. In order to solve the above problem, an adaptive multiple backtracking UKF method based on Krein space theory is proposed in this paper. Firstly, considering time-varying calibration errors of inertial sensors, a novel robust posterior filtering equation in Krein space is designed to improve the matching degree between the physical process and the mathematical model. Moreover, combined with the multiple forward and reverse navigation processes, an adaptive calculation times control method in backtracking UKF based on the innovation is constructed to solve the nonlinear fast alignment problem in the case of large misalignment angle errors with the purpose of further intelligently shortening the alignment time and ensuring alignment accuracy simultaneously in different periods and working environments. The physical experiment results demonstrate that the horizontal and azimuthal alignment accuracy of the proposed algorithm are improved compared with standard CKF alignment algorithm.

A Coarse Alignment Method Based on Vector Observation and Truncated Vectorized $\boldsymbol{\kappa}$-Matrix for Underwater Vehicle

This paper focuses on the coarse alignment problem for the strapdown inertial navigation system (SINS) applied to the underwater vehicle. The coarse alignment is one of the crucial technologies of underwater navigation and determines whether SINS can work normally. However, the traditional coarse alignment methods suffer from the complicated noises hidden in the inertial sensors’ outputs. To solve this problem, a new coarse alignment algorithm based on vector observation and truncated vectorized <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\boldsymbol{\kappa}$</tex-math></inline-formula> -matrix is proposed in this paper. Different from previous methods based on the optimal quaternion, the proposed algorithm makes the matrix state-space formulae of the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\boldsymbol{\kappa}$</tex-math></inline-formula> -matrix vectorized, and truncates the resulting state vectors by implementing the linear dependence within the components of the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\boldsymbol{\kappa}$</tex-math></inline-formula> -matrix. On one hand, based on the vectorized and truncated <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\boldsymbol{\kappa}$</tex-math></inline-formula> -matrix, a linear reduced model of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\boldsymbol{\kappa}$</tex-math></inline-formula> -matrix can be applied to the estimation process, and the measurement errors of inertial sensors can be easily restrained using the estimation algorithm. On the other hand, the proposed approach makes up for the drawbacks of the Optimal-REQUEST algorithm which has a conservative covariance matrix and scalar gain. The simulation test and practical experiment demonstrate that the proposed approach can reduce random noise effectively. Therefore, the performance of coarse alignment algorithm can be improved more enormously than the traditional algorithms.

Discussion on the Range Configuration Strategy of Tension Sensor of Icing Monitoring Terminals of High-Voltage Transmission Line

Online monitoring of transmission line icing is an important means of anti-icing in the power grid. The accuracy mainly depends on the accuracy of the terminal tension sensor, which is one of the main sources of monitoring errors from large range configuration of tension sensor. This paper analyzes the working principle and characteristics of tension sensors and the load calculation method of different types of insulator hanging points to determine the output error of over-range configuration tension sensors. It finally proposes a principle and a calculation method for tension sensors’ range configuration, which is verified to be reliable by experiments. The results can provide a basis for the selection of tension sensors for icing-monitoring terminals and reduce the error caused by temperature drift and zero drift of tension sensors.

Multi-Source Error Calibration and Observability Analysis of Integrated Inertial Navigation System/Polarization Sensor Navigation System

Accurate polarization information acquisition is the key technique of the integrated inertial navigation system (INS)/polarization sensor (PS) navigation system. To solve the problem of poor performance of polarization sensors that real-time error calibration by using a rotary table, we propose a fast calibration method that polarization sensor combined with inertial navigation systems. Firstly, we construct the calibration model of polarization sensor. A tightly coupled INS/PS calibration model is proposed, specifically, the polarization sensor errors, which are the intensity gain coefficient, the degree of polarization coefficient, and the installation angle error of a polarizer, are augmented into the state of the integrated navigation systems. By introducing the error term of polarization sensor into the state of the integrated navigation systems, the error estimation can be carried out and the speed of error calibration can be improved. Secondly, considering the nonlinearity of error calibration model, we use the Unscented Kalman Filter (UKF) to calibrate the error. On this basis, we make use of the observability analysis to verify its validity of the proposed model in a dynamic scene. Finally, real-world experiments are conducted on the self-developed multi-channel polarization sensor. The experimental results show that the calibration method can be done quickly without the use of a rotary table.

Direct position determination algorithm for non‐circular sources in the presence of mutual coupling and its theoretical performance analysis

AbstractThis article proposes a direct position determination (DPD) algorithm for non‐circular sources observed by a moving array using the self‐calibration technique in the presence of mutual coupling. The method first utilises the symmetric Toeplitz property of uniform linear array matrices with mutual coupling and cyclic Toeplitz property of uniform circular array coupling matrix, realising the decoupled estimations of target position parameters and sensor error parameters. Then the position parameters of multiple non‐circular are directly determined based on the subspace data fusion criterion in a decoupled manner, where the subspaces are obtained using the extended array data model with the non‐circular properties of the sources. This results in a significant improvement in the accuracy of the target position estimation and the number of distinguishable sources compared to the traditional mutual coupling calibration algorithm. In addition, the theoretical mean square error expression for the position estimations of the proposed algorithm under the influence of finite sampling is derived based on the matrix perturbation analysis theory, and the corresponding Cramér‐Rao bound is given. Finally, the correctness of the theoretical derivation and the superiority of the method is verified by simulation experiments.

Design of A Three-axis Helmholtz Coil for Magnetic Sensor Calibration

Accurate measurement of magnetic sensor components is always an important issue in magnetic field applications, but there are unavoidable errors in the sensor system that need to be corrected before use. The common scalar correction method is difficult to effectively correct the sensor component because it requires a uniform and stable background magnetic field and depends on the magnetic field modulus. Therefore, a set of triaxial Helmholtz coils that can be used for sensor vector correction is designed to generate a controlled standard magnetic field. The design index of the coils, the size of the uniform zone, and the relationship between the magnetic field and the current were analyzed to provide a basis for the effective calibration of the sensor components. The measurement results show that the size of the uniform zone and the accuracy of the magnetic field of the coils designed in this paper meet the design requirements. Meanwhile, by using the coils in the calibration of the sensor array and the positioning of the magnetic target, the sensor error is reduced by three orders of magnitude, and the positioning accuracy of the magnetic target reaches 0.1 m with good practical effect.

Assessing the calculation of conductive and acinar ventilatory heterogeneity indices Scond and Sacin from multiple-breath washout data.

Sensor errors resulting in elevated values of N2 concentration [N2] in commercial multiple-breath washout (MBW) devices have been shown to prolong the washout and result in erroneously high functional residual capacity (FRC) and lung clearance index (LCI) values. The errors also affect the indices of conductive and acinar ventilatory heterogeneity (Scond and Sacin) although the mechanism by which this change in values occurs remains unclear. Exploring these effects also provides a timely opportunity to examine the appropriateness of the algorithm used to calculate these indices. Using a two-compartment model with differing specific ventilation (SV) such that the lower SV unit empties late, noise-free MBW were simulated both corrected and uncorrected for the recent sensor error. Scond was calculated using regression of normalized phase III slope (SnIII) against lung turnover (TO) from a TO range starting at 1.5 and ending at an upper turnover (TOupper) between 4 and 8 (default 6) over a range of simulated values. The principal effect of the sensor error was that as the MBW proceeded the phase III slope of successive breaths was normalized by an increasingly overestimated [N2], resulting in SnIII values that fell precipitously at high TO, greatly reducing Scond. Reanalysis of previously published data and of simulated data showed a large proportional bias in Scond, whereas Sacin was only minimally affected. In adult subject data, reducing TOupper below 5.5 was associated with a large drop of up to ∼60% in Scond calculated from data corrected for sensor error. Raising the upper TO limit elevated Scond by ∼20% but with a large concomitant increase in variability. In contrast to Scond, Sacin was relatively unaffected by changes in TOupper with changes of <3%. This work serves to emphasize that the upper limit of TO of 6 represents an appropriate upper limit for the calculation of Scond.NEW & NOTEWORTHY Sensor errors that elevated values of N2 concentration in commercial multiple-breath washout (MBW) devices resulted in errors in calculated parameters including Scond and Sacin. We examined the mechanism of the change in values produced by these errors and explored the appropriateness of the calculation of Scond and Sacin. This work serves to emphasize that the current algorithm in use is appropriate for the calculation of Scond and Sacin.

Online Monitoring of Sensor Calibration Status to Support Condition-Based Maintenance

Condition-Based Maintenance (CBM), based on sensors, can only be reliable if the data used to extract information are also reliable. Industrial metrology plays a major role in ensuring the quality of the data collected by the sensors. To guarantee that the values collected by the sensors are reliable, it is necessary to have metrological traceability made by successive calibrations from higher standards to the sensors used in the factories. To ensure the reliability of the data, a calibration strategy must be put in place. Usually, sensors are only calibrated on a periodic basis; so, they often go for calibration without it being necessary or collect data inaccurately. In addition, the sensors are checked often, increasing the need for manpower, and sensor errors are frequently overlooked when the redundant sensor has a drift in the same direction. It is necessary to acquire a calibration strategy based on the sensor condition. Through online monitoring of sensor calibration status (OLM), it is possible to perform calibrations only when it is really necessary. To reach this end, this paper aims to provide a strategy to classify the health status of the production equipment and of the reading equipment that uses the same dataset. A measurement signal from four sensors was simulated, for which Artificial Intelligence and Machine Learning with unsupervised algorithms were used. This paper demonstrates how, through the same dataset, it is possible to obtain distinct information. Because of this, we have a very important feature creation process, followed by Principal Component Analysis (PCA), K-means clustering, and classification based on Hidden Markov Models (HMM). Through three hidden states of the HMM, which represent the health states of the production equipment, we will first detect, through correlations, the features of its status. After that, an HMM filter is used to eliminate those errors from the original signal. Next, an equal methodology is conducted for each sensor individually and using statistical features in the time domain where we can obtain, through HMM, the failures of each sensor.

Development of personal comfort model and its use in the control of air conditioner

The accurate identification of the real-time thermal state of personnel working indoors has been the focus of researchers. In this study, a detailed examination of the entire process of developing a personal comfort model, from theory to practice, is conducted. In particular, the subject of this investigation is a smart air conditioner capable of predicting thermal sensation based on an infrared (IR) sensor that measures the skin temperature of personnel and then implements automatic control. Random forest algorithm was employed to establish a thermal sensation prediction model, which accepts skin and air temperatures as input parameters. The model achieves a high prediction accuracy value of 0.84. Given the measurement errors of low-cost IR sensors, a simulated temperature measurement experiment based on the manikin was conducted, and an error calibration method based on multiple linear regression was developed through the experiment. 30 subjects participated in another prototype test experiment, which proved that the air conditioner can accomplish effective automatic control based on the prediction of thermal sensation, avoid the occurrence of extreme temperatures, and ensure the thermal comfort of personnel. The possible causes of remaining problems and potential improvement schemes are discussed in detail.