Showing papers in "Measurement Science and Technology in 2022"

Few shot cross equipment fault diagnosis method based on parameter optimization and feature mertic

Abstract: With the rapid development of industrial informatization and deep learning technology, modern data-driven fault diagnosis (MIFD) methods based on deep learning have been receiving attention from the industry. However, most of these methods require sufficient training samples to achieve the desired diagnostic effect, and the scarcity of fault samples in the actual industrial environment leads to the limitation of the development of MIFD methods. In addition, data-driven fault diagnosis methods often need to face cross-load or even cross-domain problems across different devices due to changes in equipment operating conditions and production requirements. In this paper, we design a parameter optimization and feature metric-based fault diagnosis method with few samples, called model unknown matching network model, for the problem of sparse fault samples and cross-domain between data sets in real industrial environments. The method combines both a parametric optimization-based meta-learning network, which extracts optimization information to adapt between different domains, and a metric-based metric learning network, which extracts metric information for similarity discriminations. The experimental results show that the method outperforms the current baseline method for the five-shot fault diagnosis problem of bearings under limited data conditions and achieves an accuracy of up to 94.4 % in cross-device diagnosis experiments from bearings to gas regulators, indicating the feasibility of the method. The features are visualized by T-SNE to show the validity of the model.

Bearing fault diagnosis using transfer learning and optimized deep belief network

Abstract: Bearing is an important component in mechanical equipment. Its main function is to support the rotating mechanical body and reduce the friction coefficient and axial load. In the actual operating environment, the bearings are affected by complex working conditions and other factors. Therefore, it is very difficult to effectively obtain data that meets the conditions of independent and identical distribution of training data and test data, which result in unsatisfactory fault diagnosis results. As a transfer learning method, joint distribution adaptive (JDA) can effectively solve the learning problem of inconsistent distribution of training data and test data. In this paper, a new bearing fault diagnosis method based on JDA and deep belief network (DBN) with improved sparrow search algorithm (CWTSSA), namely JACADN is proposed. In the JACADN, the JDA is employed to carry out feature transfer between the source domain samples and target domain samples, that is, the source domain samples and target domain samples are mapped into the same feature space by the kernel function. Then the maximum mean difference is used as the metric to reduce the joint distribution difference between the samples in the two domains. Aiming at the parameter selection of the DBN, an improved sparrow search algorithm (CWTSSA) with global optimization ability is used to optimize the parameters of the DBN in order to construct an optimized DBN model. The obtained source domain samples and target domain samples are divided into training set and test set, which are input the optimized DBN to construct a bearing fault diagnosis model for improving the diagnosis accuracy. The effectiveness of the proposed method is verified by vibration data of QPZZ-II rotating machinery. The experimental results show that the proposed JACADN method can effectively improve the fault diagnosis accuracy of rolling bearings under variable operating conditions.

Development of a new high-precision friction test platform and experimental study of friction characteristics for pneumatic cylinders

Abstract: In order to achieve high-precision pneumatic cylinder friction test, this paper proposes a new direct measurement method based on electric cylinder in which the axially acting forces from the compressed air in the two facing pneumatic cylinders cancel each other out and the detected value of the force transducer is just friction. For the sake of the implementation of the method, a new low-cost test method for identifying deadband of proportional directional valve was proposed, and a set of fuzzy PI constant pressure control system was designed to cope with a certain degree of leakage in the chamber. Based on the above, a friction test platform with two pneumatic cylinders facing each other was eventually built to study the influence of pressure, pressure difference, and piston speed on the friction of two commonly used different types of pneumatic cylinders. Through multiple sets of tests, it is found that when the lip seals are used in pairs between the piston and the inner wall of the cylinder, the friction between the piston and the cylinder is only related to the sum of the two chamber pressures, but not to the pressure difference between the two chambers. When the O-ring seal is used between the piston and the inner wall of the cylinder, the friction between the piston and the cylinder is related not only to the pressure of the two chambers, but also to the pressure difference between the two chambers. In addition, a series of comparative tests with the traditional single-cylinder friction test method directly demonstrate the effectiveness of the proposed new method.

A novel performance trend prediction approach using ENBLS with GWO

Abstract: Bearings are a core component of rotating machinery, and directly affect its reliability and operational efficiency. Effective evaluation of a bearing’s operational state is key to ensuring the safe operation of the equipment. In this paper, a novel prediction method of bearing performance trends based on the elastic net broad learning system (ENBLS) and the grey wolf optimization (GWO) algorithm is proposed. The proposed method combines the advantages of the ENBLS and GWO algorithms to achieve better prediction results. In order to solve the problem that traditional regression prediction algorithms may lead to unsatisfactory prediction results and long training time, we propose a performance trend prediction method based on ENBLS. To further improve the prediction accuracy, we utilize the GWO algorithm to optimize various parameters present in the model to improve the performance of the model. The bearing data of the whole life cycle from the 2012 IEEE PHM challenge are selected to verify the effectiveness of the proposed method. The results show that the proposed method has high prediction accuracy and stability.

Interpretability of deep convolutional neural networks on rolling bearing fault diagnosis

Abstract: Abstract Despite the rapid development of deep learning-based intelligent fault diagnosis methods on rotating machinery, the data-driven approach generally remains a ‘black box’ to researchers, and its internal mechanism has not been sufficiently understood. The weak interpretability significantly impedes further development and application of the effective deep neural network-based methods. This paper contributes to understanding the mechanical signal processing of deep learning on the fault diagnosis problems. The diagnostic knowledge learned by the deep neural network is visualized using the neuron activation maximization and the saliency map methods. The discriminative features of different machine health conditions are intuitively observed. The relationship between the data-driven methods and the well-established conventional fault diagnosis knowledge is confirmed by the experimental investigations on two datasets. The results of this study can benefit researchers on understanding the complex neural networks, and increase the reliability of the data-driven fault diagnosis model in real engineering cases.

An ameliorated African vulture optimization algorithm to diagnose the rolling bearing defects

Abstract: In this work, a novel bearing fault identification scheme making use of deep learning has been proposed. Initially, the raw vibration signal is passed through a time-varying filter based empirical mode decomposition (TVF-EMD) to obtain different modes. Filter parameters of TVF-EMD are optimized by a newly developed optimization algorithm i.e. ameliorated African vulture optimization algorithm The Kernel estimate for mutual information has been considered as the fitness index for the developed optimization algorithm. The mode having the least value of fitness index is known as a prominent mode from which sensitive features representing different bearing conditions are extracted. These extracted features help in preparing the data matrix which is further utilised to build fuzzy-based classification models. The results obtained revealed that the linguistic hedge neuro-fuzzy classifier obtained maximum performance with the least computational time. The comparison of the developed method has also been done with other classification models viz., KNN, SVM, ELM and random forest that revealed the superiority of the developed method.

MEMS technology and applications in geotechnical monitoring: a review

Abstract: In-situ monitoring is an important aspect of geotechnical projects to ensure safety and optimise design measures. However, existing conventional monitoring instruments are limited in their accuracy, durability, complex and high cost of installation and requirement for ongoing real time measurement. Advancements in sensing technology in recent years have created a unique prospect for geotechnical monitoring to overcome some of those limitations. For this reason, micro-electro-mechanical system (MEMS) technology has gained popularity for geotechnical monitoring. MEMS devices combine both mechanical and electrical components to convert environment system stimuli to electrical signals. MEMS-based sensors provide advantages to traditional sensors in that they are millimetre to micron sized and sufficiently inexpensive to be ubiquitously distributed within an environment or structure. This ensures that the monitoring of the in-situ system goes beyond discrete point data but provides an accurate assessment of the entire structures response. The capability to operate with wireless technology makes MEMS microsensors even more desirable in geotechnical monitoring where dynamic changes in heterogeneous materials at great depth and over large areas are expected. Many of these locations are remote or hazardous to access directly and are thus a target for MEMS development. This paper provides a review of current applications of existing MEMS technology to the field/s of geotechnical engineering and provides a path forward for the expansion of this research and commercialisation of products.

A hybrid FBG-based load and vibration transducer with a 3D fused deposition modelling approach

Abstract: A fibre Bragg grating (FBG)-based load and vibration transducer (FLVT) was developed using a 3D fused deposition modelling (FDM) approach. A newly FLVT was designed by the equal-strength cantilever beam in which the FBG sensors were embedded in the beam during the FDM process. The temperature effect was eliminated by the temperature sensor in the vibration sensing unit. The parameters of the proposed FLVT was examined by the finite element method. The simulated results were matched well with the theoretical analysis results and laboratory calibration results. The proposed transducer has the pressure measurement sensitivity of 0.01274 nm kPa−1 for the earth pressure below 150 kPa. In addition, the proposed transducer could accurately measure low-frequency vibration signals with maximum frequency of 4 Hz and the maximum displacement amplitude of 4 mm with sensitivity of 117.6 pm g−1. The measurement accuracy and stability were carried out. Results shown that the maximum relative errors between the calculation results and the experimental results was 1.3%. The effect of vibration direction was also analysed for the proposed FLVT. The results indicated that the transversal vibration has less influence on the longitudinal vibration. The outcome of this study indicated that the proposed FLVT provide a newly approach for the measurement of earth pressure and soil vibration in one transducer which is quit suit for soil mass.

Improving accuracy of cavitation severity recognition in axial piston pumps by denoising time–frequency images

Abstract: The vibration signal is a good indicator of cavitation in axial piston pumps. Some vibration-based machine learning methods have been developed for recognizing pump cavitation. However, their fault diagnostic performance is often unsatisfactory in industrial applications due to the sensitivity of the vibration signal to noise. In this paper, we present an intelligent method for recognizing the cavitation severity of an axial piston pump in a noisy environment. First, we adopt short-time Fourier transformation to convert the raw vibration data into spectrograms that act as input images of a modified LeNet-5 convolutional neural network (CNN). Second, we propose a denoising method for the converted spectrograms based on frequency spectrum characteristics. Finally, we verify the proposed method on the dataset from a test rig of a high-speed axial piston pump. The experimental results indicate that the denoising method significantly improves the diagnostic performance of the CNN model in a noisy environment. For example, using the denoising method, the accuracy rate forcavitation recognition increases from 0.52 to 0.92 at a signal-to-noise ratio of 4 dB.

Augmented flame image soft sensor for combustion oxygen content prediction

Abstract: Oxygen content is one of the most critical factors for high-efficiency combustion. Online measurement of oxygen content from flame images is important but still challenging. For construction of an oxygen content prediction model, most current feature extraction methods are not straightforward. Additionally, there are always sufficient data for common operating conditions in practice, while only limited data for other operating conditions. The data collection process for model training is costly and time-consuming. To tackle the problem, this work presents an augmented flame image soft sensor for automated combustion oxygen content prediction. A convolutional neural network (CNN) regression model is designed to predict the oxygen content directly from flame images, without a single feature extraction process. Moreover, a regression generative adversarial network with gradient penalty is proposed to generate flame images with oxygen content labels. It overcomes the imbalanced and insufficient data problem arising in the CNN regression model training. The proposed soft sensor is compared with several common regression methods for oxygen content prediction. Experimental results show that the proposed method can predict the combustion oxygen content with high accuracy from flame images although the original datasets are imbalanced.

AFM microfluidic cantilevers as weight sensors for live single cell mass measurements

Abstract: Reliably measuring small mass changes at the single-cell level is challenging. In this manuscript, we report the use of microfluidic cantilevers in liquid with sub-nanogram scale weight sensing capability for the measurement of cellular mass changes of living single cells. With this instrumentation, we were able to perform fast mass measurements within 3 min. We show results of mass measurements of polystyrene and metal beads of various sizes (smallest weight measured at 280 ± 95 pg) and live single-cell mass measurements in a physiologically relevant environment. We also performed finite element analysis to simulate and optimize the structural design and materials of cantilevers. Our simulation results indicate that using polymer materials, such as SU8 and polyimide, could improve the minimal detectable mass by three-fold compared to conventional silicon cantilevers. The simulations also suggest that smaller dimensions of length, width, and thickness would improve the mass detection capability of microfluidic cantilevers.

Generative adversarial network and transfer-learning-based fault detection for rotating machinery with imbalanced data condition

Abstract: Abstract Intelligent fault diagnosis achieves tremendous success in machine fault diagnosis because of its outstanding data-driven capability. However, the severely imbalanced dataset in practical scenarios of industrial rotating machinery is still a big challenge for the development of intelligent fault diagnosis methods. In this paper, we solve this issue by constructing a novel deep learning model incorporated with a transfer learning (TL) method based on the time-generative adversarial network (Time-GAN) and efficient-net models. Firstly, the proposed model, called Time-GAN-TL, extends the imbalanced fault diagnosis of rolling bearings using time-series GAN. Secondly, balanced vibration signals are converted into two-dimensional images for training and classification by implementing the efficient-net into the transfer learning method. Finally, the proposed method is validated using two types of rolling bearing experimental data. The high-precision diagnosis results of the transfer learning experiments and the comparison with other representative fault diagnosis classification methods reveal the efficiency, reliability, and generalization performance of the presented model.

Bearing fault diagnosis method based on a multi-head graph attention network

Abstract: The bearing is the core component of mechanical equipment, and attention has been paid to its health monitoring and fault diagnosis. Bearing fault diagnosis technology based on deep learning has been widely developed because of its powerful feature learning and fault classification ability. However, the traditional deep learning-based bearing fault diagnosis methods fail in mining the relationship between signals explicitly, which is beneficial to fault classification. Therefore, this paper proposes a new method based on a multi-head graph attention network (MHGAT) for bearing fault diagnosis. Firstly, it employs dynamic time warping to transform the original vibration signals into graph data with topological structure, so as to exploit the intrinsic structural information of the independent samples. Next, the graph data is input into the MHGAT, and the weights of neighbor nodes are learned automatically. Then, the MHGAT extracts the discriminative features from different scales and aggregates them into an enhanced, new feature representation of graph nodes through the multi-head attention mechanism. Finally, the enhanced, new features are fed into the SoftMax classifier for bearing fault diagnosis. The effectiveness of the proposed method is examined by two bearing datasets. The superiority of the proposed method is verified by comparison to traditional deep learning diagnosis models.

Multiview Wasserstein generative adversarial network for imbalanced pearl classification

Abstract: This work described in this paper aims to enhance the level of automation of industrial pearl classification through deep learning methods. To better extract the features of different classes and improve classification accuracy, balanced training datasets are usually needed for machine learning methods. However, the pearl datasets obtained in practice are often imbalanced; in particular, the acquisition cost of some classes is high. An enhanced generative adversarial network, named the multiview Wasserstein generative adversarial network (MVWGAN), is proposed for the imbalanced pearl classification problem. For the minority classes in the training datasets, the MVWGAN method can generate high-quality multiview images simultaneously to balance the original imbalanced datasets. The augmented balanced datasets are used to train a multistream convolution neural network (MS-CNN) for pearl classification. The experimental results show that MVWGAN can overcome the imbalanced learning problem and improve the classification performance of MS-CNN effectively. Moreover, feature visualization is implemented to intuitively explain the effectiveness of MVWGAN.

Bearing fault diagnosis method based on multi-source heterogeneous information fusion

Abstract: Bearing fault diagnosis is a critical component of the mechanical equipment monitoring system. In the complex and harsh environment in which bearings operate, the fault diagnosis approach of multi-source information fusion can extract fault features more stably and extensively than the traditional single-source fault diagnosis method. However, most existing multi-source fusion methods are in infancy, and there are a number of pressing issues to address, such as subjective elements having a significant impact, excessive data redundancy, fuzzy multi-source signal fusion strategy, and insufficient accuracy. As a result, a new multi-source fusion fault diagnosis method is proposed in this paper. First, the residual pyramid algorithm is utilized to fuse the acoustic and vibration signals of multiple spatial positions respectively and then form two fused acoustic and vibration signals. Second, two improved 2D-CNN are used to extract the fault features contained in the above two signals separately to form a multi-source fault feature set. Third, an AdaBoost algorithm with a dynamic deletion mechanism is designed to fuse multi-source fault feature sets and produce the fault diagnosis findings. Finally, six different experimental data sets are used to test the performance of the model. The results reveal that the model has better generalization, higher and more stable fault diagnostic accuracy, and stronger anti-interference capacity.

Flow field tomography with uncertainty quantification using a Bayesian physics-informed neural network

Abstract: Abstract We report a new approach to flow field tomography that uses the Navier–Stokes and advection–diffusion equations to regularize reconstructions. Tomography is increasingly employed to infer 2D or 3D fluid flow and combustion structures from a series of line-of-sight (LoS) integrated measurements using a wide array of imaging modalities. The high-dimensional flow field is reconstructed from low-dimensional measurements by inverting a projection model that comprises path integrals along each LoS through the region of interest. Regularization techniques are needed to obtain realistic estimates, but current methods rely on truncating an iterative solution or adding a penalty term that is incompatible with the flow physics to varying degrees. Physics-informed neural networks (PINNs) are new tools for inverse analysis that enable regularization of the flow field estimates using the governing physics. We demonstrate how a PINN can be leveraged to reconstruct a 2D flow field from sparse LoS-integrated measurements with no knowledge of the boundary conditions by incorporating the measurement model into the loss function used to train the network. The resulting reconstructions are remarkably superior to reconstructions produced by state-of-the-art algorithms, even when a PINN is used for post-processing. However, as with conventional iterative algorithms, our approach is susceptible to semi-convergence when there is a high level of noise. We address this issue through the use of a Bayesian PINN, which facilitates comprehensive uncertainty quantification of the reconstructions, enables the use of a more intuitive loss function, and reveals the source of semi-convergence.

A simple and precise calibration method for binocular vision

Abstract: The binocular vision is an important part of machine vision measurement. The calibration accuracy is crucial for binocular vision. As for the determination of the structure parameters of the two cameras, the existing approaches usually obtain the initial values and optimize them according to the image-space errors, object-space errors or combination of them. In the optimization process, constructing the objective function only through the image-space errors or object-space errors is not enough. Moreover, the image-space errors and object-space errors can form a variety of combinations for constructing objective function. Therefore, it is hard to choose the error criterion. The inadequate error criterion may lead to over optimized or local minima (ambiguity solution). To solve the problem above, this paper proposes a simple and precise calibration method for binocular vision based on the points distance constraints and image-space errors. The process of determining the structure parameters was divided into non-iterative and iterative parts. We calculated the structure parameters of the two cameras according to distance constraints of every two feature points non-iteratively. The results obtained in this step were set as the initial value and refined through minimizing the reprojection errors by Levenberg-Marquardt method. Because the results obtained in the non-iterative step are accurate enough, only one iteration is needed. In this way, we finish the calibration avoiding to choose the error criterions. Furthermore, our method reduces the number of iterations to improve the calibration efficiency on the premise of guaranteeing the calibration accuracy. The experimental results show the superiority of this calibration method compared with other calibration methods.

A hybrid deep-learning model for fault diagnosis of rolling bearings in strong noise environments

Abstract: Strong noise in practical engineering environments interferes with the signal of a rolling bearing, which leads to the decline of the diagnosis accuracy of intelligent diagnosis models. This paper proposes a novel hybrid model (a convolutional denoising auto-encoder (CDAE)-BLCNN) to address this problem. First, the rolling bearing vibration signal containing noise was input into the CDAE, which denoises the signal through unsupervised learning and then outputs the reconstructed data. Secondly, a hybrid neural network (BLCNN), composed of a multi-scale wide convolution neural network and a bidirectional long-short-term memory network, was used to extract intrinsic fault features from the reconstructed signal and diagnose fault types. The analysis results demonstrate that the proposed hybrid deep-learning model achieves higher detection accuracy, even under different noise levels and various rotating speeds. Compared with other models, there is a high fault recognition rate, robustness, and generalization ability, which may be favorable to practical applications.

Acoustic-based method for identifying surface damage to wind turbine blades by using a convolutional neural network

Abstract: Damage to the surface of the blades of a large wind turbine may lead to catastrophic blade failure. Although numerous methods have been proposed for detecting surface damage to wind turbine blades, many of them involve laboratory tests because of the difficulty in acquiring data from a commercial wind farm. This lack of data variety is an obstacle to the development of machine learning approaches for identifying the aforementioned damage. Therefore, we developed a damage detection method for wind turbine blade surfaces that is based on the physical correlation between surface conditions and acoustic signals of operating wind turbines under realistic environmental conditions. In the preprocessing stage of the aforementioned method, the short-time Fourier transform and smoothing techniques are used to analyze real-time spectrograms and the rotor speed. The derived spectrogram and rotor speed are then input into a convolutional neural network (CNN) to classify the wind turbine blade surfaces into two classes: turbines with at least one or no damaged blade. The CNN proposed in this paper is a hybrid network containing a masking module and residual classifier. The masking module suppresses redundant information in the spectrogram, and the residual classifier quantifies the difference between the masked spectrogram and a standard spectrogram. The proposed CNN can be easily trained on a small dataset with a few trainable parameters by using the physical characteristics in the residual classifier. The proposed damage detection method was evaluated using the operational noise of commercial wind turbines; according to the results, this method outperformed approaches proposed in previous studies and exhibited an accuracy of 97.11%.

Investigation of the stability of graphene devices for quantum resistance metrology at direct and alternating current

Abstract: Interlaboratory comparisons of the quantized Hall resistance (QHR) are essential to verify the international coherence of primary impedance standards. Here, we report on the investigation of the stability of p-doped graphene-based QHR devices at direct and alternating currents at CMI, KRISS, and PTB. To improve the stability of the electronic transport properties of the polymer-encapsulated devices, they were shipped in an over-pressurized transport chamber. The agreement of the quantized resistance with R K/2 at direct current was on the order of 1 nΩ Ω−1 between 3.5 and 7.5 T at a temperature of 4.2 K despite changes in the carrier density during the shipping of the devices. At alternating current, the quantized resistance was realized in a double-shielded graphene Hall device. Preliminary measurements with digital impedance bridges demonstrate the good reproducibility of the quantized resistance near the frequency of 1 kHz within 0.1 μΩ Ω−1 throughout the international delivery.

Multimodal convolutional neural network model with information fusion for intelligent fault diagnosis in rotating machinery

Abstract: Accurate and efficient fault diagnosis in rotating machinery has long been important and challenging, as it strongly affects the system reliability and safety of industrial applications. In recent years, deep-learning-based methods are developing rapidly and have been widely used in different areas. However, most of them are data-driven and focus on the architecture and design of convolutional neural network (CNN) models, while neglecting the representation of information itself. The intrinsic characteristics of the signal can not fully explored. Moreover, rich multidirectional information hidden inside the signal, which is the key to improving the predictive performance of the entire fault diagnosis model, has usually been ignored. In this work, we propose a multimodal neural-network-based model to pursue feature representation more efficiently and effectively and further improve the diagnostic performance. This method innovatively combines continuous wavelet transform and symmetrized dot pattern graphs through the channel information fusion mechanism after the two-dimensional domain modal transformation of the time-domain signal. The integration of one- and two-dimensional convolutions could fully utilize the feature extraction capability of CNN for multimodal signals, thus forming a multimodal CNN architecture under two-level information fusion. The experiment results prove that the designed model can achieve better performance than the traditional single-modal CNN structure.

Quantify pixel-level detection of dam surface crack using deep learning

Abstract: An increasing number of detection methods based on computer vision are applied to detect cracks in water conservancy infrastructure. However, most studies directly use existing feature extraction networks to extract crack information, which are proposed for open-source datasets. As the crack distribution and pixel features are different from these data, the extracted crack information is incomplete. In this paper, a deep learning-based network for dam surface crack detection is proposed, which mainly addresses the semantic segmentation of cracks on the dam surface. Particularly, we design a shallow encoding network to extract features of crack images based on the statistical analysis of cracks. Further, to enhance the relevance of contextual information, we introduce an attention module into the decoding network. During the training, we use the sum of cross-entropy and Dice loss as the loss function to overcome data imbalance. The quantitative crack information is extracted by the imaging principle after using morphological algorithms to extract the morphological features of the predicted result. We built a manual annotation dataset containing 1577 images to verify the effectiveness of the proposed method. This method achieves state-of-the-art performance on our dataset. Specifically, the precision, recall, Intersection of Union (IoU), F1_measure, and accuracy are 90.81%, 81.54%, 75.23%, 85.93%, 99.76%, respectively, and the quantification error of cracks is less than 4%.

Extended tuning of distributed-feedback lasers in a bias-tee circuit via waveform optimization for MHz-rate absorption spectroscopy

Abstract: Variations in injection-current waveform are examined using diplexed radio-frequency modulation with continuous-wave distributed-feedback (CW-DFB) lasers, with the aim to maximize the spectral tuning range and signal-to-noise ratio for MHz-rate laser absorption spectroscopy (LAS). Utilizing a bias-tee circuit, laser chirp rates are shown to increase by modulating the AC input voltage using square waves instead of sine waves and by scanning the laser below the lasing threshold during the modulation period. The effect of waveform duty cycle and leading-edge ramp rate are further examined. A spectral scan depth on the order of 1 cm−1 at a scan frequency of 1 MHz is achieved with a representative CW-DFB quantum cascade laser near 5 μm. Distortion of high-frequency optical signals due to detector bandwidth is also examined, and limitations are noted for applications with narrow spectral features and low-bandwidth detectors. Based on common detection system limitations, an optimization approach is established for a given detection bandwidth and target spectra. A representative optimization is presented for measurements of sub-atmospheric carbon monoxide spectra with a 200-MHz detection system. The methods are then demonstrated to resolve transient gas properties (pressure and temperature) via LAS at MHz rates in a detonation tube and shock tube facility. An appendix detailing a first-order model of high-speed distributed feedback laser tuning dynamics is also included to support the experimental observations of this work.

Emerging technologies in the field of thermometry

Abstract: The past decade saw the emergence of new temperature sensors that have the potential to disrupt a century-old measurement infrastructure based on resistance thermometry. In this review we present an overview of emerging technologies that are either in the earliest stages of metrological assessment or in the earliest stages of commercial development and thus merit further consideration by the measurement community. The following emerging technologies are reviewed: Johnson noise thermometry, optical refractive-index gas thermometry, Doppler line broadening thermometry, optomechanical thermometry, fiber-coupled phosphor thermometry, fiber-optic thermometry based on Rayleigh, Brillouin and Raman scattering, fiber-Bragg-grating thermometry, Bragg-waveguide-grating thermometry, ring-resonator thermometry, and photonic-crystal-cavity thermometry. For each emerging technology, we explain the working principle, highlight the best known performance, list advantages and drawbacks of the new temperature sensor and present possibilities for future developments.

Adversarial domain adaptation of asymmetric mapping with CORAL alignment for intelligent fault diagnosis

Abstract: Abstract Rolling bearings play a vital role in the overall operation of rotating machinery. In practice, many learning methods for variable-speed fault diagnosis ignore task-specific decision boundaries, making it very difficult to completely match feature distribution between different domains. Therefore, to overcome this problem, an adversarial domain adaptation of asymmetric mapping with CORAL alignment is presented. The asymmetric mapping feature extractor is able to extract more specific-domain features with obvious distinction. Meanwhile, combining the maximum classifier discrepancy of deep transfer to give an adversarial approach and taking the task-specific decision boundaries into account, class-level alignment between the features of the source domain and target domain can be attempted. To prevent degenerate learning, which is possibly caused by asymmetric mapping and adversarial learning, the model is constrained by deep CORAL alignment to extract more domain-invariant features. Experimental results show that the proposed method can solve the variable-speed (a small span of intermediate vehicle speeds) fault diagnosis problem well, with high transfer accuracy and strong generalization.