Search results

The sources of magnetic sensors errors are numerous, such as currents around, soft magnetic and hard magnetic materials and so on. The traditional methods mainly use explicit error models, and it is difficult to include all interference factors. This paper aims to present an implicit error model and studies its high-precision training method.

A multi-level extreme learning machine based on reverse tuning (MR-ELM) is presented to compensate for magnetic compass measurement errors by increasing the depth of the network. To ensure the real-time performance of the algorithm, the network structure is fixed to two ELM levels, and the maximum number of levels and neurons will not be continuously increased. The parameters of MR-ELM are further modified by reverse tuning to ensure network accuracy. Because the parameters of the network have been basically determined by least squares, the number of iterations is far less than that in the traditional BP neural network, and the real-time can still be guaranteed.

The results show that the training time of the MR-ELM is 19.65 s, which is about four times that of the fixed extreme learning algorithm, but training accuracy and generalization performance of the error model are better. The heading error is reduced from the pre-compensation ±2.5° to ±0.125°, and the root mean square error is 0.055°, which is about 0.46 times that of the fixed extreme learning algorithm.

MR-ELM is presented to compensate for magnetic compass measurement errors by increasing the depth of the network. In this case, the multi-level ELM network parameters are further modified by reverse tuning to ensure network accuracy. Because the parameters of the network have been basically determined by least squares, the number of iterations is far less than that in the traditional BP neural network, and the real-time training can still be guaranteed. The revised manuscript improved the ELM algorithm itself (referred to as MR-ELM) and bring new ideas to the peers in the magnetic compass error compensation field.

The purpose of this study is to analyze the intelligent semisupervised fault diagnosis method of aeroengine.

A semisupervised fault diagnosis method based on denoising autoencoder (DAE) and deep belief network (DBN) is proposed for aeroengine. Multiple state parameters of aeroengine with long time series are processed to form high-dimensional fault samples and corresponding fault types are taken as sample labels. DAE is applied for unsupervised learning of fault samples, so as to achieve denoised dimension-reduction features. Subsequently, the extracted features and sample labels are put into DBN for supervised learning. Thus, the semisupervised fault diagnosis of aeroengine can be achieved by the combination of unsupervised learning and supervised learning.

The JT9D aeroengine data set and simulated aeroengine data set are applied to test the effectiveness of the proposed method. The result shows that the semisupervised fault diagnosis method of aeroengine based on DAE and DBN has great robustness and can maintain high accuracy of fault diagnosis under noise interference. Compared with other traditional models and separate deep learning model, the proposed method also has lower error and higher accuracy of fault diagnosis.

Multiple state parameters with long time series are processed to form high-dimensional fault samples. As a typical unsupervised learning, DAE is used to denoise the fault samples and extract dimension-reduction features for future deep learning. Based on supervised learning, DBN is applied to process the extracted features and fault diagnosis of aeroengine with multiple state parameters can be achieved through the pretraining and reverse fine-tuning of restricted Boltzmann machines.

The primary aim of this article is to ascertain the modalities of leveraging Lean Six Sigma (LSS) for Industry 4.0 (I4.0) with special reference to the process industries. Moreover, it intends to determine the applicability of simulation-based LSS in the automation of the mineral water industry, with special emphasis on the robust design of the control system to improve productivity and performance.

This study adopts the action research methodology, which is exploratory in nature along with the DMAIC (define-measure-analyze-improve-control) approach to systematically unearth the root causes and to develop robust solutions. The MATLAB simulation software and Minitab statistical software are effectively utilized to draw the inferences.

The root causes of critical to quality characteristic (CTQ) and variation in purity level of water are addressed through the simulation-based LSS approach. All the process parameters and noise parameters of the reverse osmosis (RO) process are optimized to reduce the errors and to improve the purity of the water. The project shows substantial improvement in the sigma rating from 1.14 to 3.88 due to data-based analysis and actions in the process. Eventually, this assists the management to realize an annual saving of 20% of its production and overhead costs. This study indicates that LSS can be applicable even in the advent of I4.0 by reinforcing the existing approach and embracing data analysis through simulation.

The limitation of this research is that the inference is drawn based on a single case study confined to process industry automation. Having said that, the methodology deployed, scientific information related to optimization, and technical base established can be generalized.

This article is the first of its kind in establishing the integration of simulation, LSS, and I4.0 with special reference to automation in the process industry. It also delineates the case study in a phase-wise manner to explore the applicability and relevance of LSS with I4.0. The study is archetype in enabling LSS to a new era, and can act as a benchmark document for academicians, researchers, and practitioners for further research and development.

The purpose of this study is to analyze the intelligent fault diagnosis method of rolling bearing.

The vibration signal data of rolling bearing has long time series and strong noise interference, which brings great difficulties for the accurate diagnosis of bearing faults. To solve those problems, an intelligent fault diagnosis model based on stacked denoising autoencoder (SDAE) and convolutional neural network (CNN) is proposed in this paper. The SDAE is used to process the time series data with multiple dimensions and noise interference. Then the dimension-reduced samples can be put into CNN model, and the fault classification results can be obtained by convolution and pooling operations of hidden layers in CNN.

The effectiveness of the proposed method is validated through experimental verification and comparative experimental analysis. The results demonstrate that the proposed model can achieve an average classification accuracy of 96.5% under three noise levels, which is 3-13% higher than the traditional models and single deep-learning models.

The combined SDAE–CNN model proposed in this paper can denoise and reduce dimensions of raw vibration signal data, and extract the in-depth features in image samples of rolling bearing. Consequently, the proposed model has more accurate fault diagnosis results for the rolling bearing vibration signal data with long time series and noise interference.

The peer review history for this article is available at: https://publons.com/publon/10.1108/ILT-11-2019-0496/

Aiming at the problem that the transmission mechanism of the assembly error of the multi-stage rotor with saddle surface type is not clear, the purpose of this paper is to propose a deep belief network to realize the prediction of the coaxiality and perpendicularity of the multi-stage rotor.

First, the surface type of the aero-engine rotor is classified. The rotor surface profile sampling data is converted into image structure data, and a rotor surface type classifier based on convolutional neural network is established. Then, for the saddle surface rotor, a prediction model of coaxiality and perpendicularity based on deep belief network is established. To verify the effectiveness of the coaxiality and perpendicularity prediction method proposed in this paper, a multi-stage rotor coaxiality and perpendicularity assembly measurement experiment is carried out.

The results of this paper show that the accuracy rate of face type classification using convolutional neural network is 99%, which meets the requirements of subsequent assembly process. For the 80 sets of test samples, the average errors of the coaxiality and perpendicularity of the deep belief network prediction method are 0.1 and 1.6 µm, respectively.

Therefore, the method proposed in this paper can be used not only for rotor surface classification but also to guide the assembly of aero-engine multi-stage rotors.

The purpose of this paper is to evaluate the photochromic performance of photochromic compounds in polymer matrices.

The poly(methyl methacrylate) (PMMA) and epoxy resin doped with photochromic spirobenzopyran were prepared and the effects of ultraviolet (UV) irradiation were studied using spectrophotometer. The reversible reaction was effected using white light. Photochemical fatigue resistance of these films was also studied.

Irradiation of colourless 1′,3′,3′‐trimethyl‐6‐nitrospiro[2H‐1‐benzopyran‐2,2′‐indoline] spiropyran (SP) doped in PMMA and epoxy resin with UV light (366 nm) results in the formation of an intense purple‐red coloured zwitterionic photomerocyanine (PMC). The reverse reaction was photochemically induced by irradiation with white light. Photocolouration of SP doped in PMMA follows a first‐order rate equation (k=0.0011 s⁻¹), while that doped in epoxy resin deviates from linearity. It was found that photobleaching follows a first‐order equation in both matrices. The photobleaching rate constant of PMC in both matrices is the same and equals 0.0043 s⁻¹. Spirobenzopyran doped in PMMA shows better fatigue resistance than that doped in epoxy resin.

The PMMA and epoxy resin polymers doped with photochromic spirobenzopyran described in the present paper were prepared and studied. The principle of study established can be applied to any type of polymer or to any type of photochromic compounds.

The photochromic materials developed can be used for different applications, such as coatings and holography.

The method developed may be used to enhance the performance of photochromic materials.

The three-axis magnetic sensors are mostly calibrated by scalar method such as ellipsoid fitting and so on, but these methods cannot completely determine the 12 parameters of the error model. A two-stage calibration method based on particle swarm optimization (TSC-PSO) is proposed, which makes full use of the amplitude invariance and direction invariance of Earth’s magnetic field vector.

The TSC-PSO designs two-stage fitness function. Stage 1: design a fitness function of the particle swarm by the amplitude invariance of the Earth’s magnetic field to obtain a preliminary error matrix G and the bias error B. Stage 2: further design the fitness function of the particle swarm by the invariance of the Earth’s magnetic field to obtain a rotation matrix R, thereby determining the error matrix uniquely.

The proposed TSC-PSO can completely determine 12 unknown parameters in error model and further decrease the maximum fluctuation error of the Earth’s magnetic field amplitude and the absolute error of heading.

The proposed TSC-PSO provides an effective solution for three-axis magnetic sensor error compensation, which can greatly reduce the price of magnetic sensors and be used in the fields of Earth’s magnetic survey, drilling and Earth’s magnetic integrated navigation.

The proposed TSC-PSO has significantly improved the magnetic field amplitude and heading accuracy and does not require additional heading reference. In addition, the method is insensitive to noise and initialization conditions, has good robustness and can converge to a global optimum.

THE Funk Gerat 10 equipment is the latest standardized type, and is installed in all the later bombers and reconnaissance machines of the Luftwaffe.

The purpose of this paper is to design a third-order linear active disturbance rejection controller (LADRC) to improve the response characteristics and robustness of the electrohydraulic servo system.

The LADRC was designed by replacing the nonlinear functions in each part of ADRC with linear functions or linear combinations, and the parameters of each part of the LADRC were connected with their bandwidth through the pole configuration method to reduce the required tuning parameters, and used an improved grey wolf optimizer to tune the LADRC parameters.

The anti-interference control simulation and experiment on the LADRC, ADRC and proportion integration differentiation (PID) were carried out to test the robustness, anti-interference ability and superiority of the designed LADRC. The simulation and experiment results showed that the LADRC control and anti-interference control had excellent performance, and because of its simple structure and fewer parameters, LADRC was easier to implement and had a better control effect and anti-interference.

For the problems of parameter perturbation, unknown interference and inaccurate model in the electrohydraulic position servo system, the designed third-order LADRC has good tracking accuracy and anti-interference, has few parameters and is conducive to promotion.

The purpose of this paper is to design and realize a low‐phase noise, high‐output power, and high‐tuning range, fully integrated source injection parallel coupled (SIPC)‐based inductor‐capacitor (LC)‐quadrature voltage controlled oscillator (QVCO) covering WiMAX frequency range in 0.18‐μm deep submicron CMOS technology.

A pMOS based‐SIPC LC‐QVCO topology is realized with the center frequency of 2.58 GHz. On chip spiral inductor is integrated with substantial quality factor, Q coupled with underlying pattern ground shield (PGS) shielding. An enhanced tuning range is achieved by integrating the diode connected MOS‐based varactors. The CMOS‐based autonomous SIPC LC‐QVCO circuit was characterized for its output phase noise, tuning range and power spectrum response via wafer probing, utilizing a signal source analyzer (Agilent E5052 A).

A quadrature oscillator catering to the needs of local oscillator (LO) generation covering the frequency range of WiMAX is realized. The parallel coupled architecture adapts direct source coupling, bypassing the LC resonator tank and relaxes the close in phase noise up‐conversion. The design consumes 2.19 mm² of active chip area and measures a phase noise of −114.34 dBc/Hz at 1 MHz of offset frequency with 2.67 GHz of output frequency at 0.9 V of input tuning voltage. The corresponding output power measures to be −10.1 dBm, well suited for mixer hard switching. The design is realized in one poly, six metal 0.18‐μm standard CMOS technology.

Owing to convergence discrepancy in the analysis, a diode‐connected MOS varactor is adapted in contrary to the accumulation mode MOS varactors with superior tuning range.

The designed SIPC LC‐QVCO is of need in the generation of low‐phase noise, highly matched quadrature LO generation covering the WiMAX frequency range. The adapted parallel coupling also relaxes the voltage headroom limitation.

This paper shows how a fully integrated CMOS‐based SIPC LC‐QVCO architecture is adapted with low‐output phase noise and low voltage headroom consumption covering the WiMAX frequency range.