Search

Wear debris analysis (WDA) enables the provision of essential information towards the monitoring of machine fault diagnosis and the analysis of wear mechanism. However, this experience-based technology has not yet been automated for the identification of similar particle types due to the small number of samples and highly dispersed features. To address this problem, a knowledge-guided convolutional neural network model is developed to focus on two representative severe wear particles: fatigue and severe sliding particles that have highly similar contours but weakly discriminative surfaces. The height images of particle surfaces are adopted as the initial objective. Characterized by typical particle features, the empirical WDA knowledge is represented into the feature-marked images, and further automatically learned by a U-Net-based knowledge extraction network. By weighting with the U-Net output, a knowledge-guided particle classification network is constructed to identify similar particles under a small number of samples. With this methodology, the empirical WDA knowledge is transferred to guide the classification network for locating the discriminative features in particle height images. Thirty sets of fatigue and severe sliding particles are acquired from wear tests as the training and testing samples. For verification, the network kernel is visualized to trace the particle feature propagation in the classification. Experimental results reveal that the proposed method can accurately identify fault particles that are acquired from wear tests.

Lubricating oil, which carries information about machine’s health condition, is of great importance to the performance of machines in the full life cycle. The main purpose of oil deterioration modeling and its remaining useful life prediction is to determine the exact time that the lubricating oil has degraded and it is no longer able to maintain its functions. Generally, lubricating oil deterioration can be partially detected by condition monitoring based on wear debris analysis, and thus can be categorized into three states. In our paper, vector data, which contain wear debris concentration and carry information about the state of lubricating oil, are obtained by an on-line visual ferrograph sensor from a four-ball tester at regular sampling epochs. The oil’s state process is described by a hidden semi-Markov model, and its sojourn times in each state are assumed to be Erlang distributed. A vector autoregressive method based on time series modeling is presented to obtain residual observations, which are regarded as the observable process of oil information in the hidden semi-Markov model framework. The unknown parameters of the hidden semi-Markov model are then estimated by using expectation-maximization algorithm. Afterward, a Bayesian updating approach is presented to derive the explicit formulas of the conditional reliability and mean residual life. To validate the proposed approach, a real case study of lubricating oil deterioration is demonstrated and a comparison with the hidden Markov model is given to illustrate the effectiveness of the new developed remaining useful life prediction approach for lubricating oil.

Skidding in rolling bearings often causes unexpected surface wear and early failures. Although vibration monitoring is widely used for bearing fault diagnosis, it is much less developed for wear analysis. This paper presents an investigation into characterizing the surface wear of a simplified sliding–rolling contact using friction-induced vibration features. The friction vibration mechanism under a rough sliding–rolling contact is explored by a mixed elastohydrodynamic lubrication model. It is found that the friction coefficient has a positive correlation with the surface roughness, which indicates that the friction behaviour can be used to track the wear state under the sliding–rolling contact. Furthermore, the vibration excited by different rough surfaces is studied experimentally on a roller–ring test rig. The friction-induced vibration signal is extracted and a feature parameter ( K) is defined for quantitative wear characterization. Results show that the friction-induced vibration can well reflect the surface wear under the sliding–rolling contact. Compared with traditional time-domain parameters, the proposed parameter has a better linear relationship with the surface roughness.

Since wear particles usually contain valuable information about lubricant and wear condition of lubricated components, wear debris analysis is widely used to monitor machine/component wear. Current literature reports about the importance and necessity of 3-D surface characterization of wear particles as opposed to 2-D characterization. It may be borne in mind that traditional 3-D analysis has been a synonym only for local surface morphologies for stationary particles. This results in large errors when irregular particles are under observation. A new 3-D imaging methodology is proposed to reconstruct multiview 3-D surfaces for a moving particle whereby the target particle is passed through a microchannel with rolling motion, and recorded via a digital microscope. The multiple moving particles are tracked based on Kalman filter to obtain different-view images. Sparse and dense reconstruction of the particle surfaces are enabled by these images using Structure from Motion (SfM) and Shape from Shading (SfS) methodologies, respectively. The method was verified using real particles and evaluated by the results of laser scanning confocal microscopy. The proposed method is able to reconstruct wear particles under various perspectives, and the errors from the characterization parameters of the areal are less than 20 $\%$ .

Lubricating oil carries important health information of operating machines, and oil replacement scheme is crucial for ensuring machine health, reducing operation costs, and improving machine availability. However, few works have been done on the determination of reasonable replacement time for lubricating oil in the industry. Therefore, the main motivation of this article is to present a replacement scheme based on the Bayesian approach to detect and prevent the potential failures of lubricating oil. A three-state statistical model based on the hidden Markov chain is applied to characterize oil deterioration, which contains partially observable healthy and unhealthy states, and an observable failure state. A novel Bayesian control scheme for oil replacement based on the hidden stochastic process is proposed under the objective of long-term expected average availability maximization. A computational algorithm in a semi-Markov decision process is presented to estimate the optimal decision variable of the Bayesian control chart. The 2-D oil data based on wear debris collected at regular time epochs from a four-ball tester are adopted to validate the effectiveness of the proposed replacement approach. Given comparisons with the age-based scheme and the failure-based scheme, the proposed Bayesian replacement approach for lubricating oil is demonstrated to achieve better fault detection performance and the longer average availability.

Roller bearings support heavy loads by riding on an ultra-thin oil film (between the roller and raceway), the thickness of which is critical as it reflects the lubrication performance. Ultrasonic interfacial reflection, which facilitates the non-destructive measurement of oil-film thickness, has been widely studied. However, insufficient spatial resolution around the rolling line contact zone remains a barrier despite the use of miniature piezoelectric transducers. In this study, a finite-element-aided method is utilized to simulate wave propagation through a three-layered structure of roller-oil-raceway under elastohydrodynamic lubrication (EHL) with nonlinear characteristics of the i) deformed curvature of the cylindrical roller and ii) nonuniform distribution of the fluid bulk modulus along the circumference of the oil layer being considered. A load and speed-dependent look-up table is then developed to establish an accurate relationship between the overall reflection coefficient (directly measured by an embedded ultrasonic transducer) and objective variable of the central oil-film thickness. The proposed finite-element-aided method is verified experimentally in a roller-raceway test rig with the ultrasonically measured oil-film thickness corresponding to the values calculated using the EHL theory.

For the purpose of automatic wear debris classification, a hybrid convolution neural network (CNN) is used with transfer learning (TL) and support vector machine (SVM) to identify four types of wear debris including cutting, sphere, fatigue and severe sliding particles. Experimental results indicate that image features extracted from the CNN is more distinguishable than that acquired from the local binary pattern, the histogram of oriented gradients and the color-based methods. The classification accuracy and efficiency of the proposed hybrid CNN with TL and SVM is also higher than that of the CNN, the CNN with TL, and the CNN with SVM. This work provides an effective solution for automatic wear debris identification applicable for machine wear mechanism analysis.

Lubricating oil contains a lot of tribological information of the machine and plays an important role in machine health. Oil degrades with serving time and causes severe wear afterwards, which is a complex dynamic process, and difficult to be accurately described by a single property. Therefore, the main purpose of deterioration prediction is to estimate the remaining useful life that the oil can still fulfill its functions by analyzing oil condition monitoring data. With a large amount of oil condition monitoring data collected, a vector autoregressive model is applied to the original oil data to describe the dynamic deterioration process. Then dynamic principal component analysis, an effective dimensionality reduction method, is employed to obtain the principal components capturing the most information of the oil data. The proportional hazards model is then built to calculate the failure risk of the lubricating oil based on the condition monitoring information, where its baseline function represents the aging process assuming to follow the Weibull distribution and its positive link function represents the influence of covariates (the principal components) on the failure risk. Finally, the remaining useful life prediction of lubricating oil can be obtained by explicit formulas of the characteristics such as the conditional reliability function and the mean residual life function. This work provides an approach to assess the health of lubricating oil, and a guidance for oil maintenance strategy.

Rolling element bearings are commonly used in rotatory machines and their operation conditions need to be monitored to prevent catastrophic failures. This research aims at developing an effective online monitoring method to analyse wear severity and wear mechanisms of bearings. For this purpose, morphological features of wear debris from bearings, including quantity, colour, size and shape, are extracted from videos of moving particles carried in lubrication oil. Moving particles are detected and tracked based on the Gaussian background mixture model and the blob detection algorithm, and the target particles are separated from the image background by background subtraction. Then particle shape and dimensional features both in two- and three-dimensions are extracted from multiple images captured from different views. At the same time, the numbers of moving particles are determined based on the tracking results. The developed techniques for online particle feature extraction are applied to a rolling element bearing test rig. The particle quantity is used to indicate the trend of wear state evolution, while the colour, size and shape features of wear debris are used to classify particles into different types for wear mechanism analysis. The relationship between wear mechanisms and the trend of wear states in the time domain is established. Based on the gathered information and wear analyses, a comprehensive characterisation is obtained for online monitoring the wear state evolution as well as evaluating the wear severity and wear modes. The proposed method is able to provide wear mechanism information for root cause analysis and thus enhance the capabilities of existing online wear debris monitoring techniques.

The principle of resonance is often applied in the ultrasonic measurement of the thickness of lubricant films. The information data relating to the thickness of the lubricant film involves the acquisition of the resonance frequency of a continuous wave with the application of a continuum model. However, ultrasonic signals are often times, generated by piezoelectric elements but these exhibit some variations from the continuous wave because they are dispersed pulses that have a wide range of frequency bandwidths. In this paper, the authors have applied the principle of wave superposition for the measurement of lubricant film thickness. This principle exhibits the capability to generate the resonant mechanisms of the pulse waves. The implemented theoretical analysis in this research work, depicted that the principle of wave superposition may demonstrate more applicability than the continuum model under the condition of the partial inclusion of the reflected pulse waves. The application of this principle facilitated the analysis of the resonant mechanisms of the pulse wave from the phase variations of the reflected echoes. It followed the further investigations into the influence of both the number of the reflected echoes and the materials of the solid layers on the film resonance method. The results of these investigations were validated using experimental results.

Rolling bearing performance often degrades due to extra wear introduced by sliding-rolling contacts. Thus, it is vital to monitor the evolution of such wear process through investigating the worn surface. Compared with traditional two-dimensional (2-D) methods, three-dimensional (3-D) measurements of worn surfaces can provide more information. Due to the lack of in-situ 3-D measurement techniques and the scale-dependency of characterization parameters, it remains a challenge to examine the wear evolution of sliding-rolling contact using 3-D surface topography features. A characterization framework is here developed for inspecting worn surface topography variations under sliding-rolling contact, by combing 3-D surface reconstruction and computed fractal dimension. The worn surface is firstly imaged by an in-situ microscope. Next, a virtual 3-D surface is obtained from 2-D images via topography reconstruction. Then, the fractal dimension of worn surfaces is calculated to characterize the wear state with 3-D root-mean-square. A wear test is carried out on a roller-ring test rig to verify the proposed method. Results indicate that the proposed 3-D characterization performance is comparable to laser scanning confocal microscopy (LSCM) and allows rapid description of the wear process.

Wear debris analysis is used for machine condition monitoring because it is capable of identifying wear related faults in machinery components. In particular, wear mechanisms can be explored based on debris shape and texture features. As current wear monitoring practices prefer rapid data interpretation, on-line ferrograph is favored where debris images are collected and processed on-site with an imaging apparatus. However, such images are often blurred due to lubricant contamination and limited optical field depth. This drawback makes the subsequent investigation of wear debris features a challenging task. To address this issue, a restoration method is developed to reduce the influence of out-of-focus blurring in on-line ferrograph images. Firstly, in order to model the out-of-focus blurring process, a degradation model is constructed with a convolutional neural network. Different from general deep learning structures, larger convolutional kernels are embedded in the network to more comprehensively characterize the blurring process. Next, training samples of different types of debris are collected in the laboratory. The neural network structure then is optimized to minimize the difference between restored images and their corresponding ground truths. The final restoration is conducted based on the trained network via a pixel-wise regression process. To evaluate the performance of the developed method, experiments are carried out with debris images collected from a gear-box test rig. Results have demonstrated that: (1) the proposed restoration strategy allows robust extractions of debris features in greater detail; (2) the developed method is more computationally efficient than traditional deblurring techniques, which enables it to be applicable in on-line machine health monitoring.

Mechanism-based wear debris classification (WDC) is important for root cause analysis and prediction of wear related faults. Compared to manual classifications, automatic WDC is more efficient and often more reliable for a wide range of industrial applications. However, existing methods unavoidably encounter some difficulties when dealing with those wear particles with highly geometric similarity, especially for fatigue particles and severe sliding particles. To meet the requirement for automatic WDC, an integrated, automated method for identifying typical wear debris is proposed with a two-level classification procedure. By referring to the traditional ferrography – a widely used wear particle imaging and analysis technique, the first-level classification is performed by a general back-propagation (BP) neural network with selected particle's morphological features. By doing this, three types of wear particles including rubbing, cutting, and spherical particles can be determined. In the second-level classification, a deep learning model of a 6-layer convolution neural network (CNN) is adopted to identify fatigue particles and severe sliding particles by analyzing their very slight surface details in pixel-level. The method is tested with over 100 images of real particles generated from an extruder machine in a petrochemical plant and identified by a ferrograph specialist. A high recognition rate of over 80% is achieved for the three types including rubbing, cutting, and spherical particles with the first procedure. Further, the identification rates are 85.7% and 80% for fatigue particles and severe sliding particles, respectively, which is distinctly improved from the reported values (they are 45.5% and 36.4%, respectively) of other intelligent methods.

Ferrography has emerged as a significant candidate for the provision of relevant information for the determination of the status of machine wear. However, this conventional methodology provides only marginal results due to its inability to provide 3-dimensinal (3D) surface information. The authors of this paper have developed a methodology based on photometric-stereo towards the enhancement of the capabilities of ferrography. This enhanced and innovative methodology consists of three main components, the multi-illumination image acquisition, the wear particle extraction, and the 3D surface reconstruction. The methodology ensures the reliable and efficient extraction of the wear particles surface topographies for further feature-based wear particle identification. The performance of this methodology has been compared with results observed from the laser scanning confocal microscopy. The outcome of this comparison has depicted that the methodology involving this new low-cost ferrography system exhibits very high accuracy for the 3D surface feature extraction of wear particles.

As a significant technique in machine condition monitoring, wear debris analysis enables investigation of machine running condition with respect to debris features including size, quantity and morphology. In particular, being capable of providing more comprehensive morphological information, three-dimensional debris features are regarded essential and often acquired through a video-based debris imaging process. However, debris images captured often suffer degradation due to debris motion blur and lubrication contamination, that hinder reliable debris features extraction. To address the image degradation issue, a new method of wear debris image restoration is developed to reduce the effect of blur. In order to avoid the expensive computation involved in blind deconvolution methods, the debris image was restored using localized boundary features. Based on the fact that debris area and background area indicate distinctive brightness, a step edge model is applied to describe the original debris boundary. Localized kernels on each side of debris are then determined. Next, restorations are conducted with the estimated kernels to produce sharper debris profiles with respect to different motion features. Final restoration is conducted by fusing the restored profiles according to the maximum local sharpness. Experimental results have demonstrated that this method allows reliable features extraction from blurred image, improving the robustness of video based wear debris analysis.

The ultrasonic reflection from a lubricated interface has been widely analyzed to measure fluid film thickness, with different algorithms being applied to overcome measurement accuracy and resolution issues. Existing algorithms use either the amplitude or the phase angle of the ultrasonic interfacial reflection. In this paper, a new algorithm (named the “exact model – complex”) that simultaneously utilizes both the amplitude and the phase of the complex ultrasonic reflection coefficient is proposed and mathematically derived. General procedures for theoretical analysis in terms of measurement accuracy and uncertainty are proposed and applied to the new algorithm, the beneficial features of which (as compared to other existing algorithms) can be summarized as: 1) a direct calculation, instead of an iterative approximation, 2) guaranteed maximum measurement accuracy, and 3) acceptable measurement uncertainty. None of the existing methods have showed this combination of benefits. Moreover, two groups of raw data from previous experimental studies are utilized to further validate the practical feasibility of the new algorithm. Overall, the proposed “exact model – complex” algorithm fully exploits the potential of ultrasonic reflection for oil film thickness measurement, with an accurate and a convenient calculation suited to practical implementation.

Due to insufficient monitoring data, the reliability and accuracy of oil condition predictions are not guaranteed. Data-driven models provide data augmentation with small samples to solve this problem. However, the absence of degradation mechanisms would introduce unpredictable uncertainties in a long-term prediction. To address this, a data augmentation method is proposed for improved prediction by integrating degradation mechanisms and monitoring data. Primarily, a degradation model is established considering the degradation mechanisms. The model parameters are estimated with the time-vary probability distribution of the monitoring data. Therefore, the evidential variables are used to describe parameters with small samples. Then, the detailed parameters are estimated by integrating small-sample and prior parameters. With this well-trained model, the augmented data can be obtained with a particle filtering method for prediction. For validation, both the sparse and truncated samples from real-world monitoring are used to demonstrate the superiority of the proposed method. The high predicted accuracy demonstrates that the reliability of oil condition prediction can be guaranteed even with small samples.

Ferrograph analysis has been adopted over decades for determining the root causes of on-going wear faults. After decades of manual operation, this traditional technique is being driven by intelligent algorithms for automatic identification of wear debris. However, the accuracy and robustness of this algorithm remain marginalized when applied in industries due to various types and color blurry of particles. To address this issue, this paper introduces an automatic ferrograph analysis model with a segmentation method and a two-level classification strategy. In order to obtain wear particles from the color ferrograph image, an adaptive Otsu threshold is adopted in three channel images to solve the color blurry in particle segmentation. By grouping particle parameters into shape and morphology ones, a two-level identification strategy is proposed. The first one is to classify rubbing, cutting, and spherical particles, referring to the fuzzy approach degree of shape parameters. In the second level, the shape-close particles are classified with imperceptible textures and back propagation neural network (BPNN). These objective parameters are constructed by applying the principal component analysis into seven texture features and inputted into a BPNN-based model to classify fatigue and severe sliding particles. In order to train the BPNN, more than 100 ferrograph images are sampled together, whereby standard ferrograph analysis is performed on the particle identification. The performance of the identification exhibits an accuracy exceeding 90% for rubbing, cutting, and spherical particles, whereas about 80% accuracy has been registered for both severe sliding and fatigue particles.

Ultrasonic method is quite promising for oil film thickness measurement in industry, while there is normally a dead zone for one ultrasonic sensor with a special center frequency when measuring the oil film thickness by the traditional reflection coefficient amplitude. In this paper, an ultrasonic measurement method for full range of oil film thickness was investigated. The theoretical relationship between the oil film thickness and the reflection coefficient phase was firstly built up and the reflection coefficient phase was found to be able to measure the oil film thickness in the dead zone. Then the reflection coefficient amplitude and phase were combined to measure the oil film thickness in the full range. A high-precision calibrated rig, which could form a series of known film thicknesses oil layers, was set up and the performance of this method was shown to work well. This method is significant for online oil film thickness monitoring in industry.

Micro-cutting is a material removal mechanism with cutting debris generation, where the condition monitoring of the mechanism is important in a wear process. As a useful technique, wear debris analysis has been widely adopted for identifying the wear mechanisms in a running machine. However, there is no corresponding relationship between wear particle features and wear conditions. This paper investigates the generation mechanism of cutting debris by simulating a micro-cutting process. In particular, this study is to establish a quantitative relationship between their morphologies and cutting conditions. A three-dimensional model with a rigid pyramid sliding on the surface of #45 steel has been developed. The deformation and failure criteria of the steel are the Johnson–Cook and shear failure model, respectively. The conditions for producing cutting wear debris are studied and then the morphological features of wear debris are extracted. The main findings are as follows: (1) the critical conditions for cutting wear particle generation is jointly determined by the attacking angle and the cutting depth; (2) the width and curvature of cutting wear debris are mainly correlated with the normal load, which determines the indentation depth of the pyramid; (3) the curvature of cutting wear debris depends mainly on the sliding velocity. The understanding of the relationship between the cutting wear conditions and the morphologies of wear debris is useful for supporting debris-based wear monitoring.

A rolling bearing is an essential component of a rotating mechanical transmission system. Its performance and quality directly affects the life and reliability of machinery. Bearings’ performance and reliability need high requirements because of a more complex and poor working conditions of bearings. A bearing with high reliability reduces equipment operation accidents and equipment maintenance costs and achieves condition-based maintenance. First in this paper, the development of technology of the main individual physical condition monitoring and fault diagnosis of rolling bearings are introduced, then the fault diagnosis technology of multi-sensors information fusion is introduced, and finally, the advantages, disadvantages, and trends developed in the future of the detection main individual physics technology and multi-sensors information fusion technology are summarized. This paper is expected to provide the necessary basis for the follow-up study of the fault diagnosis of rolling bearings and a foundational knowledge for researchers about rolling bearings.

In real-time lubricant monitoring operation, the wear’s generation inside the flow lubricant is identified as the lubricant’s performance indicator. The online visual ferrograph (OLVF) based on magnetic deposition and image analysis could detect the wear during the running machine process. However, the time gap during OLVF’s data processing makes the corrective actions of abnormal high wear rate are not based on time-sensitive data. Therefore, this study proposes a data-driven approach based on Gaussian process regression approximation to analyze the acquired data and thus create new knowledge on the understanding of real-time wear generation. Moreover, running-in processes with high seasonality (abnormal) data are being investigated to give insight into the initial process’s phenomena. In this study, the combined temperature-controlled four-ball tribometer with an OLVF is employed to acquire debris data inside the flow channel, and the coefficient of friction (COF) represents the wear trend under varying working conditions. Results show that the experimental setup and the approach can be used to investigate running-in real-time wear generation.

The oil film thickness in an oil-lubricated tribo-pair can be measured using reflected ultrasonic waves and various transformation models. Conventionally, this approach requires the incident signal to be calibrated using off-line methods prior to testing, and this limits the on-line measurement of oil film thickness in sliding components such as journal bearings. To enable on-line calibration, we propose a method of reconstructing the incident signal from the easily obtained reflected signal. This involves analyzing the amplitude and phase spectrum of the reflection coefficient to reconstruct the incident signal. More specifically, the following main findings of the amplitude and phase of reflection coefficient at the resonance frequency are reported. 1) There is a zero-crossing at the resonance frequency, and therefore the phases of the incident and reflected signal are the same. 2) If part of the reflected signal is included for calculation, the frequency of the extreme point in the amplitude spectrum of the reflected signal is equal to the resonance frequency only when the extreme point phenomenon occurs at the center frequency of the transducer. At other positions, the frequency of the minimum amplitude in the amplitude spectrum of the reflected signal is not equal to the resonance frequency. Utilizing these relationships, the phase and amplitude of the incident signal can be accurately reconstructed by following the proposed method, provided the thickness of the oil film between the tribo-pairs can be widely ranged to cover both the blind and the resonance zones. Correspondingly, a practical schedule for the on-line reconstruction of the incident signal is proposed, which includes an operation to adjust the oil film thickness within the blind and the resonance zone. This method is validated on a test rig by comparing it with the traditional off-line methods.

Ferrograph-based wear debris analysis (WDA) provides essential information for the root cause analysis of wear failures. However, this technique has been hampered as an intelligent approach by two problems: lack of fault particle samples and conflicts among redundant features. To address this issue, a knowledge-embedded double-CNN model is proposed to identify two representative fault particles: fatigue and severe sliding particles, by using the 3D topographical information. First, a non-parametric CNN network model is constructed with a 2D height map of 3D particle surfaces. The convolution kernels are evaluated to determine identification errors due to the small number of samples. In the refinement stage, four efficient kernels are extracted via the image similarity with the labeled images, which are created based on the physical wear mechanism of the two types of particles. Furthermore, an improved CNN network with six parallel convolution layers is established to handle the feature maps of these kernels for objective particle identification. The proposed model is trained by 20 groups of fault particles and further verified with 10 groups of shuffled particle samples and the network visualization. Validation experiments reveal that discriminative features have contributed to accurately identify all tested fatigue and severe sliding particles.

Due to non-destructive testing characteristics, ultrasonic-based measurements are regarded as potential strategies in real-time monitoring of varied lubricant film thickness for tribological systems. Different theoretical models have been recently developed to calculate the film thickness from ultrasonic echo waves. However, the temperature influence on ultrasonic systems (for example, the acoustic parameters of materials and piezoelectric elements), which is non-negligible in the continuously running equipment, especially for heavy-loaded lubricated systems, has scarcely been considered. In this paper, the sensitivity of different parameters to the temperature variation is investigated in classical ultrasonic models. With the theoretical error analysis, a comprehensive temperature compensation strategy that considering the acoustic speed, material density, and reference signal, is proposed and integrated into the ultrasonic measurement algorithms. It is worth noting that the amplitude attenuation, waveform expansion, and signal time shift are considered in the compensation of the reference signal. Experimental verification is finally carried out in a calibrated rig with swept lubricant film thickness and different ambient temperatures. Test results suggest that the ultrasonic measurements with the proposed strategy effectively compensates the temperature influence and enables accurate calculations of lubricant film thickness under varying temperatures.

High boron Fe-based alloys, possessing superior wear-resistant performance, have always been restricted to be applied in impacting conditions by the poor toughness. In the present work, Fe-3.0B-0.3C alloy has been toughened by introducing Cr element. The evolutions of the solidification process, microstructure and the mechanical properties have been systematically investigated by means of the scanning electron microscope (SEM), transmission electron microscope (TEM), differential scanning calorimetry (DSC) and nano-indentation. The experimental results show that Cr addition affects the solidification process so as to result in the microstructure evolution of Fe2B hard phase. Cr atoms are inclined to aggregate in Fe2B grain to improve its toughness without sacrificing the hardness. The optimal fracture toughness of Fe-3.0B-0.3C alloy can be improved by nearly 38.5%. Through the analysis of crack's propagation and fractography, the toughening mechanisms have been revealed to be the coupling actions of the improved toughness and microstructure evolution of Fe2B hard phase.

Reliable operation of machinery is very desirable in engineering. To achieve this objective, the assessment of the lubrication oil state is necessary. However, due to the unpredictable variations, uncertainty detection and handling in the oil state has been a bottleneck in practice. A solution strategy is proposed in this paper that integrates information from the monitoring data and expert knowledge. On the other hand, since insufficient data and limited knowledge, two types of uncertainty are present, namely, aleatory and epistemic uncertainty. To handle these uncertainties, an integrated model with a three-layer structure is constructed that incorporates both expert knowledge and data. First, for the detection of stochastic data variation, the initial connection among the layers is assigned by membership probabilities as the characterization evidence. Second, the oil state that produces a unified output with various pieces of evidence is determined by evidential reasoning with knowledge-based rules. Third, to provide consistent monitoring adaptively, a knowledge-integrated neural network is established for determining the initial parameters from measurements. The effectiveness of the proposed model is demonstrated using both simulated and real-world data from industrial vehicles.

Frictional behaviour of mixed Elasto-hydrodynamic lubrication (EHL) arises from the coupling of the lubricant fluid and asperity interaction frictions. Due to the difficulties in modelling asperity interaction friction, existing approaches often use a constant friction coefficient obtained in boundary lubrication to approach the asperity interaction friction coefficient in mixed EHL. In this study, the asperity interaction friction is, for the first time, considered to result from either the boundary film friction or solid-to-solid ploughing and adhesion friction depending on the local contact and deformation conditions. The friction of mixed EHL was predicted by the combination result of lubricants fluid, boundary film, and solid-to-solid frictions. This development provides an alternative and cost effective method to estimate friction coefficient in mixed EHL.

Purpose For oil film thickness measurement using ultrasonic spring model, obtaining the isolated reflection from the oil film layer is the key point. While for oil film thickness measurement in thrust bearings with thin liner, the reflection from the substrate-Babbitt interface will overlap with the reflection from the oil film layer. This overlapping will render the ultrasonic spring model invalid. To obtain the isolated reflected signal from the oil film layer accurately, an adaptive method was developed to recover the overlapping echoes. Design/methodology/approach A genetic-algorithm-based support matching pursuit (GA-based SMP) was developed to provide the optimal echo number and initial parameters guesses automatically and efficiently. Then, the traditional expectation maximization (EM) model was used to fine tune the accurate results. Findings The developed method was tested using both simulated echoes and the overlapping echoes encountered in the ultrasonic oil film thickness measurement of thrust bearings. The results demonstrated that the developed method performed well on recovering overlapping echoes adaptively. Originality/value The work shows an adaptive method to recover the ultrasonic overlapping echoes. When used in ultrasonic oil film thickness measurement, it can help extend the application of traditional ultrasonic spring model to objects with four or more layers.