Highly enhanced pump power density inevitably results in a profound rise in pump temperature, which seriously influences both power loss and service performance. Heat loss analysis is an important part of analyzing the mechanical and cooling efficiency of a 2D piston pump. This paper focuses on heat loss analysis of this pump’s transmission. Firstly, theoretical and experimental studies are carried out on the thermal–hydraulic model to investigate the heat loss of the pump’s transmission. A pump test rig is developed and thermal experiments are conducted, from 1000 rpm to 6000 rpm. Furthermore, its transient thermal simulation model is implemented with Ansys software to capture the pump’s thermal status. The test convective heat transfer coefficients and temperature data are set in the model, and the simulation results are mutually validated with the experimental ones. Finally, the transmission’s heat loss is compared with its reference churning loss formula. The distribution of the transient heat loss is 49.66% into the end cap, 27.74% into the cylinder head, 13.30% into the inner cylinder, and 9.30% into the oil. The heat loss simulation results agree with the churning loss below 4000 rpm; therefore, the transmission thermal model is accurate and efficient. Full article

Four-wheel independently driven electric vehicles are prone to rollover when driving at high speeds on high-adhesion roads and to sideslip on low-adhesion roads, increasing the risks associated with such vehicles. To solve this problem, this study proposes a path tracking and stability-integrated controller based on a model predictive control algorithm. First, a vehicle planar dynamics model and a roll dynamics model are established, and the lateral velocity, yaw rate, roll angle, and roll angle velocity of the vehicle are estimated based on an unscented Kalman filter. The lateral stiffness of the tires is estimated online according to the real-time feedback state of the vehicle. Then, the path tracking controller, roll stability controller, and lateral stability controller are designed. An integrated control strategy is designed for the path tracking and stability, and the conditions and coordination strategies for the vehicle roll and lateral stability state in the path tracking are studied. The simulation results show that the proposed algorithm can effectively limit the lateral load transfer rate on high-adhesion roads and the sideslip angle on low-adhesion roads at high speeds. Hence, the driving stability of the vehicle under different road adhesion coefficients can be ensured and the path tracking performance can be improved. Full article

Resilient manufacturing is a vision in the Industry 5.0 blueprint for satisfying sustainable development goals under pandemics or the rising individualized product needs. A resilient manufacturing strategy based on the Industrial Internet of Things (IIoT) networks plays an essential role in facilitating production and supply chain recovery. IIoT contains confidential data and private information, and many security issues arise through vulnerabilities in the infrastructure. The traditional centralized IIoT framework is not only of high cost for system configuration but also vulnerable to cyber-attacks and single-point failure, which is not suitable for achieving the resilient manufacturing vision in Industry 5.0. Recently, researchers are seeking a secure solution of middleware based on blockchain technology integration for decentralized IIoT, which can effectively protect the consistency, integrity, and availability of IIoT data by utilizing the auditing and tamper-proof features of the blockchain. This paper presented a review of secure blockchain middleware for decentralized IIoT towards Industry 5.0. Firstly, the security issues of conventional IIoT solutions and the advantages of blockchain middleware are analyzed. Secondly, an architecture of secure blockchain middleware for decentralized IIoT is proposed. Finally, enabling technologies, challenges, and future directions are reviewed. The innovation of this paper is to study and discuss the distributed blockchain middleware, investigating its ability to eliminate the risk of a single point of failure via a distributed feature in the context of resilient manufacturing in Industry 5.0 and to solve the security issues from traditional centralized IIoT. Also, the four-layer architecture of blockchain middleware presented based on the IIoT application framework is a novel aspect of this review. It is expected that the paper lays a solid foundation for making IIoT blockchain middleware a new venue for Industry 5.0 research. Full article

Wire rope manufacturing is an old industry that maintains its place in the market due to the need for products with specific characteristics in different sectors. The necessity for modernization and performance improvement in this industry, where there is still a high amount of labor dedicated to internal logistics operations, led to the development of a new technology method, to overcome uncertainties related to human behaviour and fatigue. The removal of successive yarn coils from a twisting and winding machine, as well as cutting the yarn and connecting the other end to the shaft in order to proceed with the process, constitutes the main problem. As such, a mobile automatic system was created for this process, due to its automation potential, with a project considering the design of a 3D model. This novel robotic manipulator increased the useful production time and decreased the winding coil removal cycle time, resulting in a more competitive, fully automated product with the same quality. This system has led to better productivity and reliability of the manufacturing process, eliminating manual labor and its cost, as in previously developed works in other industries. Full article

The manipulation of complex robotics, which is in general high-dimensional continuous control without an accurate dynamic model, summons studies and applications of reinforcement learning (RL) algorithms. Typically, RL learns with the objective of maximizing the accumulated rewards from interactions with the environment. In reality, external rewards are not trivial, which depend on either expert knowledge or domain priors. Recent advances on hindsight experience replay (HER) instead enable a robot to learn from the automatically generated sparse and binary rewards, indicating whether it reaches the desired goals or pseudo goals. However, HER inevitably introduces hindsight bias that skews the optimal control since the replays against the achieved pseudo goals may often differ from the exploration of the desired goals. To tackle the problem, we analyze the skewed objective and induce the decayed hindsight (DH), which enables consistent multi-goal experience replay via countering the bias between exploration and hindsight replay. We implement DH for goal-conditioned RL both in online and offline settings. Experiments on online robotic control tasks demonstrate that DH achieves the best average performance and is competitive with state-of-the-art replay strategies. Experiments on offline robotic control tasks show that DH substantially improves the ability to extract near-optimal policies from offline datasets. Full article

The aim of this paper is to study the influence of non-uniform suction flow on the transient characteristics of a vertical axial-flow pump device. The unsteady calculation is employed to forecast the unstable flow structure with three inlet deflection angles $\alpha$, and the calculation accuracy under uniform inlet flow is verified by the external characteristic test. The results depict that a promotion in the $\alpha$ will increase the head and shaft power and thus improve the stress and fatigue failure risk of the impeller. At the impeller inlet, the pressure pulsation intensity (PPI) with $\alpha$ = 40° is lower than that with $\alpha$ = 0° caused by a decline in the axial velocity. The dominant frequency of the unsteady pressure signal is the blade-passing frequency (BPF), and the dominant frequency amplitude rises with the increase in $\alpha$ due to the improvement of the pre-rotation impact intensity. At the guide vanes inlet, the dominant frequency of the unsteady pressure signal at the guide vane inlet is also the blade-passing frequency. An improvement in $\alpha$ magnifies the angle between the trailing edge jet of the impeller and the leading edge of the guide vanes under 0.8Q_des and 1.0Q_des, while it diminishes the angle under 1.2Q_des. Thus, the PPI and dominant frequency amplitude with $\alpha$ = 40° are higher than that with $\alpha$ = 0° under 0.8Q_des and 1.0Q_des, but these are lower than that with $\alpha$ = 0° under 1.2Q_des. Full article

Wearable electronics have showed their profound impact in military, sports, medical and other fields, but their large-scale applications are still limited due to high manufacturing costs. As an advanced micro-fabrication process, laser processing technology has the advantages of high speed, high flexibility, strong controllability, environmental protection and non-contact in preparing micro-nano structures of wearable electronics. In this paper, a 355 nm ultraviolet laser was used to pattern the copper foil pasted on the flexible substrate, and the interconnection electrodes and wires were constructed. A processing method of multi-parallel line laser cutting and high-speed laser scanning is proposed to separate and assist in peeling off excess copper foil. The process parameters are optimized. A stretchable 3 × 3 light-emitting diode (LED) array was prepared and its performance was tested. The results showed that the LED array can work normally under the conditions of folding, bending and stretching, and the stretch rate can reach more than 50%. A stretchable temperature measurement circuit that can be attached to a curved surface was further fabricated, which proves the feasibility of this process in the fabrication of small-scale flexible wearable electronic devices. Requiring no wet etching or masking process, the proposed process is an efficient, simple and low-cost method for the fabrication of stretchable circuits. Full article

Eye tracking is an important technique for realizing safe and efficient human–machine interaction. This study proposes a facial-based eye tracking system that only relies on a non-intrusive, low-cost web camera by leveraging a data-driven approach. To address the challenge of rapid deployment to a new scenario and reduce the workload of the data collection, this study proposes an efficient transfer learning approach that includes a novel affine layer to bridge the gap between the source domain and the target domain to improve the transfer learning performance. Furthermore, a calibration technique is also introduced in this study for model performance optimization. To verify the proposed approach, a series of comparative experiments are conducted on a designed experimental platform to evaluate the effects of various transfer learning strategies, the proposed affine layer module, and the calibration technique. The experiment results showed that the proposed affine layer can improve the model’s performance by $7\%$ (without calibration) and $4\%$ (with calibration), and the proposed approach can achieve state-of-the-art performance when compared to the others. Full article

In view of the increasingly stringent emission regulations, the automotive sector needs considerable support from the development of robust and reliable engine and aftertreatment models. Accurate reproduction of engine-out and tailpipe pollutants plays a crucial role in complying with these legislations. Given the difficulty in characterizing some critical phenomena, frequently caused by strong dynamics and related to experimental uncertainties, communication between several calibrated and reliable models is mandatory. This is certainly valid for powertrains that will be powered with alternative gas fuels such as natural gas, bio-methane and hydrogen in the future. This paper describes a methodology to co-simulate a 1D CNG HD 6-cyl engine model and a 1D quasi-steady Three-Way Catalyst model in a global framework for high-fidelity virtual prototyping of the vehicle system. Through the implementation of a dedicated control logic in MATLAB/Simulink, the modeling architecture allows for the reproduction of the engine performance parameters together with the evaluation of the TWC pollutants’ conversion efficiency. An extensive database of experimental tests was used to assess the model response. The latter was validated in multiple steady-state operating conditions of the engine workplan. Using a semi-predictive combustion model, the validation was carried out over a wide range of different air-to-fuel ratios and during fast rich/lean transitions to evaluate the formation and conversion phenomena of the main chemical species, both engine-out and tailpipe. Subsequently, the complete model was validated in dynamic conditions throughout a WHTC, accurately reproducing the cut-off phases and their sudden accelerations. The numerical–experimental agreement on pollutant reproduction is generally good and globally below 3%. Larger deviations occur in extremely rich conditions and in CH₄ emission evaluation due to the lack of information related to the combustion process and chemical mechanisms involving the Pd surface. Full article

An Inertial Measurement Unit (IMU) is a significant component of a spacecraft, and its fault diagnosis results directly affect the spacecraft’s stability and reliability. In recent years, deep learning-based fault diagnosis methods have made great achievements; however, some problems such as how to extract effective fault features and how to promote the training process of deep networks are still to be solved. Therefore, in this study, a novel intelligent fault diagnosis approach combining a deep residual convolutional neural network (CNN) and a data preprocessing algorithm is proposed. Firstly, the short-time Fourier transform (STFT) is adopted to transform the raw time domain data into time–frequency images so the useful information and features can be extracted. Then, the Z-score normalization and data augmentation strategies are both explored and exploited to facilitate the training of the subsequent deep model. Furthermore, a modified CNN-based deep diagnosis model, which utilizes the Parameter Rectified Linear Unit (PReLU) as activation functions and residual blocks, automatically learns fault features and classifies fault types. Finally, the experiment’s results indicate that the proposed method has good fault features’ extraction ability and performs better than other baseline models in terms of classification accuracy. Full article

The cloud manufacturing system can provide consumers with on-demand manufacturing services, which significantly improve the utilization rate of distributed manufacturing resources and the response speed of personalized product needs. In the cloud manufacturing platform, the successful implementation of various industrial applications relies on the uploading and streaming of related field-level manufacturing data. For example, the realization of manufacturing service composition application should match the manufacturing tasks with distributed manufacturing resources according to their working state data and performance measurement data. Therefore, this paper proposes a data integration and analysis framework of a cloud manufacturing system based on cloud–edge collaboration and the Industrial Internet of Things (IIoT). A service-oriented information model is established to uniformly describe the related operational data and functional attributes of heterogeneous manufacturing resources. Secondly, a real-time transmission and integration method of high-volume operational field and sensor data based on message middleware is proposed to realize the remote monitoring of distributed manufacturing resources and efficient distribution of related data. Finally, a cloud–edge collaboration mechanism is put forward to train and update the parameters of various artificial intelligence models deployed at edge gateways. In the experiment, taking the computer numerical control (CNC) lathe as an example, the effectiveness of the proposed manufacturing resource access method is verified. Taking the fault diagnosis model of the CNC lathe as an example, the efficiency of the proposed cloud–edge collaboration mechanism for model updating is verified. Full article

Extracting intuitive operating state features from vibration signals without prior knowledge is a prospective requirement for health monitoring and fault diagnosis in bearings. In this paper, a visualized stacked denoising auto-encoder (VSDAE) model is proposed for the unsupervised extraction and quantitative evaluation of bearings’ state features. First, the stacked denoising auto-encoder (SDAE) was used to reconstruct vibration signals. The intermediate vector of the SDAE, which is a high-information-density representation of vibration signals, was regarded as the pending state feature. Then, the dimension of the intermediate vector was reduced by the t-distributed stochastic neighbor embedding (t-SNE) method to the two-dimensional visualization space. Finally, the silhouette coefficient of feature distribution was calculated to quantitatively evaluate the extracted features. The proposed model was evaluated using experimental bearing signals simulating various operating states. The results proved that the features, extracted and evaluated by the VSDAE, allowed the recognition of the operating states of the examined bearings. Full article

Vibration energy harvesting is a new alternative to lithium battery power for low-power devices, attempting to recover wasted or lost vibration energy to generate electricity. Magnetostrictive-based energy harvesting exploits the coupling properties of the Villari and Faraday electromagnetic induction effects to achieve mechanical–magnetic–electric energy conversion. In order to better apply to the actual vibration environment, such as buses, and improve the ability to capture low-frequency vibration energy, a double-stage rhombus vibration energy harvesting device, based on Terfenol-D rods, was developed. By establishing an analytical model of the force amplification ratio of the harvesting device, the design is optimized using the Single-Objective Genetic Algorithm, and the safety and pre-magnetization layout methods are analyzed by Finite Element Analysis. The output characteristics of the prototype, including the output voltage frequency response under low-frequency regular excitation and random excitation, the effect of external resistance, and the vibration energy capture performance under random excitation, are investigated in detail through experiments. The results of the experiments showed that the peak output power of the fabricated prototype was 1.056 mW at 30 Hz operating frequency, the energy harvesting capability reached 41.4 μW/N, and the peak open circuit voltage and output power were 2.92 V and 266 mW, respectively, under random excitation. Practical application test results showed that the peak voltage generated was 1.06–1.51 V when the excitation level was 2.2–4.9 m/s². The comparative study indicates that the output performance of the proposed double-stage rhombus magnetostrictive vibration energy harvesting system is a great improvement over the proposals of existing literature. Full article

Due to emerging requirements and pressures related to environmental protection, manufacturing enterprises have expressed growing concern for adopting various energy-saving strategies. However, environmental criteria were usually not considered in traditional production scheduling problems. To overcome this deficiency, energy-saving scheduling has drawn more and more attention from academic scholars and industrial practitioners. In this paper, an energy-saving flexible job shop scheduling problem (EFJSP) is introduced in accordance with the criterion of optimizing power consumption and processing costs simultaneously. Since the classical FJSP is strongly NP-hard, an Improved Sparrow Search Algorithm (ISSA) is developed for efficiently solving the EFJSP. In the ISSA, a Hybrid Search (HS) method is used to produce an initial high-quality population; a Quantum Rotation Gate (QRG) and a Sine–Cosine Algorithm (SCA) are integrated to intensify the ability of the ISSA to coordinate exploration and exploitation; the adaptive adjustment strategy and Variable Neighborhood Search (VNS) are applied to strengthen diversification of the ISSA to move away from local optima. Extensive computational experiments validate that the ISSA outperforms other existing algorithms in solving the EFJSP due to the advantages of intensification and diversification mechanisms in the ISSA. Full article

Current state-of-the-art engine condition monitoring is based on a minimum of one steady-state data point per flight. Due to the scarcity of available data points, there are difficulties distinguishing between random scatter and an underlying fault introducing a detection latency of several flights. Today’s increased availability of data acquisition hardware in modern aircraft provides continuously sampled in-flight measurements, so-called full-flight data. These full-flight data give access to sufficient data points to detect faults within a single flight, significantly improving the availability and safety of aircraft. Artificial neural networks are considered well suited for the timely analysis of an extensive amount of incoming data. This article proposes uncertainty quantification for artificial neural networks, leading to more reliable and robust fault detection. An existing approach for approximating the aleatoric uncertainty was extended by an Out-of-Distribution Detection in order to take the epistemic uncertainty into account. The method was statistically evaluated, and a grid search was performed to evaluate optimal parameter combinations maximizing the true positive detection rates. All test cases were derived based on in-flight measurements of a commercially operated regional jet. Especially when requiring low false positive detection rates, the true positive detections could be improved 2.8 times while improving response times by approximately 6.9 compared to methods only accounting for the aleatoric uncertainty. Full article