A Novel Generative Method for Machine Fault Diagnosis

Deep learning is widely used in fault diagnosis of mechanical equipment and has achieved good results. However, these deep learning models require a large number of labeled samples for training, which is difficult to obtain enough labeled samples in the actual production process. However, it is easier to obtain unlabeled samples in the industrial environment. To overcome this problem, this paper proposes a novel method to generative enough label samples for training deep learning models. Unlike the generative adversarial networks, which required complex computing time, the calculation of the proposed novel generative method is simple and effective. First, we calculate the Euclidean distance between the training sample and the test sample; then, the weight coefficient between the training sample and the test sample is settled to generate pseudosamples; finally, combine with the pseudosamples, the deep learning method is training for machine fault diagnosis. In order to verify the effectiveness of the proposed method, two experiment datasets with planetary gearboxes and wind gearboxes are carried out with different activation functions. Experimental results show that the proposed method is effective for most activation function models.

Triacetin as Lubricant Additive: Slipping Friction between Metal Pairs under Boundary Lubrication

Friction between rubbing pairs plays a key role in operating machines in an efficient approach. In some intended works or occasional circumstances, slipping friction may occur during dry or boundary lubrication. Lubricating mechanical equipment using proper and efficient lubricant agents is tremendously necessary. This work explores the synthesized triacetin as an additive for lubricant under slipping friction between steel rollers and aluminum, brass, copper, and stainless-steel rods under boundary lubrication. The metal surface morphology under the lubricant with 10% triacetin additive covering roughness periphery is investigated by Field Emission Scanning Electron Microscope imaging. In the dry slipping condition, the friction coefficient is lower for the copper-steel pair compared to the aluminum-steel combination. Compared to the absence of triacetin additive, the steel roller combinations with the rod metal specimens undergoing boundary lubrication with 10% triacetin additive in the lubricant can reduce the slipping friction coefficient by up to 49.2% in the case of steel roller and brass rod pair. The quantitative influences of triacetin additive on metal rubbing pair friction coefficients under boundary lubrication are inversely exponential correlated to triacetin additive, varying in the range of 0 to 10% v/v.

Occupational risk assessment and selected morbidities among cement brick unit workers in a rural area of Bangalore District, India

Introduction: The labor-intensive nature of cement brick manufacturing, its unorganized nature and internal migration, expose the employees to several occupational health hazards. The objective of the study was to assess the occupational risks in cement brick unit settings and to estimate the prevalence of respiratory and musculoskeletal morbidities among the cement brick unit workers in a rural area of Bangalore urban district. Methods: A cross-sectional study was conducted among cement brick unit workers over two months. A semi-structured questionnaire was used to capture sociodemographic details. Multiple observations on the field and the World Health Organization semi-quantitative risk assessment matrix were used to obtain risk scores of the occupational hazards. A structured questionnaire on respiratory symptoms and Minispir Portable Spirometer were used to assess the respiratory morbidities and lung functions. Musculoskeletal morbidities were assessed using the Modified Nordic questionnaire. Proportions were used to describe respiratory and musculoskeletal morbidities. Chi-square test, Fisher’s exact test and multivariate logistic regressions were done to identify significant variables. Results: Among 120 subjects, 110 (91.6%) were men and 85.8% were migrants. Injury due to falls of heavy objects, back injury, respiratory complaints and slips/falls were found to be high-risk health hazards. The prevalence of respiratory morbidity was 21.7% and that of musculoskeletal morbidity was 51.7%. Workers receiving a higher salary (≥ 1500 Indian rupees) had higher odds of having respiratory morbidity. Conclusion: The prevalence of respiratory and musculoskeletal morbidities was high. Introduction of mechanical equipment, decreasing work hours, periodic medical examinations and appropriate use of personal protective equipment will help in risk reduction as per this study.

Germination of radish seeds (Raphanus sativus) treated with homeopathic drugs

The radish is a short cycle crop, since it is harvested at 25-30 days after direct sowing. Under the economic point of view it is an important species, but there are few studies on germination of radish seeds. The objective of this study was to evaluate the effect of high diluted substances on the germination of radish seeds. The trial was conducted at the Agricultural Research Institute of Paraná (IAPAR) in Londrina / Paraná. It was used a pesticide free cultivar named Cometa. The treatments were: Bryonia, hydroalcoholic solution, Arnica montana, Cina and Lupine + Oat, all of them diluted and agitated at 9x; distilled water and agitated distilled water were used as controls. The mother tincture of Lupine + Oat was prepared from plants collected at the experimental station of IAPAR in Londrina. The mother tincture and all treatments were prepared according to the guidelines in the Brazilian Homeopathic Pharmacopeia, Part I [1]. The agitations of the treatments were made by a mechanical equipment, model Denise 10-50 manufactured by Autic. The water was distilled the day before preparing the treatments. The experiment was performed with 300 seeds per treatment. The seeds were placed in gerbox with germitest paper, and 50 gerbox were used per treatment, with six seeds in each gerbox. The germitest papers were moistened with the treatments and the seeds were soaked for 2 hours previously set up the experiment. The substances in high dilutions were agitated 100 times on the machine before soaking the seeds and moistening the germitest paper. The experimental design was entirely randomized and the gerbox were kept at the bench at the Laboratory of Plant Protection of IAPAR. A person not involved in conduct of the experiment coded (blinded) the treatments solutions with a random letter code. The code was kept secret until all measurements and data processing were finished. Seeds were observed daily for germination and counted only those considered germinated. Seeds were considered germinated when the radicle was at least two millimeters length. Arnica montana 9x increased 5.9% the seed germination when compared with distilled water.

An Intelligent Diagnosis Method for Machine Fault Based on Federated Learning

In engineering, the fault data unevenly distribute and difficultly share, which causes that the existing fault diagnosis methods cannot recognize the newly added fault types. An intelligent diagnosis method for machine fault is proposed based on federated learning. Firstly, the local fault diagnosis models diagnosing the existing fault data and the newly added fault data are established by deep convolutional neural network. Then, the weight parameters of local models are fused into global model parameters by federated learning. Finally, the global model parameters are transmitted to each local model. Therefore, each local model update into a global shared model which can recognize the newly added fault types. The proposed method is verified by bearing data. Compared with the traditional model, which can only diagnose the existing fault data but cannot recognize newly added fault types, the federated fault diagnosis model fusing weight parameters can diagnose newly added faults without exchanging the data, and the accuracy is 100%. The proposed method provides an effective method to solve the poor sharing of fault data and poor generalization of fault diagnosis model for mechanical equipment.

Life Prediction Method of Remanufactured Machinery Equipment Based on Vibration Signal Feature Extraction

Mechanical equipment is a key component of mechanical equipment, and its working condition is directly related to the overall performance of mechanical equipment. Accurate evaluation and prediction of the performance degradation trend of mechanical equipment is of great significance to ensure the reliability and safety of the mechanical equipment system. Based on the data of typical faulty equipment, this paper analyzes the energy characteristic parameters of mechanical equipment under different types and degrees of failure in the time domain. Using amplitude spectrum analysis, Hilbert envelope demodulation and wavelet packet decomposition method, and other vibration signal processing methods, preliminary extraction of multiple statistical feature parameters are given. Secondly, in view of the irrelevant and redundant components of multiple statistical parameters, a new method for extracting fault features of mechanical equipment based on variance value and principal component analysis is proposed. This method can effectively classify the fault status of mechanical equipment. The effectiveness of the method is verified by actual equipment signals. After that, the value extracted from the vibration signal of the double-row roller equipment is used as the degradation feature. In order to reduce the influence of irregular characteristics in the vibration signal and simplify the complexity of the vibration signal, the wavelet transform and the support vector machine model are combined, according to the degradation after decomposition. The 95% confidence interval of the predicted value is also given. The SVM model is established based on data characteristics, and single-step and multistep prediction of equipment degradation trends are carried out. The prediction result shows that, according to the mapping position formula, the distribution of equipment degradation prediction points is obtained, and a 95% confidence interval based on the distribution of the prediction points is given. Finally, on the basis of completing feature extraction, this paper applies an unsupervised feature selection method. The sensitive characteristics of life prediction and the prediction results of a single SVM model and a neural network model are compared and analyzed at the same time.

Cortical bone grinding mechanism modeling and experimental studyfor damage minimization in craniotomy

Craniotomy, as a part of neurosurgery, implies a safe opening of the skull with mechanical equipment. Grinding is a traditional machining method that can accurately and efficiently remove bone tissue. Aiming at low-damage and high-efficiency bone grinding, this study analyzed the kinematic law of a single abrasive grain during the grinding process. The theoretical model of grinding force was established based on the calculation of specific energy and friction force. The grinding test platform was set up, and the full factorial experimental design was performed to link the grinding force evolution with different processing parameters. The experimental results obtained on porcine femurs validated the model predictions where the grinding force grew with feed speed and grinding depth; it exhibited a decreasing trend with rotation speed, followed by increasing one.

Kalman filter identification method for micro-vibration transfer paths of satellites

Micro-vibrations on-board a satellite have degrading effects on the performance of certain payloads like observation cameras. The major sources of vibrations include momentum wheels, solar array drives, other rotary mechanical equipment, etc. These vibrations result in loss of the pointing precision and image quality of the payload through intricate transfer paths. To improve the accuracy of a satellite system with many vibration sources and complex transfer paths, it is necessary to determine the main transfer path of vibration. In this study, a path identification method is proposed and applied to the transfer system from the momentum wheel to the camera mount. First, the observer/Kalman filter identification (OKID) algorithm is used to acquire the state-space equation of each path subsystem. Then, the subsystem order is obtained based on the slope of the singular entropy increment. In the next phase, combined with the measured disturbance force of the momentum wheel, the displacement response of the target point is predicted. Finally, the dominant transfer path of vibration is achieved by calculating the vibration contribution of each path to the response point. The results indicate that the dominant transfer path is the axial path of the horizontal momentum wheel, which contributes to the vibration of the camera mount at most. Effective vibration reduction measures should be taken to this path to suppress the vibration signal. In comparing the identified displacement response with the finite element response of the camera mount under different noise conditions, the correlation coefficients are >0.85, which proves the accuracy and anti-noise capability of the identification method.