A new dynamic model and transfer learning based intelligent fault diagnosis framework for rolling element bearings race faults: Solving the small sample problem.

Intelligent fault diagnosis of rolling element bearings gains increasing attention in recent years due to the promising development of artificial intelligent technology. Many intelligent diagnosis methods work well requiring massive historical data of the diagnosed object. However, it is hard to get sufficient fault data in advance in real diagnosis scenario and the diagnosis model constructed on such small dataset suffers from serious overfitting and losing the ability of generalization, which is described as small sample problem in this paper. Focus on the small sample problem, this paper proposes a new intelligent fault diagnosis framework based on dynamic model and transfer learning for rolling element bearings race faults. In the proposed framework, dynamic model of bearing is utilized to generate massive and various simulation data, then the diagnosis knowledge learned from simulation data is leveraged to real scenario based on convolutional neural network (CNN) and parameter transfer strategies. The effectiveness of the proposed method is verified and discussed based on three fault diagnosis cases in detail. The results show that based on the simulation data and parameter transfer strategies in CNN, the proposed method can learn more transferable features and reduce the feature distribution discrepancy, contributing to enhancing the fault identification performance significantly.

A fault diagnosis scheme for rotating machinery using hierarchical symbolic analysis and convolutional neural network.

Fault diagnosis of rotating machinery is crucial to improve safety, enhance reliability and reduce maintenance cost. The manual feature extraction and selection of traditional fault diagnosis methods depend on signal processing skills and expert experience, which is labor-intensive and time-consuming. As a typical intelligent fault diagnosis method, the convolutional neural network automatically learns features from original data, but it is extremely difficult to design and train a deep network architecture. This paper proposes a fault diagnosis scheme combined of hierarchical symbolic analysis (HSA) and convolutional neural network (CNN), which achieves laborsaving and timesaving preliminary feature extraction and accomplishes automatically feature learning with simplified network architecture. Firstly, hierarchical symbolic analysis is employed to extract features from original signals. The extracted features are able to identify different health conditions under various operating conditions. Then, convolutional neural network instead of human labor is used to learn the complex non-linear relationship between features and health conditions automatically. The architecture of CNN diagnosis model is simple and convenient to implement. Finally, a centrifugal pump dataset and a motor bearing dataset are adopted to validate the effectiveness of the proposed method. The diagnosis results show that the proposed method exhibits superior performance compared with shallow methods and deep learning methods.

Spinal cord compression syndrome caused by intraspinal epidural fibrous cord: Three case reports.

RATIONALE: The spinal cord compression caused by intraspinal epidural fibrous cord. PATIENT CONCERNS: All patients in this study had spinal cord compression syndrome caused by an intraspinal epidural fibrous cord, manifested as abnormally increased epidural adipose tissue by imaging. DIAGNOSE: These abnormal fibrous connective tissue strips were not identical to the known pathological tissue such as "meningovertebral ligament." Instead, it might be a novel pathogenic cause for the spinal cord compression. INTERVENTIONS: The intraspinal exploratory operation. OUTCOMES: the first case has expected effect, the remaining two need further test. LESSONS SUBSECTIONS: The disease could be easily misdiagnosed as spinal epidural lipoma or lipomatosis before the operation. However, the overt intraoperative finding was the indefinite starting and ending points of the epidural adipose mass in addition to the increased amount of adipose tissue. The obvious compression on the spinal cord could be found as the extraordinarily large and broad hypertrophic fibrous connective tissue strips.Further studies are needed to elucidate whether it is different from, or associated with, lipoma and epidural lipomatosis, which is a serious issue to be considered by both clinicians and radiologists. Therefore, early discovery,diagnosis, and treatment should be the prerequisites to achieve a satisfactory effect.

MicroRNA-185 regulates spinal cord injuries induced by thoracolumbar spine compression fractures by targeting transforming growth factor-ß1.

The aims of the present study were to examine the expression of transforming growth factor (TGF)-ß1 and microRNA (miR)-185 in the bone tissue, blood and cerebrospinal fluid of patients with spinal cord injuries and to evaluate the regulation of spinal cord injuries by miR-185. A total of 44 patients with spinal cord injuries induced by thoracolumbar spine compression fractures, who were hospitalized at Luoyang Orthopedic-Traumatological Hospital between June 2012 and February 2015 were enrolled in the present study. Among the patients enrolled, 18 underwent surgery between 1 and 7 days following fracture, and 26 patients underwent surgery between 8 and 14 days following fracture. Bone tissue, peripheral blood and cerebrospinal fluid were subsequently harvested from patients for analysis. Reverse transcription-quantitative polymerase chain reaction was performed to determine the expression of miR-185 and TGF-ß1 mRNA. Western blotting was performed to evaluate TGF-ß1 protein expression in bone tissue and ELISA was employed to quantify TGF-ß1 protein expression in the blood and cerebrospinal fluid. TGF-ß1 mRNA and protein levels in bone tissue, blood and cerebrospinal fluid from patients who underwent surgery 8-14 days post-fracture were significantly higher than those who underwent surgery 1-7 days post-fracture (P<0.05). By contrast, miR-185 levels were significantly lower in bone tissue, blood and cerebrospinal fluid from patients who underwent surgery 8-14 days post-fracture compared with those who underwent surgery 1-7 days post-fracture (P<0.05). The results of the present study desmonstrate that the upregulation of TGF-ß1 in the bone tissue, blood and cerebrospinal fluid of patients with spinal cord injuries induced by thoracolumbar spine compression fractures is correlated with the downregulation of miR-185. Furthermore, miR-185 may target TGF-ß1, affecting its transcription and translation, indicating that it serves an important role in spinal cord injuries induced by thoracolumbar spine compression fractures.

[Evaluation of percutaneous vertebroplasty of 190 cases].

OBJECTIVE: To evaluate the therapeutic effect of percutaneous vertebroplasty (PVP) guided by X-ray fluoroscopy in treating osteoporotic spinal compression fractures, hemangioma of vertebra and metastatic carcinoma of vertebra. METHODS: One hundred and ninety patients with 275 diseased vertebra underwent PVP under the guidance of C-arm fluoroscopy (male 80, female 110, ranging in age from 53 to 91 years, with an average of 66 years). Bone marrow biopsy needle was inserted percutaneously via transpedicular way into the diseased vertebra. Polymethylmethacrylate (PMMA) was then injected into the diseased vertebra. Visual analogue scale (VAS), mobility and analgesic usage were evaluated pre-operation and 3 months after PVP. RESULTS: PVP was successful in 190 cases (275 vertebrae). VAS was tested by t test at 3 months after PVP (P < 0.05). Simultaneously, scale of patient's mobility and scale of analgesic usage was tested by rank sum test at 3 months after PVP (P < 0.05). CONCLUSION: As the mimimally invasive operation, PVP can alleviate pain in early time, avoid kinds of complications by shortening the patient's time in bed and have the characteristic of simply operative procedure and low expenses. It is an effective mini-invasive technique for osteoporotic spinal compression fractures, hemangioma of vertebra and metastatic carcinoma of vertebra.