Powdery mildew is a common disease in plants, and it also one of the main diseases middle final stages cucumber [Cucumis sativus]. on plant leaves affects photosynthesis, which may reduce yield. Therefore, great significance to automatically identify powdery mildew. Currently, most image-based models commonly regard identification problem as dichotomy case, yielding true or false classification assertion. However, quantitative assessment resistance traits plays an important role screening...

Motor fault diagnosis based on deep learning frameworks has gained much attention from academic research and industry to guarantee motor reliability. Those methods are commonly under two default assumptions: 1) massive labeled training samples 2) the test data share a similar distribution unvarying working conditions. Unfortunately, these assumptions nearly invalid in real-world scenario, where signals unlabeled condition changes constantly, resulting models of previous studies that always...

Automatic recognition of mature fruits in a complex agricultural environment is still challenge for an autonomous harvesting robot due to various disturbances existing the background image. The bottleneck robust fruit reducing influence from two main disturbances: illumination and overlapping. In order recognize tomato tree canopy using low-cost camera, algorithm based on multiple feature images image fusion was studied this paper. Firstly, novel images, a*-component I-component image, were...

In order to improve the efficiency of robotic harvesting in unstructured environment, a modular concept dual-arm robot for tomatoes is proposed this paper. The objective develop system which works based on human-robot collaboration reached. Due complexity working an artificial recognition approach conducted by operator through marking tomato object graphic user interface used and localization. A frame equipped with two 3 DoF manipulators different type end-effectors pick designed tested...

Data-driven machinery fault diagnosis has gained much attention from academic research and industry to guarantee the reliability. Traditional frameworks are commonly under a default assumption: training test samples share similar distribution. However, it is nearly impossible in real industrial applications, where operating condition always changes over time quantity of same-distribution often not sufficient build qualified diagnostic model. Therefore, transfer learning, which possesses...

Machinery remaining useful life (RUL) prediction is an important task in condition-based maintenance. Data-driven methods have been widely studied and applied, however, almost all the researches learn degradation trends regardless of different fault conditions, which can lead to patterns. This article proposes a novel information assisted RUL method based on convolutional long short-term memory (LSTM) ensemble network, where conditions are obtained via knowledge transfer. Divergence...

Motors are one of the most critical components in industrial processes due to their reliability, low cost and robust performance. Motor failure will lead shutdown a whole production line cause great loss. Therefore, accurate, reliable effective motor fault diagnosis must be performed. Currently, motors has gained much attention guarantee safe operations. In this paper, novel method is proposed for three-phase asynchronous using Long Short-Term Memory (LSTM) neural network, which possesses...

Motor fault diagnosis has gained much attention from academic research and industry to guarantee motor reliability. Generally, there exist two major approaches in the feature engineering for diagnosis: (1) traditional learning, which heavily depends on manual extraction, is often unable discover important underlying representations of faulty motors; (2) state‐of‐the‐art deep learning techniques, have somewhat improved diagnostic performance, while intrinsic characteristics black box lack...

Machinery remaining useful life (RUL) prediction plays a pivotal role in modern industrial maintenance. Traditional methods entail the manual selection of features, which requires prior knowledge and lack adaptability to diverse cases. Moreover, as features may have different relevance degradation process at various stages, prognostic performance will be limited by utilization fixed throughout full lifetime. Additionally, most deep-learning perception global information is critical RUL...

Existing research indicates that job satisfaction has effects on performance, but little evidence exists about the mechanism through which satisfaction-performance association operates. This study aims to examine effect of performance in a district-level health care system China and explore mediated by organizational commitment burnout.Cluster sampling was used this study. All healthcare professionals Nanshan Medical Group, who were at work last 3 months able complete online questionnaire...