The surface inspection of steel parts like rolling elements for roller bearings is an essential component of the quality assurance process in their production. Existing inspection systems require high maintenance cost and allow little flexibility. In this paper, we propose the use of a rapidly retrainable convolutional neural network. Our approach reduces the development and maintenance cost compared to a manually programmed classification system for steel surface defect detection. One of the main disadvantages of neural network approaches is their high demand for labeled training data. To bypass this, we propose the use of simulated defects. In the production of rolling elements, real defects are a rarity. Collecting a balanced dataset thus costs a lot of time and resources. Simulating defects reduces the time required for data collection. It also allows us to automatically label the dataset. This further eases the data collection process compared to existing approaches. Combined, this allows us to train our system faster and cheaper than existing systems. We will show that our system can be retrained in a matter of minutes, minimizing production downtime, while still allowing high accuracy in defect detection.
1 May 2019 in IOP Conference Series: Earth and Environmental Science
Volume change of graphite leads to change in thickness of battery storage layers during discharging and charging. Pouch cell lithium ion batteries are used in the field of electric vehicles and solar home storage. This paper shows a measurement setup for the three-dimensional measurement of thickness change on a flat 6.7mm thick pouch cell using a white light interferometer. With a measuring field of 7.05mm diameter the resulting 3D thickness change record contains 226000 3D readings. The measuring points have a lateral distance of 13.1μm. The repeatability of the measurement is 312.8nm for the individual values and 64.1nm for the average value. In addition, this paper shows how the storage capacity of this pouch cell drops over 30 charge cycles.
An optical measuring method is presented, with which it is possible to measure and evaluate reflective cylindrical surfaces using a combination of deflectometry and subsequent reconstruction of the surface. The system is set up and tested on rolling elements of cylindrical roller bearings. However, it is not limited to this use case and can be applied to other cylindrical specular surfaces. The system distinguishes itself from existing test methods through the combination of high-resolution three-dimensional defect measurement with a very short recording time, and offers the possibility of introducing tolerance limits in the production of cylindrical specular surfaces. With this method, it is possible to record a defect with the dimensions of by within 5 and to reconstruct the absolute depth. The resolution of the system is below 10 μ in both X- and Y-direction, and is therefore sufficiently accurate to detect typical surface defects such as scratches, dents, or deformations. To validate the measured values of the system, the results of an artificially generated μ deep defect location were compared with those of a highly accurate mechanical stylus measurement.
In the developing world artisanal fishermen use kerosene lanterns for night fishing. Solar powered fishing lights became an ecologic and economic alternative to the kerosene lanterns due to the development of high efficiency LED light sources and low price solar cells. In the last years several solar fishing light systems were developed. The choice of the battery technology influences the reliability and the operating cost of the fishing light, because the battery has the lowest lifetime of all components of the fishing light.In this paper we describe the results of a battery simulation over 5 years time: The battery is daily charged by a solar module and discharged by night fishing. The meteorological irradiation data of Tanzania are used. Different battery technologies (Lead Acid, Lithium-Ion, Lithium-Iron-Phosphate) are tried out.The results of the simulation are the battery lifetime, cost and waste mass per year dependent on the battery technology. The study shows, that the Lithium-Iron-Phosphate technology is the best choice in terms of these factors and to the advantage of the poverty-stricken fishermen at the Victoria Lake in Tanzania and the environment.