Mingde Optoelectronics Artificial Intelligence Sorting equipemnt take the lead in introducing artificial intelligence methods such as deep convolutional neural networks(CNN) in the field of visible light photoelectic sorting to analyze and process material images,and through CNN partial connection,weight sharing,multiple convolution kernels and other methods,during the training process, the multi-dimensional features of materials are automatically extracted to establish a database,whose sorting effect is far better than traditional photoelectric methods.
The new generation of Mingde MAI-TD6 intelligent ore separator breaks through the existing ore separation technology, adopts heavy fast track design, has strong integration technology, large ore particles and high separation output.
Taking metal silicon as an example, the particles selected are 3~8cm, and the hourly output can reach 50 tons. Compared with the traditional manual selection of metal silicon, the heavy artificial intelligence machine can quickly and stably separate the good and bad materials on the premise of reducing the cost of manual selection, which has the advantages of one-time investment, low operating cost and long-term high return.
In order to meet the requirements of different mineral separation, the equipment supports customized design, and is simple in operation, highly intelligent, and complete in after-sales service. Its application scope in the ore separation field covers various metals and nonmetals, such as silicon metal, talc, calcium carbonate, iron ore, phosphate rock, lead zinc ore, gold mine, etc. The intelligent ore separator can be used to separate ores that can be distinguished by eyes. It provides important technical support for improving efficiency, reducing cost and increasing income in ore separation field.
Technical Advantages
1,Introduced artifical intelligence methods such as deep convolutional neural networks(CNN) in the field of visible light photoelectric sorting to analyze and process material images.
2,AI photoelectric sorting technology can automatically extract the multi-dimensional characteristics of materials,like texture,shape,color,quality,luster,etc., which greatly improves the sorting effect,expands the sorting scene and material types,to meets the market diversification and personalized sorting requirements,and solves the problem of limited color sorting materials in current color sorter market.
3,Photoelectric sorting requires high real-time performance,while CNN operation is relatively slow.In this regard, we adopt the model compression technology to accelerate CNN operation speed and greatly improve the recognition efficiency.
4,In view of the situation that many mineral materials cannot obtain massive data,our company adopts transfer lerning technology and industrial image sample enhancement technology to ensure the recognition accuracy of non-massive data training.
5, The AI sorting machine uses a gigabit camera to transmit image data to multi-GPU computing platform,which adopts CNN to analyze material types and accurately identify material surface features and texture structures.
|
Model
|
Mineral particle size (cm)
|
Capacity
(T/H)
|
Air pressure (Mpa)
|
Sorting accuracy
|
finished product accuracy
|
Power(kW)
|
Dimension(mm)
|
Weight(kg)
|
|
MAI-TD6
|
3<d≤8
|
40~60
|
0.5~1.0
|
99
|
96%~98%
|
10
|
6790*2502*2190
|
4.5T
|
| |
|
|
|
|
|
|
The above index is based on 10% impurity content Calcium carbonate as an example,The specific index varies with the material and impurity content.
Product feature of AI sorting machine
1,it’s the first to introduce artificial intelligence means of neural network in the field of sorting,which solves the problem that color sorting machine can only separate according to simple criteria.
2, The sorting mode is established according to users’ sorting requirements to meet users’ diversified and personalized sorting requirements.
3,We own the self-developed software system and closed machine structure, the main internal components are all imported,which can adapt to the harsh environment requirements like high dust,high pollution, and high corrosion in the industry and mining area.It has a wider application range and longer life.
4,Flexible track-type material conveying system,with samll drop,large output,and suitable for the sorting of more materials.
5,The vibrating feeding part and the main part of the equipment adopt a split structure to avoid the impact of vibration generated during the feeding process on the host and make the equipment operation more stable.
6, the sorting effect can be continuously improved by learning mode, and the deep learning mode can be developed.
7,High intelligence,remote debugging,smart monitoring,remote service and software upgrading.
Sortable ores
Applicable sorting ore materials
Talc, wollastonite ,calcite, quartzite
Fluorite, Potassium feldspar, Magnesite, Lithium pyroxene
Phosphate ore, Gold ore, High crystal silicon, oxide copper ore
Barite, bauxite ,lead-zinc ore and fluorite, barite lead-zinc ore
Not limited to the above ores, eye visible distinctions are applicable to AI sorting machines!
FAQ
Q:Are you a factory or trading company?
A:We are a factory.located in Hefei city,280 miles west away from Shanghai port
Q:Where is your factory located?
A: No.39 JinrongRd, Shuangfeng Economic development zone,Hefei,China
Q:Can we use our own logo or design for sticker?
A:Yes,you can .You can contact with the salesmen, please send an email to her/him and tell more
details about the logo or sticker.
Q:How can I get the samples?
A:no sample,we can do the experiment on the ore offered by you, offer the test report and techincal advice
Q:What’s your warranty?
A:one year
.
Q. How about the packing?
Packing will do as customer 's requirement
