This method is called “unboxed” assembly technology, which will abandon the traditional assembly line operation method, and no longer allow the car body to be assembled like a box along the assembly line through various stations in sequence. Tesla’s “deconstructed” approach involves assembling different parts of the car simultaneously in different areas of the factory, then bringing together several large subassemblies at the end.

It is claimed that this approach can cut production costs in half and require about 40% less factory space than traditional car factories for the same output. If true, it will inevitably greatly reduce Tesla’s manufacturing costs, thereby lowering the price of the entire vehicle.

Tesla CEO Elon Musk has repeatedly hinted that this new production method will be adopted, but has not disclosed specific details. So far, he has only mentioned that the new technology used to produce the upcoming $25,000 model will be “revolutionary” and “bigger than anywhere else in the world.” Any car manufacturing system is far more advanced.”

The affordable Tesla model is expected to begin production (or at least launch) in late 2024 or early 2025, with Musk confirming that the project is “very close to completion” without revealing further details.

The Automotive News website quoted Mathew Vachaparampil, CEO of engineering and automotive benchmarking company Caresoft, as saying that Tesla first verified the feasibility of the “deconstruction” assembly method through digital simulation. He did not disclose the results of the simulation test, but he did confirm that this innovative way of manufacturing cars will significantly reduce Tesla’s manufacturing costs.

It’s unclear where Tesla will pioneer this “deconstructed” approach, but it could be related to its upcoming affordable models. Considering that Tesla is currently building or expanding multiple factories, this technology may be first put into production in places such as China, Berlin, and even Mexico.

The post Tesla’s New Car Assembly Tech to Slash Production Costs appeared first on TechGoing.

Friends from 9to5Google have discovered that Google is currently working on cough and snore detection feature that will be part of the Digital Health Suite. In the latest beta update to the app, it was discovered that Google will offer to snore and cough tracking; it is intended to be part of the bedtime mode section and will use the phone’s microphone to listen for snoring or coughing.

In addition, Digital Wellbeing works with Google Clock’s sleep tracking feature, which actually tracks the owner’s sleep time using the phone’s gyroscope and ambient light sensor.

Users can also go ahead and turn on cough and snore detection during scheduled bedtime, which will be displayed along with other options such as Show Custom and Do Not Disturb, and enabling this feature requires granting microphone permissions.

It is worth noting that the sensor is only active during the time you set. Data on coughing and snoring will also appear along with the information present in the app’s usage. The end user will get a graphical view of the week, as well as the average number of coughs and average snoring time.

The upcoming feature will also show you how long you have slept without coughing or snoring. There is no given news on when this feature will be available on the digital health app.

The post Android phones can now track and analyze coughs and snores with Digital Wellbeing appeared first on TechGoing.

Around this problem, Xiaomi has developed a set of table recognition algorithms, which efficiently and accurately extracts the tables in pictures and converts them into editable Excel files. The algorithm has been successfully implemented in Xiaomi 10S series, MIX Fold 2, and other flagship models, you can access the experience from Album – More – Table Recognition, or swipe to enter.

Form detection algorithm

Xiaomi said that the table detection algorithm mainly extracts the table area accurately from the picture and corrects the table to get a flat table picture for the next step of table recognition.

The table recognition algorithm mainly extracts the table structure and table text content from the picture, and then combines these information effectively to output an editable Excel table.

Form detection has the following difficulties: on the one hand, the algorithm and memory on the cell phone are limited, on the other hand, the requirements for the form detection results are very high, the form often contains other text around it, and if the detection results are not accurate, it will have a negative impact on the recognition results later.

Xiaomi’s table detection algorithm will detect both the table area and the four corner points of the table, and through perspective transformation and our self-developed anti-distortion algorithm to get a flat table with only the table area, the effect is shown in the figure.

Since the algorithm runs on the cell phone side, it needs to ensure the running speed and model size, Xiaomi adopts a very lightweight one-stage detection framework, backbone using shuffleNetV2.

regressing the key point information while detecting the table box to facilitate perspective correction of the table, and using Wing loss instead of L1 loss to make the key point regression more accurate.

In terms of data, the algorithm is used to mine a large amount of form detection data from public data at low cost, which significantly improves the form detection effect. The final model size is about 1M and runs smoothly on Xiaomi phones.

Table Recognition Algorithm

The table recognition algorithm runs on the server side and contains the following main modules: text detection, text recognition, table structure prediction, cell matching, alignment algorithm, and Excel export.

The current mainstream approach is to represent tables in HTML hypertext, and then encode the HTML to predict the HTML sequence and the corresponding coordinate information.

This method has achieved good results on open source datasets, and Ping An Technology of China and Baidu have also adopted this scheme, but too many tags in HTML lead to error-prone table structure recognition.

To address the shortcomings of this method, we adopt a new encoding method for tables, which can represent tables of arbitrary structure with only four tags, greatly improving the accuracy of table structure recognition.

Table recognition is accelerated by using the Faster transformer inference framework during deployment, which officially claims that Xiaomi’s inference speed is improved by about 20 times, significantly improving user experience.

Summary

The algorithm can efficiently and easily extract tables from images, greatly improving office efficiency. Xiaomi said that engineers will continue to improve the recognition experience of document-based images in Xiaomi phones.

The post Xiaomi’s new technology: convert the table in the picture into an Excel file appeared first on TechGoing.

Zhu Huarong, chairman of Changan Automobile, made several suggestions for the development of comprehensive electrification, including further accelerating the top-level design of the new energy industry and systematically promoting the synergistic development of new energy industrialization, social applications and energy structure.

Suggesting that corporate research institutes and universities strengthen cooperation to accelerate the research and development application of new generation batteries.

It is suggested that the pace of transformation be accelerated and the cessation of fuel car sales in China be put on the agenda.

Zhu Huarong believes that China’s auto industry has initially had the basic conditions to stop selling fuel cars and can enter the research agenda.

He suggested that the relevant state ministries and industries and industries clarify the deadline for research on traditional fuel vehicles, and guide enterprises and society as a whole to make an orderly transition to new energy.

The post China’s auto industry has begun to have basic conditions for stopping the sale of fuel vehicles appeared first on TechGoing.

Currently, battery systems are the most expensive component of electric vehicles. Therefore, improving performance and reducing costs are seen as key to sustaining global sales growth.

In an interview, Shoichiro Watanabe, chief technology officer (CTO) of Panasonic Energy, a core subsidiary of Panasonic, said the new technology will use a new combination of additives that will allow individual batteries to operate at higher voltages without compromising pack performance.

Shoichiro Watanabe added: “The competition among battery manufacturers is to introduce higher performance and more effective additives.”

Currently, Panasonic’s batteries for Tesla use a voltage of 4.2 volts, while the new technology can increase the voltage to 4.3 or 4.4 volts. Shoichiro Watanabe said, “If you can get the voltage to 4.5 or 4.6 volts, then the whole world’s perception of electric cars will change radically. “

The so-called “energy density” is essentially the ability of the battery to store energy in a given volume. A 20 percent increase in energy density means that the new technology’s batteries will have an energy density of 900 watt-hours per liter (Wh/l), compared to the current 750 Wh/l.

Shoichiro Watanabe said Panasonic plans to achieve this goal in the next few years but did not say when it will launch battery packs based on the new technology.

Shirley Meng, a professor at the University of Chicago, said in response: “If Panasonic can achieve the improvements described, it is entirely possible to increase energy density by 20 percent. I’m optimistic about that goal.”

Currently, Tesla is already producing a new, larger size 4680 battery. Compared to the current generation of 2170 cells, the 4680 cells are expected to reduce production costs and increase range.

A Panasonic spokesman declined to comment on whether Panasonic’s new battery technology will be introduced into the 4680 or 2170 batteries in the future. Tesla has not yet commented on Panasonic’s new technology.

The post Panasonic says new technology can increase battery density by 20%- Model Y range increased by 100 km appeared first on TechGoing.