Miwen Power CTO Su Jun: Edge Ai Enable Factory Wisdom Upgrade

Hello everyone, I am very happy to participate in the "Edge Calculation Frontal Practice" series of rice, this series of public classes focuses on the application cases of rice dynamics in edge computing practice, and prospects to the edge computing technology route.

This issue will focus on the application of edge calculation in smart plants. My name is Su Jun, is the cto of rice.

01, what is the utilization of rice?

As a video-assisted AIOT edge solution provider, rice power is committed to solving all problems encountered during the batch landing process for edge computing scene users.

HardwareMilin power provides a variety of low-power, different powerful hardware computational products for different scene requirements.

Software aspectTo provide hardware users with a variety of free value-added services such as remote system upgrades, bulk burning tools.

At the same time,Part of the sceneMiwen’s power also provides a complete solution of clouds, clearing obstacles to customers, solving the final artificial intelligence scenes.

Therefore, if you want to solve a edge problem, your questions will be answered in rice.

Today, I will combine the actual application scenarios, and everyone to explore the application of the edge AI in the intelligence of the factory.

02, the development trend of smart plants

The concept of smart factory, the earliest industry 4.0 proposed by Germany, generally equipped with the following characteristics:

The first is the digitalization of the factory, can automatically monitor the device, the management of information resources, and information services to the user;

Secondly, the equipment status is monitored by Internet of Things technology, which combines Internet network technology, information management and information service technology;

Based on these technologies, information-based energy saving and consumption consumption is realized, and the purpose of achieving green intelligence.

03, pain points applied in smart plants

For the goal of factory wisdom, it will always fall to the essence of factory production, such as:

How to shorten the order production time?
How to improve product quality, reduce manufacturing costs?
How to reduce inventory?
How to control the human cost of production and management?
How to monitor production site?
How to make production management transparency, visualization, can be quantified?
How to provide complete, accurate manufacturing data?
How to effectively control product quality?

04, the edge application inside the wisdom factory

Of course, there are many solutions to these problems, and in the edge computing application of rice dynamics, it will mainly involve the following aspects:

Industrial Quality Inspection: Find out the defects caused by the product in the production process, classify the product itself, main purpose is to strengthen the control of product quality, improve quality inspection efficiency, transparent, visualization, and quantification of quality inspection Management.

Safety production: refers to the production activities, in order to avoid the accident prevention and control measures to avoid personal injury and property loss accidents, ensure the personal safety and health, equipment and facilities of employees, and the environment is protected from damage. .

Wisdom operations: including safety production, but broader, the purpose is to make the information related information transparent and visualize.

existIndustrial quality inspectionAs shown in the figure, it is a feather grading application in partners. In this system, there will be 21 different levels of different grades of feathers.Its accuracy exceeds 98%, and the operational efficiency is 100 times that of manual detection.

This type of application scenario has highly requested the efficiency, real-time and response speed, and is usually high temperature, high humidity in industrial quality inspection. It is, with the company’s industrial specifications and powerful computing power of rice power EVO Xavier, it can achieve such high efficiency.

In terms of safety productionUsing the factory’s existing monitoring camera, whether the employee wears a hard hat, whether it is detected in violations such as smoking in the factory, timely warning fireworks, gas leaks and other safety accidents.

Smart operations often contain safe production, but the range is wider.

In the wisdom operationIt is necessary to confirm that the personnel entering the warehouse, performs perimeter inspection on the important area of ??the factory, and inspects whether the workers work is qualified, and the employees are departed, and the monitoring of sleeping posts. These are all could not data or quantifically, and now you can provide more dimensions for operational decisions by dataization.

05,Edge VS cloud

Maybe someone will ask, these things seem to be made through the cloud, what is the benefit of using the edge of the edge?

A comparison is carried out for the dressing (such as safety cap detection, hand suit compliance, etc.) to simultaneously access 15 channels.

Divide costs into hardware costs and communication costs

In terms of hardware costs, it is also 30T computing power, and it takes 28,000 / year’s high cost in the cloud. At the edge of the edge, only 12 million / year, while enjoying the three-year warranty,Cost difference reached 7 times.

In terms of communication costs, it is assumed that the data path is free. One minute needs to upload a 1M data to the cloud.The communication cost that needs to spend approximately 100 yuan.. And the cloud program, due to the cost of video traffic, it takes 6,000 yuan.


06, embedded edge VS desktop GPU

Of course, the cost of clouds and ends has long been self-evident.

However, in many applications, users use the GPU of the desktop as the edge computing equipment, the embedded edge devices provided by the desktop GPU and rice power supply?

Taking industrial vision as an example, comparison from both power costs and downtime probability.

Petitude is electrified: 0.725 yuan per degree, 12 hours of full load. Due to power differences, in terms of electricity cost, use Jetson Xavier embedded and using desktop GPUs, the gap is large, the year is 600 yuan, but for an expensive testing equipment, 600 yuan is completely what.

Industrial use scenarios: We found that workers’ switchgear operations will not be carried out in accordance with the manual, press the power button to use the most habitual use of them. This habit has caused the maintenance probability to make both gaps more than 20 times.

For equipment manufacturers, this is an additional maintenance cost; for factories, it will face the loss caused by stopping.. This is where we think is the largest difference in embedded edge devices and desktop GPUs.

We will look at the difference between desktops and embedded GPUs in terms of integrity:

In this figure, we can see that the left half of the Y-axis is an embedded edge device, that is, the Jetson series, the right half of the Y-axis is usually the graphics card.

It can be seen that so far, even the strongest embedded edge device – Jetson AGX Xavier, its strength is just a brother relative to the graphics card on the right, is only equivalent to the previous 1050Ti graphics card.

The poor of the force is one of the reasons why the embedded edge equipment is currently used in industrial scenarios. However, everyone can see,ORIN’s emergence has brought very huge changes to the entire pattern..

Although its computational power is still not as follows, the power consumption of 3080Ti is 350 watts, while ORIN is just an embedded device.

In this case, the force problem of embedded edge devices is no longer a big problem, butHigh reliability, strong energy savingThe advantages will continue to keep it.

Therefore, the application of embedded edge devices in the future industry will be more extensive.

07, the exploration of rice power in the smart factory scene

In order to make the edge calculation in industrial scenes, it is more likely to land.End users who have business needs, rice power and partners jointly launched a series of tools and products that are closer to application practices..

In terms of industrial quality inspection, there are very many small parts in industrial requirement, and Miwen Power Joint Partners Commentary provides a one-stop solution for industrial quality inspection. The standardization machine is launched.

For parts such as seals such as seals, screws, lamp holders, buttons, this standardized machine can be used to effectively detect, and only a small transformation is required, and it can be docked with the current production lines, and a set of " Fool "training tools to help users perform rapid tuning.

Similarly, in the factory scene, due to the very sensitive production process data, a large number of customers want themselves to hold this data to ensure data security.

Based on this consideration, we provide the following models with our partners:

Firstly, the common model is preset, enabling users to perform fast verification.

At the same time, support users to perform scenario selection and model design, allowing users to perform quick validation without giving data.

In the industrial sector, how to use a small amount of data to achieve the best effect is still a technical challenge, and the user does not exclude the user in the case of using our model, it is still unsatisfactory. Based on this requirement, rice dynamics also provides custom algorithm services to provide users with algorithms.

In a variety of modes, the user data security is not only protected, but also meet the performance requirements of different levels of users.

These tools are for users who ultimately have business needs.

Provide a series of easy-to-use software tools for developer user needs

Demand 1: Remote operation of the dispersed edge device

The application scenario of the edge calculation is usually very dispersed. For development types, customers who serve their customers are often far away from the city, relatively dispersed. When remote maintenance is required, they have to pay more high travel and human costs, so they want to be able to pass remotely as much as possible. True question.

These pain points and demand for users,Miwen’s power independent research and development cloud management platformThis platform is managed by enterprises. The information of different enterprises is isolated from each other and can simultaneously supervise different projects and various devices in each project.When the user needs remote maintenance, open the remote access function (green icon), click to jump to the device interface, you can view the device usage statusYou can also use the web terminal to make a more in-depth command line debug.

It is worth noting that in addition toThe user has permission settings, view, modify the username and password of the device, anyone includes merit power, there is no need to set up, check the accountIt greatly guarantees the security of equipment data.

In addition to remote operation and maintenance,The platform can also remotely monitor the CPU usage, hard disk usage, temperature, etc.. The hard drive is often the main reason for the problem of users. If the hard disk is full, the system cannot start, the remote monitoring function can effectively view the abnormal state, timely alarm, and make the corresponding countermeasure. As shown above, both the hard disk and the CPU have a sharp concave, indicating that the device is restarted at this point in time.

at the same time,Big screen display function is also availableIt is convenient for users to control the equipment in the project.

Demand 2: Application and model deployment, update

Milin motivationProvide graphical batch burn toolsIt can simultaneously support multiple devices to burn and mirror clones, and users can issue themselves from the volume of the containers and models.

Demand 3: Need a large number of engineers to customize development

Take the remote monitoring production site as an example, develop this function requires embedded engineers, front-end engineers, backend engineers, etc. Users who have limited resources have more hope that they can focus on the part that is really good, this part may be business functions, or the algorithm performance.

The video is an example of the production management system used in our company, showing rice powerBox, ready-to-use platform functionHelp users better integrate artificial intelligence with their business systems, speed up the speed of the project.

This production management system can remotely detect intrusion, fireworks, temperature and humidity sensor data, etc., system background reception, record, analysis of abnormal data, and further manage the library. In addition to providing a similar set of outlookable features in addition to different users’ needs, Milin Dynamics can also be passed directly to users, or allow users to upload their own algorithms themselves to quickly verify their algorithms.

08, the future calculation


Let’s discuss the future of the edge calculation.

As we all know,Next year NVIDIA will release the Embedded GPU of Orin.

For Xavier, in the CPU, ORIN’s CPU core is 50% more Xavier, and the single core performance will have further improvement. The CUDA core of GPU is 4 times that of Xavier, and the force reaches 254T, close to 3080ti and 3090. The level, although the memory bandwidth is not as good as Apple’s latest IMAX (400GB / s), but also reached an amazing 200Gb / s, it is possible to play the GPU computational performance very well.

Under the bonding of this chip, more industrial scenes will solve faster, and that is the top peak of embedded GPU?

No, let’s take another picture.


Atlan is the chip that NVIDIA announces that the chip is being developed. The power will reach 1000T, and 1000T is 4 times the most powerful 3090 desktop video card. Therefore, from ORIN, the performance of the edge calculation will be improved. At the same time, in various applications of the edge, it is no longer using SOC designed specifically for the data center, but has a strong powerful new chip specifically suitable for edge scenarios.

This change will push the edge application to a higher dimension, in the scene calculated,Use chips and programs designed specifically for edges to the future of the edge.

My sharing content is over, thank you for your listening.

Canadian Master’s Application Notice

Profitfully master the orientation of software engineering, select the applicable itself:

Technical Professional Overview: Computer Science (CS) is closely combined with mobile phone software and mobile phone software. Teaching system software. Professional wide caliber technology using it. According to the teaching and professional training of professional lesson, this technical professional uses scientific research in computer science and technology. Cultural education. Development and design and high-end talents.

In general, Australian software engineering majors can be divided into the following orientation:

Computer Science:

Computer science includes many branch industries; there are some calculations that pay attention to special results, such as electronic computer image processing; not what is the characteristics of the measurement of the problem, such as calculating diversification; The basic theory of computer language is a scientific research narrative measurement, and programming design is to handle special measurement problems in special computer languages. Summarket, computer science depends on basic mathematics, learning and training is highlighted by mobile phone software, for mathematics lessons. Optimization algorithm. Measurement. Effects of entity models. There are some colleges and even the establishment of computer science and technology in the field of art, such as Herch’s famous Waterloo University.

Computer science is particularly suitable for students with high school work ability. To strengthen your own competitiveness, you can have a planned participation in mathematics.

2. Internet big data

Learning content is all levels related to database management, including data storage, text retrieval, statistical analysis, and visual effects. If you develop design efficient optimization algorithms for the extra large data information group, a large and medium-sized information system is created for a wide range of newly used main purposes. It is also a scientific research with other industries, and there are online games. Design, data information personal privacy and security, etc.

3. Artificial intelligence technology

The key to learning content includes equipment concepts (including deep learning, expertise, intelligence), dynamic simulation system, kinetic model measurement, tactile control (HAPTIC control) natural language understanding and solving, human machine interaction technology, Nervous system estimation, machine vision, visual effect scenario cognitive capacity, computer vision, artificial immunity, manufacturing and control theory.

4. Information Management System

MIS, as a new technical professional, key goal is to maximize the use of modern computer and network communication technology to improve company information management, based on human resources, material resources, funds. Fund. Machine equipment. Technical The investigation of resources, create proper data information, production and processing solutions and make a variety of data materials to give administrators to manage, facilitate proper management decisions, and continue to enhance the company’s management capabilities and economic benefits.

Software Engineering Major School Rankings and Related Application Conditions:

University of Toronto:

Location: An province, Toronto

Ranking: McColin Medal Boys NO.2, Duo Duo NO.1

Admission regulations: related undergraduate majors, GPA: proposal 85 points

IELTS: 7.0 (single project 6.5) or TOEFL: 93 (creation. English speaking 22)

Waterloo University:

Location: An province, Waterloo

Rank: McColen Medical Boat Rank No.3, Duplex NO.3

Admission regulations: related undergraduate majors, GPA: 3.0 (2 years)

IELTS: 6.5 (single project 6.0) or TOEFL: 90

British American Columbia University:

Location: BC Province, Los Angeles

Rank: McColen Medical Boat Rank No.3, Duplex NO.3

Admission regulations: About the undergraduate professional environment and stipulate that a certain amount of computer professional courses have been taken, GPA: The proposed 85 points (985 211 proposes 80 points)

IELTS: 7 (Various parts of 6.5) or 100 (reading article 22 Creation 21 English Listening 22 English Speaking 21)

Location: Alberta, Edmonton

Australian postgraduate new semester started, most schools have only one season in each year, the key is to enroll in autumn. For schools and technical professional precision positioning. Language expression and GPA regulations. Procedures for application and raw materials are prepared in advance.

Petrong Shares Develop Agricultural Artificial Intelligence Countermeasures and Suggestions

Shanghai Herong Agricultural Science and Technology Development Co., Ltd. is obviously increasingly driving the development of an agricultural and intelligent technology development, accelerating operational efficiency and resource utilization. Developing agricultural artificial intelligence, making it a challenge and opportunity for my country, it is necessary to live, catch up with advanced technology, develop work should take the absorption, lending, innovation, and beyond the way to improve the research as soon as possible. Innovation? Application system to meet the requirements of agricultural development on agricultural monitoring, agricultural data analysis, agricultural equipment transformation and upgrading, agricultural products supply and marketing chain tracking, etc., improve agricultural intelligence level, promote the development of agricultural modernization, play "head geese Effect, add bricks in the era of human agricultural intelligence. Comprehensive analysis, the following suggestions for the development of agricultural intelligence in my country:

1) Pay attention to the cultivation and management of artificial intelligence related professional talents. The root of promoting science and technology development is talent. Domestic agriculture and forestry universities should conduct professional reforms in accordance with the development trend of intelligence agriculture to meet the needs of new intelligence agricultural industries on new agricultural science and technology talents. In addition, it should be actively encouraged to support enterprises to cultivate composite talents that have both manual intelligence and agricultural background, solve the practical problems of farmers, and provide intelligence and talent support for new technologies such as artificial intelligence in agriculture. In terms of scientific research and team building, it is encouraged research teams with multidisciplinary cross-integration.

2) Promote infrastructure construction of agricultural intelligence development. The development of agricultural artificial intelligence is inseparable from massive data accumulation and network real-time response. The farm agricultural infrastructure is not perfect, and agricultural data has high acquisition costs, which greatly limits the breadth and depth of machine learning in scenarios. It should pay attention to the construction of 5G infrastructure construction in agricultural materials and rural areas, improve the level of infrastructure of intelligent agricultural sensors, build agricultural production information and digitalization projects, introduce agricultural data sharing mechanisms, etc., provide fundamentals for the large-scale application of artificial intelligent agricultural equipment And conditions.

3) Promote research and development of agricultural production intelligent control technology. Promote agricultural production intelligence sensation, identify research and development of operation decision models, for agricultural planting, breeding different environments, establish a multi-source data fusion, agricultural whole process decision support method, building field crops, greenhouses, livestock and poultry, and water products In the field of decision management and intelligent control models, using cloud? Edge-end architecture, realize the intelligent decision system based on "agricultural brain" under data driver management.

4) Strengthen the development of intelligent equipment and systems. For agricultural production needs, accelerate the popularity of intelligent machines, improve resource utilization and agricultural output rate, and improve economic benefits. Cultivate my country’s advantageous intelligent agricultural machinery such as agricultural drones, enhance the cross-boundary technology integration of agriculture and other industries, meet new generation information technology, open innovation model, seamless integration of human wisdom and machinery intelligence, re-assessing agricultural future, and create new business opportunities. First, research and development special equipment should consider reducing cost and improving adaptability, hardware, the sensors on smart devices such as robots and drones can increase or decrease depending on the actual situation, and the control part is indwelling the air interface; software, support secondary development And expand, provide a good platform for human machine collaboration and multi-machine collaboration. Second, Based on the cloud? Side-end architecture to build a "agricultural brain" intelligent decision system: Cloud platform provides storage and computing services, and the edge calculates the robots and other equipment on the Internet of Things and other equipment real-time dynamic management, the clouds are coordinated to the agricultural robot field The job provides decision support. Finally, the future agricultural robot will bear more and more job tasks and become key components in agricultural production. For this purpose, new technologies such as artificial intelligence, Internet of Things, big data, virtual perception system, multi-sensor fusion, human machine blending is required.

As children come back to school, they will need both time and patience

While the pandemic and associated school closure has affected us in many ways, loss of learning among children is emerging among the most explicit and worrying aspects. This learning loss comprises two dimensions — one is the learning that has not happened due to school closures. To this loss of curricular learning is added the “forgetting” of what they already knew. This forgetting is not unusual — it is clearly seen after long holidays, and is generally made up during the first few weeks of schooling. However, when this loss is of foundational abilities like reading, writing and basic arithmetic, it deeply hinders further learning.

Loss of learning due to school closure during the pandemic has been seen the world over. Quantified in terms of months that children are “behind” their class, it varies from less than a month after 11 weeks of school closure to four years after 57 weeks of school closure. According to the report, “What’s next? Lessons on Education Recovery” by UNICEF, UNESCO, World Bank and OECD, among measures taken to alleviate this loss, 41 per cent of countries reported extending the academic year while 42 per cent reported prioritising certain curriculum areas or skills. Over two-thirds of countries reported implementing remedial measures to address learning gaps for primary and secondary school students when schools reopened.

Our primary schools have been closed for about 500 days, which translates to over 70 weeks of schooling. Given the amount of time schools have been closed, as we reopen now, we cannot start with the regular curriculum as if it is the beginning of a regular academic year. We need to think deeply about what should be done. This question is particularly moot for primary schools, where the foundations of later learning are established. To answer this question, it is necessary to examine how children learn in primary schools. Children learn not only through interaction in the classroom but also through observation, dialogue and exploration through unstructured experiences. Thus, given that we have to make up for over 70 weeks of school closure, we must not hurry children into the learning process. Not only the learning associated with the current class but relearning from the previous classes must be in focus.

The next question is — what is important to learn? The learning outcomes for each class have been clearly indicated by the National Council of Educational Research and Training (NCERT), which is the nodal academic institution for school education at the national level. These learning outcomes focus on the abilities children have to acquire as opposed to the content of textbooks. Thus, reading a poem is important, memorising the content of the poem is not important. Being able to add is important, not adding all the problems at the end of the chapter in the textbook. And language and mathematics are most important, since they enable the learning of other subjects. Thus, learning outcomes of specific subjects must be prioritised, and the curriculum reset for at least a couple of years.

When schools reopen, differences in the learning levels of children will be starker than before. A solution that is deceptively simple is that of placing children in groups according to their current learning levels. Termed ability grouping, it seems like the perfect solution, with children starting with similar sets of abilities and proceeding thereon. However, the approach of grouping students based on their abilities often results in “labelling”, adversely impacting their self-esteem and worth; research studies have found students in “low” ability groups have significantly lower self-esteem than low achievers in mixed ability classes, and are also likely to have behavioural problems. This approach also neglects to take into account the fact that children learn from each other. It is not unusual to have children at different levels in the same classroom. Some schools use this difference as a resource, using sets of teaching-learning materials that children use in groups under the guidance of teachers. As children attain pre-set learning milestones, they move onto the next level. This approach using peer learning benefits all.

When we examine the available data from various studies on the learning levels that our children are at, it is clear that at the primary level, the focus ought to be on foundational abilities. For instance, Azim Premji Foundation’s field study in January 2021 across 44 districts covering five states indicated that nearly three-fourths of the children in Class II have lost the ability to identify a word in print; in Class IV, for instance, a majority of them have lost the ability to express the gist of a poem while in Class VI more than half the children lost the ability to write their views on various events happening around them. The recently released SCHOOL survey carried out across 15 states shows that overall 42 per cent of children in urban areas and 48 per cent in rural areas are unable to read more than a few words. These studies indicate that most children across the primary grades have lost the basic abilities required to continue their learning journeys.

The curricular priorities will have to be set specific to the stages of schooling. If the priority at primary level is on recovery of foundational abilities in language and mathematics, the focus in middle school should be an integrated approach to achieving learning outcomes across subjects, while at the secondary and senior secondary level, core learning outcomes must be identified and mapped to textbooks; and for this level additional material could be developed, given that students at this stage are capable of some independent study.

As persons closest to learners, teachers must be given the autonomy and support to determine what children learn and when, within the broad contours of the curriculum. Changes in curriculum and the approach to teaching-learning would require orientation of teachers, and materials to support their work with children. This material must be attractive and meaningful, related to children’s context, while encouraging them to speak about visuals, read small pieces of text, respond to interesting questions, and perform simple exercises. This material must cover a range of abilities so the teacher can use similar resources for the entire class.

To track recovery from learning loss, periodic assessment would be necessary — this must be done in a non-threatening way, by the teacher through observation and interaction with her students. The stress of regular testing must not demotivate children from learning.

Finally, it is important to acknowledge that school closure has resulted in more than learning loss. It has led to a disconnect from the processes of schooling. Children have experienced loss; some have entered the workforce while others have been given responsibilities within the household. The most important thing that must be done when schools reopen is to welcome them back — to listen to their stories, to give them time to settle back into routines, to involve them in activities that allow them to express themselves. Time and patience may help us find ways to compensate not only the learning loss but also to change our schools for the better.