• Không có kết quả nào được tìm thấy

12.2% 171000 190M TOP 1% 154 6300

N/A
N/A
Nguyễn Gia Hào

Academic year: 2023

Chia sẻ "12.2% 171000 190M TOP 1% 154 6300"

Copied!
62
0
0

Loading.... (view fulltext now)

Văn bản

Monitoring, supervision and control layer ensure the real-time optimization and advanced process control. The rest of the chapter will mainly focus on the factory production of digital manufacturing and describe the 3-C's implementation plan, the enabling technology and the achievable outcome ahead.

Conclusion

Finally, remote manning and control of the entire autonomous factory platform is accomplished through the dashboard in the command and control center. This autonomous factory software platform under development will enable: (1) the remote connectivity for the manufacturing solution to access their local factory floor in China and (2) the 24×7 real-time monitoring and management of the factory products outside of China - system.

TOP 1%

Introduction

  • Mechanism optimization
  • Energy consumption optimization
  • Process optimization

The error of the tool during manufacturing and machining wear [24] requires us to monitor it in real time to detect problems in time, check and integrate and summarize these problems, and then establish an error compensation model through the data system [ 25]. The hardness and thickness of the workpiece during the machining process [43] and the power of the machine tool are taken into account [44].

CNC common processing optimization approach

  • Cutting force monitoring
  • Processing path optimization
  • Processing dynamic profile optimization

In order to prevent CNC machining in normal condition, the acceleration and speed of the movement stages should be monitored and should be less than the maximum design range of the CNC machine. With the known coordinates of two adjacent track pointsðxnþ1,znþ1Þ,ðxn,znÞ and the velocity of the major axis, the acceleration and velocity of point n are approximately. Extreme value Stand root mean square value Sq of the shape of the machining surface are the two main indicators of machining accuracy and are calculated by the following equations:

In order to minimize the value of S_(t) and S_(q), the optimized machining profile should be performed as shown in Figure 8. In order to make the movement of the machine tool smooth and the processing more stable, the concept of "jerk" is introduced and made as constant. As we know, the reaction force of the work table and the feed screw becomes infinite if the acceleration changes suddenly.

Usually, in order to obtain high quality of the machining parts and extend the life of the CNC machining, the speed of the CNC is kept as constant as possible in addition to the start and end stages of the machining processing.

Figure 5 shows the monitored acceleration in x and z directions respectively.
Figure 5 shows the monitored acceleration in x and z directions respectively.

Processing tools deflection compensation

  • Displacement sensor for tool compensation
  • Tool deflection compensation approach
  • Algorithm adopted in tool deflection compensation
  • Tool deflection compensation experiment

The cloud computing device uses genetic programming (see Figure 12) to generate an algorithm to compensate for the bending of the cutting tool and send it back to the local 5G AI edge computing network. The 5G AI edge computing device then calculates the compensation value and sends it to the MCU to compensate for the deflection of the cutting tool. Fitness¼ min abs predicted resultð ð expected resultÞÞ: (10) The genetic programming scheme for tool deflection compensation is shown in Figure 12.

The optimal tool deflection compensation algorithm is obtained through hundreds of generation selection, crossover and mutation operations until set fitness function is reached. The cutting surface error compensation with and without cutting tool deflection compensation is shown in Figure 13. The deviation distribution of machining with/without tool deflection compensation is shown in Figure 14 in three dimensions.

It can be seen that at almost all measured points, the machine error on a curved surface without tool deviation is greater than that on a curved machining surface with tool deviation compensation.

Figure 11 shows 5G AI Edge computing configuration for CNC cutting tool deflection compensation
Figure 11 shows 5G AI Edge computing configuration for CNC cutting tool deflection compensation

Processing error feedback compensation

  • Experimental setup of error feedback compensation
  • Signal processing in error feedback compensation
  • Experimental results of error feedback compensation

Moreover, the error is the largest at the lower area of ​​bending of the curved surface, which reaches 0.053 mm. It can be seen that the maximum machining error is reduced by 35% from 0.032 to 0.021 mm when the error feedback compensation is applied. Moreover, in two series (point 20–28, point 45–55), machining error is larger than that with only tool deflection compensation strategy.

The deviation distribution of machining without compensation, with tool deflection compensation, with error feedback compensation is shown in Figure 18. It can be seen that the deviation distribution of the curved surface of the machine with feedback compensation is minimal. On the other hand, the deviation distribution of the curved surface of the machine without tool deflection and error feedback compensation is the largest.

In other words, to achieve a good machining quality product, the tool deflection and error feedback compensation strategy must be adopted.

Figure 16 shows error feedback compensation signal noise filter and recon- recon-struction processing
Figure 16 shows error feedback compensation signal noise filter and recon- recon-struction processing

Processing parameter optimization compensation

  • Network configuration for processing parameter optimization
  • Data collection for processing parameter optimization
  • Signal processing technologies for processing parameter optimization There are various signal processing technologies for analyzing the monitoring
  • Experimental results of processing parameter optimization

The CNC machine processing monitoring signal and the corresponding machine number information are sent to the company's data center and the cloud computer data center if necessary. The technician from the company then sends a control command file or a file with the new compensation algorithm trained by cloud computing to the customer's computer in the CAM center. To obtain the vibration signal to train the GP, Neural Networks (NNR) and Support Vector Machine (SVM) Algorithm, two wireless accelerometers, Sensor 1 and Sensor 2, are attached to the cutting tool.

Their signals will be sent to the cloud for basic GP, NNR and SVM computing. When the rotation speed of the main spindle of the CNC machine is the same, the same feed rate is also selected. In addition, only the frequency domain dominates the frequencies and their amplitudes are selected to be sent to the cloud to reduce the data size and increase the data transfer rate.

The experimental parameters such as material, dimensions, temperature, reaction forces, vibration data and machining quality such as tolerances will be sent to the Multilayer Artificial Neural Network (MANN) to train the optimized machining parameters.

Figure 20 shows the cloud-based intelligent manufacturing configuration in the CAM center
Figure 20 shows the cloud-based intelligent manufacturing configuration in the CAM center

Conclusions

The machining of the complex surface can be decoupled to simpler machining for path optimization to minimize speed fluctuation-induced machining errors. Before the deep learning approach is applied in cloud computing with expert system and database, all the information in the train data instance, such as raw material type and dimensions, systematic parameters of CNC machine tools and processing operating conditions and vibration output from the CNC machine. tool must be sent to a cloud-based computing center. Multi-objective optimization of operating conditions in a cutting process based on low CO2 emission costs.

Numerical modeling of the influence of process parameters and workpiece hardness on white layer formation in AISI 52100 steel. Use of the factory with its two platforms as demonstrators for Industry 4.0 (development of the platform should be completed within the next 6 months). Leveraging the platforms to test new building blocks, technologies and solutions for their potential effects on KPI before investing in them.

Play with various combinations of the two platforms to create different variants of factories of the future and to see their impact on KPIs.

Human factors in logistics and warehouse industry

Indian scenario for the human factors in logistical/warehousing industries

Need for autonomous mobile robot in manufacturing industries Automation in the manufacturing industry will ensure that the end result will

Autonomous mobile robots are machines designed to maneuver themselves in an obstacle-filled environment using sensors and feedback. Due to its design, it can be used in the manufacturing industry, thereby reducing wear and tear in various industrial components and improving productivity.

Human robot interactions in logistics/warehousing industry

Information about the status of the machine is provided to the human operator through the interface, and the operator directly controls the machine through his commands and maneuvers the machine appropriately. The operator notifies the supervisor of any interruptions that may affect the overall performance of the system, allowing the supervisor to perform exception handling tasks. The supervisor layer interfaces are for a human supervisor in the human-machine system.

In normal scenarios, the supervisor will monitor the key monitoring indexes for logistics warehouses and maintain the task progress. In cases of exceptions, the supervisor must advise the operator to take corrective action. Design of human machine systems should consider that human machine system should help humans or supervisor to deal with an unforeseen scenario.

Due to a high degree of complexity, the problems of exceptions will only be challenging through autonomous robots, creating the need for human involvement.

Present problems in autonomous navigation in factory set-up

Further due to the lack of regular maintenance schedule it will reduce the lifespan of the performance of the robot. Due to the functionality of the AMR software once the steps involved in the production process are trained, it will retain these steps thus reducing labor intensity. Next, an action function is defined, which will be a Lagrange integral for the path from the beginning to the end. according to Eq.

Typically, the initial cost for such robots will be high due to the complexity of the system. Some of the current solutions included in the IISC CEFC Smart Manufacturing Facility are shown in Figures 3–5. In addition, the stabilizer attached to the robot arm will ensure the smooth operation of the robot.

There are magnetic strips provided along the floor of the smart factory which will guide the robot through different parts of the factory.

Conclusion

The motion path for the robot can be appropriately programmed according to the requirements and can be uploaded to the interactive human machine interface. Human machine interaction will play an important factor in determining the effectiveness of the process. The proposed theory is simple and can be used for real-time obstacle detection for a complex environment.

The proposed concept can be viewed for a multi-robot system, and IOT can be used to better control the proposed warehouse robot system. Distributed under the terms of the Creative Commons Attribution - NonCommercial 4.0 License (https://creativecommons.org/ . licenses/by-nc/4.0/), which permits use, distribution, and reproduction for noncommercial purposes, provided the original is properly cited.

Hình ảnh

Figure 5 shows the monitored acceleration in x and z directions respectively.
Figure 7 shows the implementation of cutting tool compensation to reduce the machining error
Figure 11 shows 5G AI Edge computing configuration for CNC cutting tool deflection compensation
Figure 16 shows error feedback compensation signal noise filter and recon- recon-struction processing
+7

Tài liệu tham khảo

Tài liệu liên quan

- Đi đều vòng phải.. - Chia tổ tập luyện theo khu vực quy định do tổ trưởng điều khiển.. -Tập hợp lớp, cho các tổ thi đua trình diễn... b) Trò chơi vận động: