Things that can be done: 1. Can help customers participate in innovation activities such as product demand analysis and product design, and contribute to product innovation; 2. Conduct product fault diagnosis and prediction, which can be used in products After-sales service and product improvement; 3. Analyze and optimize the industrial supply chain to achieve a significant increase in warehousing, distribution, and sales efficiency and a significant reduction in costs; 4. Use big data to analyze current demand changes and combination forms to achieve product sales Forecasting and demand management; 5. Production planning and scheduling; 6. Product quality management and analysis; 7. Industrial pollution and environmental protection testing.
The operating environment of this tutorial: Windows 7 system, Dell G3 computer.
Industrial Internet and big data applications refer to a large-scale network that connects various machines, equipment groups, facilities and system networks in the world with advanced sensors, controls and software applications. Things like MRI machines, aircraft engines, electric vehicles, and even power plants can all be connected to the Industrial Internet. By combining network interconnection and big data analysis to make reasonable decisions, we can more effectively unleash the potential of each machine and improve productivity. The most significant feature of the Industrial Internet is that it can maximize production efficiency, save costs, promote the upgrading of equipment technology, and improve efficiency.
To put it simply, it means combining industry with the Internet, and then combining it with big data, because big data is indeed very convenient now, and every industry has its uses. In order to improve efficiency and increase benefits.
Scenario analysis of industrial Internet and big data applications
1. Accelerate product innovation
The interaction and transaction behavior between customers and industrial enterprises will Generating a large amount of data, mining and analyzing these customer dynamic data can help customers participate in innovative activities such as product demand analysis and product design, and contribute to product innovation. Ford is a leading example in this regard. They have applied big data technology to the product innovation and optimization of the Ford Focus electric vehicle, making this car a veritable "big data electric vehicle". The first-generation Ford Focus EV generates massive amounts of data while driving and parking. While driving, the driver continuously updates the vehicle's acceleration, braking, battery charge, and location information. This is useful for drivers, but the data is also sent back to Ford engineers to understand customers' driving habits, including how, when and where they charge. It continuously transmits data about the vehicle's tire pressure and battery system to the nearest smartphone, even when the vehicle is stationary.
This customer-centric big data application scenario has many benefits, because big data enables valuable new product innovation and collaboration methods. Drivers receive useful, up-to-date information, while engineers in Detroit aggregate information about driving behavior to understand customers, plan product improvements, and implement new product innovations. And power companies and other third-party providers can also analyze millions of miles of driving data to decide where to build new charging stations and how to prevent fragile grids from being overloaded.
2. Product fault diagnosis and prediction
This can be used for product after-sales service and product improvement. The introduction of ubiquitous sensors and Internet technology has made real-time diagnosis of product faults a reality, and big data applications, modeling and simulation technologies have made it possible to predict dynamics. During the search for missing Malaysia Airlines MH370, the engine operation data obtained by Boeing played a key role in determining the missing path of the aircraft. Let’s take Boeing’s aircraft system as an example to see how big data applications play a role in product fault diagnosis. On a Boeing aircraft, hundreds of variables including engines, fuel systems, hydraulic and electrical systems make up the in-flight status, and this data is measured and transmitted in less than a few microseconds. Taking the Boeing 737 as an example, the engine can generate 10TB of data every 30 minutes in flight.
These data are not only engineering telemetry data that can be analyzed at a certain point in the future, but also promote real-time adaptive control, fuel usage, part failure prediction and pilot notification, and can effectively realize fault diagnosis and prediction. Let’s take another example from General Electric (GE). The GE Energy Monitoring and Diagnostics (M&D) Center in Atlanta, USA, collects data from thousands of GE gas turbines in more than 50 countries around the world. It can collect 10G of data for customers every day. Analyzing the constant big data flow from sensor vibration and temperature signals within the system, these big data analyzes will provide support for GE's gas turbine fault diagnosis and early warning. Wind turbine manufacturer Vestas also improves wind turbine layouts by cross-analyzing weather data with periodic turbine instrumentation data, thereby increasing the power output levels of wind turbines and extending their service life.
3. Big data application in industrial IoT production lines
Modern industrial manufacturing production lines are equipped with thousands of small sensors to detect temperature, pressure, heat, vibration and noise. Because data is collected every few seconds, many forms of analysis can be achieved using these data, including equipment diagnosis, power consumption analysis, energy consumption analysis, quality accident analysis (including violations of production regulations, component failures), etc. First of all, in terms of production process improvement, using these big data during the production process can analyze the entire production process and understand how each link is performed. Once a certain process deviates from the standard process, an alarm signal will be generated, errors or bottlenecks can be discovered more quickly, and the problem can be solved more easily. Using big data technology, you can also build a virtual model of the production process of industrial products, simulate and optimize the production process. When all processes and performance data can be reconstructed in the system, this transparency will help manufacturers improve their production processes. . For another example, in terms of energy consumption analysis, sensors are used to centrally monitor all production processes during the equipment production process. Abnormalities or peaks in energy consumption can be discovered, so that energy consumption can be optimized during the production process and all processes can be monitored. Analysis will significantly reduce energy consumption.
4. Analysis and Optimization of Industrial Supply Chain
Currently, big data analysis has become an important means for many e-commerce companies to improve the competitiveness of their supply chain. For example, the e-commerce company JD.com uses big data to analyze and predict the demand for goods in various places in advance, thereby improving the efficiency of distribution and warehousing and ensuring the customer experience of goods arriving the next day. Product electronic identification technology such as RFID, Internet of Things technology, and mobile Internet technology can help industrial companies obtain big data of the complete product supply chain. Using these data for analysis will bring about significant improvements in warehousing, distribution, and sales efficiency and cost. decline.
Taking Haier as an example, Haier’s supply chain system is very complete. It uses the market chain as a link and order information flow as the center to drive the movement of logistics and capital flow, integrating global supply chain resources and global users. resource. In all aspects of Haier's supply chain, customer data, internal corporate data, and supplier data are aggregated into the supply chain system. Through big data collection and analysis in the supply chain, Haier can continue to improve and optimize the supply chain, ensuring Haier's agile response to customers. There are more than a thousand larger OEM suppliers in the United States, providing more than 10,000 different products to manufacturing companies. Each manufacturer relies on market forecasts and other different variables, such as sales data, market information, exhibitions, news, competitor data , even weather forecasts, etc. to sell their products.
Using sales data, product sensor data and data from supplier databases, industrial manufacturing companies can accurately predict demand in different regions around the world. Manufacturing companies can save a lot of costs because they can track inventory and sales prices and buy when prices fall. If they can reuse the data generated by the sensors in the product to know what's wrong with the product and where parts are needed, they can also predict where and when parts will be needed. This will greatly reduce inventory and optimize the supply chain.
5. Product sales forecast and demand management
Use big data to analyze current demand changes and combinations. Big data is a good sales analysis tool. Through the multi-dimensional combination of historical data, we can see the proportion and changes of regional demand, the market popularity of product categories, the most common combination forms, the level of consumers, etc. Use this to adjust product strategy and distribution strategy. In some analyses, we can find that the demand for stationery in cities with more colleges and universities will be much higher during the school season. In this way, we can increase promotions for dealers in these cities to attract them to order more during the school season. Capacity planning begins one or two months in advance to meet promotional needs. In terms of product development, product functions and performance are adjusted based on the concerns of the consumer group. For example, a few years ago everyone liked to use music phones, but now people are more inclined to use mobile phones to surf the Internet, take photos and share them, etc. The improvement of the camera function of mobile phones is one Trend, 4G mobile phones also occupy a larger market share. Through big data analysis of some market details, more potential sales opportunities can be found.
6. Production planning and scheduling
The manufacturing industry faces a multi-variety and small-batch production model. The refinement of data, automatic, timely and convenient collection (MES/DCS) and variability have led to a dramatic increase in data. Coupled with more than ten years of informatized historical data , which is a huge challenge for APS that requires quick response. Big data can give us more detailed data information, discover the probability of deviation between historical predictions and actual, consider production capacity constraints, personnel skill constraints, material availability constraints, tooling and mold constraints, and use intelligent optimization algorithms to formulate pre-planned production schedules and monitor If there is any deviation between the plan and the actual situation on site, the production schedule will be dynamically adjusted. Help us avoid the shortcomings of "portraits" and directly impose group characteristics on individuals (work center data is directly changed into specific data of equipment, personnel, molds, etc.). By correlating data and monitoring it, we can plan for the future. Although big data has some flaws, as long as it is properly applied, big data will become a powerful weapon for us. At that time, Ford asked what the customer needs of big data were, and the answer was "a faster horse", not the cars that are now popular. Therefore, in the world of big data, creativity, intuition, adventurous spirit and intellectual ambition are particularly important.
7. Product quality management and analysis
The traditional manufacturing industry is facing the impact of big data, and is eagerly looking forward to product development, process design, quality management, production operations and other aspects. There are innovative approaches emerging to address big data challenges in industrial contexts. For example, in the semiconductor industry, chips will go through many complex processes such as doping, layering, photolithography, and heat treatment during the production process. Each step must meet extremely stringent physical property requirements. Highly automated equipment is required to process products. At the same time, a huge amount of detection results are also generated simultaneously. Is this massive data a burden for the company or a gold mine for the company? If it is the latter, then how can we quickly see through the clouds and accurately discover the key reasons for product yield fluctuations from the "gold mine"? This is a A technical problem that has troubled semiconductor engineers for many years.
After the wafers produced by a semiconductor technology company go through the testing process, a data set containing more than a hundred test items and millions of lines of test records is generated every day. According to the basic requirements of quality management, an essential task is to conduct a process capability analysis for more than one hundred test items with different technical specifications. If we follow the traditional working model, we need to calculate more than one hundred process capability indices step by step and assess each quality characteristic one by one. Regardless of the huge and cumbersome workload here, even if someone can solve the calculation problem, it is difficult to see the correlation between them from the more than 100 process capability indexes, and it is even harder to evaluate the overall quality of the product. Have a comprehensive understanding and summary of performance. However, if we use the big data quality management analysis platform, in addition to quickly obtaining a long process capability analysis report with traditional single indicators, more importantly, we can also obtain many new analyzes from the same big data set. result.
8. Industrial pollution and environmental protection testing
The most impressive thing about "Under the Dome" is that through visual reports, Chai Jing's team conveys to the audience the seriousness of the haze problem, the causes, etc.
This brings us a revelation, that is, big data is of great value to environmental protection. Where does the raw data for the charts in "Under the Dome" come from? In fact, not all of them are obtained through high-level relationships. Many of the data are publicly available and can be found on the Chinese government website, the websites of various ministries and commissions, the official website of PetroChina and Sinopec, the official website of environmental protection organizations, and some special Organizations, more and more public welfare and environmental protection data can be queried, including national air, hydrological and other data, meteorological data, factory distribution and pollution emission compliance data, etc. It's just that these data are too scattered, too professional, lack analysis, and have no visualization, so ordinary people can't understand them. If you can understand it and keep paying attention, big data will become an important means for society to supervise environmental protection. The recent launch of Baidu's "National Pollution Monitoring Map" is a good way to do this. Combined with open environmental protection big data, Baidu Map has added a pollution detection layer. Anyone can use it to view the whole country and the provinces and cities in their own region. All in The location information, name of the organization, types of emission sources, and the latest pollution discharge standards announced by the Environmental Protection Bureau (including various thermal power plants, state-controlled industrial enterprises, and sewage treatment plants) under the supervision of the Environmental Protection Bureau. You can check the pollution source closest to you, and a reminder will appear to tell you which items tested at the monitoring point exceed the standard and how many times it exceeds the standard. This information can be shared to social media platforms in real time to inform friends and remind everyone to pay attention to pollution sources and personal safety and health.
Summary: The value potential of industrial big data applications is huge. However, there is still much work to be done to realize these values. One is the issue of establishing big data awareness. In the past, there was such big data, but due to lack of awareness of big data and insufficient data analysis methods, a lot of real-time data was discarded or shelved, and the potential value of a large amount of data was buried. Another important issue is the problem of data islands. The data of many industrial companies is distributed in various silos across the enterprise, especially within large multinational companies, making it difficult to extract this data across the entire enterprise. Therefore, an important issue in industrial big data application is integrated application.
For more related knowledge, please visit the FAQ column!
The above is the detailed content of What are industrial Internet and big data applications used for?. For more information, please follow other related articles on the PHP Chinese website!