Traditional Culture Encyclopedia - Traditional virtues - Eight industrial big data application scenarios in the era of the Internet of Things
Eight industrial big data application scenarios in the era of the Internet of Things
Eight industrial big data application scenarios in the era of Internet of Things
Industrial big data is a brand new concept, which literally refers to the big data generated in the application of informationization in the industrial field.
With the deep fusion of informationization and industrialization, information technology has penetrated into all aspects of the industrial enterprise chain, and technologies such as barcode, two-dimensional code, RFID, industrial sensors, industrial automatic control system, industrial Internet of Things (IoT), ERP, CAD/CAM/CAE/CAI, and so on, have been widely applied to industrial enterprises, especially the Internet, mobile Internet, and Internet of Things (IoT). The application of new generation information technology in the industrial field, industrial enterprises have also entered the new development stage of Internet industry, and the data owned by industrial enterprises are increasingly rich. Industrial enterprises in the production line is in high-speed operation, the amount of data generated, collected and processed by industrial equipment is much larger than the data generated by computers and manpower in the enterprise, from the data type is also mostly unstructured data, the high-speed operation of the production line of the real-time requirements of the data is also higher. Therefore, the problems and challenges faced by industrial big data applications are not less than those faced by big data applications in the Internet industry, and in some cases are even more complex.
Industrial big data applications will bring a new era of innovation and change for industrial enterprises. Through low-cost sensing, high-speed mobile connectivity, distributed computing and advanced analytics brought about by the Internet, mobile Internet of Things, etc., information technology and the global industrial system are y converging, bringing profound changes to global industry and innovating the way companies develop, produce, operate, market and manage. These innovations are bringing faster speeds, greater efficiencies, and greater insights to industrial companies in different industries. Typical applications of industrial big data include product innovation, product fault diagnosis and prediction, IoT analysis of industrial production lines, supply chain optimization of industrial enterprises, and precision marketing of products, among many others. This article will sort out the application scenarios of industrial big data in manufacturing enterprises one by one.
1. Accelerate product innovation
The interaction and transaction behavior between customers and industrial enterprises will generate a large amount of data, mining and analyzing these customer dynamic data can help customers participate in product demand analysis and product design and other innovative activities, contributing to product innovation. Ford is a role model in this regard, they will be big data technology applied to the Ford Focus Electric product innovation and optimization, this car has become a real "big data electric car". The first-generation Ford Focus Electric generates large 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 the driver, but the data is also sent back to Ford engineers to understand the customer's driving habits, including how, when and where to charge. Even when the vehicle is at a standstill, it continues to send data about the vehicle's tire pressure and battery system to the nearest smartphone.
This customer-centric big data application scenario has multiple benefits, as big data enables valuable new types of product innovation and collaboration. Drivers receive useful, up-to-date information, while Detroit-based engineers aggregate information about driving behavior to understand customers, develop product improvement plans, and implement new product innovations. And, electric utilities and other third-party providers can analyze millions of miles of driving data to determine where to build new charging stations and how to prevent overloading the fragile power grid.
2. Product Failure Diagnosis and Prediction
This can be used for after-sales service and product improvement. The introduction of ubiquitous sensors and Internet technologies makes real-time diagnosis of product failures a reality, while big data applications, modeling and simulation technologies make it possible to predict dynamics. During the search for the lost Malaysia Airlines MH370, the engine operation data obtained by Boeing played a key role in determining the lost path of the airplane. Let's take Boeing's airplane system as a case study to see how big data applications play a role in product troubleshooting. On Boeing's airplanes, hundreds of variables such as engines, fuel systems, hydraulics and electrical systems make up the on-air status, and this data is measured and sent less than once every few microseconds. In the Boeing 737, for example, the engines generate 10 terabytes of data every 30 minutes in flight.
These data are not just engineering telemetry that can be analyzed at some point in the future, but they also facilitate real-time adaptive control, fuel usage, parts failure prediction and pilot briefings that can effectively enable troubleshooting and prediction. Look at another General Electric (GE) example, the GE Energy Monitoring and Diagnostics (M&D) Center in Atlanta, GA, collects data from thousands of GE gas turbines in more than 50 countries around the world, and is able to collect 10G of data per day alone for its customers, and by analyzing the constant streams of big data that come from the vibration and temperature signals from sensors in the system, these big data analytics will provide GE with the ability to gas turbine fault diagnosis and early warning. Wind turbine manufacturer Vestas has also been able to improve wind turbine layouts by cross-analyzing weather data and period turbine instrumentation data, thereby increasing the level of power output from the wind turbines and extending their service life.
3. Big data for industrial IoT production lines
Modern industrial manufacturing lines are fitted 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 this data, including equipment diagnostics, electricity consumption analysis, energy consumption analysis, and quality incident analysis (including violations of production regulations and component failures). First, in terms of production process improvement, using this big data during the production process makes it possible to analyze the entire production process and understand how each step is being executed. Once there is a process that deviates from the standard process, an alarm signal will be generated, which can more quickly find out where the error or bottleneck is, and it will be easier to solve the problem. Using big data technology, it is also possible to build virtual models of the production process of industrial products to simulate and optimize the production process, and when all process and performance data can be reconstructed in the system, this transparency will help manufacturers to improve their production processes. For example, in the analysis of energy consumption, the use of sensors to centrally monitor all production processes in the production of equipment can identify abnormal or peak situations in energy consumption, which can be optimized in the production process of energy consumption, the analysis of all processes will greatly reduce energy consumption.
4. Industrial supply chain analysis and optimization
Currently, big data analysis has been an important means for many e-commerce enterprises to enhance the competitiveness of the supply chain. For example, e-commerce enterprise Jingdong Mall, through big data to analyze and predict the demand for goods around in advance, thus improving the effectiveness of distribution and warehousing, to ensure that the next day goods to the customer experience. RFID and other product electronic identification technology, Internet of Things technology and mobile Internet technology can help industrial enterprises to obtain the complete product supply chain of big data, the use of these data for analysis, will bring warehousing, distribution, sales efficiency and a significant reduction in costs.
Taking Haier as an example, Haier has a perfect supply chain system, which takes the market chain as a link, takes the order information flow as the center, drives the movement of logistics and capital flow, and integrates the global supply chain resources and global user resources. In all aspects of Haier's supply chain, customer data, internal data and supplier data are aggregated into the supply chain system. Through the collection and analysis of big data in the supply chain, Haier is able to continuously improve and optimize its supply chain, which ensures Haier's agile response to customers. There are more than a thousand larger OEM suppliers in the U.S., providing more than 10,000 different products to manufacturing companies, each of which relies on market forecasts and other different variables, such as sales data, market information, tradeshows, news, competitor data, and even weather forecasts, to sell their products.
Using sales data, sensor data on products, and data from supplier databases, industrial manufacturers can accurately predict demand in different regions of the world. By tracking inventory and selling prices and buying when prices fall, manufacturers can realize significant cost savings. If they then utilize the data generated by the sensors in the product to know what is failing and where parts are needed, they can also predict where and when parts will be needed. This would dramatically reduce inventory and optimize the supply chain.
5. Product Sales Forecasting and Demand Management
Big data is used to analyze current demand changes and mix forms. Big data is a good sales analysis tool, through the multi-dimensional combination of historical data, we can see the proportion and changes in regional demand, the market popularity of product categories and the most common forms of combinations, the level of consumers, etc., in order to adjust the product strategy and store strategy. In some analysis we can find that the demand for stationery in cities with more colleges and universities will be much higher in the school season, so we can increase the promotion of dealers in these cities to attract them to order more in the school season, and at the same time, we can start the production capacity planning one or two months before the school season to meet the promotional demand. In terms of product development, the adjustment of product functions and performance is made through the focus of consumer groups. For example, a few years ago, people liked to use music phones, but now they are more inclined to use cell phones to surf the Internet and take photos for sharing, etc. The improvement of the photo function of cell phones is a trend, and 4G cell phones also occupy a larger market share. By analyzing some market details through big data, more potential sales opportunities can be found.
6. Production planning and scheduling
Manufacturing industry facing multi-species and small batch production mode, data refinement automatic timely and convenient collection (MES/DCS) and versatility lead to a dramatic increase in data, coupled with more than a decade of information technology of the historical data for the need to respond quickly to the APS, is a huge challenge. Big data can give us more detailed data information, discover the probability of deviation between historical forecast and actual, consider capacity constraints, personnel skills constraints, material availability constraints, tooling constraints, through intelligent optimization algorithms, to formulate a pre-planning scheduling, and monitor the deviation between the plan and the actual site, and dynamically adjust the plan scheduling. Help us to avoid the defects of "portrait", directly impose the group characteristics directly to the individual (work center data is directly changed to a specific equipment, personnel, mold and other data). By correlating and analyzing the data and monitoring it, we can plan for the future. Although, Big Data is slightly flawed, as long as it is properly applied, Big Data will turn into a powerful weapon for us. Back in the day, Ford asked what the customer need for Big Data was. The answer was "a faster horse", not the automobile that is now so popular. So creativity, intuition, risk-taking, and intellectual ambition are especially important in the world of big data.
7. Product quality management and analysis
The traditional manufacturing industry is facing the impact of big data, and is eagerly awaiting the birth of innovative methods to meet the challenges of big data in the industrial context in all aspects of product research and development, process design, quality management, and production operations. For example, in the semiconductor industry, chips in the production process will undergo many times doping, layering, lithography and heat treatment and other complex processes, each step must meet the extremely demanding physical characteristics of the requirements of the highly automated equipment in the processing of products at the same time, but also synchronized to generate a huge number of test results. These massive data is actually the burden of the enterprise, or the enterprise's gold mine? If the latter, then how to quickly see the sun, from the "gold mine" in the accurate discovery of the key reasons for product yield fluctuations? This is a semiconductor engineers have been plagued by years of technical difficulties.
A semiconductor technology company produces wafers in the test link, every day will contain more than a hundred test items, the length of several million lines of test records of the data set. According to the basic requirements of quality management, an essential task is the need for these technical specifications of the requirements of the more than one hundred test items were carried out a process capability analysis. According to the traditional working mode, we need to calculate more than one hundred process capability indexes step by step, and evaluate each quality characteristic one by one. Here, regardless of the huge and cumbersome workload, even if someone can solve the problem of calculation volume, but it is difficult to see the correlation between these more than one hundred process capability indexes, and it is even more difficult to have a comprehensive understanding of the overall quality of the product performance and summary. However, if we utilize a big data quality management analysis platform, in addition to quickly getting a long list of traditional single-index process capability analysis reports, more importantly, we can also get a lot of brand-new analysis results from the same big data set.
8. Industrial Pollution and Environmental Protection Testing
The impressive point of "Under the Dome" is that through the visualization report, Chai Jing's team conveys to the audience the severity of the haze problem, the causes of the haze, and so on.
This brings us a revelation that big data has great value for environmental protection. Where did the raw data for the charts in Under the Dome come from? In fact, it is not all obtained by virtue of high-level relations, a lot of data are publicly available, in the Chinese government network, ministries and commissions website, PetroChina Sinopec official website, the official website of the environmental protection organizations and some special institutions, can query more and more public welfare environmental protection data, including the national air, hydrological and other data, meteorological data, the distribution of factories and pollution emissions to meet the standards and other data and so on. Only these data are too scattered, too professional, lack of analysis, no visualization, ordinary people can not understand. If you can read and keep an eye on it, big data will become an important means of social supervision of environmental protection. Recently Baidu online "National Pollution Monitoring Map" is a good way, combined with open environmental protection big data, Baidu map added pollution detection layer, anyone can use it to view the whole country and their own regional provinces and cities, all under the monitoring of the Environmental Protection Agency emission agencies (including various types of thermal power plants, state-controlled industrial enterprises and sewage treatment plants, etc.) location information, the name of the organization, the emission of pollutant sources of The location information, name of the organization, type of pollutant discharged, and the most recent pollution discharge compliance status announced by EPA. You can view the nearest source of pollution, appear alerts, the monitoring point testing program, which exceeds the standard, and how many times the standard is exceeded. This information can be shared in real time to social media platforms, informing friends and reminding everyone to pay attention to the pollution source situation and personal safety and health together.
Summarizing the value potential of industrial big data applications is huge. However, there is still a lot of work to be done to realize these values. One is the problem of building awareness of big data. In the past, there is also all this big data, but because there is no awareness of big data, and the means of data analysis is also insufficient, a lot of real-time data is discarded or put on the shelf, and a large amount of the potential value of the data is buried. Another important issue is the problem of data silos. The data of many industrial enterprises are distributed in various silos in the enterprise, especially in large multinational companies, and it is quite difficult to extract these data in the whole enterprise. Therefore, an important topic for industrial big data applications is integration applications.
The above is what I shared with you about the eight industrial big data application scenarios in the era of the Internet of Things, and for more information, you can follow the Global Green Ivy to share more dry goods
- Previous article:What is the professional cognition of Wushu and traditional national sports?
- Next article:Where does Henan Museum belong?
- Related articles
- Personality characteristics of 12 constellation
- English composition, 100 words or so. If you are an exchange student studying in the United States, you should introduce Chinese paper-cutting art to your American classmates.
- What are the Four Great Jades of China?
- How many temples are there in Pengcheng, a thousand-year-old town in Fengfeng?
- Teaching plan of safe crossing the road in kindergarten
- What negative factors in China's traditional culture are still affecting the current China society?
- Try to describe the characteristics of bureaucracy and analyze its advantages and disadvantages in combination with practice. Thesis problem
- Why are raw mung bean sprouts red?
- Zhongshan University questions about swimming lessons~
- How can sweet potatoes at home be stored for longer?