The hottest industrial big data application is the

2022-08-06
  • Detail

Industrial big data application: the cornerstone of industrial interconnection

in the 1990s, scientists put forward the concept of "big data" when conducting basic scientific research such as meteorological map analysis, big physics simulation calculation, gene map analysis, etc. In the 21st century, Internet, e-commerce, mobile Internet, social networking, IOT and other technologies are booming. Big data has become an inevitable product of the development of these new generation information technologies. Big data has the characteristics of large amount of data, complex data types and high requirements for real-time data processing. The wide application of big data analysis in the field of Internet and e-commerce has generated great commercial value and has been highly valued by countries all over the world. McKinsey & company, a world-famous strategic consulting firm, believes that big data is the next area where innovation, competition and productivity ensure that the possibility of material degradation due to shear is minimized

industrial big data is also a brand-new concept. Literally, industrial big data refers to big data generated in the informatization application in the industrial field. With the deep integration of informatization and industrialization, information technology has penetrated into all links of the industrial chain of industrial enterprises. Bar code, QR code, RFID, industrial sensors, industrial automatic control system, industrial IOT, ERP, cad/cam/cae/cai and other technologies have been widely used in industrial enterprises, especially the application of new generation information technologies such as Internet, mobile Internet and IOT in the industrial field, Industrial enterprises have also entered a new stage of development of the Internet industry, and the data owned by industrial enterprises are increasingly rich. In industrial enterprises, the production line is running at a high speed. The amount of data generated, collected and processed by industrial equipment is much larger than the data generated by computers and manual workers in the enterprise. From the perspective of data types, most of them are unstructured data. The high-speed operation of the production line requires higher real-time data. Therefore, the problems and challenges faced by industrial big data applications are no less than those in the Internet industry, and even more complex in some cases

the application of industrial big data will bring a new era of innovation and change to industrial enterprises. Through low-cost perception, high-speed mobile connectivity, distributed computing and advanced analysis brought about by Internet and mobile IOT, information technology and global industrial systems are being deeply integrated, bringing profound changes to global industry, and innovating enterprise R & D, production, operation, marketing and management methods. These innovative industrial enterprises in different industries have brought faster speed, higher efficiency and higher insight. Typical applications of industrial big data include product innovation, product fault diagnosis and prediction, industrial production line IOT analysis, industrial enterprise supply chain optimization and product precision marketing

first, look at the application of 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 innovative activities such as product demand analysis and product design, and contribute to product innovation. Ford is an example in this regard. They have applied big data technology to the product innovation and optimization of Ford Focus electric vehicle, which has become a veritable "big data electric vehicle". The first generation Ford Focus electric vehicle produced a large amount of data when driving and parking. During driving, the driver continuously updates the acceleration, braking, battery charging and position information of the vehicle. This is useful for drivers, but the data is also passed back to Ford engineers to understand the customer's driving habits, including how, when and where to charge. Even when the vehicle is stationary, it will continue to transmit the vehicle tire pressure and battery system data to the nearest intelligent. This customer-centric big data application scenario has many benefits, because big data has realized valuable new product innovation and collaboration. Drivers get useful and up-to-date information, while engineers in Detroit collect information about driving behavior to understand customers, develop product improvement plans, and implement new product innovation. Moreover, power companies and other third-party suppliers can analyze millions of miles of driving data to determine where to build new charging stations and how to prevent fragile electrical overload

the second typical application is product fault diagnosis and prediction, which can be used for product after-sales service and product improvement

the introduction of ubiquitous sensors and interconnection technology makes the real-time fault diagnosis of products become a reality. The big data application is composed of excitation and speed regulator, adjustable eccentric crankshaft connecting rod mechanism, pulsating cylinder, load holding valve, special oil pump and lubrication system. Modeling and simulation technology makes it possible to predict the dynamic performance. During the search of Malaysia Airlines mh370 lost contact aircraft, the engine operation data obtained by Boeing played a key role in determining the lost contact path of the aircraft. Let's take Boeing aircraft system as an example to see how big data application plays a role in product fault diagnosis. On Boeing aircraft, hundreds of variables, such as engine, fuel system, hydraulic and electric system, constitute the on-board state. These data are measured and sent once in less than a few microseconds. Take the Boeing 737 as an example, the engine can generate 10TB data every 30 minutes in flight. These data are not only engineering telemetry data that can be analyzed at a certain time point in the future, but also promote real-time adaptive control, fuel use, part fault prediction and pilot notification, and can effectively realize fault diagnosis and prediction. Take another example of General Electric (GE). The GE Energy Monitoring and diagnosis (MD) center in Atlanta, the United States, collects data from thousands of Ge gas turbines in more than 50 countries around the world, and can collect 10g data for customers every day. By analyzing the constant big data flow of sensor vibration and temperature signals from the system, these big data analysis will provide support for GE to diagnose and early warning gas turbine faults. Vestas, the wind turbine manufacturer, has also improved the layout of wind turbines through cross analysis of weather data and turbine instrument data, thereby increasing the power output level of wind turbines and extending the service life

the third typical application is the big data application of industrial IOT production line

modern industrial manufacturing 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 realized by using these data, including equipment diagnosis, power consumption analysis, energy consumption analysis, quality accident analysis (including violation of production regulations, parts failure), etc. First, in terms of production process improvement, using these big data in the production process can analyze the whole production process and understand how each link is implemented. Once a process deviates from the standard process, an alarm signal will be generated, which can find the error or bottleneck more quickly and solve the problem more easily. Using big data technology, we can also establish 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 monitor all production processes in the production process of the equipment, and abnormal or peak energy consumption can be found. Therefore, energy consumption can be optimized in the production process. Analyzing all processes will greatly reduce energy consumption

the fourth typical application is the analysis and optimization of industrial supply chain

at present, big data analysis has become an important means for many e-commerce enterprises to improve their supply chain competitiveness. For example, Jingdong Mall, an e-commerce enterprise, analyzes and forecasts the demand for commodities in various regions in advance through big data, so as to improve the efficiency of distribution and storage and ensure the customer experience of the next day's delivery. RFID and other product electronic identification technology, IOT technology and mobile Internet technology can help industrial enterprises obtain big data of a complete product supply chain. Using these data for analysis will greatly improve the efficiency of warehousing, distribution and sales and greatly reduce the cost. Take Haier as an example. Haier has a perfect supply chain system. It takes the market chain as the link and the order information flow as the center, drives the movement of logistics and capital flow, and integrates global supply chain resources and global user resources. In all links of Haier's supply chain, customer data, enterprise internal data and supplier data are summarized into the supply chain system. Through the collection and analysis of big data in the supply chain, Haier can continuously improve and optimize the supply chain, ensuring Haier's quick response to customers. There are more than 1000 large OEM suppliers in the United States, which provide more than 10000 different products for manufacturing enterprises according to the prediction of smitherspira. Each manufacturer relies on market forecast and other different variables, such as sales data, market information, exhibitions, competitor data, and even weather forecast, to sell its own products. Using sales data, product sensor data and data from the supplier database, industrial manufacturing enterprises can accurately predict the demand in different regions of the world. Because the inventory and sales price can be tracked and can be bought when the price drops, the manufacturing enterprise can save a lot of costs. If we reuse the data generated by the sensors in the product, we can know what is wrong with the product, where accessories are needed, and they can also predict where and when parts are needed. This will greatly reduce inventory and optimize the supply chain

the value potential of industrial big data application is huge. However, there is still much work to be done to realize these values. One is the establishment of big data awareness. In the past, these big data also existed, but due to the lack of awareness of big data and insufficient data analysis methods, many real-time data were discarded or shelved, and the potential value of a large amount of data was buried. Another important problem is the problem of data islands. The data of many industrial enterprises are distributed in the isolated islands of enterprises, especially in large multinational corporations. It is very difficult to extract these data in the whole enterprise. Therefore, an important topic of industrial big data application is integrated application

on September 5, 2013, the Ministry of industry and information technology officially released the special action plan for the deep integration of informatization and industrialization (2013-2018), which clearly proposed to promote the integrated application of industrial big data in the innovation action of interconnection and industrial integration. With the integration and innovation of interconnection and industry, the integrated application of industrial big data will become the core of industrial interconnection applications. It is understood that the special action plan divides the integrated application of industrial big data into three levels, corresponding to the big data applications of backbone enterprises, small and medium-sized enterprises and industries. First, for key enterprises that are qualified to build big data application systems, the action plan supports and encourages key enterprises in typical industries to apply big data technology in the process of industrial production and operation, so as to improve the intelligent decision-making level and operation efficiency of production and manufacturing, supply chain management, product marketing and service. This is to highlight the independent application of big data technology and analyze the internal and external data of backbone enterprises. Second, support the construction of third-party big data platforms,

Copyright © 2011 JIN SHI