Industrial internet data compensation method

Abstract

The invention relates to an industrial internet data compensation method, which comprises the following steps of: monitoring industrial internet data, performing real-time data anomaly detection by utilizing a machine learning algorithm, and processing at a data source in combination with an edge computing technology, so that delay and bandwidth consumption are reduced; an algorithm for adaptively adjusting a compensation strategy according to data characteristics and historical trends is developed, the compensation accuracy and efficiency are improved, multi-dimensional integrity verification is carried out on data in combination with methods of checksum, hash functions and digital signatures, and more comprehensive safety guarantee is provided; according to the data compensation method provided by the invention, the overall change trend of real data and the accuracy of a single data point can be accurately restored, enough precision is provided, and meanwhile, the method can be applied to a plurality of industrial internet scenes and shows good performance.

Description

Technical Field

[0001] The present invention relates to the technical field of data management, and in particular to an industrial Internet data compensation method. Background Art

[0002] Industrial Internet data refers to data related to industrial production activities collected through various sensors, equipment, and systems during the industrial production process. These data include equipment operation data, production process data, product quality data, environmental data, etc.; Industrial Internet data are usually diverse in type, large in quantity, real-time, and contain rich commercial value. With the help of this data, it can help optimize production processes, improve production efficiency, predict production equipment failures, etc.; currently, with the rapid development of technologies such as the Internet of Things, artificial intelligence, machine learning, and big data, Industrial Internet data has been widely used, promoting the development of industrial production towards intelligence and efficiency, and more and more production activities are using Industrial Internet data.

[0003] However, in the process of data collection, transmission and storage, when data is missing, damaged or erroneous due to various reasons, certain methods are needed to restore and repair the data in order to accurately and completely reflect the real situation, that is, to perform data compensation; the current common data compensation methods cannot completely and accurately restore the overall change trend of the real data and the accuracy of a single data point, especially when dealing with complex data changes or anomalies, they often cannot provide sufficient accuracy, resulting in deviations between the compensated data and the actual data, and the existing data compensation methods cannot perform well in all scenarios, especially when dealing with large-scale, high-frequency data, resulting in large amount of calculation and poor real-time performance. Summary of the invention

[0004] In view of this, the present invention provides an industrial Internet data compensation method, which effectively solves the problems of insufficient compensation accuracy and limited applicable scenarios of existing data compensation methods.

[0005] To achieve the above object, the present invention provides an industrial Internet data compensation method, comprising the following steps:

[0006] S1. Obtain industrial Internet data;

[0007] S2, real-time monitoring of data and anomaly detection;

[0008] S3. Verify data integrity;

[0009] S4. Back up data at multiple levels and implement data redundancy on critical data paths;

[0010] S5. Data compensation, including:

[0011] Model-based compensation: using a predictive model to estimate the missing data value for a known data model;

[0012] Statistics-based compensation: using historical data and statistical analysis to predict the likely value of lost data;

[0013] Rule-based compensation: define rules to automatically fill in missing data for specific types of data;

[0014] S6, data synchronization;

[0015] Use consistency protocols in distributed systems and record the change history of data.

[0016] Preferably, edge computing technology is used to perform real-time monitoring at the source of data;

[0017] Identify unusual patterns in your data.

[0018] Preferably, checksums and hash functions are used to verify transmitted data, and digital signatures are used for critical data.

[0019] Preferably, machine learning methods are used to identify abnormal patterns in data values, including sudden data jumps, missing data, and data that does not conform to expectations.

[0020] Preferably, the multi-level backup includes local backup, remote backup and cloud backup, and uses RAID technology and a distributed storage system to implement data redundancy.

[0021] Preferably, the data compensation method further includes fault-tolerant design and failover;

[0022] The fault-tolerant design implements redundancy by using dual power supplies and dual network connections in the components at the data source, and the failover is to automatically switch to the backup component at the data source when a fault is detected.

[0023] Preferably, the data compensation method also includes monitoring and optimization, by simulating data loss and damage to evaluate the effectiveness of the compensation method, monitoring the compensation time and resource consumption of the data compensation process to evaluate the performance of the data compensation method and perform optimization.

[0024] Preferably, the data compensation method further includes establishing a user interface and interaction, monitoring the data status in real time through a monitoring dashboard, and supporting users to manually trigger data compensation.

[0025] Compared with the prior art, the present invention has the following beneficial effects:

[0026] 1. The data compensation method provided by the present invention detects the data source through edge computing to ensure the continuity and integrity of the data, implements a multi-level data backup strategy to prevent data loss, can accurately restore the overall change trend of real data and the accuracy of a single data point, provide sufficient accuracy, and reduce the deviation between the compensated data and the actual data;

[0027] 2. The data compensation method provided by the present invention records the change history of data through transaction logs, ensuring that data recovery can quickly trace back to the correct state. The redundant design and failover mechanism can ensure the normal operation of the system, and can show good performance in a variety of application scenarios, even when processing large-scale, high-frequency data, it also has real-time performance;

[0028] 3. The data compensation method provided by the present invention can improve production efficiency, reduce energy consumption and maintenance costs by real-time monitoring and optimizing equipment operation, promote industrial equipment to the cloud, provide important application scenarios for industrial Internet platform operators, test the technical level and application results in practice, and comprehensively accelerate the optimization of the platform function system;

[0029] 4. The data compensation method provided by the present invention provides equipment suppliers with data on the entire life cycle of the equipment, supports services such as predictive maintenance and feedback innovation, optimizes equipment operation and maintenance efficiency and performance indicators, maximizes the use value of the equipment, and drives business model innovation;

[0030] 5. The data compensation method provided by the present invention realizes the free flow of information, materials, funds and other resources across departments, enterprises and regions through equipment interconnection, improves the synergy of the industrial chain, and realizes the optimal allocation of resources;

[0031] 6. The data compensation method provided by the present invention strengthens the formulation of standards and specifications, develops endogenously secure industrial Internet smart devices, establishes a security vulnerability sharing mechanism for industrial Internet smart devices, and improves the security protection capabilities of industrial Internet smart devices. DETAILED DESCRIPTION

[0032] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation method, structure, characteristics and effects of the present invention are described in detail below in combination with the preferred embodiments.

[0033] In order to reduce the deviation between compensated data and actual data, improve data accuracy, and expand the application scenarios of the data compensation method, the present invention provides an industrial Internet data compensation method, comprising the following steps:

[0034] S1. Obtain industrial Internet data;

[0035] S2, real-time monitoring of data and anomaly detection;

[0036] Monitor data security status in real time and detect abnormal behaviors and potential risks in a timely manner; collect all data related to the target, including internal and external data, to ensure data accuracy and completeness; clean, transform and standardize the collected data, eliminate noise and outliers, and ensure data quality; select or create useful features based on the warning target, which is the key to successful anomaly detection; select algorithms and models suitable for the data, train models with historical data, and evaluate and adjust them; formulate warning rules based on the trained model to guide the system when to trigger the alarm; deploy the warning system to the production environment and set up an automatic alarm sending mechanism; regularly monitor system performance and make necessary adjustments;

[0037] Use edge computing technology to monitor data sources in real time, use machine learning algorithms or statistical methods to detect data in real time, and identify abnormal patterns in data, including sudden data jumps, missing data, and data that does not meet expectations. Common machine learning methods include support vector machines (SVMs) and isolation forests, and common statistical methods include time series analysis and hypothesis testing.

[0038] Combining common machine learning and statistical methods, we developed algorithms that can adaptively adjust compensation strategies based on data characteristics and historical trends to improve the accuracy and efficiency of compensation.

[0039] S3. Verify data integrity;

[0040] Use checksum and hash functions to verify the transmitted data to ensure that the data has not been tampered with during transmission, and use digital signatures for key data to ensure the source and integrity of the data;

[0041] S4. Multi-level data backup, including local backup, remote backup and cloud backup, and use RAID technology and distributed storage systems to implement data redundancy on key data paths, dynamically adjust the data redundancy level according to the importance and access frequency of the data, and optimize the use of storage resources;

[0042] S5. Data compensation, including:

[0043] Model-based compensation: using a predictive model to estimate the missing data value for a known data model;

[0044] Statistics-based compensation: using historical data and statistical analysis to predict the likely value of lost data;

[0045] Rule-based compensation: define rules to automatically fill in missing data for specific types of data;

[0046] S6, data synchronization;

[0047] In a distributed system, the distributed consistency protocol and transaction log are combined to record the change history of data, achieve data consistency maintenance and rapid recovery, and trace back to the correct state; common consistency protocols include Paxos and Raft;

[0048] S7, Fault-tolerant design and failover;

[0049] Provide users with configurable fault tolerance and failover strategies, by implementing redundancy in the components at the data source using dual power supplies and dual network connections, and automatically switching to the backup components at the data source when a fault is detected to meet different business continuity requirements;

[0050] S8, monitoring and optimization;

[0051] Implement continuous performance monitoring to adapt to the ever-changing data traffic and business needs, evaluate the effectiveness of compensation methods by simulating data loss and damage, monitor the compensation time and resource consumption of the data compensation process, evaluate the performance of data compensation methods, and use automated tools to optimize the compensation process;

[0052] S9, establishing a user interaction interface;

[0053] The data status can be monitored in real time through the monitoring dashboard, and users are supported to manually trigger data compensation to increase the flexibility of the system. It covers nodes such as industrial cloud platforms, industrial apps, enterprise intranets, enterprise extranets, and provincial networks, and integrates in-depth spatial data security monitoring and protection capabilities on the cloud, network side, and terminals.

[0054] The data compensation method provided in this embodiment can perform data compensation across platforms and devices, and use environmental sensor data to predict and compensate for data problems caused by environmental factors (temperature, humidity, vibration, etc.); and provide data protection that complies with regulations and industry standards, and encrypt sensitive data to protect the security of data during transmission and storage.

[0055] The data compensation method provided in this embodiment can promote the cloud-based industrial equipment, and can carry out services such as operation monitoring and energy efficiency optimization. It is expected to reduce the energy consumption of coal-fired boilers by 3%, increase the utilization rate of CNC machine tools by 8%, and bring direct economic benefits of up to hundreds of billions of yuan, greatly improving production efficiency while reducing production costs. At the same time, industrial equipment on the cloud can provide important application scenarios for industrial Internet platform operators, test the technical level and application results in practice, comprehensively accelerate the optimization of the platform function system, and realize the free flow of information, materials, funds and other resources across departments, enterprises and regions through equipment interconnection, improve the synergy of the industrial chain, and achieve optimal allocation of resources.

[0056] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. An industrial Internet data compensation method, characterized in that: The following steps are involved: S1. Obtain industrial Internet data; S2, real-time monitoring of data and anomaly detection; Use edge computing technology to conduct real-time monitoring at the source of data; Identify unusual patterns in data; S3. Verify data integrity; Use checksums and hash functions to verify transmitted data, and use digital signatures for critical data; S4. Back up data at multiple levels and implement data redundancy on critical data paths; S5. Data compensation, including: Model-based compensation: using a predictive model to estimate the missing data value for a known data model; Statistics-based compensation: using historical data and statistical analysis to predict the likely value of lost data; Rule-based compensation: define rules to automatically fill in missing data for specific types of data; S6, data synchronization; Use consistency protocols in distributed systems and record the change history of data.

2. The industrial Internet data compensation method according to claim 1 is characterized in that: Use machine learning methods to identify unusual patterns in data values, including sudden data jumps, missing values, and data that does not match expectations.

3. The industrial Internet data compensation method according to claim 1 is characterized in that: The multi-level backup includes local backup, remote backup and cloud backup, and uses RAID technology and distributed storage system to implement data redundancy.

4. The industrial Internet data compensation method according to claim 1 is characterized in that: Data compensation methods also include fault-tolerant design and failover; The fault-tolerant design implements redundancy by using dual power supplies and dual network connections in the components at the data source, and the failover is to automatically switch to the backup component at the data source when a fault is detected.

5. The industrial Internet data compensation method according to claim 4 is characterized in that: The data compensation method also includes monitoring and optimization. The effectiveness of the compensation method is evaluated by simulating data loss and damage, and the compensation time and resource consumption of the data compensation process are monitored to evaluate the performance of the data compensation method and optimize it.

6. The industrial Internet data compensation method according to claim 5 is characterized in that: The data compensation method also includes establishing a user interface and interaction, monitoring the data status in real time through a monitoring dashboard, and supporting users to manually trigger data compensation.