CN118282531A - Interactive information system based on industrial digitization - Google Patents
Interactive information system based on industrial digitization Download PDFInfo
- Publication number
- CN118282531A CN118282531A CN202410368261.2A CN202410368261A CN118282531A CN 118282531 A CN118282531 A CN 118282531A CN 202410368261 A CN202410368261 A CN 202410368261A CN 118282531 A CN118282531 A CN 118282531A
- Authority
- CN
- China
- Prior art keywords
- data
- module
- unit
- network
- real
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000002452 interceptive effect Effects 0.000 title claims abstract description 42
- 230000005540 biological transmission Effects 0.000 claims abstract description 117
- 238000012545 processing Methods 0.000 claims abstract description 84
- 230000006854 communication Effects 0.000 claims abstract description 69
- 238000004891 communication Methods 0.000 claims abstract description 66
- 230000006978 adaptation Effects 0.000 claims abstract description 32
- 230000003044 adaptive effect Effects 0.000 claims abstract description 27
- 238000013135 deep learning Methods 0.000 claims abstract description 27
- 238000010801 machine learning Methods 0.000 claims abstract description 14
- 230000003993 interaction Effects 0.000 claims abstract description 9
- 238000000034 method Methods 0.000 claims description 101
- 238000007726 management method Methods 0.000 claims description 86
- 230000006870 function Effects 0.000 claims description 63
- 238000012423 maintenance Methods 0.000 claims description 43
- 238000001914 filtration Methods 0.000 claims description 41
- 238000012544 monitoring process Methods 0.000 claims description 28
- 238000006243 chemical reaction Methods 0.000 claims description 27
- 230000008569 process Effects 0.000 claims description 26
- 238000005457 optimization Methods 0.000 claims description 25
- 230000001629 suppression Effects 0.000 claims description 24
- 238000013528 artificial neural network Methods 0.000 claims description 23
- 238000004458 analytical method Methods 0.000 claims description 22
- 230000007246 mechanism Effects 0.000 claims description 20
- 125000004122 cyclic group Chemical group 0.000 claims description 18
- 238000004171 remote diagnosis Methods 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 16
- 238000003860 storage Methods 0.000 claims description 16
- 238000007405 data analysis Methods 0.000 claims description 14
- 238000013468 resource allocation Methods 0.000 claims description 13
- 238000004519 manufacturing process Methods 0.000 claims description 11
- 238000013500 data storage Methods 0.000 claims description 9
- 238000009826 distribution Methods 0.000 claims description 9
- 230000000694 effects Effects 0.000 claims description 9
- 238000010223 real-time analysis Methods 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 7
- 238000013461 design Methods 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 6
- 238000010295 mobile communication Methods 0.000 claims description 6
- 230000000306 recurrent effect Effects 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000003745 diagnosis Methods 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 3
- 238000007418 data mining Methods 0.000 claims description 3
- 238000003066 decision tree Methods 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 238000005065 mining Methods 0.000 claims description 3
- 238000003058 natural language processing Methods 0.000 claims description 3
- 238000013439 planning Methods 0.000 claims description 3
- 230000008521 reorganization Effects 0.000 claims description 3
- 230000008439 repair process Effects 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000003595 spectral effect Effects 0.000 claims description 3
- 238000004148 unit process Methods 0.000 claims description 3
- 230000004044 response Effects 0.000 abstract description 7
- 230000007547 defect Effects 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 13
- 238000012549 training Methods 0.000 description 9
- 238000012360 testing method Methods 0.000 description 7
- 230000004913 activation Effects 0.000 description 5
- 238000013507 mapping Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 238000013136 deep learning model Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013524 data verification Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000011423 initialization method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses an interactive information system based on industrial digitization, relates to the field of industrial Internet of things, and solves the defects of lag in interactive capability, signal interference, poor safety and poor compatibility existing in the existing interactive information system based on industrial digitization; the interaction capability and response speed of the system are improved through the intelligent signal processing module and the real-time data processing algorithm based on deep learning; reducing the influence of signal interference on communication quality through a real-time data processing algorithm based on deep learning; the safety of the system is improved through a block chain model based on quantum cryptography; optimizing data transmission rate and reliability through an adaptive communication module and an adaptive modulation algorithm based on machine learning; intelligent compatibility with different devices and systems is achieved by using a cross-platform application module and a compatibility adaptation system; the invention greatly improves the data processing and information interaction capability of the industrial digital interaction information system.
Description
Technical Field
The invention relates to the field of industrial Internet of things, and in particular relates to an interactive information system based on industrial digitization.
Background
With the rapid development of information technology, industrial digitization has become an important trend in the global manufacturing and industrial fields. The core of industrial digitization is to realize automation, intellectualization and high efficiency through digital technology, thereby improving production efficiency, reducing cost, improving product quality and promoting industrial upgrading. Interactive information systems based on industrial digitization have been developed, and have become one of the key technologies for realizing digitization transformation and intelligent manufacturing.
Currently, the era of industrial digitization has come, and both manufacturing and industrial enterprises across the world are actively advancing the digitization transformation. Under the background of the age, an industrial digital interactive information system becomes an indispensable technical means, and can help enterprises to realize functions of remote monitoring of equipment, real-time acquisition and analysis of data, intelligent control of a production process and the like, so that the production efficiency and the product quality are improved.
Currently, many interactive information systems based on industrial digitization exist, including wireless sensor networks, internet of things, industrial internet, and the like. These techniques have certain advantages, but also have problems. For example, based on the interaction capability hysteresis of industrial digitization, the data transmission speed and response time are slow, and the real-time requirement cannot be met; the signal interference problem is serious, and the accuracy and the reliability of data can be affected; the security problem is outstanding, and the risks of data leakage and attack are high; the compatibility is poor, the interoperability between different devices and systems is poor, and the information sharing and the cooperative work cannot be realized.
Accordingly, the present invention discloses an interactive information system based on industrial digitization.
Disclosure of Invention
Aiming at the defects of the prior art, the invention discloses an interactive information system based on industrial digitization, and solves the defects of lagging interactive capability, signal interference, poor safety and poor compatibility of the industrial digitization existing in the existing interactive information system based on the industrial digitization.
In order to achieve the technical effects, the invention adopts the following technical scheme:
an industrial digital based interactive information system, wherein the system comprises:
An intelligent signal processing module; the intelligent signal processing module performs real-time analysis and processing on signals acquired by the sensor through a real-time data processing algorithm based on deep learning, and the real-time data processing algorithm based on deep learning reduces the influence of signal interference on communication quality through a self-adaptive filtering and interference suppression method;
An adaptive communication module; the self-adaptive communication module optimizes the data transmission rate and the reliability through a self-adaptive modulation algorithm based on machine learning;
a blockchain security module; the block chain safety module realizes end-to-end safety communication and data encryption through a block chain model based on quantum cryptography;
A communication link transmission module; the communication link transmission module transmits data through a plurality of different paths by a multi-path transmission method;
A dynamic scheduling module; the dynamic scheduling module realizes the self-adaptive allocation and priority management of tasks through a real-time data stream management and scheduling mechanism;
a cross-platform application module; the cross-platform application module realizes intelligent compatibility with different devices and systems through a compatibility adaptation system;
an operation and maintenance support module; the operation and maintenance support module realizes remote monitoring and fault processing of the industrial digital system through a remote diagnosis and maintenance system;
A network topology optimization module; according to the real-time channel state and the equipment load condition, the network topology optimization module realizes automatic optimization and adjustment of a network topology structure through a self-organizing network;
A user management module; the user management module limits the user access authority through a user authority management mechanism, and prevents unauthorized operation and data leakage;
The output ends of the intelligent signal processing module and the network topology optimization module are connected with the input end of the self-adaptive communication module; the output end of the self-adaptive communication module is connected with the input end of the communication link transmission module; the output end of the block chain safety module is connected with the input end of the network topology optimization module; the output end of the communication link transmission module is connected with the input end of the dynamic scheduling module; the output ends of the dynamic scheduling module and the operation and maintenance support module are connected with the input end of the user management module; and the output end of the cross-platform application module is connected with the input end of the operation and maintenance support module.
As a further technical scheme of the invention, the block chain model based on quantum cryptography comprises a key management module, a block chain data structure module, an encryption authentication module, a secure communication module and an intelligent contract module; the key management module generates and distributes a key through a quantum random number generator and a quantum key distribution protocol, and ensures the key security through public-private key conversion and a key memory; the quantum random number generator generates a secret key through the superposition state of single photons and the quantum effect of the detector; the quantum key distribution protocol ensures the privacy of the key through quantum state transmission and quantum measurement; the public-private key conversion realizes the generation and conversion of the public-private key through an elliptic curve encryption algorithm; the key memory stores and manages keys through a cloud database; the block chain data structure module realizes data distributed storage and intelligent management through block chain nodes, a consensus mechanism and intelligent contracts, and the block chain nodes ensure the integrity and the non-tamper property of data through hash functions and merck trees; the encryption authentication module guarantees confidentiality and integrity of data through an asymmetric encryption algorithm and a digital signature, and verifies user identity and data legitimacy through a certificate verification mechanism; the security communication module protects data security in the communication process through a TLS/SSL transmission protocol and prevents illegal access and attack through a firewall and a data packet filter; the intelligent contract module ensures the safety and reliability of intelligent contracts through the Ethernet virtual machine and the intelligent contract framework.
As a further technical scheme of the invention, the principle steps of the multi-path transmission method in an interactive information system based on industrial digitization are as follows:
Step one, planning a path;
Calculating an optimal path and a standby path through a routing algorithm and a dynamic routing protocol BGP according to network topology and transmission requirements;
step two, data segmentation;
dividing data to be transmitted into a plurality of small blocks through a segmentation protocol TCP;
Step three, selecting a path;
selecting a transmission path for each divided data packet through a load balancing algorithm and link state information;
step four, parallel transmission;
transmitting the divided data packets in parallel through a plurality of physical channels and network interfaces;
fifthly, data reorganization;
The received data packets are recombined according to the sequence through the sequence number identification, the time stamp and the caching and sequencing method, and original data is restored;
Step six, checking and correcting errors;
And carrying out integrity check and error repair on the data through Cyclic Redundancy Check (CRC) and Forward Error Correction (FEC).
As a further technical scheme of the invention, the real-time data stream management and scheduling mechanism comprises a task management module, a resource management module and a data stream management module; the task management module comprises a task collection unit, a task ordering unit and a task distribution unit; the task collecting unit collects task requests through a network transmission protocol and a sensor; the task ordering unit orders and distributes tasks through fuzzy logic; the task allocation unit realizes the dynamic allocation and scheduling of tasks through a parallel computing and load balancing method; the resource management module comprises a resource monitoring unit and a resource allocation unit; the resource monitoring unit monitors and manages resources in real time through an internet of things transmission protocol and a cloud computing mode; according to the demands of tasks and the availability of resources, the resource allocation unit dynamically allocates and schedules the resources through a virtualization and containerization method; the data stream management module comprises a data acquisition unit, a data transmission unit, a data storage unit and a data processing unit; the data acquisition unit acquires environmental and production data in real time through the Internet of things equipment and the sensor network; the data transmission unit realizes the rapid transmission and sharing of data through a wireless network and a distributed storage method; the data storage unit realizes the storage and management of data through a cloud storage and big data storage method; the data processing unit processes and analyzes the data through a real-time data processing algorithm based on deep learning.
As a further technical scheme of the invention, the real-time data processing algorithm based on deep learning carries out signal filtering through a self-adaptive filtering function; the self-adaptive filtering function performs weighted summation on the input signals through convolution operation to obtain filtered output signals; the formula expression of the adaptive filter function is as follows:
In the formula (1), P is an output filtering result, and is used for representing a signal obtained after filtering; alpha is an offset term used for adjusting the offset of the filtering result; omega is an error term representing the filtered residual part; θ represents the weight in the convolution kernel for performing a weighted summation operation on the input signal; n is the convolution kernel size, used to determine the window size of the filtering; c i denotes an input signal of time domain i for filtering; realizing interference suppression by an interference suppression function based on a cyclic neural network;
The interference suppression function based on the cyclic neural network processes an input signal through a cyclic neural network structure; the formula expression of the interference suppression function based on the cyclic neural network is as follows:
In the formula (2), Y is a hidden layer state and is used for storing historical information and processing input signals; z represents an input signal for updating the hidden layer state; w h、Wf and W g are weight matrices of the hidden layer, the input layer and the output layer respectively, and are used for learning and adjusting network parameters; b h and b g are bias items of a hidden layer and an output layer respectively, and are used for adjusting the offset of a network output result; realizing real-time data processing through a real-time data processing function; the real-time data processing function processes the input signal through a depth residual error network; the depth residual error network improves the processing capacity of complex signals by adding a jump connection and residual error block structure; the formula expression of the real-time data processing function is as follows:
In the formula (3), M is an output signal for representing a result obtained after the processing; n is a residual function and is used for processing an input signal and extracting characteristics; { U d } is a weight parameter in the residual network, used for learning and adjusting network parameters; x is the input signal.
As a further technical scheme of the invention, the compatibility adaptation system comprises a device interface module, a data format conversion module, a communication protocol adaptation module, a user interface adaptation module and a functional compatibility module; the device interface module comprises a device identification unit and a device configuration unit; the device identification unit identifies and verifies the characteristics of different devices through an image identification method; the equipment configuration unit initializes and configures equipment according to equipment types and function requirements through a remote configuration protocol SNMP; the data format conversion module comprises a data analysis unit and a data conversion unit; the data analysis unit analyzes and extracts data generated by the equipment through a data mining and natural language processing method; the data conversion unit converts the analyzed data through a data processing and conversion method; the communication protocol adaptation module realizes intercommunication and data exchange between devices through a network protocol analysis and protocol conversion method; the user interface adaptation module adapts the display and interaction modes of the system through interface layout adjustment and a responsive design method; the function compatibility module maps functions of different devices to a unified field model through a field driving design method so as to realize function compatibility and operation consistency among different devices.
As a further technical scheme of the invention, the self-adaptive modulation algorithm based on machine learning carries out channel state estimation and selection through a self-adaptive modulation selection formula; the adaptive modulation selection formula realizes the selection of adaptive modulation through the judgment of candidate channel state errors; the expression of the adaptive modulation selection formula is:
In formula (4), T represents an optimal channel state; σ represents a set of selectable channel states for selecting the best channel state; k is a transmitted signal for evaluating the channel state; l represents the received signal for evaluating the current channel state; τ represents the ζ channel state for calculating an error between the received signal and the predicted signal; calculating the information transmission rate under each channel state through an information transmission rate calculation formula; the information transmission rate calculation formula evaluates the channel reliability and the transmission rate through the signal-to-noise ratio of the channel state so as to optimize the data transmission rate and the reliability; the expression of the information transmission rate calculation formula is as follows:
in formula (5), R represents an information transmission rate; delta represents the transmit power for calculating the signal-to-noise ratio; s represents noise power spectral density, which is used for influencing information transmission rate; m represents a channel bandwidth for calculating an information transmission rate in each channel state.
As a further technical scheme of the invention, the self-organizing network comprises a node management module, a topology management module, a routing selection module, a security management module and a resource scheduling module; the node management module comprises a node state detection unit and a load condition analysis unit; the node state detection unit monitors the node running state in real time through a sensor; the load condition analysis unit analyzes and predicts the load condition of the nodes through a neural network and a decision tree; the topology management module dynamically optimizes and adjusts a network topology structure according to the real-time channel state and the equipment load condition through a graph theory and a network optimization method; constructing a topological structure in the Ethernet by the graph theory through a minimum spanning tree algorithm so as to optimize the network communication efficiency; the network optimization method dynamically adjusts a routing path in a network according to the real-time flow condition through a flow balancing algorithm so as to improve the overall performance of the network; the routing module selects an optimal path and a route according to a network topological structure and equipment load conditions through a routing selection and minimum cost greedy algorithm; the resource scheduling module comprises a resource allocation unit and a task cooperative unit; the resource allocation unit realizes the dynamic allocation and management of bandwidth through frequency division multiplexing and time division multiplexing; the task cooperation unit realizes task allocation and cooperation execution through a shortest job priority scheduling and round-robin scheduling method.
As a further technical scheme of the invention, the remote diagnosis and maintenance system comprises a remote monitoring module, a remote diagnosis module and a remote maintenance module; the remote monitoring module comprises a state monitoring unit and an early warning notification unit; the state monitoring unit monitors the running state of the equipment in real time through a sensor, and extracts abnormal information and fault signals through a big data analysis method; the big data analysis method is used for carrying out real-time analysis and mining through a distributed storage and calculation framework; the early warning notification unit sends early warning notification to related personnel through the Internet of things and a mobile communication method; the mobile communication method sends out early warning notification to related personnel in a short message, mail and pushing mode; the remote diagnosis module comprises a fault analysis unit and a remote maintenance guide unit; the fault analysis unit performs fault analysis and diagnosis according to historical data and real-time data through a rule-based expert system; the remote maintenance guiding unit gives out remote operation guiding and fault removal suggestions through a remote desktop and a remote assistance method; the remote maintenance module comprises a remote control unit and a remote upgrading unit; the remote control unit realizes remote control operation on equipment through a network communication protocol; the remote upgrading unit realizes remote updating, parameter configuration and calibration operation through an over-the-air downloading method and a cloud management platform.
Has the positive beneficial effects that:
According to the invention, through the intelligent signal processing module and the real-time data processing algorithm based on deep learning, the real-time analysis and processing of the signals acquired by the sensor are realized, and the interaction capability and response speed of the system are improved. The influence of signal interference on communication quality is reduced through a real-time data processing algorithm based on deep learning by a self-adaptive filtering and interference suppression method, and the stability and reliability of signal transmission are improved. By introducing the blockchain security module, the blockchain model based on quantum cryptography realizes end-to-end secure communication and data encryption, improves the security of the system and prevents data leakage and tampering. The data transmission rate and the reliability are optimized through the self-adaptive communication module and the self-adaptive modulation algorithm based on machine learning, and the communication capacity and the performance of the system are improved. By using the cross-platform application module and the compatibility adaptation system, intelligent compatibility with different devices and systems is realized, the problem of poor compatibility in the existing system is solved, and the compatibility and interoperability of the system are improved.
Drawings
For a clearer description of embodiments of the invention or of solutions in the prior art, the drawings that are necessary for the description of the embodiments or of the prior art will be briefly described, it being apparent that the drawings in the description below are only some embodiments of the invention, from which, without inventive faculty, other drawings can be obtained for a person skilled in the art, in which:
FIG. 1 is a block diagram of an interactive information system based on industrial digitization in accordance with the present invention;
Fig. 2 is a schematic flow chart of a multi-path transmission method according to the present invention;
FIG. 3 is a schematic diagram of a remote diagnostic and maintenance system of the present invention;
FIG. 4 is a schematic block chain model based on quantum cryptography of the present invention;
FIG. 5 is a step diagram of the operation of the ad hoc network of the present invention;
fig. 6 is a schematic diagram of the operation of the compatibility adapter system of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1-6, an industrial digital-based interactive information system, comprising:
An intelligent signal processing module; the intelligent signal processing module performs real-time analysis and processing on signals acquired by the sensor through a real-time data processing algorithm based on deep learning, and the real-time data processing algorithm based on deep learning reduces the influence of signal interference on communication quality through a self-adaptive filtering and interference suppression method;
An adaptive communication module; the self-adaptive communication module optimizes the data transmission rate and the reliability through a self-adaptive modulation algorithm based on machine learning;
a blockchain security module; the block chain safety module realizes end-to-end safety communication and data encryption through a block chain model based on quantum cryptography;
A communication link transmission module; the communication link transmission module transmits data through a plurality of different paths by a multi-path transmission method;
A dynamic scheduling module; the dynamic scheduling module realizes the self-adaptive allocation and priority management of tasks through a real-time data stream management and scheduling mechanism;
a cross-platform application module; the cross-platform application module realizes intelligent compatibility with different devices and systems through a compatibility adaptation system;
an operation and maintenance support module; the operation and maintenance support module realizes remote monitoring and fault processing of the industrial digital system through a remote diagnosis and maintenance system;
A network topology optimization module; according to the real-time channel state and the equipment load condition, the network topology optimization module realizes automatic optimization and adjustment of a network topology structure through a self-organizing network;
A user management module; the user management module limits the user access authority through a user authority management mechanism, and prevents unauthorized operation and data leakage;
The output ends of the intelligent signal processing module and the network topology optimization module are connected with the input end of the self-adaptive communication module; the output end of the self-adaptive communication module is connected with the input end of the communication link transmission module; the output end of the block chain safety module is connected with the input end of the network topology optimization module; the output end of the communication link transmission module is connected with the input end of the dynamic scheduling module; the output ends of the dynamic scheduling module and the operation and maintenance support module are connected with the input end of the user management module; and the output end of the cross-platform application module is connected with the input end of the operation and maintenance support module.
In the above embodiment, the blockchain model based on quantum cryptography includes a key management module, a blockchain data structure module, an encryption authentication module, a secure communication module, and an intelligent contract module; the key management module generates and distributes a key through a quantum random number generator and a quantum key distribution protocol, and ensures the key security through public-private key conversion and a key memory; the quantum random number generator generates a secret key through the superposition state of single photons and the quantum effect of the detector; the quantum key distribution protocol ensures the privacy of the key through quantum state transmission and quantum measurement; the public-private key conversion realizes the generation and conversion of the public-private key through an elliptic curve encryption algorithm; the key memory stores and manages keys through a cloud database; the block chain data structure module realizes data distributed storage and intelligent management through block chain nodes, a consensus mechanism and intelligent contracts, and the block chain nodes ensure the integrity and the non-tamper property of data through hash functions and merck trees; the encryption authentication module guarantees confidentiality and integrity of data through an asymmetric encryption algorithm and a digital signature, and verifies user identity and data legitimacy through a certificate verification mechanism; the security communication module protects data security in the communication process through a TLS/SSL transmission protocol and prevents illegal access and attack through a firewall and a data packet filter; the intelligent contract module ensures the safety and reliability of intelligent contracts through the Ethernet virtual machine and the intelligent contract framework.
In a specific embodiment, a blockchain model based on quantum cryptography generates and manages a public key and a private key through a key management module, so that the security and the non-counterfeitability of the key are ensured. And linking the data in the interactive information system according to the time sequence and the hash value by using a block chain technology through a block chain data structure module to form a tamper-proof chain structure. And the encryption authentication module encrypts the data to ensure confidentiality and integrity in the data transmission process. The end-to-end secure communication is realized by the secure communication module by adopting a quantum communication technology, so that data is prevented from being eavesdropped and tampered, and the security of communication is ensured. The intelligent contract module realizes automatic contract execution and data verification by utilizing intelligent contract technology, and ensures that the operation in the interactive information system accords with preset rules.
In an interactive information system based on industrial digitization, the application of a quantum cryptography algorithm can provide higher-level data protection, prevent data from being illegally acquired and tampered, and ensure confidentiality and integrity of the data. In addition, the public key and the private key generated by the quantum cryptography algorithm have non-counterfeitability, and the accuracy of identity verification and data authentication in the interactive information system is ensured. And secondly, the quantum communication technology is adopted for safety communication, so that the data transmission speed and efficiency can be improved, and the response time of information interaction can be shortened. Meanwhile, the application of the blockchain technology enables the data in the interactive information system to have the characteristics of decentralization and traceability, and the transparency and the credibility of the system are enhanced.
In the above embodiment, the principle steps of the multi-path transmission method in an interactive information system based on industrial digitization are as follows:
Step one, planning a path;
Calculating an optimal path and a standby path through a routing algorithm and a dynamic routing protocol BGP according to network topology and transmission requirements;
step two, data segmentation;
dividing data to be transmitted into a plurality of small blocks through a segmentation protocol TCP;
Step three, selecting a path;
selecting a transmission path for each divided data packet through a load balancing algorithm and link state information;
step four, parallel transmission;
transmitting the divided data packets in parallel through a plurality of physical channels and network interfaces;
fifthly, data reorganization;
The received data packets are recombined according to the sequence through the sequence number identification, the time stamp and the caching and sequencing method, and original data is restored;
Step six, checking and correcting errors;
And carrying out integrity check and error repair on the data through Cyclic Redundancy Check (CRC) and Forward Error Correction (FEC).
In a specific embodiment, the multi-path transmission method refers to transmitting data by using a plurality of different paths at the same time, so as to improve the robustness and reliability of data transmission. In a specific embodiment, the communication link transmission module selects a plurality of different paths to transmit data before data transmission, so as to reduce risks such as network congestion and signal interference faced by single path transmission.
In the working principle of the multipath transmission method, path selection is first required, and the selection may be based on various information, such as available bandwidth of a path, delay time, packet loss rate, and the like. After the path is selected, the data is divided into a plurality of small blocks and transmitted through different paths. And the receiving end reorganizes the data blocks according to the serial numbers to obtain complete data. Since the data is divided into a plurality of small blocks and transmitted through different paths, even if some paths have problems, all the data cannot be lost, thereby improving the robustness and reliability of data transmission.
In a specific implementation, the multipath transmission can reduce risks such as network congestion, signal interference and the like, which may be faced by single path transmission, thereby improving the reliability of data transmission. In addition, the multipath transmission can simultaneously use a plurality of paths to transmit data, thereby improving the speed and the efficiency of data transmission. And secondly, the multipath transmission can select an optimal path for data transmission according to the delay conditions of different paths, so that the delay of the data transmission is reduced. Meanwhile, the multipath transmission can improve the robustness of the network, and even if some paths have problems, the whole network is not greatly influenced.
In the above embodiment, the real-time data stream management and scheduling mechanism includes a task management module, a resource management module, and a data stream management module; the task management module comprises a task collection unit, a task ordering unit and a task distribution unit; the task collecting unit collects task requests through a network transmission protocol and a sensor; the task ordering unit orders and distributes tasks through fuzzy logic; the task allocation unit realizes the dynamic allocation and scheduling of tasks through a parallel computing and load balancing method; the resource management module comprises a resource monitoring unit and a resource allocation unit; the resource monitoring unit monitors and manages resources in real time through an internet of things transmission protocol and a cloud computing mode; according to the demands of tasks and the availability of resources, the resource allocation unit dynamically allocates and schedules the resources through a virtualization and containerization method; the data stream management module comprises a data acquisition unit, a data transmission unit, a data storage unit and a data processing unit; the data acquisition unit acquires environmental and production data in real time through the Internet of things equipment and the sensor network; the data transmission unit realizes the rapid transmission and sharing of data through a wireless network and a distributed storage method; the data storage unit realizes the storage and management of data through a cloud storage and big data storage method; the data processing unit processes and analyzes the data through a real-time data processing algorithm based on deep learning.
In a specific embodiment, the working mode principle of the real-time data stream management and scheduling mechanism for realizing the self-adaptive allocation and priority management of tasks through the dynamic scheduling module is as follows:
R1, data flow monitoring: the real-time data stream management and scheduling mechanism first monitors various data streams in the system, including real-time sensor data, control instructions, communication data, etc. These data streams may have different priorities and processing requirements.
R2, task analysis: the system analyzes the data streams according to actual conditions, including importance, urgency, processing time requirements and the like of the data, so as to determine the task type and the characteristics of each data stream.
R3, resource allocation: according to the characteristics of the data flow and the current resource condition of the system, the dynamic scheduling module can carry out self-adaptive allocation on the tasks, and the tasks are allocated to proper computing resources or communication channels for processing and transmission.
R4, priority management: aiming at the importance and the emergency degree of different tasks, the system can carry out priority management on the tasks, and ensure that the important tasks can be processed preferentially, thereby improving the response speed and the real-time performance of the system.
R5, real-time adjustment: the real-time data stream management and scheduling mechanism can adjust task allocation and priority management strategies in real time according to the running condition of the system so as to adapt to dynamically-changed environments and requirements.
In an interactive information system based on industrial digitization, a real-time data stream management and scheduling mechanism can ensure that important data and tasks can be processed in time by carrying out real-time analysis and scheduling on data streams, and the real-time performance and response speed of the system are improved. In addition, the dynamic scheduling module can reasonably allocate computing resources and communication channels according to the current resource conditions and task characteristics of the system, and the utilization efficiency of the resources is improved. And secondly, by priority management and real-time adjustment, the delay of task processing can be reduced, the important tasks can be ensured to be processed in time, and the response delay of the system is reduced. Meanwhile, the real-time data stream management and scheduling mechanism can adjust task allocation and priority management strategies in real time according to the running condition of the system, so that the system can better adapt to dynamically-changed environments and requirements.
In the above embodiment, the real-time data processing algorithm based on deep learning performs signal filtering by using an adaptive filtering function; the self-adaptive filtering function performs weighted summation on the input signals through convolution operation to obtain filtered output signals; the formula expression of the adaptive filter function is as follows:
In the formula (1), P is an output filtering result, and is used for representing a signal obtained after filtering; alpha is an offset term used for adjusting the offset of the filtering result; omega is an error term representing the filtered residual part; θ represents the weight in the convolution kernel for performing a weighted summation operation on the input signal; n is the convolution kernel size, used to determine the window size of the filtering; c i denotes an input signal of time domain i for filtering; realizing interference suppression by an interference suppression function based on a cyclic neural network; the interference suppression function based on the cyclic neural network processes an input signal through a cyclic neural network structure;
An adaptive filter function is a filtering algorithm that automatically adjusts the filter parameters according to the characteristics and requirements of the input signal. The working process mainly comprises the following steps:
1. Initializing filter parameters: before starting the filtering, it is first necessary to set initial parameters for the filter, such as the filter order, cut-off frequency, etc. These parameters may be set according to the characteristics of the input signal or may be determined by a preset rule.
2. Calculating filter coefficients: and calculating the coefficients of the filter according to the input signal and preset filter parameters. These coefficients will be used to adjust the filter performance in the subsequent filtering process.
3. Updating a filter: and filtering the input signal according to the input signal and the calculated filter coefficient. In the filtering process, the filter can automatically adjust the coefficients according to the real-time change of the input signal so as to realize the optimal filtering effect.
4. Evaluating filter performance: in the filtering process, the performance of the filter, such as indexes of cut-off frequency, group delay, signal to noise ratio and the like, needs to be continuously evaluated. These performance metrics can be used to measure the effect of the filter and provide a reference for the next filtering process.
5. Adjusting filter parameters: parameters of the filter, such as filter order, cut-off frequency, etc., are automatically adjusted according to the estimated filter performance index and a preset threshold. This process may be implemented using optimization algorithms such as least squares, genetic algorithms, and the like.
6. Repeating the steps 3-5: after the filter parameters are adjusted, filtering of the input signal is continued. The filter automatically adjusts its performance according to the input signal and the adjusted parameters, which are changed in real time, so as to achieve the best filtering effect.
Through the working process, the self-adaptive filter function can automatically adjust the filter parameters according to the characteristics and the requirements of the input signals, so that a better filter effect is realized. The function described above is a feature vector value,
The formula expression of the interference suppression function based on the cyclic neural network is as follows:
In the formula (2), Y is a hidden layer state and is used for storing historical information and processing input signals; z represents an input signal for updating the hidden layer state; w h、Wf and W g are weight matrices of the hidden layer, the input layer and the output layer respectively, and are used for learning and adjusting network parameters; b h and b g are bias items of a hidden layer and an output layer respectively, and are used for adjusting the offset of a network output result; realizing real-time data processing through a real-time data processing function; the real-time data processing function processes the input signal through a depth residual error network;
The interference suppression function based on the cyclic neural network (Recurrent Neural Network, RNN) is mainly used for suppressing interference noise in the communication signal and improving the signal quality. The working process is as follows:
1. Input signal processing: the input signal (e.g., communication signal) is preprocessed, including filtering, denoising, etc., to remove portions of interference and noise. Initial weights and offsets of the network are set. The initial values of the weights and offsets are typically set randomly, and a pre-trained weight initialization method may also be used.
2. Building a cyclic neural network: and constructing a proper cyclic neural network model according to the characteristics of the input signals. The recurrent neural network includes a plurality of time steps, each having an output node for calculating a signal estimate for the current time step. The output of the activation function is calculated based on the input to the network and the type of activation function (e.g., reLU, tanh, etc.). The activation function is used to introduce non-linear characteristics, enhancing the expressive power of the network.
3. Training a recurrent neural network: the recurrent neural network is trained using the input signal and the corresponding clean signal (without interference signal) as training data. In the training process, the weight and bias of the network are adjusted through an optimization algorithm (such as a gradient descent method), so that the network can learn the mapping relation between the input signal and the clean signal. At each time step of the network, the internal state is updated based on the internal state of the last time step and the input of the current time step. The internal state is used to store and communicate historical information of the network.
4. Predicting an interference suppression value: after training is completed, the input signal is predicted using a recurrent neural network. The network predicts the signal estimate for the current time step based on the historical information of the input signal and calculates a prediction error.
5. Suppression of interference: and according to the prediction error, performing interference suppression on the input signal. The interference suppression method may be to directly subtract the prediction error, or may be to perform processing such as weighting filtering on the prediction error. The processed signal is the signal after interference suppression.
6. Outputting the suppressed signal: and taking the signal after interference suppression as output for subsequent signal processing and analysis. And calculating the output of the network according to the internal state of the current time step and the output of the activation function. The output may be used for signal estimation, classification, etc. The back propagation computes updated values of the network weights and offsets based on output errors (e.g., mean square error, cross entropy, etc.). The update process uses an optimization algorithm (e.g., gradient descent) to adjust the weights and offsets to reduce the output error. And updating the weight and the bias of the network according to the weight and bias updating values obtained by back propagation calculation.
Then steps 3-6: in a subsequent time step, the network will repeat steps 3-6 based on the new internal state and input to update the internal state and output. Through the working process, the interference suppression function based on the cyclic neural network can effectively suppress interference noise in communication signals, and improves signal quality. Different data parameters are used as characteristic values to calculate different data information.
The depth residual error network improves the processing capacity of complex signals by adding a jump connection and residual error block structure; the formula expression of the real-time data processing function is as follows:
In the formula (3), M is an output signal for representing a result obtained after the processing; n is a residual function and is used for processing an input signal and extracting characteristics; { U d } is a weight parameter in the residual network, used for learning and adjusting network parameters; x is the input signal.
In a specific embodiment, in the working process of a real-time data processing algorithm based on deep learning, data information is calculated in real time through data information processing, and a plurality of convolution layers and residual modules are integrated: the residual module in the network is the core of ResNet for learning the residual mapping between the input data and the output data. The residual module comprises several convolution layers and a skip connection (skip connection). The jump connection adds the input data and the output data, so that the network can directly learn the residual mapping between the input data and the output data, thereby avoiding the problem of gradient disappearance. An activation function (such as ReLU, tanh, etc.) is added between layers of the network, and after calculation by a plurality of residual modules, the network outputs a feature map. This feature map may be further processed, such as for classification, regression, etc., according to task requirements. Based on the difference between the predicted output and the real label, a loss function (e.g., mean square error, cross entropy, etc.) is calculated. The loss function is used for measuring the performance of the network and providing basis for the subsequent optimization process. Based on the loss function, the back propagation computes updated values of weights and biases for layers in the network. The update process uses an optimization algorithm (e.g., gradient descent) to adjust the weights and biases to reduce the loss function. And updating the weights and the biases in the network according to the weight and bias updated values obtained by back propagation calculation. And then repeating the steps 3-8: in the subsequent training process, the network repeatedly executes the steps 3-8 according to the updated weights and offsets, and continuously learns the residual mapping between the input data and the output data. Through the calculation process, the depth residual error network can process input data in real time and learn the mapping relation between the data characteristics step by step. During the training process, the network automatically adjusts the weights and offsets according to the loss function to achieve the best performance.
In a specific implementation, the deep learning algorithm can identify interference in the signal and effectively inhibit the interference, so that the communication quality and the data accuracy are improved. And secondly, the deep learning algorithm can be adaptively adjusted according to different working conditions and environments, so that the applicability is wider. In specific implementation, a data test comparison table of the real-time data processing algorithm based on deep learning and the conventional algorithm is shown in table 1:
table 1 real-time data processing algorithm data test comparison table based on deep learning
| Data test item | Results of conventional algorithms | Deep learning algorithm results |
| Communication signal to noise ratio | 20 dB | 25dB |
| Data transmission rate | 100Mbps | 150Mbps |
| Anti-interference capability | 80％ | 95％ |
As can be seen from the table, compared with the traditional algorithm, the real-time data processing algorithm based on deep learning has better effects in the aspects of communication signal-to-noise ratio, data transmission rate, anti-interference capability and the like; in an interactive information system based on industrial digitization, an Abo-card is an operation hardware environment of a real-time data processing algorithm based on deep learning: CPU is Intel Core i7 or above; the memory is 16GB or more; NVIDIA GeForce GTX or more than NVIDIA GeForce GTX; the software environment is as follows: windows 10 or above; development environment Python3.6 or above; a deep learning frame TensorFlow 2.0.0 or more; in a specific implementation, a test data table of the real-time data processing algorithm based on deep learning is shown in table 2:
Table 2 real-time data processing algorithm test data table based on deep learning
In the data table 2, sensor data represents data originally acquired from a sensor. The preprocessed data represents data that has been processed by a preprocessing step (e.g., denoising, filtering, normalizing, etc.). The model input data means that the data after preprocessing is input to the deep learning model for processing. The prediction result represents a prediction result obtained by processing the input data by the deep learning model. The actual results represent actual results or labels. The accuracy represents the accuracy obtained by comparing and calculating the predicted result and the real result.
In the above embodiment, the compatibility adaptation system includes a device interface module, a data format conversion module, a communication protocol adaptation module, a user interface adaptation module, and a functional compatibility module; the device interface module comprises a device identification unit and a device configuration unit; the device identification unit identifies and verifies the characteristics of different devices through an image identification method; the equipment configuration unit initializes and configures equipment according to equipment types and function requirements through a remote configuration protocol SNMP; the data format conversion module comprises a data analysis unit and a data conversion unit; the data analysis unit analyzes and extracts data generated by the equipment through a data mining and natural language processing method; the data conversion unit converts the analyzed data through a data processing and conversion method; the communication protocol adaptation module realizes intercommunication and data exchange between devices through a network protocol analysis and protocol conversion method; the user interface adaptation module adapts the display and interaction modes of the system through interface layout adjustment and a responsive design method; the function compatibility module maps functions of different devices to a unified field model through a field driving design method so as to realize function compatibility and operation consistency among different devices.
In a specific embodiment, the working mode principle of the compatibility adapting system is as follows:
p1, equipment identification: when a new device is connected to the system, the compatibility adapter system automatically recognizes information such as its device type, operating system, and software environment.
P2, compatibility detection: the system can automatically detect the compatibility of the device with the system according to the type of the device, the software environment and other information, and judge whether the device can communicate and interact with the system.
P3, compatibility adaptation: for devices which cannot be directly compatible, the compatibility adaptation system can convert device data into a format which can be recognized by the system through a compatibility adaptation technology, so that intelligent compatibility of the devices and the system is realized.
P4, cross-platform application: the cross-platform application module is an important component of the compatibility adaptation system, and can seamlessly transmit and share application programs and data in the system between different devices and operating systems, so that a user can use the same application programs and data on a plurality of platforms.
P5, automatic updating: the compatibility adaptation system can automatically update the compatibility adaptation technology and the cross-platform application module so as to ensure that the compatibility of the system and the equipment is always supported up to date.
In an interactive information system based on industrial digitization, through a compatibility adaptation technology, the compatibility adaptation system can realize intelligent compatibility of equipment and the system, so that more equipment can be accessed and used by the system. In addition, the cross-platform application module can seamlessly transmit and share the application programs and data in the system between different devices and operating systems, so that a user can use the same application program and data on a plurality of platforms, and user experience and working efficiency are improved. And secondly, the compatibility adaptation system can automatically update the compatibility adaptation technology and the cross-platform application module, so that the system is ensured to always have the latest compatibility support, and the expandability and the adaptability of the system are improved. At the same time, a compatibility adaptation system may reduce the cost and complexity of system integration because it enables intelligent compatibility with different devices and systems, thereby reducing the custom development and integration for a particular device and system.
In the above embodiment, the adaptive modulation algorithm based on machine learning performs channel state estimation and selection through an adaptive modulation selection formula; the adaptive modulation selection formula realizes the selection of adaptive modulation through the judgment of candidate channel state errors; the expression of the adaptive modulation selection formula is:
In formula (4), T represents an optimal channel state; σ represents a set of selectable channel states for selecting the best channel state; k is a transmitted signal for evaluating the channel state; l represents the received signal for evaluating the current channel state; τ represents the ζ channel state for calculating an error between the received signal and the predicted signal; calculating the information transmission rate under each channel state through an information transmission rate calculation formula; the information transmission rate calculation formula evaluates the channel reliability and the transmission rate through the signal-to-noise ratio of the channel state so as to optimize the data transmission rate and the reliability; the expression of the information transmission rate calculation formula is as follows:
in formula (5), R represents an information transmission rate; delta represents the transmit power for calculating the signal-to-noise ratio; s represents noise power spectral density, which is used for influencing information transmission rate; m represents a channel bandwidth for calculating an information transmission rate in each channel state.
In a specific embodiment, in an embodiment of the machine learning-based adaptive modulation algorithm in an industrial digital interactive information system, the hardware environment is: CPU is Intel Xeon E5 or above; the memory is 32GB or more; network equipment: a switch, router, etc. device supporting Software Defined Networks (SDN) and Network Function Virtualization (NFV); the self-adaptive modulation algorithm based on machine learning has the following operation processes:
f1, data acquisition: raw data is collected from sensors or other data sources.
F2, extracting features: and extracting the characteristics of the original data, and extracting the characteristic parameters for modulation.
F3, model training: the feature parameters are trained using a machine learning model to optimize data transmission rate and reliability.
F4, adaptive modulation: and dynamically adjusting the modulation mode and parameters of data transmission according to the result obtained by model training.
F5, data transmission: and carrying out data transmission according to the parameters optimized by the adaptive modulation algorithm.
In a specific embodiment, the test data table of the adaptive modulation algorithm based on machine learning is shown in table 3:
Table 3 machine learning based adaptive modulation algorithm test data table
| Time stamp | Channel state | Characteristic parameter | Modulation scheme | Transmission rate | Reliability of |
| 0 | Good quality | 0.8 | QAM16 | 100Mbps | 95％ |
| 1 | Failure of | 0.6 | QPSK | 50Mbps | 80％ |
| 2 | Good quality | 0.9 | QAM64 | 150Mbps | 97％ |
| 3 | Poor quality | 0.5 | BPSK | 30Mbps | 75％ |
| 4 | Good quality | 0.7 | QAM32 | 80Mbps | 90％ |
In the data table 3, the channel state and the characteristic parameters are collected, and are input into a machine learning model for training, so that the optimal modulation mode under different conditions, the corresponding transmission rate and the reliability evaluation are obtained. These results can be used to optimize the data transmission process and improve the data transmission efficiency and reliability of the industrial digital interactive information system.
In the above embodiment, the self-organizing network includes a node management module, a topology management module, a routing module, a security management module, and a resource scheduling module; the node management module comprises a node state detection unit and a load condition analysis unit; the node state detection unit monitors the node running state in real time through a sensor; the load condition analysis unit analyzes and predicts the load condition of the nodes through a neural network and a decision tree; the topology management module dynamically optimizes and adjusts a network topology structure according to the real-time channel state and the equipment load condition through a graph theory and a network optimization method; constructing a topological structure in the Ethernet by the graph theory through a minimum spanning tree algorithm so as to optimize the network communication efficiency; the network optimization method dynamically adjusts a routing path in a network according to the real-time flow condition through a flow balancing algorithm so as to improve the overall performance of the network; the routing module selects an optimal path and a route according to a network topological structure and equipment load conditions through a routing selection and minimum cost greedy algorithm; the resource scheduling module comprises a resource allocation unit and a task cooperative unit; the resource allocation unit realizes the dynamic allocation and management of bandwidth through frequency division multiplexing and time division multiplexing; the task cooperation unit realizes task allocation and cooperation execution through a shortest job priority scheduling and round-robin scheduling method.
In a specific embodiment, the self-organizing network is a network management module capable of automatically optimizing and adjusting a network topology according to a real-time channel state and a device load condition. The working mode principle is as follows:
t1, real-time channel state monitoring: the self-organizing network monitors the channel state among all nodes in the network in real time through sensors or other means, wherein the channel state comprises parameters such as signal strength, signal-to-noise ratio, transmission rate and the like.
T2, monitoring equipment load: the self-organizing network also monitors the load condition of each node in the network, including the indexes such as CPU utilization, memory utilization, bandwidth utilization, etc.
T3, selecting neighbor nodes: according to the real-time channel state and the equipment load condition, the self-organizing network can select proper neighbor nodes to communicate, and establish temporary connection.
T4, route optimization and adjustment: the self-organizing network can automatically optimize and adjust the routing paths in the network according to the channel state and the equipment load condition monitored in real time. For example, if the channel quality of a certain node is poor or the load is high, the ad hoc network will automatically adjust the routing path, and select other available nodes for communication, so as to ensure the stability and efficiency of data transmission.
T5, adaptive protocol control: the self-organizing network can also automatically adjust parameters and configuration of a network protocol according to the real-time channel state and the equipment load condition so as to improve the performance and stability of the network.
In an interactive information system based on industrial digitization, a self-organizing network monitors channel states and equipment load conditions in real time and optimizes and adjusts, so that the self-organizing network can effectively improve the transmission rate, stability and reliability of the network and improve the overall performance of the network. In addition, the self-organizing network can automatically adjust a routing path and select neighbor nodes according to the real-time channel state and the equipment load condition, avoid the region with larger channel interference, and reduce the error and the packet loss rate of data transmission. And secondly, the self-organizing network can automatically adjust the topological structure and the routing path of the network according to the real-time channel state and the equipment load condition, adapt to different industrial environments and network requirements, and improve the flexibility and the adaptability of the network. Meanwhile, the self-organizing network can automatically optimize and adjust the network topology structure, so that the requirement for manual intervention is reduced, and the cost and complexity of network management are reduced.
In the above embodiment, the remote diagnosis and maintenance system includes a remote monitoring module, a remote diagnosis module, and a remote maintenance module; the remote monitoring module comprises a state monitoring unit and an early warning notification unit; the state monitoring unit monitors the running state of the equipment in real time through a sensor, and extracts abnormal information and fault signals through a big data analysis method; the big data analysis method is used for carrying out real-time analysis and mining through a distributed storage and calculation framework; the early warning notification unit sends early warning notification to related personnel through the Internet of things and a mobile communication method; the mobile communication method sends out early warning notification to related personnel in a short message, mail and pushing mode; the remote diagnosis module comprises a fault analysis unit and a remote maintenance guide unit; the fault analysis unit performs fault analysis and diagnosis according to historical data and real-time data through a rule-based expert system; the remote maintenance guiding unit gives out remote operation guiding and fault removal suggestions through a remote desktop and a remote assistance method; the remote maintenance module comprises a remote control unit and a remote upgrading unit; the remote control unit realizes remote control operation on equipment through a network communication protocol; the remote upgrading unit realizes remote updating, parameter configuration and calibration operation through an over-the-air downloading method and a cloud management platform.
In particular embodiments, the remote diagnostic and maintenance system monitors the operating status and performance parameters of the industrial equipment in real-time via a remote monitoring module. Data is collected through sensors, monitoring equipment and the like, and the data is transmitted to a remote server or a cloud platform for storage and analysis. The remote diagnosis module processes and analyzes the collected data by using advanced algorithm and data analysis technology to realize fault diagnosis of the equipment. By comparing the actual data of the equipment with preset performance indexes, abnormal conditions are detected and possible fault reasons are identified. After the equipment fault is diagnosed, the remote maintenance module is used for remotely performing maintenance operations, including remote restarting of the equipment, equipment parameter adjustment, firmware update and the like. Through the remote maintenance module, manual intervention and equipment downtime can be reduced, and maintenance efficiency is improved.
In an interactive information system based on industrial digitization, a remote diagnosis and maintenance system can predict possible faults in advance by real-time monitoring and data analysis, and take corresponding precautions to avoid the influence of equipment faults on industrial production. In addition, the remote diagnosis and maintenance system can realize rapid fault location and remote maintenance operation, avoid the time delay of traditional field maintenance, reduce the equipment downtime and improve the production efficiency. Secondly, through remote diagnosis and maintenance system, can reduce the demand of manual inspection and maintenance, reduced manpower resources and maintenance cost. Meanwhile, the remote diagnosis and maintenance system can analyze and mine a large amount of real-time data, find potential problems and improve space, and optimize equipment performance and production flow.
In a specific embodiment, an interactive information system based on industrial digitization firstly, the system collects real-time data such as industrial parameters of temperature, humidity, pressure and the like through various sensors. The data are sent to an intelligent signal processing module for real-time analysis and processing, and then optimized data transmission is performed through an adaptive communication module, so that efficient, stable and reliable data transmission is ensured.
In the data transmission process, the blockchain security module is responsible for carrying out end-to-end encryption and verification on data so as to protect the security and the integrity of the data and prevent the data from being tampered or leaked.
And then, the system transmits the data through a plurality of different paths by utilizing a multi-path transmission method, and the network topology optimization module automatically adjusts the network topology structure and the routing path according to the real-time channel state and the equipment load condition so as to improve the stability and the reliability of data transmission.
Then, the system utilizes the dynamic scheduling module to realize the self-adaptive allocation and priority management of tasks, and simultaneously the operation and maintenance support module realizes the remote diagnosis and maintenance system so as to ensure the efficient operation of the system and timely fault handling.
Finally, the system realizes intelligent compatibility with different devices and systems through a compatibility adaptation system, and limits the access rights of users through a user management module so as to protect the security and confidentiality of the system.
While specific embodiments of the present invention have been described above, it will be understood by those skilled in the art that these specific embodiments are by way of example only, and that various omissions, substitutions, and changes in the form and details of the methods and systems described above may be made by those skilled in the art without departing from the spirit and scope of the invention. For example, it is within the scope of the present invention to combine the above-described method steps to perform substantially the same function in substantially the same way to achieve substantially the same result. Accordingly, the scope of the invention is limited only by the following claims.
Claims (10)
1. An interactive information system based on industrial digitization, which is characterized in that: comprising the following steps:
the intelligent signal processing module is used for carrying out real-time analysis and processing on signals acquired by the sensor through a real-time data processing algorithm based on deep learning, and the real-time data processing algorithm based on the deep learning is used for reducing the influence of signal interference on communication quality through a self-adaptive filtering and interference suppression method;
the self-adaptive communication module optimizes the data transmission rate and the reliability through a self-adaptive modulation algorithm based on machine learning;
The block chain safety module is used for realizing end-to-end safety communication and data encryption through a block chain model based on quantum cryptography;
the communication link transmission module is used for transmitting data through a plurality of different paths by a multi-path transmission method;
the dynamic scheduling module is used for realizing the self-adaptive allocation and priority management of tasks through a real-time data stream management and scheduling mechanism;
The cross-platform application module is intelligently compatible with different devices and systems through a compatibility adaptation system;
The operation and maintenance support module is used for realizing remote monitoring and fault processing of the industrial digital system through a remote diagnosis and maintenance system;
The network topology optimization module is used for realizing automatic optimization and adjustment of a network topology structure through a self-organizing network according to the real-time channel state and the equipment load condition;
And the user management module limits the user access rights through a user rights management mechanism and prevents unauthorized operation and data leakage.
2. An industrial digital based interactive information system according to claim 1, wherein: the block chain model based on quantum cryptography comprises a key management module, a block chain data structure module, an encryption authentication module, a secure communication module and an intelligent contract module;
The key management module generates and distributes a key through a quantum random number generator and a quantum key distribution protocol, and ensures the key security through public-private key conversion and a key memory; the quantum random number generator generates a secret key through the superposition state of single photons and the quantum effect of the detector; the quantum key distribution protocol ensures the privacy of the key through quantum state transmission and quantum measurement; the public-private key conversion realizes the generation and conversion of the public-private key through an elliptic curve encryption algorithm; the key memory stores and manages keys through a cloud database; the block chain data structure module realizes data distributed storage and intelligent management through block chain nodes, a consensus mechanism and intelligent contracts, and the block chain nodes ensure the integrity and the non-tamper property of data through hash functions and merck trees; the encryption authentication module guarantees confidentiality and integrity of data through an asymmetric encryption algorithm and a digital signature, and verifies user identity and data legitimacy through a certificate verification mechanism; the security communication module protects data security in the communication process through a TLS/SSL transmission protocol and prevents illegal access and attack through a firewall and a data packet filter; the intelligent contract module ensures the safety and reliability of intelligent contracts through the Ethernet virtual machine and the intelligent contract framework.
3. An industrial digital based interactive information system according to claim 1, wherein: the principle steps of the multipath transmission method in the interactive information system are as follows:
Step one, planning a path;
Calculating an optimal path and a standby path through a routing algorithm and a dynamic routing protocol BGP according to network topology and transmission requirements;
step two, data segmentation;
dividing data to be transmitted into a plurality of small blocks through a segmentation protocol TCP;
Step three, selecting a path;
selecting a transmission path for each divided data packet through a load balancing algorithm and link state information;
step four, parallel transmission;
transmitting the divided data packets in parallel through a plurality of physical channels and network interfaces;
fifthly, data reorganization;
The received data packets are recombined according to the sequence through the sequence number identification, the time stamp and the caching and sequencing method, and original data is restored;
Step six, checking and correcting errors;
And carrying out integrity check and error repair on the data through Cyclic Redundancy Check (CRC) and Forward Error Correction (FEC).
4. An industrial digital based interactive information system according to claim 1, wherein: the real-time data stream management and scheduling mechanism comprises a task management module, a resource management module and a data stream management module;
The task management module comprises a task collection unit, a task ordering unit and a task distribution unit; the task collecting unit collects task requests through a network transmission protocol and a sensor; the task ordering unit orders and distributes tasks through fuzzy logic; the task allocation unit realizes the dynamic allocation and scheduling of tasks through a parallel computing and load balancing method; the resource management module comprises a resource monitoring unit and a resource allocation unit; the resource monitoring unit monitors and manages resources in real time through an internet of things transmission protocol and a cloud computing mode; according to the demands of tasks and the availability of resources, the resource allocation unit dynamically allocates and schedules the resources through a virtualization and containerization method; the data stream management module comprises a data acquisition unit, a data transmission unit, a data storage unit and a data processing unit; the data acquisition unit acquires environmental and production data in real time through the Internet of things equipment and the sensor network; the data transmission unit realizes the rapid transmission and sharing of data through a wireless network and a distributed storage method; the data storage unit realizes the storage and management of data through a cloud storage and big data storage method; the data processing unit processes and analyzes the data through a real-time data processing algorithm based on deep learning.
5. An industrial digital based interactive information system according to claim 1, wherein: the real-time data processing algorithm based on the deep learning carries out signal filtering through a self-adaptive filtering function; the self-adaptive filtering function performs weighted summation on the input signals through convolution operation to obtain filtered output signals; the formula expression of the adaptive filter function is as follows:
In the formula (1), P is an output filtering result, and is used for representing a signal obtained after filtering; alpha is an offset term used for adjusting the offset of the filtering result; omega is an error term representing the filtered residual part; θ represents the weight in the convolution kernel for performing a weighted summation operation on the input signal; n is the convolution kernel size, used to determine the window size of the filtering; c i denotes an input signal of time domain i for filtering; interference suppression is achieved by an interference suppression function based on a recurrent neural network.
6. An industrial digital based interactive information system according to claim 5, wherein: the interference suppression function based on the cyclic neural network processes an input signal through a cyclic neural network structure; the formula expression of the interference suppression function based on the cyclic neural network is as follows:
In the formula (2), Y is a hidden layer state and is used for storing historical information and processing input signals; z represents an input signal for updating the hidden layer state; w h、Wf and W g are weight matrices of the hidden layer, the input layer and the output layer respectively, and are used for learning and adjusting network parameters; b h and b g are bias items of a hidden layer and an output layer respectively, and are used for adjusting the offset of a network output result; realizing real-time data processing through a real-time data processing function; the real-time data processing function processes the input signal through a depth residual error network; the depth residual error network improves the processing capacity of complex signals by adding a jump connection and residual error block structure; the formula expression of the real-time data processing function is as follows:
In the formula (3), M is an output signal for representing a result obtained after the processing; n is a residual function and is used for processing an input signal and extracting characteristics; { U d } is a weight parameter in the residual network, used for learning and adjusting network parameters; x is the input signal.
7. An industrial digital based interactive information system according to claim 1, wherein: the compatibility adaptation system comprises a device interface module, a data format conversion module, a communication protocol adaptation module, a user interface adaptation module and a functional compatibility module;
The device interface module comprises a device identification unit and a device configuration unit; the device identification unit identifies and verifies the characteristics of different devices through an image identification method; the equipment configuration unit initializes and configures equipment according to equipment types and function requirements through a remote configuration protocol SNMP; the data format conversion module comprises a data analysis unit and a data conversion unit; the data analysis unit analyzes and extracts data generated by the equipment through a data mining and natural language processing method; the data conversion unit converts the analyzed data through a data processing and conversion method; the communication protocol adaptation module realizes intercommunication and data exchange between devices through a network protocol analysis and protocol conversion method; the user interface adaptation module adapts the display and interaction modes of the system through interface layout adjustment and a responsive design method; the function compatibility module maps functions of different devices to a unified field model through a field driving design method so as to realize function compatibility and operation consistency among different devices.
8. An industrial digital based interactive information system according to claim 1, wherein: the self-adaptive modulation algorithm based on machine learning carries out channel state estimation and selection through a self-adaptive modulation selection formula; the adaptive modulation selection formula realizes the selection of adaptive modulation through the judgment of candidate channel state errors; the expression of the adaptive modulation selection formula is:
In formula (4), T represents an optimal channel state; σ represents a set of selectable channel states for selecting the best channel state; k is a transmitted signal for evaluating the channel state; l represents the received signal for evaluating the current channel state; τ represents the ζ channel state for calculating an error between the received signal and the predicted signal; calculating the information transmission rate under each channel state through an information transmission rate calculation formula; the information transmission rate calculation formula evaluates the channel reliability and the transmission rate through the signal-to-noise ratio of the channel state so as to optimize the data transmission rate and the reliability; the expression of the information transmission rate calculation formula is as follows:
in formula (5), R represents an information transmission rate; delta represents the transmit power for calculating the signal-to-noise ratio; s represents noise power spectral density, which is used for influencing information transmission rate; m represents a channel bandwidth for calculating an information transmission rate in each channel state.
9. An industrial digital based interactive information system according to claim 1, wherein: the self-organizing network comprises a node management module, a topology management module, a routing module, a security management module and a resource scheduling module;
The node management module comprises a node state detection unit and a load condition analysis unit; the node state detection unit monitors the node running state in real time through a sensor; the load condition analysis unit analyzes and predicts the load condition of the nodes through a neural network and a decision tree; the topology management module dynamically optimizes and adjusts a network topology structure according to the real-time channel state and the equipment load condition through a graph theory and a network optimization method; constructing a topological structure in the Ethernet by the graph theory through a minimum spanning tree algorithm so as to optimize the network communication efficiency; the network optimization method dynamically adjusts a routing path in a network according to the real-time flow condition through a flow balancing algorithm so as to improve the overall performance of the network; the routing module selects an optimal path and a route according to a network topological structure and equipment load conditions through a routing selection and minimum cost greedy algorithm; the resource scheduling module comprises a resource allocation unit and a task cooperative unit; the resource allocation unit realizes the dynamic allocation and management of bandwidth through frequency division multiplexing and time division multiplexing; the task cooperation unit realizes task allocation and cooperation execution through a shortest job priority scheduling and round-robin scheduling method.
10. An industrial digital based interactive information system according to claim 1, wherein: the remote diagnosis and maintenance system comprises a remote monitoring module, a remote diagnosis module and a remote maintenance module;
The remote monitoring module comprises a state monitoring unit and an early warning notification unit; the state monitoring unit monitors the running state of the equipment in real time through a sensor, and extracts abnormal information and fault signals through a big data analysis method; the big data analysis method is used for carrying out real-time analysis and mining through a distributed storage and calculation framework; the early warning notification unit sends early warning notification to related personnel through the Internet of things and a mobile communication method; the mobile communication method sends out early warning notification to related personnel in a short message, mail and pushing mode; the remote diagnosis module comprises a fault analysis unit and a remote maintenance guide unit; the fault analysis unit performs fault analysis and diagnosis according to historical data and real-time data through a rule-based expert system; the remote maintenance guiding unit gives out remote operation guiding and fault removal suggestions through a remote desktop and a remote assistance method; the remote maintenance module comprises a remote control unit and a remote upgrading unit; the remote control unit realizes remote control operation on equipment through a network communication protocol; the remote upgrading unit realizes remote updating, parameter configuration and calibration operation through an over-the-air downloading method and a cloud management platform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410368261.2A CN118282531A (en) | 2024-03-28 | 2024-03-28 | Interactive information system based on industrial digitization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410368261.2A CN118282531A (en) | 2024-03-28 | 2024-03-28 | Interactive information system based on industrial digitization |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118282531A true CN118282531A (en) | 2024-07-02 |
Family
ID=91633139
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410368261.2A Pending CN118282531A (en) | 2024-03-28 | 2024-03-28 | Interactive information system based on industrial digitization |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118282531A (en) |
-
2024
- 2024-03-28 CN CN202410368261.2A patent/CN118282531A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10904125B2 (en) | Active probe construction using machine learning for measuring SD-WAN tunnel metrics | |
| EP2918044B1 (en) | Root cause analysis in a sensor-actuator network | |
| US20200389371A1 (en) | Predicting network states for answering what-if scenario outcomes | |
| Junior et al. | A Survey on Trustworthiness for the Internet of Things | |
| Gupta et al. | Optimal LQG control across packet-dropping links | |
| EP1738470B1 (en) | Apparatus and method for improving reliability of collected sensor data over a network | |
| JP6212276B2 (en) | Power system event processing system | |
| US20150188751A1 (en) | Dynamically computing fate sharing in computer networks using learning machines | |
| EP3697063B1 (en) | Communication control device, communication control method, and communication system | |
| WO2019116418A1 (en) | Failure analysis device, failure analysis method, and failure analysis program | |
| Friesen et al. | Machine learning for zero-touch management in heterogeneous industrial networks-a review | |
| Ye et al. | Federated traffic engineering with supervised learning in multi-region networks | |
| Tonini et al. | Network slicing automation: Challenges and benefits | |
| CN116668381A (en) | Virtual distributed network interface controller | |
| US11902127B2 (en) | Automatic detection and tracking of anomalous rectifiable paths using time-series dynamics | |
| Yu et al. | Digital twin driven service self-healing with graph neural networks in 6g edge networks | |
| CN116708246A (en) | Method, device, equipment and storage medium for detecting transmission link | |
| CN118282531A (en) | Interactive information system based on industrial digitization | |
| CN116224791A (en) | Collaborative training control method for intelligent manufacturing collaborative robot edge system | |
| Tang et al. | How to use in-band network telemetry wisely: Network-wise orchestration of Sel-INT | |
| Tajiri et al. | Optimizing edge-cloud cooperation for machine learning accuracy considering transmission latency and bandwidth congestion | |
| Chen et al. | Determining redundant links of multiagent systems in keeping or improving consensus convergence rates | |
| Wubete et al. | Importance of optical metrics for IGP configuration change prediction | |
| Zhi et al. | The flexible resource management in optical data center networks based on machine learning and SDON | |
| Bolodurina et al. | Development and research of model for ensuring reliability of operation of network infrastructure objects in cyber-physical system located in the cloud platform |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |