Signal edge acquisition method and system based on apl

Abstract

The application provides an APL-based signal edge collection method and system, and relates to the field of signal collection. The method is applied to an edge server and comprises the following steps: acquiring a first signal data stream of a machine device in an industrial automation scene; determining a working condition state based on the first signal data stream in combination with a context perception method, adjusting the working mode and sampling frequency of each sensor node according to the working condition state, and obtaining an adjusted operation instruction set; generating a system running state report based on the first signal data stream and the adjusted operation instruction set to obtain a second signal data stream; constructing a trust framework of the industrial automation scene, and transmitting the second signal data stream to a central control system by using a standardized communication protocol based on the trust framework; and the standardized communication protocol is a communication protocol determined based on an adaptive protocol conversion gateway method. The technical scheme provided by the application improves the reliability of signal collection and processing.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of signal acquisition, and in particular to a signal edge acquisition method and system based on APL. BACKGROUND

[0002] In the modern industrial automation environment, especially in the oil and gas, chemical, water and wastewater treatment, food and beverage industries, a large number of sensor nodes are distributed around the machine equipment in a wide area. The edge server is located on the side of the machine equipment and is responsible for collecting, processing and summarizing the sensor signal data collected by the sensor nodes. With the in-depth development of industrial automation, higher requirements are put forward for the signal edge acquisition method, such as high precision and real-time, resource optimization and efficiency improvement, safety and reliability, self-adaptation and intelligence, etc.

[0003] At present, most industrial automation systems use traditional communication protocols and fixed configuration of sensor nodes working mode, for example: the sensor nodes are usually set to a fixed sampling frequency, which leads to collecting too much redundant data in some cases, wasting resources; while in other cases, it may miss the key changes. The traditional communication protocol is a single communication protocol, which is vulnerable to unauthorized access and attacks.

[0004] Therefore, the prior art has the problems of low data acquisition reliability, and low data transmission security and reliability. SUMMARY

[0005] Embodiments of the present application provide a signal edge acquisition method and system based on an advanced physical layer (APL) to solve the problem of low data acquisition reliability and low data transmission security and reliability in the prior art.

[0006] In a first aspect, embodiments of the present application provide a signal edge acquisition method based on APL, applied to an edge server, the edge server being a device located on the side of the machine equipment and connected to the sensor nodes through the advanced physical layer (APL) technology, the method comprising:

[0007] Obtaining a first signal data stream of the machine equipment in the industrial automation scene; the first signal data stream is a signal data stream formed by multiple sensor signal data;

[0008] Based on the first signal data stream, a working condition state is determined by combining a context awareness method, the working condition state is used to adjust the working mode and sampling frequency of each sensor node, and an adjusted operation instruction set is obtained;

[0009] generate a system running status report based on the first signal data stream and the adjusted operation instruction set, aggregate the first signal data stream, the adjusted operation instruction set, and the system running status report to obtain a second signal data stream;

[0010] construct a trust framework for the industrial automation scene, and transmit the second signal data stream to the central control system based on the trust framework and using a standardized communication protocol; the standardized communication protocol is a communication protocol determined based on an adaptive protocol conversion gateway method.

[0011] Optionally, the constructing of the trust framework for the industrial automation scene and the transmitting of the second signal data stream to the central control system based on the trust framework and using the standardized communication protocol comprise:

[0012] using a graph database to construct a graph model by taking sensor nodes as vertices and taking the association relationship between the sensor nodes as edges; the vertices include the following attributes: identifier, location information, and type identifier; the weight corresponding to the edges represents the association strength or communication quality between the sensor nodes;

[0013] extracting index features of the graph model; the index features include node degree distribution, average path length, and clustering coefficient;

[0014] designing and deploying a trust framework based on the graph model and the index features;

[0015] calculating target trust scores of each sensor node in the trust framework, and establishing a dynamic encryption tunnel for transmitting the second signal data stream based on the target trust scores of the sensor nodes; the dynamic encryption tunnel uses different target levels of encryption methods for different data segments in the second signal data stream;

[0016] transmitting the second signal data stream from the edge server to the central control system by using the dynamic encryption tunnel and the standardized communication protocol.

[0017] Optionally, the designing and deploying of the trust framework based on the graph model and the index features comprise:

[0018] obtaining requirement information of the industrial automation scene, selecting a blockchain platform meeting the requirement information from a plurality of blockchain platforms, and selecting a consensus algorithm corresponding to the requirement information from a plurality of consensus algorithms; the requirement information includes real-time information, security information, and expansibility information;

[0019] after the selected blockchain platform and consensus algorithm, compiling a smart contract based on the graph model and a preset compilation rule; the smart contract is used to manage the identity authentication and authorization mode of all sensor nodes;

[0020] design a trust score mechanism according to the index characteristics;

[0021] The blockchain platform, consensus algorithm, smart contract and trust score mechanism are comprehensively utilized to design and deploy a trust framework.

[0022] Optionally, the target trust scores of the sensor nodes in the trust framework are calculated, and a dynamic encryption tunnel for transmitting the second signal data stream is established based on the target trust scores of the sensor nodes; the dynamic encryption tunnel adopts different target levels of encryption modes for different data segments in the second signal data stream, including:

[0023] According to the historical behavior, location information and type identification of the sensor nodes, the initial trust scores of the sensor nodes are calculated by using the target trust score mechanism in the trust framework;

[0024] According to the dynamic adjustment mechanism, the initial trust scores of the sensor nodes are adjusted by the smart contract in the trust framework to obtain the target trust scores of the sensor nodes in the trust framework;

[0025] The second signal data stream is divided into multiple data segments;

[0026] For each data segment, the following process is performed: determining the sensor nodes related to the data segment, when the number of related sensor nodes is one, determining the target trust score of the related sensor node as the final value; or when the number of related sensor nodes is multiple, determining the weighted sum of the target trust scores of all the related sensor nodes as the final value;

[0027] Determining the target interval in which the final value is located, and determining the target level of encryption mode corresponding to the target interval as the encryption mode adopted by the dynamic encryption tunnel when transmitting the data segment.

[0028] Optionally, the target level of encryption mode corresponding to the target interval is determined as the encryption mode adopted by the dynamic encryption tunnel when transmitting the data segment, including:

[0029] An encryption level mapping table is obtained, and the initial level corresponding to the target interval is determined according to the encryption level mapping table; wherein each interval corresponds to an initial level;

[0030] The encryption strength adjustment factor is dynamically calculated according to the real-time network status and system load of the edge server, and the initial level corresponding to the target interval is adjusted by using the encryption strength adjustment factor to obtain the target level;

[0031] The encryption mode of the target level is determined as an encryption mode adopted by a dynamic encryption tunnel when the data segments are transmitted; the target level includes a high priority level, a medium priority level and a low priority level; different encryption modes correspond to different target levels.

[0032] Optionally, the working condition state is determined based on the first signal data stream and in combination with a context awareness method, including:

[0033] The first signal data stream is cleaned, and in the cleaning process, a Z-score method is used in combination with a local outlier factor to remove abnormal values, and a wavelet transform is used in combination with a Kalman filter to remove noise, to obtain a third signal data stream;

[0034] Key features of the third signal data stream under different scales are extracted using a multi-scale wavelet transform to reduce data dimensions, to obtain a feature set; the key features include an average value, a variance and a trend change;

[0035] The importance of the key features is evaluated using a context awareness method in combination with information gain and context factors, to obtain a feature importance evaluation result;

[0036] Based on the feature set and the feature importance evaluation result, a trained random forest is used to identify the working condition state of the machine device.

[0037] Optionally, the importance of the key features is evaluated using a context awareness method in combination with information gain and context factors, to obtain a feature importance evaluation result, including:

[0038] For each key feature in the feature set, information gain of the key feature to the working condition state classification is calculated, and a context factor of the key feature is generated; the context factor is at least one of a timestamp, an operation mode and an external environment parameter;

[0039] The context factor is quantified to obtain a context factor quantization value;

[0040] The information gain and the context factor quantization value are nonlinearly transformed using a context awareness method to evaluate the importance of the key features, to obtain a feature importance evaluation result.

[0041] In a second aspect, an embodiment of the present application provides an APL-based signal edge collection system, applied to an edge server, the edge server being a device located on a machine device side and connected to a sensor node through an advanced physical layer (APL) technology, and including:

[0042] An acquisition module is configured to acquire a first signal data stream of a machine device in an industrial automation scene; the first signal data stream is a signal data stream formed by multi-sensor signal data;

[0043] determining an adjustment module for determining a working condition state based on the first signal data stream in combination with a context awareness method, adjusting the working mode and sampling frequency of each sensor node according to the working condition state to obtain an adjusted operation instruction set;

[0044] generating a summary module for generating a system running state report based on the first signal data stream and the adjusted operation instruction set, summarizing the first signal data stream, the adjusted operation instruction set and the system running state report to obtain a second signal data stream;

[0045] constructing a transmission module for constructing a trust framework of the industrial automation scene, transmitting the second signal data stream to a central control system based on the trust framework by using a standardized communication protocol; the standardized communication protocol is a communication protocol determined based on an adaptive protocol conversion gateway method.

[0046] In a third aspect, an embodiment of the present application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement the APL-based signal edge collection method according to any one of the first aspect.

[0047] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program, when the computer program is executed by a computer, a APL-based signal edge collection method according to any one of the first aspect is implemented.

[0048] In an embodiment of the present application, an APL-based signal edge collection method is provided, which is applied to an edge server, the edge server is a device located at a machine device side and connected with a sensor node through an advanced physical layer (APL) technology, and the method includes the following steps: obtaining a first signal data stream of the machine device in an industrial automation scene; the first signal data stream is a signal data stream formed by multiple sensor signal data; determining a working condition state based on the first signal data stream in combination with a context awareness method, adjusting the working mode and sampling frequency of each sensor node according to the working condition state to obtain an adjusted operation instruction set; generating a system running state report based on the first signal data stream and the adjusted operation instruction set, summarizing the first signal data stream, the adjusted operation instruction set and the system running state report to obtain a second signal data stream; constructing a trust framework of the industrial automation scene, transmitting the second signal data stream to a central control system based on the trust framework by using a standardized communication protocol; the standardized communication protocol is a communication protocol determined based on an adaptive protocol conversion gateway method.

[0049] The embodiments of the present application realize efficient acquisition and processing of the first signal data stream of machine equipment in the industrial automation scene by integrating advanced physical layer technology in the edge server and connecting with intelligent sensing nodes. This method not only accurately determines the working condition state by combining the context awareness method, and dynamically adjusts the working mode and sampling frequency of each sensor node, optimizes the resource configuration, and improves the accuracy and real-time performance of data acquisition; but also builds a trust framework for the industrial automation scene, adopts a standardized communication protocol based on an adaptive protocol conversion gateway method, ensures the security and reliability of data transmission, and enhances the compatibility and flexibility of the industrial automation system. This method improves the overall performance and intelligent level of the industrial automation system, and provides reliable technical support for real-time monitoring and decision-making. Moreover, the embodiments of the present application can ensure the security and reliability of data transmission through graph database and blockchain technology, and also improve the adaptive ability and management efficiency of the system architecture.

[0050] These aspects or other aspects of the present application will be more apparent in the following description of the embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0052] Figure 1 A flow chart of a signal edge acquisition method based on APL provided by an embodiment of the present application;

[0053] Figure 2 A structural schematic diagram of a signal edge acquisition system based on APL provided by an embodiment of the present application;

[0054] Figure 3 A structural schematic diagram of a computing device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0055] In order to make those skilled in the art better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application.

[0056] In some of the flowcharts described in the specification and claims of the present application and in the above description of the drawings, a plurality of operations are included in a particular order, but it should be clearly understood that these operations can be performed in the order in which they appear in this text or in parallel, and the serial numbers of the operations, such as 11, 12, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these flowcharts can include more or fewer operations, and these operations can be performed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this text are used to distinguish different messages, devices, modules, etc., and do not represent the order of precedence, nor do "first" and "second" represent different types.

[0057] The technical solutions in the embodiments of the present application will be described clearly and completely in the specification of the present application in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0058] Figure 1 A flowchart of a signal edge collection method based on APL provided by an embodiment of the present application is shown in Figure 1 The method is applied to an edge server, which is a device located on the side of a machine device and connected to a sensor node through an advanced physical layer (APL) technology, and includes the following steps.

[0059] S11, obtaining a first signal data stream of a machine device in an industrial automation scene. The first signal data stream is a signal data stream formed by multi-sensor signal data.

[0060] In this embodiment, the machine device is provided with a plurality of sensor nodes, and the plurality of sensor nodes are used to collect multi-sensor signal data. The multi-sensor signal data can be original signal data or pre-processed signal data, which is not limited in this embodiment. Exemplarily, the signal data includes physical parameters such as temperature, pressure, humidity, vibration, and flow. These data reflect the real-time running condition of the machine device under the current working condition.

[0061] S12, determining a working condition state based on the first signal data stream and in combination with a context awareness method, adjusting the working mode and sampling frequency of each sensor node according to the working condition state, and obtaining an adjusted operation instruction set.

[0062] The context awareness method can evaluate the importance of key features using context factors (such as timestamps, operating modes, external environmental parameters, etc.) to more accurately determine the current working condition state of the machine device. The working condition state can refer to the specific working state of the machine device at a certain time, such as normal operation, slight abnormality, or serious failure, etc. The parameters of the sensor nodes are dynamically adjusted according to the current working condition state to optimize data acquisition efficiency and resource utilization. The operation instruction set contains a set of instructions for adjusting the sensor operating mode and sampling frequency, which is used to control the sensor nodes to make corresponding adjustments.

[0063] For example, the current working condition state of the machine device is "mild overheating", and the embodiment automatically adjusts the sampling frequency of the related temperature sensor nodes according to the working condition state, so that the sampling frequency is increased from 1 per second to 5 per second. In addition, the embodiment can also control the activation of additional cooling mechanisms to prevent the overheating problem from worsening while ensuring timely capture of temperature changes.

[0064] S13, generating a system running state report based on the first signal data stream and the adjusted operation instruction set, and summarizing the first signal data stream, the adjusted operation instruction set, and the system running state report to obtain a second signal data stream.

[0065] The system running state report includes the current working condition state of the machine device, the operation measures taken, and the future adjustment plan. The report not only contains historical data, but also provides a detailed analysis of the current working condition state.

[0066] S14, constructing a trust framework for the industrial automation scene, and transmitting the second signal data stream to the central control system based on the trust framework using a standardized communication protocol. The standardized communication protocol is determined based on an adaptive protocol conversion gateway method.

[0067] The trust framework can be a decentralized trust framework or a hybrid framework, which is not limited in the embodiment. The communication protocol determined based on the adaptive protocol conversion gateway method supports seamless connection of multiple network environments and device types, ensuring efficient and reliable data transmission. The trust framework can also provide a dynamic encryption tunnel, which uses different levels of encryption for different target trust score data segments to ensure data security and integrity.

[0068] By performing steps S11-S14, the embodiment of the application can achieve efficient and secure data collection and transmission in an industrial automation environment. Specifically, the work condition state evaluation is more accurate by combining the context awareness method, the working mode and sampling frequency of the sensor node are dynamically adjusted according to the work condition state, the resource configuration is optimized, unnecessary energy consumption and network load are avoided, and the overall efficiency of the industrial automation system is improved. By constructing a trust framework, only verified and authorized devices can participate in data transmission, and dynamic encryption tunnels are used to protect the security and integrity of data, preventing unauthorized access and data tampering. The adaptive protocol conversion gateway method supports standardized communication protocols for seamless connection of various network environments and device types, enhancing the compatibility and scalability of the system. The application of smart contracts simplifies identity verification and authorization management, reduces management and maintenance costs, and the trust score mechanism can adjust the trust level of the node in real time to ensure the continuous and stable operation of the industrial automation system.

[0069] In some possible embodiments, the embodiment can further describe step S12 as follows. For example, S12, based on the first signal data stream, determines the work condition state by combining the context awareness method, including:

[0070] Step 121, cleaning the first signal data stream, using the Z-score method combined with the local outlier factor to remove outliers, and using wavelet transform combined with the Kalman filter to remove noise to obtain the third signal data stream.

[0071] It should be understood that the local outlier factor is an algorithm for identifying outliers in the first signal data set. For a signal data point, its local density is compared with the value 1. If it is greater than 1, it means that the local density of the signal data point is lower than that of the signal data points in its neighborhood, so the signal data point may be an outlier. The local outlier factor considers the local density. For a data set with complex distribution or different density regions, the local outlier factor can more accurately identify outliers, which are outliers.

[0072] The embodiment of the application removes outliers according to the Z-score method combined with the local outlier factor, and removes noise using wavelet transform combined with the Kalman filter, ensuring the quality of the third signal data stream. This not only reduces the interference in the data, but also improves the accuracy of subsequent analysis.

[0073] Step 122, using multi-scale wavelet transform to extract key features of the third signal data stream under different scales to reduce the data dimension to obtain a feature set; the key features include mean, variance and trend change.

[0074] It should be understood that in the embodiments of the present application, the multi-scale wavelet transform can effectively extract key features at different scales, such as mean value, variance and trend change, thereby retaining important information in the data while reducing the data dimension and improving the processing efficiency.

[0075] In step 123, the importance of the key features is evaluated using a context-aware method by combining the information gain and the context factor, to obtain a feature importance evaluation result.

[0076] It should be understood that the importance of the key features is evaluated by combining the information gain and the context factor, which ensures that the most useful features for the working condition state classification are selected. This context-aware method takes into account multiple factors such as timestamps, operating modes and external environmental parameters, making the feature selection more accurate.

[0077] As a possible implementation, in step 123, the importance of the key features is evaluated using a context-aware method by combining the information gain and the context factor, to obtain a feature importance evaluation result, which includes:

[0078] In step a1, for each key feature in the feature set, the information gain of the key feature for the working condition state classification is calculated, and the context factor of the key feature is generated; the context factor refers to the environment and operating conditions related to the current working condition state, such as timestamps, operating modes and external environmental parameters. The information gain is used to evaluate the importance of each key feature in distinguishing different working condition states. Among them, the operating mode refers to the working mode of the machine equipment, such as normal operation, maintenance mode or fault mode.

[0079] In step a2, the context factor is quantized to obtain a context factor quantization value. In this embodiment, the non-numeric context factor is converted to a numeric representation to ensure that all features can be evaluated in the same framework.

[0080] In step a3, a context-aware method is used to perform a nonlinear transformation on the information gain and the context factor quantization value to evaluate the importance of the key features, to obtain a feature importance evaluation result.

[0081] It should be understood that the nonlinear transformation enhances the understanding and adaptability to complex working condition states, especially in a variable industrial environment.

[0082] By performing steps a1 to a3, the embodiments of the present application not only improve the accuracy of feature selection and enhance the adaptability and flexibility of the method, but also improve the reliability and stability of the industrial automation system, simplify the management and maintenance work. These technologies provide reliable technical support for efficient operation in the industrial automation environment, ensuring the accuracy and reliability of data-driven decision-making.

[0083] Step 124, based on the feature set and the feature importance evaluation result, a trained random forest is used to identify the working condition state of the machine equipment.

[0084] It should be understood that the random forest is a powerful ensemble learning method with high accuracy and good generalization ability, which can provide reliable classification results in complex data environments. Based on the feature set and the feature importance evaluation result, the trained random forest model can accurately identify the working condition state of the machine equipment.

[0085] By performing steps 121-124, the embodiments of the present application clean the data stream, extract features, and evaluate importance, so that the industrial automation system can quickly and accurately identify the current working condition state of the machine equipment, and dynamically adjust the working mode and sampling frequency of the sensor nodes as needed. This not only improves the real-time response capability of the industrial automation system, but also optimizes resource allocation and avoids unnecessary energy consumption and network load. The entire process from data cleaning to working condition state identification is automated, reducing the need for manual intervention and reducing management and maintenance costs. At the same time, the application of intelligent algorithms enables the industrial automation system to adaptively respond to different working condition requirements, enhancing the flexibility and intelligence level of the industrial automation system.

[0086] In some possible embodiments, the present embodiment can further describe step S14. For example, step S14, constructing a trust framework for the industrial automation scene, and based on the trust framework, transmitting the second signal data stream to the central control system using a standardized communication protocol, includes:

[0087] Step 141, using a graph database to construct a graph model by taking the sensor nodes as vertices and the association relationship between the sensor nodes as edges; the vertices include the following attributes: identifier, location information, and type identifier; the weight corresponding to the edge represents the association strength or communication quality between the sensor nodes. It should be understood that the identifier is used to uniquely identify each sensor node. The location information can refer to the position coordinates of the sensor node in the physical space. The type identifier can refer to the type of the sensor node, such as a temperature sensor, a pressure sensor, etc.

[0088] Step 142, extracting index features of the graph model; the index features include node degree distribution, average path length, and clustering coefficient. Among them, the node degree distribution describes the statistical distribution of the connection number of each vertex, reflecting the connectivity of the graph model network. The average path length is the average length of the shortest path from one vertex to another, reflecting the compactness of the graph model network. The clustering coefficient is used to measure the degree of connection between the neighbors of a vertex, reflecting the local clustering characteristics of the graph model network.

[0089] Step 143, based on the graph model and the index features, designing and deploying a trust framework.

[0090] As a possible implementation, step 143, based on the graph model and the index feature, designs and deploys a trust framework, including:

[0091] Step b1, obtaining the requirement information of the industrial automation scene, selecting a blockchain platform meeting the requirement information from multiple blockchain platforms, and selecting a consensus algorithm corresponding to the requirement information from multiple consensus algorithms; the requirement information includes real-time information, security information, and expansibility information.

[0092] Step b2, after selecting the blockchain platform and the consensus algorithm, compiling a smart contract based on the graph model and a preset compilation rule; the smart contract is used to manage the identity authentication and authorization mode of all sensor nodes.

[0093] Step b3, designing a trust score mechanism according to the index feature.

[0094] Step b4, comprehensively utilizing the blockchain platform, the consensus algorithm, the smart contract, and the trust score mechanism, designing and deploying a trust framework.

[0095] By performing steps b1-b4, the embodiment of the present application selects the most suitable combination from multiple blockchain platforms and consensus algorithms according to the requirement information such as real-time, security, and expansibility, to ensure the security and stability of the industrial automation system. This customized selection method enables the industrial automation system to better meet the needs of different application scenarios. The smart contract is used to manage the identity authentication and authorization mode of all sensor nodes, ensuring that only verified and authorized devices can participate in data transmission. The application of the smart contract simplifies management and maintenance, while providing tamper-proof records and enhancing the credibility of the industrial automation system. Therefore, the embodiment of the present application not only enhances the security and reliability of data transmission, but also improves the compatibility and flexibility of the industrial automation system, simplifying management and maintenance. These technologies provide more comprehensive technical support for efficient operation in the industrial automation environment.

[0096] Step 144, calculating the target trust score of each sensor node under the trust framework, and based on the target trust score of each sensor node, establishing a dynamic encryption tunnel for transmitting the second signal data stream; the dynamic encryption tunnel uses different target levels of encryption methods for different data segments in the second signal data stream.

[0097] For example, the encryption method can involve identity authentication and access control.

[0098] As a possible implementation manner, step 144, the target trust score of each sensor node in the trust framework is calculated, and a dynamic encryption tunnel for transmitting the second signal data stream is established based on the target trust score of each sensor node; the dynamic encryption tunnel adopts different target level encryption modes for different data segments in the second signal data stream, including:

[0099] Step c1, according to the historical behavior, location information and type identification of the sensor node, the initial trust score of each sensor node is calculated by using the target trust score mechanism in the trust framework.

[0100] Step c2, according to the dynamic adjustment mechanism, the initial trust score of each sensor node is adjusted by the smart contract in the trust framework to obtain the target trust score of each sensor node in the trust framework.

[0101] Step c3, the second signal data stream is divided into multiple data segments.

[0102] Step c4, for each data segment, the following process is performed: determining the sensor nodes related to the data segment, when the number of related sensor nodes is one, the target trust score of the related sensor nodes is determined as the final value; or when the number of related sensor nodes is multiple, the weighted sum of the target trust scores of all related sensor nodes is determined as the final value; determining the target interval where the final value is located, and determining the encryption mode corresponding to the target level of the target interval as the encryption mode adopted by the dynamic encryption tunnel when transmitting the data segment.

[0103] Specifically, in step c4, the encryption mode corresponding to the target level of the target interval is determined as the encryption mode adopted by the dynamic encryption tunnel when transmitting the data segment, including:

[0104] Step c41, an encryption level mapping table is obtained, and the initial level corresponding to the target interval is determined according to the encryption level mapping table; each interval corresponds to an initial level.

[0105] Step c42, the encryption strength adjustment factor is dynamically calculated according to the real-time network status and system load of the edge server, and the initial level corresponding to the target interval is adjusted by using the encryption strength adjustment factor to obtain the target level.

[0106] Step c43, the encryption mode of the target level is determined as the encryption mode adopted by the dynamic encryption tunnel when transmitting the data segment; the target level includes high priority, medium priority and low priority; different target levels correspond to different encryption modes.

[0107] By performing steps c41-c43, the present embodiment introduces an encryption strength adjustment factor, dynamically adjusts the encryption level based on real-time network conditions and system load, enhancing the adaptive ability and response speed of the industrial automation system. Moreover, the present embodiment proposes a hierarchical encryption strategy with high, medium and low priority levels, ensuring that data segments of different importance levels are encrypted in corresponding ways, further improving the security and resource utilization efficiency of data transmission. In addition, the present embodiment also considers the influence of real-time network conditions and system load on the encryption method, ensuring that the selection of the encryption method is not only based on static trust scores, but also combined with real-time network and system status, enhancing the flexibility and adaptability of the industrial automation system.

[0108] By performing steps c1-c4, the present embodiment provides an initial trust score calculation method based on historical behavior, location information and type identification, and dynamically adjusts the trust score through a smart contract, ensuring the accuracy and real-time performance of the evaluation. The method of data segment division and sharding encryption is introduced, and appropriate encryption levels are selected according to the importance of different data segments, improving the security and flexibility of data transmission. The method of data segment division and sharding encryption is introduced, and appropriate encryption levels are selected according to the importance of different data segments, improving the security and flexibility of data transmission. According to the target interval where the final value is located, the corresponding encryption method is selected, ensuring that data of different importance levels is encrypted with corresponding encryption strength, further improving the security of data transmission.

[0109] Step 145, through the dynamic encryption tunnel, the second signal data stream is transmitted from the edge server to the central control system using a standardized communication protocol.

[0110] By performing steps 141-145, the embodiment of the application designs a trust framework according to the graph model and the index feature, ensuring that only verified and authorized devices can participate in data transmission, preventing unauthorized access and data tampering. According to the target trust score of different data segments, different levels of encryption are used to ensure the security and integrity of data transmission, especially when transmitting sensitive data. By extracting index features such as node degree distribution, average path length, and clustering coefficient, industrial automation systems can more accurately assess the strength of node association and communication quality, reasonably allocate resources, reduce unnecessary energy consumption and network load, and improve overall efficiency. Based on real-time context information, the importance of the feature is dynamically adjusted to ensure that the industrial automation system can flexibly respond to different working condition requirements, improving the real-time response capability of the industrial automation system. The security and reliability of the industrial automation system in data transmission are enhanced, and the compatibility and flexibility of the industrial automation system are improved. These technologies not only improve the overall performance and reliability of the industrial automation system, but also provide more comprehensive technical support for efficient operation in the industrial automation environment. In particular, by introducing graph databases, blockchain technology, and smart contracts, these methods not only enhance the security of data transmission, but also improve the adaptive ability and management efficiency of the industrial automation system.

[0111] Figure 2 A structural diagram of a signal edge collection system based on APL provided by the embodiment of the application is shown in Figure 2 The system is applied to an edge server, which is a device located on the side of a machine device and connected to a sensor node through advanced physical layer (APL) technology. The system includes:

[0112] The acquisition module 21 is configured to acquire a first signal data stream of a machine device in an industrial automation scene. The first signal data stream is a signal data stream formed by multiple sensor signal data.

[0113] The determination and adjustment module 22 is configured to determine a working condition state based on the first signal data stream and a context perception method, adjust the working mode and sampling frequency of each sensor node according to the working condition state, and obtain an adjusted operation instruction set.

[0114] The generation and summary module 23 is configured to generate a system running state report based on the first signal data stream and the adjusted operation instruction set, summarize the first signal data stream, the adjusted operation instruction set, and the system running state report, and obtain a second signal data stream.

[0115] The construction transmission module 24 is configured to construct a trust framework of the industrial automation scene, and transmit the second signal data stream to the central control system based on the trust framework by using a standardized communication protocol.

[0116] Figure 2 The APL-based signal edge acquisition system can perform Figure 1 The APL-based signal edge acquisition method of the embodiments described above has the same implementation principles and technical effects, and will not be described in detail. The specific operation modes of each module and unit of the APL-based signal edge acquisition system in the above embodiments have been described in detail in the embodiments related to the method, and will not be described in detail here.

[0117] In one possible design, Figure 2 The APL-based signal edge acquisition system of the embodiments described above can be implemented as a computing device, such as a computer. Figure 3 As shown in the figure, the computing device can include a storage component 31 and a processing component 32.

[0118] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32.

[0119] The processing component 32 is configured to obtain a first signal data stream of a machine device in an industrial automation scene; the first signal data stream is a signal data stream formed by multi-sensor signal data; based on the first signal data stream, a working condition state is determined by combining a context perception method, the working mode and the sampling frequency of each sensor node are adjusted according to the working condition state, and an adjusted operation instruction set is obtained; based on the first signal data stream and the adjusted operation instruction set, a system running state report is generated, the first signal data stream, the adjusted operation instruction set and the system running state report are summarized, and a second signal data stream is obtained; a trust framework of the industrial automation scene is constructed, and the second signal data stream is transmitted to the central control system based on the trust framework by using a standardized communication protocol; the standardized communication protocol is a communication protocol determined based on an adaptive protocol conversion gateway method.

[0120] The processing component 32 can include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component can also be one or more Application-Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Process Device (DSPD), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components, for executing the above method.

[0121] The storage component 31 is configured to store various types of signal data to support the operation of the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Random Access Memory (RAM), Static Random-Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0122] Of course, the computing device can also include other components, such as an input / output interface, a display component, a communication component, etc.

[0123] The input / output interface provides an interface between the processing component and peripheral interface modules, which can be output devices, input devices, etc.

[0124] The communication component is configured to facilitate wired or wireless communication between the computing device and other devices, etc.

[0125] The computing device can be a physical device or an elastic computing host provided by a cloud computing platform, and the computing device can refer to a cloud server, and the processing component, the storage component, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0126] The embodiment of the application further provides a computer storage medium, which stores a computer program, and the computer program can realize the above-mentioned Figure 1 The APL-based signal edge acquisition method of the embodiment shown.

[0127] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-mentioned system and units can refer to the corresponding processes in the foregoing method embodiments, and will not be described here.

[0128] The system embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, can be located in one place or can be distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the embodiment scheme according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0129] Through the foregoing description of the embodiments, those skilled in the art can clearly understand that each embodiment can be realized by means of software and a necessary general hardware platform, and of course, can also be realized by hardware. Based on such understanding, the foregoing technical solutions can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the method described in each embodiment or some parts of the embodiment.

[0130] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the application, and not to limit them; although the application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement to some technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the application.

Claims

1. A signal edge acquisition method based on APL, characterized in that, Applied to edge servers, which are devices located on the machine side and connected to sensor nodes via Advanced Physical Layer (APL) technology, including: Acquire the first signal data stream of machines and equipment in an industrial automation scenario; the first signal data stream is a signal data stream formed by signal data from multiple sensors. Based on the first signal data stream, the working condition is determined by combining the context awareness method, and the working mode and sampling frequency of each sensor node are adjusted according to the working condition to obtain the adjusted operation instruction set. Based on the first signal data stream and the adjusted operation instruction set, a system operation status report is generated. The first signal data stream, the adjusted operation instruction set, and the system operation status report are then summarized to obtain the second signal data stream. A trust framework for industrial automation scenarios is constructed. Based on the trust framework, a standardized communication protocol is used to transmit the second signal data stream to the central control system. The standardized communication protocol is a communication protocol determined based on an adaptive protocol conversion gateway method. The aforementioned trust framework for constructing an industrial automation scenario, based on which a standardized communication protocol is used to transmit the second signal data stream to the central control system, includes: A graph model is constructed using a graph database, with sensor nodes as vertices and the relationships between sensor nodes as edges. The vertices contain the following attributes: identifier, location information, and type identifier. The weights of the edges represent the association strength or communication quality between sensor nodes. Extract the index features of the graph model; the index features include node degree distribution, average path length, and clustering coefficient; Based on the graph model and the indicator features, a trust framework is designed and deployed. Calculate the target trust score of each sensor node under the trust framework, and establish a dynamic encrypted tunnel for transmitting the second signal data stream based on the target trust score of each sensor node; the dynamic encrypted tunnel adopts different target level encryption methods for different data segments in the second signal data stream; The second signal data stream is transmitted from the edge server to the central control system via the dynamic encrypted tunnel using a standardized communication protocol.

2. The method according to claim 1, characterized in that, The design and deployment of the trust framework based on the graph model and the indicator features includes: The system acquires demand information for industrial automation scenarios, selects a blockchain platform that meets the demand information from multiple blockchain platforms, and selects a consensus algorithm that corresponds to the demand information from multiple consensus algorithms; the demand information includes real-time information, security information, and scalability information. After selecting a blockchain platform and consensus algorithm, a smart contract is written based on the graph model and preset writing rules; the smart contract is used to manage the authentication and authorization methods of all sensor nodes. Design a trust scoring mechanism based on the aforementioned indicator characteristics; A trust framework is designed and deployed by comprehensively utilizing the aforementioned blockchain platform, consensus algorithm, smart contract, and trust scoring mechanism.

3. The method according to claim 1, characterized in that, The target trust score of each sensor node under the trust framework is calculated, and a dynamic encrypted tunnel for transmitting the second signal data stream is established based on the target trust score of each sensor node. The dynamic encryption tunnel employs different target-level encryption methods for different data segments in the second signal data stream, including: Based on the historical behavior, location information, and type identifier of the sensor nodes, the initial trust score of each sensor node is calculated using the target trust scoring mechanism in the trust framework. According to the dynamic adjustment mechanism, the initial trust score of each sensor node is adjusted through the smart contract in the trust framework to obtain the target trust score of each sensor node under the trust framework. The second signal data stream is divided into multiple data segments; For each data segment, the following process is performed: determine the sensor nodes associated with the data segment; if there is only one associated sensor node, determine the target trust score of the associated sensor node as the final value; or, if there are multiple associated sensor nodes, determine the final value by the weighted sum of the target trust scores of all associated sensor nodes. Determine the target range in which the final value is located, and determine the encryption method of the target level corresponding to the target range as the encryption method used by the dynamic encryption tunnel when transmitting the data segment.

4. The method according to claim 3, characterized in that, The step of determining the encryption method at the target level corresponding to the target interval as the encryption method used by the dynamic encryption tunnel when transmitting the data segment includes: Obtain an encryption level mapping table, and determine the initial level corresponding to the target interval based on the encryption level mapping table; wherein, each interval corresponds to one initial level; The encryption strength adjustment factor is dynamically calculated based on the real-time network conditions and system load of the edge server, and the initial level corresponding to the target range is adjusted using the encryption strength adjustment factor to obtain the target level; The target-level encryption method is determined as the encryption method used by the dynamic encryption tunnel when transmitting the data segment; the target level includes high priority, medium priority and low priority; different target levels correspond to different encryption methods.

5. The method according to claim 1, characterized in that, The step of determining the operating condition based on the first signal data stream and using a context-aware method includes: The first signal data stream is cleaned. During the cleaning process, the Z-score method combined with the local outlier factor is used to remove outliers, and wavelet transform combined with Kalman filter is used to remove noise to obtain the third signal data stream. Multi-scale wavelet transform is used to extract key features at different scales of the third signal data stream to reduce data dimensionality and obtain a feature set; the key features include mean, variance, and trend change. By combining information gain and context factors, a context-aware method is used to evaluate the importance of key features, and the feature importance evaluation results are obtained. Based on the feature set and the feature importance evaluation results, a trained random forest is used to identify the operating status of the machine equipment.

6. The method according to claim 5, characterized in that, The method combines information gain and context factors to evaluate the importance of key features using a context-aware approach, yielding feature importance evaluation results, including: For each key feature in the feature set, calculate the information gain of the key feature for classifying the operating condition, and generate a context factor for the key feature; the context factor is at least one of timestamp, operating mode, and external environment parameters. The context factor is quantized to obtain the quantized value of the context factor; A context-aware method is used to perform a nonlinear transformation on the information gain and the quantized value of the context factor to evaluate the importance of key features and obtain the feature importance evaluation results.

7. A signal edge acquisition system based on APL, characterized in that, Applied to edge servers, which are devices located on the machine side and connected to sensor nodes via Advanced Physical Layer (APL) technology, including: The acquisition module is used to acquire the first signal data stream of machines and equipment in an industrial automation scenario; the first signal data stream is a signal data stream formed by signal data from multiple sensors; The adjustment module is used to determine the operating status based on the first signal data stream and in combination with the context awareness method, and adjust the working mode and sampling frequency of each sensor node according to the operating status to obtain the adjusted operation instruction set. The generation and summarization module is used to generate a system operation status report based on the first signal data stream and the adjusted operation instruction set, and to summarize the first signal data stream, the adjusted operation instruction set and the system operation status report to obtain a second signal data stream; A transmission module is constructed to build a trust framework for industrial automation scenarios. Based on the trust framework, the second signal data stream is transmitted to the central control system using a standardized communication protocol. The standardized communication protocol is a communication protocol determined based on an adaptive protocol conversion gateway method. The aforementioned trust framework for constructing an industrial automation scenario, based on which a standardized communication protocol is used to transmit the second signal data stream to the central control system, includes: A graph model is constructed using a graph database, with sensor nodes as vertices and the relationships between sensor nodes as edges. The vertices contain the following attributes: identifier, location information, and type identifier. The weights of the edges represent the association strength or communication quality between sensor nodes. Extract the index features of the graph model; the index features include node degree distribution, average path length, and clustering coefficient; Based on the graph model and the indicator features, a trust framework is designed and deployed. Calculate the target trust score of each sensor node under the trust framework, and establish a dynamic encrypted tunnel for transmitting the second signal data stream based on the target trust score of each sensor node; the dynamic encrypted tunnel adopts different target level encryption methods for different data segments in the second signal data stream; The second signal data stream is transmitted from the edge server to the central control system via the dynamic encrypted tunnel using a standardized communication protocol.

8. A computing device, characterized in that, It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement the signal edge acquisition method based on APL as described in any one of claims 1 to 6.

9. A computer storage medium, characterized in that, The device contains a computer program that, when executed by a computer, implements an APL-based signal edge acquisition method as described in any one of claims 1 to 6.

Images