Industrial internet of things data access and processing method, system, device and storage medium

Abstract

The present disclosure relates to the technical field of computers, and provides an industrial Internet of Things data access and processing method, system, device and storage medium. The industrial Internet of Things data access and processing method comprises: receiving heterogeneous raw data from different industrial Internet of Things protocols in parallel through a plurality of protocol adapter microservices; performing batch data verification, preprocessing and storage on the received heterogeneous raw data, and sending data information to a device state prediction message queue; obtaining tasks from the device state prediction message queue, creating algorithm execution tasks according to the task type and data validity conditions, and pushing the algorithm execution tasks to an algorithm execution message queue; obtaining tasks from the algorithm execution message queue, dynamically loading and analyzing corresponding algorithm files and configuration parameters, and performing algorithm task processing. The industrial Internet of Things data access and processing scheme of the present disclosure can improve the access and processing efficiency of industrial Internet data.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of computer, and particularly relates to an industrial Internet of Things data access and processing method and system, an electronic device and a computer readable storage medium. BACKGROUND

[0002] The data access framework based on multiple industrial Internet of Things protocols needs to access multiple industrial Internet of Things protocol data. These industrial Internet of Things data come from devices of different years and different manufacturers, and the protocols used by the devices are different. Traditional solutions need to develop an independent collection program for each protocol, resulting in a large, complex, difficult-to-manage and maintain system.

[0003] Industrial Internet of Things data is continuously generated, and the scale of data points can be tens of thousands or even hundreds of thousands per second. Traditional software architecture and databases cannot handle such a large number of connections and data write requests at the same time, resulting in data congestion, loss, high delay, and system crashes.

[0004] In addition, industrial Internet of Things data, such as process data, vibration waveform data, and vibration feature data, has a large volume and a complex format. Different data types require different processing methods and storage media. This will result in low efficiency of data processing during industrial Internet of Things data access, and even congestion. SUMMARY

[0005] Therefore, the embodiments of the present disclosure provide an industrial Internet of Things data access and processing method, system, electronic device and computer readable storage medium to solve the problem of low efficiency of industrial Internet of Things data access and processing in the prior art.

[0006] In a first aspect, the embodiments of the present disclosure provide an industrial Internet of Things data access and processing method, which comprises: receiving heterogeneous raw data from different industrial Internet of Things protocols in parallel through multiple protocol adapter microservices; performing batch data verification, preprocessing and storage on the received heterogeneous raw data, and sending data information to a device state prediction message queue, the data verification including data existence verification, data compliance verification and data correctness verification, and the data information including the heterogeneous raw data after data verification and preprocessing; obtaining a task from the device state prediction message queue, creating an algorithm execution task according to the task type and data validity condition, and pushing the algorithm execution task to an algorithm execution message queue; obtaining a task from the algorithm execution message queue, dynamically loading and parsing the corresponding algorithm file and configuration parameters, and performing algorithm task processing.

[0007] In a second aspect, the embodiment of the present disclosure provides an industrial Internet of Things data access and processing system, comprising: a data receiving module configured to receive heterogeneous raw data from different industrial Internet of Things protocols in parallel through a plurality of protocol adapter microservices; a data processing module configured to perform batch data verification, preprocessing and storage on the received heterogeneous raw data, and send data information to a device state prediction message queue, wherein the data verification comprises data existence verification, data compliance verification and data correctness verification, and the data information comprises the heterogeneous raw data after data verification and preprocessing; a state prediction module configured to obtain a task from the device state prediction message queue, create an algorithm execution task according to the task type and data validity condition, and push the algorithm execution task to an algorithm execution message queue; and a task processing module configured to obtain a task from the algorithm execution message queue, dynamically load and parse corresponding algorithm files and configuration parameters, and perform algorithm task processing.

[0008] In a third aspect, the embodiment of the present disclosure provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0009] In a fourth aspect, the embodiment of the present disclosure provides a readable storage medium, which stores a computer program, and the computer program implements the steps of the above method when executed by a processor.

[0010] Compared with the prior art, the embodiment of the present disclosure has the beneficial effects that through the cross-field and deep-level innovative fusion of batch processing technology, microservice architecture and industrial Internet of Things data processing requirements, a new, efficient and flexible solution is formed, and a series of significant technical effects such as improving throughput, reducing delay and enhancing flexibility are produced. BRIEF DESCRIPTION OF DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings needed in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without creative labor.

[0012] Figure 1 is a scene schematic diagram of an application scenario of the embodiment of the present disclosure;

[0013] Figure 2 is a flow schematic diagram of an industrial Internet of Things data access and processing method provided by the embodiment of the present disclosure;

[0014] Figure 3is a structural schematic diagram of an industrial Internet of Things data access and processing system provided by an embodiment of the present disclosure.

[0015] Figure 4 is a structural schematic diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0016] In the following description, specific details such as specific system structures, techniques, etc. are presented in order to provide a thorough understanding of the embodiments of the present disclosure. However, it should be apparent to those skilled in the art that the present disclosure can be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present disclosure with unnecessary details.

[0017] The industrial Internet of Things data access and processing method and system according to the embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0018] Figure 1 is a scenario schematic diagram of an application scenario of the embodiments of the present disclosure. The application scenario can include terminal devices 101, 102 and 103, a server 104 and a network 105.

[0019] The terminal devices 101, 102 and 103 can be hardware or software. When the terminal devices 101, 102 and 103 are hardware, they can be various electronic devices with a display screen and supporting communication with the server 104, including but not limited to smart phones, tablet computers, laptop computers and desktop computers, etc.; when the terminal devices 101, 102 and 103 are software, they can be installed in the above electronic devices. The terminal devices 101, 102 and 103 can be implemented as multiple software or software modules, or as a single software or software module, and the embodiments of the present disclosure do not limit this. Further, various applications can be installed on the terminal devices 101, 102 and 103, such as data processing applications, instant messaging tools, social platform software, search applications, shopping applications, etc.

[0020] The server 104 can be a server providing various services, for example, a background server receiving a request sent by a terminal device establishing a communication connection therewith. The background server can receive and analyze the request sent by the terminal device, etc., and generate a processing result. The server 104 can be a server, a server cluster composed of several servers, or a cloud computing service center, and the embodiments of the present disclosure do not limit this.

[0021] It should be noted that the server 104 can be hardware or software. When the server 104 is hardware, it can be various electronic devices that provide various services for the terminal devices 101, 102 and 103. When the server 104 is software, it can be multiple software or software modules that provide various services for the terminal devices 101, 102 and 103, or can be a single software or software module that provides various services for the terminal devices 101, 102 and 103, and the embodiments of the present disclosure do not limit this.

[0022] The network 105 can be a wired network that adopts coaxial cables, twisted pairs and optical fibers, or can be a wireless network that realizes interconnection of various communication devices without wiring, for example, Bluetooth, Near Field Communication (NFC), Infrared, etc., and the embodiments of the present disclosure do not limit this.

[0023] The user can establish a communication connection with the server 104 via the network 105 through the terminal devices 101, 102 and 103, to receive or send information, etc.

[0024] It should be noted that the specific types, quantities and combinations of the terminal devices 101, 102 and 103, the server 104 and the network 105 can be adjusted according to the actual needs of the application scenario, and the embodiments of the present disclosure do not limit this.

[0025] Figure 2 FIG. 1 is a flow diagram of an industrial Internet of Things data access and processing method provided by an embodiment of the present disclosure. The method provided by the embodiment of the present disclosure can be executed by any electronic device with computer processing capability, for example, a terminal or a server.

[0026] As shown in FIG. 2, the industrial Internet of Things data access and processing method provided by the embodiment of the present disclosure includes the following steps. Figure 2

[0027] In step S201, parallel receive heterogeneous raw data from different industrial Internet of Things protocols through multiple protocol adapter microservices. The heterogeneous raw data can be structured process data, feature data and unstructured vibration waveform data, and is not limited to this. The protocol adapter microservice supports dynamic loading and can increase support for new industrial Internet of Things protocols without restarting the system.

[0028] ​Step S202, batch data verification, preprocessing and storage are performed on the received heterogeneous raw data, and data information is sent to the device state prediction message queue, the data verification includes data existence verification, data compliance verification and data correctness verification, and the data information includes the heterogeneous raw data after data verification and preprocessing. Among them, the data correctness verification is used to investigate the abnormal values or data jump that does not conform to the physical logic in the data.

[0029] Step S203, get the task from the device state prediction message queue, create an algorithm execution task according to the task type and data validity condition, and push the algorithm execution task to the algorithm execution message queue.

[0030] Step S204, get the task from the algorithm execution message queue, dynamically load and parse the corresponding algorithm file and configuration parameters, and perform algorithm task processing.

[0031] Specifically, when dynamically loading and parsing the corresponding algorithm file and configuration parameters, according to the data source protocol or the device identifier contained in the data, the data parsing template and data processing process rules matched therewith are dynamically loaded from the configuration center. Specifically, the data parsing template can include data format parsing rules, processing parameters and business algorithm configuration.

[0032] In step S204, if the task in the algorithm execution message queue contains feature extraction instructions, the data set to be feature extracted is obtained; the algorithm service is called to perform feature extraction on the data set.

[0033] In some embodiments, after calling the algorithm service to perform feature extraction on the data set, if inference needs to be performed, after all online measurement point data at the same collection time point of the same unit are arrived, the inference task is written into the inference waiting queue; the task is taken out from the inference waiting queue, the AI algorithm model file bound to the unit is found and batch inference is performed, wherein the AI algorithm model file is a pre-trained and stored model.

[0034] In some embodiments, after performing algorithm task processing, the algorithm execution result and log also need to be stored, and a diagnostic report is automatically generated, and the device state update information is sent to the state update service, so that the state update service updates the running state and historical trend of the device according to the received information.

[0035] The technical scheme of the embodiment of the present disclosure can be cooperatively executed by a plurality of loosely coupled microservices, including: a data receiving and storing microservice, configured to batch receive, verify, preprocess, and store data; a device state prediction microservice, configured to create an algorithm execution task according to a task type and a data validity condition; an algorithm task execution microservice, configured to dynamically load and parse a corresponding algorithm file and configuration parameters, and perform algorithm task processing; and a device state updating microservice, configured to update a running state and a historical trend of a device according to received information.

[0036] The technical scheme of the embodiment of the present disclosure can efficiently batch receive various Internet of Things data, including but not limited to process data, vibration waveform data, vibration feature data, and other common industrial Internet of Things data, can reduce the delay of Internet of Things data, process industrial data in real time, and facilitate cleaning and processing between services.

[0037] The embodiment of the present disclosure provides an open platform architecture based on data, which performs multi-protocol data receiving, data format self-defined matching, data self-defined cleaning and screening, and dynamic loading, and can be quickly deployed by using a microservice architecture to complete efficient processing and concurrent rapid storage of structured and unstructured sensor data.

[0038] The program function batch classifies and receives original data provided by a third party and a hardware sensor, performs batch feature extraction, batch reasoning, batch storage, and business batch processing after receiving the data, and finally efficiently provides AI automated diagnosis suggestions. Specifically, the AI model reasoning result can be used to generate automated diagnosis suggestions and provide them to upper-layer business applications.

[0039] In the data access analysis process, data existence verification, data compliance verification, and data correctness verification are performed. Data that passes the verification is subjected to data dynamic type matching and parameter dynamic loading, and then algorithm usage selection is completed through business configuration.

[0040] The technical scheme of the embodiment of the present disclosure can provide a batch processing framework based on a Spring framework to process various types of batch processing tasks, such as process data, Internet of Things vibration data import / export, report generation, etc. By defining components such as Job, Step, ItemReader, ItemProcessor, and ItemWriter of the Spring framework, a reusable batch processing application program can be constructed, so that concurrent processing, fault tolerance, retry, and other functions of batch processing can be easily realized, and the batch processing framework can be easily integrated with other Spring components such as Spring Boot and Spring Data, to form a flexible and easy-to-use batch processing framework for quickly, efficiently, and reliably processing industrial Internet of Things data.

[0041] The AI model inference processing performed by the ItemProcessor component is completed in batches, that is, model inference is performed on multiple pieces of data in a batch at the same time to improve processing efficiency. The ItemWriter component supports concurrent writing to heterogeneous data sources, including time series databases and relational databases, to achieve fast persistence of processing results.

[0042] Based on the batch processing framework, the dynamically configured data can be organized into a batch processing task, for example, batch reading data through a defined ItemReader component, feature extraction and AI model inference processing on batch data through a defined ItemProcessor component, and batch concurrent storage of processing results to a target database through a defined ItemWriter component.

[0043] The technical solution of the embodiment of the present disclosure constructs a unified and open data entry, which can solve the access problem of multi-protocol, high concurrency and heterogeneous data in an industrial scene. By integrating batch processing and real-time processing capabilities, the full-process automation from raw data access to AI intelligent diagnosis can be realized, aiming to reduce data delay, improve data processing efficiency, and provide clean, compliant and instant data services for upper-layer applications.

[0044] The technical solution of the embodiment of the present disclosure provides an open architecture for data, which is designed based on data flow, provides standardized access and processing interfaces, allows flexible access to third-party systems and algorithms, and avoids vendor lock-in. The open architecture decouples the system into a series of services with single responsibility and loose coupling, which can realize rapid deployment, independent scaling and high availability. The technical solution of the embodiment of the present disclosure adopts batch processing optimization, deeply integrates and extends the Spring Batch batch processing framework, to cope with the demand for efficient batch processing of massive data in an industrial scene, and supports concurrency, fault tolerance and retry mechanisms natively.

[0045] The open architecture in the embodiment of the present disclosure can seamlessly integrate AI models such as machine learning and deep learning models, perform batch inference on processed data, and finally automatically generate diagnostic recommendations or analysis reports, complete the closed loop from “data” to “insight”, and realize AI automated diagnostic recommendation.

[0046] In one embodiment, sensor data is accessed through the framework via protocols such as MQTT, and existence, compliance and correctness verification is performed. Failed data enters the dead letter queue. The verified data is dynamically loaded with corresponding processing parameters and algorithm configurations according to its type.

[0047] In the AI data batch processing process, the data sender can be a third-party data sender and various platforms. In the modules involved in the AI data batch processing process, the data receiving and storage module includes vibration waveform receiving, vibration data filtering, vibration waveform feature extraction, vibration waveform atlas drawing, vibration feature receiving, vibration feature data storage, process data receiving, and process data storage. In the device state prediction module, it includes start-stop state prediction, working condition state prediction, and diagnosis report drawing. In the device state update module, it includes running state update and historical trend update. The device model learning module includes device model learning update. In the unit management module, it includes unit management, device management, configuration management, and unit algorithm configuration. In the algorithm management module, it includes version management, call verification configuration, and call parameter configuration. In the IOT hardware management module, it includes sensor management, data acquisition gateway management, IOT gateway management, and industrial intelligence machine management. In the model management module, it includes device model management and unit model management. In the product management module, it includes configuration management, model management, and dictionary management. In the timing task module, it includes offline monitoring, automatic learning detection, offline monitoring, and email notification.

[0048] In the data receiving batch processing process, after obtaining the waveform data, it can be judged whether the current point exists and whether the timestamp of the data type corresponding to the current measuring point has existed in the library. When the algorithm is used for data filtering, algorithm feature extraction and algorithm atlas drawing can be performed. Then, it is judged whether the current value exceeds the customer set threshold value, and if not, the filtered atlas and original data are compressed and stored. Then, data information is sent to the device state prediction queue. When receiving edge feature data and hardware state information, the above process is also referred to.

[0049] In the state prediction batch execution process, the to-be-executed task is obtained from the device state prediction queue, the to-be-executed task type is judged, and the vibration type point information, unit device information, and algorithm information bound by the data ID are obtained. Then, it is judged whether the current task is manually re-executed, and if not, it is judged whether the current data corresponding to the measuring point sensor axial direction is the z-axis high-frequency acceleration waveform. If yes, all main shaft high-frequency acceleration data IDs in the offset time point range corresponding to the current axial direction acquisition time are obtained, and it is judged whether the number of obtained data IDs accounts for more than a specified number of main shafts. If yes, an algorithm execution task is created, the algorithm call precondition is obtained through the configuration file provided by the algorithm, and the data is pushed to the algorithm execution service queue.

[0050] In the algorithm task batch execution process, an execution task is obtained from an algorithm task queue, algorithm information and unit equipment information are obtained through a task ID, and it is judged whether the equipment and the algorithm exist. If they exist, an algorithm compression file is obtained and parsed, parameters required for calling the algorithm are obtained. Then, it is judged whether all necessary parameters for algorithm execution are available. If yes, the algorithm performs algorithm task processing and records execution calling to a log. Then, algorithm result storage, algorithm log storage and algorithm task state updating are performed, and data is pushed to a state updating service. An algorithm is generated, a file is saved, and is stored to a set path.

[0051] In the feature extraction batch execution process, it is judged whether the current task is deleted. If not, a feature extraction instruction is received from the queue, a data set to be feature extracted is obtained, an algorithm service is called to perform feature extraction, feature extraction results are recorded, and feature extraction task state is updated. Then, it is judged whether reasoning is needed for this type, and all online measurement point information of the unit is obtained. Then, it is judged whether there is data of the unit at this collection time point in the waiting queue. If there is, it is judged whether the data of the unit at this collection time point in the waiting queue already contains all online measurement points. If yes, the data is written into a start-stop reasoning waiting queue, and then the data is written into a working condition reasoning waiting queue.

[0052] In the reasoning execution batch process, a reasoning task instruction is received from the queue task, it is judged whether the current task is canceled. If not, it is judged whether the current unit is bound to a specific algorithm. If yes, the file corresponding to the bound algorithm is found and called. Then, it is judged whether the training state of the current unit is successful, and the model file is found according to the unit ID and the trained model ID of the unit. Then, the algorithm model file is decompressed and reasoning is performed. If the reasoning is successful, the reasoning result is saved.

[0053] According to the industrial Internet of Things data access and processing method provided in the embodiments of the present disclosure, through cross-field and deep-level innovative fusion of batch processing technology, micro-service architecture and industrial Internet of Things data processing requirements, a new, efficient and flexible solution is formed, and a series of significant technical effects such as improving throughput, reducing delay and enhancing flexibility are produced.

[0054] As shown in Figure 3 The industrial Internet of Things data access and processing system provided by the present disclosure includes:

[0055] The data receiving module 301 is configured to receive heterogeneous raw data from different industrial Internet of Things protocols in parallel through a plurality of protocol adapter microservices.

[0056] The data processing module 302 is configured to perform batch data verification, preprocessing and storage on the received heterogeneous raw data, and send data information to the equipment state prediction message queue. The data verification includes data existence verification, data compliance verification and data correctness verification. The data information includes the heterogeneous raw data after data verification and preprocessing.

[0057] The state prediction module 303 is configured to obtain a task from the equipment state prediction message queue, create an algorithm execution task according to the task type and data validity condition, and push the algorithm execution task to the algorithm execution message queue.

[0058] The task processing module 304 is configured to obtain a task from the algorithm execution message queue, dynamically load and parse the corresponding algorithm file and configuration parameters, and perform algorithm task processing.

[0059] Since the various functional modules of the industrial Internet of Things data access and processing system of the example embodiments of the present disclosure correspond to the steps of the example embodiments of the industrial Internet of Things data access and processing method described above, for details not disclosed in the device embodiments of the present disclosure, please refer to the above-mentioned embodiments of the industrial Internet of Things data access and processing method of the present disclosure.

[0060] The industrial Internet of Things data access and processing system according to the embodiments of the present disclosure, through the cross-field and deep-level innovative fusion of batch processing technology, micro-service architecture and industrial Internet of Things data processing requirements, forms a new, efficient and flexible solution, and produces a series of significant technical effects such as improving throughput, reducing delay and enhancing flexibility.

[0061] Figure 4 is a schematic diagram of an electronic device 4 provided by an embodiment of the present disclosure. As shown in Figure 4 The electronic device 4 of this embodiment includes a processor 401, a memory 402, and a computer program 403 stored in the memory 402 and executable on the processor 401. The processor 401 implements the steps in the above-mentioned various method embodiments when executing the computer program 403. Alternatively, the processor 401 implements the functions of each module in the above-mentioned various device embodiments when executing the computer program 403.

[0062] The electronic device 4 can be a desktop computer, a notebook computer, a palm computer, a cloud server and the like. The electronic device 4 can include but is not limited to the processor 401 and the memory 402. Those skilled in the art can understand that Figure 4 The electronic device 4 is only an example and does not constitute a limitation on the electronic device 4, and can include more or fewer components or different components than those shown.

[0063] The processor 401 can be a central processing unit (CPU), or other general purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, etc.

[0064] The memory 402 can be an internal storage unit of the electronic device 4, for example, a hard disk or a memory of the electronic device 4. The memory 402 can also be an external storage device of the electronic device 4, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 4. The memory 402 can also include both the internal storage unit and the external storage device of the electronic device 4. The memory 402 is used to store computer programs and other programs and data required by the electronic device.

[0065] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above division of functional units and modules is taken as an example, and in actual application, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the above described functions. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The above integrated unit can be realized in the form of hardware or in the form of software functional unit.

[0066] If the integrated module is implemented in the form of a software function unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by instructing related hardware through a computer program, and the computer program can be stored in a computer readable storage medium. When the processor executes the computer program, the steps of the above-mentioned various method embodiments can be implemented. The computer program can include computer program code, which can be in the form of source code, object code, executable file or some intermediate form, etc. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), electric carrier wave signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer readable medium does not include electric carrier wave signal and telecommunication signal.

[0067] The above embodiments are only used to illustrate the technical solutions of the present disclosure, rather than limit them; although the present disclosure has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for part of the 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 present disclosure, and should be included in the protection scope of the present disclosure.

Claims

1. An industrial Internet of Things data access and processing method, characterized in that, The method comprises the following steps: parallel receiving of heterogeneous raw data from different industrial internet of things protocols through a plurality of protocol adapter microservices; batch data verification, preprocessing and storage of the received heterogeneous raw data, and sending of data information to a device state prediction message queue, the data verification including data existence verification, data compliance verification and data correctness verification, the data information including the heterogeneous raw data after data verification and preprocessing; obtaining a task from the device state prediction message queue, creating an algorithm execution task according to the task type and data validity condition, and pushing the algorithm execution task to an algorithm execution message queue, the creating of the algorithm execution task according to the task type and data validity condition including: judging the type of the to-be-executed task obtained from the device state prediction queue, and obtaining the vibration type point information, unit equipment information and algorithm information bound by the data ID; then, judging whether the current task is a manually re-executed task, if not, judging whether the current data corresponds to the z-axis high-frequency acceleration waveform of the measuring point sensor axis; if yes, obtaining all main shaft high-frequency acceleration data IDs within the offset time point range corresponding to the current axis direction collection time, and judging whether the proportion of the number of obtained data IDs to the number of all main shafts exceeds a specified number ratio; if yes, creating an algorithm execution task, obtaining algorithm calling prerequisites through a configuration file provided by the algorithm, and pushing data to an algorithm execution service queue; obtaining a task from the algorithm execution message queue, dynamically loading and analyzing the corresponding algorithm file and configuration parameter, and performing algorithm task processing.

2. The method of claim 1, wherein, The algorithm task processing includes: if the task in the algorithm execution message queue contains a feature extraction instruction, obtaining a data set to be feature extracted; calling an algorithm service to perform feature extraction on the data set.

3. The method of claim 2, wherein, After the algorithm service performs feature extraction on the data set, the method further comprises: if inference needs to be performed, waiting for all online measuring point data of the same unit at the same collection time point to arrive, and then writing an inference task into an inference waiting queue; obtaining a task from the inference waiting queue, finding an AI algorithm model file bound to the unit and performing batch inference, wherein the AI algorithm model file is a pre-trained and stored model.

4. The method of claim 1, wherein, After the algorithm task processing, the method further comprises: storing algorithm execution results and logs, and automatically generating a diagnosis report, and sending device state update information to a state update service, so that the state update service updates the running state and historical trend of the device according to the received information.

5. The method of claim 1, wherein, The heterogeneous raw data at least includes one of the following data: structured process data, feature data and unstructured vibration waveform data.

6. The method of claim 1, wherein, The method is cooperatively executed by a plurality of loosely coupled microservices, and the microservices include: a data receiving and storing microservice for batch receiving, verifying, preprocessing and storing data; a device state prediction microservice for creating an algorithm execution task according to the task type and data validity condition; An algorithm task execution microservice is configured to dynamically load and parse corresponding algorithm files and configuration parameters for algorithm task processing. A device state update microservice is configured to update the running state and historical trends of a device based on received information.

7. The method of claim 1, wherein, The dynamic loading and parsing of corresponding algorithm files and configuration parameters includes dynamically loading and parsing data processing flow rules and data parsing templates from a configuration center based on the source protocol of the data or a device identifier included in the data.

8. An industrial Internet of Things data access and processing system, characterized in that, The method comprises: A data receiving module is configured to receive heterogeneous raw data from different industrial Internet of Things protocols in parallel through multiple protocol adapter microservices; A data processing module is configured to perform batch data verification, preprocessing, and storage on the received heterogeneous raw data, and send data information to a device state prediction message queue, wherein the data verification includes data existence verification, data compliance verification, and data correctness verification, and the data information includes the heterogeneous raw data after data verification and preprocessing; A state prediction module is configured to obtain tasks from the device state prediction message queue, create algorithm execution tasks based on task types and data validity conditions, and push the algorithm execution tasks to an algorithm execution message queue, wherein the creation of algorithm execution tasks based on task types and data validity conditions includes determining the type of a task to be executed obtained from the device state prediction queue, and obtaining binding vibration type point information, unit device information, and algorithm information through a data ID; then, determining whether the current task is a manually re-executed task, and if not, determining whether the current data corresponds to a z-axis high-frequency acceleration waveform of a sensor axial direction; if so, obtaining all main shaft high-frequency acceleration data IDs within a range of offset time points corresponding to the current axial direction collection time, and determining whether the number of obtained data IDs exceeds a specified number ratio with respect to the number of all main shafts; if so, creating an algorithm execution task, obtaining algorithm call prerequisites through a configuration file provided by the algorithm, and pushing data to an algorithm execution service queue; A task processing module is configured to obtain tasks from the algorithm execution message queue, dynamically load and parse corresponding algorithm files and configuration parameters, and perform algorithm task processing.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the steps of the method of any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 9. The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 7.

Images