Process industry real-time monitoring and early warning system and method and storage medium

Abstract

The embodiment of the invention provides a process industry real-time monitoring and early warning system and method and a storage medium, and the system comprises a data collection module which is used for receiving the safety instrument data of each device and the sensing data of each sensor in the process industry in real time; the verification module is used for calling an SIL level verification model to perform online verification on the data according to the safety instrument data, and determining risk information of each piece of equipment; the anomaly detection module is used for determining anomaly data based on an anomaly detection model according to the sensing type data and the risk information; and the early warning module is used for generating early warning information according to the abnormal data and the risk information. Through cooperative work of all the modules, safety and reliability in the industrial production process can be remarkably improved, potential problems can be warned in advance, non-planned downtime and maintenance cost are reduced, meanwhile, the service life of equipment is prolonged, and therefore production efficiency is improved.

Description

Technical Field

[0001] This document relates to the field of process industry technology, and in particular to a real-time monitoring and early warning system, method and storage medium for the process industry. Background Art

[0002] The process industry mainly includes chemical engineering, petroleum engineering, metallurgical engineering, etc. The production process is generally characterized by large scale, long process, and multiple steps. There are many safety hazards in the raw material production and technology involved in the production operation.

[0003] In the existing technology, process industries all use manual routine inspections as a monitoring method to analyze and warn of risks.

[0004] However, existing technologies use routine manual inspections as a monitoring method, but lack scientific and effective monitoring and early warning of major safety hazards, resulting in low efficiency in hazard perception, difficulty in quickly identifying risks and issuing early warnings, possible misjudgments or missed judgments, and inability to achieve real-time monitoring and early warning of equipment and processes. Summary of the invention

[0005] In view of the above solutions, the present application aims to propose a real-time monitoring and early warning system, method and storage medium for the process industry to solve at least one of the above technical problems.

[0006] In a first aspect, one or more embodiments of this specification provide a real-time monitoring and early warning system for a process industry, including:

[0007] Data acquisition module, used to receive safety instrument data of various equipment in the process industry and sensor data of various sensors in real time;

[0008] A verification module, used to call a SIL level verification model to perform online verification on the data according to the safety instrument data, and determine the risk information of each of the devices;

[0009] An anomaly detection module, used to determine abnormal data based on the sensor data and the risk information based on an anomaly detection model;

[0010] The early warning module is used to generate early warning information according to the abnormal data and the risk information.

[0011] Furthermore, it also includes: a collaboration module, which is used to adjust the operating parameters of the verification module, the abnormality detection module and the early warning module according to the risk information, the abnormal data and the early warning information.

[0012] Furthermore, it also includes: a performance evaluation module, which is used to automatically update the threshold alarm mechanism according to the preset performance indicators of each module.

[0013] Furthermore, the safety instrument data includes real-time equipment operation data, historical fault data and equipment configuration data, and the verification module is configured to:

[0014] Based on the SIL level verification model, determining a target SIL level according to the historical fault data and the device configuration data;

[0015] Determine the failure probability level of each device according to the real-time operation data of the device and the target SIL level;

[0016] According to the failure probability level, the risk information of each device is determined, and the risk information includes the failure level, the failure location, and the failure cause.

[0017] Furthermore, the anomaly detection module is configured to:

[0018] Based on the anomaly detection model, determining anomaly detection feature data according to the sensor data and the risk information;

[0019] The abnormal data is determined according to the abnormal detection feature data and a preset abnormal threshold.

[0020] Furthermore, the anomaly detection module is further configured to:

[0021] Determine variable data based on the sensor data and the risk information based on a Bayesian network inference algorithm;

[0022] Determine the change probability and change condition of each variable data according to the variable data;

[0023] A fault diagnosis result is obtained according to the change probability and the change condition.

[0024] Furthermore, the early warning module is configured to:

[0025] Obtaining a risk score according to the abnormal data and the risk information;

[0026] The warning information is generated according to the risk score and a preset warning threshold.

[0027] Furthermore, it also includes: an updating module, which is used to update the preset thresholds in the abnormality detection module and the early warning module based on the incremental learning technology according to the sensor data received in real time, the preset abnormality thresholds and the preset early warning thresholds.

[0028] In a second aspect, the embodiment of the present application provides a real-time monitoring and early warning method for a process industry, including:

[0029] Receive safety instrument data from each device in the process industry and sensor data from each sensor in real time;

[0030] Based on the safety instrument data, calling the SIL level verification model to perform online verification on the data, and determining the risk information of each of the devices;

[0031] Based on the anomaly detection model, determining abnormal data according to the sensor data and the risk information;

[0032] Generate warning information based on the abnormal data and the risk information.

[0033] In a third aspect, an embodiment of the present application provides a computer-readable storage medium storing computer instructions, which, when executed by a processor, implement the process industry real-time monitoring and early warning system instructions described in any one of the first aspects.

[0034] Compared with the prior art, this application can at least achieve the following technical effects:

[0035] This application can receive and process data from each device in real time, and promptly discover potential safety hazards through the anomaly detection module and early warning module, effectively reducing the false alarm rate and missed alarm rate, improving the accuracy of the early warning, and enhancing the safety and reliability of the process industry when facing a complex and changing working environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate one or more embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0037] Figure 1 A schematic diagram of the device structure of a process industry real-time monitoring and early warning system provided by one or more embodiments of this specification;

[0038] Figure 2 A flow chart of a real-time monitoring and early warning method for a process industry provided in one or more embodiments of this specification. DETAILED DESCRIPTION

[0039] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the following will be combined with the drawings in one or more embodiments of this specification to clearly and completely describe the technical solutions in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this document.

[0040] Process industries often involve high-risk environments such as high temperature, high pressure, flammable and explosive materials. In the production process, there are various instruments, meters, and equipment. Due to their harsh operating conditions, any abnormality may lead to serious safety accidents. It is often difficult to detect and deal with potential safety hazards in a timely manner in existing technologies. Once a failure occurs, it is difficult to take effective measures quickly.

[0041] To solve the above technical problems, this application proposes a real-time monitoring and early warning system for process industries, such as Figure 1 As shown, including:

[0042] In an embodiment of the present application, a data acquisition module 101 is used to receive in real time the safety instrument data of each device in the process industry and the sensor data of each sensor; a verification module 102 is used to call a SIL level verification model to perform online verification on the data based on the safety instrument data, and determine the risk information (failure probability level) of each device; an anomaly detection module 103 is used to determine abnormal data based on the anomaly detection model, the sensor data and the risk information; an early warning module 104 is used to generate early warning information based on the abnormal data and the risk information.

[0043] Preferably, for the data acquisition module: hardware, software, operation and maintenance safety instrument data are collected from the safety-related system (SIS) of each device. The safety instrument data includes real-time operation data of each device, historical fault data and device configuration data, etc., wherein the real-time operation data represents the value measured by the sensor in real time; the historical fault data represents the operation log, fault report and maintenance record, etc., which records all operation behaviors in the past period of time, including the timestamp and specific content of the actions such as start, stop, and adjust settings, the fault information and processing results of the system history, and the detailed records of the previous maintenance activities, including the maintenance time, content and personnel, etc.; the device configuration data represents the hardware components involved in the SIS system, such as model, specification, installation location, etc. The sensor data collected from each sensor includes data such as temperature, pressure, liquid level, flow rate and status information of the device, such as: temperature sensor, pressure sensor, flow meter, liquid level sensor, vibration sensor, etc.

[0044] Preferably, for the verification module: input the real-time operation data, historical fault data and equipment configuration data of each device into the SIL level verification model to determine the key risk factors affecting the safety of the system; calculate the risk score based on the key risk factors and current standards, where the current standards are based on international standards such as IEC 61508 and IEC 61511; then use Markov model prediction, fault tree analysis (FTA), reliability block diagram (RBD) and other tools to quantitatively analyze and qualitatively evaluate the safety instrument data such as hardware, software, operation and maintenance of the equipment, where the Markov model is used to predict the probability of state change of each device; use the number of faults analysis to identify potential fault paths and key points; use the reliability block diagram to determine the connection relationship between each component. Then determine the SIL level of each device based on the results of quantitative and qualitative analysis. Then determine the fault point based on the SIL level of each device. Then analyze the cause of the fault at each fault point and generate a risk information report for each device.

[0045] For example, in a petrochemical plant, first, collect real-time data from the pressure sensor of the reactor, the action log of the control valve, the latest international standard IEC 61508 and the specific specifications of the petrochemical industry, the model and configuration information of all hardware equipment in the system, and other data; then use FTA and RBD to combine historical fault data and equipment configuration data to confirm that the target SIL level that the system should achieve is SIL 2; secondly, calculate the failure probability level of each device, and predict the failure probability level of each key device through the Markov model based on the real-time operation data and the target SIL level, and ensure that these levels meet the requirements of SIL2; finally, generate a diagnostic report and recommended measures, which can provide detailed health status assessment, fault detection and location, recommended measures and other outputs. For example, if a slight deviation is found in the pressure sensor on a production line, it is recommended to calibrate it immediately; and provide early warning of pressure fluctuations that may be caused by seasonal temperature changes in the next few days.

[0046] By automatically verifying the SIL level and generating risk information, the safety and reliability of the production of each equipment can be greatly improved.

[0047] Preferably, for the anomaly detection module: first, the sensor data is standardized to obtain data in a unified format. Then, the anomaly detection feature data is extracted from the sensor data and risk information. Secondly, the feature is input into the deep neural network model, and the output anomaly probability is calculated by forward propagation. Finally, the output result is compared with the preset anomaly threshold. If it exceeds the threshold, it is determined to be abnormal. Among them, the training process of the deep neural network model is: collect a large amount of historical data from sensors, control systems, etc., including data under normal operating conditions and data under known faults or abnormal conditions. Then perform data preprocessing and clean the data to remove noise and missing values. Standardize or normalize the data to ensure that the scales between different features are consistent. Then select key features that are helpful for anomaly detection (such as mean, variance, trend change rate, etc.) based on domain knowledge. Then label these data, and divide the data set into training set, validation set and test set. Then divide the training data into small batches (batches), and input them into the neural network batch by batch for forward propagation (Forward Propagation) and backpropagation (Backpropagation) to minimize the loss function. Adjust hyperparameters such as learning rate, batch size, number of hidden layers, number of neurons in each layer, and use grid search or random search to find the optimal combination. When the parameters in the deep neural network model remain unchanged, a deep neural network model is obtained.

[0048] Furthermore, the anomaly detection module can also determine variable data based on the sensor data and the risk information based on the Bayesian network inference algorithm; determine the change probability and change conditions of each variable data based on the variable data; and obtain a fault diagnosis result based on the change probability and change conditions.

[0049] First, the sensor data and the risk information data determine all the variables that need to be modeled. Among them, the variables are sensor data, operation data, state variables, etc. Based on historical data, the causal relationship between variables is determined and represented by directed edges. For example, if an increase in temperature may lead to an increase in pressure, a directed edge from temperature to pressure is added between the temperature node and the pressure node. Using parameter learning algorithms (such as maximum likelihood estimation, Bayesian estimation, etc.), the probability distribution of each node when its parent node takes a specific value is estimated from historical data. Given a set of observations (such as an abnormal sensor reading), the Bayesian network is used for forward reasoning to calculate the state probability distribution of other related variables and predict possible fault modes. When one or more abnormal results are found, the Bayesian network is used for backward reasoning to track the root cause of the abnormality. Finally, a directed acyclic graph (DAG) is constructed to represent the causal relationship between variables, clarifying how different factors affect each other, find the cause of the fault, and output the final fault diagnosis result. For example, in a petrochemical plant, the Bayesian network inference algorithm is used to build a causal chain, determine the variables as the pressure, temperature, flow rate of the reactor, and the state of the control valve, etc., establish the causal relationship of the variables, and determine the probability of pressure change under different temperature conditions. When the real-time monitoring shows that the pressure sensor reading on a production line suddenly increases, the Bayesian network is used for backward reasoning to find out the pressure increase caused by heater failure or other factors, and provide the specific failure type and probability.

[0050] The anomaly detection module can detect potential risks at an early stage and more accurately identify data points that deviate from normal patterns, effectively reducing the false alarm rate and missed alarm rate and improving the accuracy of early warning.

[0051] Preferably, for the early warning module: use the pre-trained long short-term memory network model (LSTM) to calculate the risk score of each device by combining the abnormal data and the risk information; compare the preset early warning threshold with the risk score, and trigger the alarm mechanism if it exceeds the threshold. Different alarm mechanisms will be triggered according to different threshold ranges, for example: divide the early warning into different levels (such as low, medium, and high), when the level is low, a pop-up notification prompt; when the level is medium, a text message notification; when the level is high, multiple phone notifications.

[0052] The early warning module can not only detect potential risks at an early stage, but also provide detailed diagnostic information, prevention suggestions and alarm prompts, thereby effectively improving the system's response speed and decision-making accuracy, and enhancing the safety and reliability of the process industry in the face of complex and changing working environments.

[0053] In an embodiment of the present application, the collaboration module is used to adjust the operating parameters of the verification module, the anomaly detection module and the early warning module according to the risk information, the abnormal data and the early warning information.

[0054] Preferably, for collaborative modules: first, define the interactive interfaces and collaborative rules of each module to achieve real-time sharing and collaborative processing of information; second, perform real-time parameter monitoring and optimization for each module, introduce high-precision sensors, advanced data acquisition technology and real-time transmission protocols; finally, provide all other modules with detailed reports on their performance, including accuracy, recall rate, F1 score, etc., to help each module perform self-optimization.

[0055] In an embodiment of the present application, the performance evaluation module is used to automatically update the threshold alarm mechanism according to the preset performance indicators of each module.

[0056] Preferably, for the performance evaluation module: continuously monitor and evaluate each module of the entire security monitoring system, track key performance indicators (KPIs), set up a reasonable threshold alarm mechanism, and collect feedback from end users, especially false positives or missed negatives, so as to correct deviations in the model in a timely manner.

[0057] In an embodiment of the present application, the update module is used to update the preset thresholds in the abnormality detection module and the early warning module based on incremental learning technology according to the sensor data received in real time, the preset abnormality thresholds and the preset early warning thresholds.

[0058] Preferably, for the update module: incremental learning technology is used to fine-tune the preset abnormality threshold in the abnormality detection module and the preset warning threshold in the warning module using the sensor data received in real time.

[0059] Incremental learning technology not only improves the efficiency of model updating, but also reduces the consumption of computing resources, thereby enhancing the model's ability to adapt to changing scenarios.

[0060] This application proposes a real-time monitoring and early warning method for process industries, such as Figure 2 As shown, the following steps are included:

[0061] Step S1, receiving safety instrument data of each device in the process industry and sensor data of each sensor in real time;

[0062] Step S2, based on the safety instrument data, calling the SIL level verification model to perform online verification on the data to determine the risk information of each of the devices;

[0063] Step S3, determining abnormal data based on the abnormality detection model according to the sensor data and the risk information;

[0064] Step S4: generating warning information according to the abnormal data or the risk information.

[0065] The present application proposes a computer-readable storage medium storing computer instructions, which, when executed by a processor, implement the process industry real-time monitoring and early warning system instructions described in any one of the above embodiments.

[0066] It should be noted that the embodiments of the storage medium in this specification and the embodiments of the blockchain-based service provision method in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the aforementioned corresponding implementation of the blockchain-based service provision method, and the repeated parts will not be repeated.

[0067] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0068] In the 1930s, improvements to a technology could be clearly distinguished as hardware improvements (for example, improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the method flow). However, with the development of technology, many improvements to the method flow today can be regarded as direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement in a method flow cannot be implemented using a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask a chip manufacturer to design and produce a dedicated integrated circuit chip. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0069] The controller can be implemented in any appropriate manner, for example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in a purely computer-readable program code manner, the controller can be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, this controller can be considered as a hardware component, and the devices included therein for implementing various functions can also be regarded as structures within the hardware component. Or even, the devices for implementing various functions can be regarded as both software modules for implementing the method and structures within the hardware component.

[0070] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0071] For the convenience of description, the above devices are described in terms of functions and are divided into various units. Of course, when implementing the embodiments of this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0072] It should be understood by those skilled in the art that one or more embodiments of this specification may be provided as a method, system or computer program product. Therefore, one or more embodiments of this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0073] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0074] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0075] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0076] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0077] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0078] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0079] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0080] One or more embodiments of the present specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. One or more embodiments of the present specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0081] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0082] The above description is only an embodiment of this document and is not intended to limit this document. For those skilled in the art, this document may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this document should be included in the scope of the claims of this document.

Claims

1. A real-time monitoring and early warning system for process industries, characterized by include: Data acquisition module, used to receive safety instrument data of various equipment in the process industry and sensor data of various sensors in real time; A verification module, used to call a SIL level verification model to perform online verification on the data according to the safety instrument data, and determine the risk information of each of the devices; An anomaly detection module, used to determine abnormal data based on the sensor data and the risk information based on an anomaly detection model; The early warning module is used to generate early warning information according to the abnormal data and the risk information.

2. The process industry real-time monitoring and early warning system according to claim 1 is characterized in that Also includes: A collaboration module is used to adjust the operating parameters of the verification module, the anomaly detection module and the early warning module according to the risk information, the abnormal data and the early warning information.

3. The process industry real-time monitoring and early warning system according to claim 1 is characterized in that Also includes: The performance evaluation module is used to automatically update the threshold alarm mechanism according to the preset performance indicators of each module.

4. According to the process industry real-time monitoring and early warning system of claim 1, the safety instrument data includes real-time equipment operation data, historical fault data and equipment configuration data, characterized in that The verification module is configured as follows: Based on the SIL level verification model, determining a target SIL level according to the historical fault data and the device configuration data; Determine the failure probability level of each device according to the real-time operation data of the device and the target SIL level; According to the failure probability level, the risk information of each device is determined, and the risk information includes the failure level, the failure location, and the failure cause.

5. The process industry real-time monitoring and early warning system according to claim 1 is characterized in that The anomaly detection module is configured to: Based on the anomaly detection model, determining anomaly detection feature data according to the sensor data and the risk information; The abnormal data is determined according to the abnormal detection feature data and a preset abnormal threshold.

6. The process industry real-time monitoring and early warning system according to claim 5 is characterized in that The anomaly detection module is also configured to: Determine variable data based on the sensor data and the risk information based on a Bayesian network inference algorithm; Determine the change probability and change condition of each variable data according to the variable data; A fault diagnosis result is obtained according to the change probability and the change condition.

7. The process industry real-time monitoring and early warning system according to claim 1 is characterized in that The early warning module is configured as follows: Obtaining a risk score according to the abnormal data and the risk information; The warning information is generated according to the risk score and a preset warning threshold.

8. The process industry real-time monitoring and early warning system according to claim 1 is characterized in that Also includes: The updating module is used to update the preset thresholds in the abnormality detection module and the early warning module based on the incremental learning technology according to the sensor data received in real time, the preset abnormality thresholds and the preset early warning thresholds.

9. A real-time monitoring and early warning method for process industry, characterized in that include: Receive safety instrument data from each device in the process industry and sensor data from each sensor in real time; Based on the safety instrument data, calling the SIL level verification model to perform online verification on the data, and determining the risk information of each of the devices; Based on the anomaly detection model, determining abnormal data according to the sensor data and the risk information; Generate warning information based on the abnormal data and the risk information.

10. A computer-readable storage medium storing computer instructions, which, when executed by a processor, implement the process industry real-time monitoring and early warning system instructions as described in any one of claims 1 to 8.

Images