Chemical equipment fault early warning system based on Internet of Things

Abstract

The invention belongs to the technical field of chemical equipment fault early warning, and provides a chemical equipment fault early warning system based on the Internet of Things, which comprises an intelligent sensor network, a dynamic data analysis engine, a fault early warning and decision support system, a self-adaptive learning module and an integrated visual interface, according to the invention, equipment data is collected in real time through the intelligent sensor network, and real-time analysis and prediction are carried out by using the dynamic data analysis engine, so that the accuracy and timeliness of fault early warning are improved; meanwhile, the adaptive learning module can continuously optimize algorithm parameters, and the prediction performance is improved; the fault early warning and decision support system provides maintenance suggestions and optimization schemes, a visual interface is integrated to facilitate equipment management by a user, and the management efficiency and safety of the chemical equipment are integrally improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of chemical equipment fault warning, and specifically relates to a chemical equipment fault warning system based on the Internet of Things. Background Art

[0002] In the chemical industry, the stable operation of equipment is crucial for production efficiency and safety. In recent years, with the rapid development of Internet of Things technology, more and more industries have begun to try to apply Internet of Things technology to equipment fault warning systems. Through means such as sensor networks, cloud computing, and big data analysis, Internet of Things technology can achieve real-time monitoring of equipment status and data analysis, thereby discovering signs of equipment faults in advance and providing strong support for equipment maintenance and management.

[0003] However, since chemical equipment usually operates in harsh environments such as high temperature, high pressure, and corrosive environments, these equipment often face higher fault risks, making most of the current traditional fault detection methods rely on manual inspections and regular maintenance. This method is not only inefficient but also difficult to detect and handle potential faults in a timely manner, resulting in production interruptions, equipment damage, and even safety accidents.

[0004] Therefore, those skilled in the art have proposed a chemical equipment fault warning system based on the Internet of Things to solve the problems raised in the background art. Summary of the Invention

[0005] To solve the above technical problems, the present invention provides a chemical equipment fault warning system based on the Internet of Things to solve the problems in the prior art that most fault detection methods rely on manual inspections and regular maintenance, which is not only inefficient but also difficult to detect and handle potential faults in a timely manner, resulting in production interruptions, equipment damage, and even safety accidents.

[0006] A chemical equipment fault warning system based on the Internet of Things includes:

[0007] Intelligent sensing network: Deployed at key parts of chemical equipment, used to collect equipment operation parameters and environmental conditions in real time and with high precision, including but not limited to vibration, temperature, pressure, flow rate, sound, and the concentration of specific chemical substances;

[0008] Dynamic data analysis engine: Integrated in the cloud server, using machine learning algorithms to perform real-time analysis on the collected data, identify abnormal data patterns, and predict the possibility and type of equipment faults;

[0009] Fault warning and decision support system: According to the output of the data analysis engine, automatically generate fault warning signals and send them to relevant personnel immediately through the Internet of Things communication module, and at the same time provide maintenance suggestions and optimization plans based on the prediction results;

[0010] Adaptive learning module: It can automatically adjust and optimize the parameters of the analysis algorithm based on historical fault data and newly collected real-time data, improving the accuracy and timeliness of fault prediction;

[0011] Integrated visualization interface: It provides users with functions such as intuitive display of device operating status, historical query of fault warnings, and maintenance task management, supporting multi-platform access, including mobile devices and desktop browsers.

[0012] Preferably, in the intelligent sensing network, a data transformation algorithm is introduced to normalize a large amount of collected raw data to improve the performance of subsequent algorithms; the intelligent sensing network adopts low-power wireless communication technology, which ensures long-term stable operation while reducing the impact on the operation of chemical equipment itself. The low-power wireless communication technology realizes the maximum reduction of energy consumption while maintaining the necessary communication performance by means of optimizing data transmission rate, reducing communication overhead, and adopting energy-saving modes. The low-power wireless communication technology includes Bluetooth Low Energy (BLE), Zigbee, LoRa, NB-IoT, etc.

[0013] Preferably, in the dynamic data analysis engine, the formula of the machine learning algorithm is as follows:

[0014]

[0015] Among them, N is the number of support vectors, α i is the coefficient of the support vector, y i is the label of the support vector, K(x i x) is the kernel function, and b is the bias term.

[0016] Preferably, the dynamic data analysis engine further includes a deep learning model, which can automatically learn the normal and abnormal modes of device operation and can effectively predict faults even in the case of complex and variable device states;

[0017] At the same time, a random forest algorithm is introduced: the prediction accuracy is improved by constructing multiple decision trees and integrating their prediction results.

[0018] Preferably, the fault warning and decision support system further includes a simulation function, which can simulate the device operating status under different maintenance strategies based on the current device state and prediction model to assist decision-making. The simulation function adopts the Monte Carlo simulation method to simulate the random fault process and uncertainty factors of the device.

[0019] Preferably, in the adaptive learning module, an adaptive learning algorithm is introduced, which can automatically adjust and optimize the parameters of the analysis algorithm based on historical fault data and newly collected real-time data.

[0020] Preferably, the adaptive learning module further includes a user feedback mechanism that allows users to provide feedback on the system based on the accuracy of the warning results, further promoting the optimization of the algorithm. The user feedback mechanism automatically adjusts the parameters of the warning algorithm by using the Bayesian optimization algorithm.

[0021] A processor is configured to execute a chemical equipment fault warning system based on the Internet of Things as described above.

[0022] A computer-readable storage medium stores a computer program thereon. When the computer program is executed by a processor, it implements a chemical equipment fault warning system based on the Internet of Things as described above.

[0023] Compared with the prior art, the present invention has the following beneficial effects:

[0024] 1. The present invention can accurately identify abnormal data patterns, predict the possibility and type of equipment failures by using a dynamic data analysis engine to collect and process key operation parameters and environmental conditions of chemical equipment in real time through an intelligent sensing network, thereby greatly improving the accuracy and timeliness of fault warning.

[0025] 2. The present invention introduces an adaptive learning module that can automatically adjust and optimize the parameters of the analysis algorithm based on historical fault data and newly collected real-time data, continuously improving the accuracy and timeliness of fault prediction; this adaptive learning ability enables the system to better adapt to the variability and complexity of the state of chemical equipment.

[0026] 3. The present invention not only provides fault warning signals, but also provides maintenance suggestions and optimization plans based on the prediction results for users through a fault warning and decision support system, which can help users better manage equipment, reduce maintenance costs and improve production efficiency.

[0027] 4. The present invention provides an integrated visualization interface that supports multi-platform access, including mobile devices and desktop browsers; users can intuitively understand information such as equipment operation status, fault warning history, and maintenance task management through these platforms, making it more convenient to manage and maintain equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 It is a framework diagram of a chemical equipment fault warning system based on the Internet of Things of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0029] The following further describes the embodiments of the present invention in conjunction with the accompanying drawings and embodiments. The following embodiments are used to illustrate the present invention, but cannot be used to limit the scope of the present invention.

[0030] Embodiment: The present invention provides a chemical equipment fault warning system based on the Internet of Things. As Figure 1 shown, it includes an intelligent sensing network, a dynamic data analysis engine, a fault warning and decision support system, an adaptive learning module, and an integrated visualization interface. The intelligent sensing network, dynamic data analysis engine, fault warning and decision support system, adaptive learning module, and integrated visualization interface are electrically connected in sequence:

[0031] Intelligent sensing network: Deployed at key parts of chemical equipment, it is used to collect equipment operation parameters and environmental conditions in real time and with high precision, including but not limited to vibration, temperature, pressure, flow rate, sound, and the concentration of specific chemical substances;

[0032] Dynamic data analysis engine: Integrated in the cloud server, it uses machine learning algorithms to perform real-time analysis on the collected data, identify abnormal data patterns, and predict the possibility and type of equipment failures;

[0033] Fault warning and decision support system: According to the output of the data analysis engine, it automatically generates fault warning signals and immediately sends them to relevant personnel through the Internet of Things communication module. At the same time, it provides maintenance suggestions and optimization solutions based on the prediction results;

[0034] Adaptive learning module: It can automatically adjust and optimize the parameters of the analysis algorithm based on historical fault data and newly collected real-time data, improving the accuracy and timeliness of fault prediction;

[0035] Integrated visualization interface: It provides functions such as intuitive display of equipment operation status, query of fault warning history, and maintenance task management for users, and supports multi-platform access, including mobile devices and desktop browsers.

[0036] As can be seen from the above, by collecting equipment data in real time through the intelligent sensing network and using the dynamic data analysis engine for real-time analysis and prediction, the accuracy and timeliness of fault warning are improved; at the same time, the adaptive learning module can continuously optimize the algorithm parameters to improve the prediction performance; the fault warning and decision support system provides maintenance suggestions and optimization solutions, and the integrated visualization interface facilitates users to manage equipment, overall improving the management efficiency and safety of chemical equipment.

[0037] Furthermore, in the intelligent sensing network, a data transformation algorithm is introduced to perform normalization processing on a large amount of collected raw data to improve the performance of subsequent algorithms. The formula of the data transformation algorithm is as follows:

[0038]

[0039] Among them, x is the original data, μ is the mean of the data, σ is the standard deviation of the data, z is the data after standardization.

[0040] As can be seen from the above, in the intelligent sensing network, introducing a data transformation algorithm to normalize the original data can significantly improve the performance of subsequent algorithms; through this algorithm, the original data is converted into standard data with a unified scale and distribution, which helps the machine learning algorithm to converge faster, improve the analysis efficiency and accuracy, and thus further optimize the overall performance of the fault warning system.

[0041] Furthermore, in the dynamic data analysis engine, the formula of the machine learning algorithm is as follows:

[0042]

[0043] Among them, N is the number of support vectors, α i is the coefficient of the support vector, y i is the label of the support vector, K(x i x) is the kernel function, and b is the bias term.

[0044] As can be seen from the above, in the dynamic data analysis engine, adopting a specific machine learning algorithm can make full use of support vectors and their related information (including the number, coefficient, label, and kernel function, etc.), as well as the bias term, to accurately analyze the collected data. This algorithm helps to accurately identify abnormal data patterns, predict the possibility and type of equipment failures, and thus improves the accuracy and reliability of fault warning, providing a strong guarantee for the stable operation of chemical equipment.

[0045] Furthermore, the dynamic data analysis engine further includes a deep learning model, which can automatically learn the normal and abnormal modes of equipment operation and can effectively predict faults even under complex and changeable equipment states. The formula of the deep learning model is as follows:

[0046] y = σ(W·x + b);

[0047] Among them, x is the input data, W is the weight matrix of the convolution kernel, b is the bias term, and σ is the activation function;

[0048] At the same time, the random forest algorithm is introduced: by constructing multiple decision trees and integrating their prediction results to improve the prediction accuracy. The prediction result formula of the random forest algorithm is as follows:

[0049]

[0050] Among them, M is the number of decision trees, and T m (x) is the prediction result of the m-th decision tree.

[0051] As can be seen from the above, in the dynamic data analysis engine, introducing a deep learning model and a random forest algorithm can significantly improve the effect of fault prediction; the deep learning model can cope with the complex and changeable device states by automatically learning the normal and abnormal operation modes of the device, and achieve accurate prediction; at the same time, the random forest algorithm further improves the accuracy and stability of prediction by constructing multiple decision trees and integrating their prediction results; the combined use of these two algorithms provides more reliable and accurate technical support for the fault warning of chemical equipment.

[0052] Furthermore, the fault warning and decision support system further includes a simulation function, which can simulate the operation states of the device under different maintenance strategies based on the current device state and the prediction model to assist in decision-making. The simulation function adopts the Monte Carlo simulation method to simulate the random fault process and uncertainty factors of the device. The formula of the Monte Carlo simulation method is as follows:

[0053]

[0054] Among them, P(A) is the probability of the occurrence of event A, N is the number of simulations, and N A is the number of occurrences of event A.

[0055] As can be seen from the above, by introducing the simulation function and adopting the Monte Carlo simulation method, it is possible to effectively simulate the operation states of the device under different maintenance strategies based on the current device state and the prediction model; this method fully considers the random fault process and uncertainty factors of the device, and provides more comprehensive and accurate simulation results for decision-makers; through simulation, users can intuitively understand the impact of different maintenance strategies on the device operation, and thus make more scientific and reasonable decisions, optimize the device maintenance plan, reduce the fault risk, and improve the production efficiency.

[0056] Furthermore, in the adaptive learning module, introducing an adaptive learning algorithm can automatically adjust and optimize the parameters of the analysis algorithm based on historical fault data and newly collected real-time data. The formula of the adaptive learning algorithm is as follows:

[0057]

[0058] Among them, θ t is the model parameter of the t-th iteration, η is the learning rate, is the gradient of the loss function J with respect to the model parameter θ.

[0059] As can be seen from the above, the introduction of the adaptive learning algorithm can significantly improve the intelligence and self - adaptability of the fault warning system; this algorithm can automatically adjust and optimize the parameters of the analysis algorithm based on historical fault data and newly collected real - time data, enabling the model to better adapt to the changes and complexities of the equipment state; through continuous iteration and optimization, the system can gradually improve its prediction accuracy and timeliness, providing a more reliable technical guarantee for the stable operation of chemical equipment.

[0060] Furthermore, the adaptive learning module also includes a user feedback mechanism that allows users to provide feedback on the system according to the accuracy of the warning results, further promoting the optimization of the algorithm. The user feedback mechanism automatically adjusts the parameters of the warning algorithm by using the Bayesian optimization algorithm. The formula of the Bayesian optimization algorithm is as follows:

[0061]

[0062] where θ * is the optimal parameter combination, Θ is the parameter space, and f(θ) is the objective function (such as the loss function).

[0063] As can be seen from the above, in the adaptive learning module, the introduction of the user feedback mechanism and the application of the Bayesian optimization algorithm further enhance the interactivity and optimization ability of the system; users can provide feedback on the system according to the accuracy of the warning results, and the system then uses the Bayesian optimization algorithm to automatically adjust the parameters of the warning algorithm to pursue better prediction effects; this not only improves the accuracy and reliability of the system, but also enhances the interactivity between users and the system, enabling the system to continuously learn and progress, and better serving the fault warning and management of chemical equipment.

[0064] Working principle: The system collects the operation parameters and environmental condition data of chemical equipment in real - time through an intelligent sensing network, and then uses the dynamic data analysis engine integrated in the cloud server to perform real - time analysis on these data by using machine learning algorithms to identify abnormal data patterns and predict the possibility and type of equipment failures; the fault warning and decision - making support system automatically generates warning signals according to the analysis results and immediately sends them to relevant personnel through the Internet of Things communication module, while providing maintenance suggestions and optimization plans; the adaptive learning module automatically adjusts and optimizes the parameters of the analysis algorithm according to historical fault data and newly collected real - time data to improve prediction accuracy; in addition, the system also provides an integrated visualization interface, supports multi - platform access, and facilitates users to manage equipment status and maintenance tasks.

[0065] Even further, a comparison of the effects between an Internet - of - Things - based chemical equipment fault warning system in an embodiment and the current traditional fault detection methods (comparative examples) is made, and the following table is obtained:

[0066]

[0067]

[0068] As can be seen from the above table, a chemical equipment fault warning system based on the Internet of Things in the embodiment is superior to traditional fault detection methods in terms of data collection, data analysis, warning accuracy, timeliness, adaptability, user interaction, maintenance cost, production efficiency, and security; therefore, this system has higher application value and development prospects.

[0069] An embodiment of the present application provides an electronic device, which is applicable to the above-mentioned chemical equipment fault warning system based on the Internet of Things, and includes:

[0070] A memory for protecting computer programs and data;

[0071] A processor for running system programs.

[0072] An embodiment of the present application provides a computer storage medium, which is applicable to the above-mentioned chemical equipment fault warning system based on the Internet of Things, and performs hierarchical confidentiality management on the above system and data according to confidentiality management requirements.

[0073] Those skilled in the art should understand that the embodiments of the present application can be provided as a system or a computer program product. Therefore, the present application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can 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.

[0074] The present application is described with reference to the flowcharts and / or block diagrams of the devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, and the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate for implementing in the process Figure 1 one process or multiple processes and / or blocks Figure 1 a device for the functions specified in one block or multiple blocks.

[0075] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements in the processFigure 1 one or more processes and / or blocks Figure 1 the functions specified in one or more blocks.

[0076] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one or more processes and / or blocks Figure 1 the functions specified in one or more blocks.

[0077] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0078] The memory may include non-permanent memory in the computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0079] Computer-readable media include permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. The 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 technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information accessible by a computing device. As defined herein, computer-readable media do not include transitory computer-readable media, such as modulated data signals and carrier waves.

[0080] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, article or device comprising the element.

[0081] Embodiments of the present invention are provided for purposes of illustration and description. Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A chemical equipment fault early warning system based on the Internet of Things, characterized in that: include: Intelligent sensor network: deployed in key parts of chemical equipment to collect equipment operating parameters and environmental conditions in real time and with high precision, including but not limited to vibration, temperature, pressure, flow, sound and concentration of specific chemicals; Dynamic data analysis engine: integrated into the cloud server, using machine learning algorithms to analyze collected data in real time, identify abnormal data patterns, and predict the possibility and type of equipment failure; Fault warning and decision support system: Based on the output of the data analysis engine, fault warning signals are automatically generated and sent to relevant personnel instantly through the IoT communication module. At the same time, maintenance suggestions and optimization plans based on the prediction results are provided; Adaptive learning module: It can automatically adjust and optimize the parameters of the analysis algorithm based on historical fault data and newly collected real-time data to improve the accuracy and timeliness of fault prediction; Integrated visual interface: provides users with intuitive equipment operation status display, fault warning history query, maintenance task management functions, and supports multi-platform access, including mobile devices and desktop browsers.

2. A chemical equipment fault early warning system based on the Internet of Things as claimed in claim 1, characterized in that: In intelligent sensor networks, data transformation algorithms are introduced to normalize the large amount of raw data collected.

3. A chemical equipment fault early warning system based on the Internet of Things as claimed in claim 1, characterized in that: In the dynamic data analysis engine, the formula of the machine learning algorithm is as follows: Where N is the number of support vectors, α i is the coefficient of the support vector, y i is the label of the support vector, K(x i x) is the kernel function and b is the bias term.

4. The chemical equipment fault early warning system based on the Internet of Things as claimed in claim 1, characterized in that: The dynamic data analysis engine further includes a deep learning model that can automatically learn normal and abnormal modes of equipment operation and effectively predict failures even when equipment status is complex and changeable; At the same time, the random forest algorithm is introduced: the prediction accuracy is improved by constructing multiple decision trees and combining their prediction results.

5. The chemical equipment fault early warning system based on the Internet of Things as claimed in claim 1, characterized in that: The fault warning and decision support system also includes a simulation function, which can simulate the equipment operation status under different maintenance strategies based on the current equipment status and prediction model. The simulation function adopts the Monte Carlo simulation method to simulate the random failure process and uncertainty factors of the equipment.

6. The chemical equipment fault early warning system based on the Internet of Things as claimed in claim 1, characterized in that: In the adaptive learning module, an adaptive learning algorithm is introduced, which can automatically adjust and optimize the parameters of the analysis algorithm based on historical fault data and newly collected real-time data.

7. The chemical equipment fault early warning system based on the Internet of Things as claimed in claim 1, characterized in that: The adaptive learning module also includes a user feedback mechanism, which allows users to provide feedback to the system based on the accuracy of the early warning results, further promoting the optimization of the algorithm. The user feedback mechanism automatically adjusts the parameters of the early warning algorithm by utilizing the Bayesian optimization algorithm.

8. A processor, characterized in that: The method is configured to execute a chemical equipment failure early warning system based on the Internet of Things according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the chemical equipment fault warning system based on the Internet of Things as described in any one of claims 1 to 7 is implemented.

Images