Equipment state monitoring method and device, equipment, storage medium and product

Abstract

The invention discloses an equipment state monitoring method and device, equipment, a storage medium and a product. The method is applied to a nuclear power station equipment monitoring system comprising an edge platform and a data center platform, and comprises the steps of determining a comprehensive anomaly detection value of nuclear power station equipment according to current operation state data of the nuclear power station equipment through the edge platform, and determining the nuclear power station equipment as abnormal equipment under the condition that the comprehensive anomaly detection value is greater than a preset early warning threshold value, target data of the abnormal equipment is sent to a data center platform, and the target data comprises current operation state data and an abnormal indication value in a preset time window; and through the data center platform, determining a target fault reason of the abnormal equipment based on the received current operation state data and the abnormal indication value in the preset time window, and generating a maintenance operation suggestion according to the target fault reason. The data transmission delay is reduced, the real-time performance is improved, the quick response to the equipment abnormity is realized, and the fault diagnosis efficiency is improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of nuclear power plant monitoring, and in particular, to a method, device, equipment, storage medium and product for monitoring the state of equipment. Background Art

[0002] With the increasing complexity and criticality of nuclear power plant equipment, higher requirements are put forward for the real-time monitoring of its operating status and fault early warning. Traditional monitoring systems often rely on regular maintenance and manual inspections, and cannot respond in a timely manner when equipment anomalies occur, which easily leads to small faults evolving into major problems, thereby affecting the safety and efficiency of nuclear power plants. Therefore, it is particularly important to develop a method that can monitor the equipment status in real time, quickly identify potential faults, and provide intelligent maintenance suggestions.

[0003] Currently, there is a remote diagnosis platform for key equipment in nuclear power plants based on cloud data management, which can realize real-time data collection, aggregation, transmission, online monitoring and fault diagnosis of key equipment in nuclear power plants; however, existing solutions usually rely on the cloud for data storage and diagnosis, which results in a large data transmission delay, poor real-time performance, and difficulty in quickly responding to equipment anomalies, thereby affecting the fault diagnosis efficiency. Summary of the Invention

[0004] The present invention provides a method, device, equipment, storage medium and product for monitoring the state of equipment, so as to solve the problems of large data transmission delay, poor real-time performance, difficulty in quickly responding to equipment anomalies and low fault diagnosis efficiency existing in the existing equipment state monitoring methods.

[0005] According to one aspect of the present invention, there is provided a method for monitoring the state of equipment, which is applied to a nuclear power plant equipment monitoring system. The nuclear power plant equipment monitoring system includes an edge platform and a data center platform, wherein the edge platform is deployed on the side of nuclear power plant equipment. The method includes:

[0006] Through the edge platform, according to the current operating status data of the nuclear power plant equipment, determine the comprehensive anomaly detection value of the nuclear power plant equipment. In the case where the comprehensive anomaly detection value is greater than a preset warning threshold, determine that the nuclear power plant equipment is an abnormal equipment, and send the target data of the abnormal equipment to the data center platform, wherein the target data includes the current operating status data and the anomaly indication value within a preset time window;

[0007] Through the data center platform, based on the received current operating status data and the anomaly indication value within the preset time window, determine the target fault cause of the abnormal equipment, and generate a maintenance operation suggestion according to the target fault cause.

[0008] According to another aspect of the present invention, there is provided a device status monitoring device configured in a nuclear power plant equipment monitoring system. The nuclear power plant equipment monitoring system includes an edge platform and a data center platform. Among them, the edge platform is deployed on the side of the nuclear power plant equipment. The device includes:

[0009] An anomaly detection module, which is used to determine the comprehensive anomaly detection value of the nuclear power plant equipment through the edge platform according to the current operating status data of the nuclear power plant equipment. When the comprehensive anomaly detection value is greater than a preset warning threshold, it is determined that the nuclear power plant equipment is an abnormal device, and the target data of the abnormal device is sent to the data center platform. Among them, the target data includes the current operating status data and the anomaly indication value within a preset time window;

[0010] A fault generation module, which is used to determine the target fault cause of the abnormal device through the data center platform based on the received current operating status data and the anomaly indication value within the preset time window, and generate maintenance operation suggestions according to the target fault cause.

[0011] According to another aspect of the present invention, there is provided an electronic device configured as a nuclear power plant equipment monitoring system. The electronic device includes:

[0012] At least one processor; and

[0013] A memory communicatively connected to the at least one processor; wherein,

[0014] The memory stores a computer program executable by the at least one processor. The computer program is executed by the at least one processor so that the at least one processor can execute the device status monitoring method according to any embodiment of the present invention.

[0015] According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement the device status monitoring method according to any embodiment of the present invention when executed.

[0016] According to another aspect of the present invention, there is provided a computer program product including a computer program that implements the device status monitoring method according to any embodiment of the present invention when executed by a processor.

[0017] The technical solution provided by the embodiment of the present invention is applied to a nuclear power plant equipment monitoring system. The nuclear power plant equipment monitoring system includes an edge platform and a data center platform. Among them, the edge platform is deployed on the side of the nuclear power plant equipment. The method includes: through the edge platform, according to the current operating state data of the nuclear power plant equipment, determining the comprehensive anomaly detection value of the nuclear power plant equipment. When the comprehensive anomaly detection value is greater than a preset warning threshold, determining that the nuclear power plant equipment is an abnormal equipment, and sending the target data of the abnormal equipment to the data center platform, where the target data includes the current operating state data and the anomaly indication value within a preset time window; through the data center platform, based on the received current operating state data and the anomaly indication value within the preset time window, determining the target fault cause of the abnormal equipment, and generating a maintenance operation suggestion according to the target fault cause. Through the above technical solution, by using the edge platform deployed on the side of the nuclear power plant equipment, the anomaly detection of the nuclear power plant equipment can be quickly completed locally. After determining that the nuclear power plant equipment is an abnormal equipment, the target data of the abnormal equipment is sent to the data center platform, thus avoiding transmitting all data to the data center platform for processing and detection, greatly reducing the data transmission delay in the equipment anomaly detection process, and significantly improving the real-time performance of data processing; furthermore, the data center platform determines the target fault cause based on the target data and generates a maintenance suggestion, realizing a quick response to equipment anomalies and effectively improving the fault diagnosis efficiency.

[0018] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. Brief Description of the Drawings

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0020] Figure 1 It is a flowchart of a device status monitoring method provided by Embodiment 1 of the present invention;

[0021] Figure 2 It is a schematic structural diagram of a device status monitoring device provided by Embodiment 2 of the present invention;

[0022] Figure 3 It is a schematic structural diagram of an electronic device provided by Embodiment 3 of the present invention. Detailed Embodiments

[0023] To enable those skilled in the art to better understand the solution of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0024] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0025] Embodiment 1

[0026] Figure 1 is a flowchart of a device status monitoring method provided in Embodiment 1 of the present invention. This embodiment is applicable to the situation of monitoring nuclear power plant equipment. This method can be executed by a device status monitoring device, which can be implemented in the form of hardware and / or software. The device status monitoring device can be configured in an electronic device, which can be configured as a nuclear power plant equipment monitoring system. The nuclear power plant equipment monitoring system includes an edge platform and a data center platform, wherein the edge platform is deployed on the side of the nuclear power plant equipment. As Figure 1 shown, this method includes:

[0027] S110. Through the edge platform, determine the comprehensive anomaly detection value of the nuclear power plant equipment according to the current operating status data of the nuclear power plant equipment. When the comprehensive anomaly detection value is greater than a preset warning threshold, determine that the nuclear power plant equipment is an abnormal device, and send the target data of the abnormal device to the data center platform, where the target data includes the current operating status data and the anomaly indication value within a preset time window.

[0028] In this embodiment, the edge platform is deployed on the nuclear power plant equipment side. The current operating state data can be understood as the parameter data generated during the operation of the nuclear power plant equipment at the current moment obtained through data acquisition devices. These parameter data can include data in multiple dimensions such as temperature, vibration, pressure, and flow rate. Among them, each parameter represents a dimension. The comprehensive anomaly detection value can be understood as the result of comprehensively evaluating the abnormal conditions of the nuclear power plant equipment based on the current operating state data. The preset warning threshold can be understood as a preset value used to determine whether the comprehensive anomaly detection value is within the normal range. The target data can be understood as the data used to determine the fault cause of the nuclear power plant equipment. Among them, the target data includes the current operating state data and the anomaly indication values within a preset time window. The preset time window can be understood as a preset time range, which is cut off at the current time and is used to count the anomaly indication values of the corresponding dimension data in each dimension over a period of time in the past. The anomaly indication value is used to determine whether the abnormal data in the operating state data is in a high abnormal state or a low abnormal state. For example, an anomaly indication value of 1 indicates that the abnormal data is in a high abnormal state, and an anomaly indication value of 0 indicates that the abnormal data is in a low abnormal state. For any one dimension, each time point in the preset time window corresponds to an anomaly indication value.

[0029] Specifically, through the edge platform, various data acquisition devices deployed on the nuclear power plant equipment, such as temperature sensors and pressure sensors, are used to collect the original operating state data of the nuclear power plant equipment in real time. Preprocessing operations are performed on these original operating state data to obtain the current operating state data. Among them, the preprocessing operations include but are not limited to filtering, denoising, and normalization processing. Furthermore, based on the current operating state data, a preset anomaly detection algorithm is used to calculate the comprehensive anomaly detection value of the nuclear power plant equipment to comprehensively evaluate the nuclear power plant equipment. In the case where it is determined that the comprehensive anomaly detection value is greater than the preset warning threshold, it is determined that the nuclear power plant equipment is an abnormal equipment. Furthermore, the target data corresponding to the abnormal equipment is sent to the data center platform.

[0030] It should be noted that in this embodiment, the preset anomaly detection algorithm is not specifically limited, and a suitable algorithm can be selected according to the characteristics of the nuclear power plant equipment and the data characteristics.

[0031] S120. Through the data center platform, based on the received current operating state data and the anomaly indication values within the preset time window, determine the target fault cause of the abnormal equipment, and generate a maintenance operation suggestion according to the target fault cause.

[0032] In this embodiment, the target fault cause can be understood as the fault cause corresponding to the abnormal equipment.

[0033] Specifically, the target data is received through the data center platform, and based on the current operating status data in the target data and the abnormal indication values within a preset time window, the target fault cause of the abnormal device is determined using a fault cause prediction algorithm. Furthermore, based on the determined target fault cause, a maintenance operation suggestion is generated using a preset suggestion generation model.

[0034] It should be noted that the fault cause prediction algorithm can be a pre-set algorithm for predicting the fault cause of abnormal devices. The specific form of the fault cause prediction algorithm is not limited in this embodiment. For example, the algorithm can be a neural network model based on deep learning or an algorithm based on machine learning. The preset suggestion generation model can be a pre-trained model for generating maintenance operation suggestions. The specific form of the preset suggestion model is not limited in this embodiment. For example, it can be a model based on a large language model or a model based on deep learning.

[0035] The technical solution provided in the first embodiment of the present invention is applied to a nuclear power plant equipment monitoring system. The nuclear power plant equipment monitoring system includes an edge platform and a data center platform. Among them, the edge platform is deployed on the side of the nuclear power plant equipment. The method includes: through the edge platform, according to the current operating status data of the nuclear power plant equipment, determining the comprehensive abnormal detection value of the nuclear power plant equipment. When the comprehensive abnormal detection value is greater than a preset warning threshold, determining that the nuclear power plant equipment is an abnormal device, and sending the target data of the abnormal device to the data center platform, where the target data includes the current operating status data and the abnormal indication values within a preset time window; through the data center platform, based on the received current operating status data and the abnormal indication values within the preset time window, determining the target fault cause of the abnormal device, and generating a maintenance operation suggestion according to the target fault cause. Through the above technical solution, by using the edge platform deployed on the side of the nuclear power plant equipment, the abnormal detection of the nuclear power plant equipment can be quickly completed locally. After determining that the nuclear power plant equipment is an abnormal device, the target data of the abnormal device is sent to the data center platform, thus avoiding transmitting all data to the data center platform for processing and detection, greatly reducing the data transmission delay in the equipment abnormal detection process, and significantly improving the real-time performance of data processing; furthermore, the data center platform determines the target fault cause based on the target data and generates a maintenance suggestion, realizing a rapid response to equipment abnormalities and effectively improving the fault diagnosis efficiency.

[0036] In some embodiments, determining the comprehensive anomaly detection value of the nuclear power plant equipment based on the current operating state data of the nuclear power plant equipment includes: calculating the membership value of the dimension data of each dimension in the current operating state data of the nuclear power plant equipment by using a preset membership algorithm, where the membership value represents the degree to which the corresponding dimension data approaches the abnormal state; determining the comprehensive anomaly detection value of the nuclear power plant equipment based on an adjustment coefficient, the membership value of the dimension data of each dimension, and the corresponding preset weight, where the adjustment coefficient is determined based on the anomaly indication value of the dimension data of each dimension, and the anomaly indication value is determined by using the anomaly indication function of the dimension data based on the membership value and membership threshold of the corresponding dimension data.

[0037] In this embodiment, the preset membership algorithm can be understood as an algorithm that is preset to calculate the membership value of the dimension data of each dimension. The specific form of the preset membership algorithm is not limited in this embodiment. For example, it can be a neural network algorithm based on deep learning or an algorithm based on traditional statistical methods. The membership value represents the degree to which the corresponding dimension data approaches the abnormal state.

[0038] Specifically, use the preset membership algorithm to calculate the membership value of the dimension data of each dimension in the current operating state data of the nuclear power plant equipment. Furthermore, based on the adjustment coefficient, the membership value of the dimension data of each dimension, and the corresponding preset weight, use the following algorithm to determine the comprehensive anomaly detection value of the nuclear power plant equipment:

[0039]

[0040] where K represents the comprehensive anomaly detection value of the nuclear power plant equipment; represents the initial comprehensive anomaly detection value; δ represents the adjustment coefficient used to correct the initial comprehensive anomaly detection value; γ i represents the preset weight of the dimension data of the i-th dimension, which is used to reflect the influence degree of this dimension data on the failure of the nuclear power plant equipment; u(i) is the membership value of the dimension data of the i-th dimension; m represents the total number of all dimensions in the current operating state data.

[0041] where the adjustment coefficient is determined by the following algorithm based on the anomaly indication value of the dimension data of each dimension:

[0042]

[0043] where E(i) represents the anomaly indication value of the dimension data of the i-th dimension.

[0044] The anomaly indication value is determined by using the anomaly indication function of the dimension data based on the membership value and membership threshold of the corresponding dimension data, where the anomaly indication function can be expressed as:

[0045]

[0046] Among them, E(i) represents the abnormal indication value of the dimensional data of the i-th dimension, u(i) represents the membership value of the dimensional data of the i-th dimension, and ε represents the membership threshold, which is used to determine whether the dimensional data of the i-th dimension is in a high-abnormal state or a low-abnormal state.

[0047] Through the above technical solution, the membership value of the dimensional data of each dimension is calculated by using the preset membership algorithm, quantifying the degree to which the dimensional data of each dimension approaches the abnormal state, which helps to accurately identify abnormalities; introducing an adjustment coefficient and combining the preset weights of the dimensional data of each dimension, fully considering the contribution differences of different-dimensional data to the abnormalities of nuclear power plant equipment, and further optimizing the calculation of the comprehensive abnormal detection value; thus, not only can key abnormal points be effectively identified, but also the misjudgment of the overall condition of nuclear power plant equipment due to single-dimensional abnormalities can be avoided, ensuring a comprehensive, accurate and efficient assessment of the operating state of nuclear power plant equipment.

[0048] In some embodiments, the preset membership algorithm is expressed as:

[0049]

[0050] Among them, u(i) is the membership value of the dimensional data of the i-th dimension in the current operating state data, representing the degree to which the dimensional data of the i-th dimension approaches the abnormal state; x i represents the dimensional data of the i-th dimension in the current operating state data; c i is the abnormal state reference value of the dimensional data of the i-th dimension, representing the typical value at which the dimensional data of the i-th dimension is considered to be in an abnormal state; a i is the scaling parameter of the dimensional data of the i-th dimension, which is used to control the sensitivity of the membership value to the change of x i and is set according to pre-experiments; b i is the deformation parameter of the dimensional data of the i-th dimension, which is used to determine the non-linear degree of the membership value with respect to the change of x i and is set according to pre-experiments. The accurate calculation of the membership value of the dimensional data of each dimension is realized, laying a foundation for improving the accuracy of abnormal identification of nuclear power plant equipment.

[0051] In some embodiments, determining the target fault cause of the abnormal device based on the received current operating status data and the abnormal indication values within the preset time window includes: based on the current operating status data and the abnormal frequency eigenvalue of the dimension data of each dimension, using a preset fault identification model to determine the comprehensive eigenvalue corresponding to each preset fault cause, where the abnormal frequency eigenvalue is determined based on the abnormal indication values within the preset time window; determining the preset fault cause corresponding to the largest comprehensive eigenvalue as the target fault cause of the abnormal device.

[0052] In this embodiment, the preset fault cause can be understood as the fault cause that is preset and may exist in the nuclear power plant equipment. The preset fault identification model can be understood as a model that is preset and used to determine the comprehensive eigenvalue corresponding to each preset fault cause.

[0053] The abnormal frequency eigenvalue is used to quantify the abnormal occurrence frequency of each dimension within the preset time window. Based on the abnormal indication values within the preset time window, the abnormal frequency eigenvalue is determined through the following algorithm:

[0054]

[0055] where g i represents the abnormal frequency eigenvalue of the dimension data of the i-th dimension, σ represents a preset adjustment coefficient, which is used to control the influence of the abnormal frequency feature on the preset fault identification model and is set through prior experiments; T represents the preset time window, that is, the abnormal detection time window, t represents the time step within T, and E i (t) represents the abnormal indication value of the dimension data of the i-th dimension at the time step t; N is a normalization coefficient, which is set through prior experiments.

[0056] Specifically, for the dimension data of each dimension in the current operating status data, based on the abnormal indication values of the current dimension within the preset time window, calculate the abnormal frequency eigenvalue of the dimension data of the current dimension; furthermore, based on the current operating status data and the abnormal frequency eigenvalues of the dimension data of each dimension, use the preset fault identification model to determine the comprehensive eigenvalue corresponding to each preset fault cause; furthermore, determine the largest comprehensive eigenvalue, and determine the preset fault cause corresponding to the largest comprehensive eigenvalue as the target fault cause of the abnormal device.

[0057] Through this solution, combining real-time operating status data, introducing the abnormal frequency features of the dimension data of each dimension, and taking into account both the abnormal degree of the current operating status data and the frequency of abnormalities in historical data, it is possible to more accurately discover potential fault causes, especially in the case of faults caused by long-term accumulated abnormalities, thereby improving the accuracy and real-time performance of fault cause determination.

[0058] In some embodiments, the preset fault identification model is expressed as:

[0059]

[0060] where G j represents the comprehensive eigenvalue of the preset fault cause j, reflecting the matching degree between the abnormal device and the preset fault cause j; θ i，j represents the influence weight of the dimensional data of the i-th dimension on the preset fault cause j, obtained through machine learning; x i represents the dimensional data of the i-th dimension; f(x i ) represents the feature processing function for x i , representing the degree of abnormality of the dimensional data of the i-th dimension, where f() is set according to the abnormal characteristics of the corresponding dimensional data; represents the abnormal frequency weight of the dimensional data of the i-th dimension, obtained through machine learning; g i is the abnormal frequency eigenvalue of the dimensional data of the i-th dimension.

[0061] where the abnormal characteristics refer to the deviation, trend, fluctuation, frequent abnormality or non-linear characteristics shown when the corresponding dimensional data deviates from its normal range.

[0062] In some embodiments, the device status monitoring method further includes: presenting the maintenance operation suggestions, the current operating status data, and the target fault cause on the user interaction interface through the data center platform, and triggering an alarm mechanism to give an alarm prompt to the user.

[0063] Specifically, the maintenance operation suggestions, the current operating status data, and the target fault cause can be presented on the user interaction interface through the data center platform, and the alarm mechanism is triggered to give an alarm prompt to the user. The alarm mechanism in this embodiment includes, but is not limited to, prompting the user through the interface and giving an alarm prompt through sound, so as to ensure that the user can notice the emergency of the device in time and take quick actions. Through the above solution, the combination of the intuitive display of the abnormal device status and the real-time alarm function is realized, thereby effectively improving the safety and reliability of the operation of nuclear power plant equipment and ensuring the stable operation of the nuclear power plant.

[0064] Embodiment 2

[0065] Figure 2 is a schematic structural diagram of a device status monitoring device provided by Embodiment 2 of the present invention. The device status monitoring device is configured in the nuclear power plant equipment monitoring system, and the nuclear power plant equipment monitoring system includes an edge platform and a data center platform, where the edge platform is deployed on the nuclear power plant equipment side. As Figure 2 shown, the device includes:

[0066] Anomaly detection module 21 is configured to determine a comprehensive anomaly detection value of the nuclear power plant equipment through the edge platform according to the current operating status data of the nuclear power plant equipment. When the comprehensive anomaly detection value is greater than a preset warning threshold, it determines that the nuclear power plant equipment is an abnormal equipment, and sends the target data of the abnormal equipment to the data center platform, where the target data includes the current operating status data and an anomaly indication value within a preset time window;

[0067] Fault generation module 22 is configured to determine the target fault cause of the abnormal equipment through the data center platform based on the received current operating status data and the anomaly indication value within the preset time window, and generate maintenance operation suggestions according to the target fault cause.

[0068] The technical solution provided in the second embodiment of the present invention utilizes an edge platform deployed on the nuclear power plant equipment side to quickly complete the anomaly detection of the nuclear power plant equipment locally. After determining that the nuclear power plant equipment is an abnormal equipment, it sends the target data of the abnormal equipment to the data center platform, thus avoiding transmitting all data to the data center platform for processing and detection, greatly reducing the data transmission delay in the equipment anomaly detection process, and significantly improving the real-time performance of data processing; furthermore, the data center platform determines the target fault cause based on the target data and generates maintenance suggestions, realizing a rapid response to equipment anomalies and effectively improving the fault diagnosis efficiency.

[0069] Optionally, the anomaly detection module 21 is specifically configured to: calculate the membership degree value of the dimension data of each dimension in the current operating status data of the nuclear power plant equipment by using a preset membership degree algorithm, where the membership degree value represents the degree to which the corresponding dimension data approaches the abnormal state; determine the comprehensive anomaly detection value of the nuclear power plant equipment based on an adjustment coefficient, the membership degree value of the dimension data of each dimension, and the corresponding preset weight, where the adjustment coefficient is determined based on the anomaly indication value of the dimension data of each dimension, and the anomaly indication value is determined by using the anomaly indication function of the dimension data based on the membership degree value and the membership degree threshold of the corresponding dimension data.

[0070] Optionally, the preset membership degree algorithm is expressed as:

[0071]

[0072] where u(i) is the membership degree value of the dimension data of the i-th dimension in the current operating status data, representing the degree to which the dimension data of the i-th dimension approaches the abnormal state; x i represents the dimension data of the i-th dimension in the current operating status data; c iis the abnormal state reference value of the dimensional data for the i-th dimension, representing the typical value at which the dimensional data for the i-th dimension is considered to be in an abnormal state; a i is the scaling parameter of the dimensional data for the i-th dimension, used to control the sensitivity of the membership value to the change of x i and is set according to pre-experiments; b i is the deformation parameter of the dimensional data for the i-th dimension, used to determine the non-linear degree of the membership value with respect to the change of x i and is set according to pre-experiments.

[0073] Optionally, the fault generation module 22 is specifically configured to determine the comprehensive eigenvalue corresponding to each preset fault cause based on the current operating state data and the abnormal frequency eigenvalue of the dimensional data of each dimension by using a preset fault identification model, where the abnormal frequency eigenvalue is determined based on the abnormal indication value within the preset time window; and determine the preset fault cause corresponding to the maximum comprehensive eigenvalue as the target fault cause of the abnormal device.

[0074] Optionally, the preset fault identification model is expressed as:

[0075]

[0076] where G j represents the comprehensive eigenvalue of the preset fault cause j, reflecting the matching degree between the abnormal device and the preset fault cause j; θ i，j represents the influence weight of the dimensional data of the i-th dimension on the preset fault cause j, which is obtained through machine learning; x i represents the dimensional data of i dimensions; f(x i ) represents the feature processing function for x i and represents the degree of abnormality of the dimensional data of the i-th dimension, where f() is set according to the abnormal characteristics of the corresponding dimensional data; represents the abnormal frequency weight of the dimensional data of the i-th dimension, which is obtained through machine learning; g i is the abnormal frequency eigenvalue of the dimensional data of the i-th dimension.

[0077] Optionally, the device status monitoring device further includes:

[0078] An alarm prompt module, configured to present the maintenance operation suggestion, the current operating state data, and the target fault cause on the user interaction interface through the data center platform, and trigger an alarm mechanism to give an alarm prompt to the user.

[0079] The device status monitoring device provided by the embodiments of the present invention can execute the device status monitoring method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0080] Embodiment 3

[0081] Figure 3 FIG. is a schematic structural diagram of an electronic device provided in Embodiment 3 of the present invention. The electronic device can be configured as a nuclear power plant equipment monitoring system, and is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0082] As Figure 3 shown, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. The memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0083] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0084] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include but are not limited to a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the device status monitoring method.

[0085] In some embodiments, the device status monitoring method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the device status monitoring method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the device status monitoring method by any other suitable means (e.g., by means of firmware).

[0086] The various implementations of the systems and techniques described above in this document may be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include: being implemented in one or more computer programs that may be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a special-purpose or general-purpose programmable processor that may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0087] The computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer programs may be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine, or entirely on the remote machine or server.

[0088] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0089] To provide for interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can also be used to provide for interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0090] The systems and techniques described herein can be implemented in a computing system that includes backend components (such as, for example, a data server), or a computing system that includes middleware components (such as, for example, an application server), or a computing system that includes frontend components (such as, for example, a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (such as, for example, a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0091] A computing system may include a client and a server. The client and the server are generally far from each other and usually interact via a communication network. The relationship between the client and the server is created by computer programs that run on respective computers and have a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0092] It should be understood that the various forms of processes shown above can be used, steps can be reordered, added or deleted. For example, the steps described in the present invention can be executed in parallel, sequentially or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is made herein.

[0093] The above specific embodiments do not constitute a limitation to the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

[0094] The embodiment of the present invention also provides a computer program product, including a computer program and / or instructions, which when executed by a processor implement the device state monitoring method provided in any embodiment of the present application.

[0095] In the process of implementing the computer program product, computer program code for performing the operations of the present invention can be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network - including a local area network (LAN) or a wide area network (WAN) - or can be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0096] Note that the above is only the preferred embodiment of the present invention and the technical principles applied. Those skilled in the art will understand that the present invention is not limited to the specific embodiments here, and various obvious changes, re-adjustments and substitutions can be made by those skilled in the art without departing from the protection scope of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments. Without departing from the concept of the present invention, more other equivalent embodiments can be included, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A device status monitoring method, characterized in that, Applied to the nuclear power plant equipment monitoring system, the nuclear power plant equipment monitoring system includes an edge platform and a data center platform. Among them, the edge platform is deployed on the side of the nuclear power plant equipment. The method includes: Through the edge platform, according to the current operating status data of the nuclear power plant equipment, determine the comprehensive anomaly detection value of the nuclear power plant equipment. When the comprehensive anomaly detection value is greater than the preset warning threshold, determine that the nuclear power plant equipment is an abnormal equipment, and send the target data of the abnormal equipment to the data center platform, where the target data includes the current operating status data and the anomaly indication value within a preset time window; Through the data center platform, based on the received current operating status data and the anomaly indication value within the preset time window, determine the target failure cause of the abnormal equipment, and generate maintenance operation suggestions according to the target failure cause.

2. The method according to claim 1, characterized in that, The determining the comprehensive anomaly detection value of the nuclear power plant equipment according to the current operating status data of the nuclear power plant equipment includes: Use a preset membership algorithm to calculate the membership value of the dimension data of each dimension in the current operating status data of the nuclear power plant equipment, where the membership value represents the degree to which the corresponding dimension data approaches the abnormal state; Based on the adjustment coefficient, the membership value of the dimension data of each dimension, and the corresponding preset weight, determine the comprehensive anomaly detection value of the nuclear power plant equipment, where the adjustment coefficient is determined based on the anomaly indication value of the dimension data of each dimension, and the anomaly indication value is determined by using the anomaly indication function of the dimension data based on the membership value and the membership threshold of the corresponding dimension data.

3. The method according to claim 2, wherein The preset membership algorithm is expressed as: Among them, u(i) is the membership value of the dimensional data of the i-th dimension in the current operating state data, indicating the degree to which the dimensional data of the i-th dimension approaches the abnormal state; x i represents the dimensional data of the i-th dimension in the current operating state data; c i is the abnormal state reference value of the dimensional data of the i-th dimension, indicating the typical value at which the dimensional data of the i-th dimension is considered to be in an abnormal state; a i is the scaling parameter of the dimensional data of the i-th dimension, used to control the sensitivity of the membership value to the change of x i , and is set according to pre-experiments; b i is the deformation parameter of the dimensional data of the i-th dimension, used to determine the non-linear degree of the membership value with respect to the change of x i , and is set according to pre-experiments.

4. The method according to claim 1, wherein The determining the target failure cause of the abnormal equipment based on the received current operating status data and the anomaly indication value within the preset time window includes: Based on the current operating status data and the anomaly frequency characteristic value of the dimension data of each dimension, use a preset fault identification model to determine the comprehensive characteristic value corresponding to each preset fault cause, where the anomaly frequency characteristic value is determined based on the anomaly indication value within the preset time window; Determine the preset fault cause corresponding to the maximum comprehensive characteristic value as the target failure cause of the abnormal equipment.

5. The method according to claim 4, characterized in that, The preset fault identification model is expressed as: Among them, G j represents the comprehensive characteristic value of the preset fault cause j, reflecting the matching degree between the abnormal device and the preset fault cause j; θ i,j represents the influence weight of the dimension data of the i-th dimension on the preset fault cause j, obtained through machine learning; i Represents the dimensional data of i dimensions; f(x i ) means for x i The feature processing function represents the abnormality degree of the dimension data of the i-th dimension, where f() is set according to the abnormal characteristics of the corresponding dimension data; represents the abnormal frequency weight of the dimension data of the i-th dimension, obtained through machine learning; g i is the abnormal frequency characteristic value of the dimension data of the i-th dimension.

6. The method according to claim 1, wherein It also includes: Through the data center platform, present the maintenance operation suggestions, the current operating status data, and the target failure cause on the user interaction interface, and trigger an alarm mechanism to give an alarm prompt to the user.

7. A device status monitoring device, characterized in that, Configured in the nuclear power plant equipment monitoring system, the nuclear power plant equipment monitoring system includes an edge platform and a data center platform. Among them, the edge platform is deployed on the side of the nuclear power plant equipment. The device includes: Anomaly detection module, configured to determine a comprehensive anomaly detection value of the nuclear power plant equipment through the edge platform according to the current operating status data of the nuclear power plant equipment. When the comprehensive anomaly detection value is greater than a preset warning threshold, determine that the nuclear power plant equipment is an abnormal equipment, and send the target data of the abnormal equipment to the data center platform, where the target data includes the current operating status data and the anomaly indication value within a preset time window; Fault generation module, configured to determine the target fault cause of the abnormal equipment through the data center platform based on the received current operating status data and the anomaly indication value within the preset time window, and generate maintenance operation suggestions according to the target fault cause.

8. An electronic device, characterized in that, The electronic device is configured as a nuclear power plant equipment monitoring system, and the electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the equipment status monitoring method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a processor to implement the equipment status monitoring method according to any one of claims 1-6 when executed.

10. A computer program product, characterized in that, The computer program product includes a computer program that implements the equipment status monitoring method according to any one of claims 1-6 when executed by a processor.

Images