Energy equipment intelligent operation and maintenance method and system based on internet of things driving, and medium

Abstract

The application discloses an energy equipment intelligent operation and maintenance method and system based on Internet of Things driving, relates to the related field of energy equipment operation and maintenance automation control, and comprises the following steps: collecting the energy equipment distribution topology in a preset area; performing fault diffusion fitting on each energy equipment, including diffusion from the minimum fault degree to the maximum fault degree, and generating each fault diffusion path; identifying diffusion convergence points and performing global fusion; performing bottom-up multi-layer monitoring system configuration based on the global diffusion path through the Internet of Things technology, performing energy equipment operation monitoring, and generating target monitoring information; and performing operation and maintenance management of the fault equipment according to the target monitoring information. The technical problems that potential faults cannot be found in time, fault diffusion trends cannot be accurately predicted, and global operation and maintenance strategies cannot be efficiently formulated in the existing energy equipment operation and maintenance are solved, and the technical effects that potential faults can be found in time, fault diffusion trends can be accurately predicted, and global operation and maintenance strategies can be efficiently formulated are achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of energy equipment operation and maintenance automation control, in particular to an energy equipment intelligent operation and maintenance method and system based on Internet of Things driving and a medium. BACKGROUND

[0002] The stable operation of energy equipment is crucial for ensuring energy supply safety, improving energy utilization efficiency, and maintaining social production and life order, and effective operation and maintenance management is a key link to ensure the reliable operation of energy equipment. At present, the main method to solve the problem of energy equipment operation and maintenance management is to monitor and troubleshoot the operation state of energy equipment through artificial regular inspection combined with a single level monitoring system. In the current method, artificial inspection has poor timeliness, limited coverage and is easily affected by subjective factors, and a single level monitoring system is difficult to comprehensively capture the complex fault correlation between devices.

[0003] At present, in the related technology, there are technical problems of energy equipment operation and maintenance that cannot timely discover potential faults, accurately predict fault diffusion trends, and efficiently formulate global operation and maintenance strategies. SUMMARY

[0004] The present application provides an energy equipment intelligent operation and maintenance method, system and medium based on Internet of Things driving, which collects the distribution topology of energy equipment in a preset area, simulates the diffusion of each device from the minimum to the maximum fault degree, generates all possible fault propagation paths, performs global fusion analysis by identifying the intersection convergence points of these paths, forms a comprehensive fault influence map, and based on this map, a multi-layer monitoring system from the bottom equipment to the upper system is constructed through Internet of Things technology, the device operation state is monitored in real time and monitoring data is generated, the fault equipment is located according to the monitoring information, and technical means such as operation and maintenance management are implemented, which solves the technical problems of existing energy equipment operation and maintenance that cannot timely discover potential faults, accurately predict fault diffusion trends, and efficiently formulate global operation and maintenance strategies, and achieves the technical effects of timely discovering potential faults, accurately predicting fault diffusion trends, and efficiently formulating global operation and maintenance strategies.

[0005] The present application provides an energy equipment intelligent operation and maintenance method based on Internet of Things driving, which includes: collecting the distribution topology of energy equipment in a preset area; performing fault diffusion fitting on each energy equipment in the energy equipment distribution topology, including diffusion from the minimum fault degree to the maximum fault degree, generating each fault diffusion path; identifying diffusion convergence points for each fault diffusion path, performing global fusion, and generating global diffusion paths; based on the global diffusion paths, configuring a multi-layer monitoring system from the bottom to the top through Internet of Things technology, using the multi-layer monitoring system to perform energy equipment operation monitoring in the preset area, generating target monitoring information; and performing operation and maintenance management of fault equipment according to the target monitoring information.

[0006] In a possible implementation, the fault diffusion fitting of each energy device in the energy device distribution topology includes diffusion from a minimum fault degree to a maximum fault degree, each fault diffusion path is generated, and the following processing is performed: integrated modeling of energy devices and connection relationships is performed based on the energy device distribution topology, and a device integrated twin is constructed; a first energy device in the each energy device is extracted; the device integrated twin is invoked, fault diffusion simulation of the first energy device from a minimum fault degree to a maximum fault degree is performed, and a first fault diffusion path is generated; and the first fault diffusion path is added to the each fault diffusion path.

[0007] In a possible implementation, the fault diffusion fitting of each energy device in the energy device distribution topology includes diffusion from a minimum fault degree to a maximum fault degree, each fault diffusion path is generated, and the following processing is performed: integrated modeling of energy devices and connection relationships is performed based on the energy device distribution topology, and a device integrated twin is constructed; a first energy device in the each energy device is extracted; the device integrated twin is invoked, fault diffusion simulation of the first energy device from a minimum fault degree to a maximum fault degree is performed, and a first fault diffusion path is generated; and the first fault diffusion path is added to the each fault diffusion path.

[0008] In a possible implementation, the fault diffusion fitting of each energy device in the energy device distribution topology includes diffusion from a minimum fault degree to a maximum fault degree, each fault diffusion path is generated, and the following processing is performed: integrated modeling of energy devices and connection relationships is performed based on the energy device distribution topology, and a device integrated twin is constructed; a first energy device in the each energy device is extracted; the device integrated twin is invoked, fault diffusion simulation of the first energy device from a minimum fault degree to a maximum fault degree is performed, and a first fault diffusion path is generated; and the first fault diffusion path is added to the each fault diffusion path.

[0009] In a possible implementation, the fault diffusion fitting of each energy device in the energy device distribution topology includes diffusion from a minimum fault degree to a maximum fault degree, each fault diffusion path is generated, and the following processing is performed: integrated modeling of energy devices and connection relationships is performed based on the energy device distribution topology, and a device integrated twin is constructed; a first energy device in the each energy device is extracted; the device integrated twin is invoked, fault diffusion simulation of the first energy device from a minimum fault degree to a maximum fault degree is performed, and a first fault diffusion path is generated; and the first fault diffusion path is added to the each fault diffusion path.

[0010] In a possible implementation, based on the global diffusion path, a bottom-up multi-layer monitoring system is configured through Internet of Things technology, and the following processing is performed: similar merging of diffusion characteristics of adjacent diffusion nodes according to the global diffusion path is performed to generate an updated diffusion path; feature screening based on diffusion identification contribution is performed on each diffusion node based on the updated diffusion path to generate a monitoring demand path; diffusion characteristic relationship modeling is performed based on the updated diffusion path and the monitoring demand path to construct a fault diffusion analysis model; and the Internet of Things architecture is configured based on the Internet of Things technology, connected with the fault diffusion analysis model, and the multi-layer monitoring system is generated.

[0011] In a possible implementation, the multi-layer monitoring system is used to perform energy equipment operation monitoring in the preset area to generate target monitoring information, and the following processing is performed: each energy equipment is monitored in real time using the Internet of Things architecture, and each monitoring data is sent to the fault diffusion analysis model for analysis to generate the target monitoring information; wherein the fault diffusion analysis model includes a fault source, a fault type and a fault severity of the fault source, and a fault type and a fault severity of a fault diffusion node.

[0012] In a possible implementation, according to the target monitoring information, the operation and maintenance of the fault equipment is performed, and the following processing is performed: fault operation and maintenance record data is collected, and the operation and maintenance relationship between the source node and the diffusion node under fault diffusion is analyzed based on the global diffusion path to construct a fault diffusion operation and maintenance graph; the fault source, the fault diffusion node, the fault type and the fault severity of the fault source, and the fault type and the fault severity of the fault diffusion node in the target monitoring information are input into the fault diffusion operation and maintenance graph for operation and maintenance strategy matching to generate a target operation and maintenance strategy; and the operation and maintenance of the fault equipment is performed based on the target operation and maintenance strategy.

[0013] The application also provides an energy equipment intelligent operation and maintenance system driven by Internet of Things, comprising: an energy equipment distribution topology collection module, configured to collect energy equipment distribution topology in a preset area; a fault diffusion fitting module, configured to perform fault diffusion fitting on each energy equipment in the energy equipment distribution topology, including diffusion from the minimum fault degree to the maximum fault degree, to generate each fault diffusion path; a global fusion module, configured to identify diffusion convergence points for the each fault diffusion path, perform global fusion, and generate a global diffusion path; an energy equipment operation monitoring module, configured to configure a bottom-up multi-layer monitoring system through Internet of Things technology based on the global diffusion path, perform energy equipment operation monitoring in the preset area using the multi-layer monitoring system, and generate target monitoring information; and a fault operation and maintenance module, configured to perform operation and maintenance of fault equipment according to the target monitoring information.

[0014] The application also provides a computer readable storage medium, comprising: a computer program stored thereon, which is executed by a processor to implement the energy equipment intelligent operation and maintenance method based on Internet of Things driving.

[0015] The energy equipment intelligent operation and maintenance method, system and medium based on Internet of Things driving provided by the application first collect the energy equipment distribution topology in a preset area, then perform fault diffusion fitting on each energy equipment in the energy equipment distribution topology, including diffusion from the minimum fault degree to the maximum fault degree, generate each fault diffusion path, then identify diffusion convergence points for the each fault diffusion path, perform global fusion, generate a global diffusion path, then perform bottom-up multi-layer monitoring system configuration based on the global diffusion path through Internet of Things technology, use the multi-layer monitoring system to perform energy equipment operation monitoring in the preset area, generate target monitoring information, and finally perform operation and maintenance management of fault equipment according to the target monitoring information. The technical effects of timely discovering potential faults, accurately predicting fault diffusion trends and efficiently formulating global operation and maintenance strategies are achieved. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the application, the drawings of the embodiments of the application will be briefly introduced below. The flowcharts are used to illustrate the operations performed by the system according to the embodiments of the application in the present application. It should be understood that the foregoing or the following operations are not necessarily performed in sequence. On the contrary, various steps can be processed in reverse order or at the same time according to needs. Meanwhile, other operations can be added to these processes, or one or more steps of operations can be removed from these processes.

[0017] Figure 1 The flowchart of the energy equipment intelligent operation and maintenance method based on Internet of Things driving provided by the embodiments of the application.

[0018] Figure 2 The structure diagram of the energy equipment intelligent operation and maintenance system based on Internet of Things driving provided by the embodiments of the application.

[0019] Legend: energy equipment distribution topology collection module 10, fault diffusion fitting module 20, global fusion module 30, energy equipment operation monitoring module 40, fault operation and maintenance management module 50. DETAILED DESCRIPTION

[0020] The above description is only a summary of the technical solutions of the application. In order to more clearly understand the technical means of the application, the embodiments of the application can be implemented according to the content of the specification, and in order to make the above and other purposes, characteristics and advantages of the application more obvious and easy to understand, the following specific embodiments of the application are described.

[0021] In order to make the purposes, technical solutions and advantages of the present application clearer, the following will further describe the present application in detail with reference to the drawings, and the described embodiments should not be regarded as limitations to the present application. All other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0022] In the following description, "some embodiments" are referred to, which describe a subset of all possible embodiments, but it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict. The term "first\second" referred to only distinguishes similar objects, and does not represent a specific order of the objects. The terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or server including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or modules not clearly listed or inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as understood by those skilled in the art to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application.

[0023] The embodiments of the present application provide an energy equipment intelligent operation and maintenance method based on Internet of Things driving, as shown in the following Figure 1 The method comprises the following steps:

[0024] In step S100, the energy equipment distribution topology in a preset area is collected.

[0025] Specifically, the energy equipment distribution topology refers to a collection of physical locations, connection relationships, hierarchical structures and other information of energy equipment in a preset area, which represents the distribution and mutual relationship between devices in the form of a graph or data structure. First, sensor nodes are installed in the preset area, which can sense the information of the surrounding environment and devices; at the same time, RFID tags are installed for energy equipment, and the identity information of the equipment is collected through the RFID reader. Then, the equipment is positioned by using GPS, and all the collected information is transmitted back to the central control system to generate an energy equipment distribution topology graph through topology construction.

[0026] For example, in a large wind farm, sensors with GPS modules and RFID tags are installed on each wind turbine generator, sensor nodes are deployed around the wind farm, and the position, running state and other information of the wind turbine generator are collected to construct the energy equipment distribution topology of the entire wind farm, and the geographical position and mutual connection relationship of each wind turbine are determined.

[0027] Step S200, fault diffusion fitting is performed on each energy device in the energy device distribution topology, including diffusion from the minimum fault degree to the maximum fault degree, to generate each fault diffusion path.

[0028] Specifically, fault diffusion fitting refers to simulating and fitting the possible propagation process of faults between energy devices through mathematical models and algorithms, to predict the diffusion trend and path of faults from small to large. Simulation techniques, probability models, or numerical simulation methods can be used to fit the fault diffusion path of energy devices.

[0029] For example, if simulation is used, a virtual model of the energy device is established, different initial conditions and system parameters of the fault are set, and the propagation process of the fault between devices is simulated. At each time step, the range and degree of the fault are recorded, and the fault diffusion path is generated. For example, in a power system, simulation models of devices such as transformers and transmission lines are created, fault types (such as short circuits, overloads, etc.) and fault locations are set, and the propagation of the fault in the power grid is observed. The size and direction of the fault current are recorded, and the fault diffusion path is formed.

[0030] If a probability model is used, historical fault data needs to be analyzed to calculate the probability of fault propagation between devices. According to the connection relationship and fault correlation of the devices, a probability matrix is constructed, and Markov chain and other methods are used to derive the fault diffusion path and its likelihood. For example, in a gas supply network, the fault history of devices such as gas pipelines and valves is counted, the probability of fault propagation between adjacent devices is determined, a probability model is established, and the path that the fault may spread from a leak point to other devices is predicted.

[0031] If numerical simulation is used, based on the physical properties and operating principles of the devices, numerical calculation methods are used to solve differential equations or difference equations that describe fault diffusion. This method can more accurately simulate the dynamic process of fault diffusion. For example, in an industrial cooling system, numerical simulation is performed on the cooling liquid leakage fault, fluid mechanics equations are calculated, factors such as the pressure, flow rate, and pipe geometry of the leakage point are considered, and the path and speed of the cooling liquid leakage diffusion are simulated.

[0032] In a possible implementation, the fault diffusion fitting of each energy device in the energy device distribution topology is performed, including diffusion from the minimum fault degree to the maximum fault degree, to generate each fault diffusion path, and step S200 further includes step S210 of performing integrated modeling of energy devices and connection relationships based on the energy device distribution topology to construct a device integrated twin. Specifically, various data of the energy devices are acquired, such as device models, parameters, geographic positions, connection ports, and the like. A virtual model of each energy device is constructed according to the data by using a digital twin modeling tool (such as a 3D modeling software, a physics engine, or the like), and the virtual models are connected in a virtual space according to actual connection relationships to form a complete device integrated twin.

[0033] For example, taking a solar power station as an example, the solar panels, inverters, transformers, power transmission lines, and the like in the power station are integrated modeled. The accurate size and position information of the devices are acquired by laser scanning and sensor measurement, the 3D models of each device are created by using a modeling software, and the 3D models are connected according to the circuit connection relationships to form a device integrated twin that completely corresponds to the actual power station. In the twin, the running states of each device, such as the power generation power of the solar panels, the conversion efficiency of the inverters, the temperature of the transformers, and the like, and the energy flow conditions between the devices can be monitored in real time.

[0034] Step S220 extracts a first energy device in the energy devices. Specifically, according to a preset condition or rule (such as the importance of the device, the fault frequency, the position, or the like), the energy device that needs to be simulated for fault diffusion, that is, the first energy device, is found and extracted from the database or list of the energy device distribution topology by using the device identifier, the position information, the device type, and the like. For example, the device with the most fault history records, the device located on a key energy transmission path, or the device with an abnormal recent running state can be selected as the first energy device.

[0035] Step S230, call the device integration twin, simulate the fault propagation of the first energy device from the minimum fault degree to the maximum fault degree, and generate the first fault propagation path. Specifically, in the simulation environment of the device integration twin, different fault degrees from slight to severe are applied to the first energy device by selecting fault injection methods (such as modifying device parameters, adding fault events, etc.). Then start the simulation program and let the fault propagate in the virtual model. During the simulation, the state changes of each device are monitored in real time, and the propagation path, influence range and time sequence of the fault are recorded. When the simulation is completed, the first fault propagation path is generated according to the recorded data, including the propagation order of the fault between devices, the influence degree, etc. For example, in the device integration twin, the output voltage parameter of the first energy device (transformer) is modified to simulate the fault, and the influence of the fault on the power transmission line, power distribution cabinet and other related devices connected thereto is observed, and the entire fault propagation process is recorded.

[0036] Step S240, add the first fault propagation path to each fault propagation path. Specifically, the data format of the first fault propagation path is standardized to ensure consistency with the data format of other fault propagation paths. Then, select a data storage location (such as a database table, file system, etc.) to add the first fault propagation path to the data set that stores each fault propagation path. During the addition process, the relevant index, relationship and other data structures need to be updated to facilitate subsequent unified management and query of all fault propagation paths.

[0037] For example, in the energy management database of the data center, there is a table specifically for storing fault propagation paths. When a new first fault propagation path is generated, the data of the path is arranged according to the requirements of the table fields, including fault device name, fault propagation order, affected device list, fault impact degree, etc. Then, through the database insertion operation, this new fault propagation path is added to the table together with other fault propagation paths, facilitating subsequent comprehensive analysis and query of the fault propagation of the data center energy devices.

[0038] This implementation method can accurately reflect the actual situation of energy devices and their connection relationships by modeling based on the topology of energy device distribution and constructing a device integration twin. On this basis, the fault propagation simulation of the first energy device can more realistically simulate the propagation process of the fault in the actual system, avoiding the errors caused by model simplification or inaccuracy in traditional simulation methods.

[0039] In one possible implementation, the device integration twin is called to perform a fault propagation simulation of the first energy device from a minimum fault level to a maximum fault level, generating a first fault propagation path, and step S230 further includes step S231 of collecting a historical fault record data set of the first energy device. Specifically, a unique identifier of the first energy device is determined, and all fault records of the device are extracted from a device fault database using a device management system or database query statement, including fault time, fault type, fault severity, maintenance record, and other related information. At the same time, operating parameter data of the device at the time of the fault (such as temperature, pressure, current, etc. recorded by sensors) is collected, and these data are associated with the fault records to be arranged into a structured data set to obtain the historical fault record data set.

[0040] For example, in a wind turbine device management system of a wind farm, the historical fault records of a wind turbine are queried according to the number of the wind turbine, including fault codes, occurrence times, maintenance times, and other information, and operating parameter data at the time of the fault, such as rotational speed, power generation power, and environmental wind speed, are extracted from a SCADA (Supervisory Control And Data Acquisition) system of the wind turbine to be integrated together to form a historical fault record data set.

[0041] Step S232 analyzes the fault level of each piece of data in the historical fault record data set to determine a first fault event corresponding to a minimum fault level and a second fault event corresponding to a maximum fault level. Specifically, a quantitative indicator and grading standard of the fault level are defined. For example, the fault level can be divided into several levels such as slight fault, general fault, severe fault, and major fault according to factors such as the output power drop ratio of the device, the fault repair time, and the impact of the fault on the service life of the device. Then, for each piece of data in the historical fault record data set, relevant fault feature parameters (such as the output power of the device at the time of the fault and the fault repair time) are extracted, and a data analysis algorithm (such as clustering analysis, regression analysis, etc.) or a fault diagnosis model (such as a fault diagnosis model based on a decision tree) is used to evaluate and grade the fault level. Finally, the fault with the lowest fault level is found as the first fault event, and the fault with the highest fault level is found as the second fault event.

[0042] For example, when analyzing the historical fault records of a power transmission line, the fault level is evaluated according to the power outage range and power outage time caused by the fault. Through statistical analysis, it is determined that a fault that only affects a small number of users and has a short power outage time is the first fault event of the minimum fault level, and a fault that causes a large area power outage and has a long power outage time is the second fault event of the maximum fault level.

[0043] Step S233, call the device integration twin, load the first fault event until evolution to the second fault event, read the diffusion path of the first fault event to the second fault event, and generate the first fault diffusion path. Specifically, in the simulation environment of the device integration twin, load the relevant parameters of the first fault event (such as the operating state of the device when the fault occurs, the fault characteristic parameters, etc.) as the initial conditions of the simulation. Then start the simulation program and let the fault start to spread in the twin. During the simulation, the state changes of each device in the device integration twin are continuously monitored, and the propagation path, impact range and state evolution process of each device of the fault are recorded. When the simulation reaches the state of the second fault event (such as the device completely stops running, the fault parameter reaches the set severity, etc.), stop the simulation. According to the recorded data, generate the first fault diffusion path, including the order of fault propagation, the list of affected devices, the fault state change of each device, etc.

[0044] For example, taking a reaction kettle in chemical production as an example, in the historical fault record, it is determined that the first fault event is a slight overload fault of the stirring motor of the reaction kettle (the motor current slightly exceeds the rated value, but can still maintain operation), and the second fault event is that the stirring motor is completely burned out, causing the reaction kettle to stop stirring, and causing a serious fault of abnormal reaction of chemical materials. In the device integration twin, load the motor overload parameters of the first fault event (such as increase the set value of the motor load current), start the fault diffusion simulation. It is observed that during the simulation process, the motor overload causes the motor temperature to gradually rise, which in turn affects the material temperature and stirring effect in the reaction kettle. With the evolution of the fault, the insulation performance of the motor decreases, and finally the burning of the motor is simulated, and the diffusion path of the fault in the reaction kettle system is recorded, such as the order and degree of influence from the stirring motor to the temperature control system of the reaction kettle, to the material conveying system, etc., to generate a detailed first fault diffusion path.

[0045] This implementation mode determines the fault events corresponding to the minimum and maximum fault degrees by collecting and analyzing the historical fault record data set of the first energy device, so that the fault diffusion simulation has clear and actual data-based starting and ending conditions. Compared with theoretical assumptions or simple fault scene construction, this method is closer to the actual operation of the device and can more accurately simulate the diffusion process of the fault at different degrees.

[0046] In a possible implementation, the fault degree analysis is performed on each piece of data in the historical fault record data set, the first fault event corresponding to the minimum fault degree is determined, and the second fault event corresponding to the maximum fault degree is determined, and step S232 further includes step S2321 of extracting the fault influence range and the fault loss from each piece of data in the historical fault record data set, performing normalization processing, and then performing weighted fusion to obtain a fault degree label set. Specifically, the fault influence range (such as the number of affected devices, the size of the affected area, the number of affected users, etc.) and the fault loss (such as economic loss, production loss, time loss, etc.) related data of each fault record in the historical fault record data set are extracted. Then, the data is normalized to unify the numerical range to a specified interval (such as [0, 1]). According to the importance of the fault influence range and the fault loss in evaluating the fault degree, corresponding weights are respectively given, and the normalized fault influence range and fault loss are fused and calculated by weighted fusion to obtain the fault degree label of each fault record. All fault degree labels are sorted into a fault degree label set.

[0047] For example, in a server device of a data center, the number of servers affected by each fault record (fault influence range) and the service downtime and economic loss caused by the fault (fault loss) are extracted from the historical fault record. After Min-Max normalization processing is performed on these data, according to the business continuity requirement and the economic cost factor, linear weighted fusion is performed by giving the fault influence range a weight of 60% and the fault loss a weight of 40% to obtain the fault degree label of each fault record and form a fault degree label set.

[0048] Step S2322, using the mapping relationship between the fault degree label set and the historical fault record data set, selects the first fault event corresponding to the minimum fault degree. Specifically, an index or mapping table is established between the fault degree label set and the historical fault record data set, and the position or identifier of the historical fault record corresponding to each fault degree label is recorded. Then, the fault degree label set is sorted, and the fault degree label with the smallest value is found. The historical fault record corresponding to the label is obtained as the first fault event through the mapping relationship.

[0049] For example, in the device fault database, the fault degree label field is associated with the primary key ID of the fault record, the fault degree labels are sorted in ascending order through an SQL query statement, and the fault record corresponding to the record with the smallest label value is selected as the first fault event.

[0050] Step S2323, with the first fault event as the diffusion source, screening the fault events corresponding to the maximum fault degree in the historical fault record dataset corresponding to the same diffusion source to generate a second fault event. Specifically, the diffusion source characteristics of the first fault event are determined, such as the number of fault equipment, the physical location of fault occurrence, fault type, etc. With these characteristics as query conditions, screening is performed in the historical fault record dataset to obtain a subset of fault records with the same diffusion source characteristics. In this subset, according to the size of the fault degree label, the fault record with the largest fault degree label is selected as the second fault event.

[0051] For example, in the transmission line fault record dataset of the power system, the first fault event is that a certain transmission line fails due to slight insulator contamination fault, resulting in partial discharge. With the transmission line number and insulator contamination fault type as query conditions, all records of faults related to the same transmission line and insulator contamination are screened out, and then the fault record with the largest fault degree label (such as the fault record of insulator complete breakdown leading to transmission line outage) is selected as the second fault event.

[0052] This implementation generates a fault degree label set by extracting fault impact range and fault loss information, normalizing and weighting fusion, making the evaluation of fault degree more scientific, quantitative and standardized, and solving the problem of strong subjectivity and lack of unified standard in previous fault degree evaluation. The first fault event is used as the diffusion source to screen out the second fault event, ensuring the continuity and integrity of fault diffusion simulation under the same fault source.

[0053] Step S300, for each fault diffusion path, identifying diffusion convergence points, global fusion, and generating a global diffusion path.

[0054] Specifically, the diffusion convergence point refers to the node or area where multiple fault diffusion paths intersect or jointly affect in multiple fault diffusion paths, which is usually a key node of fault diffusion and plays an important role in the propagation and impact range of faults. The global diffusion path refers to the fault diffusion path diagram in the entire system generated by integrating each fault diffusion path, which comprehensively reflects the propagation direction, impact range and key nodes of the fault in the system, etc.

[0055] Each fault diffusion path is converted into a graph structure, with nodes representing equipment or key locations and edges representing fault propagation paths and strengths. Cluster analysis is performed on the nodes in the graph using a clustering algorithm to find nodes that frequently appear in multiple paths as diffusion convergence points. Then, through data fusion algorithm, the information of each path is integrated, and factors such as fault propagation probability and impact range are considered to generate a global diffusion path diagram.

[0056] In one possible implementation, for each fault diffusion path, a diffusion convergence point is identified, global fusion is performed, and a global diffusion path is generated. Step S300 further includes step S310, in which the same diffusion nodes are identified after aligning the various fault diffusion paths with diffusion nodes as alignment elements, to obtain a first diffusion convergence point, a second diffusion convergence point, and an Nth diffusion convergence point. Specifically, each fault diffusion path is converted into a graph structure, in which nodes contain unique identifiers (such as device numbers), location information, device types, and other attributes of devices, and edges represent the direction and weight (such as propagation probability or propagation time) of fault propagation. By using device numbers, location information, and the like as alignment elements, the nodes in different fault diffusion paths are aligned to ensure that the same devices or locations are represented in the same way in different paths. Using a node matching algorithm in graph theory, the node attributes in different graph structures are compared to identify the same nodes. For example, by comparing device numbers and location information, the same device nodes in different fault diffusion paths are determined. All nodes in the fault diffusion paths are scanned to count the frequency of each node appearing in different paths. Nodes with a higher frequency are identified as diffusion convergence points, and are ranked according to the frequency or importance to obtain a first diffusion convergence point, a second diffusion convergence point, and an Nth diffusion convergence point.

[0057] Step S320, the various fault diffusion paths are connected at multiple levels with the first diffusion convergence point, the second diffusion convergence point, and the Nth diffusion convergence point as connection points, to generate the global diffusion path. Specifically, according to the ranking (such as frequency or importance) of the diffusion convergence points, the priority of connection is determined. Diffusion convergence points with a higher frequency are connected first. Starting from the first diffusion convergence point, the part of each fault diffusion path connected to the convergence point is fused. Then, the second diffusion convergence point is processed in turn until the Nth diffusion convergence point, and all fault diffusion paths are gradually connected. In the fusion process, the hierarchical structure of the path is maintained to ensure that the fault propagation relationship at each level is clear. For example, the bottom layer represents device-level propagation, the middle layer represents system-level propagation, and the top layer represents global-level propagation.

[0058] This implementation can generate a comprehensive global diffusion path by identifying diffusion convergence points and connecting various fault diffusion paths at multiple levels. This enables operation and maintenance personnel to clearly understand the overall propagation pattern of faults in the energy system, rather than being limited to the fault propagation of a single device or a local area.

[0059] Step S400, based on the global diffusion path, a bottom-up multi-layer monitoring system configuration is performed through Internet of Things technology, and the multi-layer monitoring system is used to perform energy device operation monitoring in the preset area to generate target monitoring information.

[0060] Specifically, the Internet of Things technology is a technology that realizes the interconnection and intercommunication between things and people through the architecture of the perception layer, the network layer and the application layer, and the use of sensor, communication network, cloud computing and other technical means, which can realize real-time monitoring, control and management of energy equipment. According to the global diffusion path, the key monitoring points and monitoring parameters are determined, and corresponding sensors and intelligent instruments such as temperature sensors, pressure sensors and vibration sensors are installed on the energy equipment to collect real-time operation data of the equipment. A data transmission network is set up, and appropriate communication technology is selected to transmit the data of the perception layer to the monitoring and management platform of the application layer. In the platform, the collected data is processed and analyzed, threshold alarm, fault diagnosis and other functional modules are set, and a multi-layer monitoring system from bottom to top is formed. The multi-layer monitoring system is a hierarchical monitoring architecture composed of data collection in the perception layer, data transmission in the network layer and data processing and analysis in the application layer, which can monitor the energy equipment in all directions and multiple levels, and provide monitoring information and decision support at different levels. The target monitoring information refers to the key information about the running state of the energy equipment obtained after the multi-layer monitoring system collects, processes and analyzes the data, including the running parameters, fault alarm information and performance indicators of the equipment, which can provide the basis for the operation and maintenance management of the faulty equipment.

[0061] In a possible implementation, the multi-layer monitoring system from bottom to top is configured based on the global diffusion path through the Internet of Things technology, and step S400 further includes step S410 of performing similarity merging of diffusion characteristics of adjacent diffusion nodes according to the global diffusion path to generate an updated diffusion path. Specifically, the diffusion characteristic vector of each diffusion node is extracted from the global diffusion path, and the vector contains information of multiple diffusion characteristic dimensions such as fault propagation speed, propagation probability and influence range. The similarity between adjacent diffusion nodes is calculated by using a similarity measurement method such as Euclidean distance or cosine similarity. According to the similarity result, adjacent diffusion nodes with a similarity higher than a certain threshold are divided into a cluster, and a merged node is used to represent the cluster. The diffusion characteristics of the merged node are the weighted average or other fusion of the characteristics of all nodes in the cluster. The merged node replaces the original adjacent node to generate the updated diffusion path.

[0062] Step S420, based on the update diffusion path, each diffusion node is screened based on the diffusion recognition contribution degree of the feature, and the monitoring demand path is generated. Specifically, the diffusion characteristics of each diffusion node in the update diffusion path are trained by using a machine learning model to obtain the importance score of each feature. This score reflects the contribution degree of the feature to distinguishing different fault diffusion modes. According to the actual demand, a contribution degree threshold is set to retain the top certain proportion (such as the top 20%-30%) of features with high contribution degree. The diffusion characteristics of each diffusion node are screened, and the features with a contribution degree lower than the threshold are removed, and the high-contribution-degree features are retained. The monitoring demand path is reconstructed according to the screened features, and the path only contains the feature information critical to fault diffusion identification.

[0063] For example, taking the smart grid as an example, each node in the update diffusion path has multiple diffusion characteristics, including fault voltage fluctuation amplitude, current mutation rate, power drop speed, etc. By training a random forest model to evaluate these features, it is found that the feature importance scores of fault voltage fluctuation amplitude and power drop speed are higher, and the score of current mutation rate is lower. The contribution degree threshold is set to the top 20% of features, and only the fault voltage fluctuation amplitude and power drop speed are retained. Then, the monitoring demand path is reconstructed according to these screened features, which focuses more on the features critical to fault diffusion identification and reduces the redundancy of monitoring information.

[0064] Step S430, based on the update diffusion path and the monitoring demand path, the diffusion feature relationship modeling is performed, and the fault diffusion analysis model is constructed. Specifically, the diffusion feature data in the update diffusion path and the monitoring demand path are collected, including historical fault data and normal operation data. According to the data characteristics and actual demand, a suitable modeling method is selected, such as a statistical modeling method or a machine learning modeling method, the data is divided into a training set and a test set, the training set is used to train the model, and the model parameters are adjusted to optimize the performance. The test set is used to verify the trained model, and the accuracy, recall rate and other indicators of the model are evaluated. According to the verification result, the model is optimized, such as adjusting the model structure, adding a regularization term, etc. The verified model is deployed as a fault diffusion analysis model for real-time or near-real-time fault diffusion analysis.

[0065] Step S440, based on the Internet of Things technology, configure the Internet of Things architecture based on the monitoring demand path, connect with the fault diffusion analysis model, and generate the multi-layer monitoring system. Specifically, according to the diffusion characteristics in the monitoring demand path, deploy sensors and intelligent monitoring devices at the corresponding diffusion nodes. These devices are responsible for collecting device operation data such as temperature, pressure, voltage, etc. Select appropriate communication technologies (such as wired Ethernet, wireless Wi-Fi, ZigBee, etc.) to build a network layer to transmit the data collected by the perception layer to the application layer. In the process of data transmission, data fusion technology can be used to fuse data from multiple sensors. Deploy the fault diffusion analysis model and the monitoring management platform at the application layer. The monitoring management platform is used to visualize the monitoring data and analysis results, and provides fault alarm and operation and maintenance decision support. Use middleware technology to seamlessly connect the Internet of Things architecture and the fault diffusion analysis model. Middleware is responsible for data conversion, protocol adaptation and message passing, ensuring that data can be smoothly transmitted from Internet of Things devices to analysis models, and the analysis results of the model are fed back to the monitoring management platform.

[0066] This implementation can accurately determine the diffusion nodes and features that need to be monitored by similar merging the diffusion characteristics of adjacent diffusion nodes and feature screening based on contribution degree, avoiding the blindness of deploying a large number of monitoring resources on all nodes, and reducing the monitoring cost. The fault diffusion analysis model constructed based on the updated diffusion path and the monitoring demand path can more accurately analyze the fault diffusion trend. The model can more timely discover potential faults and predict their propagation paths using screened and fused diffusion characteristics.

[0067] In one possible implementation, the multi-layer monitoring system is used to perform energy equipment operation monitoring in the preset area to generate target monitoring information. Step S400 further includes step S450, using the Internet of Things architecture to perform real-time monitoring on each energy equipment, sending each monitoring data to the fault diffusion analysis model for analysis to generate the target monitoring information, wherein the fault diffusion analysis model includes fault sources, fault types and fault severity of the fault sources, and fault types and fault severity of the fault diffusion nodes.

[0068] Specifically, the Internet of Things sensors installed on various energy equipment collect real-time equipment operation data and perform preliminary preprocessing (such as data cleaning, format conversion, etc.) to ensure the accuracy and consistency of the data. Through the selected communication protocol, the preprocessed monitoring data is sent in real time to the server or cloud computing platform where the fault diffusion analysis model is located. In this process, the data can be encrypted and compressed to improve the security and efficiency of data transmission. After receiving the monitoring data, the fault diffusion analysis model uses its internal algorithms and parameters to analyze the data. The model first identifies whether there is a fault source, and if there is, further determines the fault type (such as short circuit, overload, leakage, etc.) and severity (such as minor fault, severe fault, etc.) of the fault source. At the same time, the model also analyzes the fault type and severity of the fault diffusion nodes to evaluate the possible diffusion path and impact range of the fault. According to the analysis results of the model, target monitoring information is generated, including the running state evaluation of the equipment, fault warning, fault location and type, etc. These information is displayed to the operation and maintenance personnel through the monitoring management platform in a graphical interface, or timely notified to the relevant personnel in the form of alarm messages.

[0069] Step S500, according to the target monitoring information, the operation and maintenance management of the fault equipment is carried out.

[0070] Specifically, when the monitoring system issues a fault alarm, according to the severity of the fault and the importance of the equipment, the predictive maintenance technology is used to develop maintenance plans and strategies. For some devices that can be remotely operated, remote maintenance or parameter adjustment is performed through automated control technology; for devices that need on-site maintenance, operation and maintenance personnel are dispatched to carry out maintenance on site with necessary tools and spare parts, and the maintenance situation is recorded in the operation and maintenance management system.

[0071] In one possible implementation, according to the target monitoring information, the operation and maintenance management of the fault equipment is carried out, step S500 further includes step S510, collecting fault operation and maintenance record data, analyzing the operation and maintenance relationship between the source nodes and the diffusion nodes under fault diffusion based on the global diffusion path, and constructing a fault diffusion operation and maintenance map. Specifically, fault operation and maintenance record data is extracted from multiple data sources such as equipment management system, operation and maintenance work order system, etc. For example, the equipment fault occurrence time, fault equipment number, etc. are obtained from the equipment management system, and the operation and maintenance personnel processing method, processing time, etc. are obtained from the operation and maintenance work order system. The collected fault operation and maintenance record data is associated with the source nodes and diffusion nodes in the global diffusion path. For example, according to the equipment number and fault time, the operation and maintenance record is matched with the corresponding nodes in the global diffusion path. Taking the global diffusion path as the framework, nodes (including source nodes and diffusion nodes) and edges (representing operation and maintenance relationship) are created in the graph database. The attributes of the edges can include operation and maintenance processing method, processing time, processing cost, etc.

[0072] For example, in an intelligent factory, the global diffusion path includes production equipment A and connected equipment B, C. From the equipment management system and the operation and maintenance order system, it is collected that after the failure of equipment A, the operation and maintenance record is obtained, such as the motor damage of equipment A, the operation and maintenance personnel carries out the processing mode of replacing the motor, the processing time is 2 hours, and the processing cost is 1000 yuan. At the same time, equipment B and equipment C are affected by fault diffusion, the operation and maintenance personnel adjusts the parameters of equipment B, the processing time is 1 hour, and the processing cost is 200 yuan; equipment C is simply checked, the processing time is 0.5 hours, and the processing cost is 100 yuan. Based on the global diffusion path, the operation and maintenance records are sorted to construct a fault diffusion operation and maintenance graph, and the operation and maintenance relationship and corresponding processing details of equipment A after failure, equipment B and equipment C can be displayed in the graph.

[0073] In step S520, the fault source, fault diffusion node, fault type and fault severity of the fault source, fault type and fault severity of the fault diffusion node in the target monitoring information are input into the fault diffusion operation and maintenance graph for operation and maintenance strategy matching to generate a target operation and maintenance strategy. Specifically, the related information such as fault source and fault diffusion node is extracted from the target monitoring information and converted into a format that can be recognized by the fault diffusion operation and maintenance graph. For example, the fault type name is converted into a unified fault type code in the graph, and the fault severity is converted into a corresponding numerical range. In the fault diffusion operation and maintenance graph, the fault source and the fault diffusion node are used as the starting point, and the graph query language is used to find the historical operation and maintenance relationship path matched therewith to generate the target operation and maintenance strategy. For example, when the motor damage fault type of equipment A and the fault severity are moderate, the corresponding operation and maintenance processing mode and processing flow are obtained.

[0074] Step S530, performing operation and maintenance management of the fault equipment according to the target operation and maintenance policy. Specifically, according to the target operation and maintenance policy, a corresponding operation and maintenance work order is created in the operation and maintenance work order management system. The work order content includes fault equipment information, operation and maintenance task description, estimated processing time, required spare parts and tools, etc. Then the work order is assigned to the corresponding operation and maintenance personnel or operation and maintenance team. For example, for the operation and maintenance task of replacing the motor heat dissipation component of equipment A, a work order is created and assigned to the electrical maintenance team of the factory. The operation and maintenance personnel operates through the remote monitoring system for the equipment that can be remotely operated according to the work order content. For example, parameter recalibration of equipment B can be realized through remote IO control. For the equipment that needs to be handled on site, the operation and maintenance personnel carries a mobile application device to the site, operates according to the operation and maintenance policy, and records the processing process and result on the mobile application. The operation and maintenance work order management system tracks the execution state of the operation and maintenance task in real time, and the operation and maintenance personnel feeds back the result in time after completing each step. For example, the operation and maintenance personnel marks the task as completed on the mobile application after completing the replacement of the heat dissipation component of equipment A, and the system automatically updates the work order state to "completed". At the same time, the operation and maintenance result is fed back to the fault diffusion operation and maintenance graph as the basis for subsequent operation and maintenance policy optimization.

[0075] The fault diffusion operation and maintenance graph in this implementation provides rich historical data and experience patterns for operation and maintenance decision-making. By matching the target monitoring information with the graph, a scientific and reasonable operation and maintenance policy can be quickly generated, reducing the time and error rate of manual decision-making.

[0076] The embodiment of the present application adopts collecting the distribution topology of energy equipment in a preset area, simulating the diffusion of each equipment from the minimum to the maximum fault degree, generating all possible fault propagation paths, performing global fusion analysis by identifying the intersection and convergence points of these paths, forming a comprehensive fault influence graph, based on which a multi-layer monitoring system from the bottom equipment to the upper system is constructed through Internet of Things technology, the running state of the equipment is monitored in real time and monitoring data is generated, the fault equipment is located according to the monitoring information, and technical means such as operation and maintenance management are implemented, which solves the technical problems that the existing energy equipment operation and maintenance cannot timely discover potential faults, accurately predict fault diffusion trend and efficiently formulate global operation and maintenance policy, and achieves the technical effects of timely discovering potential faults, accurately predicting fault diffusion trend and efficiently formulating global operation and maintenance policy.

[0077] In the foregoing, the Figure 1 The energy equipment intelligent operation and maintenance method based on Internet of Things driving according to the embodiment of the present application is described in detail. Next, the energy equipment intelligent operation and maintenance system based on Internet of Things driving according to the embodiment of the present application will be described with reference to Figure 2 The energy equipment intelligent operation and maintenance system based on Internet of Things driving according to the embodiment of the present application is described.

[0078] The energy equipment intelligent operation and maintenance system based on the Internet of Things driving according to the embodiment of the present application is used to solve the technical problems that the existing energy equipment operation and maintenance cannot timely find potential faults, accurately predict fault diffusion trends and efficiently formulate global operation and maintenance strategies, and achieves the technical effects of timely finding potential faults, accurately predicting fault diffusion trends and efficiently formulating global operation and maintenance strategies. The energy equipment intelligent operation and maintenance system based on the Internet of Things driving comprises an energy equipment distribution topology collection module 10, a fault diffusion fitting module 20, a global fusion module 30, an energy equipment operation monitoring module 40 and a fault operation and maintenance management module 50.

[0079] The energy equipment distribution topology collection module 10 is used to collect the energy equipment distribution topology in a preset area; the fault diffusion fitting module 20 is used to perform fault diffusion fitting on each energy equipment in the energy equipment distribution topology, including diffusion from the minimum fault degree to the maximum fault degree, to generate each fault diffusion path; the global fusion module 30 is used to perform global fusion on the each fault diffusion path, identify diffusion convergence points and generate global diffusion paths; the energy equipment operation monitoring module 40 is used to perform bottom-up multi-layer monitoring system configuration based on the global diffusion paths through the Internet of Things technology, perform energy equipment operation monitoring in the preset area by using the multi-layer monitoring system and generate target monitoring information; and the fault operation and maintenance management module 50 is used to perform operation and maintenance management of fault equipment according to the target monitoring information.

[0080] In the following, the specific configuration of the fault diffusion fitting module 20 will be described in detail. As described above, the fault diffusion fitting on each energy equipment in the energy equipment distribution topology, including diffusion from the minimum fault degree to the maximum fault degree, to generate each fault diffusion path, the fault diffusion fitting module 20 can further comprise: an integrated modeling unit used to perform integrated modeling of energy equipment and connection relationship based on the energy equipment distribution topology, to construct a device integrated twin; a first energy equipment extraction unit used to extract a first energy equipment in the each energy equipment; a fault diffusion simulation unit used to call the device integrated twin, perform fault diffusion simulation from the minimum fault degree to the maximum fault degree on the first energy equipment and generate a first fault diffusion path; and a first fault diffusion path adding unit used to add the first fault diffusion path to the each fault diffusion path.

[0081] The device integrated twin is called to perform a fault propagation simulation from a minimum fault degree to a maximum fault degree on the first energy equipment to generate a first fault propagation path. The fault propagation simulation unit can further include: a historical fault record dataset collection subunit configured to collect a historical fault record dataset of the first energy equipment; a fault degree analysis subunit configured to perform fault degree analysis on each piece of data in the historical fault record dataset, determine a first fault event corresponding to a minimum fault degree, and a second fault event corresponding to a maximum fault degree; and a propagation path reading subunit configured to call the device integrated twin, load the first fault event until evolution to the second fault event, read a propagation path of the first fault event to the second fault event, and generate the first fault propagation path.

[0082] The fault degree analysis subunit can further include: a fault degree label set obtaining component configured to extract a fault influence range and a fault loss from each piece of data in the historical fault record dataset, perform normalization processing and weighted fusion to obtain a fault degree label set; a first fault event selecting component configured to select a first fault event corresponding to a minimum fault degree by using a mapping relationship between the fault degree label set and the historical fault record dataset; and a second fault event generating component configured to take the first fault event as a propagation source, filter a fault event corresponding to a maximum fault degree corresponding to the same propagation source in the historical fault record dataset, and generate a second fault event.

[0083] The global fusion module 30 can further include: a same diffusion node identifying unit configured to take a diffusion node as an alignment element, align the various fault propagation paths to identify a same diffusion node to obtain a first diffusion convergence point, a second diffusion convergence point, and an Nth diffusion convergence point; and a multi-level connection unit configured to take the first diffusion convergence point, the second diffusion convergence point, and the Nth diffusion convergence point as connection points, perform multi-level connection on the various fault propagation paths, and generate the global propagation path.

[0084] The specific configuration of the energy equipment operation monitoring module 40 will be described in detail below. As described above, based on the global diffusion path, the bottom-up multi-layer monitoring system configuration is implemented through the Internet of Things technology, and the energy equipment operation monitoring module 40 can further include: a diffusion feature similarity merging unit for performing similarity merging of diffusion features of adjacent diffusion nodes according to the global diffusion path, to generate an updated diffusion path; a feature screening unit for performing feature screening based on diffusion identification contribution degree of each diffusion node based on the updated diffusion path, to generate a monitoring demand path; a diffusion feature relationship modeling unit for performing diffusion feature relationship modeling based on the updated diffusion path and the monitoring demand path, to construct a fault diffusion analysis model; and a multi-layer monitoring system generation unit for configuring an Internet of Things architecture based on the monitoring demand path, connecting the Internet of Things architecture with the fault diffusion analysis model, and generating the multi-layer monitoring system.

[0085] In the process of performing energy equipment operation monitoring in the preset area by using the multi-layer monitoring system to generate target monitoring information, the energy equipment operation monitoring module 40 can further include a target monitoring information generation unit for performing real-time monitoring of each energy equipment by using the Internet of Things architecture, sending each monitoring data to the fault diffusion analysis model for analysis, and generating the target monitoring information, wherein the fault diffusion analysis model includes a fault source, a fault type and a fault severity of the fault source, and a fault type and a fault severity of a fault diffusion node.

[0086] The specific configuration of the fault operation and maintenance management module 50 will be described in detail below. As described above, according to the target monitoring information, the operation and maintenance management of the fault equipment is performed, and the fault operation and maintenance management module 50 can further include: a fault diffusion operation and maintenance graph construction unit for collecting fault operation and maintenance record data, performing operation and maintenance relationship analysis of source nodes and diffusion nodes under fault diffusion based on the global diffusion path, and constructing a fault diffusion operation and maintenance graph; an operation and maintenance strategy matching unit for inputting a fault source, a fault diffusion node, a fault type and a fault severity of the fault source, and a fault type and a fault severity of the fault diffusion node in the target monitoring information into the fault diffusion operation and maintenance graph for operation and maintenance strategy matching, to generate a target operation and maintenance strategy; and an operation and maintenance management unit for performing operation and maintenance management of the fault equipment by using the target operation and maintenance strategy.

[0087] The energy equipment intelligent operation and maintenance system based on the Internet of Things driving provided in the embodiments of the present application can implement the energy equipment intelligent operation and maintenance method based on the Internet of Things driving provided in any of the embodiments of the present application, and has the corresponding function modules and beneficial effects of the implementation method.

[0088] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or server, the various units and modules are only divided according to the functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific name of each functional unit is only for the convenience of mutual differentiation, and does not limit the protection scope of the present application.

[0089] Based on the foregoing embodiments, the embodiments of the present application also provide a computer readable storage medium, the computer readable storage medium stores a computer program, the computer program is executed by a processor of an electronic device, and the computer program can realize the energy equipment intelligent operation and maintenance method based on the Internet of Things driving as any one of the foregoing embodiments.

[0090] The above detailed description does not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent replacement and improvement made within the spirit and principle of the present application should be included in the protection scope of the present application. In some cases, the actions or steps described in the present application can be executed 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, multi-task processing and parallel processing are possible or can be advantageous.

Claims

1. A smart operation and maintenance method for energy equipment based on the Internet of Things, characterized in that, include: Collect the topology of energy equipment distribution within a preset area; Fault propagation fitting is performed on each energy device in the energy device distribution topology, including propagation from the minimum fault level to the maximum fault level, to generate each fault propagation path; For each fault propagation path, identify the diffusion convergence point, perform global fusion, and generate a global propagation path; Based on the global diffusion path, a multi-layered monitoring system is configured from bottom to top using Internet of Things technology. The multi-layered monitoring system is used to monitor the operation of energy equipment within the preset area and generate target monitoring information. The operation and maintenance management of faulty equipment is carried out based on the target monitoring information.

2. The IoT-driven intelligent operation and maintenance method for energy equipment as described in claim 1, characterized in that, Fault propagation fitting is performed on each energy device in the energy device distribution topology, including propagation from minimum fault severity to maximum fault severity, generating various fault propagation paths, including: Based on the energy equipment distribution topology, an integrated model of the energy equipment and its connection relationships is constructed to create an integrated twin of the equipment. Extract the first energy device from the various energy devices; The device integrated twin is invoked to simulate the fault propagation of the first energy device from the minimum fault level to the maximum fault level, thereby generating a first fault propagation path; Add the first fault propagation path to each of the fault propagation paths.

3. The IoT-driven intelligent operation and maintenance method for energy equipment as described in claim 2, characterized in that, The device integrated twin is invoked to simulate the fault propagation of the first energy device from the minimum fault level to the maximum fault level, generating a first fault propagation path, including: Collect a dataset of historical fault records from the first energy device; For each data point in the historical fault record dataset, a fault severity analysis is performed to determine the first fault event corresponding to the minimum fault severity and the second fault event corresponding to the maximum fault severity. The device integrated twin is invoked to load the first fault event until it evolves into the second fault event. The propagation path from the first fault event to the second fault event is read, and the first fault propagation path is generated.

4. The IoT-driven intelligent operation and maintenance method for energy equipment as described in claim 3, characterized in that, For each data point in the historical fault record dataset, a fault severity analysis is performed to determine the first fault event corresponding to the minimum fault severity and the second fault event corresponding to the maximum fault severity, including: For each data point in the historical fault record dataset, the fault impact range and fault loss are extracted, normalized, and then weighted and fused to obtain a fault severity label set. Using the mapping relationship between the fault severity label set and the historical fault record dataset, the first fault event corresponding to the minimum fault severity is selected; Using the first fault event as the source of diffusion, the fault events corresponding to the maximum fault severity of the same source are filtered from the historical fault record dataset to generate the second fault event.

5. The IoT-driven intelligent operation and maintenance method for energy equipment as described in claim 1, characterized in that, For each fault propagation path, the propagation convergence point is identified, and global fusion is performed to generate a global propagation path, including: Using the diffusion nodes as alignment elements, the various fault diffusion paths are aligned and the same diffusion nodes are identified to obtain the first diffusion convergence point, the second diffusion convergence point, and so on up to the Nth diffusion convergence point. Using the first diffusion convergence point, the second diffusion convergence point, and so on up to the Nth diffusion convergence point as connection points, the various fault diffusion paths are connected in multiple layers to generate the global diffusion path.

6. The IoT-driven intelligent operation and maintenance method for energy equipment as described in claim 1, characterized in that, Based on the aforementioned global diffusion path, a multi-layered monitoring system is configured from bottom to top using IoT technology, including: Based on the global diffusion path, adjacent diffusion nodes are merged according to the similarity of their diffusion characteristics to generate an updated diffusion path; Based on the updated diffusion path, feature filtering based on diffusion identification contribution is performed on each diffusion node to generate a monitoring requirement path; Based on the update diffusion path and the monitoring requirement path, a diffusion characteristic relationship model is constructed to build a fault diffusion analysis model. Based on Internet of Things (IoT) technology, an IoT architecture is configured according to the monitoring demand path and connected with the fault propagation analysis model to generate the multi-layer monitoring system.

7. The IoT-driven intelligent operation and maintenance method for energy equipment as described in claim 6, characterized in that, The multi-layer monitoring system is used to monitor the operation of energy equipment within the preset area, generating target monitoring information, including: The IoT architecture is used to monitor various energy devices in real time, and the monitoring data is sent to the fault propagation analysis model for analysis to generate the target monitoring information. The fault propagation analysis model includes the fault source, the fault type and severity of the fault source, and the fault type and severity of the fault propagation node.

8. The IoT-driven intelligent operation and maintenance method for energy equipment as described in claim 7, characterized in that, Based on the target monitoring information, the operation and maintenance management of faulty equipment is carried out, including: Collect fault operation and maintenance record data, and analyze the operation and maintenance relationship between the source node and the diffusion node under the fault diffusion based on the global diffusion path to construct a fault diffusion operation and maintenance map; The fault source, fault propagation node, fault type and severity of the fault source, and fault type and severity of the fault propagation node in the target monitoring information are input into the fault propagation operation and maintenance map for operation and maintenance strategy matching to generate the target operation and maintenance strategy. The operation and maintenance management of faulty equipment is carried out using the target operation and maintenance strategy.

9. An intelligent operation and maintenance system for energy equipment based on the Internet of Things, characterized in that: The system is used to implement the IoT-driven intelligent operation and maintenance method for energy equipment as described in any one of claims 1-8, and the system comprises: The energy equipment distribution topology acquisition module is used to acquire the energy equipment distribution topology within a preset area; The fault propagation fitting module is used to perform fault propagation fitting on each energy device in the energy device distribution topology, including propagation from the minimum fault degree to the maximum fault degree, and generate each fault propagation path. The global fusion module is used to identify the diffusion convergence point of each fault diffusion path, perform global fusion, and generate a global diffusion path; The energy equipment operation monitoring module is used to configure a multi-layer monitoring system from bottom to top based on the global diffusion path using Internet of Things technology, and to use the multi-layer monitoring system to perform energy equipment operation monitoring within the preset area and generate target monitoring information. The fault operation and maintenance management module is used to perform operation and maintenance management of faulty equipment based on the target monitoring information.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the IoT-driven intelligent operation and maintenance method for energy equipment as described in any one of claims 1-8.

Images