New energy station intelligent monitoring method and system based on Internet of Things

Abstract

The invention provides a new energy station intelligent monitoring method and system based on the Internet of Things. The method comprises the following steps: acquiring equipment working parameters, surface temperatures, material parameters and structure parameters of a plurality of Internet of Things equipment in a new energy station, and environment parameters of the environment where the equipment is located; based on the equipment working parameters, the surface temperatures, the material parameters and the structure parameters of the multiple pieces of Internet of Things equipment, determining equipment stability parameters of each piece of Internet of Things equipment; based on the device working parameters, the material parameters and the structure parameters of the plurality of Internet of Things devices and the environment parameters of the environment, determining the environment influence parameters of each Internet of Things device; based on the equipment working parameters, the equipment stability parameters and the environment influence parameters of the multiple pieces of Internet of Things equipment, target Internet of Things equipment in the multiple pieces of Internet of Things equipment is determined and displayed, and the target Internet of Things equipment is the Internet of Things equipment with the high fault risk.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an intelligent monitoring method and system for new energy stations based on the Internet of Things. Background Art

[0002] With the growing demand for clean energy, the scale and number of new energy power plants (such as solar power plants and wind farms) are increasing. These power plants contain numerous IoT devices with computing power, which play a key role in their operation, monitoring, and management.

[0003] Currently, there are shortcomings in monitoring IoT devices in new energy power plants. Most monitoring methods only capture a subset of device parameters. For example, they focus solely on operating parameters, while ignoring important factors such as surface temperature, material parameters, structural parameters, and environmental parameters. This incomplete parameter acquisition makes it difficult to accurately assess the stability of the device itself, effectively determining its stability parameters.

[0004] At the same time, existing monitoring systems lack the ability to comprehensively consider the interactions between device-specific and environmental factors. Without the ability to effectively determine environmental impact parameters, it's difficult to accurately locate IoT devices with high failure risk among multiple IoT devices. This poses challenges to the stable operation, maintenance cost control, and safety assurance of new energy stations.

[0005] In summary, there is an urgent need for an improved intelligent monitoring method for new energy stations based on the Internet of Things to overcome the limitations of existing monitoring methods. Summary of the Invention

[0006] The present application provides an IoT-based intelligent monitoring method and system for new energy stations, which can improve the monitoring effect of new energy stations and promptly detect equipment with high failure risks in new energy stations. The technical solution is as follows: On the one hand, a method for intelligent monitoring of new energy stations based on the Internet of Things is provided, the method comprising: Obtaining device operating parameters, surface temperature, material parameters, structural parameters, and environmental parameters of a plurality of IoT devices in a new energy station, wherein the IoT devices are devices with computing capabilities in the new energy station; Determine, based on device operating parameters, surface temperatures, material parameters, and structural parameters of the plurality of IoT devices, a device stability parameter for each IoT device, the device stability parameter being used to indicate a stability condition of the IoT device itself; Determine an environmental impact parameter of each of the IoT devices based on device operating parameters, material parameters, structural parameters, and environmental parameters of the environments in which the multiple IoT devices are located, where the environmental impact parameter is used to represent the impact of the environment on the IoT device; Based on the device operating parameters, device stability parameters, and environmental impact parameters of the multiple IoT devices, a target IoT device among the multiple IoT devices is determined and displayed, where the target IoT device is an IoT device with a high risk of failure.

[0007] On the one hand, a new energy station intelligent monitoring device based on the Internet of Things is provided, the device comprising: An acquisition module is configured to acquire device operating parameters, surface temperature, material parameters, structural parameters, and environmental parameters of a plurality of IoT devices in a new energy station, wherein the IoT devices are devices with computing capabilities in the new energy station; a device stability parameter determination module, configured to determine a device stability parameter of each of the plurality of IoT devices based on device operating parameters, surface temperature, material parameters, and structural parameters of the plurality of IoT devices, wherein the device stability parameter is used to indicate the stability of the IoT device itself; an environmental impact parameter determination module, configured to determine an environmental impact parameter of each of the plurality of IoT devices based on device operating parameters, material parameters, structural parameters, and environmental parameters of the environment in which the plurality of IoT devices are located, wherein the environmental impact parameter is used to represent the impact of the environment on the IoT device; The target IoT device determination module is used to determine and display a target IoT device among the multiple IoT devices based on the device operating parameters, device stability parameters, and environmental impact parameters of the multiple IoT devices, where the target IoT device is an IoT device with a high risk of failure.

[0008] In one possible embodiment, the material parameters include specific heat capacity and thermal conductivity coefficient, and the device stability parameter determination module is used to determine the basic heating value and working abnormality parameters of each of the multiple IoT devices based on the device working parameters of the multiple IoT devices; determine the basic heat transfer value of each of the IoT devices based on the specific heat capacity, the thermal conductivity coefficient and the structural parameters; and determine the device stability parameters of each of the IoT devices based on the basic heating value, basic heat transfer value, surface temperature and working abnormality parameters of each of the IoT devices.

[0009] In one possible embodiment, the device operating parameters include a working log, working heat parameters, and resource occupancy. The device stability parameter determination module is used to determine the basic heating value of the IoT device for any IoT device among the multiple IoT devices based on the working heat parameters and resource occupancy of the IoT device; and determine the abnormal working parameters of the IoT device based on the working log of the IoT device.

[0010] In one possible embodiment, the working heating parameters include thermal power conversion parameters and device heating value, and the thermal power conversion parameters are used to represent the relationship between resource occupancy and thermal power. The device stability parameter determination module is used to determine the operating heating value of the Internet of Things device based on the thermal power conversion parameters and the resource occupancy; the operating heating value and the device heating value are merged to obtain the basic heating value of the Internet of Things device, and the device heating value refers to the heating value when the Internet of Things device is not performing any calculation.

[0011] In one possible implementation, the work log includes work data and data processing results, and the device stability parameter determination module is used to parse the work log to obtain the work data and data processing results; based on the work data and the data processing results, determine the abnormal working parameters of the Internet of Things device.

[0012] In one possible embodiment, the environmental parameters include ambient temperature, and the device stability parameter determination module is used to obtain the basic temperature of the IoT device for any IoT device among the multiple IoT devices based on the basic heat output and the basic heat transfer of the IoT device; determine the temperature anomaly parameter of the IoT device based on the surface temperature and the basic temperature of the IoT device, where the temperature anomaly parameter is used to indicate the degree of temperature anomaly; and determine the device stability parameter of the IoT device based on the temperature anomaly parameter and the operating anomaly parameter of the IoT device.

[0013] In one possible implementation, the device stability parameter determination module is used to encode the temperature anomaly parameter and the operating anomaly parameter to obtain the temperature anomaly characteristics and the operating anomaly characteristics of the Internet of Things device; fuse the temperature anomaly characteristics and the operating anomaly characteristics to obtain the device stability prediction characteristics of the Internet of Things device; and decode the device stability prediction characteristics to obtain the device stability parameter.

[0014] In one possible embodiment, the environmental impact parameter determination module is used to determine the environmental operating impact parameters of each of the multiple Internet of Things devices based on the device operating parameters and environmental parameters of the multiple Internet of Things devices; determine the environmental device impact parameters of each of the multiple Internet of Things devices based on the material parameters, structural parameters and environmental parameters of the multiple Internet of Things devices; and determine the environmental impact parameters of each of the Internet of Things devices based on the environmental operating impact parameters and environmental device impact parameters of each of the Internet of Things devices.

[0015] In one possible embodiment, the device operating parameters include operating logs and operating heat parameters, and the environmental impact parameter determination module is used to determine the first reference environmental operating impact parameters of each of the multiple Internet of Things devices based on the operating logs and the environmental parameters of the multiple Internet of Things devices; determine the second reference environmental operating impact parameters of each of the multiple Internet of Things devices based on the operating heat parameters and the environmental parameters of the multiple Internet of Things devices; and determine the environmental operating impact parameters of each of the multiple Internet of Things devices based on the first reference environmental operating impact parameters and the second reference environmental operating impact parameters of the multiple Internet of Things devices.

[0016] In one possible embodiment, the environmental impact parameter determination module is used to determine the environmental material impact parameters of each of the multiple Internet of Things devices based on the material parameters of the multiple Internet of Things devices and the environmental parameters; determine the environmental structure impact parameters of each of the multiple Internet of Things devices based on the structural parameters of the multiple Internet of Things devices and the environmental parameters; and determine the environmental device impact parameters of each of the multiple Internet of Things devices based on the environmental material impact parameters and environmental structure impact parameters of the multiple Internet of Things devices.

[0017] In one possible implementation, the environmental impact parameter determination module is used to encode the environmental working impact parameters and environmental equipment impact parameters of each of the Internet of Things devices respectively to obtain the environmental working impact characteristics and environmental equipment impact characteristics of each of the Internet of Things devices; fuse the environmental working impact characteristics and environmental equipment impact characteristics of each of the Internet of Things devices to obtain the environmental impact characteristics of each of the Internet of Things devices; and decode the environmental impact characteristics of each of the Internet of Things devices to obtain the environmental impact parameters of each of the Internet of Things devices.

[0018] In one possible implementation, the target IoT device determination module is configured to determine device abnormality parameters of each of the IoT devices based on device operating parameters and device stability parameters of the multiple IoT devices, where the device abnormality parameters are used to indicate a degree of abnormality of the corresponding IoT device; determine the target IoT device from the multiple IoT devices based on the device abnormality parameters of each of the IoT devices and the environmental impact parameters; and highlight the target IoT device and display its geographic location.

[0019] In one possible implementation, the target IoT device determination module is configured to fuse device abnormality parameters and environmental impact parameters of each of the IoT devices to obtain a fault risk parameter for each of the IoT devices, where the fault risk parameter is used to indicate the risk of a failure; and to determine the IoT device with the highest fault risk parameter among the multiple IoT devices as the target IoT device.

[0020] On the one hand, a new energy station intelligent monitoring system based on the Internet of Things is provided, the system including one or more processors and one or more memories, at least one computer program stored in the one or more memories, the computer program being loaded and executed by the one or more processors to implement the new energy station intelligent monitoring method based on the Internet of Things.

[0021] On the one hand, a computer-readable storage medium is provided, in which at least one computer program is stored. The computer program is loaded and executed by a processor to implement the intelligent monitoring method of new energy stations based on the Internet of Things.

[0022] On the one hand, a computer program product or computer program is provided, which includes a program code, and the program code is stored in a computer-readable storage medium. The processor of the monitoring platform reads the program code from the computer-readable storage medium, and the processor executes the program code, so that the monitoring platform executes the above-mentioned new energy station intelligent monitoring method based on the Internet of Things.

[0023] Through the technical solution provided in the embodiment of the present application, the device operating parameters, surface temperature, material parameters, structural parameters and environmental parameters of the environment of multiple IoT devices in the new energy station are obtained. The device stability parameters are determined by using the acquired device operating parameters, surface temperature, material parameters and structural parameters, and the stability of the IoT device itself can be represented by the device stability parameters. The environmental impact parameters of the IoT device can be determined by using the device operating parameters, material parameters, structural parameters and environmental parameters, thereby quantifying the impact of the environment on the IoT device. Based on the device operating parameters, device stability parameters and environmental impact parameters of multiple IoT devices, the target IoT devices with a high risk of failure are determined and displayed, so that technical personnel can promptly maintain the target IoT devices and improve the stability of the new energy station. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0025] Figure 1 This is a schematic diagram of an implementation environment of an IoT-based new energy station intelligent monitoring method provided in an embodiment of the present application; Figure 2 This is a flow chart of an intelligent monitoring method for new energy stations based on the Internet of Things provided in an embodiment of the present application; Figure 3 This is a flow chart of another method for intelligent monitoring of new energy stations based on the Internet of Things provided in an embodiment of the present application; Figure 4 This is a structural diagram of an IoT-based new energy station intelligent monitoring device provided in an embodiment of the present application; Figure 5 This is a structural diagram of an IoT-based new energy station intelligent monitoring system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art. Like reference numerals in the figures represent like or similar structures, and thus their detailed description will be omitted.

[0027] The terms "a", "an", "the", and "said" are used to indicate the presence of one or more elements / components / etc.; the terms "including" and "having" are used to express an open-ended inclusive meaning and mean that additional elements / components / etc. may be present in addition to the listed elements / components / etc.

[0028] In order to illustrate the technical solutions provided by the embodiments of the present application, the terms involved in the embodiments of the present application are introduced below.

[0029] New Energy Station: A new energy station is a collection of all equipment connected to the grid connection point of a wind farm or solar power station. It includes transformers, busbars, lines, converters, energy storage components, wind turbines, photovoltaic power generation equipment, reactive power regulation equipment, and auxiliary equipment.

[0030] IoT devices: IoT devices are physical devices connected via the internet that can collect, transmit, and interact with data. In the embodiments of this application, IoT devices refer to devices with computing capabilities in new energy stations, such as encoder control devices, converter control devices, energy storage component control devices, wind turbine control devices, and photovoltaic power generation equipment control devices.

[0031] Machine learning (ML) is a multidisciplinary field that encompasses probability theory, statistics, approximation theory, convex analysis, and algorithmic complexity theory. It specifically studies how computers can simulate or implement human learning behaviors to acquire new knowledge or skills and reorganize existing knowledge sub-models to continuously improve their performance. Machine learning is at the core of artificial intelligence and the fundamental way to make computers intelligent. Its applications span all areas of AI. Machine learning and deep learning typically include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and learning through demonstration.

[0032] Normalization: Mapping sequences of numbers with different value ranges to the interval (0, 1) facilitates data processing. In some cases, the normalized values can be directly implemented as probabilities.

[0033] The implementation environment of the embodiments of the present application is introduced below.

[0034] Figure 1 This is a schematic diagram of the implementation environment of a new energy station intelligent monitoring method based on the Internet of Things provided in the embodiment of the present application, see Figure 1 , the implementation environment may include a monitoring platform 110 and a server 140 .

[0035] Monitoring platform 110 is connected to server 140 via a wireless or wired network. Monitoring platform 110 is used by the station monitoring center. It is connected to multiple IoT devices in the new energy station and can obtain relevant data from the IoT devices. Applications supporting new energy station management are installed on monitoring platform 110.

[0036] Server 140 is an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. Server 140 provides backend services for applications running on monitoring platform 110.

[0037] After introducing the implementation environment of the embodiment of the present application, the application scenario of the embodiment of the present application is introduced below. The technical solution provided by the embodiment of the present application can be applied in the scenario of monitoring new energy stations. After adopting the technical solution provided by the embodiment of the present application, the target IoT devices in the new energy station can be discovered in a timely manner, that is, the IoT devices with a high risk of failure in the new energy station can be discovered, which facilitates maintenance personnel to maintain the target IoT devices in a timely manner, reduces the probability of complete failure of the target IoT devices, and improves the stability of the new energy station.

[0038] After introducing the application scenarios of the embodiments of the present application, the intelligent monitoring method for new energy stations based on the Internet of Things provided by the embodiments of the present application is described below. Figure 2 This is a flow chart of a new energy station intelligent monitoring method based on the Internet of Things provided by the embodiment of the present application, see Figure 2 , taking the execution subject as a monitoring platform as an example, the method includes the following steps.

[0039] 201. The monitoring platform obtains device operating parameters, surface temperature, material parameters, structural parameters, and environmental parameters of the environment in which multiple Internet of Things devices in the new energy station are located. The Internet of Things devices are devices with computing capabilities in the new energy station.

[0040] New energy stations are wind power stations or photovoltaic power stations that primarily generate electricity using renewable energy. IoT devices refer to intelligent devices deployed within the stations that perform data collection, computing, or control functions, such as environmental monitoring terminals, inverter controllers, and energy storage system management units. Each IoT device is equipped with sensors to collect operating parameters, surface temperature, and environmental parameters. Device operating parameters represent the operating status of the IoT device. Environmental parameters represent the environmental conditions of the environment in which the IoT device operates. Material and structural parameters are physical properties preset for IoT devices at the factory.

[0041] 202. The monitoring platform determines a device stability parameter of each IoT device based on the device operating parameters, surface temperature, material parameters, and structural parameters of the multiple IoT devices. The device stability parameter is used to indicate the stability of the IoT device itself.

[0042] Among them, the device stability parameter is a quantification of the stability of the IoT device itself. The device stability parameter is determined based on the device operating parameters, surface temperature, material parameters and structural parameters. It can reflect the stability of the IoT device when it is not affected by the outside world. The device operating parameters, surface temperature, material parameters and structural parameters are used to reflect the stability of the IoT device from multiple dimensions.

[0043] 203. The monitoring platform determines an environmental impact parameter of each IoT device based on device operating parameters, material parameters, structural parameters, and environmental parameters of the environment in which the multiple IoT devices are located. The environmental impact parameter is used to represent the impact of the environment on the IoT device.

[0044] Among them, the environmental impact parameter is used to represent the impact of the environment on the IoT device.

[0045] 204. The monitoring platform determines and displays a target IoT device among the multiple IoT devices based on the device operating parameters, device stability parameters, and environmental impact parameters of the multiple IoT devices. The target IoT device is an IoT device with a high risk of failure.

[0046] Among them, the target IoT device is an IoT device with a high risk of failure. After determining and displaying the target IoT device, maintenance personnel can perform targeted maintenance on the target IoT device, thereby timely eliminating the failure risk of the new energy station and improving the stability of the new energy station.

[0047] Through the technical solution provided in the embodiment of the present application, the device operating parameters, surface temperature, material parameters, structural parameters and environmental parameters of the environment of multiple IoT devices in the new energy station are obtained. The device stability parameters are determined by using the acquired device operating parameters, surface temperature, material parameters and structural parameters, and the stability of the IoT device itself can be represented by the device stability parameters. The environmental impact parameters of the IoT device can be determined by using the device operating parameters, material parameters, structural parameters and environmental parameters, thereby quantifying the impact of the environment on the IoT device. Based on the device operating parameters, device stability parameters and environmental impact parameters of multiple IoT devices, the target IoT devices with a high risk of failure are determined and displayed, so that technical personnel can promptly maintain the target IoT devices and improve the stability of the new energy station.

[0048] The above steps 201-204 are a brief introduction to the intelligent monitoring method for new energy stations based on the Internet of Things provided by the embodiment of the present application. The following will combine some examples to more clearly illustrate the intelligent monitoring method for new energy stations based on the Internet of Things provided by the embodiment of the present application. Figure 3 , taking the execution subject as a monitoring platform as an example, the method includes the following steps.

[0049] 301. The monitoring platform obtains device operating parameters, surface temperature, material parameters, structural parameters, and environmental parameters of the environment of multiple Internet of Things devices in the new energy station. The Internet of Things devices are devices with computing capabilities in the new energy station.

[0050] New energy stations are wind power stations or photovoltaic power stations that primarily generate electricity using renewable energy. IoT devices refer to intelligent devices deployed within the stations that perform data collection, computing, or control functions, such as environmental monitoring terminals, inverter controllers, and energy storage system management units. Each IoT device is equipped with sensors to collect device operating parameters, surface temperature, and environmental parameters. Device operating parameters represent the operating status of the IoT device. Environmental parameters represent the environmental conditions of the environment in which the IoT device operates. Material parameters represent the material properties used in the production of the IoT device, while structural parameters represent the structural properties of the IoT device's hardware structure. Material and structural parameters are physical property parameters preset at the factory for IoT devices.

[0051] In one possible implementation, the monitoring platform obtains IoT device identifiers for multiple IoT devices within a new energy station. Based on the IoT device identifiers of each IoT device, the monitoring platform retrieves operating parameters, surface temperature, material parameters, structural parameters, and environmental parameters of the multiple IoT devices from an IoT device database.

[0052] The IoT device database stores information about multiple IoT devices within the new energy station. Device operating parameters, surface temperature, and environmental parameters are measured by sensors installed on the IoT devices. Material parameters include specific heat capacity and thermal conductivity. The structural parameters of IoT devices reflect their structural type. Structural types are defined by technical personnel based on actual conditions, and different structural types have different heat transfer and heat dissipation effects.

[0053] Under this implementation, the device operating parameters, surface temperature, structural parameters and environmental parameters of the environment in which the IoT device is located can be obtained by querying the IoT device database using the IoT device identifier of the IoT device, and the efficiency of parameter acquisition is high.

[0054] It should be noted that since the technical solution provided in the embodiment of the present application has a large amount of computational complexity and requires a large amount of computational resources and time, in the actual process of adopting the technical solution provided in the embodiment of the present application, it is executed periodically or triggered by technical personnel.

[0055] The following describes a method for measuring the device operating parameters of an IoT device.

[0056] In some embodiments, the device operating parameters include a work log, a work heating parameter, and a resource occupancy amount. The work log, the resource occupancy amount, and the work heating parameter are respectively obtained from the storage medium of the IoT device. Among them, the work log and the resource occupancy amount will change with time, and the work heating parameter will not change. The work heating parameter is stored in the storage medium of the IoT device by the manufacturer.

[0057] The following describes how to measure the surface temperature of an IoT device.

[0058] In some embodiments, the IoT device is provided with a contact temperature sensor, which is mounted on the outside of the IoT device. The surface temperature of the IoT device can be directly measured by the contact temperature sensor.

[0059] In some embodiments, an image acquisition device is installed around the IoT device, and an IoT device image of the IoT device can be captured by the image acquisition device. In this embodiment of the present application, the IoT device image includes an infrared IoT device image, which is captured by the infrared image acquisition device. The surface temperature of the IoT device can also be obtained using this IoT device image.

[0060] The following describes how to measure the environmental parameters of IoT devices.

[0061] In some embodiments, an environmental sensor is provided on the IoT device, and the environmental parameters can be obtained through the environmental sensor.

[0062] 302. The monitoring platform determines the basic heat generation and abnormal working parameters of each IoT device based on the device working parameters of the multiple IoT devices.

[0063] Among them, the basic heating value refers to the benchmark heating value when the IoT device is working normally, and the working abnormality parameter is used to indicate the degree of abnormality when the IoT device is working.

[0064] In one possible implementation, the device operating parameters include an operating log, operating heat parameters, and resource usage. For any of the multiple IoT devices, the monitoring platform determines a baseline heat output of the IoT device based on the operating heat parameters and resource usage of the IoT device. The monitoring platform also determines abnormal operating parameters of the IoT device based on the operating log of the IoT device.

[0065] The operating heat generation parameter describes the relationship between resource usage and base heat generation. Using the operating heat generation parameter, we can find the heat generation corresponding to resource usage, thus obtaining the base heat generation. The work log records the operating status of IoT devices. Analysis of the work log can reveal the degree of abnormality in IoT device operation, which can then be quantified using the operating abnormality parameter.

[0066] In this implementation, the IoT device's operating heating parameters and resource usage are used to determine its base heating value. The device's operating log is then used to determine its abnormal operating parameters, resulting in high accuracy in both base heating value and abnormal operating parameters.

[0067] In order to explain the above embodiment more clearly, the above embodiment will be described in several parts below.

[0068] In the first part, the monitoring platform determines the basic heat output of the IoT device based on the working heat parameters and resource usage of the IoT device.

[0069] In one possible implementation, the operating heat generation parameter includes a thermal power conversion parameter and a device heat generation value. The thermal power conversion parameter represents the relationship between resource usage and thermal power. Based on the thermal power conversion parameter and resource usage, the monitoring platform determines the operating heat generation value of the IoT device. The monitoring platform combines the operating heat generation value with the device heat generation value to obtain the IoT device's baseline heat generation value. This device heat generation value refers to the heat generation value when the IoT device is not performing any computations.

[0070] Among them, thermal power refers to the heat power generated by the IoT device during operation. The thermal power conversion parameters are set by technical personnel based on actual conditions and are not limited in the embodiments of this application. Operational heat generation refers to the heat generated by the IoT device due to data processing (resource usage is not zero), mainly generated by chips, memory, and storage media. Device heat generation refers to the heat generation when the IoT device is not processing data (resource usage is zero), mainly generated by auxiliary components such as sensors, motherboards, and display panels. In the embodiments of this application, the device heat generation is calibrated by technical personnel based on actual conditions.

[0071] In this implementation, resource usage and thermal power conversion parameters are used to determine the operating heat output of IoT devices. This combined operating heat output with the device heat output yields a baseline heat output for IoT devices, which is highly accurate and interpretable.

[0072] For example, the monitoring platform determines the target thermal power of the IoT device based on the thermal power conversion parameter and the resource occupancy. The monitoring platform multiplies the target thermal power by the first preset time and adds it to the historical operating heat value to obtain the operating heat value of the IoT device. The historical operating heat value is determined based on multiple historical resource occupancy, the thermal power conversion parameter and the first preset time value. The first preset time value is the data collection interval of the resource occupancy. The monitoring platform adds the operating heat value and the device heat value to obtain the basic heat value of the IoT device. Among them, in the embodiment of the present application, the resource occupancy is collected once every first preset time period, and the thermal power corresponding to the collected resource occupancy can be obtained by using the thermal power conversion parameter. The obtained thermal power is multiplied by the first preset time period to obtain the approximate device heating value. By continuously accumulating the historical device heating value, the current device heating value can be obtained.

[0073] The second part is that the monitoring platform determines the abnormal working parameters of the IoT device based on the working log of the IoT device.

[0074] In one possible implementation, the work log includes work data and data processing results, and the monitoring platform parses the work log to obtain the work data and data processing results. The monitoring platform determines the abnormal working parameters of the IoT device based on the work data and the data processing results.

[0075] Working data refers to the data processing target of IoT data, and data processing results refer to the results obtained after processing the working data. Working data is a collection of multiple data items, and data processing results are a collection of multiple processing results. Each piece of data in the working data corresponds to a processing result in the data processing results.

[0076] In this implementation, the work log is parsed to obtain work data and data processing results, and the work data and data processing results are used to determine the work abnormality parameters, and the accuracy of the work abnormality parameters is relatively high.

[0077] For example, the monitoring platform performs data identification and classification on the work log to obtain the work data and data processing results. The monitoring platform then reconstructs multiple data items within the work data and multiple processing results within the data processing results to obtain multiple data pairs, where each data pair includes a data item and a corresponding processing result. The monitoring platform then inputs these multiple data pairs into a work anomaly identification model, which then identifies anomalies for each data pair and obtains data pair anomaly parameters for each data pair. The monitoring platform then superimposes the data pair anomaly parameters for the multiple data pairs to obtain the work anomaly parameters for the IoT device.

[0078] For example, the monitoring platform performs data identification and data classification on the work log to obtain the work data and data processing results. Based on the data identification, the monitoring platform reorganizes multiple data in the work data and multiple processing results in the data processing results to obtain multiple data pairs. The monitoring platform inputs these multiple data pairs into the work anomaly recognition model, and uses the work anomaly recognition model to extract features from each data pair to obtain data pair features for each data pair. Using the work anomaly recognition model, the monitoring platform fully connects and normalizes the data pair features of each data pair to obtain data pair anomaly parameters for each data pair. The monitoring platform superimposes the data pair anomaly parameters of multiple data pairs to obtain the work anomaly parameters of the IoT device.

[0079] The work anomaly recognition model is a regression model that maps input data pairs into data pair anomaly parameters. In some embodiments, the data pair anomaly parameters are positively correlated with the degree of anomaly; that is, the higher the degree of anomaly, the larger the data pair anomaly parameters; the lower the degree of anomaly, the smaller the data pair anomaly parameters. The present embodiments do not limit the structure and training methods of the work anomaly recognition model.

[0080] 303. The monitoring platform determines the basic heat transfer capacity of each IoT device based on the specific heat capacity and thermal conductivity coefficient in the material parameters of each IoT device and the structural parameters.

[0081] The basic heat transfer refers to the amount of heat transferred from an IoT device to its surface during a single data collection cycle. This basic heat transfer is closely related to the specific heat capacity, thermal conductivity, and structural parameters. Structural parameters represent the distance, connection method, and relative position between different components in an IoT device.

[0082] In one possible implementation, the monitoring platform determines the component heat storage capacity of each IoT device based on its specific heat capacity and structural parameters. The monitoring platform also determines the component heat transfer capacity of each IoT device based on its thermal conductivity and structural parameters. The monitoring platform also determines the basic heat transfer capacity of each IoT device based on its component heat storage and component heat transfer capacity.

[0083] Component heat storage refers to the amount of heat retained by multiple components in an IoT device during heat transfer, and is associated with specific heat capacity and structural parameters. Component heat transfer refers to the amount of heat transferred by multiple components in an IoT device during heat transfer, and is associated with thermal conductivity and structural parameters.

[0084] In order to explain the above embodiment more clearly, the above embodiment will be described in several parts below.

[0085] In the first part, the monitoring platform determines the heat storage capacity of the components of each IoT device based on the specific heat capacity and structural parameters of each IoT device.

[0086] In one possible implementation, for any of the multiple IoT devices, the monitoring platform inputs the specific heat capacity and structural parameters of each component of the IoT device into a heat storage determination model. Using this heat storage determination model, the monitoring platform extracts features from the specific heat capacity and structural parameters of each component of the IoT device to obtain a heat storage characteristic for the IoT device. Using this heat storage determination model, the monitoring platform maps the heat storage characteristic to obtain the component heat storage of the IoT device.

[0087] The heat storage determination model is a regression model that can map the input specific heat capacity and structural parameters to the component heat storage. The present embodiment does not limit the structure and training method of the heat storage determination model.

[0088] For example, the monitoring platform inputs the specific heat capacity and structural parameters of each component of the IoT device into a heat storage determination model. Using this heat storage determination model, the monitoring platform performs multiple full connections on the specific heat capacity and structural parameters of each component of the IoT device to obtain the heat storage characteristics of each component of the IoT device. Using this heat storage determination model, the monitoring platform performs full connections and normalization on these heat storage characteristics to obtain the component heat storage of each component of the IoT device. The monitoring platform then adds the component heat storage values of each component of the IoT device to obtain the component heat storage of the IoT device.

[0089] In the second part, the monitoring platform determines the heat transfer amount of the components of each IoT device based on the thermal conductivity coefficient and structural parameters of each IoT device.

[0090] In one possible implementation, for any IoT device among multiple IoT devices, the monitoring platform inputs the thermal conductivity coefficients and structural parameters of each component of the IoT device into a heat transfer determination model. Using this heat transfer determination model, the monitoring platform extracts features from the thermal conductivity coefficients and structural parameters of each component of the IoT device to obtain a heat transfer characteristic for the IoT device. Using this heat transfer determination model, the monitoring platform maps this heat transfer characteristic to obtain the component heat transfer characteristics of the IoT device.

[0091] The heat transfer determination model is a regression model that can map the input heat transfer coefficient and structural parameters into component heat transfer. The present embodiment does not limit the structure and training method of the heat transfer determination model.

[0092] For example, the monitoring platform inputs the thermal conductivity coefficients and structural parameters of each component of the IoT device into a heat transfer determination model. Using this heat transfer determination model, the monitoring platform performs multiple full connections on the thermal conductivity coefficients and structural parameters of each component of the IoT device to obtain the heat transfer characteristics of each component of the IoT device. Using this heat transfer determination model, the monitoring platform performs full connections and normalization on these heat transfer characteristics to obtain the component heat transfer characteristics of each component of the IoT device. The monitoring platform then superimposes the component heat transfer characteristics of each component of the IoT device to obtain the component heat transfer characteristics of the IoT device.

[0093] The third part, the monitoring platform determines the basic heat transfer of each IoT device based on the component heat storage and component heat transfer of each IoT device.

[0094] In one possible implementation, for any IoT device among the multiple IoT devices, the monitoring platform subtracts the component heat transfer value from the component heat storage value to obtain the current base heat transfer value of the IoT device. The monitoring platform then adds the current base heat transfer value to the historical base heat transfer value to obtain the base heat transfer value of the IoT device.

[0095] The current base heat transfer refers to the base heat transfer determined by combining the component heat transfer and component heat storage, as determined by the currently collected data. The historical base heat transfer refers to the base heat transfer determined by combining the component heat transfer and component heat storage, as determined by historically collected data. In this embodiment of the present application, data collection is performed every first preset time interval, and a base heat transfer is determined based on the collected data. The historical heat transfer is the sum of the base heat transfers determined during a single operation of the IoT device.

[0096] 304. The monitoring platform determines the device stability parameter of each IoT device based on the basic heat output, basic heat transfer, surface temperature and the abnormal working parameter of each IoT device. The device stability parameter is used to indicate the stability of the IoT device itself.

[0097] Among them, the device stability parameter is a quantification of the stability of the IoT device itself. The device stability parameter is determined based on the device operating parameters, surface temperature, material parameters and structural parameters. It can reflect the stability of the IoT device when it is not affected by the outside world. The device operating parameters, surface temperature, material parameters and structural parameters are used to reflect the stability of the IoT device from multiple dimensions.

[0098] In one possible implementation, the environmental parameter includes ambient temperature. For any of the multiple IoT devices, the monitoring platform determines the base temperature of the IoT device based on the base heat output and the base heat transfer of the IoT device. Based on the surface temperature and base temperature of the IoT device, the monitoring platform determines a temperature anomaly parameter for the IoT device, where the temperature anomaly parameter indicates the degree of temperature anomaly. Based on the temperature anomaly parameter and the operating anomaly parameter, the monitoring platform determines a device stability parameter for the IoT device.

[0099] Among them, the basic temperature is the theoretical surface temperature of the Internet of Things device. The basic problem determined based on the basic heat output and the basic heat transfer in the above implementation is an ideal temperature without considering the heat dissipation situation. There will be a correction coefficient to make corrections later so that the determined basic temperature takes into account the influence of heat dissipation.

[0100] In order to explain the above embodiment more clearly, the above embodiment will be described in several parts below.

[0101] Part 1: The monitoring platform determines the basic temperature of the IoT device based on the basic heat generation and basic heat transfer of the IoT device.

[0102] In one possible implementation, the monitoring platform determines the base temperature of the IoT device based on the base heat output of the IoT device, the base heat transfer, and an environmental correction coefficient, where the environmental correction coefficient is associated with the ambient temperature of the environment in which the IoT device is located.

[0103] The environmental correction coefficient is determined based on the ambient temperature. The environmental correction coefficient is used to correct the temperature determined based on the basic heat output and the basic heat transfer, so that the resulting basic problem is closer to the actual theoretical situation. The environmental correction coefficient is an approximate estimate and cannot accurately describe heat loss. In some embodiments, there is a corresponding relationship between the environmental correction coefficient and the ambient temperature. This corresponding relationship can be represented by a relationship data (relationship function). In this case, the corresponding environmental correction coefficient can be obtained by inputting the ambient temperature into the relationship data. The relationship data is set by technicians based on actual conditions and is not limited in this embodiment of the present application.

[0104] For example, the monitoring platform determines the initial surface temperature of the IoT device based on the basic heat output and the basic heat transfer of the IoT device. The monitoring platform corrects the initial surface temperature using the environmental correction factor to obtain the basic temperature of the IoT device.

[0105] For example, the monitoring platform inputs the IoT device's base calorific value and base heat transfer value into its temperature prediction model. The temperature prediction model then extracts features from these values to obtain a temperature prediction signature for the IoT device. The monitoring platform then maps these features using the temperature prediction model to obtain the IoT device's initial surface temperature. The monitoring platform then multiplies this initial surface temperature by the environmental correction factor to obtain the IoT device's base temperature.

[0106] Among them, the value range of the environmental correction coefficient is (0, 1). Generally speaking, the environmental temperature correction coefficient is less than 0.2. There is a mapping relationship between the ambient temperature and the environmental correction coefficient, which can be specifically represented by a relationship function. The relationship function is set by technical personnel according to actual conditions, and the embodiments of this application do not limit this. The temperature prediction model is a temperature prediction model dedicated to the IoT device. It is trained based on multiple sample basic calorific values of the IoT device and the sample basic heat transfer values corresponding to each sample basic calorific value. The temperature prediction model is a regression model. The embodiments of this application do not limit the structure of the temperature prediction model.

[0107] In the second part, the monitoring platform determines the temperature anomaly parameters of the IoT device based on the surface temperature and base temperature of the IoT device. The temperature anomaly parameters are used to indicate the degree of temperature anomaly.

[0108] In a possible implementation, the monitoring platform divides the surface temperature by an absolute value obtained by subtracting the surface temperature from the base temperature to obtain a temperature anomaly parameter of the IoT device.

[0109] Among them, the temperature anomaly parameter is used to indicate the degree of deviation between the surface temperature and the base temperature. The larger the temperature anomaly parameter is, the greater the degree of deviation is, and the correspondingly greater the degree of temperature anomaly is; the smaller the temperature anomaly parameter is, the smaller the degree of deviation is, and the correspondingly smaller the degree of temperature anomaly is.

[0110] Part 3: The monitoring platform determines the device stability parameters of the IoT device based on the temperature abnormality parameters and the working abnormality parameters of the IoT device.

[0111] In one possible implementation, the monitoring platform encodes the temperature anomaly parameter and the operational anomaly parameter to obtain temperature anomaly characteristics and operational anomaly characteristics of the IoT device. The monitoring platform then fuses the temperature anomaly characteristics and operational anomaly characteristics to obtain a device stability prediction characteristic of the IoT device. The monitoring platform then decodes the device stability prediction characteristic to obtain the device stability parameter.

[0112] For example, the monitoring platform performs multiple full connections on the temperature anomaly parameter and the operational anomaly parameter to obtain the temperature anomaly signature and operational anomaly signature of the IoT device. The monitoring platform then performs a weighted fusion of these temperature anomaly signatures and operational anomaly signatures to obtain the device stability prediction signature for the IoT device. Using the attention mechanism, the monitoring platform performs multiple rounds of iterative decoding on these device stability prediction signatures to obtain the device stability parameter.

[0113] Among them, the weights of weighted fusion are set by technical personnel according to actual conditions, and the embodiments of this application do not limit this.

[0114] 305. The monitoring platform determines the environmental operating impact parameters of each IoT device based on the device operating parameters and environmental parameters of the multiple IoT devices.

[0115] In one possible implementation, the device operating parameters include an operating log and an operating heat parameter. The monitoring platform determines a first reference environmental operating impact parameter for each IoT device based on the operating logs of the multiple IoT devices and the environmental parameters. The monitoring platform determines a second reference environmental operating impact parameter for each IoT device based on the operating heat parameter and the environmental parameters of the multiple IoT devices. The monitoring platform determines the environmental operating impact parameter for each IoT device based on the first reference environmental operating impact parameter and the second reference environmental operating impact parameter of the multiple IoT devices.

[0116] Among them, the working heating parameters include thermal power conversion parameters and equipment heat generation. The first reference environment working influence parameter and the second reference environment working influence parameter are used to reflect the impact of the environment on the operation of the Internet of Things device in different dimensions. The first reference environment working influence parameter is used to represent the impact of the environment on the work log, and the second reference environment working influence parameter is used to represent the impact of the environment on heating. It should be noted that the first reference environment working influence parameter and the second reference environment working influence parameter are intermediate variables used to finally locate the target Internet of Things device in the embodiment of the present application, and have no actual physical meaning. In other words, the first reference environment working influence parameter and the second reference environment working influence parameter are similar to the hidden variables in the model processing process. In order to facilitate adjustment, the first reference environment working influence parameter and the second reference environment working influence parameter are displayed and determined in the embodiment of the present application.

[0117] In order to explain the above embodiment more clearly, the above embodiment will be described in several parts below.

[0118] In the first part, the monitoring platform determines a first reference environment work impact parameter of each IoT device based on the work logs of the multiple IoT devices and the environmental parameters.

[0119] In one possible implementation, for any IoT device among the multiple IoT devices, the monitoring platform extracts features from the work log of the IoT device and the environmental parameters to obtain a first predicted feature of the IoT device. The monitoring platform then maps the first predicted feature to obtain a first reference environmental work impact parameter for the IoT device.

[0120] For example, the monitoring platform concatenates the IoT device's work log and the environmental parameters and performs multiple full joins to obtain a first prediction feature of the IoT device. The monitoring platform performs full joins and normalization on the first prediction feature to obtain a first reference environmental work impact parameter of the IoT device.

[0121] In the second part, the monitoring platform determines a second reference environment working impact parameter of each IoT device based on the working heating parameters of the multiple IoT devices and the environmental parameters.

[0122] In one possible implementation, for any IoT device among the multiple IoT devices, the monitoring platform extracts features from the operating heat parameters of the IoT device and the environmental parameters to obtain a second predicted feature of the IoT device. The monitoring platform maps the second predicted feature to obtain a second reference environmental operating impact parameter of the IoT device.

[0123] For example, the monitoring platform combines the IoT device's operating heat parameters with the environmental parameters and performs multiple full joins to obtain a second prediction feature for the IoT device. The monitoring platform performs full joins and normalization on the second prediction feature to obtain a second reference environmental operating impact parameter for the IoT device.

[0124] Part 3: The monitoring platform determines the environmental working impact parameter of each Internet of Things device based on the first reference environmental working impact parameter and the second reference environmental working impact parameter of the multiple Internet of Things devices.

[0125] In one possible implementation, for any IoT device among the multiple IoT devices, the monitoring platform performs weighted fusion on the first reference environmental working impact parameter and the second reference environmental working impact parameter of the IoT device to obtain the environmental working impact parameter of the IoT device.

[0126] Among them, the weights of weighted fusion are set by technical personnel according to actual conditions, and the embodiments of this application do not limit this.

[0127] 306. The monitoring platform determines the environmental device impact parameters of each IoT device based on the material parameters, structural parameters, and environmental parameters of the multiple IoT devices.

[0128] In one possible implementation, the monitoring platform determines the environmental material impact parameters of each IoT device based on the material parameters of the multiple IoT devices and the environmental parameters. The monitoring platform determines the environmental structural impact parameters of each IoT device based on the structural parameters of the multiple IoT devices and the environmental parameters. The monitoring platform determines the environmental device impact parameters of each IoT device based on the environmental material impact parameters and environmental structural impact parameters of the multiple IoT devices.

[0129] Similar to the first reference environment working influence parameter and the second reference environment working influence parameter, the environment material influence parameter and the environment structure influence parameter in the above embodiment are also hidden variables without physical meaning.

[0130] In order to explain the above embodiment more clearly, the above embodiment will be described in several parts below.

[0131] In the first part, the monitoring platform determines the environmental material impact parameters of each IoT device based on the material parameters of the multiple IoT devices and the environmental parameters.

[0132] In one possible implementation, for any IoT device among the multiple IoT devices, the monitoring platform extracts features from the material parameters and the environmental parameters of the IoT device to obtain a third predicted feature of the IoT device. The monitoring platform then maps the third predicted feature to obtain an environmental material impact parameter for the IoT device.

[0133] For example, the monitoring platform concatenates the material parameters of the IoT device and the environmental parameters and performs multiple full joins to obtain a third prediction feature of the IoT device. The monitoring platform performs full joins and normalization on the third prediction feature to obtain the environmental material impact parameter of the IoT device.

[0134] In the second part, the monitoring platform determines the environmental structure impact parameters of each IoT device based on the structural parameters of the multiple IoT devices and the environmental parameters.

[0135] In one possible implementation, for any IoT device among the multiple IoT devices, the monitoring platform extracts features from the structural parameters and the environmental parameters of the IoT device to obtain a fourth prediction feature of the IoT device. The monitoring platform maps the fourth prediction feature to obtain an environmental structural impact parameter of the IoT device.

[0136] For example, the monitoring platform concatenates the structural parameters of the IoT device and the environmental parameters and performs multiple full joins to obtain a fourth prediction feature of the IoT device. The monitoring platform performs full joins and normalization on the fourth prediction feature to obtain the environmental structural impact parameter of the IoT device.

[0137] Part 3: The monitoring platform determines the environmental device impact parameters of each IoT device based on the environmental material impact parameters and the environmental structure impact parameters of the multiple IoT devices.

[0138] In a possible implementation, for any IoT device among the multiple IoT devices, the monitoring platform performs weighted fusion on the environmental material impact parameter and the environmental structure impact parameter of the IoT device to obtain the environmental device impact parameter of the IoT device.

[0139] Among them, the weights of weighted fusion are set by technical personnel according to actual conditions, and the embodiments of this application do not limit this.

[0140] 307. The monitoring platform determines the environmental impact parameters of each IoT device based on the environmental work impact parameters and environmental device impact parameters of each IoT device.

[0141] Among them, the environmental impact parameter is used to represent the impact of the environment on the IoT device.

[0142] In one possible implementation, the monitoring platform encodes the environmental impact parameters and environmental device impact parameters of each IoT device to obtain the environmental impact characteristics and environmental device impact characteristics of each IoT device. The monitoring platform then fuses the environmental impact characteristics and environmental device impact characteristics of each IoT device to obtain the environmental impact characteristics of each IoT device. The monitoring platform then decodes the environmental impact characteristics of each IoT device to obtain the environmental impact parameters of each IoT device.

[0143] In the above implementation, encoding refers to encoding based on the attention mechanism, and decoding refers to decoding based on the attention mechanism.

[0144] 308. The monitoring platform determines a target IoT device among the multiple IoT devices based on the device operating parameters, device stability parameters, and environmental impact parameters of the multiple IoT devices. The target IoT device is an IoT device with a high risk of failure.

[0145] Among them, the target IoT device is an IoT device with a high risk of failure. After determining and displaying the target IoT device, maintenance personnel can perform targeted maintenance on the target IoT device, thereby timely eliminating the failure risk of the new energy station and improving the stability of the new energy station.

[0146] In one possible implementation, the monitoring platform determines a device abnormality parameter for each IoT device based on the device operating parameters and device stability parameters of the multiple IoT devices. The device abnormality parameter indicates the degree of abnormality of the corresponding IoT device. The monitoring platform determines the target IoT device from the multiple IoT devices based on the device abnormality parameters of each IoT device and the environmental impact parameter.

[0147] In order to explain the above embodiment more clearly, the above embodiment will be described in several parts below.

[0148] In the first part, the monitoring platform determines the device abnormal parameters of each IoT device based on the device operating parameters and device stability parameters of the multiple IoT devices.

[0149] In one possible implementation, the monitoring platform inputs the operating parameters and stability parameters of each IoT device into an anomaly prediction model. The anomaly prediction model then encodes the operating parameters and stability parameters of each IoT device to obtain an anomaly signature for each IoT device. Using this anomaly prediction model, the monitoring platform fully concatenates and normalizes the anomaly signatures of each IoT device to obtain an anomaly parameter for each IoT device.

[0150] In the second part, the monitoring platform determines the target IoT device from the multiple IoT devices based on the device abnormality parameters of each IoT device and the environmental impact parameters.

[0151] In one possible implementation, the monitoring platform integrates the device anomaly parameters and environmental impact parameters of each IoT device to obtain a failure risk parameter for each IoT device. This failure risk parameter indicates the risk of a failure. The monitoring platform then identifies the IoT device with the highest failure risk parameter among the multiple IoT devices as the target IoT device.

[0152] For example, for any IoT device among multiple IoT devices, the monitoring platform performs a weighted fusion of the device anomaly parameters and environmental impact parameters of the IoT device to obtain the fault risk parameter of the IoT device. The monitoring platform then identifies the IoT device with the highest fault risk parameter among the multiple IoT devices as the target IoT device.

[0153] The weights of the weighted summation are set by technicians according to actual conditions, and are not limited in the present embodiment. The fault risk parameter is positively correlated with the fault risk. The higher the fault risk, the greater the fault risk parameter.

[0154] It should be noted that the above steps 301-308 are described by taking the execution subject as the monitoring platform as an example. In other possible implementations, the above steps 301-308 can also be executed by the server, and the embodiment of the present application does not limit this.

[0155] 309. The monitoring platform displays the target IoT device.

[0156] In a possible implementation, the monitoring platform highlights the target IoT device and displays the geographic location of the target IoT device.

[0157] Among them, highlighting includes highlighting. During the process of highlighting the target IoT device, the monitoring platform can also play alarm audio.

[0158] Under this implementation method, it helps managers to find target IoT devices in a timely manner, thereby performing targeted maintenance on the target IoT devices and improving the stability of the target cable.

[0159] All of the above optional technical solutions can be combined in any way to form optional embodiments of the present application, and will not be described in detail here.

[0160] Through the technical solution provided in the embodiment of the present application, the device operating parameters, surface temperature, material parameters, structural parameters and environmental parameters of the environment of multiple IoT devices in the new energy station are obtained. The device stability parameters are determined by using the acquired device operating parameters, surface temperature, material parameters and structural parameters, and the stability of the IoT device itself can be represented by the device stability parameters. The environmental impact parameters of the IoT device can be determined by using the device operating parameters, material parameters, structural parameters and environmental parameters, thereby quantifying the impact of the environment on the IoT device. Based on the device operating parameters, device stability parameters and environmental impact parameters of multiple IoT devices, the target IoT devices with a high risk of failure are determined and displayed, so that technical personnel can promptly maintain the target IoT devices and improve the stability of the new energy station.

[0161] Figure 4 This is a schematic diagram of the structure of an intelligent monitoring device for a new energy station based on the Internet of Things provided by the embodiment of the present application, see Figure 4 The device includes: an acquisition module 401, a device stability parameter determination module 402, an environmental impact parameter determination module 403 and a target Internet of Things device determination module 404.

[0162] The acquisition module 401 is used to obtain the device operating parameters, surface temperature, material parameters, structural parameters and environmental parameters of the environment of multiple Internet of Things devices in the new energy station. The Internet of Things devices are devices with computing capabilities in the new energy station.

[0163] The device stability parameter determination module 402 is used to determine the device stability parameter of each IoT device based on the device operating parameters, surface temperature, material parameters and structural parameters of the multiple IoT devices. The device stability parameter is used to represent the stability of the IoT device itself.

[0164] The environmental impact parameter determination module 403 is used to determine the environmental impact parameters of each IoT device based on the device operating parameters, material parameters, structural parameters and environmental parameters of the environment in which the multiple IoT devices are located. The environmental impact parameters are used to represent the impact of the environment on the IoT device.

[0165] The target IoT device determination module 404 is configured to determine and display a target IoT device among the multiple IoT devices based on the device operating parameters, device stability parameters, and environmental impact parameters of the multiple IoT devices. The target IoT device is an IoT device with a high risk of failure.

[0166] In one possible embodiment, the material parameters include specific heat capacity and thermal conductivity. The device stability parameter determination module 402 is configured to determine the basic heating value and abnormal operating parameters of each IoT device based on the device operating parameters of the multiple IoT devices. The basic heat transfer capacity of each IoT device is determined based on the specific heat capacity, the thermal conductivity, and the structural parameters. The device stability parameters of each IoT device are determined based on the basic heating value, basic heat transfer capacity, surface temperature, and abnormal operating parameters of each IoT device.

[0167] In one possible implementation, the device operating parameters include an operating log, operating heat parameters, and resource usage. The device stability parameter determination module 402 is configured to determine, for any IoT device among the multiple IoT devices, a basic heat output of the IoT device based on the operating heat parameters and resource usage of the IoT device. Furthermore, the device stability parameter determination module 402 is configured to determine an abnormal operating parameter of the IoT device based on the operating log of the IoT device.

[0168] In one possible implementation, the operating heating parameter includes a thermal power conversion parameter and a device heating value. The thermal power conversion parameter is used to represent the relationship between resource usage and thermal power. The device stability parameter determination module 402 is used to determine the operating heating value of the IoT device based on the thermal power conversion parameter and the resource usage. The operating heating value and the device heating value are combined to obtain a basic heating value of the IoT device. The device heating value refers to the heating value of the IoT device when it is not performing any operations.

[0169] In one possible implementation, the work log includes work data and data processing results, and the device stability parameter determination module 402 is configured to parse the work log to obtain the work data and data processing results, and determine the abnormal working parameters of the IoT device based on the work data and the data processing results.

[0170] In one possible implementation, the environmental parameter includes an ambient temperature. The device stability parameter determination module 402 is configured to determine, for each of the multiple IoT devices, a base temperature of the IoT device based on the base heat output and the base heat transfer of the IoT device. Based on the surface temperature and base temperature of the IoT device, determine a temperature anomaly parameter for the IoT device, the temperature anomaly parameter being used to indicate the degree of temperature anomaly. Based on the temperature anomaly parameter and the operating anomaly parameter of the IoT device, determine a device stability parameter for the IoT device.

[0171] In one possible implementation, the device stability parameter determination module 402 is configured to encode the temperature anomaly parameter and the operational anomaly parameter to obtain a temperature anomaly signature and an operational anomaly signature of the IoT device. The temperature anomaly signature and the operational anomaly signature are then integrated to obtain a device stability prediction signature of the IoT device. The device stability prediction signature is then decoded to obtain the device stability parameter.

[0172] In one possible implementation, the environmental impact parameter determination module 403 is configured to determine the environmental operating impact parameter of each IoT device based on the device operating parameters and environmental parameters of the multiple IoT devices. The environmental device impact parameter of each IoT device is determined based on the material parameters, structural parameters, and environmental parameters of the multiple IoT devices. The environmental impact parameter of each IoT device is determined based on the environmental operating impact parameter and environmental device impact parameter of each IoT device.

[0173] In one possible implementation, the device operating parameters include an operating log and an operating heat parameter, and the environmental impact parameter determination module 403 is configured to determine a first reference environmental operating impact parameter for each IoT device based on the operating logs of the multiple IoT devices and the environmental parameters. Determine a second reference environmental operating impact parameter for each IoT device based on the operating heat parameter of the multiple IoT devices and the environmental parameters. Determine the environmental operating impact parameter for each IoT device based on the first reference environmental operating impact parameter and the second reference environmental operating impact parameter of the multiple IoT devices.

[0174] In one possible implementation, the environmental impact parameter determination module 403 is configured to determine an environmental material impact parameter for each IoT device based on the material parameters of the multiple IoT devices and the environmental parameters. Determine an environmental structural impact parameter for each IoT device based on the structural parameters of the multiple IoT devices and the environmental parameters. Determine an environmental device impact parameter for each IoT device based on the environmental material impact parameters and environmental structural impact parameters of the multiple IoT devices.

[0175] In one possible implementation, the environmental impact parameter determination module 403 is configured to encode the environmental operating impact parameter and environmental device impact parameter of each IoT device to obtain the environmental operating impact characteristics and environmental device impact characteristics of each IoT device. The environmental operating impact characteristics and environmental device impact characteristics of each IoT device are then integrated to obtain the environmental impact characteristics of each IoT device. The environmental impact characteristics of each IoT device are then decoded to obtain the environmental impact parameters of each IoT device.

[0176] In one possible implementation, the target IoT device determination module 404 is configured to determine a device abnormality parameter for each IoT device based on the device operating parameters and device stability parameters of the multiple IoT devices, where the device abnormality parameter indicates the degree of abnormality of the corresponding IoT device. Based on the device abnormality parameters of each IoT device and the environmental impact parameter, the target IoT device is determined from the multiple IoT devices. The target IoT device is highlighted and its geographic location is displayed.

[0177] In one possible implementation, the target IoT device determination module 404 is configured to combine device anomaly parameters and environmental impact parameters of each IoT device to obtain a failure risk parameter for each IoT device, where the failure risk parameter indicates the risk of a failure. The IoT device with the highest failure risk parameter among the multiple IoT devices is determined as the target IoT device.

[0178] It should be noted that the above-mentioned embodiment provides an example of the division of the above-mentioned functional modules when monitoring the new energy station based on the Internet of Things. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the monitoring platform can be divided into different functional modules to complete all or part of the functions described above. In addition, the above-mentioned embodiment provides an example of the same concept as the embodiment of the method for intelligent monitoring of new energy stations based on the Internet of Things. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0179] Through the technical solution provided in the embodiment of the present application, the device operating parameters, surface temperature, material parameters, structural parameters and environmental parameters of the environment of multiple IoT devices in the new energy station are obtained. The device stability parameters are determined by using the acquired device operating parameters, surface temperature, material parameters and structural parameters, and the stability of the IoT device itself can be represented by the device stability parameters. The environmental impact parameters of the IoT device can be determined by using the device operating parameters, material parameters, structural parameters and environmental parameters, thereby quantifying the impact of the environment on the IoT device. Based on the device operating parameters, device stability parameters and environmental impact parameters of multiple IoT devices, the target IoT devices with a high risk of failure are determined and displayed, so that technical personnel can promptly maintain the target IoT devices and improve the stability of the new energy station.

[0180] Figure 5This is a structural diagram of an intelligent monitoring system for a new energy station based on the Internet of Things provided in an embodiment of the present application. The system 500 may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) 501 and one or more memories 502, wherein the one or more memories 502 store at least one computer program, and the at least one computer program is loaded and executed by the one or more processors 501 to implement the methods provided in the above-mentioned various method embodiments. Of course, the monitoring platform 500 may also have components such as a wired or wireless network interface, a keyboard, and an input and output interface for input and output. The monitoring platform 500 may also include other components for implementing the functions of Internet of Things devices, which will not be described in detail here.

[0181] In an exemplary embodiment, a computer-readable storage medium is also provided, such as a memory including a computer program. The computer program can be executed by a processor to implement the IoT-based new energy station intelligent monitoring method described in the above embodiment. For example, the computer-readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, or an optical data storage IoT device.

[0182] In an exemplary embodiment, a computer program product or computer program is also provided, which includes a program code, which is stored in a computer-readable storage medium. The processor of the monitoring platform reads the program code from the computer-readable storage medium, and the processor executes the program code, so that the monitoring platform executes the above-mentioned new energy station intelligent monitoring method based on the Internet of Things.

[0183] In some embodiments, the computer program involved in the embodiments of the present application can be deployed and executed on a monitoring platform, or on multiple monitoring platforms located at one location, or on multiple monitoring platforms distributed at multiple locations and interconnected through a communication network. Multiple monitoring platforms distributed at multiple locations and interconnected through a communication network can constitute a blockchain system.

[0184] Those skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware, or may be accomplished by a program to instruct the relevant hardware, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0185] The above are only optional embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

Claims

1. A new energy station intelligent monitoring method based on the Internet of Things, characterized in that: The method comprises: Obtaining device operating parameters, surface temperature, material parameters, structural parameters, and environmental parameters of a plurality of IoT devices in a new energy station, wherein the IoT devices are devices with computing capabilities in the new energy station; Determine, based on device operating parameters, surface temperatures, material parameters, and structural parameters of the plurality of IoT devices, a device stability parameter for each IoT device, the device stability parameter being used to indicate a stability condition of the IoT device itself; Determine an environmental impact parameter of each of the IoT devices based on device operating parameters, material parameters, structural parameters, and environmental parameters of the environments in which the multiple IoT devices are located, where the environmental impact parameter is used to represent the impact of the environment on the IoT device; Based on the device operating parameters, device stability parameters, and environmental impact parameters of the multiple IoT devices, a target IoT device among the multiple IoT devices is determined and displayed, where the target IoT device is an IoT device with a high risk of failure.

2. The method according to claim 1, characterized in that The material parameters include specific heat capacity and thermal conductivity, and determining the device stability parameters of each of the IoT devices based on the device operating parameters, surface temperature, material parameters, and structural parameters of the multiple IoT devices includes: Determine, based on the device operating parameters of the plurality of IoT devices, a basic heating value and an operating abnormality parameter of each of the IoT devices; Determining a basic heat transfer capacity of each of the IoT devices based on the specific heat capacity, the thermal conductivity coefficient, and the structural parameters; Based on the basic heat output, basic heat transfer, surface temperature and abnormal working parameters of each of the IoT devices, the device stability parameters of each of the IoT devices are determined.

3. The method according to claim 2, characterized in that The device operating parameters include a working log, a working heating parameter, and a resource occupancy amount. The determining of the basic heating value and the working abnormality parameter of each of the IoT devices based on the device operating parameters of the plurality of IoT devices includes: For any one of the plurality of IoT devices, determining a basic heating value of the IoT device based on an operating heating parameter and resource usage of the IoT device; Based on the work log of the Internet of Things device, determine the abnormal working parameters of the Internet of Things device.

4. The method according to claim 3, characterized in that The working heating parameter includes a thermal power conversion parameter and a device heating value, wherein the thermal power conversion parameter is used to represent the relationship between resource occupancy and thermal power. Determining the basic heating value of the IoT device based on the working heating parameter and resource occupancy of the IoT device includes: Determining an operating heat output of the IoT device based on the thermal power conversion parameter and the resource occupancy; The operating calorific value and the device calorific value are combined to obtain the basic calorific value of the IoT device, where the device calorific value refers to the calorific value when the IoT device is not performing any operation.

5. The method according to claim 3, characterized in that The work log includes work data and data processing results. The determining of abnormal working parameters of the IoT device based on the work log of the IoT device includes: Parsing the work log to obtain the work data and data processing results; Based on the working data and the data processing result, the working abnormality parameters of the Internet of Things device are determined.

6. The method according to claim 2, characterized in that The environmental parameters include the ambient temperature, and determining the device stability parameters of each of the IoT devices based on the basic heat output, basic heat transfer, surface temperature, and the abnormal working parameters of each of the IoT devices includes: For any one of the plurality of IoT devices, obtaining a basic temperature of the IoT device based on a basic heat output and a basic heat transfer value of the IoT device; Determining a temperature anomaly parameter of the IoT device based on the surface temperature and the base temperature of the IoT device, where the temperature anomaly parameter is used to indicate a degree of temperature anomaly; Based on the temperature abnormality parameter and the working abnormality parameter of the Internet of Things device, a device stability parameter of the Internet of Things device is determined.

7. The method according to claim 6, characterized in that The determining, based on the temperature anomaly parameter and the operating anomaly parameter of the IoT device, a device stability parameter of the IoT device includes: Encoding the temperature abnormality parameter and the operation abnormality parameter to obtain the temperature abnormality characteristics and the operation abnormality characteristics of the Internet of Things device; The temperature anomaly feature and the working anomaly feature are combined to obtain a device stability prediction feature of the IoT device; The device stability prediction feature is decoded to obtain the device stability parameter.

8. The method according to claim 1, characterized in that The determining of the environmental impact parameter of each of the IoT devices based on device operating parameters, material parameters, structural parameters, and environmental parameters of the environment in which the plurality of IoT devices are located includes: Determining an environmental operating impact parameter of each of the IoT devices based on device operating parameters and environmental parameters of the plurality of IoT devices; Determining an environmental device impact parameter of each of the IoT devices based on material parameters, structural parameters, and environmental parameters of the plurality of IoT devices; Based on the environmental working impact parameters and environmental equipment impact parameters of each of the Internet of Things devices, the environmental impact parameters of each of the Internet of Things devices are determined.

9. The method according to claim 8, characterized in that The device operating parameters include an operating log and an operating heating parameter. The determining of the environmental operating impact parameter of each of the IoT devices based on the device operating parameters and environmental parameters of the plurality of IoT devices includes: Determining a first reference environment work impact parameter of each of the IoT devices based on the work logs of the plurality of IoT devices and the environmental parameters; Determine a second reference environment working impact parameter of each of the Internet of Things devices based on the working heating parameters of the multiple Internet of Things devices and the environmental parameters; Based on the first reference environmental operation impact parameters and the second reference environmental operation impact parameters of the multiple Internet of Things devices, the environmental operation impact parameters of each of the Internet of Things devices are determined.

10. The method according to claim 8, characterized in that The determining, based on the material parameters, structural parameters, and environmental parameters of the plurality of IoT devices, an environmental device impact parameter of each IoT device includes: Determining an environmental material impact parameter of each of the IoT devices based on the material parameters of the plurality of IoT devices and the environmental parameters; Determining an environmental structural impact parameter of each of the IoT devices based on the structural parameters of the plurality of IoT devices and the environmental parameters; Based on the environmental material impact parameters and environmental structure impact parameters of the multiple Internet of Things devices, the environmental device impact parameter of each of the Internet of Things devices is determined.

11. The method according to claim 8, characterized in that Determining the environmental impact parameters of each of the IoT devices based on the environmental working impact parameters and the environmental device impact parameters of each of the IoT devices includes: Encoding the environmental work impact parameters and environmental equipment impact parameters of each of the IoT devices respectively to obtain the environmental work impact characteristics and environmental equipment impact characteristics of each of the IoT devices; fusing the environmental work impact characteristics and environmental device impact characteristics of each of the IoT devices to obtain the environmental impact characteristics of each of the IoT devices; The environmental impact characteristics of each of the IoT devices are decoded to obtain environmental impact parameters of each of the IoT devices.

12. The method according to claim 1, characterized in that The determining and displaying a target IoT device among the plurality of IoT devices based on device operating parameters, device stability parameters, and environmental impact parameters of the plurality of IoT devices includes: Determining, based on the device operating parameters and device stability parameters of the plurality of IoT devices, a device abnormality parameter of each IoT device, wherein the device abnormality parameter is used to indicate a degree of abnormality of the corresponding IoT device; Determining the target IoT device from the plurality of IoT devices based on the device abnormality parameters of each IoT device and the environmental impact parameters; The target IoT device is highlighted and its geographic location is displayed.

13. The method according to claim 12, characterized in that The determining the target IoT device from the plurality of IoT devices based on the device abnormality parameters and the environmental impact parameters of each IoT device includes: The device abnormality parameters and environmental impact parameters of each of the IoT devices are integrated to obtain a failure risk parameter of each of the IoT devices, where the failure risk parameter is used to indicate the risk of a failure; The IoT device with the highest failure risk parameter among the multiple IoT devices is determined as the target IoT device.

14. An intelligent monitoring system for new energy stations based on the Internet of Things, characterized in that: The system includes one or more processors and one or more memories, wherein at least one computer program is stored in the one or more memories, and the computer program is loaded and executed by the one or more processors to implement the intelligent monitoring method of new energy stations based on the Internet of Things as described in any one of claims 1 to 13.

Images