Building energy data collection system, method and electronic equipment

By dividing the data acquisition network in the building energy consumption monitoring system and using data relay nodes for anomaly analysis and preprocessing, the inaccuracy of data caused by equipment failures during the data acquisition process was solved, enabling accurate energy data acquisition and real-time monitoring, and reducing operating costs.

CN118694794BActive Publication Date: 2024-11-05CECEP WEILV (BEIJING) TECH CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202411165544.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-23
Publication Date
2024-11-05
Estimated Expiration
2044-08-23

AI Technical Summary

Technical Problem

Existing building energy consumption monitoring systems are susceptible to problems such as damage, relocation, malfunction, and fire during the data collection process, leading to inaccurate data, affecting project delivery cycles, and increasing operating costs.

Method used

By dividing the data acquisition network and using data relay nodes for anomaly analysis, abnormal data is identified and preprocessed. Combined with image recognition technology, changes in the installation location of the acquisition terminal equipment are determined, and early warning information is sent in a timely manner to achieve rapid recovery from abnormal situations.

Benefits of technology

This ensures the accuracy and reliability of collected energy data, reduces the data processing pressure on the cloud service platform, improves the effectiveness of data analysis, reduces operating costs, and enables real-time monitoring of the on-site environment and equipment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118694794B_ABST
    Figure CN118694794B_ABST
Patent Text Reader

Abstract

The present application relates to the technical field of energy data monitoring, and provides a building energy data collection system, method and electronic equipment, the system comprising at least one data collection network and a data transfer node; the data collection network is connected with a data collection node and a data transmission node for collecting energy data; wherein each of the data collection nodes sends the collected energy data to the data transfer node through the data transmission node; the data transfer node receives the energy data sent by the data transmission node, and performs an abnormality analysis on the energy data to determine the abnormal cause corresponding to the abnormal energy data, and pre-processes the abnormal energy data according to the pre-processing method corresponding to the abnormal cause. The system can timely discover the abnormality during the collection process, locate the abnormal cause, and then reasonably select the pre-processing method of the abnormal energy data to ensure the reliability of the data analysis basis.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of energy data monitoring, and in particular to a building energy data collection system, method and electronic equipment. Background Art

[0002] With the development of intelligent buildings, building energy consumption monitoring systems have become an important tool for energy conservation, emission reduction and equipment maintenance.

[0003] After winning the bid for the building comprehensive energy project, in order to formulate long-term energy planning and energy-saving strategies, it is necessary to conduct efficiency tests on a wide variety of energy-consuming equipment such as the building energy system, understand the energy consumption of each device, and the usage requirements of each energy-consuming equipment. Therefore, it is necessary to use the building energy consumption monitoring system to collect test data and daily usage data of various energy-consuming equipment.

[0004] In existing energy consumption monitoring systems, various data collection devices are usually deployed on site and the data is sent to the background. When the amount of data collected meets the analysis requirements, the background will analyze the data in a unified manner to assist analysts in formulating energy-saving strategies.

[0005] However, in order to obtain comprehensive energy consumption data, the collection cycle is often long. During the process, there may be problems such as damage or displacement of the collection terminal equipment, failure of the energy-consuming equipment, fire on site, water immersion, etc., which makes the collected energy consumption data unable to accurately reflect the actual situation of the equipment. The relevant data needs to be collected again, resulting in the subsequent analysis work cannot be carried out smoothly on time, which not only affects the project delivery cycle, but also increases the project operating costs. Summary of the invention

[0006] In order to avoid the collected energy consumption data failing to accurately reflect the actual situation of the energy-consuming equipment, timely discover the cause of the data anomaly, and thus guide on-site personnel to quickly take relevant recovery measures, an embodiment of the present application provides a building energy data collection system, the system comprising at least one data collection network and a data transfer node; wherein the data collection network is connected with a data collection node and a data transmission node for collecting energy data; wherein each of the data collection nodes sends the collected energy data to the data transfer node through the data transmission node; the data transfer node receives the energy data sent by the data transmission node, and performs an abnormality analysis on the energy data; when it is determined that the energy data is abnormal, the data collection node corresponding to the abnormal energy data is determined to be a node to be detected, and detection instructions are respectively sent to the data transmission nodes in each of the data collection networks to instruct the detection nodes in each of the data collection networks to send detection signals to the node to be detected according to preset requirements; and the detection data returned by the node to be detected is analyzed to determine the abnormal cause corresponding to the abnormal energy data, and the abnormal energy data is preprocessed according to the preprocessing method corresponding to the abnormal cause.

[0007] Based on the above technical scheme, by dividing the data collection network, it is possible to achieve classified management of various data collection nodes and realize on-demand networking, so as to facilitate the unified management of similar data; by exchanging data between data transmission nodes and data transfer nodes, the network communication pressure of data transfer nodes can be reduced; by identifying and analyzing abnormal energy data through data transfer nodes to determine the cause of the abnormality, and selecting a suitable method to pre-process the abnormal energy data based on the cause of the abnormality, not only can the abnormal energy data be reasonably corrected in time, ensuring that the data obtained by the cloud service platform can be directly used for energy analysis, and accurate and reliable, but also reduce the data processing pressure of the cloud service platform. Furthermore, by performing real-time detection on the detection node to determine whether the abnormal cause includes abnormality of the collection terminal equipment, the fault of the collection terminal equipment is accurately located in time, which is convenient for on-site personnel to restore the abnormality in time, ensure that the state of the collection terminal equipment is normal and the installation method meets the requirements, and then ensure that the collected energy data is accurate and reliable.

[0008] In one implementation, each of the data collection networks is divided based on collection objects.

[0009] In one implementation, the data collection node accesses the data collection network by means of virtual access.

[0010] Based on the above technical solution, when the hardware of the data collection terminal device is limited, it is possible to access multiple data collection networks, so that data collection can be performed according to the collection requirements of each access network, so that each data collection network can completely collect energy data that meets the preset requirements.

[0011] In one implementation, the system further includes a client, and the data transfer node sends abnormal warning information to on-site personnel through the client, and receives abnormal detection results fed back by on-site personnel through the client.

[0012] Based on the above method, abnormal warning information is sent to on-site personnel through the client, so that the on-site personnel can check and confirm the on-site situation in time according to the abnormal warning information, and restore the abnormal situation as soon as possible.

[0013] In one implementation, the system further includes a cloud service platform, and after preprocessing the energy data, the data transfer node sends the energy consumption analysis data obtained after the preprocessing to the cloud service platform.

[0014] Based on the above technical solution, the data transfer node pre-processes the energy data to obtain the corresponding energy consumption analysis data to reduce the data processing pressure of the cloud service platform.

[0015] Based on the same inventive concept, an embodiment of the present application also provides a building energy data collection method, which is applied to the above-mentioned building energy data collection system and is executed by the data transfer node, including: receiving the energy data reported by the data transmission node; performing abnormality analysis on the energy data; when it is judged that the energy data is abnormal, determining that the data collection node corresponding to the abnormal energy data is a node to be detected, and sending a detection instruction to the data transmission node in each of the data collection networks; wherein the detection instruction is used to instruct the detection node in each of the data collection networks to send a detection signal to the node to be detected according to preset requirements; receiving the detection data returned by the node to be detected; analyzing the detection data to determine the abnormal cause corresponding to the abnormal energy data, and preprocessing the abnormal energy data according to the preprocessing method corresponding to the abnormal cause.

[0016] In one implementation, the method for performing abnormality analysis on the energy data includes: when the data transfer node receives the encapsulated energy data sent by the data transmission node, the data transfer node calculates the size of the encapsulated energy data, and determines whether there is an abnormality in the encapsulated energy data based on the standard amount of encapsulated data corresponding to the data transmission node.

[0017] Based on the above technical solution, by calculating and comparing the size of the encapsulated energy data, it is possible to determine whether there is abnormal energy data. The logic is simple and the processing is fast.

[0018] In one implementation, the analyzing the detection data to determine the abnormal cause corresponding to the abnormal energy data includes: generating a detection map based on the detection data, and identifying the detection map based on an image recognition model to determine whether the installation position of the node to be detected has changed.

[0019] Based on the above technical solution, by converting the detection data into a detection map and determining whether the installation position of the acquisition terminal device has changed based on image recognition technology, various normal interference conditions can be simulated in the training sample acquisition stage, and corresponding training samples can be obtained to fully train the image recognition model and improve recognition accuracy.

[0020] In one implementation, the method further includes receiving abnormality inspection results fed back by on-site personnel, and when the abnormality inspection results indicate that the cause of the abnormality is inaccurate, sending a request including the cause of the abnormality and the abnormality inspection results to a cloud service platform to request the cloud service platform to optimize the abnormality analysis method.

[0021] Based on the above technical solutions, the abnormality analysis method can be continuously optimized, thereby continuously improving the early warning accuracy of the data transfer node.

[0022] In addition, an embodiment of the present application also provides an electronic device, which includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor, and the program or instruction implements the above method when executed by the processor.

[0023] In summary, the embodiments of the present application at least include the following beneficial technical effects:

[0024] 1. Timely discover anomalies in real-time collected data and pre-process the abnormal data to ensure the effectiveness of the analyzed data.

[0025] 2. By locating the cause of the abnormality, real-time monitoring and early warning of the on-site environment, target equipment and acquisition terminal equipment can be achieved to avoid invalid collection data caused by the abnormal situation being unable to be restored for a long time.

[0026] 3. Realize multi-network access of acquisition terminal devices based on virtual access to meet different networking requirements.

[0027] 4. By sinking data pre-processing to the data transfer node close to the site, it not only reduces the data processing pressure of the cloud service platform, but also enables the data transfer node to detect abnormal situations in a timely manner, assisting the building management party or on-site personnel to deal with abnormal situations in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The drawings constituting a part of the present application are used to provide further understanding of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute improper limitations on the present application.

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. 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 creative work.

[0030] Figure 1 A structural schematic diagram of a building energy data acquisition system provided in an embodiment of the present application is shown.

[0031] Figure 2 A schematic diagram of the structure of a building energy data collection system in an application example of the first embodiment of the present application is shown.

[0032] Figure 3 A flow chart of a building energy data collection system method provided in an embodiment of the present application is shown.

[0033] Figure 4 The detection diagram provided in the embodiment of the present application is shown. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0035] In the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more, and various digital numbers are only used for the convenience of description and are not used to limit the scope of the embodiments of the present application.

[0036] The features, structures or characteristics in this application may be combined in one or more embodiments in any suitable manner. In various embodiments of this application, the size of the sequence number of each process does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0037] Some optional features in the embodiments of the present application may be implemented independently in some scenarios without relying on other features to solve corresponding technical problems and achieve corresponding effects. They may also be combined with other features in some scenarios as needed.

[0038] In this application, unless otherwise specified, the same or similar parts between the various embodiments can refer to each other. In the various embodiments of this application, if there is no special description and logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships. The implementation methods of this application do not constitute a limitation on the scope of protection of this application.

[0039] The embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0040] Please refer to Figure 1 The building energy data acquisition system provided in the embodiment of the present application includes a data acquisition network 11, a data transfer node 12, and a cloud service platform 13.

[0041] The data collection network 11 is connected with a data collection node 111 for collecting energy data and a data transmission node 112. Specifically, at least one data collection node 111 is connected to a data collection network 11, and the data collection node 111 is used to collect energy information of target equipment in the building, corresponding to a collection terminal device. In an example, the target equipment is any energy-consuming equipment related to the energy optimization project in the building. The specific type is related to the building site, and can include one or more of lighting equipment, temperature control equipment, power equipment, and business equipment.

[0042] The acquisition terminal device is used to collect relevant energy data of the target device, such as external devices such as electricity meters, flow meters, temperature and humidity sensors, cold and heat source meters, infrared meter readers, etc. It can also be the target device itself with an external data interface, such as an air conditioner host.

[0043] The data transmission node 112 is a data collection node in the data collection network.

[0044] In one implementation, after each data acquisition node 111 is connected to the data acquisition network 11, it sends its own equipment performance data to other data acquisition nodes in the network. After receiving the equipment performance data sent by other data acquisition nodes, based on the same preset rules, it evaluates the equipment performance of each data acquisition node in the network, and selects a data acquisition node that meets the requirements as a data transmission node. In other words, the data acquisition node and the data transmission node correspond to the same acquisition terminal device.

[0045] Among them, the preset rules include the equipment performance data that can support the resources that the data transmission node needs to occupy when completing data interaction. When there are multiple data collection nodes that meet the requirements, they are selected in turn according to the storage space size, collection task volume and other indicators. For example, the largest storage space is selected first. When the number of selected data collection nodes is greater than one, the ones with less collection tasks are selected. Among them, the collection task volume is related to the collection cycle. The shorter the collection cycle, the greater the task volume. Based on this, each data collection node in the network can select the data transmission node based on the same standard, which is both fast and consistent.

[0046] In another implementation, the data transmission node 112 is a network device dedicated to implementing network data interaction.

[0047] It can be understood that, in actual application, the layout of the data transmission nodes 12 in each data acquisition network can be determined according to actual conditions.

[0048] It is worth noting that due to the differences in building conditions and optimization requirements of various energy optimization projects, the networking method of the data collection network can be selected according to the specific situation.

[0049] In one implementation, the data acquisition nodes 111 may be networked based on the data types corresponding to them. For example, the data acquisition nodes 111 for collecting electricity consumption data, the data acquisition nodes 111 for collecting illumination data, the data acquisition nodes 111 for collecting ambient temperature and humidity, and the data acquisition nodes 111 for collecting data related to cold and heat sources may be networked.

[0050] In this way, the data types and data formats corresponding to each data acquisition node 111 in the same data acquisition network 11 are the same, which makes it easy to maintain the uniformity of the format and transmission method of the data within each data acquisition network. Furthermore, since the types of acquisition terminal devices that collect the same type of data are often roughly the same, the network access method of each acquisition terminal device is also the same, which facilitates the management of each data acquisition network.

[0051] In another implementation, the network can be divided based on the collection object corresponding to the data collection node 111, where the collection object is one or more target devices. In one example, the data collection demand analysis can be performed on each target device first, and all data collection nodes 111 used to collect energy data related to the target device can be determined, and these data collection nodes 111 are grouped into a data collection network 11. Based on this, each target device corresponds to a data collection network, which can facilitate independent monitoring of the target device.

[0052] It is worth noting that in this embodiment, there may be a situation where a data acquisition node 111 has multiple acquisition objects, that is, a data acquisition node needs to access multiple data acquisition networks. Therefore, in the networking process, it is necessary to first determine whether these acquisition terminal devices have enough network interfaces to ensure that they can be connected to the corresponding data acquisition networks through different network interfaces.

[0053] However, in actual applications, due to the hardware conditions of the collection terminal equipment, the number of network interfaces of some collection terminals may not meet the access requirements. In order to overcome this problem, a virtual access method is also provided in the embodiment of the present application based on the above implementation method to synchronize the collection data of this type of data collection node to the data collection network to be accessed.

[0054] In one example, the implementation method of virtual access includes first connecting the data acquisition node 111 to a data acquisition network. When the acquisition terminal device reports data, the network identifiers corresponding to other data acquisition networks to be connected are encapsulated and sent to the data transfer node through the data transmission node. The data transfer node determines the other data acquisition networks to which the collected data belongs through the encapsulated network identifiers.

[0055] In another example, in order to meet the different data collection cycle requirements of each target device, the implementation method of virtual access includes first connecting the data collection node 111 to a data collection network, and configuring the collection cycle requirements of each data collection network to be connected to the data collection node 111 on the data transmission node 112 in the data collection network. Based on each collection cycle requirement, the data transmission node 112 requests data from the data collection node 111 and sends the collected energy data to the corresponding data collection network.

[0056] Among them, each data transmission node 112 communicates with each other through a first designated port, and the first designated port is dedicated to sending and receiving interactive data between each data transmission node 112. Each data transmission node 112 is also provided with a second designated port for data interaction with the data transfer node 12. In this way, each data transmission node 112 can determine the processing method of the received data according to the data receiving port. For example, in the above example, the data transmission node 112 encapsulates the collected data received through the first designated port with other collected data in the network, and sends it to the data transfer node 12 through the second designated port.

[0057] Each data collection node 111 in each data collection network 11 reports the collected energy data to the corresponding data transmission node 112 based on the preset collection cycle, and the data transmission node 112 encapsulates the energy data received within the reporting cycle according to the preset reporting cycle, and sends it to the data transfer node 12 through the second designated port, wherein the data transmission node 112 and the data transfer node 12 perform data exchange based on the wireless network. The reporting cycle is greater than the collection cycle, for example, the reporting cycle is 4 hours, and the collection cycle is 1 hour or 1 minute. It can be understood that the target devices and collection data types corresponding to each data collection node 111 are different, so the collection cycle may also be different.

[0058] The data transfer node 12 can be deployed in a central control room in a building, or in a data center close to the building area. The data transfer node 12 is used to perform abnormal analysis and preprocessing on the received energy data, and send the preprocessing results to the cloud service platform 13.

[0059] In one implementation, the data transfer node 12 is only used to process the energy data of one or several specific buildings, and is deployed in the private intranet of these buildings. It interacts with each data transmission node 112 through the intranet, and interacts with the cloud platform service 13 through a dedicated line, thereby ensuring data security.

[0060] In another implementation, the data transfer node 12 can be used to process the energy data of each project building in the target area, wherein the target area can be divided based on geographical location or determined based on the distribution of 5G base stations, and the climate environment in the same target area is basically the same. In one example, the division of the target area can be confirmed based on historical climate data.

[0061] After the data transfer node 12 receives the energy data sent from the data transmission node 112, it first performs an abnormality analysis on the energy data to determine whether the energy data is abnormal. When it is determined that the energy data is abnormal, the data collection node corresponding to the abnormal energy data is determined as the node to be detected based on the data collection node identifier carried in the energy data, and a detection instruction is sent to the data transmission node 112 in each data collection network to which the node to be detected belongs, so as to instruct the data collection nodes (i.e., detection nodes) in each data collection network that can be used to detect the validity of the node to be detected to send detection signals to the node to be detected in turn; and the detection data returned by the node to be detected is analyzed to determine the cause of the abnormality.

[0062] After determining the cause of the abnormality, the data transfer node 12 can also send corresponding warning information to the on-site personnel through the client application or calling the third-party application interface, so that the on-site personnel can quickly restore the abnormality, such as restoring the correct installation of the acquisition terminal equipment, restarting or repairing the target equipment, and the on-site personnel can feedback the abnormality inspection results through the client. Among them, the on-site personnel can be building management personnel or on-site personnel of the energy project team.

[0063] Furthermore, when the abnormality check results determine that the target device is operating abnormally, the data transfer node 12 adds a mark to the abnormal energy data during the pre-processing of the energy data to indicate that the corresponding target device is operating abnormally, and at the same time tracks the relevant energy data of the target device to determine whether the abnormality type of the relevant energy data is consistent with the abnormal operation of the target device. If not, the collection terminal devices corresponding to the energy data are detected to determine whether there is an abnormality in the collection terminal devices.

[0064] The cloud service platform 13 is deployed in the cloud server, and is used to receive the energy efficiency analysis data sent by the data transfer node, and perform energy efficiency analysis statistics on each target device based on the energy efficiency analysis data, and display it to the analyst, so that the analyst can provide an optimized control solution for each target device in the building according to the energy efficiency analysis statistics results to save building energy consumption. It can be understood that according to the distribution of building energy-saving projects, multiple data transfer nodes 12 can be set in the system, all of which communicate data with the cloud service platform 13.

[0065] The system provided in the embodiment of the present application is described in detail below with reference to a specific application example.

[0066] Please refer to Figure 2The data transfer node is deployed in the central control room. The four data acquisition networks use wireless temperature and humidity sensors, smart circuit breakers, NB-IoT (Narrow Band Internet of Things) modules and 4G modules as data transmission nodes to interact with the data transfer nodes.

[0067] Wireless temperature and humidity sensors are used to detect the outdoor temperature of a building.

[0068] Smart circuit breakers are used to control the switching of electrical equipment.

[0069] A portable heat meter is connected to the data acquisition network where the NB-IoT module is located. The portable heat meter is installed on the chilled water pipe in the refrigeration room to detect the supply and return water temperature, supply and return water temperature difference, flow rate, and cooling capacity of the chilled water pipe.

[0070] The data collection network where the 4G module is located is connected to multiple electricity meters, air-conditioning hosts, and infrared meter readers for collecting total electricity consumption data.

[0071] These data acquisition terminal devices are connected to the corresponding data acquisition network by wireless or wired means. The wireless access method includes the LORA communication protocol, and the wired access method includes the 485 bus. The wired transmission method can ensure stable data transmission, and the wireless transmission method can solve the problem that some building spaces cannot be drilled and wired.

[0072] Based on the above-mentioned building energy data collection system, relevant energy data collection terminal devices are deployed on energy-consuming equipment in the building to collect relevant energy data, and these collection terminal devices are divided into different data collection networks to facilitate the classification management of the collection terminal devices and realize on-demand networking. By having the data transmission node be responsible for the interaction of data inside and outside the network, unified control of data within the network can be achieved, and the pressure on the communication port of the data transfer node can be reduced, saving network connection resources. Through the identification and analysis of abnormal energy data by data transfer data, real-time monitoring of the on-site environment and related equipment can be achieved. At the same time, the abnormal energy data is pre-processed based on the abnormal cause, which can ensure that the data reported to the cloud service platform is valid and relatively accurate, thereby minimizing the occurrence of invalid collection due to the inability of the collected data to truly reflect the equipment status.

[0073] Based on the building energy data collection system provided in the above embodiment, the present application embodiment also provides a building energy data collection method, please refer to Figure 3 The method is executed by the data transfer node 12 and specifically includes the following steps:

[0074] S301, receiving energy data reported by a data transmission node.

[0075] In one implementation, in order to avoid over-congestion of the data interface port, a corresponding reporting period can be configured for each data transmission node in advance, and each reporting period is staggered. The data transmission node encapsulates the energy data received within the period according to the preset reporting period and sends it to the data transfer node.

[0076] S302, performing abnormality analysis on energy data.

[0077] Specifically, when receiving the encapsulated energy data, the data transfer node first calculates the size of the encapsulated energy data, and determines whether there is an abnormality based on the size of the historical encapsulated energy data uploaded by the data transmission node.

[0078] In one example, the data collection node collects and reports data according to a preset collection cycle. At the same time, the data collection node can first analyze the collected energy data. If it is found that the currently collected energy data does not match the predicted change trend, the number of collections is increased to continuously collect data from the target device, and the collected data is sent to the data transmission node in real time. The predicted change trend is obtained by the data transfer node based on historical data analysis. For example, the linear relationship between energy data and time can be obtained by fitting historical data, and the predicted change trend can be obtained based on the linear relationship and the current collection time.

[0079] It can be seen that in this case, the amount of data that needs to be encapsulated will be larger than the standard amount of data obtained after data collection is performed completely according to the collection cycle. Therefore, the data transfer node can directly determine whether the energy data is abnormal by the size of the received encapsulated energy data.

[0080] Correspondingly, since the amount of data collected by each data collection node is generally fixed, if the currently received packaged energy data is smaller than the standard data amount, it can be determined that there is a lack of collected data and the energy data is abnormal.

[0081] In another example, the data transfer node may parse the encapsulated energy data and determine whether each energy data is abnormal based on a preset threshold range corresponding to each energy data. For example, energy data within the preset threshold range is normal data, otherwise it is abnormal data.

[0082] Optionally, the preset threshold range includes a numerical range and / or a numerical fluctuation range, wherein the numerical range is used to indicate the upper and lower limits of the data value, and the numerical fluctuation range is used to indicate the upper and lower limits of the difference between adjacent energy data.

[0083] Based on the above method, when it is determined that the energy data is abnormal, step S303 is executed.

[0084] S303: Determine the data collection node corresponding to the abnormal energy data as the node to be detected, and send a detection instruction to the data transmission node in each data collection network.

[0085] The detection instruction is used to instruct the detection nodes in each data collection network to send a detection signal to the node to be detected. The detection node is determined by the data transmission node from the currently online data collection nodes when receiving the detection instruction. For example, all currently online data collection nodes can be determined as detection nodes, or the data collection node that recently reported data can be selected as the detection node. In this way, it can be ensured that the detection node itself can communicate normally, avoiding the influence of the detection result due to the abnormality of the detection node.

[0086] In implementation, after determining the node to be detected, the data transfer node sends a detection instruction to all data transmission nodes in the building where the node to be detected is located.

[0087] After receiving the detection instruction, the data transmission node determines the data collection nodes in the network that can be used to detect the node to be detected based on the above method as detection nodes. A control instruction is sent to the detection node to instruct each detection node to send a detection signal to the node to be detected according to the preset requirements, wherein the detection signal is a wireless network signal.

[0088] In one implementation, before sending a control instruction, the data transmission node may also confirm whether the node to be detected is a node in the network. If it is, it first sends a detection notification to the node to be detected, and after receiving a reply from the node to be detected, it notifies other data transmission nodes to start sending control instructions. After receiving the notification, other data transmission nodes send control instructions to each detection node in the network.

[0089] It is worth noting that if the node to be detected does not respond normally, it means that the node to be detected has been offline, and the data transmission node will feedback the offline information of the node to be detected to the data transfer node. Based on this, by first confirming whether the node to be detected is online, and only sending control instructions after the confirmation is completed, the task processing pressure of each detection node and data transmission node can be reduced, useless work can be avoided, service resources can be saved, and rapid positioning and feedback of abnormalities can be achieved.

[0090] In other implementations, a keep-alive mechanism can be enabled between the data transmission node and the data collection node, that is, by periodically sending a survival signal, it is determined that both parties are online. Based on this, when the data transmission node receives a detection instruction, it can directly determine the survival status of the node to be detected based on the keep-alive mechanism, and when it is determined that the node to be detected is offline, it directly provides feedback to the data transfer node. When it is determined that the node to be detected is online, it notifies other data transmission nodes to start sending control instructions.

[0091] Among them, the preset requirements are pre-configured on each data acquisition node, including the detection signal strength and time window. The time window is used to limit the sending time of the detection signal. After receiving the control instruction, the data acquisition node calculates the deadline for sending the detection signal according to the instruction sending time and the time window, and completes the sending of the detection signal before the deadline. If the difference between the time when the control instruction is received and the time when the control instruction is sent is greater than the time window, the data acquisition node does not need to perform this detection task, and replies to the data transmission node with a message that the task has not been executed.

[0092] After receiving the detection signal, the node to be detected records the signal strength and source address information, and adds the receiving time of the first detection signal to the time window to obtain the stop receiving time. When the stop receiving time arrives, the node to be detected sends detection data to the data transfer node through the data transmission node. The detection data includes the detection node address information, the received signal strength and the receiving time.

[0093] S304: Receive detection data returned by the node to be detected.

[0094] S305, analyzing the detection data and energy data to determine the cause of the abnormality.

[0095] Specifically, the causes of energy data anomalies mainly include one or more of the following: abnormalities in the acquisition terminal device, abnormalities in the target device, or abnormalities in the environment. The following methods are used to analyze the detection data and energy data to determine the causes of the anomalies.

[0096] The data transfer node obtains the temperature and humidity data in the physical area where the node to be detected is located from the energy data to determine whether the environment in the area is normal. If it is abnormal, a first warning information is generated.

[0097] The data transfer node can generate a detection map based on the detection data. In an example, please refer to Figure 4 The detection map is represented by multiple left-aligned parallel line segments. The generation method of the detection map includes determining the unique icon corresponding to each detection node in the detection data, using the icon of the node to be detected and the detection node icon as the two end points of the line segment, and determining the distance between the two based on the detection signal strength. The longer the signal strength, the longer the line segment. Each line segment is aligned with the node to be detected and arranged in sequence according to the length of the line segment, such as the longest line segment is the first and the shortest is the last.

[0098] After obtaining the detection map, the data transfer node identifies the detection map based on the image recognition model to determine whether the installation position of the node to be detected has changed.

[0099] The image recognition model can be built based on algorithms such as template matching, feature extraction, support vector machine, convolutional neural network, etc., and the specific selection can be made according to actual needs.

[0100] It is worth noting that during the detection process, the nodes to be detected may not receive the detection signals or the strength of the received detection signals may weaken due to factors such as detection node failure and environmental interference with the wireless signal. Therefore, when obtaining model training samples, the sample detection map generated based on the real sample detection data can be deformed to obtain a new sample detection map, so as to obtain more model training samples.

[0101] In one example, the deformation processing includes deleting some line segments in the sample detection image, or simulating the strength and position of the interference signal source, predicting the impact of the interference signal on the strength of each detection signal, and adjusting the length of the line segment.

[0102] It is understandable that the activity space of personnel in each building is relatively fixed, and the types of commonly used electronic equipment can also be learned through investigation. In one implementation, a signal transmitter can be used to simulate various signal interference situations, and corresponding detection data can be collected to generate a sample detection map. At the same time, the influence of various interference signals on the detection signal strength can be obtained. In this way, the influence intensity of various interference signals on each detection signal can be predicted based on the influence law.

[0103] It can be seen that in the embodiment of the present application, by using the detection map to identify the installation status of the acquisition terminal equipment, a large number of new sample detection maps can be obtained by deforming the real sample detection map, thereby realizing automatic expansion of the sample, so that the training of the image recognition model can be completed quickly, and the model recognition accuracy can be quickly improved.

[0104] When it is identified that the collection terminal device corresponding to the node to be detected is installed abnormally or it is confirmed that the node to be detected is offline according to the information fed back by the data transmission node, the second warning information is generated.

[0105] Based on the analysis of abnormal energy data, the data transfer node further determines whether the target device is abnormal, including identifying abnormal energy data based on the device diagnosis model to determine whether the target device is abnormal. The device diagnosis model can be built based on machine learning algorithms and deep learning algorithms. It is understandable that all types of target devices in the building are purchased from the market. Therefore, the corresponding sample data can be generated based on the device operation data provided by the device manufacturer and the historical operation data obtained from the cloud service platform to train the device diagnosis model.

[0106] When the model output result indicates that the target device is abnormal, a third warning information is generated.

[0107] S306, sending abnormal warning information.

[0108] After determining the cause of the abnormality based on step S305 and generating corresponding warning information, the data transfer node sends the warning information to the on-site personnel to remind the on-site personnel to confirm and restore the abnormal situation.

[0109] In implementation, the data transfer node can send relevant warning information by calling a third-party message application interface or through a client application. In addition, it can also send warning information to on-site personnel through other means such as SMS and email. After receiving the warning information, the on-site personnel will go to the site to check and confirm whether the abnormality has actually occurred, and feedback the abnormality inspection results through the client.

[0110] In one implementation, after sending the warning information, the data transfer node receives the abnormality check results fed back by the on-site personnel, and the abnormality check includes: confirming whether the actual on-site situation is consistent with the warning information.

[0111] The data transfer node can further determine whether the on-site situation is consistent with the cause of the abnormality based on the abnormality inspection result, that is, determine whether the abnormality inspection result indicates that the cause of the abnormality is inaccurate, and if it indicates that the cause of the abnormality is inaccurate, send a request containing the cause of the abnormality and the abnormality inspection result to the cloud service platform to request the cloud service platform to optimize the relevant abnormality analysis method.

[0112] When receiving the request, the cloud service platform can evaluate the optimization project and optimize the relevant dimensions, including introducing other parameters, optimizing model training, etc.

[0113] Based on this, during the data collection process, the anomaly recognition method can be optimized simultaneously to improve the accuracy of anomaly recognition, thereby being able to discover abnormal situations more accurately and timely, and being able to select more reasonable preprocessing for abnormal energy data, thereby ensuring that the collected energy data can provide an effective data basis for subsequent optimization analysis.

[0114] S307, pre-processing the energy data, and sending the energy consumption analysis data obtained after the pre-processing to the cloud service platform.

[0115] In order to reduce the data processing pressure of the cloud service platform and process abnormal energy data in a timely manner, the data transfer node needs to pre-process the energy data after analyzing the abnormal energy data to obtain energy analysis data that can be directly used for energy consumption analysis.

[0116] Specifically, when there are anomalies in the energy data, the abnormal energy data must be preprocessed first.

[0117] In one example, when the abnormality is caused by abnormal environment, abnormal installation location of the collection terminal device, or offline, the abnormal energy data can be reassigned. For example, the new value of the abnormal energy data can be determined based on the average value, approximate value, or using a prediction model.

[0118] In one example, when the cause of the abnormality is a failure of the target device, the original value of the abnormal energy data can be retained and a mark can be added to indicate that the value is collected when the device is abnormal, so that the cloud service platform can be aware of the device failure condition, thereby having a clearer understanding of the device operation status, and providing a multi-dimensional data foundation for subsequent device control optimization.

[0119] After completing the preprocessing of abnormal energy data, continue to perform secondary preprocessing on the preprocessed abnormal energy data and other normal energy data. The secondary preprocessing includes dirty data cleaning and format processing of all energy data, and packaging according to actual analysis needs to obtain corresponding energy consumption analysis data.

[0120] For example, all energy data used to analyze the same target device are packaged, or related energy data within the same physical space are packaged.

[0121] In this way, when the cloud service platform receives the data, it can parse it and directly use it for data analysis to generate corresponding data analysis charts and display them to analysts.

[0122] Based on the above technical solution, by identifying abnormal energy data and analyzing the abnormal causes through the transfer server, the on-site environmental anomalies (such as high temperature caused by overheating of equipment, fire, soaking in water, etc.), abnormalities in the acquisition terminal equipment and abnormal operation of the target equipment are discovered in time, and the on-site personnel are notified to handle them in time to recover as soon as possible. Based on this, not only can the pre-processing method of abnormal energy data be clarified, but also the situation where the collected energy data is unavailable due to the failure to timely discover the on-site anomalies can be avoided as much as possible, thereby ensuring that the collected energy data can provide a good data basis for subsequent energy consumption analysis. At the same time, real-time monitoring of the target equipment, acquisition terminal equipment and on-site environmental conditions is realized.

[0123] In addition, an embodiment of the present application also provides an electronic device, which includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements a method as in any one of the implementations in the embodiments of the present application; wherein the processor may adopt a general-purpose central processing unit (CPU), a microprocessor, an application specific integrated circuit (ASIC), a graphics processing unit (GPU), or one or more integrated circuits, for executing relevant programs to implement the method in any one of the implementations in the embodiments of the present application.

[0124] The processor may also be an integrated circuit electronic device with signal processing capability. In the implementation process, each step of the method in any implementation of the embodiments of the present application may be completed by an integrated logic circuit of hardware in the processor or by instructions in the form of software.

[0125] The above-mentioned processor can also be a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor to be executed, or the hardware and software modules in the decoding processor can be combined and executed.

[0126] The software module may be located in a storage medium mature in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory, and combines its hardware to complete the functions required to be performed by the units included in the data processing device of the embodiment of the present application, or executes the method in any one of the implementation modes in the embodiment of the present application.

[0127] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A building energy data acquisition system, characterized in that: The system includes at least one data collection network, a data transfer node and a cloud service platform; wherein, The data acquisition network is connected with data acquisition nodes and data transmission nodes for collecting energy data; wherein each of the data acquisition nodes sends the collected energy data to the data transfer node through the data transmission node; wherein the data transmission node is one of the data acquisition nodes in the data acquisition network, and when each of the data acquisition nodes is connected to the data acquisition network, it sends its own equipment performance data to other data acquisition nodes in the network, and after receiving the equipment performance data sent by other data acquisition nodes, it evaluates the equipment performance of each of the data acquisition nodes in the network based on the same preset rules, and selects a data acquisition node that meets the requirements as the data transmission node; The data transfer node receives the energy data sent by the data transmission node, and performs abnormality analysis on the energy data; When it is determined that the energy data is abnormal, the data acquisition node corresponding to the abnormal energy data is determined as the node to be detected, and detection instructions are sent to the data transmission nodes in each of the data acquisition networks respectively to instruct the detection nodes in each of the data acquisition networks to send detection signals to the node to be detected according to preset requirements; and the detection data returned by the node to be detected is analyzed to determine the abnormal cause corresponding to the abnormal energy data, the abnormal energy data is preprocessed according to the preprocessing method corresponding to the abnormal cause, and the energy consumption analysis data obtained after the preprocessing is sent to the cloud service platform.

2. The system according to claim 1, characterized in that Each of the data collection networks is divided based on the collection object.

3. The system according to claim 2, characterized in that The data collection node accesses the data collection network in a manner that includes virtual access.

4. The system according to claim 1, characterized in that The system also includes a client, through which the data transfer node sends abnormal warning information to on-site personnel, and receives abnormal detection results fed back by on-site personnel through the client.

5. A building energy data collection method, characterized in that: The method is applied to the building energy data acquisition system according to any one of claims 1 to 4, and is executed by the data transfer node, comprising: Receiving the energy data reported by the data transmission node; Performing abnormality analysis on the energy data; When it is determined that the energy data is abnormal, the data acquisition node corresponding to the abnormal energy data is determined to be a node to be detected, and a detection instruction is sent to the data transmission node in each data acquisition network; wherein the detection instruction is used to instruct the detection node in each data acquisition network to send a detection signal to the node to be detected according to preset requirements; Receiving detection data returned by the node to be detected; The detection data is analyzed to determine the abnormal cause corresponding to the abnormal energy data, and the abnormal energy data is preprocessed according to the preprocessing method corresponding to the abnormal cause.

6. The method according to claim 5, characterized in that The method for performing abnormality analysis on the energy data comprises: When the encapsulated energy data sent by the data transmission node is received, the size of the encapsulated energy data is calculated, and whether there is an abnormality in the encapsulated energy data is determined based on the standard amount of encapsulated data corresponding to the data transmission node.

7. The method according to claim 5, characterized in that The analyzing the detection data to determine the abnormal cause corresponding to the abnormal energy data includes: A detection map is generated based on the detection data, and the detection map is recognized based on an image recognition model to determine whether the installation position of the node to be detected has changed.

8. The method according to claim 5, characterized in that The method also includes receiving abnormality inspection results fed back by on-site personnel. When the abnormality inspection results indicate that the cause of the abnormality is inaccurate, a request including the cause of the abnormality and the abnormality inspection results is sent to a cloud service platform to request the cloud service platform to optimize the abnormality analysis method.

9. An electronic device, characterized in that: The method comprises a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction implements the method according to any one of claims 5 to 8 when executed by the processor.

Citation Information

Patent Citations

  • Energy data acquisition method and system of smart building

    CN117193624A

  • Building environment data processing method, system and device based on Internet of Things

    CN117238114A

  • Building energy consumption real-time monitoring control system and method

    CN117494032A

  • Intelligent building energy consumption abnormity analysis system and method

    CN118427761A

  • Operational energy consumption anomalies in intelligent energy consumption systems

    US20200242493A1