Intelligent decision support system for fault diagnosis and energy efficiency improvement of intelligent building energy consumption equipment

Abstract

The invention belongs to the technical field of smart buildings, and relates to a smart building energy consumption equipment fault diagnosis and energy efficiency improvement intelligent decision support system comprising an Internet of Things sensing module used for collecting equipment operation parameters and environment data; the fault diagnosis module outputs three-dimensional fault information through a time sequence behavior analysis model and a system topology correlation model; the energy efficiency optimization module is used for receiving the risk level in the three-dimensional fault information as a dynamic constraint condition and generating an equipment control instruction; and the decision execution module outputs a natural language collaboration scheme containing the maintenance measures and the energy efficiency strategy. According to the method, the fault risk level is fed back to the energy efficiency optimization model in real time for the first time, and self-adaptive adjustment of the safety boundary is achieved. According to the method, the independent operation characteristics of the equipment and the system-level topology influence are synchronously analyzed, and the diagnosis accuracy is improved to 95% or above.

Description

Technical Field

[0001] This invention belongs to the field of smart building technology and relates to an intelligent decision support system for fault diagnosis and energy efficiency improvement of smart building energy-consuming equipment. Background Technology

[0002] Currently, in the field of smart buildings, existing fault diagnosis and energy efficiency management generally suffer from the following problems: 1. Fault diagnosis blind spots: Traditional methods rely on fixed threshold alarms (such as over-temperature alarms), which cannot identify progressive faults such as compressor bearing wear, leading to sudden shutdowns. Research data shows that approximately 68% of building equipment failures are caused by delayed warnings.

[0003] 2. Rigid energy efficiency management: Existing energy management systems (BMS) operate only according to preset strategies. When equipment efficiency declines, they continue to operate in the original mode, resulting in hidden energy waste.

[0004] 3. Lack of decision-making coordination: The operations and maintenance department needs to retrieve fault logs and energy consumption reports across systems. Manually formulating strategies is inefficient, with an average response time of over 48 hours. Summary of the Invention

[0005] The purpose of this invention is to solve the above-mentioned problems and provide an intelligent decision support system for fault diagnosis and energy efficiency improvement of energy-consuming equipment in smart buildings.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: A smart building energy-consuming equipment fault diagnosis and energy efficiency improvement intelligent decision support system includes: The IoT sensing module is used to collect device operating parameters and environmental data; The fault diagnosis module outputs three-dimensional fault information through the temporal behavior analysis model and the system topology association model; The energy efficiency optimization module receives the risk level from the three-dimensional fault information as a dynamic constraint and generates equipment control commands. The decision execution module outputs a natural language collaborative solution that includes maintenance measures and energy efficiency strategies.

[0007] Furthermore, the three-dimensional fault information includes fault type, equipment location, and risk level quantification indicators.

[0008] Furthermore, the energy efficiency optimization module includes a dynamic constraint mechanism that automatically limits the maximum load rate of the equipment when the risk level reaches a threshold.

[0009] Furthermore, the decision execution module integrates a maintenance knowledge base and matches maintenance plans with different response times based on the risk level.

[0010] Furthermore, the contingency plan includes a countdown mechanism, where the risk level is inversely proportional to the response time.

[0011] Furthermore, the system deploys edge computing nodes to perform real-time filtering and feature extraction on sensor data; The time-series behavior analysis model identifies gradual abnormal patterns in device parameters through deep learning; The system topology correlation model analyzes the energy flow transfer relationship between multiple devices and assesses the system-level impact of local faults. The decision execution module supports mobile work order dispatch and provides real-time feedback on strategy execution status.

[0012] The beneficial effects of this invention are as follows: The present invention relates to an intelligent decision support system for fault diagnosis and energy efficiency improvement of smart building energy-consuming equipment. This invention is the first to feed back fault risk levels to the energy efficiency optimization model in real time, enabling adaptive adjustment of safety boundaries. It simultaneously analyzes the independent operating characteristics of equipment and the impact of system-level topology, improving diagnostic accuracy to over 95%. Detailed Implementation

[0013] This invention provides an intelligent decision support system for fault diagnosis and energy efficiency improvement of energy-consuming equipment in smart buildings, comprising: an IoT sensing module for collecting equipment operating parameters and environmental data; a fault diagnosis module for outputting three-dimensional fault information through a time-series behavior analysis model and a system topology association model; an energy efficiency optimization module for receiving the risk level in the three-dimensional fault information as a dynamic constraint condition and generating equipment control commands; and a decision execution module for outputting a natural language collaborative solution that includes maintenance measures and energy efficiency strategies.

[0014] The three-dimensional fault information includes fault type, equipment location, and risk level quantification indicators. The energy efficiency optimization module includes a dynamic constraint mechanism that automatically limits the maximum load rate of equipment when the risk level reaches a threshold. The decision execution module integrates a maintenance knowledge base and matches maintenance plans with different response times based on the risk level. The maintenance plan includes a countdown handling mechanism, with the risk level inversely proportional to the response time. The system deploys edge computing nodes to perform real-time filtering and feature extraction on sensor data; the time-series behavior analysis model uses deep learning to identify gradual abnormal patterns in equipment parameters; the system topology association model analyzes the energy flow transfer relationships between multiple devices and assesses the system-level impact of local faults; the decision execution module supports mobile work order dispatch and provides real-time feedback on strategy execution status.

[0015] The intelligent decision support system for fault diagnosis and energy efficiency improvement of smart building energy-consuming equipment of the present invention has the following system architecture: 1. IoT Sensing Layer Deploy multi-sensor devices such as vibration sensors, infrared thermal imagers, and power quality analyzers. Connect to external data sources such as building management systems (BMS), weather forecasting platforms, and personnel dispatching systems; 2. Intelligent Analysis Layer Fault diagnosis engine: Time-series behavior analysis model: detects abnormal fluctuation patterns in the operating parameters of the equipment (such as sudden increases in current harmonics). System topology correlation model: Analyzing the linkage relationships between devices (such as the impact of cooling tower efficiency reduction on chiller units). Output three-dimensional diagnostic results: [Fault Type] - [Location Location] - [Risk Level] (e.g., wind turbine impeller imbalance / B2 machine room / Level III risk) 3. Dynamic Energy Efficiency Optimizer: Establish a mapping model between equipment health status and energy consumption. Introduce fault risk level as an optimization constraint (such as automatic load limiting operation when the risk is high). Generate a set of control parameters that balances safety and economy. 3. Decision-making and execution level Knowledge Fusion Engine: Structured knowledge base: integrates equipment technical manuals, maintenance procedures, and historical cases. Rule-based inference engine: Matches contingency plans to risk levels (e.g., Level III risk triggers 72-hour countdown maintenance). Human-machine collaboration interface: Output natural language commands (e.g., "Cooling water pump bearing vibration exceeds the standard; it is recommended to replace it within 48 hours and reduce the flow rate to 80% of the rated value"). Supports mobile work order dispatch and policy execution confirmation.

[0016] The present invention relates to an intelligent decision support system for fault diagnosis and energy efficiency improvement of smart building energy-consuming equipment. This invention is the first to feed back fault risk levels to the energy efficiency optimization model in real time, enabling adaptive adjustment of safety boundaries. It simultaneously analyzes the independent operating characteristics of equipment and the impact of system-level topology, improving diagnostic accuracy to over 95%. Furthermore, it generates traceable decision-making criteria based on a maintenance knowledge graph, solving the "black box" problem of AI models.

[0017] The above description is merely one embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the invention by those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A smart building energy-consuming equipment fault diagnosis and energy efficiency improvement intelligent decision support system, characterized in that, include: The IoT sensing module is used to collect device operating parameters and environmental data; The fault diagnosis module outputs three-dimensional fault information through the temporal behavior analysis model and the system topology association model; The energy efficiency optimization module receives the risk level from the three-dimensional fault information as a dynamic constraint and generates equipment control commands. The decision execution module outputs a natural language collaborative solution that includes maintenance measures and energy efficiency strategies.

2. The intelligent decision support system for fault diagnosis and energy efficiency improvement of smart building energy-consuming equipment according to claim 1, characterized in that, The three-dimensional fault information includes fault type, equipment location, and risk level quantification indicators.

3. The intelligent decision support system for fault diagnosis and energy efficiency improvement of smart building energy-consuming equipment according to claim 2, characterized in that, The energy efficiency optimization module includes a dynamic constraint mechanism that automatically limits the maximum load rate of the equipment when the risk level reaches a threshold.

4. The intelligent decision support system for fault diagnosis and energy efficiency improvement of smart building energy-consuming equipment according to claim 3, characterized in that, The decision execution module integrates a maintenance knowledge base and matches maintenance plans with different response times based on the risk level.

5. The intelligent decision support system for fault diagnosis and energy efficiency improvement of smart building energy-consuming equipment according to claim 4, characterized in that, The maintenance plan includes a countdown mechanism, and the risk level is inversely proportional to the response time.

6. The intelligent decision support system for fault diagnosis and energy efficiency improvement of smart building energy-consuming equipment according to claim 5, characterized in that, The system deploys edge computing nodes to perform real-time filtering and feature extraction on sensor data; The time-series behavior analysis model identifies gradual abnormal patterns in device parameters through deep learning; The system topology correlation model analyzes the energy flow transfer relationship between multiple devices and assesses the system-level impact of local faults. The decision execution module supports mobile work order dispatch and provides real-time feedback on strategy execution status.