Intelligent Building Apparatus Control Using Neural Predictive Diagnosis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing intelligent building management systems lack the capability for automatic diagnosis and control of apparatuses, relying on manual strategies and multiple sensors to detect issues, which limits their ability to optimize operations efficiently.
Innovation Solution
A method that uses historical data to perform abnormal diagnosis on real-time working parameters, selects a neural network predictive control model, and adjusts parameters based on non-abnormal data close in time to optimize control of abnormal apparatuses, thereby automating the diagnosis and control process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If traditional DDC controller with alarm module and manual formulation strategy is used, then the system can detect problems through multiple sensors, but the system fails to realize automatic diagnosis and failure analysis, requiring manual intervention for control strategy formulation
Solution Approach 1:
The system enables self-service by allowing the apparatus to automatically diagnose its own abnormal conditions and generate control strategies without manual intervention. The neural network model processes sensor data autonomously to identify abnormalities and determine optimal control actions, making the system self-sufficient in monitoring and decision-making tasks.
Solution Approach 2:
The patent replaces manual mechanical intervention with an intelligent algorithmic system. Instead of operators physically examining equipment and manually formulating control strategies, a neural network-based diagnostic system automatically analyzes sensor data, identifies abnormalities, and generates control strategies, substituting human cognitive and manual processes with automated computational processes.
2Productivity
If manual control strategy formulation is used, then staff can use personal practical experience to control apparatus, but optimization control is completed manually at the central control platform, reducing productivity
Solution Approach 1:
The system performs self-service by automatically generating optimization control strategies without requiring manual staff intervention. The neural network model continuously processes operational data and autonomously determines optimal control actions, eliminating the time-consuming manual analysis and decision-making process while maintaining or improving control quality.
Solution Approach 2:
The system implements preliminary action by pre-training the neural network model with historical data and operational experiences before actual deployment. This preliminary training phase enables the model to quickly generate accurate control strategies during operation, eliminating the need for manual strategy formulation and significantly improving response time and productivity.
3Extent of automation
If multiple sensors are arranged to detect problems, then the system can notify staff by alarm, but the system fails to automatically optimize and control the apparatus through machine
Solution Approach 1:
The neural network diagnostic model serves as an intermediary between the sensors and the control system. It receives raw sensor data, automatically processes and analyzes the information to identify abnormalities, and generates control strategies based on the analysis. This intermediary layer transforms unprocessed sensor information into actionable control decisions, enabling automatic optimization without manual intervention.
Solution Approach 2:
The patent replaces manual information processing with automated computational analysis. Instead of operators reviewing alarm data and sensor readings to formulate control strategies, the neural network model automatically processes sensor information, identifies patterns indicating abnormalities, and determines optimal control actions, substituting human analytical processes with automated machine learning processes.
Data Source
AI summary
Disclosed are a method for automatically diagnosing and controlling an apparatus in an intelligent building and relevant device. The method includes: performing, based on historical data of working parameters of multiple apparatuses, an abnormal diagnosis on received real-time data of the working parameters; determining an abnormal apparatus; selecting a neural network predictive control model corresponding to the abnormal apparatus; selecting one piece of non-abnormal data which has a same parameter type as that of the abnormal data and is close to the current abnormal data in time as a predictive control target, and determining a predictive control data that can cause an output matching the predictive control target; and controlling the abnormal apparatus according to the predictive control data. The automatic diagnosis and automatic control of an apparatus in an intelligent building are realized, meanwhile the safe and efficient operation of all apparatuses in an intelligent building is ensured.