Industrial Sensor Network Modeling for Parameter Tuning Paths
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Industrial big data analysis in process industries faces challenges due to data complexity, missing values, noise, and reliance on domain experts for equipment optimization, as conventional data mining algorithms are inadequate for handling large-scale, fluctuating data.
Innovation Solution
A complex network model is constructed using industrial equipment sensor data, where the Spearman correlation coefficient is used to connect sensors as nodes and calculate optimal parameter adjustment paths, reducing dependence on domain experts and improving data-driven models.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional data mining algorithms are used for industrial big data analysis, then the analysis process can be implemented, but the system cannot effectively handle data complexity, missing values, and noise
Solution Approach 1:
The patent transforms the data analysis approach by changing parameters from conventional statistical methods to complex network theory parameters. Sensor data is converted into network nodes and edges with specific topological parameters (degree, betweenness, closeness), enabling reliable analysis of complex industrial data with missing values and noise through network topology characteristics rather than traditional statistical parameters.
Solution Approach 2:
The patent replaces conventional data mining algorithms with a complex network modeling approach. Instead of using traditional mechanical data processing algorithms that struggle with industrial big data complexities, the system substitutes a network-based modeling mechanism that naturally handles complexity, missing data, and noise through its topological structure and mathematical framework.
2Manufacturing precision
If domain experts are used to assemble and optimize equipment parameters, then equipment optimization can be achieved, but enterprise development becomes highly dependent on domain experts
Solution Approach 1:
The patent implements a self-service system where the complex network model automatically analyzes sensor data and generates equipment parameter optimization recommendations without requiring domain experts. The system uses topological analysis of sensor networks to self-determine optimal parameter adjustments, making enterprises independent of expert dependency while maintaining manufacturing precision.
Solution Approach 2:
The patent introduces a complex network model as an intermediary between raw sensor data and equipment optimization decisions. This intermediary system processes and interprets industrial big data, transforming complex sensor readings into actionable optimization recommendations, thereby replacing the need for human domain experts as intermediaries.
3Loss of information
If existing data-driven models are used, then some service aspects can be covered, but technical weaknesses beyond service experience cannot be found
Solution Approach 1:
The patent adds a new dimension to data analysis by introducing network topological dimensions (degree, betweenness, closeness) that go beyond traditional service experience parameters. This dimensional expansion enables the discovery of technical weaknesses and insights that conventional models cannot detect, as it analyzes equipment operation from a network connectivity and influence perspective rather than just operational parameters.
Data Source
AI summary
The present invention discloses an industrial equipment operation, maintenance and optimization method and system based on a complex network model. The method includes the following steps: obtaining data of all sensors of industrial equipment, and calculating a Spearman correlation coefficient between data of every two of the sensors within the same time period; using each sensor as a node, and using the Spearman correlation coefficient as a weight of a network edge, to construct a fully connected weighted network; and obtaining, when an adjustment instruction for a target feature is received, a currently optimal parameter adjustment path of the target feature based on the fully connected weighted network. In the present invention, production equipment in reality is digitized to construct a complex network oriented to industrial big data. An optimal path for equipment parameter tuning may be found by using the network, thereby reducing dependence of an enterprise on a domain expert.