Intelligent elevator operation and maintenance system based on cooperation of large model and knowledge graph

Abstract

The invention discloses an elevator intelligent operation and maintenance system based on cooperation of a large model and a knowledge graph in the technical field of elevator operation and maintenance. The elevator intelligent operation and maintenance system comprises a data acquisition module used for acquiring elevator operation data and historical fault data in real time; the large model processing module performs feature extraction and fault mode recognition on the collected data based on a pre-trained large model; the knowledge graph construction module is used for constructing a knowledge graph by utilizing the elevator domain knowledge; the collaborative reasoning module is used for performing fault reasoning and operation and maintenance decision generation in combination with the output of the large model and the structured knowledge of the knowledge graph; and the visualization module is used for displaying the fault prediction result and the operation and maintenance suggestions to operation and maintenance personnel in a visualization form. According to the scheme, elevator data are collected and deeply analyzed in real time, faults are accurately predicted, problems are intelligently diagnosed, operation and maintenance decisions are optimized, and results are visually displayed, so that the elevator operation and maintenance efficiency is improved, the cost is reduced, and safe operation is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of elevator operation and maintenance, and in particular to an intelligent elevator operation and maintenance system based on the collaboration of a large model and a knowledge graph. Background Art

[0002] With the rapid development of urbanization, the importance of elevators in the vertical transportation system has become increasingly prominent, and their safety and reliability have become the focus of public attention. The traditional elevator operation and maintenance model mainly relies on manual inspections and regular maintenance. This method is not only inefficient and costly, but also has limited ability in fault prediction, making it difficult to detect potential fault hazards in advance. In recent years, although artificial intelligence technology has been gradually promoted and applied in the industrial field, most existing technologies are limited to single data analysis or rule reasoning, cannot effectively integrate multi-source data, lack deep knowledge reasoning capabilities, and are difficult to adapt to the intelligent operation and maintenance needs of complex elevator systems. Summary of the invention

[0003] The present invention aims to provide an intelligent elevator operation and maintenance system based on the collaboration of a large model and a knowledge graph, so as to solve the problem that the existing technology lacks the ability of deep fusion of multi-source data and knowledge reasoning, and is difficult to meet the needs of intelligent operation and maintenance of complex elevator systems.

[0004] In this solution, an intelligent elevator operation and maintenance system based on the collaboration of a large model and a knowledge graph includes a data acquisition module, a large model processing module, a knowledge graph construction module, a collaborative reasoning module, and a visualization module;

[0005] The data acquisition module is used to collect elevator operation data and historical fault data in real time;

[0006] The large model processing module extracts features and identifies fault patterns from the collected data based on the pre-trained large model;

[0007] Knowledge graph construction module: constructs a knowledge graph using elevator domain knowledge;

[0008] Collaborative reasoning module: combines the output of the large model with the structured knowledge of the knowledge graph to perform fault reasoning and generate operation and maintenance decisions;

[0009] Visualization module: displays fault prediction results and operation and maintenance suggestions to operation and maintenance personnel in a visual form.

[0010] The working principle of this solution is as follows: the data acquisition module uses sensors and IoT devices installed at various key parts of the elevator to obtain elevator operation data in real time and accurately, and transmits the data to the large model processing module; the large model processing module preprocesses and extracts features of the data, and outputs the probability of various types of elevator failures and the corresponding failure modes; the knowledge graph construction module sorts out and integrates the elevator field knowledge and converts it into a graph-structured knowledge graph. In the knowledge graph, device nodes and fault nodes are connected by edges, which clearly indicate the fault association relationship, provide a basis for subsequent reasoning, and support fast query and reasoning; the collaborative reasoning module receives the output results of the large model processing module and the relevant knowledge in the knowledge graph, performs comprehensive reasoning analysis, and finally generates a detailed fault diagnosis report and reasonable operation and maintenance suggestions; the visualization module displays the fault prediction results and operation and maintenance suggestions in a graphical interface, through which operation and maintenance personnel can intuitively view the information and perform interactive operations, such as querying fault prediction data for a specific time period and obtaining detailed operation and maintenance suggestions. The synergy mechanism between big models and knowledge graphs: Use big models to process unstructured data (such as text logs, sensor data), and associate the results with structured knowledge in knowledge graphs to achieve deep fusion of multi-source data. Fault prediction and diagnosis algorithms: Based on the time series data analysis capabilities of big models and the reasoning capabilities of knowledge graphs, fault prediction models and diagnosis models are constructed. Operation and maintenance decision optimization: Generate the optimal operation and maintenance strategy based on fault prediction results and historical maintenance records.

[0011] The beneficial effects of this solution are as follows: Through automated data collection, intelligent fault prediction and diagnosis, and optimized operation and maintenance decisions, unnecessary manual intervention and maintenance work can be reduced, operation and maintenance efficiency can be improved, and operation and maintenance costs can be reduced; with the help of the time series data analysis capabilities of the big model and the reasoning capabilities of the knowledge graph, a fault prediction model is constructed, which can monitor the elevator operation data in real time, predict the possibility of faults, and take measures in advance to avoid faults or reduce the impact of faults; a collaborative mechanism between the big model and the knowledge graph is proposed, the big model processes unstructured data, and the knowledge graph integrates structured knowledge, realizing deep fusion of multi-source data and efficient knowledge reasoning, comprehensively and accurately analyzing the elevator operation status, and providing strong support for operation and maintenance.

[0012] Furthermore, the elevator operation data includes vibration, temperature, and current.

[0013] Furthermore, the large model includes GPT and BERT. The large model processing module uses pre-trained large models such as GPT and BERT to pre-process and extract features of data and output fault probability and mode.

[0014] Furthermore, the fault prediction process includes data collection, data preprocessing, large model feature extraction, knowledge graph reasoning, and fault prediction output.

[0015] Furthermore, the knowledge graph includes equipment structure, fault type, and maintenance record. In the knowledge graph constructed by the knowledge graph construction module, equipment nodes and fault nodes are connected by edges to represent fault association relationships, and fast query and reasoning are supported. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flow chart of an elevator intelligent operation and maintenance system based on the collaboration of a large model and a knowledge graph according to the present invention;

[0017] Figure 2 It is a knowledge graph structure diagram;

[0018] Figure 3 This is a fault prediction flow chart. DETAILED DESCRIPTION

[0019] The following is a further detailed description through specific implementation methods:

[0020] The embodiment is basically as shown in the attached Figures 1 to 3 As shown: An elevator intelligent operation and maintenance system based on the collaboration of a large model and a knowledge graph, including a data acquisition module, a large model processing module, a knowledge graph construction module, a collaborative reasoning module, and a visualization module;

[0021] Data acquisition module: Install vibration sensors, temperature sensors, current sensors and other equipment at key locations such as the elevator's motor, car, and guide rails. Use the Internet of Things technology to transmit the real-time operating data collected by the sensors to the data acquisition module. At the same time, import the elevator's historical fault data into the data acquisition module for integration.

[0022] Large model processing module: Select a suitable pre-trained large model, such as the BERT model based on the Transformer architecture, to process the collected data. First, perform pre-processing operations such as cleaning and normalization on the data, and then input it into the large model for feature extraction. Through model training, learn the relationship between elevator operation data and failure mode, and output failure probability and failure mode.

[0023] Knowledge graph construction module: collects professional knowledge in the elevator field, including equipment composition structure, common fault types, fault causes, maintenance methods, etc. Use the knowledge graph construction tool to convert this information into a graph structure, create equipment nodes, fault nodes, maintenance record nodes, etc., and use edge connections to represent the relationship between them to complete the construction of the elevator field knowledge graph.

[0024] Collaborative reasoning module: The collaborative reasoning module obtains the fault probability and pattern output by the large model processing module, as well as the structured knowledge in the knowledge graph. For example, when the large model predicts that the motor may have an overheating fault, the collaborative reasoning module queries the knowledge graph for information related to the motor overheating fault, such as possible causes (excessive load, poor heat dissipation, etc.), previous maintenance records of similar faults, etc., and generates a fault diagnosis report and operation and maintenance suggestions after comprehensive analysis, such as suggestions to check the motor load and clean the cooling fan.

[0025] Visualization display module: Using visualization tools such as Echarts and D3.js, fault prediction results and operation and maintenance suggestions are displayed on the monitoring interface in intuitive forms such as charts and graphs. Operation and maintenance personnel can view the real-time operating status and fault prediction information of different elevators through the interface, and click on a specific elevator to obtain detailed operation and maintenance suggestions, realizing convenient interactive operations.

[0026] The above is only an embodiment of the present invention, and the common knowledge such as the known specific structure and characteristics in the scheme is not described in detail here. It should be pointed out that for those skilled in the art, several deformations and improvements can be made without departing from the structure of the present invention, which should also be regarded as the protection scope of the present invention, and these will not affect the effect of the implementation of the present invention and the practicality of the patent. The scope of protection required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to interpret the content of the claims.

Claims

1. An intelligent elevator operation and maintenance system based on the collaboration of a large model and a knowledge graph, characterized by: It includes data acquisition module, large model processing module, knowledge graph construction module, collaborative reasoning module and visualization module; The data acquisition module is used to collect elevator operation data and historical fault data in real time; The large model processing module extracts features and identifies fault patterns from the collected data based on the pre-trained large model; Knowledge graph construction module: constructs a knowledge graph using elevator domain knowledge; Collaborative reasoning module: combines the output of the large model with the structured knowledge of the knowledge graph to perform fault reasoning and generate operation and maintenance decisions; Visualization module: displays fault prediction results and operation and maintenance suggestions to operation and maintenance personnel in a visual form.

2. According to claim 1, an intelligent elevator operation and maintenance system based on the collaboration of a large model and a knowledge graph is characterized in that: The elevator operation data includes vibration, temperature, and current.

3. According to claim 2, an intelligent elevator operation and maintenance system based on the collaboration of a large model and a knowledge graph is characterized in that: The large model includes GPT and BERT.

4. According to claim 3, an intelligent elevator operation and maintenance system based on the collaboration of a large model and a knowledge graph is characterized in that: The fault prediction process includes data collection, data preprocessing, large model feature extraction, knowledge graph reasoning, and fault prediction output.

5. According to claim 4, an intelligent elevator operation and maintenance system based on the collaboration of a large model and a knowledge graph is characterized in that: The knowledge graph includes equipment structure, fault type, and maintenance records.

Images