Search

CN-121998610-A - Intelligent decision support method and system for real-time analysis of big data

CN121998610ACN 121998610 ACN121998610 ACN 121998610ACN-121998610-A

Abstract

The invention relates to the technical field of intellectualization, in particular to an intelligent decision support method and system for real-time analysis of big data. The method comprises the steps of obtaining equipment running state data, equipment historical maintenance data and equipment maintenance supply data in real time, carrying out data transmission preprocessing optimization and fault potential risk assessment to obtain equipment fault historical maintenance potential risk factors, carrying out equipment fault prediction and task emergency analysis on equipment running standard data to obtain equipment fault maintenance task emergency degree, carrying out fault maintenance decision support analysis on equipment fault maintenance task points to generate equipment fault maintenance decision strategies, carrying out maintenance feedback optimization on equipment with corresponding faults based on the equipment fault maintenance decision strategies and combining a preset decision model to execute corresponding equipment fault maintenance decision dynamic optimization and improvement operation. The invention can provide intelligent decision basis for equipment maintenance strategy formulation and maintenance resource allocation.

Inventors

  • GUO XIN
  • JIN XIN

Assignees

  • 西藏数联科技有限公司

Dates

Publication Date
20260508
Application Date
20251224

Claims (10)

  1. 1. An intelligent decision support method for real-time analysis of big data is characterized by comprising the following steps: Step S1, acquiring equipment running state data, equipment historical maintenance data and equipment maintenance supply data in real time, and carrying out data transmission pretreatment optimization on the equipment running state data, the equipment historical maintenance data and the equipment maintenance supply data to obtain equipment running standard data, historical maintenance standard data and maintenance supply standard data; Step S2, performing fault potential risk assessment on the equipment operation standard data based on the historical maintenance standard data to obtain equipment fault historical maintenance potential risk factors; Step S3, performing task emergency analysis on the corresponding equipment fault maintenance task points in the equipment fault maintenance prediction result to obtain the emergency degree of the equipment fault maintenance task; and S4, carrying out maintenance feedback optimization on the equipment with the corresponding faults based on the equipment fault maintenance decision strategy and combining a preset decision model so as to execute the corresponding dynamic optimization and improvement operation of the equipment fault maintenance decision.
  2. 2. The intelligent decision support method for real-time analysis of big data according to claim 1, wherein step S1 comprises the steps of: Step S11, corresponding vibration sensors, temperature sensors, pressure sensors and current sensors are arranged on equipment to monitor vibration amplitude, temperature change, pressure fluctuation and current values corresponding to the operation of the equipment in the operation process of the equipment in real time so as to obtain equipment operation state data; Step S12, acquiring maintenance operation records, maintenance time and maintenance history data of replacement spare part information corresponding to equipment by maintenance personnel in a maintenance management record system in real time so as to obtain equipment history maintenance data; Step S13, acquiring the corresponding spare part stock quantity, the spare part purchasing period and the spare part supply capacity of the equipment in real time to obtain equipment maintenance supply data; Step S14, based on the industrial Internet of things and combined with a high-speed data transmission protocol, transmitting the equipment running state data, the equipment historical maintenance data and the equipment maintenance supply data to an equipment maintenance data processing center in real time in the shortest time; And S15, denoising, correcting and deduplicating the equipment operation state data, the equipment historical maintenance data and the equipment maintenance supply data by utilizing an equipment maintenance data processing center, supplementing corresponding missing data points by utilizing a real-time median interpolation and data mining technology, and carrying out standardized conversion on original data corresponding to different formats and different sources according to equipment data standards so as to obtain equipment operation standard data, historical maintenance standard data and maintenance supply standard data.
  3. 3. The intelligent decision support method for real-time analysis of big data according to claim 2, wherein step S2 comprises the steps of: s21, analyzing equipment operation faults to the equipment operation standard data to obtain equipment operation fault suspected nodes; Step S22, performing fault potential risk assessment on corresponding equipment operation parameters at the suspected equipment operation fault nodes based on historical maintenance standard data to obtain equipment fault historical maintenance potential risk factors, wherein the equipment fault historical maintenance potential risk factors comprise equipment fault operation disassembly potential factors, equipment fault maintenance duration potential factors and equipment fault replacement compatible potential factors; step S23, performing fault quantification calculation on the equipment operation parameters corresponding to the equipment operation fault suspected nodes by using an equipment fault degree calculation formula based on the equipment fault history maintenance potential risk factors and the equipment fault weights corresponding to the equipment operation parameters through giving corresponding equipment fault weights to the equipment operation parameters corresponding to the equipment operation fault suspected nodes so as to obtain equipment fault degrees; And step S24, comparing and judging the equipment fault degree according to a preset equipment fault threshold, if the equipment fault degree corresponding to the node is greater than or equal to the preset equipment fault threshold, considering that the equipment fault exists in the node and taking the node as a maintenance task point, and if the equipment fault degree corresponding to the node is less than the preset equipment fault threshold, considering that the equipment fault does not exist in the node and continuously judging the next node at the same time until all the equipment operation fault suspected nodes are judged, and obtaining an equipment fault maintenance prediction result.
  4. 4. The intelligent decision support method for real-time analysis of big data according to claim 3, wherein step S21 comprises the steps of: Performing time sequence synchronization processing on corresponding equipment operation parameters in the equipment operation standard data in a time dimension to obtain corresponding equipment operation data in the same time dimension; Carrying out time sequence change trend drawing on the equipment operation data corresponding to the same time dimension to generate an equipment operation parameter change trend graph corresponding to the same time coordinate system; And performing operation fault judgment analysis on the corresponding equipment operation parameter change trend graph under the same time coordinate system according to the corresponding operation fault abnormal threshold, and determining the corresponding time node as an operation fault suspected node if one or more corresponding equipment operation parameters are greater than or equal to the corresponding operation fault abnormal threshold, so as to obtain the equipment operation fault suspected node.
  5. 5. The intelligent decision support method for real-time analysis of big data according to claim 3, wherein step S22 comprises the steps of: Acquiring corresponding equipment maintenance operation complexity and technical difficulty required by maintenance operation disassembly through corresponding maintenance operation records in historical maintenance standard data, and evaluating corresponding equipment operation parameters at suspected nodes of equipment operation faults based on the equipment maintenance operation complexity and the technical difficulty required by maintenance operation disassembly to obtain equipment fault operation disassembly potential factors; performing maintenance period distribution analysis on corresponding maintenance time in the historical maintenance standard data to obtain equipment historical maintenance time period distribution; performing maintenance time distribution potential factor evaluation on equipment operation parameters corresponding to equipment operation fault suspected nodes based on equipment historical maintenance time period distribution so as to obtain equipment fault maintenance duration potential factors; And evaluating the replacement potential factors of the corresponding equipment operation parameters at the suspected nodes of the equipment operation faults based on the corresponding replacement spare part information in the historical maintenance standard data so as to obtain the equipment fault replacement compatible potential factors.
  6. 6. The intelligent decision support method for real-time analysis of big data according to claim 5, wherein the step of performing replacement potential factor evaluation on the corresponding equipment operation parameters at the suspected node of the equipment operation failure based on the corresponding replacement spare part information in the historical maintenance standard data comprises the steps of: Acquiring corresponding equipment replacement spare part types and equipment replacement frequencies through corresponding replacement spare part information in the historical maintenance standard data; Performing spare part operation compatibility analysis on the corresponding equipment based on the equipment replacement spare part types to obtain operation compatibility probability between the equipment and the replacement spare parts; and evaluating the replacement potential factors of the corresponding equipment operation parameters at the suspected node of the equipment operation fault based on the equipment replacement frequency and the operation compatibility probability between the equipment and the replacement spare parts so as to obtain the equipment fault replacement compatibility potential factors.
  7. 7. The intelligent decision support method for real-time analysis of big data according to claim 3, wherein the equipment failure degree calculation formula in step S23 specifically comprises: ; in the formula, In order to provide a degree of failure of the equipment, Suspected node for equipment operation fault The corresponding vibration amplitude value is obtained, For the vibration amplitude failure weight to be high, Suspected node for equipment operation fault The corresponding temperature change value is provided with a temperature change value, For the temperature change failure weight, Suspected node for equipment operation fault The corresponding value of the pressure fluctuation is provided, As a weight for the failure of the pressure fluctuation, Suspected node for equipment operation fault The corresponding current value is provided with a corresponding current value, As a weight for the failure of the current, The potential factors are disassembled for equipment failure operations, To replace the compatible potential factors for equipment failure, To equip with a potential factor for the duration of the fault maintenance, For the corresponding length of time for equipment failure maintenance, Is a correction factor for the degree of equipment failure.
  8. 8. The intelligent decision support method for real-time analysis of big data according to claim 1, wherein step S3 comprises the steps of: Step S31, acquiring a corresponding equipment fault type, equipment fault duration and equipment fault positions through corresponding equipment fault maintenance task points in the equipment fault maintenance prediction result; step S32, performing task emergency analysis on corresponding equipment fault maintenance task points based on equipment fault types, equipment fault time lengths and equipment fault positions to obtain equipment fault maintenance task emergency degrees; step S33, sequencing fault maintenance tasks of corresponding equipment fault maintenance task points based on the emergency degree of the equipment fault maintenance tasks so as to generate an equipment fault maintenance emergency priority task sequence; and step S34, carrying out fault maintenance decision support analysis on corresponding prioritized equipment fault maintenance task points in the equipment fault maintenance emergency priority task sequence based on the corresponding spare part stock quantity, the spare part purchasing period and the spare part supply capacity in the maintenance supply standard data so as to recommend an optimal fault maintenance strategy according to the corresponding spare part stock quantity, the spare part purchasing period and the spare part supply capacity, wherein the fault maintenance strategy comprises maintenance personnel allocation, spare part stock use and fault maintenance resource allocation, and the equipment fault maintenance decision strategy is generated.
  9. 9. The intelligent decision support method for real-time analysis of big data according to claim 1, wherein step S4 comprises the steps of: Step S41, performing equipment initial maintenance execution on equipment corresponding to the equipment with faults based on an equipment fault maintenance decision strategy so as to generate a corresponding equipment fault maintenance execution flow; step S42, real-time monitoring points are deployed in the corresponding equipment fault maintenance execution flow to collect corresponding maintenance time, maintenance cost, equipment maintenance efficiency and maintenance quality after maintenance decision execution in real time, so as to obtain equipment fault maintenance feedback data; Step S43, inputting equipment fault maintenance feedback data into a preset decision model to perform maintenance feedback optimization on corresponding equipment with faults by using an online learning algorithm, automatically analyzing reasons by the model to adjust maintenance resource allocation strategies if the actual maintenance time corresponding to a certain maintenance decision strategy is found to exceed expectations, and re-optimizing constraint conditions corresponding to resource allocation by the model to realize dynamic optimization and continuous improvement of maintenance decisions if the certain maintenance decision strategy is found to cause resource waste or shortage so as to execute corresponding equipment fault maintenance decision dynamic optimization and improvement operation.
  10. 10. An intelligent decision support system for real-time analysis of big data, characterized in that the intelligent decision support system for real-time analysis of big data for executing the intelligent decision support method for real-time analysis of big data according to claim 1 comprises: The equipment big data real-time acquisition module is used for acquiring equipment running state data, equipment historical maintenance data and equipment maintenance supply data in real time, and carrying out data transmission pretreatment optimization on the equipment running state data, the equipment historical maintenance data and the equipment maintenance supply data so as to obtain equipment running standard data, historical maintenance standard data and maintenance supply standard data; The equipment fault risk prediction module is used for carrying out fault potential risk assessment on the equipment operation standard data based on the historical maintenance standard data to obtain equipment fault historical maintenance potential risk factors; the equipment fault maintenance decision analysis module is used for carrying out task emergency analysis on corresponding equipment fault maintenance task points in the equipment fault maintenance prediction result to obtain the emergency degree of equipment fault maintenance tasks; and the equipment maintenance feedback optimization module is used for carrying out maintenance feedback optimization on the corresponding equipment with faults based on the equipment fault maintenance decision strategy and combining a preset decision model so as to execute corresponding equipment fault maintenance decision dynamic optimization improvement operation.

Description

Intelligent decision support method and system for real-time analysis of big data Technical Field The invention relates to the technical field of intellectualization, in particular to an intelligent decision support method and system for real-time analysis of big data. Background In the aspect of maintenance strategy formulation, the experience judgment of maintenance personnel and a simple equipment fault manual are mainly relied on in the past. For example, when equipment fails, maintenance personnel typically make a determination of a maintenance schedule with reference to typical fault cases in a fault manual based on their accumulated maintenance experience. With the development of big data technology, although a large amount of data is accumulated in the field of equipment maintenance, an effective method capable of systematically and efficiently analyzing big data related to equipment maintenance in real time and converting analysis results into intelligent decision support is lacking at present. However, the conventional method relies on regular equipment inspection and simple equipment operation parameter monitoring to perform fault detection by regularly inspecting the appearance, operation sound, etc. of the equipment and perform threshold monitoring on a few key operation parameters (such as temperature, pressure, etc.) to determine the state of the equipment, but this method cannot capture the subtle changes and potential fault hidden dangers in the operation process of the equipment in time, so that maintenance work cannot be smoothly performed, and thus the maintenance efficiency of the equipment is seriously affected. Disclosure of Invention Based on this, the present invention needs to provide an intelligent decision support method and system for real-time analysis of big data, so as to solve at least one of the above technical problems. In order to achieve the above purpose, an intelligent decision support method for real-time analysis of big data comprises the following steps: Step S1, acquiring equipment running state data, equipment historical maintenance data and equipment maintenance supply data in real time, and carrying out data transmission pretreatment optimization on the equipment running state data, the equipment historical maintenance data and the equipment maintenance supply data to obtain equipment running standard data, historical maintenance standard data and maintenance supply standard data; Step S2, performing fault potential risk assessment on the equipment operation standard data based on the historical maintenance standard data to obtain equipment fault historical maintenance potential risk factors; Step S3, performing task emergency analysis on the corresponding equipment fault maintenance task points in the equipment fault maintenance prediction result to obtain the emergency degree of the equipment fault maintenance task; and S4, carrying out maintenance feedback optimization on the equipment with the corresponding faults based on the equipment fault maintenance decision strategy and combining a preset decision model so as to execute the corresponding dynamic optimization and improvement operation of the equipment fault maintenance decision. Further, step S1 includes the steps of: Step S11, corresponding vibration sensors, temperature sensors, pressure sensors and current sensors are arranged on equipment to monitor vibration amplitude, temperature change, pressure fluctuation and current values corresponding to the operation of the equipment in the operation process of the equipment in real time so as to obtain equipment operation state data; Step S12, acquiring maintenance operation records, maintenance time and maintenance history data of replacement spare part information corresponding to equipment by maintenance personnel in a maintenance management record system in real time so as to obtain equipment history maintenance data; Step S13, acquiring the corresponding spare part stock quantity, the spare part purchasing period and the spare part supply capacity of the equipment in real time to obtain equipment maintenance supply data; Step S14, based on the industrial Internet of things and combined with a high-speed data transmission protocol, transmitting the equipment running state data, the equipment historical maintenance data and the equipment maintenance supply data to an equipment maintenance data processing center in real time in the shortest time; And S15, denoising, correcting and deduplicating the equipment operation state data, the equipment historical maintenance data and the equipment maintenance supply data by utilizing an equipment maintenance data processing center, supplementing corresponding missing data points by utilizing a real-time median interpolation and data mining technology, and carrying out standardized conversion on original data corresponding to different formats and different sources according to equipment data standards so as to ob