CN-122007978-A - Data analysis method and system based on intelligent operation and maintenance management result of numerical control machine tool

CN122007978ACN 122007978 ACN122007978 ACN 122007978ACN-122007978-A

Abstract

The invention discloses a data analysis method and a system based on an intelligent operation and maintenance management result of a numerical control machine, and relates to the technical field of data analysis; the method comprises the steps of carrying out fault type duty ratio statistics when sample data quantity meets preset indexes, determining a first trigger fault type, carrying out fault detection, respectively carrying out fault occurrence prediction on the rest N-1 associated fault types if a first detection result is normal, optimally outputting N-1 optimized fault association degrees, determining a second trigger fault type, carrying out fault detection on the numerical control machine tool according to the second trigger fault type, and carrying out iterative loop of association degree adjustment, trigger fault type screening and machine tool fault detection if a second detection result is normal until the detection result is abnormal. The invention solves the technical problems of high blindness and low efficiency of fault detection in the prior art.

Inventors

WU SHIDONG
CHENG TAO
YE FEI
DENG YE
HUANG ZHIWEI
HU LESHUI
GUAN QIFENG
YANG XINRUI
SUN SHUANGYIN
QIAN XIAOBO

Assignees

优服工业服务(集团)有限公司

Dates

Publication Date: 20260512
Application Date: 20260127

Claims (8)

1. The data analysis method based on the intelligent operation and maintenance management result of the numerical control machine tool is characterized by comprising the following steps: inputting an alarm signal of the numerical control machine tool into a local operation and maintenance database for searching to obtain a sample maintenance case set; if the sample data volume of the sample maintenance case set meets a preset index, performing fault type duty ratio statistics according to the sample maintenance case set, outputting N associated fault types and N fault association degrees, and determining a first trigger fault type; performing fault detection on the numerical control machine tool according to the first trigger fault type, and if a first detection result is normal, respectively performing fault occurrence prediction on the rest N-1 associated fault types based on the first trigger fault type to obtain N-1 predicted fault probabilities; calculating N-1 relevance adjustment coefficients according to the N-1 predicted fault probabilities, optimally correcting N-1 fault relevance of the remaining N-1 relevance fault types, outputting N-1 optimized fault relevance, and determining a second trigger fault type; and carrying out fault detection on the numerical control machine tool according to the second trigger fault type, and if the second detection result is normal, continuing the iterative loop of relevancy adjustment, trigger fault type screening and machine tool fault detection until the detection result is abnormal.
2. The method for analyzing data based on intelligent operation and maintenance management results of a numerically-controlled machine tool according to claim 1, wherein if the sample data size of the sample maintenance case set meets a preset index, performing fault type duty statistics according to the sample maintenance case set, outputting N associated fault types and N fault association degrees, and determining a first trigger fault type, comprises: If the sample data volume of the sample maintenance case set is greater than or equal to a preset index, carrying out duty statistics of the same fault type according to the sample maintenance case set, and setting the fault type duty ratio as a fault association degree to obtain N associated fault types and N fault association degrees; If the sample data size of the sample maintenance case set is smaller than the preset index, taking attribute information of the numerical control machine tool as equipment constraint, taking the alarm signal and N associated fault types as condition constraint, and searching based on big data to obtain a multi-element maintenance case set; Performing duty ratio statistics of the same fault type according to the sample maintenance case set and the multi-element maintenance case set, and setting the duty ratio of the fault type as fault association degrees to obtain N associated fault types and N fault association degrees; And setting the association fault type corresponding to the maximum fault association degree in the N association fault types as a first trigger fault type.
3. The data analysis method based on the intelligent operation and maintenance management result of the numerical control machine tool according to claim 2, wherein if the sample data size of the sample maintenance case set is smaller than the preset index, calculating a difference value between the sample data size and the preset index to obtain a data size difference, and setting the product of the data size difference and 10 as a preset retrieval data size; And taking the attribute information of the numerical control machine tool as equipment constraint, taking the alarm signal as condition constraint, and searching based on big data until the search data reach the preset search data amount, so as to obtain a multi-element maintenance case set.
4. The method for analyzing data based on intelligent operation and maintenance management results of a numerically-controlled machine tool according to claim 3, wherein performing the duty ratio statistics of the same fault type according to the sample maintenance case set and the multiple maintenance case set comprises: acquiring a comprehensive fault type set corresponding to the alarm signal, wherein the comprehensive fault type set comprises all possible fault types when the alarm signal occurs; setting the ratio of N to the number of the fault types in the comprehensive fault type set as a sample generalization coefficient; Calculating a sample weight adjustment coefficient according to the sample generalization coefficient and the data difference, and setting the ratio of the sample weight adjustment coefficient to an initial sample data weight as an adaptive sample data weight, wherein the initial sample data weight is 2, and the sample weight adjustment coefficient is positively related to the sample generalization coefficient and the data difference; configuring a multi-element data weight of big data retrieval, wherein the multi-element data weight is 0.1; and based on the adaptive sample data weight and the multivariate data weight, performing duty ratio statistics of the same fault type according to the sample maintenance case set and the multivariate maintenance case set.
5. The data analysis method based on the intelligent operation and maintenance management result of the numerically-controlled machine tool according to claim 1, wherein if the first detection result is normal, predicting occurrence of faults of the remaining N-1 associated fault types based on the first trigger fault type, respectively, to obtain N-1 predicted fault probabilities, includes: If the first detection result is abnormal, stopping subsequent analysis, and maintaining the numerical control machine tool based on the first trigger fault type; if the first detection result is normal, taking attribute information of the numerical control machine tool as equipment constraint, taking the alarm signal as condition constraint, based on big data, counting the historical event occupation ratio of the simultaneous occurrence of the remaining N-1 associated fault types when the first trigger fault type occurs, and setting the same-frequency event occupation ratio as the prediction fault probability to obtain N-1 prediction fault probabilities.
6. The data analysis method based on intelligent operation and maintenance management results of a numerically-controlled machine tool according to claim 1, wherein calculating N-1 correlation adjustment coefficients according to the N-1 predicted fault probabilities, performing optimization correction on N-1 fault correlations of the remaining N-1 correlation fault types, outputting N-1 optimized fault correlations, and determining a second trigger fault type, includes: adding and summing the N-1 prediction fault probabilities with 1 respectively to obtain N-1 association degree adjustment coefficients; and carrying out optimization correction on the N-1 fault relevancy according to the N-1 relevancy adjustment coefficients, outputting N-1 optimized fault relevancy, and selecting an associated fault type corresponding to the maximum optimized fault relevancy as a second trigger fault type.
7. The data analysis method based on the intelligent operation and maintenance management result of the numerically-controlled machine tool according to claim 1, wherein fault detection is performed on the numerically-controlled machine tool according to the second trigger fault type, if the second detection result is normal, the historical event occupation ratio of the simultaneous occurrence of the first trigger fault type and the second trigger fault type is counted, the same-frequency event occupation ratio is set as a prediction fault probability, N-2 prediction fault probabilities are obtained, and N-2 association degree adjustment coefficients are calculated; and carrying out optimization correction on the N-2 optimized fault relevancy according to the N-2 relevancy adjustment coefficients, and determining a third trigger fault type.
8. A data analysis system based on intelligent operation and maintenance management results of a numerically-controlled machine tool, characterized in that the system is used for implementing the data analysis method based on intelligent operation and maintenance management results of a numerically-controlled machine tool according to any one of claims 1 to 7, and the system comprises: The case acquisition module is used for inputting alarm signals of the numerical control machine tool into the local operation and maintenance database for searching to acquire a sample maintenance case set; The first fault type acquisition module is used for carrying out fault type duty statistics according to the sample maintenance case set if the sample data volume of the sample maintenance case set meets a preset index, outputting N associated fault types and N fault association degrees, and determining a first trigger fault type; The fault probability prediction module is used for carrying out fault detection on the numerical control machine tool according to the first trigger fault type, and if a first detection result is normal, carrying out fault occurrence prediction on the rest N-1 associated fault types based on the first trigger fault type respectively to obtain N-1 predicted fault probabilities; The second fault type acquisition module is used for calculating N-1 association degree adjustment coefficients according to the N-1 predicted fault probabilities, carrying out optimization correction on N-1 fault association degrees of the remaining N-1 association fault types, outputting N-1 optimization fault association degrees, and determining a second trigger fault type; and the loop detection module is used for carrying out fault detection on the numerical control machine tool according to the second trigger fault type, and if the second detection result is normal, continuing the iterative loop of association adjustment, trigger fault type screening and machine tool fault detection until the detection result is abnormal.

Description

Data analysis method and system based on intelligent operation and maintenance management result of numerical control machine tool Technical Field The invention relates to the technical field of data analysis, in particular to a data analysis method and system based on an intelligent operation and maintenance management result of a numerical control machine tool. Background The numerical control machine tool is used as core equipment in the modern manufacturing industry, and fault diagnosis is an important ring of intelligent operation and maintenance. The prior art mainly searches according to a fixed fault maintenance sequence, for example, according to a fault type list corresponding to the same signal, and then carries out maintenance. However, the method has the obvious defects that firstly, a complex fault scene cannot be completely covered by a historical case library, so that diagnosis deviation possibly exists, and secondly, blindness and randomness of fault overhaul by the traditional method are large, so that operation and maintenance efficiency is low. Disclosure of Invention The application provides a data analysis method and a system based on an intelligent operation and maintenance management result of a numerical control machine tool, which are used for solving the technical problems of high blindness and low efficiency of fault detection in the prior art. In view of the above problems, the application provides a data analysis method and a system based on intelligent operation and maintenance management results of a numerical control machine tool. In a first aspect, the present application provides a data analysis method based on an intelligent operation and maintenance management result of a numerically-controlled machine tool, the method comprising: inputting an alarm signal of the numerical control machine tool into a local operation and maintenance database for searching to obtain a sample maintenance case set; if the sample data volume of the sample maintenance case set meets a preset index, performing fault type duty ratio statistics according to the sample maintenance case set, outputting N associated fault types and N fault association degrees, and determining a first trigger fault type; performing fault detection on the numerical control machine tool according to the first trigger fault type, and if a first detection result is normal, respectively performing fault occurrence prediction on the rest N-1 associated fault types based on the first trigger fault type to obtain N-1 predicted fault probabilities; calculating N-1 relevance adjustment coefficients according to the N-1 predicted fault probabilities, optimally correcting N-1 fault relevance of the remaining N-1 relevance fault types, outputting N-1 optimized fault relevance, and determining a second trigger fault type; and carrying out fault detection on the numerical control machine tool according to the second trigger fault type, and if the second detection result is normal, continuing the iterative loop of relevancy adjustment, trigger fault type screening and machine tool fault detection until the detection result is abnormal. In a second aspect, the present application provides a data analysis system based on intelligent operation and maintenance management results of a numerically-controlled machine tool, including: The case acquisition module is used for inputting alarm signals of the numerical control machine tool into the local operation and maintenance database for searching to acquire a sample maintenance case set; The first fault type acquisition module is used for carrying out fault type duty statistics according to the sample maintenance case set if the sample data volume of the sample maintenance case set meets a preset index, outputting N associated fault types and N fault association degrees, and determining a first trigger fault type; The fault probability prediction module is used for carrying out fault detection on the numerical control machine tool according to the first trigger fault type, and if a first detection result is normal, carrying out fault occurrence prediction on the rest N-1 associated fault types based on the first trigger fault type respectively to obtain N-1 predicted fault probabilities; The second fault type acquisition module is used for calculating N-1 association degree adjustment coefficients according to the N-1 predicted fault probabilities, carrying out optimization correction on N-1 fault association degrees of the remaining N-1 association fault types, outputting N-1 optimization fault association degrees, and determining a second trigger fault type; and the loop detection module is used for carrying out fault detection on the numerical control machine tool according to the second trigger fault type, and if the second detection result is normal, continuing the iterative loop of association adjustment, trigger fault type screening and machine tool fault detection until the detecti