CN-122022181-A - Forging and pressing running state intelligent evaluation method and equipment combined with big data analysis

CN122022181ACN 122022181 ACN122022181 ACN 122022181ACN-122022181-A

Abstract

The application provides an intelligent evaluation method and equipment for forging and pressing operation states by combining big data analysis, and relates to the technical field of forging and pressing evaluation, wherein the method comprises the steps of carrying out chain type carding on a forging and pressing operation scheme of a forging press, establishing a forging and pressing operation chain, and carrying out multidimensional reference state deduction; the method comprises the steps of obtaining a current forging monitoring flow in real time, carrying out node association abnormal analysis and evaluation on the current forging monitoring flow according to a forging reference accompanying space, carrying out multi-element forging fault causal prediction by calling a fault causal ABF framework according to a current forging node, carrying out node conduction forging fault traceability compensation on a current forging fault causal graph according to a forging work chain, and carrying out feedback adjustment on the forging work chain according to a forging fault causal coupling graph. The application solves the technical problems of inaccurate forging fault compensation and further influencing the forging operation efficiency caused by the difficult positioning of the fault diagnosis in the prior art, and improves the forging operation efficiency through the tracing compensation of the forging fault.

Inventors

YUAN YAPENG
MA JUN
GAO SHIHENG
ZHUO YUE
LIANG QILONG
HU XIAOPING

Assignees

徐州达一重锻科技有限公司

Dates

Publication Date: 20260512
Application Date: 20260206

Claims (10)

1. The intelligent evaluation method for the forging and pressing operation state by combining big data analysis is characterized by comprising the following steps of: Chain carding is carried out on a forging and pressing operation scheme of the forging and pressing machine, a forging and pressing operation chain is established, multi-dimensional reference state deduction is carried out on the forging and pressing machine according to the forging and pressing operation chain, and a forging and pressing reference accompanying space is established; When the forging press is controlled to carry out forging operation according to the forging operation chain, current forging monitoring flow corresponding to the current forging node is obtained in real time; Performing node association anomaly analysis and evaluation on the current forging monitoring flow according to the forging reference accompanying space, and establishing a current forging anomaly coupling matrix; According to the current forging node, calling a fault causal ABF architecture to carry out multi-element forging fault causal prediction on the current forging abnormal coupling matrix, and establishing a current forging fault causal graph network; And carrying out node conduction forging fault tracing compensation on the current forging fault causal graph according to the forging work chain to obtain a forging fault causal coupling graph, and carrying out feedback adjustment on the forging work chain according to the forging fault causal coupling graph.
2. The intelligent assessment method for forging and pressing operation states in combination with big data analysis according to claim 1, wherein the step of performing multidimensional reference state deduction on the forging press according to the forging and pressing operation chain, and establishing a forging and pressing reference accompanying space, comprises the steps of: carrying out multidimensional reference state deduction on the forging press according to a forging and pressing preheating scheme to generate a preheating reference accompanying space; according to a forging and pressing impact scheme, carrying out multi-dimensional reference state deduction on the forging press to generate an impact reference accompanying space; carrying out multidimensional reference state deduction on the forging press according to a forging and pressing cooling scheme to generate a cooling reference accompanying space; And performing chain packaging according to the preheating reference accompanying space, the impact reference accompanying space and the cooling reference accompanying space to generate the forging reference accompanying space.
3. The intelligent evaluation method for the forging operation state in combination with big data analysis according to claim 2, wherein the multi-dimensional reference state deduction is performed on the forging press according to a forging preheating scheme, and a preheating reference accompanying space is generated, comprising: According to the forging press, equipment with the same specification and model is interconnected to obtain forging equipment with the same cluster; According to the forging and pressing preheating scheme, carrying out equipment state normal sample big data retrieval on the same cluster of forging and pressing equipment to obtain a preheating node equipment state registration set; Carrying out concentrated trend analysis according to the pre-heating node equipment state registration set, and constructing a pre-heating node equipment state reference matrix; According to the forging and pressing preheating scheme, carrying out large data retrieval and centralized trend analysis on normal samples of the environmental states of the same cluster of forging and pressing equipment, and constructing a preheating node environmental state reference matrix; According to the forging and pressing preheating scheme, carrying out product state normal sample big data retrieval and centralized trend analysis on the same cluster of forging and pressing equipment, and constructing a preheating node product state reference matrix; And integrating the state reference matrix of the preheating node equipment, the state reference matrix of the environment of the preheating node and the state reference matrix of the product of the preheating node to obtain the preheating reference accompanying space.
4. The intelligent evaluation method for the forging operation state in combination with big data analysis according to claim 1, wherein the step of performing node association anomaly analysis evaluation on the current forging monitoring flow according to the forging reference accompanying space, and establishing a current forging anomaly coupling matrix comprises the following steps: Executing node association mapping activation of the forging reference accompanying space according to the current forging node to obtain a current reference accompanying space, wherein the current reference accompanying space comprises a current equipment state reference matrix, a current environment state reference matrix and a current product state reference matrix; performing multi-characteristic identification cleaning according to the current forging monitoring flow, and establishing a current equipment state monitoring matrix, a current environment state monitoring matrix and a current product state monitoring matrix; Performing anomaly identification evaluation on the current equipment state monitoring matrix according to the current equipment state reference matrix to obtain a first anomaly identification evaluation matrix; Performing anomaly identification and evaluation on the current environmental state monitoring matrix according to the current environmental state reference matrix to obtain a second anomaly identification and evaluation matrix; Performing anomaly identification and evaluation on the current product state monitoring matrix according to the current product state reference matrix to obtain a third anomaly identification and evaluation matrix; And carrying out abnormal attention distribution aggregation according to the first abnormal recognition evaluation matrix, the second abnormal recognition evaluation matrix and the third abnormal recognition evaluation matrix to generate the current forging abnormal coupling matrix.
5. The intelligent assessment method for forging and pressing operation states in combination with big data analysis according to claim 1, wherein calling a fault causal ABF architecture to perform multi-element forging and pressing fault causal prediction on the current forging and pressing abnormal coupling matrix according to the current forging and pressing node, and establishing a current forging and pressing fault causal graph network comprises the following steps: performing fault type mining on the forging press according to the current forging node to obtain a current forging fault type matrix, wherein the current forging fault type matrix comprises F forging fault type labels, and F is a positive integer greater than 1; performing fault causal event retrieval according to the current forging fault type matrix to obtain F forging fault causal event areas; Carrying out multi-level causal reasoning learning on the F forging fault causal event areas according to the fault causal ABF framework, and establishing F forging fault causal prediction branches; inputting the current forging abnormal coupling matrix into the F forging fault causal prediction branches to obtain F forging fault causal prediction paths; and performing graphic networking carding according to the F forging fault causal prediction paths to generate the current forging fault causal graph network.
6. The intelligent assessment method for forging and pressing operation states in combination with big data analysis according to claim 5, wherein the performing multi-level causal inference learning on the F forging and pressing fault causal event areas according to the fault causal ABF architecture, establishing F forging and pressing fault causal prediction branches, comprises: Extracting an F forging fault causal event zone according to the F forging fault causal event zones, wherein F is a positive integer which is more than or equal to 1 and less than or equal to F; activating the fault-cause-and-effect ABF architecture, the fault-cause-and-effect ABF architecture comprising an ARIMA model, a BBN model, an FTA model, and a central server; Performing iterative supervision training on an ARIMA model, a BBN model and an FTA model according to the f forging fault causal event zone, and establishing a first forging fault causal prediction model, a second forging fault causal prediction model and a third forging fault causal prediction model; Carrying out loss characteristic analysis on the first model, the second model and the third model to establish a relationship between a teacher and students; acquiring a real-time monitoring log of the central server, carrying out safety privacy protection configuration enhancement on the central server according to the real-time monitoring log, and establishing a central trusted node; and based on the relationship between the causal prediction master and the students, carrying out distillation strengthening on the first model, the second model and the third model according to the causal prediction of the forging and pressing faults according to the central trusted node, and generating an f-th causal prediction branch of the forging and pressing faults.
7. The intelligent assessment method for forging and pressing operation states in combination with big data analysis according to claim 1, wherein the performing node conduction forging and pressing fault traceability compensation on the current forging and pressing fault causal graph according to the forging and pressing operation chain to obtain a forging and pressing fault causal coupling graph comprises the following steps: According to the current forging node, carrying out node conduction characteristic analysis on the forging operation chain, and determining a conduction node forging scheme; Respectively carrying out forging fault prediction on the conduction node forging scheme according to each forging fault causal prediction path in the current forging fault causal graph network to obtain F predicted conduction forging faults; Performing accident triggering factor tracing on the F predicted conduction forging faults according to the current forging fault causal graph and the conduction node forging scheme to obtain F conduction forging fault paths; And conducting forging fault characteristic compensation is conducted on the current forging fault causal graph according to the F conducting forging fault paths, and the forging fault causal coupling graph is generated.
8. The intelligent assessment method for forging operation state in combination with big data analysis according to claim 1, wherein the chain carding is performed on the forging operation scheme of the forging press, and the forging operation chain is established, comprising: Node division is carried out on the forging operation scheme, and a forging preheating scheme, a forging impact scheme and a forging cooling scheme are determined; and performing chain connection on the forging preheating scheme, the forging impact scheme and the forging cooling scheme to generate the forging work chain.
9. The intelligent assessment method for forge operation state in combination with big data analysis according to claim 1, wherein a forge fault alarm is generated based on said forge fault causal coupling graph.
10. A large data analysis-incorporated intelligent evaluation apparatus for a forge operating condition, characterized by the steps for carrying out the large data analysis-incorporated intelligent evaluation method according to any one of claims 1 to 9, comprising: the chain type carding module is used for carrying out chain type carding on a forging and pressing operation scheme of the forging and pressing machine, establishing a forging and pressing operation chain, carrying out multi-dimensional reference state deduction on the forging and pressing machine according to the forging and pressing operation chain, and establishing a forging and pressing reference accompanying space; The forging monitoring flow acquisition module is used for acquiring the current forging monitoring flow corresponding to the current forging node in real time when the forging press is controlled to carry out forging operation according to the forging operation chain; The associated anomaly analysis and evaluation module is used for carrying out node associated anomaly analysis and evaluation on the current forging and pressing monitoring flow according to the forging and pressing reference accompanying space, and establishing a current forging and pressing anomaly coupling matrix; The fault causal prediction module is used for calling a fault causal ABF architecture to carry out multi-element forging fault causal prediction on the current forging abnormal coupling matrix according to the current forging node, and establishing a current forging fault causal graph network; and the fault tracing compensation module is used for carrying out node conduction forging fault tracing compensation on the current forging fault causal graph according to the forging work chain to obtain a forging fault causal coupling graph, and carrying out feedback adjustment on the forging work chain according to the forging fault causal coupling graph.

Description

Forging and pressing running state intelligent evaluation method and equipment combined with big data analysis Technical Field The application relates to the technical field of forging and pressing evaluation, in particular to an intelligent evaluation method and equipment for forging and pressing running states by combining big data analysis. Background In the traditional forging operation process, equipment fault diagnosis usually depends on single-point monitoring and static threshold alarming, the fragmentation monitoring mode can only sense surface layer abnormal phenomena, and cannot reveal dynamic coupling relation between parameters and causal conduction paths of faults, so that alarm interpretability is poor, maintenance decision is highly dependent on manual experience, fault compensation usually only repairs surface phenomena, and problems cannot be fundamentally solved, equipment fault recurrence or production interruption are caused, and therefore continuity and operation efficiency of forging operation are seriously affected. In summary, in the prior art, the problem of inaccurate fault compensation and further influencing the forging operation efficiency is caused by the fact that the fault diagnosis is difficult to locate the source. Disclosure of Invention The application aims to provide an intelligent evaluation method and equipment for forging and pressing operation states by combining big data analysis, which are used for solving the technical problems that fault compensation is inaccurate and forging and pressing operation efficiency is further affected due to the fact that fault diagnosis is difficult to locate sources in the prior art. In view of the above problems, the present application provides a method and apparatus for intelligently evaluating the state of a forging operation in combination with big data analysis. The application provides a large data analysis-combined intelligent evaluation method for a forging operation state, which is realized by large data analysis-combined intelligent evaluation equipment for the forging operation state, wherein the large data analysis-combined intelligent evaluation method for the forging operation state comprises the steps of performing chain type carding on a forging operation scheme of a forging press, establishing a forging operation chain, performing multidimensional reference state deduction on the forging press according to the forging operation chain, establishing a forging reference accompanying space, acquiring a current forging monitoring flow corresponding to a current forging node in real time when the forging press is controlled to perform forging operation according to the forging operation chain, performing node association abnormal analysis evaluation on the current monitoring flow according to the forging reference accompanying space, establishing a current forging abnormal coupling matrix, invoking a fault causal ABF architecture to perform multi-component forging fault causal prediction on the current forging abnormal coupling matrix according to the current forging node, establishing a current forging fault causal compensation network, performing node forging fault conduction compensation network on the current forging fault graph network according to the forging operation chain, and performing causal fault feedback network adjustment on the current forging fault causal coupling network according to the forging operation chain. Optionally, the forging operation scheme is subjected to node division to determine a forging preheating scheme, a forging impact scheme and a forging cooling scheme, and the forging preheating scheme, the forging impact scheme and the forging cooling scheme are subjected to chain connection to generate the forging operation chain. Optionally, the forging press is subjected to multi-dimensional reference state deduction according to a forging and pressing preheating scheme to generate a preheating reference accompanying space, the forging press is subjected to multi-dimensional reference state deduction according to a forging and pressing impact scheme to generate an impact reference accompanying space, the forging press is subjected to multi-dimensional reference state deduction according to a forging and pressing cooling scheme to generate a cooling reference accompanying space, and chain packaging is performed according to the preheating reference accompanying space, the impact reference accompanying space and the cooling reference accompanying space to generate the forging and pressing reference accompanying space. The method comprises the steps of carrying out equipment interconnection of the same specification type according to a forging press to obtain the same cluster of forging equipment, carrying out equipment state normal sample big data retrieval on the same cluster of forging equipment according to a forging preheating scheme to obtain a preheating node equipment state registration