CN115906642A

CN115906642A - Bearing production detection control method and device

Info

Publication number: CN115906642A
Application number: CN202211496474.0A
Authority: CN
Inventors: 胡金福; 吕文轩; 周学兵
Original assignee: Dongguan Keda Hardware Products Co ltd
Current assignee: Dongguan Keda Hardware Products Co ltd
Priority date: 2022-11-28
Filing date: 2022-11-28
Publication date: 2023-04-04
Anticipated expiration: 2042-11-28
Also published as: CN115906642B

Abstract

The invention provides a bearing production detection control method and device, and relates to the technical field of data processing. In the invention, extracting the operation data of bearing production equipment; loading the running data of the bearing production equipment into an optimized equipment running data analysis neural network for running data feature mining processing to output running data mining feature representation, and then carrying out running data feature reduction processing on the running data mining feature representation to output key equipment running behavior, key behavior semantic data and key equipment running behavior representative data; analyzing and outputting an abnormal analysis result of the running behavior of the first equipment according to the running behavior of the key equipment, the semantic data of the key behavior and the representative data of the running behavior of the key equipment, and determining the representative data of the quality of the correspondingly produced bearing product according to the abnormal analysis result of the running behavior of the first equipment. Based on the above, the convenience and reliability of bearing production detection can be improved.

Description

Bearing production detection control method and device

Technical Field

The invention relates to the technical field of data processing, in particular to a bearing production detection control method and device.

Background

The application scenes of the bearing are more, and the quality requirement of the bearing is higher, so that the bearing needs to be detected and controlled in the production and processing process of the bearing, such as quality detection and the like. However, in the prior art, quality monitoring is generally realized based on video monitoring, that is, corresponding monitoring equipment is deployed for production equipment of a bearing or a produced bearing, so that the convenience of production detection is not high.

Disclosure of Invention

In view of this, the present invention provides a bearing production detection control method and device to improve the convenience and reliability of bearing production detection.

In order to achieve the above purpose, the embodiment of the invention adopts the following technical scheme:

a bearing production detection control method comprises the following steps:

extracting a bearing production detection instruction, wherein the bearing production detection instruction comprises bearing production equipment operation data corresponding to target bearing production equipment;

loading the bearing production equipment operation data into an optimization equipment operation data analysis neural network for operation data feature mining processing to output corresponding operation data mining feature representation, then carrying out operation data feature reduction processing on the operation data mining feature representation to output corresponding key equipment operation behavior, key behavior semantic data and key equipment operation behavior representative data, carrying out operation data feature mining processing and operation data feature reduction processing through the to-be-optimized equipment operation data analysis neural network by loading typical bearing production equipment operation data into the to-be-optimized equipment operation data analysis neural network for network optimization formation, outputting typical key equipment operation behavior, typical key behavior semantic data and typical key equipment operation behavior representative data, then analyzing and outputting corresponding equipment operation behavior abnormal analysis results according to the typical key equipment operation behavior, the typical key behavior semantic data and the typical key equipment operation behavior representative data, and carrying out operation behavior critical analysis processing on the output typical operation data mining feature representation to output corresponding typical key equipment operation behavior analysis results, and learning value analysis results of the equipment operation behavior configuration data, determining the learning value analysis results of the corresponding equipment operation behavior, learning value analysis results and learning value analysis results of the equipment corresponding operation behavior representative data, and learning value analysis results of the equipment configuration values of the corresponding operation behavior representative data, and learning value analysis results of the equipment configuration data, and learning value analysis results of the learning value of the equipment, network optimization is carried out on the device operation data analysis neural network to be optimized according to the abnormal analysis learning cost value and the behavior criticality analysis learning cost value, and a corresponding optimized device operation data analysis neural network is formed;

analyzing and outputting a corresponding first equipment operation behavior abnormity analysis result according to the key equipment operation behavior, the key behavior semantic data and the key equipment operation behavior representative data, and determining quality representative data of the bearing product correspondingly produced by the target bearing production equipment according to the first equipment operation behavior abnormity analysis result.

In some preferred embodiments, in the above bearing production detection control method, the optimizing device operation data analysis neural network includes an optimized data feature mining model and an optimized data feature reduction model; the steps of loading the bearing production equipment operation data into an optimized equipment operation data analysis neural network for operation data feature mining processing so as to output corresponding operation data mining feature representation, and then carrying out operation data feature reduction processing on the operation data mining feature representation so as to output corresponding key equipment operation behaviors, key behavior semantic data and key equipment operation behavior representative data comprise:

loading the bearing production equipment operation data into the optimized data feature mining model for operation data feature mining processing so as to output corresponding operation data mining feature representation;

and loading the running data mining feature representation into the optimized data feature reduction model for running data feature reduction processing so as to output corresponding key equipment running behavior, key behavior semantic data and key equipment running behavior representative data.

In some preferred embodiments, in the above bearing production detection control method, further comprising:

extracting typical bearing production equipment operation data, an equipment operation behavior actual result and a key equipment operation behavior actual result;

loading the typical bearing production equipment operation data into an equipment operation data analysis neural network to be optimized to carry out operation data feature mining processing so as to output corresponding typical operation data mining feature representation, and then carrying out operation data feature reduction processing on the typical operation data mining feature representation so as to output corresponding typical key equipment operation behaviors, typical key behavior semantic data and typical key equipment operation behavior representative data;

analyzing and outputting corresponding equipment operation behavior abnormal analysis results according to the typical key equipment operation behaviors, the typical key behavior semantic data and the typical key equipment operation behavior representative data, and performing operation behavior criticality analysis processing on the typical operation data mining feature expression to output corresponding typical key equipment operation behavior analysis results;

analyzing and determining the learning cost value according to the equipment operation behavior abnormal analysis result and the equipment operation behavior actual result so as to output a corresponding abnormal analysis learning cost value, and analyzing and determining the learning cost value according to the key equipment operation behavior actual result and the typical key equipment operation behavior analysis result so as to output a corresponding behavior criticality analysis learning cost value;

and performing network optimization on the equipment operation data analysis neural network to be optimized according to the abnormal analysis learning cost value and the behavior criticality analysis learning cost value to form a candidate equipment operation data analysis neural network, re-marking the candidate equipment operation data analysis neural network as the equipment operation data analysis neural network to be optimized, performing the step of extracting the typical bearing production equipment operation data, the equipment operation behavior actual result and the key equipment operation behavior actual result in a rotary manner, and forming the optimized equipment operation data analysis neural network under the condition that the target of network optimization is achieved.

In some preferred embodiments, in the above bearing production detection control method, the step of loading the typical bearing production equipment operation data into an equipment operation data analysis neural network to be optimized to perform operation data feature mining processing to output a corresponding typical operation data mining feature representation, and then performing operation data feature reduction processing on the typical operation data mining feature representation to output a corresponding typical key equipment operation behavior, typical key behavior semantic data, and typical key equipment operation behavior representative data includes:

ordering the typical bearing production equipment operation data to form a corresponding typical equipment operation behavior ordered set, and loading the typical equipment operation behavior ordered set to an equipment operation data analysis neural network to be optimized;

analyzing a neural network by utilizing the operation data of the equipment to be optimized, and excavating data excavation characteristic representations corresponding to the typical equipment operation behavior ordered set to output corresponding typical operation data excavation characteristic representations;

analyzing a neural network by using the running data of the equipment to be optimized, performing running data feature reduction processing on the typical running data mining feature representation to output corresponding typical key equipment running behaviors, typical key behavior semantic data and candidate equipment running behavior representative data, and determining corresponding running behavior indication data of each piece of key equipment according to the typical key equipment running behaviors;

and under the condition that the candidate device operation behavior representative data is consistent with the key device operation behavior indication data, marking the candidate device operation behavior representative data to form corresponding typical key device operation behavior representative data.

In some preferred embodiments, in the above bearing production detection control method, the step of ordering the typical bearing production equipment operation data to form a corresponding typical equipment operation behavior ordered set, and then loading the typical equipment operation behavior ordered set to the to-be-optimized equipment operation data analysis neural network includes:

performing operation behavior separation processing on the typical bearing production equipment operation data to output each corresponding typical equipment operation behavior;

extracting configured head end operation behavior indication information and tail end operation behavior indication information, combining the head end operation behavior indication information, the tail end operation behavior indication information and each typical device operation behavior according to the precedence relationship in the typical bearing production device operation data to form a corresponding typical device operation behavior ordered set, and loading the typical device operation behavior ordered set to a device operation data analysis neural network to be optimized.

In some preferred embodiments, in the above bearing production detection control method, the step of analyzing a neural network by using the device operation data to be optimized, comparing the candidate device operation behavior representative data with each of the key device operation behavior indication data, and, in a case where the candidate device operation behavior representative data matches the key device operation behavior indication data, marking the candidate device operation behavior representative data to form corresponding typical key device operation behavior representative data includes:

constructing a corresponding key equipment operation behavior indication data knowledge graph according to each key equipment operation behavior indication data;

screening the candidate device operation behavior representative data from the key device operation behavior indication data knowledge graph, and under the condition that the candidate device operation behavior representative data is screened, marking the candidate device operation behavior representative data to form corresponding typical key device operation behavior representative data.

In some preferred embodiments, in the above bearing production inspection control method, the typical operation data mining feature representation includes each typical operation behavior mining feature representation;

the step of performing operation behavior criticality analysis processing on the typical operation data mining feature representation to output a corresponding operation behavior analysis result of the typical key device includes:

successively traversing in each typical operation behavior mining feature representation to form a traversed typical operation behavior mining feature representation;

mapping and outputting the traversed typical operation behavior mining feature representation to output a corresponding mapped operation behavior mining feature representation, and performing operation behavior criticality analysis processing on the mapped operation behavior mining feature representation to output a typical key equipment operation behavior analysis probability corresponding to the traversed typical operation behavior mining feature representation;

analyzing a corresponding traversed typical operation behavior analysis result represented by the traversed typical operation behavior mining feature according to the typical key equipment operation behavior analysis probability;

and forming a corresponding typical key equipment operation behavior analysis result according to each typical operation behavior mining feature expression corresponding typical operation behavior analysis result.

In some preferred embodiments, in the above bearing production inspection control method, the step of performing analysis and determination of a learning cost value according to the actual result of the operation behavior of the key device and the analysis result of the operation behavior of the typical key device to output a corresponding behavior criticality analysis learning cost value includes:

analyzing and determining the learning cost value of the corresponding typical operation behavior analysis result of each typical operation behavior mining characteristic representation and the corresponding equipment operation behavior actual result in the key equipment operation behavior actual result so as to output each corresponding local behavior criticality analysis learning cost value;

and analyzing and outputting corresponding analysis and learning cost values of the behavioral criticalities according to each analysis and learning cost value of the local behavioral criticalities.

In some preferred embodiments, in the above bearing production detection control method, the to-be-optimized device operation data analysis neural network includes a to-be-optimized data feature mining model, a to-be-optimized data feature reduction model, and a to-be-optimized critical analysis processing model;

loading the typical bearing production equipment operation data into the data feature mining model to be optimized to perform operation data feature mining processing, and outputting corresponding typical operation data mining feature representation;

loading the typical operation data mining feature representation into the data feature reduction model to be optimized to perform operation data feature reduction processing, outputting corresponding typical key equipment operation behavior, typical key behavior semantic data and typical key equipment operation behavior representative data, and analyzing and outputting corresponding equipment operation behavior abnormity analysis results according to the typical key equipment operation behavior, the typical key behavior semantic data and the typical key equipment operation behavior representative data;

loading the typical operation data mining feature representation into the critical analysis processing model to be optimized to perform operation behavior critical analysis processing and output a corresponding typical key equipment operation behavior analysis result;

and constructing a corresponding optimization equipment operation data analysis neural network according to the optimized data feature mining model to be optimized and the optimized data feature reduction model to be optimized.

The embodiment of the invention also provides a bearing production detection control device, which comprises a processor and a memory, wherein the memory is used for storing the computer program, and the processor is used for executing the computer program so as to realize the bearing production detection control method.

According to the bearing production detection control method and device provided by the embodiment of the invention, the operation data of bearing production equipment can be extracted; loading the bearing production equipment operation data into an optimization equipment operation data analysis neural network for operation data feature mining processing to output operation data mining feature representation, and then carrying out operation data feature reduction processing on the operation data mining feature representation to output key equipment operation behaviors, key behavior semantic data and key equipment operation behavior representative data; analyzing and outputting an abnormal analysis result of the running behavior of the first equipment according to the running behavior of the key equipment, the semantic data of the key behavior and the representative data of the running behavior of the key equipment, and determining the representative data of the quality of the correspondingly produced bearing product according to the abnormal analysis result of the running behavior of the first equipment. Based on the foregoing, since the operation data is analyzed and processed based on the bearing production equipment, compared with the conventional technical scheme of performing video monitoring on the bearing or the equipment, no additional monitoring equipment needs to be deployed, so that the detection convenience is higher, and in addition, since the optimized equipment operation data analysis neural network is optimized based on the learning cost values in the two aspects of the abnormal analysis learning cost value and the behavior key analysis learning cost value, the reliability of the analysis function is higher, so that the convenience and the reliability of the bearing production detection can be improved, and the defects in the prior art are overcome.

In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.

Drawings

Fig. 1 is a block diagram of a bearing production detection control apparatus according to an embodiment of the present invention.

Fig. 2 is a schematic flow chart illustrating steps included in the bearing production detection control method according to an embodiment of the present invention.

Fig. 3 is a schematic diagram of modules included in a bearing production detection control system according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.

Thus, the following detailed description of the embodiments of the present invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

As shown in fig. 1, an embodiment of the present invention provides a bearing production detection control apparatus. Wherein, the bearing production detection control device can comprise a memory and a processor.

In detail, the memory and the processor are electrically connected directly or indirectly to realize data transmission or interaction. For example, they may be electrically connected to each other via one or more communication buses or signal lines. The memory can have at least one software functional module (computer program) stored therein, which can be in the form of software or firmware. The processor may be configured to execute the executable computer program stored in the memory, so as to implement the bearing production inspection control method provided by the embodiment of the present invention (described later).

It should be understood that in some embodiments, the Memory may be, but is not limited to, random Access Memory (RAM), read Only Memory (ROM), programmable Read-Only Memory (PROM), erasable Read-Only Memory (EPROM), electrically Erasable Read-Only Memory (EEPROM), and the like. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), a System on Chip (SoC), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components.

It should be understood that in some embodiments, the bearing production test control device may be a server with data processing capabilities.

With reference to fig. 2, an embodiment of the present invention further provides a bearing production detection control method, which can be applied to the bearing production detection control apparatus. The method steps defined by the related flow of the bearing production detection control method can be realized by the bearing production detection control device.

The specific process shown in FIG. 2 will be described in detail below.

And step S110, extracting a bearing production detection instruction.

In the embodiment of the invention, the bearing production detection control device can extract a bearing production detection instruction. The bearing production detection instruction comprises bearing production equipment operation data corresponding to target bearing production equipment (such as extracted from operation log data of the bearing production equipment).

And step S120, loading the bearing production equipment operation data into an optimized equipment operation data analysis neural network for operation data feature mining processing so as to output corresponding operation data mining feature representation, and then carrying out operation data feature reduction processing on the operation data mining feature representation so as to output corresponding key equipment operation behaviors, key behavior semantic data and key equipment operation behavior representative data.

In the embodiment of the present invention, the bearing production detection control device may load the bearing production equipment operation data into an optimized equipment operation data analysis neural network to perform operation data feature mining processing, so as to output corresponding operation data mining feature representations, and then perform operation data feature reduction processing on the operation data mining feature representations, so as to output corresponding key equipment operation behaviors, key behavior semantic data, and key equipment operation behavior representative data. The optimization equipment operation data analysis neural network is formed by loading typical bearing production equipment operation data into an equipment operation data analysis neural network to be optimized for network optimization, performing operation data feature mining processing and operation data feature reduction processing through the equipment operation data analysis neural network to be optimized to output typical key equipment operation behaviors, typical key behavior semantic data and typical key equipment operation behavior representative data, analyzing and outputting corresponding equipment operation behavior abnormal analysis results according to the typical key equipment operation behaviors, the typical key behavior semantic data and the typical key equipment operation behavior representative data, analyzing and determining learning cost values according to the output typical operation data mining feature representations to output corresponding typical key equipment operation behavior analysis results, analyzing and determining learning cost values according to the equipment operation behavior abnormal analysis results and configured equipment operation behavior actual results to output corresponding abnormal analysis learning cost values, analyzing and determining learning cost values according to the configured key equipment operation behavior actual results and the configured equipment operation behavior actual analysis results, analyzing and determining learning value corresponding learning cost values, and analyzing and determining learning cost values according to the learning cost analysis of the equipment operation data to be optimized and forming the optimization neural network optimization data according to the learning cost analysis values of the equipment operation data and the learning cost.

Step S130, analyzing and outputting a corresponding first equipment operation behavior abnormity analysis result according to the key equipment operation behavior, the key behavior semantic data and the key equipment operation behavior representative data, and determining quality representative data of the bearing product correspondingly produced by the target bearing production equipment according to the first equipment operation behavior abnormity analysis result.

In the embodiment of the invention, the bearing production detection control device can analyze and output a corresponding first device operation behavior abnormity analysis result according to the key device operation behavior, the key behavior semantic data and the key device operation behavior representation data, and then determine the quality representation data of the bearing product correspondingly produced by the target bearing production device according to the first device operation behavior abnormity analysis result (the operation behavior has higher correlation with the quality, for example, the device operation behavior is abnormal, which generally causes the quality of the produced bearing to be abnormal, in some applications, the quality representation data determined based on the first device operation behavior abnormity analysis result can be used as the quality representation data or the initial quality representation data of one dimension, so that the quality analysis and other processing can be further performed by combining the data of other dimensions).

Based on the foregoing, since the operation data is analyzed and processed based on the bearing production equipment, compared with the conventional technical scheme of performing video monitoring on the bearing or the equipment, no additional monitoring equipment needs to be deployed, so that the detection convenience is higher, and in addition, since the optimized equipment operation data analysis neural network is optimized based on the learning cost values in the two aspects of the abnormal analysis learning cost value and the behavior key analysis learning cost value, the reliability of the analysis function is higher, so that the convenience and the reliability of the bearing production detection can be improved, and the defects in the prior art are overcome.

It should be understood that, in some embodiments, the step S110 may include the following sub-steps (i.e., detailed implementation processes):

extracting a bearing production detection instruction, extracting bearing production equipment operation data from the bearing production detection instruction, and performing staged decomposition processing on the bearing production equipment operation data to form a plurality of corresponding original equipment operation behavior log data, wherein each original equipment operation behavior log data corresponds to one production stage (or production process, production link and the like) of a bearing;

performing feature mining (feature extraction and the like) on the original device operation behavior log data to obtain log data feature representation corresponding to the original device operation behavior log data, performing feature representation similarity calculation on the log data feature representation corresponding to the original device operation behavior log data and the log data feature representation corresponding to each adjacent original device operation behavior log data of the original device operation behavior log data to output corresponding feature representation similarity, and performing feature association processing on the log data feature representation corresponding to each adjacent original device operation behavior log data and the log data feature representation corresponding to the original device operation behavior log data according to the feature representation similarity to obtain associated log data feature representation of the original device operation behavior log data (exemplarily, the log data feature representation corresponding to the corresponding adjacent original device operation behavior log data may be weighted on the basis of the corresponding feature representation similarity, and then, the log data feature representation corresponding to each log data feature representation and the log data corresponding to the original device operation behavior log data may be superimposed to obtain associated log data;

for each piece of original equipment operation behavior log data, determining standard equipment operation behavior log data (the standard equipment operation behavior log data can be configured in advance) corresponding to the original equipment operation behavior log data, and determining associated standard log data characteristic representation (the determination method is as described above) corresponding to the standard equipment operation behavior log data;

for each piece of the original device operation behavior log data, performing feature representation distance calculation processing (the distance may be negatively correlated with the similarity) on the associated log data feature representation of the original device operation behavior log data and the associated standard log data feature representation corresponding to the standard device operation behavior log data corresponding to the original device operation behavior log data to obtain a feature representation distance corresponding to the original device operation behavior log data (the feature representation distance may be used for aggregating with the subsequently calculated device operation behavior abnormality degrees, such as weighted summation, to obtain a final device operation behavior abnormality degree, thereby implementing reliable analysis of behavior abnormality).

It should be understood that, in some embodiments, the optimization device operating data analysis neural network includes an optimized data feature mining model and an optimized data feature restoration model, based on which, the step S120 above may include the following sub-steps (i.e., detailed implementation procedures) that may be implemented:

and loading the running data mining feature representation into the optimized data feature reduction model for running data feature reduction processing so as to output corresponding key equipment running behaviors, key behavior semantic data and key equipment running behavior representative numbers.

It should be understood that, in some embodiments, the above bearing production detection control method may further include the following steps (i.e., detailed implementation procedures) that may be implemented:

extracting typical bearing production equipment operation data, an equipment operation behavior actual result and a key equipment operation behavior actual result (exemplarily, the typical bearing production equipment operation data, the equipment operation behavior actual result and the key equipment operation behavior actual result are combined as optimization bases, the equipment operation behavior actual result is used for reflecting a real behavior abnormal result of the typical bearing production equipment operation data, namely whether the typical bearing production equipment operation data is abnormal or abnormal degree and the like, and can be an integral one, and also can be used for reflecting the actual key equipment operation behavior in the typical bearing production equipment operation data according to the result of whether each equipment operation behavior has abnormality or abnormal degree and the like, and the key equipment operation behavior actual result can be formed by manual marking);

loading the typical bearing production equipment operation data into an equipment operation data analysis neural network to be optimized to perform operation data feature mining processing, so as to output corresponding typical operation data mining feature representations, and then performing operation data feature reduction processing on the typical operation data mining feature representations to output corresponding typical key equipment operation behaviors, typical key behavior semantic data and typical key equipment operation behavior representative data (for example, the typical key equipment operation behaviors may refer to key behaviors in a plurality of typical equipment operation behaviors included in the typical bearing production equipment operation data, the typical key behavior semantic data may be used for reflecting behavior attribute information of the typical key equipment operation behaviors, and may represent abnormality degrees, and the typical key equipment operation behavior representative data may be used for reflecting influence of the typical key equipment operation behaviors on subsequent equipment operation behaviors);

analyzing and outputting a corresponding device operation behavior anomaly analysis result according to the typical key device operation behavior, the typical key behavior semantic data and the typical key device operation behavior representative data (exemplarily, for each typical key device operation behavior, based on an influence of the previous typical key device operation behavior, behavior attribute information of the previous typical key device operation behavior and behavior attribute information of the current typical key device operation behavior are fused to obtain fused behavior attribute information corresponding to the current typical key device operation behavior, so as to obtain a device operation behavior anomaly analysis result;

and performing network optimization on the equipment operation data analysis neural network to be optimized according to the abnormal analysis learning cost value and the behavioral criticality analysis learning cost value to form a candidate equipment operation data analysis neural network, re-marking the candidate equipment operation data analysis neural network as the equipment operation data analysis neural network to be optimized, performing the step of extracting the typical bearing production equipment operation data, the equipment operation behavior actual result and the key equipment operation behavior actual result in a rotary manner, and forming the optimized equipment operation data analysis neural network under the condition that the goal of network optimization is achieved (for example, the learning cost value is smaller than a threshold value and the like).

It should be understood that, in some embodiments, the step of loading the typical bearing production equipment operation data into the to-be-optimized equipment operation data analysis neural network for performing the operation data feature mining process to output the corresponding typical operation data mining feature representation, and then performing the operation data feature reduction process on the typical operation data mining feature representation to output the corresponding typical key equipment operation behavior, the typical key behavior semantic data, and the typical key equipment operation behavior representation data may include some following sub-steps (i.e., detailed implementation processes) that may be implemented:

using the to-be-optimized device operation data analysis neural network to mine the data mining feature representation corresponding to the ordered set of typical device operation behaviors to output a corresponding typical operation data mining feature representation (for example, data mining feature representation mining may be performed on each typical device operation behavior in the ordered set of typical device operation behaviors, that is, feature mining, to obtain a data mining feature representation corresponding to each typical device operation behavior, and then, the data mining feature representations corresponding to each typical device operation behavior may be merged to form a data mining feature representation corresponding to the ordered set of typical device operation behaviors);

analyzing a neural network by using the device to be optimized operation data, performing operation data feature reduction processing on the typical operation data mining feature representation to output corresponding typical key device operation behaviors, typical key behavior semantic data and candidate device operation behavior representative data, and determining corresponding each key device operation behavior indication data according to the typical key device operation behaviors (each key device operation behavior indication data is used for reflecting at least one behavior influence of the typical key device operation behaviors and can be searched from historical behavior data);

It should be understood that, in some embodiments, the step of analyzing the neural network by using the device to be optimized operating data to perform the operating data feature reduction processing on the typical operating data mining feature representation to output corresponding typical key device operating behaviors, typical key behavior semantic data and candidate device operating behavior representative data may include the following sub-steps (i.e., detailed implementation procedures) that may be implemented:

performing, by using the to-be-optimized device operation data analysis neural network, operation data feature reduction processing on the configured head-end operation behavior identification feature representation and the typical operation data mining feature representation to output a corresponding first head-end operation behavior identification feature representation (for example, the head-end operation behavior identification feature representation may refer to a feature representation of configured identification information, where the identification information is used to indicate a first typical device operation behavior; in addition, the head-end operation behavior identification feature representation and the typical operation data mining feature representation may be fused, for example, by splicing or stacking, and then, the processing result is subjected to operation data feature reduction processing, where, for example, the operation data feature reduction processing may be implemented based on RNN or Long and Short Term Memory (LSTM));

performing running data feature reduction processing on the first head end running behavior identification feature representation and the typical running data mining feature representation by using the to-be-optimized equipment running data analysis neural network to output corresponding first center running behavior identification feature representation (for example, the first head end running behavior identification feature representation and the typical running data mining feature representation may be fused first, and then the fused result is subjected to running data feature reduction processing to output corresponding first center running behavior identification feature representation; in addition, the first center running behavior identification feature representations may be multiple, namely, corresponding to typical equipment running behaviors except for a head end and a tail end, wherein the latter first center running behavior identification feature is obtained by performing running data feature reduction processing on the basis of the former first center running behavior identification feature and the typical running data mining feature representation);

performing, by using the to-be-optimized device operation data analysis neural network, operation data feature reduction processing on the first center operation behavior identification feature representation and the typical operation data mining feature representation to output corresponding first end operation behavior identification feature representations (in a case where the first center operation behavior identification feature representation is multiple, operation data feature reduction processing may be performed on the last one of the first center operation behavior identification feature representation and the typical operation data mining feature representation to output a corresponding first end operation behavior identification feature representation);

analyzing the neural network by using the device operation data to be optimized, analyzing and processing the first head-end operation behavior identification feature representation, the first center operation behavior identification feature representation and the first tail-end operation behavior identification feature representation, and outputting corresponding typical key device operation behavior, typical key behavior semantic data and candidate device operation behavior representative data (based on which, each operation behavior identification feature representation can be fused with the previous operation behavior identification feature, that is, the influence of the previous device operation behavior on the later device operation behavior is considered on the whole, so that the information of each operation behavior identification feature representation is richer and more reliable, in addition, the first head-end operation behavior identification feature representation, each first center operation behavior identification feature representation and the first tail-end operation behavior identification feature representation can be spliced to form a spliced operation behavior identification feature representation, and then, analyzing the neural network by using the device operation data to be optimized, and estimating the corresponding typical key device operation behavior, candidate typical key behavior semantic data and candidate device operation behavior representative data from the spliced operation behavior identification feature representation.

It should be understood that, in some embodiments, the step of performing analysis and determination of the learning cost value according to the analysis result of the device operation behavior anomaly and the actual result of the device operation behavior to output the corresponding anomaly analysis learning cost value may include the following sub-steps (i.e., detailed implementation procedures) that may be implemented:

analyzing and outputting a head-end operation behavior analysis learning cost value corresponding to the first head-end operation behavior identification feature representation according to the first head-end operation behavior identification feature representation and the equipment operation behavior actual result (for example, an equipment operation behavior abnormality analysis result of a corresponding equipment operation behavior may be analyzed and output according to the first head-end operation behavior identification feature representation, and then, analyzing and outputting a corresponding end operation behavior analysis learning cost value based on the equipment operation behavior abnormality analysis result and the equipment operation behavior actual result corresponding to the equipment operation behavior);

analyzing and outputting a center operation behavior analysis learning cost value corresponding to the first center operation behavior identification feature representation (as described above, analysis of corresponding equipment operation behavior) according to the first center operation behavior identification feature representation and the equipment operation behavior actual result;

analyzing and outputting an end operation behavior analysis learning cost value corresponding to the first end operation behavior identification feature representation (as described above, analysis of corresponding equipment operation behavior) according to the first end operation behavior identification feature representation and the equipment operation behavior actual result;

analyzing and outputting a corresponding abnormal analysis learning cost value according to the head-end operation behavior analysis learning cost value, the center operation behavior analysis learning cost value and the tail-end operation behavior analysis learning cost value (for example, the head-end operation behavior analysis learning cost value, the center operation behavior analysis learning cost value and the tail-end operation behavior analysis learning cost value may be weighted and summed to obtain a corresponding abnormal analysis learning cost value).

It should be understood that, in some embodiments, the step of ordering the operation data of the typical bearing production equipment to form a corresponding ordered set of operation behaviors of the typical equipment, and then loading the ordered set of operation behaviors of the typical equipment to the neural network for analyzing the operation data of the equipment to be optimized may include the following sub-steps (i.e., detailed implementation procedures) that can be implemented:

extracting configured head end operation behavior indication information and tail end operation behavior indication information, combining the head end operation behavior indication information, the tail end operation behavior indication information and each typical device operation behavior according to the precedence relationship in the typical bearing production device operation data to form a corresponding typical device operation behavior ordered set (in the typical device operation behavior ordered set, the head end operation behavior indication information belongs to the first information in the set, and the tail end operation behavior indication information belongs to the last information in the set), and loading the typical device operation behavior ordered set to a device operation data analysis neural network to be optimized.

It should be understood that, in some embodiments, the step of analyzing the neural network by using the device operation data to be optimized, performing data comparison processing on the candidate device operation behavior representative data and each key device operation behavior indication data, and, in the case that the candidate device operation behavior representative data is consistent with the key device operation behavior indication data, performing marking processing on the candidate device operation behavior representative data to form corresponding typical key device operation behavior representative data may include the following sub-steps (i.e., detailed implementation processes) that may be implemented:

It should be understood that, in some embodiments, the exemplary operation data mining feature representation includes each exemplary operation behavior mining feature representation, and based on this, the step of performing operation behavior criticality analysis processing on the exemplary operation data mining feature representations to output corresponding operation behavior analysis results of the exemplary critical equipment may include the following sub-steps (i.e., detailed implementation procedures) that may be implemented:

sequentially traversing in each typical operation behavior mining feature representation (such as traversing a first typical operation behavior mining feature representation, traversing a second typical operation behavior mining feature representation, encoding a third typical operation behavior mining feature representation, and traversing a fourth typical operation behavior mining feature representation) to form a traversed typical operation behavior mining feature representation;

performing mapping output processing on the traversed typical operation behavior mining feature representation to output a corresponding mapping operation behavior mining feature representation (for example, the typical operation behavior mining feature table may be weighted based on a first parameter matrix, and then, a weighting result may be summed based on a second parameter matrix to implement shifting to obtain a mapping operation behavior mining feature representation; in addition, the first parameter matrix and the second parameter matrix belong to optimization parameters of a neural network), and then, performing operation behavior analysis processing on the mapping operation behavior mining feature representation to output a corresponding typical key device operation behavior analysis probability of the traversed typical operation behavior mining feature representation (the typical key device operation behavior analysis probability may refer to a probability that the corresponding typical device operation behavior belongs to a key device operation behavior, that is, an estimated probability value; and in addition, processing the mapping operation behavior mining feature representation based on a softmax function and outputting a corresponding typical device operation behavior analysis probability;

analyzing a corresponding traversed typical operation behavior analysis result of the traversed typical operation behavior mining feature representation according to the typical key equipment operation behavior analysis probability;

and forming a corresponding typical key equipment operation behavior analysis result according to each typical operation behavior mining feature representation corresponding typical operation behavior analysis result.

It should be understood that, in some embodiments, the step of performing an analysis determination of a learning cost value according to the actual result of the key device operation behavior and the analysis result of the typical key device operation behavior to output a corresponding behavior criticality analysis learning cost value may include the following sub-steps (i.e., detailed implementation processes):

analyzing and determining a learning cost value of the typical operation behavior analysis result corresponding to each typical operation behavior mining feature representation and the device operation behavior actual result corresponding to the key device operation behavior actual result to output each corresponding local behavior criticality analysis learning cost value (namely, for each typical operation behavior mining feature representation, performing difference analysis on the typical operation behavior analysis result corresponding to the typical operation behavior mining feature representation and the device operation behavior actual result corresponding to the typical device operation behavior in the key device operation behavior actual result to obtain a local behavior criticality analysis learning cost value);

and analyzing and outputting a corresponding analysis and learning cost value of the local behavior criticality according to each analysis and learning cost value of the local behavior criticality (illustratively, a sum value technique can be performed on each analysis and learning cost value of the local behavior criticality to obtain a corresponding analysis and learning cost value of the behavior criticality).

It should be understood that, in some embodiments, the to-be-optimized device operation data analysis neural network may include a to-be-optimized data feature mining model, a to-be-optimized data feature reduction model, and a to-be-optimized critical analysis processing model, based on which the foregoing steps may be implemented based on the to-be-optimized data feature mining model, the to-be-optimized data feature reduction model, and the to-be-optimized critical analysis processing model, and the detailed implementation process may include:

loading the typical bearing production equipment operation data into the data feature mining model to be optimized to perform operation data feature mining processing, and outputting corresponding typical operation data mining feature representation; loading the typical operation data mining feature representation into the data feature reduction model to be optimized to perform operation data feature reduction processing, outputting corresponding typical key equipment operation behavior, typical key behavior semantic data and typical key equipment operation behavior representative data, and analyzing and outputting corresponding equipment operation behavior abnormity analysis results according to the typical key equipment operation behavior, the typical key behavior semantic data and the typical key equipment operation behavior representative data; loading the typical operation data mining feature representation into the critical analysis processing model to be optimized to perform operation behavior critical analysis processing and output a corresponding typical key equipment operation behavior analysis result; and constructing a corresponding optimized device operation data analysis neural network according to the optimized data feature mining model to be optimized and the optimized data feature reduction model to be optimized (exemplarily, an optimization key analysis processing model in the optimized device operation data analysis neural network to be optimized can be directly discarded to obtain the optimized device operation data analysis neural network, and the optimized device operation data analysis neural network can also be constructed according to model parameters of the optimized data feature mining model to be optimized and the optimized data feature reduction model to be optimized).

With reference to fig. 3, an embodiment of the present invention further provides a bearing production detection control system, which can be applied to the bearing production detection control device. Wherein, the bearing production detection control system may include:

the production detection instruction extraction module is used for extracting a bearing production detection instruction, and the bearing production detection instruction comprises bearing production equipment operation data corresponding to target bearing production equipment;

a data feature processing module, configured to load the bearing production equipment operation data into an optimized equipment operation data analysis neural network for performing operation data feature mining processing to output corresponding operation data mining feature representations, perform operation data feature restoration processing to the operation data mining feature representations to output corresponding key equipment operation behaviors, key behavior semantic data, and key equipment operation behavior representative data, the optimized equipment operation data analysis neural network is formed by loading typical bearing production equipment operation data into an equipment operation data analysis neural network to be optimized for network optimization, perform operation data feature mining processing and operation data feature restoration processing through the equipment operation data analysis neural network to be optimized to output typical key equipment operation behaviors, typical key behavior semantic data, and typical key equipment operation behavior representative data, and output corresponding equipment operation behavior anomaly analysis results according to the typical key equipment operation behaviors, the typical key behavior semantic data, and the typical key equipment operation behavior representative data, and perform operation data analysis processing to the output corresponding equipment operation behavior anomaly analysis results, and perform learning value analysis to the extracted typical operation data mining feature representations to output corresponding typical operation behavior semantic data analysis results, and learning value analysis results of the equipment operation data, and determine learning value of the equipment operation data analysis results, and learning value of the equipment anomaly values of the extracted typical operation data analysis results, and learning value values of the extracted operation data of the extracted typical operation data of the extracted typical key behavior representative data of the extracted operation data of the extracted typical key equipment operation data of the extracted typical key equipment, network optimization is carried out on the device operation data analysis neural network to be optimized according to the abnormal analysis learning cost value and the behavior criticality analysis learning cost value, and a corresponding optimized device operation data analysis neural network is formed;

and the quality representative data determining module is used for analyzing and outputting a corresponding first equipment operation behavior abnormity analysis result according to the key equipment operation behavior, the key behavior semantic data and the key equipment operation behavior representative data, and then determining quality representative data of the bearing product correspondingly produced by the target bearing production equipment according to the first equipment operation behavior abnormity analysis result.

It should be understood that the production test instruction extraction module, the data feature processing module and the quality representative data determination module may all be software functional modules. Correspondingly, the bearing production detection control system can be a software functional system.

In summary, the bearing production detection control method and device provided by the invention can extract the operation data of the bearing production equipment; loading the running data of the bearing production equipment into an optimized equipment running data analysis neural network for running data feature mining processing to output running data mining feature representation, and then carrying out running data feature reduction processing on the running data mining feature representation to output key equipment running behavior, key behavior semantic data and key equipment running behavior representative data; analyzing and outputting an abnormal analysis result of the running behavior of the first equipment according to the running behavior of the key equipment, the semantic data of the key behavior and the representative data of the running behavior of the key equipment, and determining the representative data of the quality of the correspondingly produced bearing product according to the abnormal analysis result of the running behavior of the first equipment. Based on the content, because the operation data of the bearing production equipment is analyzed and processed, compared with the conventional technical scheme of carrying out video monitoring on the bearing or equipment, additional monitoring equipment is not needed to be deployed, so that the detection convenience is higher, in addition, because the operation data analysis neural network of the optimized equipment is optimized based on the learning cost values of the abnormal analysis learning cost value and the behavioral key analysis learning cost value, the reliability of the analysis function is higher, and therefore, the convenience and the reliability of the bearing production detection can be improved, and the defects in the prior art are overcome.

The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A bearing production detection control method is characterized by comprising the following steps:

2. The bearing production inspection control method of claim 1, wherein the optimization device operational data analysis neural network comprises an optimized data feature mining model and an optimized data feature reduction model; the steps of loading the bearing production equipment operation data into an optimized equipment operation data analysis neural network for operation data feature mining processing so as to output corresponding operation data mining feature representation, and then carrying out operation data feature reduction processing on the operation data mining feature representation so as to output corresponding key equipment operation behaviors, key behavior semantic data and key equipment operation behavior representative data comprise:

3. The bearing production inspection control method of claim 1, further comprising:

4. The bearing production detection control method according to claim 3, wherein the step of loading the typical bearing production equipment operation data into the equipment operation data analysis neural network to be optimized for operation data feature mining processing to output a corresponding typical operation data mining feature representation, and then performing operation data feature reduction processing on the typical operation data mining feature representation to output a corresponding typical key equipment operation behavior, typical key behavior semantic data and typical key equipment operation behavior representative data comprises:

ordering the typical bearing production equipment operation data to form a corresponding typical equipment operation behavior ordered set, and then loading the typical equipment operation behavior ordered set to an equipment operation data analysis neural network to be optimized;

and analyzing the neural network by utilizing the running data of the equipment to be optimized, performing data comparison processing on the candidate equipment running behavior representative data and each key equipment running behavior indicating data, and labeling the candidate equipment running behavior representative data under the condition that the candidate equipment running behavior representative data is consistent with the key equipment running behavior indicating data to form corresponding typical key equipment running behavior representative data.

5. The bearing production detection control method of claim 4, wherein the step of ordering the typical bearing production equipment operation data to form a corresponding typical equipment operation behavior ordered set, and then loading the typical equipment operation behavior ordered set to an equipment operation data analysis neural network to be optimized comprises:

extracting configured head end running behavior indication information and tail end running behavior indication information, combining the head end running behavior indication information, the tail end running behavior indication information and each typical device running behavior according to the precedence relationship in the typical bearing production device running data to form a corresponding typical device running behavior ordered set, and loading the typical device running behavior ordered set to a device running data analysis neural network to be optimized.

6. The bearing production inspection control method according to claim 4, wherein the step of analyzing the neural network by using the device operation data to be optimized, comparing the candidate device operation behavior representative data with each of the key device operation behavior indication data, and labeling the candidate device operation behavior representative data to form corresponding typical key device operation behavior representative data in a case where the candidate device operation behavior representative data is consistent with the key device operation behavior indication data, comprises:

7. The bearing production test control method of claim 3, wherein said representative operational data mining signature representations comprise each representative operational behavior mining signature representation;

8. The bearing production inspection control method according to claim 7, wherein the step of analyzing and determining the learning cost value according to the actual result of the operation behavior of the key device and the analysis result of the operation behavior of the typical key device to output the corresponding analysis learning cost value of the behavior criticality comprises:

and analyzing and outputting the corresponding behavior criticality analysis and learning cost value according to each local behavior criticality analysis and learning cost value.

9. The bearing production detection control method of claim 3, wherein the device to be optimized operation data analysis neural network comprises a data feature mining model to be optimized, a data feature reduction model to be optimized and a criticality analysis processing model to be optimized;

10. A bearing production inspection control apparatus comprising a processor and a memory, the memory storing a computer program, the processor executing the computer program to implement the bearing production inspection control method of any one of claims 1 to 9.