CN111992869B - Predictive maintenance method for electron beam welding equipment based on edge calculation - Google Patents
Predictive maintenance method for electron beam welding equipment based on edge calculation Download PDFInfo
- Publication number
- CN111992869B CN111992869B CN202010802205.7A CN202010802205A CN111992869B CN 111992869 B CN111992869 B CN 111992869B CN 202010802205 A CN202010802205 A CN 202010802205A CN 111992869 B CN111992869 B CN 111992869B
- Authority
- CN
- China
- Prior art keywords
- electron beam
- cathode
- beam welding
- welding
- flow data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K15/00—Electron-beam welding or cutting
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Welding Or Cutting Using Electron Beams (AREA)
Abstract
The embodiment of the invention relates to the field of electronic equipment, and discloses an edge calculation-based predictive maintenance method for electron beam welding equipment. In the invention, edge computing equipment is used for collecting first service flow data generated by electron beam welding equipment executing a welding task, wherein the first service flow data comprises: welding process data and quality information of the welded workpiece; predicting the first service flow data through a cathode loss prediction model to obtain the cathode loss of the electron beam welding equipment after the welding task is finished; and determining a cathode element storage strategy matched with the cathode loss of the electron beam welding equipment so as to give guiding opinions on the storage and purchase of the cathode elements of the production enterprise, thereby avoiding economic loss.
Description
Technical Field
The embodiment of the invention relates to the field of electronic equipment, in particular to a predictive maintenance method of electron beam welding equipment based on edge calculation.
Background
The electron beam welding has the advantages of high energy density, small heating area, deep penetration of electron beams, high welding speed, narrow weld heat affected zone, small workpiece deformation, convenient electron beam control, no pollution in vacuum electron beam welding and the like. At present, electron beam welding is widely used in the industries of automobiles, aviation, aerospace, nuclear industry and the like, and has developed into the industries of petroleum, chemical engineering, machinery, instruments, precision machining and the like.
The cathode element of the electron beam welding equipment is used for emitting electron beams, belongs to a wearing part, and can cause the fluctuation of electron beam current after the cathode reaches the service life limit, thereby causing serious influence on the welding quality and the welding efficiency; meanwhile, the cathode element is used as a main accessory of the electron beam welding equipment, and the maintenance period of the equipment is longer due to the purchase period and the purchase cost, so that the capacity of the welding unit is reduced, and the on-time delivery of products is influenced.
At present, most of enterprises using electron beam welding equipment maintain cathode elements of the equipment by adopting a passive maintainability maintenance strategy on one hand and an active preventive maintenance strategy on the other hand, and the two strategies have the defects that sudden failure risks cannot be completely eradicated, the maintenance period is difficult to control, spare part resources are unreasonably used, the maintenance cost is high and the like.
Disclosure of Invention
The invention aims to provide a predictive maintenance method of electron beam welding equipment based on edge calculation, which can give guiding opinions on the storage and purchase of cathode elements of a production enterprise by predicting the loss amount and the service life of the cathode elements of the electron beam welding equipment, thereby avoiding economic loss.
In order to solve the above technical problem, an embodiment of the present invention provides a method for predictive maintenance of an electron beam welding device based on edge calculation, including the following steps:
collecting first service flow data generated by an electron beam welding device executing a welding task, wherein the first service flow data comprises: welding process data and quality information of the welded workpiece;
predicting the first service flow data through a cathode loss prediction model generated by pre-training to obtain the cathode loss of the electron beam welding equipment after the welding task is finished;
selecting a cathode element storage strategy matched with the cathode loss amount of the electron beam welding equipment from a plurality of preset cathode element storage strategies.
An embodiment of the present invention also provides an electronic device, including:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method for predictive maintenance of electron beam welding equipment based on edge calculations as described above.
Embodiments of the present invention also provide a computer-readable storage medium storing a computer program which, when executed by a processor, implements the edge-computation-based predictive maintenance method for an electron beam welding apparatus as described above.
Compared with the prior art, the embodiment of the invention collects first service flow data generated by the electron beam welding equipment executing the welding task through the edge computing equipment, wherein the first service flow data comprises: welding process data and quality information of the welded workpiece; predicting the first service flow data through a cathode loss prediction model generated by pre-training to obtain the cathode loss of the electron beam welding equipment after the welding task is finished; and determining a cathode element storage strategy matched with the cathode loss amount of the electron beam welding equipment from a plurality of preset cathode element storage strategies so as to give guiding opinions on cathode element storage and purchase of a production enterprise, thereby avoiding economic loss.
In addition, the training process of the cathode loss prediction model specifically comprises the following steps: collecting a first business flow data sample of the electron beam welding equipment and historical record data of faults, maintenance and repair; the first traffic stream data sample comprises: historical first service flow data generated by the electron beam welding equipment executing a plurality of welding tasks; performing at least one of missing data filling, noise data removing and data dimension reduction on the historical first service flow data to obtain a preprocessed first service flow data sample; data mining is carried out on the historical record data to obtain the cathode loss of the electron beam welding equipment after each welding task is finished; and sending the preprocessed first business flow data sample and the corresponding cathode loss amount to a cloud server, so that the cloud server performs model training on the preprocessed first business flow data sample and the corresponding cathode loss amount by adopting a preset algorithm model to obtain a cathode loss prediction model. The training process of the cathode loss prediction model is executed through the cloud server, so that the computing resource advantages of cloud computing in processing of a large amount of computing data can be fully utilized, and the sufficient computing resources required by the training process are ensured; meanwhile, the edge computing equipment collects and generates sample data used for training the cathode loss prediction model, so that on one hand, the safety risk possibly caused by network delay and network transmission instability due to the fact that a large amount of originally collected data are directly transmitted to the cloud server can be avoided, on the other hand, the data processing capacity of the edge computing terminal can be fully exerted, and the network bandwidth pressure caused by a large amount of process data is avoided.
In addition, the method further comprises: acquiring second service flow data corresponding to a next welding task to be executed by the electron beam welding equipment, wherein the second service flow data comprises: pre-welding workpiece information and welding process requirement information; after the electron beam welding equipment executes the welding task, predicting the predicted cathode loss of the electron beam welding equipment and second service flow data corresponding to the next welding task to be executed by the electron beam welding equipment through a welding quality prediction model generated by pre-training to obtain the quality information of a welded workpiece corresponding to the next welding task executed by the electron beam welding equipment; determining a cathode element maintenance strategy matched with the predicted welding-finished workpiece quality information from a plurality of preset cathode element maintenance strategies; wherein the cathode element maintenance strategy comprises: at least two of the cathode continues to be used, replaced and repaired. Based on the predicted cathode loss amount of the electron beam welding equipment after the current welding task is executed, the quality information of the welded workpiece corresponding to the next welding task executed by the electron beam welding equipment is predicted by combining second service flow data corresponding to the next welding task to be executed by the electron beam welding equipment, and then a corresponding cathode element maintenance strategy is matched, so that any maintenance treatment of continuously using the cathode, replacing the cathode and maintaining the cathode can be performed on the cathode element in time according to the matched cathode element maintenance strategy, and the economic loss is avoided.
In addition, the step of determining the cathode element maintenance strategy matched with the predicted welding finished workpiece quality information from the preset cathode element maintenance strategies is specifically as follows: comparing the predicted quality information of the welded workpiece with corresponding quality information of the workpiece in a prestored workpiece quality knowledge base to generate a quality deviation result; and matching the quality deviation result with a preset maintenance rule to obtain a matched cathode element maintenance strategy, wherein the maintenance rule comprises corresponding relations between the quality deviations of different degrees and the cathode element maintenance strategy. By setting the workpiece quality knowledge base and the maintenance rules, the corresponding welded workpiece quality information is matched with the corresponding cathode element maintenance strategy when the predicted electron beam welding equipment executes the next welding task, and the normal implementation of the next welding task is ensured.
In addition, the training process of the welding quality prediction model specifically comprises the following steps: collecting a third traffic flow data sample, the third traffic flow data sample comprising: the electron beam welding equipment executes historical second service flow data and welded workpiece quality information corresponding to a plurality of welding tasks; performing at least one of preprocessing operations of missing data filling, noise data removing and data dimension reduction on the third service flow data sample to obtain a preprocessed third service flow data sample; and sending the preprocessed third business flow data sample to a cloud server so that the cloud server takes the third business flow data sample and the predicted cathode loss of the electron beam welding equipment based on the last welding task of each welding task in the third business flow data sample as training samples, and performing model training on the training samples by adopting a preset algorithm model to obtain a welding quality prediction model. The cloud server executes the training process of the welding quality prediction model, so that the computing resource advantages of cloud computing in processing of a large amount of computing data can be fully utilized, and the sufficient computing resources required by the training process are ensured; meanwhile, partial sample data used for training the welding quality prediction model is acquired and generated by the edge computing device, so that on one hand, the safety risk possibly caused by network delay and network transmission instability due to the fact that a large amount of original acquired data are directly transmitted to the cloud server can be avoided, on the other hand, the data processing capacity of the edge computing terminal can be fully exerted, and the network bandwidth pressure caused by a large amount of process data is avoided. In addition, when the welding quality prediction model is trained, the cathode loss amount predicted by the cathode loss prediction model is used as part of training samples, and the comprehensive prediction capability of the trained model is stronger by adopting an integrated training process among a plurality of models.
In addition, the method further comprises: the cloud server conducts iterative training on the trained cathode loss prediction model or welding quality prediction model, and sends the model after iterative training to the edge computing terminal to conduct model updating, so that model prediction accuracy is guaranteed through continuous updating of the model.
In addition, the preset algorithm model may specifically be: linear regression model, BP neural network.
In addition, the method further comprises: counting the accumulated service life of a cathode element currently configured on electron beam welding equipment after the electron beam welding equipment finishes the welding task; and determining a cathode element storage strategy matched with the accumulated use duration of the cathode elements currently configured on the electron beam welding equipment from a plurality of preset cathode element storage strategies, and accordingly determining a corresponding storage strategy based on the use duration of the cathode elements so as to give instructive opinions on the storage and purchase of the cathode elements of the production enterprise and avoid economic loss.
Drawings
One or more embodiments are illustrated by way of example in the accompanying drawings, which correspond to the figures in which like reference numerals refer to similar elements and which are not to scale unless otherwise specified.
FIG. 1 is a detailed flow chart of a predictive maintenance method for an electron beam welding apparatus based on edge calculation according to a first embodiment of the present invention;
fig. 2 is a detailed flowchart of a training processing method of a cathode loss prediction model according to a second embodiment of the present invention;
FIG. 3 is a detailed flowchart of a predictive maintenance method for an electron beam welding apparatus based on edge calculation according to a third embodiment of the present invention;
fig. 4 is a detailed flowchart of a training processing method of a welding quality prediction model according to a fourth embodiment of the present invention;
FIG. 5 is a detailed flow chart of a predictive maintenance method for an electron beam welding apparatus based on edge calculation according to a fifth embodiment of the present invention;
fig. 6 is a schematic structural diagram of an electronic device according to a sixth embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, embodiments of the present invention will be described in detail below with reference to the accompanying drawings. However, it will be appreciated by those of ordinary skill in the art that numerous technical details are set forth in order to provide a better understanding of the present application in various embodiments of the present invention. However, the technical solution claimed in the present application can be implemented without these technical details and various changes and modifications based on the following embodiments.
The first embodiment of the invention relates to a predictive maintenance method of an electron beam welding device based on edge calculation. The core of the embodiment lies in collecting first service flow data generated by the electron beam welding equipment executing the current welding task, wherein the first service flow data comprises: welding process data and quality information of the welded workpiece; predicting the first service flow data through a cathode loss prediction model generated by pre-training to obtain the cathode loss of the electron beam welding equipment after the welding task is finished; and determining a cathode element storage strategy matched with the cathode loss amount of the electron beam welding equipment from a plurality of preset cathode element storage strategies so as to give guiding opinions on cathode element storage and purchase of a production enterprise, thereby avoiding economic loss. The following describes implementation details of the method for preventing electronic equipment from being damaged in the present embodiment in detail, and the following description is only provided for facilitating understanding of the implementation details and is not necessary for implementing the present embodiment.
The predictive maintenance method of the electron beam welding equipment based on the edge calculation in the embodiment is shown in fig. 1, and the method is applied to an edge calculation terminal. The edge computing terminal is an open platform integrating network, computing, storage and application core capabilities on one side close to an object or a data source, provides edge side end services of an industrial field nearby, and has good local survival capability based on a strong software and hardware platform. The application program is initiated at the edge side, so that a faster network service response is generated, and the basic requirements of the industry in the aspects of real-time business, application intelligence, safety, privacy protection and the like are met.
The edge computing terminal is arranged between the physical entity and the industrial cloud connection and used as a link for connecting the sensing layer and the network layer, and protocol conversion between the sensing network and the communication network and between different types of sensing networks can be realized. The edge computing terminal is suitable for being used as an access node of large-scale distributed equipment, a protocol analyzer is embedded, data of field equipment can be collected to the terminal node, data cleaning and normalization processing are carried out, algorithm model prediction is achieved through edge computing, and core tasks can be completed on the edge side; meanwhile, the edge computing terminal is connected to the industrial cloud service, so that the access of a top management system is realized; meanwhile, the system supports virtual channels and data penetration, and can realize remote maintenance of the system (remote diagnosis of the system, remote monitoring and remote program uploading and downloading).
The electron beam welding equipment in the embodiment is connected with the edge computing terminal as the physical entity, so that the edge computing terminal can collect original data and information corresponding to the welding task from the side of the electron beam welding equipment.
As shown in fig. 1, the predictive maintenance method for an electron beam welding device based on edge calculation in the present embodiment specifically includes:
step 101: collecting first service flow data generated by an electron beam welding device executing a welding task, wherein the first service flow data comprises: welding process data and welded workpiece quality information.
Wherein, the welding process data refers to relevant state data corresponding to actual operation in the welding process, such as vacuum electron beam process parameters and environmental information shown in table 1; the welded workpiece quality information refers to quality information achieved by the welded target workpiece after welding is completed. Quality information for combustor casing ring welds as shown in table 2.
TABLE 1 welding procedure data sheet
TABLE 2 quality information table of welded workpiece
Step 102: and predicting the first service flow data through a cathode loss prediction model generated by pre-training to obtain the cathode loss of the electron beam welding equipment after the welding task is finished.
In the field of electron beam welding, the welding process data and the quality information of the welded workpiece in the first service flow data have a direct relationship with the cathode loss of the electron beam welding equipment, and the amount of the cathode loss further affects the reserve plan of the cathode elements. Therefore, in the present embodiment, the relationship between the first traffic flow data and the cathode loss amount of the electron beam welding apparatus is used in advance to train and generate the cathode loss prediction model.
For example, a cathode loss prediction model is constructed by using the first service flow data and the cathode loss of the electron beam welding equipment as sample data, and the cathode loss prediction model can predict the cathode loss of the electron beam welding equipment after any welding task is finished.
The cathode elements involved in the embodiments of the present invention are all of uniform specification and elements, and therefore, the cathode loss amount of the electron beam welding apparatus can be expressed by "percentage" by volume, for example, the cathode loss amount is 50%, that is, the consumed amount accounts for 50% of the total amount.
Specifically, in this step, the collected first traffic flow data generated when the electron beam welding device executes the current welding task may be input to the cathode loss prediction model for prediction to obtain a corresponding prediction result.
Step 103: and selecting a cathode element storage strategy matched with the cathode loss amount of the electron beam welding equipment from a plurality of preset cathode element storage strategies.
In the field of electron beam welding, the performance and quality of a cathode element of an electron beam welding apparatus at a certain time is inversely proportional to the amount of cathode loss of the electron beam welding apparatus up to that time. Therefore, by predicting the cathode loss amount of the electron beam welding apparatus, the consumption of the cathode element of the electron beam welding apparatus up to the present moment can be predicted, thereby assisting in determining the cathode element stocking strategy.
In this step, different cathode element reserve strategies are set for the cathode loss amounts of different electron beam welding devices, and the reserve strategies are specifically the reserve amounts of the cathode elements.
For example, in a factory, if the cathode consumption of a plurality of electron beam welding devices reaches a certain consumption at a certain time, the number of new cathode elements needs to be supplemented in time to avoid economic loss caused by the fact that the normal operation of the factory cannot be met due to the shortage of the cathode elements.
For this purpose, in the present embodiment, a plurality of cathode element reserve strategies are preset, and each reserve strategy specifies the reserve number of the cathode elements corresponding to the electron beam welding device in different cathode loss amount ranges. After the cathode loss amount of the electron beam welding equipment after executing the welding task is obtained based on the prediction model, the cathode loss amount can be directly matched with the cathode element storage strategies to determine the applicable cathode element storage strategy, so that a purchasing plan is guided and made based on the storage strategy.
Compared with the prior art, the embodiment of the invention collects the first service flow data generated by the electron beam welding equipment executing the welding task through the edge computing equipment, wherein the first service flow data comprises the following components: welding process data and quality information of the welded workpiece; predicting the first service flow data through a cathode loss prediction model generated by pre-training to obtain the cathode loss of the electron beam welding equipment after the welding task is finished; and determining a cathode element storage strategy matched with the cathode loss amount of the electron beam welding equipment from a plurality of preset cathode element storage strategies so as to give guiding opinions on cathode element storage and purchase of a production enterprise, thereby avoiding economic loss.
A second embodiment of the present invention relates to a training processing method of a cathode loss prediction model. The second embodiment is an improvement on the first embodiment, and the improvement is that:
the training process of the cathode loss prediction model comprises the following steps: collecting a first business flow data sample of the electron beam welding equipment and historical record data of faults, maintenance and repair; the first traffic stream data sample comprises: historical first service flow data generated by the electron beam welding equipment executing a plurality of welding tasks; performing at least one of missing data filling, noise data removing and data dimension reduction on the historical first service flow data to obtain a preprocessed first service flow data sample; data mining is carried out on the historical record data to obtain the cathode loss of the electron beam welding equipment after each welding task is finished; sending the preprocessed first business flow data sample and the corresponding cathode loss amount to a cloud server, so that the cloud server performs model training on the preprocessed first business flow data sample and the corresponding cathode loss amount by adopting a preset algorithm model to obtain the cathode loss prediction model. The training process of the cathode loss prediction model is executed through the cloud server, so that the computing resource advantages of cloud computing in processing of a large amount of computing data can be fully utilized, and the sufficient computing resources required by the training process are ensured; meanwhile, the edge computing equipment collects and generates sample data used for training the cathode loss prediction model, so that on one hand, the safety risk possibly caused by network delay and network transmission instability due to the fact that a large amount of originally collected data are directly transmitted to the cloud server can be avoided, on the other hand, the data processing capacity of the edge computing terminal can be fully exerted, and the network bandwidth pressure caused by a large amount of process data is avoided.
The specific flow chart is shown in fig. 2.
Step 201: collecting a first business flow data sample of the electron beam welding equipment and historical record data of faults, maintenance and repair; the first traffic flow data sample comprises: the electron beam welding device executes historical first traffic data generated by a plurality of welding tasks.
Wherein, the first service flow data comprises: the welding process data and the quality information of the welded workpiece, and specific information examples can be seen in tables 1 and 2. And the historical data of the fault, the repair and the maintenance of the electron beam welding equipment can be generated in the routine maintenance operation of the electron beam welding equipment.
Step 202: and performing at least one of missing data filling, noise data removing and data dimension reduction on the historical first traffic flow data to obtain a preprocessed first traffic flow data sample.
Regarding missing data padding, in order to reduce the influence caused by the sample error of the first service flow data sample, the sample data with the missing value is padded, and specifically, the data with the missing value may be padded by using a central metric (such as a mean value or a median) of an attribute.
With respect to noise data removal, to reduce the impact of sample errors of the first traffic stream data samples, outliers may be detected using a distance-based clustering method to remove noise data.
For example, each first traffic data is expressed as a multidimensional vector, each data corresponds to a point in a multidimensional space, the distance between two points is defined by using an euclidean distance, and a distance matrix R of n data objects is formed:
Regarding data dimension reduction, due to the fact that specific data items contained in the data samples are numerous, the training process complexity is increased during later model training, and the contribution of some data to the data features is not large, therefore, the scheme performs data dimension reduction on the first traffic flow data sample, and expresses the overall (main) data features of the first traffic flow data sample by using a small number of data items.
The data dimension reduction method may include, but is not limited to, Principal Component Analysis (PCA), factor Analysis, and the like.
Step 203: and (4) carrying out data mining on the historical record data to obtain the cathode loss of the electron beam welding equipment after each historical welding task is finished.
The cathode loss period of each electron beam welding device can be excavated from the historical record data of the faults, the maintenance and the maintenance of the electron beam welding devices, and the time node of the end of each historical welding task is aligned with the cathode loss period of the electron beam welding device, so that the cathode loss amount of the electron beam welding device after each historical welding task is ended can be obtained.
During the process of mining the historical record data of the faults, the maintenance and the maintenance of the electron beam welding equipment and acquiring the loss period of each electron beam welding equipment, the historical record data can be summarized by combining the experience knowledge of maintenance personnel.
Step 204: and sending the preprocessed first business flow data sample and the corresponding cathode loss amount to a cloud server, so that the cloud server performs model training on the preprocessed first business flow data sample and the corresponding cathode loss amount by adopting a preset algorithm model to obtain a cathode loss prediction model.
Because the computing resources of the edge computing terminal are limited and cannot support a large amount of computing resources required in the model training process, in the embodiment, after the edge computing terminal collects the training samples required by the training model, the training samples, namely the first business flow data samples and the corresponding cathode loss amount can be sent to the cloud server, so that the strong computing power and rich resources of the cloud server are utilized to train and generate the cathode loss prediction model. And after the cloud server trains and generates a cathode loss prediction model, returning the cathode loss prediction model to the edge computing terminal for relevant prediction.
Compared with the prior art, the embodiment of the invention executes the training process of the cathode loss prediction model through the cloud server, can fully utilize the computing resource advantages of cloud computing when processing a large amount of computing data, and ensures that the computing resources required by the training process are sufficient; meanwhile, the edge computing equipment collects and generates sample data used for training the cathode loss prediction model, so that on one hand, the safety risk possibly caused by network delay and network transmission instability due to the fact that a large amount of originally collected data are directly transmitted to the cloud server can be avoided, on the other hand, the data processing capacity of the edge computing terminal can be fully exerted, and the network bandwidth pressure caused by a large amount of process data is avoided.
A third embodiment of the invention relates to a method for predictive maintenance of electron beam welding equipment based on edge calculations. The third embodiment is an improvement on the first embodiment, and the improvement is that:
the method further comprises the following steps: acquiring second service flow data corresponding to a next welding task to be executed by the electron beam welding equipment, wherein the second service flow data comprises: pre-welding workpiece information and welding process requirement information; after the electron beam welding equipment executes the welding task, predicting the predicted cathode loss of the electron beam welding equipment and second service flow data corresponding to the next welding task to be executed by the electron beam welding equipment through a welding quality prediction model generated by pre-training to obtain the quality information of a welded workpiece corresponding to the next welding task executed by the electron beam welding equipment; determining a cathode element maintenance strategy matched with the predicted welding-finished workpiece quality information from a plurality of preset cathode element maintenance strategies; wherein the cathode element maintenance strategy comprises: at least two of the cathode continues to be used, replaced and repaired. Based on the predicted cathode loss amount of the electron beam welding equipment after the current welding task is executed, the quality information of the welded workpiece corresponding to the next welding task executed by the electron beam welding equipment is predicted by combining second service flow data corresponding to the next welding task to be executed by the electron beam welding equipment, and then a corresponding cathode element maintenance strategy is matched, so that any maintenance treatment of continuously using the cathode, replacing the cathode and maintaining the cathode can be performed on the cathode element in time according to the matched cathode element maintenance strategy, and the economic loss is avoided.
The specific flow chart is shown in fig. 3.
Step 301: collecting first service flow data generated by an electron beam welding device executing a welding task, wherein the first service flow data comprises: welding process data and welded workpiece quality information.
Step 302: and predicting the first service flow data through a cathode loss prediction model generated by pre-training to obtain the cathode loss of the electron beam welding equipment after the welding task is finished.
Step 403: and selecting a cathode element storage strategy matched with the cathode loss amount of the electron beam welding equipment from a plurality of preset cathode element storage strategies.
The contents of steps 401 to 403 are the same as those of steps 101 to 103, and are not described herein.
Step 404: acquiring second service flow data corresponding to a next welding task to be executed by the electron beam welding equipment, wherein the second service flow data comprises: workpiece information before welding and welding process requirement information.
Wherein, the pre-welding workpiece information refers to the relevant information of the object workpiece to be welded before each welding task is executed, such as the information of the parts of the combustion chamber shell assembly and the assembled assembly shown in table 1; the welding process requirement information refers to process requirement data required to be followed by actual operation in the welding process, and the specific data type is consistent with the welding process data, which is not described herein again.
TABLE 3 Pre-weld workpiece (combustor housing Assembly) information
Specifically, after the electron beam welding device has executed the current welding task, the pre-welding workpiece information and the welding process requirement information of the next welding task to be executed by the electron beam welding device may be obtained in advance, so as to predict whether the electron beam welding device is adequate for the next welding task.
Step 405: after the electron beam welding equipment executes the welding task, predicting the predicted cathode loss of the electron beam welding equipment and second service flow data corresponding to the next welding task to be executed by the electron beam welding equipment through a welding quality prediction model generated by pre-training to obtain the quality information of the welded workpiece corresponding to the next welding task executed by the electron beam welding equipment.
In the field of electron beam welding, electron beam welding equipment causes cathode loss after each welding task. This consumption has a direct influence on whether the electron beam welding apparatus can continue to complete the next welding task, i.e., the quality information of the welded workpiece after the next welding task. Therefore, in the present embodiment, in two adjacent welding jobs, the electron beam welding device is used to perform model training on the cathode loss amount corresponding to the previous welding job, the pre-welding workpiece information corresponding to the next welding job, the welding process requirement information, and the post-welding workpiece quality information, and generate the welding quality prediction model. And the corresponding cathode loss amount after the previous welding task is executed can be obtained by performing model prediction on the cathode loss prediction model.
It should be noted that, in general, the electron beam welding equipment operates according to the welding process requirement information to complete the welding task, so the generated welding process data is usually consistent with the content of the welding process requirement information, and is different only in the name of the information, the scene to which the information belongs, and the operation time node. Therefore, when the welding quality prediction model is trained, the welding quality prediction model can be generated by adopting any data of welding process data or welding process requirement information corresponding to the welding task for training. When the welding quality prediction model is used for prediction, the input data can only be the welding process requirement information of the welding task to be executed for prediction.
Specifically, in this step, the predicted cathode loss amount of the electron beam welding device after the electron beam welding device executes the current welding task and the second service flow data corresponding to the next welding task to be executed by the electron beam welding device to be predicted may be input to the welding quality prediction model as input data, so as to obtain the quality information of the welded workpiece corresponding to the next welding task executed by the electron beam welding device.
Step 406: and determining a cathode element maintenance strategy matched with the predicted welding finished workpiece quality information from a plurality of preset cathode element maintenance strategies.
Wherein the cathode element maintenance strategy comprises: at least two of the cathode continues to be used, replaced and repaired.
Whether the electron beam welding equipment is qualified for the next welding task can be judged according to the predicted welding-finished workpiece quality information, so that a cathode element maintenance strategy matched with the predicted welding-finished workpiece quality information is determined. For example, when the predicted welded finished workpiece quality is high, the cathode may continue to be used; when the predicted welded workpiece quality is low, the cathode may be replaced or a measure for repairing the cathode may be taken.
In a specific embodiment, this step can be specifically realized by the following steps:
the method comprises the following steps: and comparing the predicted quality information of the welded workpiece with corresponding quality information of the workpiece in a prestored workpiece quality knowledge base to generate a quality deviation result.
The workpiece quality knowledge base stores workpiece quality information of different workpieces to be obtained under the specified welding process requirement information in advance. By comparing the predicted quality information of the welded workpiece with the workpiece quality information of the corresponding workpiece in the workpiece quality knowledge base, which is obtained under the same welding process requirement information, whether the electron beam welding equipment has the capability requirement for executing the next welding task can be judged, and the quality deviation result after the workpiece quality comparison is the basis for quantitative evaluation of the capability requirement.
Step two: and matching the quality deviation result with a preset maintenance rule to obtain a matched cathode element maintenance strategy, wherein the maintenance rule comprises corresponding relations between the quality deviations of different degrees and the cathode element maintenance strategy.
The corresponding relationship between the quality deviation and the cathode element maintenance strategy of different degrees can be preset, for example, the corresponding cathode element maintenance strategy with no quality deviation or the quality deviation lower than the minimum threshold value is used continuously; the corresponding cathode element maintenance strategy with a quality deviation above the maximum threshold is to replace the cathode; and the corresponding cathode element maintenance strategy with a quality deviation between the minimum and maximum thresholds is to repair the cathode.
Compared with the prior art, the method and the device have the advantages that the quality information of the welded workpiece corresponding to the next welding task executed by the electron beam welding equipment is predicted by combining the second service flow data corresponding to the next welding task to be executed by the electron beam welding equipment based on the predicted cathode loss amount of the electron beam welding equipment after the current welding task is executed, and then the corresponding cathode element maintenance strategy is matched, so that any one of the maintenance processing of continuously using the cathode, replacing the cathode and maintaining the cathode can be performed on the cathode element in time according to the matched cathode element maintenance strategy, and the economic loss is avoided.
A fourth embodiment of the present invention relates to a training processing method for a welding quality prediction model. The fifth embodiment is an improvement of the fourth embodiment, and the improvement is that:
the training process of the welding quality prediction model specifically comprises the following steps: collecting a third traffic flow data sample, the third traffic flow data sample comprising: the electron beam welding equipment executes historical second service flow data and welded workpiece quality information corresponding to a plurality of welding tasks; performing at least one of preprocessing operations of missing data filling, noise data removing and data dimension reduction on the third service flow data sample to obtain a preprocessed third service flow data sample; and sending the preprocessed third business flow data sample to a cloud server so that the cloud server takes the third business flow data sample and the predicted cathode loss of the electron beam welding equipment based on the last welding task of each welding task in the third business flow data sample as training samples, and performing model training on the training samples by adopting a preset algorithm model to obtain a welding quality prediction model. The cloud server executes the training process of the welding quality prediction model, so that the computing resource advantages of cloud computing in processing of a large amount of computing data can be fully utilized, and the sufficient computing resources required by the training process are ensured; meanwhile, partial sample data used for training the welding quality prediction model is acquired and generated by the edge computing device, so that on one hand, the safety risk possibly caused by network delay and network transmission instability due to the fact that a large amount of original acquired data are directly transmitted to the cloud server can be avoided, on the other hand, the data processing capacity of the edge computing terminal can be fully exerted, and the network bandwidth pressure caused by a large amount of process data is avoided. In addition, when the welding quality prediction model is trained, the cathode loss amount predicted by the cathode loss prediction model is used as part of training samples, and the comprehensive prediction capability of the trained model is stronger by adopting an integrated training process among a plurality of models.
The specific flow chart is shown in fig. 4.
Step S401: collecting a third traffic flow data sample, the third traffic flow data sample comprising: and the electron beam welding equipment executes historical second service flow data and welded workpiece quality information corresponding to a plurality of welding tasks.
The second service flow data comprises workpiece information before welding and welding process requirement information.
Step S402: and performing at least one of missing data filling, noise data removing and data dimension reduction on the third service flow data sample to obtain a preprocessed third service flow data sample.
For the processing operations of missing data filling, noise data removing, and data dimension reduction performed on the sample data, reference may be made to the corresponding content in the foregoing step S202, which is not described herein again.
Step S403: and sending the preprocessed third business flow data sample to a cloud server so that the cloud server takes the third business flow data sample and the predicted cathode loss amount of the electron beam welding equipment based on the last welding task of each welding task in the third business flow data sample as training samples, and performing model training on the training samples by adopting a preset algorithm model to obtain a welding quality prediction model.
In the embodiment, after the edge computing terminal collects part of training samples required by the training model, the training samples, namely, the third service flow data samples, can be sent to the cloud server, and the cloud server can be used for carrying out model training on the training samples by adopting a preset algorithm model based on the cathode loss of the electron beam welding equipment predicted by the cathode loss prediction model locally as the samples and the third service flow data samples as the training samples, so as to obtain the welding quality prediction model.
Compared with the prior art, the method and the device have the advantages that the cloud server executes the training process of the welding quality prediction model, so that the computing resource advantages of cloud computing in processing of a large amount of computing data can be fully utilized, and the sufficient computing resources required by the training process are ensured; meanwhile, partial sample data used for training the welding quality prediction model is acquired and generated by the edge computing device, so that on one hand, the safety risk possibly caused by network delay and network transmission instability due to the fact that a large amount of original acquired data are directly transmitted to the cloud server can be avoided, on the other hand, the data processing capacity of the edge computing terminal can be fully exerted, and the network bandwidth pressure caused by a large amount of process data is avoided. In addition, when the welding quality prediction model is trained, the cathode loss amount predicted by the cathode loss prediction model is used as part of training samples, and the comprehensive prediction capability of the trained model is stronger by adopting an integrated training process among a plurality of models.
In addition, the method further comprises the following steps: the cloud server conducts iterative training on the trained cathode loss prediction model or welding quality prediction model, and sends the model after iterative training to the edge computing terminal to conduct model updating, so that model prediction accuracy is guaranteed through continuous updating of the model.
In addition, the preset algorithm model may specifically be: linear regression model, BP neural network.
For example, a linear regression model y ═ a may be used0+a1x1+a2x2+...+akxkAnd establishing the prediction model. Wherein xiK is a sample parameter, aiI is 0,1,2, and k is a regression coefficient.
All 1 constant vectors with x being nxk, Y being nx1 and P being nx1Let X be (P, X)T)，xTFor a transposed matrix of x, the estimation of the regression coefficient vector a using the least squares method is:
a fifth embodiment of the present invention is directed to a method for predictive maintenance of electron beam welding equipment based on edge calculations. The fifth embodiment is an improvement of the fourth embodiment, and the improvement is that:
the method further comprises the following steps: counting the accumulated service life of a cathode element currently configured on electron beam welding equipment after the electron beam welding equipment finishes the welding task; and determining a cathode element storage strategy matched with the accumulated use duration of the cathode elements currently configured on the electron beam welding equipment from a plurality of preset cathode element storage strategies, and accordingly determining a corresponding storage strategy based on the use duration of the cathode elements so as to give instructive opinions on the storage and purchase of the cathode elements of the production enterprise and avoid economic loss.
The specific flow chart is shown in fig. 5.
Step S501: and counting the accumulated service life of the cathode element currently configured on the electron beam welding equipment after the electron beam welding equipment finishes the welding task.
Specifically, after each time a new cathode element is replaced for the electron beam welding apparatus, the cumulative usage time of the cathode element, that is, the cumulative time of the welding task performed by the electron beam welding apparatus using the cathode element, is counted.
Step S502: determining a cathode element storage strategy matched with the accumulated use time of the cathode elements currently configured on the electron beam welding equipment from a plurality of preset cathode element storage strategies.
In the field of electron beam welding, the performance and quality of a cathode element of an electron beam welding apparatus at a certain time is inversely proportional to the cumulative duration of use of the cathode element up to that time. Therefore, the remaining usage time of the cathode element can be inferred by counting the accumulated usage time of the cathode element and the empirical usage time (service life) of the cathode element, thereby assisting in determining the cathode element reserve strategy.
In this step, different cathode element reserve strategies are set for the accumulated usage time of different cathode elements, and the reserve strategies are specifically the reserve number of the cathode elements.
For example, in a factory, if the accumulated use time of the cathode elements of a plurality of electron beam welding devices reaches the preset time at a certain moment, the number of new cathode elements needs to be supplemented in time to avoid economic loss caused by the fact that the normal operation of the factory cannot be met due to the lack of the reserve of the cathode elements.
For this purpose, a plurality of cathode element reserve strategies are preset in the present embodiment, each reserve strategy specifying a reserve number of cathode elements corresponding to the electron beam welding apparatus in a different range of cumulative usage periods of the cathode elements. Based on the accumulated use duration of the currently used cathode elements up to the current statistics, the accumulated use duration can be directly matched with the cathode element storage strategies to determine the applicable cathode element storage strategy, so that a purchasing plan is guided and made based on the storage strategy.
This embodiment may be used as a supplement to the first embodiment to assist in determining an applicable cathode element stocking strategy.
Compared with the prior art, the method and the device for determining the reserve strategy determine the corresponding reserve strategy based on the using time of the cathode element so as to give guiding opinions on reserve and purchase of the cathode element of a production enterprise, thereby avoiding economic loss.
The steps of the above methods are divided for clarity, and the implementation may be combined into one step or split some steps, and the steps are divided into multiple steps, so long as the same logical relationship is included, which are all within the protection scope of the present patent; it is within the scope of the patent to add insignificant modifications to the algorithms or processes or to introduce insignificant design changes to the core design without changing the algorithms or processes.
A sixth embodiment of the invention relates to an electronic device, as shown in fig. 6, comprising at least one processor 602; and a memory communicatively coupled to the at least one processor 602; wherein the memory 601 stores instructions executable by the at least one processor 602, the instructions being executable by the at least one processor 602 to enable the at least one processor 602 to perform any of the above-described method embodiments.
Where the memory 301 and the processor 602 are coupled in a bus, the bus may comprise any number of interconnected buses and bridges that couple one or more of the various circuits of the processor 602 and the memory 601 together. The bus may also connect various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface provides an interface between the bus and the transceiver. The transceiver may be one element or a plurality of elements, such as a plurality of receivers and transmitters, providing a means for communicating with various other apparatus over a transmission medium. Data processed by processor 602 is transmitted over a wireless medium through an antenna, which receives the data and transmits the data to processor 602.
The processor 602 is responsible for managing the bus and general processing and may also provide various functions including timing, peripheral interfaces, voltage regulation, power management, and other control functions. And memory 601 may be used to store data used by processor 602 in performing operations.
A seventh embodiment of the present invention relates to a computer-readable storage medium storing a computer program. The computer program realizes any of the above-described method embodiments when executed by a processor.
That is, as can be understood by those skilled in the art, all or part of the steps in the method for implementing the embodiments described above may be implemented by a program instructing related hardware, where the program is stored in a storage medium and includes several instructions to enable a device (which may be a single chip, a chip, or the like) or a processor (processor) to execute all or part of the steps of the method described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
It will be understood by those of ordinary skill in the art that the foregoing embodiments are specific examples for carrying out the invention, and that various changes in form and details may be made therein without departing from the spirit and scope of the invention in practice.
Claims (9)
1. An edge calculation-based electron beam welding equipment predictive maintenance method is applied to an edge calculation terminal and is characterized by comprising the following steps:
collecting first service flow data generated by an electron beam welding device executing a welding task, wherein the first service flow data comprises: welding process data and quality information of the welded workpiece;
predicting the first service flow data through a cathode loss prediction model generated by pre-training to obtain the cathode loss of the electron beam welding equipment after the welding task is finished;
determining a cathode element reserve strategy matched with the cathode loss amount of the electron beam welding equipment from a plurality of preset cathode element reserve strategies; each reserve strategy specifies the reserve quantity of the cathode elements corresponding to the electron beam welding equipment under different cathode loss quantity ranges;
the training process of the cathode loss prediction model comprises the following steps:
collecting a first business flow data sample of the electron beam welding equipment and historical record data of faults, maintenance and repair; the first traffic flow data sample comprises: historical first service flow data generated by the electron beam welding equipment executing a plurality of welding tasks;
performing at least one of missing data filling, noise data removing and data dimension reduction on the historical first service flow data to obtain a preprocessed first service flow data sample, wherein a mean value or median central measurement method is adopted to perform missing data filling on data with missing values, and a distance-based clustering method is used to detect outliers for noise data removing;
data mining is carried out on the historical record data, time nodes of the end of each historical welding task are aligned with the cathode loss period of the electron beam welding equipment, and the cathode loss amount of the electron beam welding equipment after each historical welding task is ended is obtained;
and sending the preprocessed first business flow data sample and the corresponding cathode loss amount to a cloud server, so that the cloud server performs model training on the preprocessed first business flow data sample and the corresponding cathode loss amount by adopting a preset algorithm model to obtain the cathode loss prediction model.
2. The method of claim 1, further comprising:
acquiring second service flow data corresponding to a next welding task to be executed by the electron beam welding equipment, wherein the second service flow data comprises: pre-welding workpiece information and welding process requirement information;
predicting the predicted cathode loss amount of the electron beam welding equipment and second service flow data corresponding to the next welding task to be executed by the electron beam welding equipment after the electron beam welding equipment executes the welding task, and predicting through a welding quality prediction model generated by pre-training to obtain the quality information of a welded workpiece corresponding to the next welding task executed by the electron beam welding equipment;
determining a cathode element maintenance strategy matched with the predicted welding-finished workpiece quality information from a plurality of preset cathode element maintenance strategies;
wherein the cathode element maintenance strategy comprises: at least two of the cathode continues to be used, replaced and repaired.
3. The method according to claim 2, wherein determining a cathode element maintenance strategy matching the predicted weld-completed workpiece quality information from a predetermined plurality of cathode element maintenance strategies comprises:
comparing the predicted quality information of the welded workpiece with corresponding quality information of the workpiece in a prestored workpiece quality knowledge base to generate a quality deviation result;
and matching the quality deviation result with a preset maintenance rule to obtain the matched cathode element maintenance strategy, wherein the maintenance rule comprises corresponding relations between the quality deviations of different degrees and the cathode element maintenance strategy.
4. The method of claim 2, wherein the training process of the weld quality prediction model comprises:
collecting a third traffic flow data sample, the third traffic flow data sample comprising: the electron beam welding equipment executes historical second service flow data and welded workpiece quality information corresponding to a plurality of welding tasks;
performing at least one of preprocessing operations of missing data filling, noise data removing and data dimension reduction on the third service flow data sample to obtain a preprocessed third service flow data sample;
and sending the preprocessed third business flow data sample to the cloud server, so that the cloud server takes the third business flow data sample and the predicted cathode loss of the electron beam welding equipment based on the last welding task of each welding task in the third business flow data sample as training samples, and performing model training on the training samples by adopting a preset algorithm model to obtain the welding quality prediction model.
5. The method of claim 4, further comprising:
and the cloud server carries out iterative training on the trained cathode loss prediction model or the trained welding quality prediction model, and sends the model after iterative training to the edge computing terminal for model updating.
6. The method according to claim 1 or 4, wherein the preset algorithm model comprises: linear regression model, BP neural network.
7. The method of claim 1, further comprising:
counting the accumulated service life of the cathode element currently configured on the electron beam welding equipment after the electron beam welding equipment finishes the welding task;
determining a cathode element storage strategy matched with the accumulated use time of the cathode elements currently configured on the electron beam welding equipment from a plurality of preset cathode element storage strategies.
8. An electronic device, comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the edge-computing-based predictive maintenance method for electron beam welding equipment of any of claims 1 to 7.
9. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the edge-computation-based predictive maintenance method for an electron beam welding apparatus according to any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010802205.7A CN111992869B (en) | 2020-08-11 | 2020-08-11 | Predictive maintenance method for electron beam welding equipment based on edge calculation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010802205.7A CN111992869B (en) | 2020-08-11 | 2020-08-11 | Predictive maintenance method for electron beam welding equipment based on edge calculation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111992869A CN111992869A (en) | 2020-11-27 |
| CN111992869B true CN111992869B (en) | 2022-04-26 |
Family
ID=73463115
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010802205.7A Active CN111992869B (en) | 2020-08-11 | 2020-08-11 | Predictive maintenance method for electron beam welding equipment based on edge calculation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111992869B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112699113B (en) * | 2021-01-12 | 2022-08-05 | 上海交通大学 | Industrial manufacturing process operation monitoring system driven by time sequence data stream |
| CN113077061B (en) * | 2021-02-20 | 2022-08-16 | 上海琥崧智能科技股份有限公司 | Equipment predictive maintenance system based on production data mining |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US3648009A (en) * | 1969-05-06 | 1972-03-07 | Karl Heinz Steigerwald | Method and device for inspecting and/or controlling thermally produced mechanical joints |
| US10031500B1 (en) * | 2017-03-01 | 2018-07-24 | PLETHORA IIoT, S.L. | Device and system including multiple devices for supervision and control of machines in industrial installation |
| CN109635958A (en) * | 2018-12-12 | 2019-04-16 | 成都航天科工大数据研究院有限公司 | A kind of predictive industrial equipment maintaining method and maintenance system based on edge calculations |
| CN109635997A (en) * | 2018-11-02 | 2019-04-16 | 广州裕申电子科技有限公司 | A kind of prediction technique and system on equipment maintenance opportunity |
| CN110414033A (en) * | 2019-05-31 | 2019-11-05 | 太原理工大学 | The mechanical equipment approaches of predictive maintenance that jointing edge calculates and number is twin |
| CN110719210A (en) * | 2019-12-05 | 2020-01-21 | 赣江新区智慧物联研究院有限公司 | Industrial equipment predictive maintenance method based on cloud edge cooperation |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9652723B2 (en) * | 2015-06-05 | 2017-05-16 | Sas Institute Inc. | Electrical transformer failure prediction |
-
2020
- 2020-08-11 CN CN202010802205.7A patent/CN111992869B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US3648009A (en) * | 1969-05-06 | 1972-03-07 | Karl Heinz Steigerwald | Method and device for inspecting and/or controlling thermally produced mechanical joints |
| US10031500B1 (en) * | 2017-03-01 | 2018-07-24 | PLETHORA IIoT, S.L. | Device and system including multiple devices for supervision and control of machines in industrial installation |
| CN109635997A (en) * | 2018-11-02 | 2019-04-16 | 广州裕申电子科技有限公司 | A kind of prediction technique and system on equipment maintenance opportunity |
| CN109635958A (en) * | 2018-12-12 | 2019-04-16 | 成都航天科工大数据研究院有限公司 | A kind of predictive industrial equipment maintaining method and maintenance system based on edge calculations |
| CN110414033A (en) * | 2019-05-31 | 2019-11-05 | 太原理工大学 | The mechanical equipment approaches of predictive maintenance that jointing edge calculates and number is twin |
| CN110719210A (en) * | 2019-12-05 | 2020-01-21 | 赣江新区智慧物联研究院有限公司 | Industrial equipment predictive maintenance method based on cloud edge cooperation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111992869A (en) | 2020-11-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111992869B (en) | Predictive maintenance method for electron beam welding equipment based on edge calculation | |
| CN109412870B (en) | Alarm monitoring method and platform, server and storage medium | |
| CN110493025B (en) | Fault root cause diagnosis method and device based on multilayer digraphs | |
| Liu et al. | Study on a tolerance grading allocation method under uncertainty and quality oriented for remanufactured parts | |
| CN110427712B (en) | Preventive maintenance method based on fault influence analysis and workshop manufacturing system | |
| Lechevalier et al. | Towards a domain-specific framework for predictive analytics in manufacturing | |
| US20140207415A1 (en) | Performance evaluation system and method therefor | |
| CN109858786B (en) | Electromechanical device management system based on Internet of things | |
| US20210166181A1 (en) | Equipment management method, device, system and storage medium | |
| Schreiber et al. | Integrated production and maintenance planning for cyber-physical production systems | |
| JP2017188038A (en) | Manufacturing control system for improving operation rate of manufacturing cell | |
| Ju et al. | Quality flow model in automotive paint shops | |
| Arnaiz et al. | Continuous improvement on information and on-line maintenance technologies for increased cost-effectiveness | |
| Xia et al. | Progressive opportunistic maintenance policies for service-outsourcing network with prognostic updating and dynamical optimization | |
| CN116992346A (en) | Enterprise production data processing system based on artificial intelligence big data analysis | |
| El Hayek et al. | Optimizing life cycle cost of complex machinery with rotable modules using simulation | |
| CN109693459A (en) | Information processing method and device | |
| CN117311295A (en) | Production quality improving method and system based on wireless network equipment | |
| CN112734447A (en) | Grain cloud after-market service cloud platform and method thereof | |
| US20180089637A1 (en) | Framework for industrial asset repair recommendations | |
| CN116339266A (en) | Composite monitoring method and system for pipe production | |
| CN114996948A (en) | Decision-making method for spare part ordering and equipment replacement | |
| Sonar et al. | Role of IoT and AI in Welding Industry 4.0. | |
| Castro et al. | Opportunistic maintenance for heterogeneous complex systems under continuous monitoring | |
| Jonkers et al. | Accommodating Marine New Technology Insertion and Design Changes Through Use of a Management Flight Simulator |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |