CN115718466A - Digital twin workshop fault prediction method based on random forest and analytic hierarchy process - Google Patents
Digital twin workshop fault prediction method based on random forest and analytic hierarchy process Download PDFInfo
- Publication number
- CN115718466A CN115718466A CN202211457614.3A CN202211457614A CN115718466A CN 115718466 A CN115718466 A CN 115718466A CN 202211457614 A CN202211457614 A CN 202211457614A CN 115718466 A CN115718466 A CN 115718466A
- Authority
- CN
- China
- Prior art keywords
- judgment matrix
- production
- predictive maintenance
- workshop
- production workshop
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 95
- 238000007637 random forest analysis Methods 0.000 title claims abstract description 62
- 230000008569 process Effects 0.000 title claims abstract description 42
- 238000004519 manufacturing process Methods 0.000 claims abstract description 192
- 239000011159 matrix material Substances 0.000 claims abstract description 148
- 238000012423 maintenance Methods 0.000 claims abstract description 118
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 24
- 238000012545 processing Methods 0.000 claims abstract description 13
- 230000000694 effects Effects 0.000 claims abstract description 11
- 238000003066 decision tree Methods 0.000 claims description 27
- 238000012163 sequencing technique Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000002452 interceptive effect Effects 0.000 claims description 4
- 230000007246 mechanism Effects 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 description 8
- 238000012549 training Methods 0.000 description 8
- 230000007547 defect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 238000009776 industrial production Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000003754 machining Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 208000033999 Device damage Diseases 0.000 description 1
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001808 coupling effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a digital twin workshop fault prediction method based on random forest and analytic hierarchy process, which relates to the technical field of intelligent manufacturing and electronic information, and comprises the steps of obtaining production element data and real-time production data of a production workshop, constructing a digital twin model of the production workshop according to the obtained production element data, carrying out digital twin processing on the real-time production data to obtain digital twin data of the production workshop, obtaining a predictive maintenance level judgment matrix by using a random forest algorithm and solving the judgment matrix to obtain a judgment matrix characteristic vector, carrying out fault prediction on the production workshop by using the judgment matrix characteristic vector to obtain a fault prediction result of the production workshop, and carrying out control management on production activities of the production workshop according to the fault prediction result of the production workshop; the method combines the random forest and the analytic hierarchy process to predict the faults of the production workshop in real time, has high prediction accuracy, high speed and strong adaptability, and obviously reduces the working difficulty of maintenance personnel.
Description
Technical Field
The invention relates to the technical field of intelligent manufacturing and electronic information, in particular to a digital twin workshop fault prediction method based on random forest and analytic hierarchy process.
Background
The digital twin technology is widely applied to more and more enterprises, particularly to an enterprise which shifts from product sales to product service bundled sales or an enterprise which sells as a service; with the improvement of the enterprise capacity and maturity, more enterprises will use the digital twin technology to optimize the process, determine data driving, revise new products, new services and business modes in the future.
As a basic unit of industrial production, the digitalization and intellectualization level of a workshop have important influence on the quality, safety and efficiency of industrial production. Meanwhile, large industrial equipment running at high speed, mobile personnel and complex operation environment make workshops become high-incidence places for enterprise safety accidents. However, the digitization level of the current workshop safety management and the equipment health condition management still needs to be improved, and no model which is based on real-time data and can comprehensively consider the coupling effect of various risk factors such as equipment, personnel, environment and the like exists at present.
The purpose of utilizing the digital twin technology is to reduce the investment of manpower and material resources and improve the working efficiency. The manual monitoring has a great number of defects, the manual monitoring equipment consumes time and labor, and wrong judgment is easy to occur. By utilizing the digital twin technology, a virtual model can be created for a physical object in a digital mode to simulate the behavior of the physical object in a real environment, the whole process of equipment operation is monitored in real time during fault prediction, the equipment is convenient to carry out real-time fault prediction, and the prediction efficiency and accuracy are improved.
The analytic hierarchy process mainly solves the problem of failure prediction. When the fault is predicted, the acquired data is processed by using an analytic hierarchy process, the analytic hierarchy process decomposes a decision problem into different hierarchical structures according to the sequence of a total target, sub targets of each layer, an evaluation criterion and a specific backup switching scheme, then a method for solving and judging a matrix eigenvector is used, wherein elements in the matrix are data acquired from equipment, the priority weight of each element of each layer to a certain element of the previous layer is obtained, finally, a method of weighting sum is used for hierarchically integrating the final weight of each backup scheme to the total target, and the final weight is the optimal scheme, so that the fault prediction of the equipment is completed.
Because the analytic hierarchy process has the defect of strong subjectivity, when the defect is avoided, a random forest algorithm and the analytic hierarchy process are combined to construct a new prediction module, and the prediction accuracy is improved. The random forest is composed of a plurality of decision trees, each decision tree is different, when the decision trees are constructed, a part of samples are randomly selected from training data, and all features of the data are not used, but part of features are randomly selected for training. The samples and characteristics used by each tree are different, and the training results are different. Due to the randomness of the random forest algorithm, the subjectivity of prediction can be well eliminated, so that the prediction accuracy is greatly improved by combining the random forest algorithm with the analytic hierarchy process.
The current state of the art discloses a digital twinning system for industrial production comprising: the data acquisition module comprises a dynamic data information unit and a static data information unit; a model building module; the model building module comprises a space model unit, a characteristic model unit, a production process model unit and a model integration unit; a digital twinning module; the digital twin module comprises an information extraction unit and a digital twin unit; in the method in the prior art, production scheme optimization, prediction and management are carried out on the production process only through a digital twin system, and no analytic hierarchy process is adopted, so that 'excessive maintenance' is easily caused, namely, parts are disassembled and replaced due to unnecessary disassembly; in addition, the method in the prior art has long equipment shutdown and maintenance time, which causes waste of manpower and material resources; in addition, the current predictive maintenance also has the defect of strong subjectivity, the accuracy of fault prediction is low, and the effect is poor when the complex model fault prediction is performed.
Disclosure of Invention
The invention provides a digital twin workshop fault prediction method based on random forest and analytic hierarchy process, which has the advantages of high accuracy, high training speed, strong adaptability and the like and can be better suitable for workshop fault prediction.
In order to solve the technical problems, the technical scheme of the invention is as follows:
a digital twin workshop fault prediction method based on random forest and analytic hierarchy process comprises the following steps:
s1: acquiring production element data and real-time production data of a production workshop;
s2: constructing a digital twin model of the production workshop according to the production element data of the production workshop;
s3: carrying out digital twinning processing on the real-time production data by using a digital twinning model of the production workshop to obtain digital twinning data of the production workshop;
s4: inputting digital twin data of a production workshop into a constructed predictive maintenance hierarchical structure model, obtaining a predictive maintenance hierarchical judgment matrix by using a random forest algorithm, solving the predictive maintenance hierarchical judgment matrix, and obtaining a judgment matrix characteristic vector;
s5: carrying out fault prediction on the production workshop by using the judgment matrix eigenvector to obtain a fault prediction result of the production workshop;
s6: and controlling and managing the production activities of the production workshop according to the fault prediction result of the production workshop.
Preferably, in step S1, the production element data of the production plant includes: device entity element data and information element data;
the device entity element data includes: the geometric dimension, the physical mechanism, the behavior characteristic and the position information of each device in the production workshop and the interactive relation among the devices in the production workshop;
the information element data includes: information of states of equipment and personnel in a production workshop, task order processing information and scheduling decision information.
Preferably, after step S5, the method further includes:
and uploading the fault prediction result of the production workshop to a database by the predictive maintenance hierarchical structure model, and interacting the digital twin model of the production workshop with the database to obtain the fault prediction result and display the predicted fault position information.
Preferably, in step S4, the constructed predictive maintenance hierarchical structure model specifically includes:
the predictive maintenance hierarchy model comprises a target layer, a criteria layer, and a measure layer;
the target layer represents target equipment predictive maintenance, denoted as A;
the criterion layer comprises a plurality of criterion layer elements marked as B k Representing a k-th criterion layer element;
the measure layer comprises a number of measure layer elements denoted C n And represents the nth measure layer element.
Preferably, in the step S4, a specific method for obtaining the predictive maintenance level judgment matrix by using the random forest algorithm includes:
the random forest algorithm comprises a plurality of decision trees;
taking digital twin data of a production workshop as an original data set;
s4.1.1: randomly sampling the original data set with the replacement for multiple times to obtain a plurality of sub data sets, wherein the number of elements of each sub data set is consistent with that of the original data set;
s4.1.2: randomly selecting a plurality of characteristics from all preset characteristics aiming at each subdata set, wherein each characteristic is used as an input characteristic of a decision tree to obtain a plurality of decision trees;
s4.1.3: setting the decision tree with large information gain value on the top of the decision tree with small information gain value to form a random forest;
s4.1.4: and obtaining a predictive maintenance level judgment matrix according to the output result of the random forest.
Preferably, the predictive maintenance hierarchy decision matrix in step S4.1.4 is specifically:
for each criterion layer element, a predictive maintenance level judgment matrix is provided, and the predictive maintenance level judgment matrix corresponding to the k-th criterion layer element is as follows:
wherein, C ij Representing the importance degree of the ith measure layer element to the kth criterion layer element compared with the jth measure layer element;
obtaining different C according to output result of random forest ij And (3) to form different predictive maintenance level decision matrices.
Preferably, in step S4, the specific method for solving the predictive maintenance level judgment matrix to obtain the characteristic vector of the judgment matrix is as follows:
the method for solving the predictive maintenance level judgment matrix corresponding to the kth criterion layer element comprises the following steps:
s4.2.1: squaring each element in the predictive maintenance level judgment matrix corresponding to the kth criterion layer element to obtain a new judgment matrix C 2 (B k )：
Wherein i and j satisfy 1-n, and 1-n;
s4.2.2: calculating a new decision matrix C 2 (B k ) Sum of all elements in each row:
wherein, sum i Represents a new decision matrix C 2 (B k ) The sum of all elements in the ith row;
s4.2.3: calculating a new decision matrix C 2 (B k ) Sum of all elements in (1):
wherein sum represents a new decision matrix C 2 (B k ) The sum of all elements in (1);
s4.2.4: calculating a new decision matrix C 2 (B k ) Normalized vector of sum of all elements per row:
wherein, W i (q) New decision matrix C representing the q-th calculation 2 (B k ) The normalized vector of the sum of all elements in the ith row;
s4.2.5: updating the digital twin data of the production workshop, and executing the steps S4.2.1-S4.2.4 again to obtain a new judgment matrix C of a new round 2 (B k ) And calculating the error value of the normalized vector obtained twice in succession according to the normalized vector of all element sums in each row:
where T represents an error value of a normalized vector obtained two consecutive times.
S4.2.6: comparing an error value T of the normalization vector obtained twice continuously with a preset threshold value; if the error value T is smaller than the preset threshold value, taking the normalized vector at the moment as the characteristic vector of the judgment matrix of the kth criterion layer element, and recording the characteristic vector as the characteristic vector
Otherwise, step S4.2.5 is executed until the error value T is smaller than the preset threshold.
Preferably, in step S5, the fault prediction is performed on the production workshop by using the judgment matrix eigenvector, so as to obtain a fault prediction result of the production workshop, and the specific method is as follows:
s5.1: solve eachA predictive maintenance level judgment matrix corresponding to the elements of the criterion layer, and a judgment matrix characteristic vector of the measure layer relative to each element of the criterion layer is obtained and recorded as
S5.2: obtaining and solving a predictive maintenance level judgment matrix of the criterion layer relative to the target layer, obtaining a judgment matrix characteristic vector of the criterion layer relative to the target layer, and recording the judgment matrix characteristic vector as W B-A ；
S5.3: and obtaining a predictive maintenance final priority sequence according to the obtained judgment matrix characteristic vector, and taking the predictive maintenance final priority sequence as a fault prediction result of the production workshop.
Preferably, in step S5.2, the predictive maintenance hierarchy decision matrix of the criterion layer relative to the target layer specifically is:
wherein, B ab Representing the degree of importance of the a-th criteria layer element to the target layer compared to the b-th criteria layer element.
Preferably, in the step S5.3, the predictive maintenance final priority ranking is obtained according to the obtained feature vector of the judgment matrix, and the specific method is as follows:
obtaining a feature vector of the measure layer relative to the target layer according to the following formula:
wherein, W C-A A feature vector representing the measure layer relative to the target layer;
according to the feature vector W of the measure layer relative to the target layer C-A And obtaining the importance degree of each measure layer element relative to the target layer, and sequencing all measure layer elements according to the importance degree to obtain the final priority sequencing of the predictive maintenance.
Compared with the prior art, the technical scheme of the invention has the beneficial effects that:
the invention provides a digital twin workshop fault prediction method based on random forests and an analytic hierarchy process, which comprises the steps of obtaining production element data and real-time production data of a production workshop, constructing a digital twin model of the production workshop according to the obtained production element data, carrying out digital twin processing on the real-time production data by using the digital twin model of the production workshop to obtain the digital twin data of the production workshop, inputting the digital twin data of the production workshop into the constructed predictive maintenance hierarchical structure model, obtaining a predictive maintenance hierarchical judgment matrix by using a random forest algorithm, solving the predictive maintenance hierarchical judgment matrix to obtain a judgment matrix characteristic vector, carrying out fault prediction on the production workshop by using the judgment matrix characteristic vector to obtain a fault prediction result of the production workshop, and finally carrying out control management on production activities of the production workshop according to the fault prediction result of the production workshop;
under the addition of a visual and real-time digital twin technology, the method not only can carry out real-time observation on the operation condition of workshop equipment in real time, but also can directly observe the position of the fault when the fault occurs, thereby saving the time cost of equipment fault retrieval of maintenance personnel, facilitating the maintenance and simultaneously reducing the working difficulty of the maintenance personnel; in addition, a random forest algorithm and an analytic hierarchy process are introduced to predict faults of the production workshop, an objective and effective judgment matrix can be obtained, the prediction result has confidence, and the method has the advantages of high accuracy, high training speed and strong adaptability.
Drawings
Fig. 1 is a flowchart of a digital twin plant fault prediction method based on random forest and analytic hierarchy process provided in embodiment 1.
FIG. 2 is a flowchart of the method for obtaining the prediction result by using the random forest and the analytic hierarchy process provided in example 2.
Fig. 3 is a schematic diagram of a machine temperature decision tree provided in embodiment 2.
Fig. 4 is a schematic diagram of a tool wear decision tree provided in example 2.
Fig. 5 is a schematic diagram of the random forest provided in example 2.
Fig. 6 is a structural diagram of a digital twin plant fault prediction system based on random forest and analytic hierarchy process according to embodiment 3.
Detailed Description
The drawings are for illustrative purposes only and are not to be construed as limiting the patent;
for the purpose of better illustrating the embodiments, certain features of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product;
it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The technical solution of the present invention is further described below with reference to the accompanying drawings and examples.
Example 1
As shown in fig. 1, the present embodiment provides a digital twin plant fault prediction method based on random forest and analytic hierarchy process, including the following steps:
s1: acquiring production element data and real-time production data of a production workshop;
s2: constructing a digital twin model of the production workshop according to the production element data of the production workshop;
s3: carrying out digital twinning processing on the real-time production data by using a digital twinning model of the production workshop to obtain digital twinning data of the production workshop;
s4: inputting digital twin data of a production workshop into a constructed predictive maintenance hierarchical structure model, obtaining a predictive maintenance hierarchical judgment matrix by using a random forest algorithm, solving the predictive maintenance hierarchical judgment matrix, and obtaining a judgment matrix characteristic vector;
s5: carrying out fault prediction on the production workshop by using the judgment matrix eigenvector to obtain a fault prediction result of the production workshop;
s6: and controlling and managing the production activities of the production workshop according to the fault prediction result of the production workshop.
In the specific implementation process, firstly, production element data and real-time production data of a production workshop are obtained, a digital twin model of the production workshop is built according to the obtained production element data, the digital twin model of the production workshop is utilized, digital twin processing is carried out on the real-time production data, the digital twin data of the production workshop is obtained, then the digital twin data of the production workshop is input into a built predictive maintenance hierarchical structure model, a predictive maintenance hierarchical judgment matrix is obtained by utilizing a random forest algorithm, the predictive maintenance hierarchical judgment matrix is solved, a judgment matrix characteristic vector is obtained, fault prediction is carried out on the production workshop by utilizing the judgment matrix characteristic vector, a fault prediction result of the production workshop is obtained, and finally, the production activities of the production workshop are controlled and managed according to the fault prediction result of the production workshop;
under the addition of a visual and real-time digital twin technology, the method not only can carry out real-time observation on the operation condition of workshop equipment in real time, but also can directly observe the position of the fault when the fault occurs, thereby saving the time cost of equipment fault retrieval of maintenance personnel, facilitating the maintenance and simultaneously reducing the working difficulty of the maintenance personnel; in addition, a random forest algorithm and an analytic hierarchy process are combined to predict the faults of the production workshop, an objective and effective judgment matrix can be obtained, and the prediction result has confidence, so that the method has the advantages of high accuracy, high training speed and strong adaptability.
Example 2
The embodiment provides a digital twin workshop fault prediction method based on a random forest and an analytic hierarchy process, which comprises the following steps of:
s1: acquiring production element data and real-time production data of a production workshop;
s2: constructing a digital twin model of the production workshop according to the production element data of the production workshop;
s3: carrying out digital twinning processing on the real-time production data by using a digital twinning model of the production workshop to obtain digital twinning data of the production workshop;
s4: as shown in fig. 2, inputting digital twin data of a production workshop into a constructed predictive maintenance hierarchical structure model, obtaining a predictive maintenance hierarchical judgment matrix by using a random forest algorithm, and solving the predictive maintenance hierarchical judgment matrix to obtain a judgment matrix eigenvector;
s5: performing fault prediction on the production workshop by using the judgment matrix eigenvector to obtain a fault prediction result of the production workshop, uploading the fault prediction result of the production workshop to a database by using a predictive maintenance hierarchical structure model, and interacting a digital twin model of the production workshop with the database to obtain the fault prediction result and display the predicted fault position information;
s6: and controlling and managing the production activities of the production workshop according to the fault prediction result of the production workshop.
In the step S1, the production element data of the production shop includes: device entity element data and information element data;
the device entity element data includes: the geometric dimension, the physical mechanism, the behavior characteristic and the position information of each device in the production workshop and the interactive relation among the devices in the production workshop;
the information element data includes: the information of the states of all equipment and personnel in the production workshop, the processing information of the task order and the scheduling decision information.
In step S4, the predictive maintenance hierarchical structure model is specifically constructed as follows:
the predictive maintenance hierarchy model comprises a target layer, a criteria layer, and a measure layer;
the target layer represents target equipment predictive maintenance, denoted as A;
the criterion layer comprises a plurality of criterion layer elements marked as B k Representing a k-th criterion layer element;
the measure layer comprises a plurality of measure layer elements marked as C n And represents the nth measure layer element.
In the step S4, a specific method for obtaining the predictive maintenance level judgment matrix by using the random forest algorithm is as follows:
the random forest algorithm comprises a plurality of decision trees;
taking digital twin data of a production workshop as an original data set;
s4.1.1: performing replaced random sampling on the original data set for multiple times to obtain a plurality of sub data sets, wherein the number of elements of each sub data set is consistent with that of the original data set;
s4.1.2: randomly selecting a plurality of characteristics from all preset characteristics aiming at each subdata set, wherein each characteristic is used as an input characteristic of a decision tree to obtain a plurality of decision trees;
s4.1.3: setting the decision tree with large information gain value at the top of the decision tree with small information gain value to form a random forest;
s4.1.4: and obtaining a predictive maintenance level judgment matrix according to the output result of the random forest.
The predictive maintenance level decision matrix in step S4.1.4 is specifically:
for each criterion layer element, a predictive maintenance level judgment matrix is provided, and the predictive maintenance level judgment matrix corresponding to the kth criterion layer element is as follows:
wherein, C ij Representing the importance degree of the ith measure layer element to the kth criterion layer element compared with the jth measure layer element;
obtaining different C according to output result of random forest ij And (3) to form different predictive maintenance level decision matrices.
In step S4, the specific method for solving the predictive maintenance level judgment matrix to obtain the characteristic vector of the judgment matrix is as follows:
the method for solving the predictive maintenance level judgment matrix corresponding to the kth criterion layer element comprises the following steps:
s4.2.1: squaring each element in the predictive maintenance level judgment matrix corresponding to the kth criterion layer element to obtain a new judgment matrix C 2 (B k )：
Wherein i and j satisfy 1 ≤ i ≤ n, and 1 ≤ j ≤ n;
s4.2.2: calculating a new decision matrix C 2 (B k ) Sum of all elements in each row:
wherein, sum i Represents a new decision matrix C 2 (B k ) The sum of all elements in the ith row;
s4.2.3: calculating a new decision matrix C 2 (B k ) Sum of all elements in (1):
wherein sum represents a new decision matrix C 2 (B k ) The sum of all elements in (1);
s4.2.4: calculating a new decision matrix C 2 (B k ) Normalized vector of sum of all elements per row:
wherein, W i (q) New decision matrix C representing the q-th calculation 2 (B k ) The normalized vector of the sum of all elements in the ith row;
s4.2.5: updating the digital twin data of the production workshop, and executing the steps S4.2.1-S4.2.4 again to obtain a new judgment matrix C of a new round 2 (B k ) And calculating the error value of the normalized vector obtained twice in succession according to the normalized vector of all element sums in each row:
where T represents an error value of a normalized vector obtained two consecutive times.
S4.2.6: comparing an error value T of the normalization vector obtained twice continuously with a preset threshold value; if the error value T is smaller than the preset threshold value, taking the normalized vector at the moment as the characteristic vector of the judgment matrix of the kth criterion layer element, and recording the characteristic vector as the characteristic vector
Otherwise, step S4.2.5 is executed until the error value T is smaller than the preset threshold.
In the step S5, the fault prediction is performed on the production workshop by using the judgment matrix eigenvector to obtain a fault prediction result of the production workshop, and the specific method is as follows:
s5.1: solving the predictive maintenance level judgment matrix corresponding to each criterion layer element, obtaining the characteristic vector of the judgment matrix of the measure layer relative to each criterion layer element, and recording the characteristic vector as
S5.2: obtaining and solving a predictive maintenance level judgment matrix of the criterion layer relative to the target layer, obtaining a judgment matrix characteristic vector of the criterion layer relative to the target layer, and recording the judgment matrix characteristic vector as W B-A ；
S5.3: and obtaining a predictive maintenance final priority sequence according to the obtained judgment matrix characteristic vector, and taking the predictive maintenance final priority sequence as a fault prediction result of the production workshop.
In step S5.2, the predictive maintenance hierarchy decision matrix of the criterion layer with respect to the target layer is specifically:
wherein, B ab Representing the aim of the a-th criterion layer element compared with the b-th criterion layer elementThe importance of the label layer.
In the step S5.3, the predictive maintenance final priority ranking is obtained according to the obtained feature vector of the decision matrix, and the specific method is as follows:
obtaining a feature vector of the measure layer relative to the target layer according to the following formula:
wherein, W C-A A feature vector representing the measure layer relative to the target layer;
according to the feature vector W of the measure layer relative to the target layer C-A And obtaining the importance degree of each measure layer element relative to the target layer, and sequencing all measure layer elements according to the importance degree to obtain the final priority sequencing of the predictive maintenance.
In the specific implementation process, the embodiment takes a numerical control machine tool in a production workshop as an example to illustrate the specific implementation process;
firstly, acquiring production element data and real-time production data of the numerical control machine tool, wherein the production element data of the numerical control machine tool comprises the following steps: machine tool entity element data and machine tool information element data; the machine tool entity element data includes: the geometric dimension, physical mechanism, behavior characteristic, position information of the machine tool, the interactive relation between the machine tools and other parameter information; the information element data of the machine tool comprises state information of the machine tool and machine tool task decision scheduling information;
constructing a digital twin model of the numerical control machine tool according to production element data of the numerical control machine tool;
then, carrying out digital twinning processing on the real-time production data of the numerical control machine tool by using a digital twinning model of the numerical control machine tool to obtain digital twinning data of the numerical control machine tool, wherein the digital twinning data of the numerical control machine tool comprises the temperature of the machine tool and the abrasion condition of a cutter;
inputting numerical twin data of a numerical control machine tool in a production workshop into a constructed predictive maintenance hierarchical structure model, wherein the predictive maintenance hierarchical structure model specifically comprises the following steps:
the predictive maintenance hierarchy model comprises a target layer, a criteria layer, and a measure layer;
the target layer represents target equipment predictive maintenance, denoted as A;
the criterion layer comprises a plurality of criterion layer elements marked as B k Representing a k-th criterion layer element;
in the present embodiment, the criterion layer includes 4 criterion layer elements, wherein the first criterion layer element B 1 Second rule layer element B indicating maintenance of machining accuracy 2 Third rule layer element B representing saving of operation cost 3 Fourth criterion layer element B, representing reduced device damage 4 Indicating avoidance of casualties;
the measure layer comprises a number of measure layer elements denoted C n Denotes an nth measure layer element;
in the present embodiment, the measure layer includes 5 criterion layer elements, wherein the first measure layer element C 1 Indicating a feed system, second measure layer element C 2 Indicating the spindle system, third measure layer element C 3 Indicating the tool machining System, fourth measure layer element C 4 Representing CNC control System, fifth action layer element C 5 Indicating an automatic tool changing system;
a predictive maintenance level judgment matrix is obtained by using a random forest algorithm, and the specific method comprises the following steps:
the random forest algorithm comprises a plurality of decision trees;
taking digital twin data of a numerical control machine tool in a production workshop as an original data set;
s4.1.1: performing replaced random sampling on the original data set for multiple times to obtain a plurality of sub data sets, wherein the number of elements of each sub data set is consistent with that of the original data set;
s4.1.2: randomly selecting a plurality of characteristics from all preset characteristics aiming at each subdata set, wherein each characteristic is used as an input characteristic of a decision tree to obtain a plurality of decision trees;
in the embodiment, the preset characteristics of the temperature of the machine tool comprise abnormal temperature and normal temperature, and the preset characteristics of the tool wear condition comprise normal tool, slight tool wear and excessive tool wear;
as shown in fig. 3 and 4, a machine temperature decision tree and a tool wear decision tree are shown respectively;
s4.1.3: as shown in fig. 5, the decision tree with a large information gain value is set on the top of the decision tree with a small information gain value to form a random forest, in this embodiment, the information gain value of the machine tool temperature is 0, and the information gain value of the tool wear condition is 0.92;
s4.1.4: obtaining a predictive maintenance level judgment matrix according to the output result of the random forest, which specifically comprises the following steps:
for each criterion layer element, a predictive maintenance level judgment matrix is provided, and the predictive maintenance level judgment matrix corresponding to the k-th criterion layer element is as follows:
wherein, C ij Representing the importance degree of the ith measure layer element to the kth criterion layer element compared with the jth measure layer element;
C ij the value of (b) satisfies 1. Ltoreq. C ij ≤9，C ij The greater the value of (a), the higher the importance of the ith measure layer element to the kth criterion layer element compared to the jth measure layer element;
obtaining different C according to output result of random forest ij Forming different predictive maintenance level judgment matrixes;
solving the predictive maintenance level judgment matrix to obtain the characteristic vector of the judgment matrix, wherein the specific method comprises the following steps:
the method for solving the predictive maintenance level judgment matrix corresponding to the kth criterion layer element comprises the following steps:
s4.2.1: squaring each element in the predictive maintenance level judgment matrix corresponding to the kth criterion layer element to obtain a new judgment matrix C 2 (B k )：
Wherein i and j satisfy 1 ≤ i ≤ 5,1 ≤ j ≤ 5;
s4.2.2: calculating a new decision matrix C 2 (B k ) Sum of all elements in each row:
wherein, sum i Represents a new decision matrix C 2 (B k ) The sum of all elements in the ith row;
s4.2.3: calculating a new decision matrix C 2 (B k ) Sum of all elements in (1):
wherein sum represents a new decision matrix C 2 (B k ) The sum of all elements in (1);
s4.2.4: calculating a new decision matrix C 2 (B k ) Normalized vector of sum of all elements per row:
wherein, W i (q) New decision matrix C representing the q-th calculation 2 (B k ) The normalized vector of the sum of all elements in the ith row;
s4.2.5: updating the digital twin data of the production workshop, and executing the steps S4.2.1-S4.2.4 again to obtain a new judgment matrix C of a new round 2 (B k ) And calculating the error value of the normalized vector obtained twice in succession according to the normalized vector of all element sums in each row:
where T represents an error value of a normalized vector obtained two consecutive times.
S4.2.6: comparing an error value T of the normalization vector obtained twice continuously with a preset threshold value; if the error value T is smaller than the preset threshold value, taking the normalized vector at the moment as the characteristic vector of the judgment matrix of the kth criterion layer element, and recording the characteristic vector as the characteristic vector
Otherwise, executing step S4.2.5 until the error value T is smaller than a preset threshold, in this embodiment, the preset threshold is a constant in the debugging process of the numerical control machine;
and predicting the fault of the production workshop by utilizing the characteristic vector of the judgment matrix to obtain a fault prediction result of the production workshop, wherein the specific method comprises the following steps of:
s5.1: solving the predictive maintenance level judgment matrix corresponding to each criterion layer element, obtaining the characteristic vector of the judgment matrix of the measure layer relative to each criterion layer element, and recording the characteristic vector as
S5.2: the method for obtaining the predictive maintenance level judgment matrix of the criterion layer relative to the target layer specifically comprises the following steps:
wherein, B ab Representing the degree of importance of the a-th criterion layer element to the target layer compared to the b-th criterion layer element;
solving the predictive maintenance level judgment matrix of the criterion layer relative to the target layer, acquiring the characteristic vector of the judgment matrix of the criterion layer relative to the target layer, and recording the characteristic vector as W B-A ；
S5.3: obtaining a predictive maintenance final priority ranking according to the obtained judgment matrix characteristic vector, specifically:
obtaining a feature vector of the measure layer relative to the target layer according to the following formula:
wherein, W C-A A feature vector representing the measure layer relative to the target layer;
according to the feature vector W of the measure layer relative to the target layer C-A Obtaining the importance degree of each measure layer element relative to the target layer, and sequencing all measure layer elements according to the importance degree to obtain the final priority sequencing of predictive maintenance;
the predictive maintenance final priority ranking is used as a fault prediction result of the production workshop;
finally, the predictive maintenance hierarchical structure model uploads the fault prediction result of the production workshop to the database, the digital twin model of the production workshop interacts with the database to obtain the fault prediction result and display the predicted fault position information;
controlling and managing the production activities of the production workshop according to the fault prediction result of the production workshop;
under the addition of a visual and real-time digital twin technology, the method not only can carry out real-time observation on the operation condition of workshop equipment in real time, but also can directly observe the position of the fault when the fault occurs, thereby saving the time cost of equipment fault retrieval of maintenance personnel, facilitating the maintenance and simultaneously reducing the working difficulty of the maintenance personnel; in addition, a random forest algorithm and an analytic hierarchy process are introduced to predict faults of the production workshop, an objective and effective judgment matrix can be obtained, the prediction result has confidence, and the method has the advantages of high accuracy, high training speed and strong adaptability.
Example 3
As shown in fig. 6, the present embodiment provides a digital twin plant fault prediction system based on random forest and analytic hierarchy process, including:
the data acquisition unit 301: the system is used for acquiring production element data and real-time production data of a production workshop;
digital twin model construction unit 302: a digital twin model for constructing a production plant from production element data of the production plant;
the digital twin data acquisition unit 303: carrying out digital twinning processing on the real-time production data by using a digital twinning model of the production workshop to obtain digital twinning data of the production workshop;
determination matrix calculation unit 304: the system comprises a predictive maintenance level structure model, a random forest algorithm, a judgment matrix and a judgment matrix characteristic vector, wherein the predictive maintenance level structure model is constructed by inputting digital twin data of a production workshop;
failure prediction unit 305: the system is used for predicting the faults of the production workshop by utilizing the judgment matrix characteristic vector to obtain the fault prediction result of the production workshop;
prediction result output unit 306: and the system is used for controlling and managing the production activities of the production workshop according to the fault prediction result of the production workshop.
In a specific implementation process, firstly, a data acquisition unit 301 acquires production element data and real-time production data of a production workshop, a digital twin model construction unit 302 constructs a digital twin model of the production workshop according to the acquired production element data, a digital twin data acquisition unit 303 performs digital twin processing on the real-time production data by using the digital twin model of the production workshop to acquire digital twin data of the production workshop, then a judgment matrix calculation unit 304 inputs the digital twin data of the production workshop into the constructed predictive maintenance hierarchical structure model, a random forest algorithm is used to acquire a predictive maintenance hierarchical judgment matrix, the predictive maintenance hierarchical judgment matrix is solved to acquire a judgment matrix characteristic vector, a fault prediction unit 305 performs fault prediction on the production workshop by using the judgment matrix characteristic vector to acquire a fault prediction result of the production workshop, and finally a prediction result output unit 306 performs control management on production activities of the production workshop according to the fault prediction result of the production workshop;
under the addition of a visual and real-time digital twin technology, the system not only can carry out real-time observation on the operation condition of workshop equipment in real time, but also can directly observe the position of the fault when the fault occurs, thereby saving the time cost of equipment fault retrieval of maintainers, being convenient for maintenance and simultaneously reducing the working difficulty of the maintainers; in addition, a random forest algorithm and an analytic hierarchy process are introduced to predict faults of the production workshop, an objective and effective judgment matrix can be obtained, the prediction result has confidence, and the system has the advantages of high accuracy, high training speed and strong adaptability.
The same or similar reference numerals correspond to the same or similar parts;
the terms describing positional relationships in the drawings are for illustrative purposes only and are not to be construed as limiting the patent;
it should be understood that the above-described embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the claims of the present invention.
Claims (10)
1. A digital twin workshop fault prediction method based on random forest and analytic hierarchy process is characterized by comprising the following steps:
s1: acquiring production element data and real-time production data of a production workshop;
s2: constructing a digital twin model of the production workshop according to the production element data of the production workshop;
s3: carrying out digital twinning processing on the real-time production data by using a digital twinning model of the production workshop to obtain digital twinning data of the production workshop;
s4: inputting digital twin data of a production workshop into a constructed predictive maintenance hierarchical structure model, obtaining a predictive maintenance hierarchical judgment matrix by using a random forest algorithm, solving the predictive maintenance hierarchical judgment matrix, and obtaining a judgment matrix characteristic vector;
s5: carrying out fault prediction on the production workshop by using the judgment matrix eigenvector to obtain a fault prediction result of the production workshop;
s6: and controlling and managing the production activities of the production workshop according to the fault prediction result of the production workshop.
2. The method for predicting the fault of the digital twin workshop based on the random forest and the analytic hierarchy process as claimed in claim 1, wherein in the step S1, the production element data of the production workshop comprises: device entity element data and information element data;
the device entity element data includes: the geometrical size, the physical mechanism, the behavior characteristic and the position information of each device in the production workshop and the interactive relation among the devices in the production workshop;
the information element data includes: information of states of equipment and personnel in a production workshop, task order processing information and scheduling decision information.
3. The method for predicting the fault of the digital twin workshop based on the random forest and the analytic hierarchy process as claimed in claim 1, wherein the step S5 is followed by further comprising:
and uploading the fault prediction result of the production workshop to a database by the predictive maintenance hierarchical structure model, and interacting the digital twin model of the production workshop with the database to obtain the fault prediction result and display the predicted fault position information.
4. The method for predicting the faults of the digital twin workshop based on the random forest and the analytic hierarchy process as claimed in claim 1, wherein the predictive maintenance hierarchical structure model constructed in the step S4 is specifically:
the predictive maintenance hierarchical model comprises a target layer, a criteria layer, and a measures layer;
the target layer represents target equipment predictive maintenance, denoted as A;
the criterion layer comprises a plurality of criterion layer elements marked as B k Representing a k-th criterion layer element;
the measure layer comprises a number of measure layer elements denoted C n And represents the nth measure layer element.
5. The method for predicting faults of the digital twin workshop based on the random forest and the analytic hierarchy process as claimed in claim 4, wherein in the step S4, the specific method for obtaining the predictive maintenance level judgment matrix by using the random forest algorithm is as follows:
the random forest algorithm comprises a plurality of decision trees;
taking digital twin data of a production workshop as an original data set;
s4.1.1: performing replaced random sampling on the original data set for multiple times to obtain a plurality of sub data sets, wherein the number of elements of each sub data set is consistent with that of the original data set;
s4.1.2: randomly selecting a plurality of characteristics from all preset characteristics aiming at each subdata set, wherein each characteristic is used as an input characteristic of a decision tree to obtain a plurality of decision trees;
s4.1.3: setting the decision tree with large information gain value at the top of the decision tree with small information gain value to form a random forest;
s4.1.4: and obtaining a predictive maintenance level judgment matrix according to the output result of the random forest.
6. The method for predicting the faults of the digital twin workshop based on the random forest and the analytic hierarchy process as claimed in claim 5, wherein the predictive maintenance level judgment matrix in the step S4.1.4 is specifically:
for each criterion layer element, a predictive maintenance level judgment matrix is provided, and the predictive maintenance level judgment matrix corresponding to the k-th criterion layer element is as follows:
wherein, C ij Representing the importance degree of the ith measure layer element to the kth criterion layer element compared with the jth measure layer element;
obtaining different C according to output result of random forest ij The values of (c) constitute different predictive maintenance level decision matrices.
7. The method for predicting the faults of the digital twin workshop based on the random forest and the analytic hierarchy process as claimed in claim 6, wherein in the step S4, the specific method for solving the predictive maintenance level judgment matrix to obtain the characteristic vector of the judgment matrix is as follows:
the method for solving the predictive maintenance level judgment matrix corresponding to the kth criterion layer element comprises the following steps:
s4.2.1: squaring each element in the predictive maintenance level judgment matrix corresponding to the kth criterion layer element to obtain a new judgment matrix C 2 (B k )：
Wherein i and j satisfy 1 ≤ i ≤ n, and 1 ≤ j ≤ n;
s4.2.2: calculating a new decision matrix C 2 (B k ) Sum of all elements in each row:
wherein, sum i Represents a new decision matrix C 2 (B k ) The sum of all elements in the ith row;
s4.2.3: calculating a new decision matrix C 2 (B k ) Sum of all elements in (1):
wherein sum represents a new judgment matrix C 2 (B k ) The sum of all elements in (1);
s4.2.4: calculating a new decision matrix C 2 (B k ) Normalized vector of sum of all elements per row:
wherein, W i (q) New decision matrix C representing the q-th calculation 2 (B k ) The normalized vector of the sum of all elements in the ith row;
s4.2.5: updating the digital twin data of the production workshop, and executing the steps S4.2.1-S4.2.4 again to obtain a new judgment matrix C of a new round 2 (B k ) And calculating the error value of the normalized vector obtained twice in succession according to the normalized vector of all element sums in each row:
where T represents an error value of a normalized vector obtained two consecutive times.
S4.2.6: comparing an error value T of the normalization vector obtained twice continuously with a preset threshold value; if the error value T is smaller than the preset threshold value, taking the normalized vector at the moment as the characteristic vector of the judgment matrix of the kth criterion layer element, and recording the characteristic vector as the characteristic vector
Otherwise, step S4.2.5 is executed until the error value T is smaller than the preset threshold.
8. The method for predicting the faults of the digital twin workshop based on the random forest and the analytic hierarchy process as claimed in claim 7, wherein in the step S5, the fault prediction of the production workshop is performed by using the judgment matrix eigenvector to obtain the fault prediction result of the production workshop, and the specific method comprises the following steps:
s5.1: solving the predictive maintenance level judgment matrix corresponding to each criterion layer element, obtaining the characteristic vector of the judgment matrix of the measure layer relative to each criterion layer element, and recording the characteristic vector as
S5.2: obtaining and solving a predictive maintenance level judgment matrix of the criterion layer relative to the target layer, obtaining a judgment matrix characteristic vector of the criterion layer relative to the target layer, and recording the judgment matrix characteristic vector as W B-A ；
S5.3: and obtaining a predictive maintenance final priority sequence according to the obtained judgment matrix characteristic vector, and taking the predictive maintenance final priority sequence as a fault prediction result of the production workshop.
9. The method for predicting the faults of the digital twin workshop based on the random forest and the analytic hierarchy process as claimed in claim 8, wherein in the step S5.2, the predictive maintenance level judgment matrix of the criterion layer relative to the target layer is specifically:
wherein, B ab Representing the degree of importance of the a-th-criteria layer element to the target layer as compared to the b-th-criteria layer element.
10. The method for predicting faults of the digital twin workshop based on the random forest and the analytic hierarchy process as claimed in claim 8, wherein in the step S5.3, the predictive maintenance final priority ranking is obtained according to the obtained judgment matrix feature vector, and the specific method is as follows:
obtaining a feature vector of the measure layer relative to the target layer according to the following formula:
wherein, W C-A A feature vector representing the measure layer relative to the target layer;
according to the feature vector W of the measure layer relative to the target layer C-A And obtaining the importance degree of each measure layer element relative to the target layer, and sequencing all measure layer elements according to the importance degree to obtain the final priority sequencing of the predictive maintenance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211457614.3A CN115718466B (en) | 2022-11-21 | 2022-11-21 | Digital twin workshop fault prediction method based on random forest and analytic hierarchy process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211457614.3A CN115718466B (en) | 2022-11-21 | 2022-11-21 | Digital twin workshop fault prediction method based on random forest and analytic hierarchy process |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115718466A true CN115718466A (en) | 2023-02-28 |
| CN115718466B CN115718466B (en) | 2024-05-14 |
Family
ID=85255729
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211457614.3A Active CN115718466B (en) | 2022-11-21 | 2022-11-21 | Digital twin workshop fault prediction method based on random forest and analytic hierarchy process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115718466B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116224905A (en) * | 2023-03-02 | 2023-06-06 | 广东工业大学 | Machine tool thermal error prediction method and system based on joint distribution self-adaption |
| CN116861204A (en) * | 2023-09-05 | 2023-10-10 | 山东山森数控技术有限公司 | Intelligent manufacturing equipment data management system based on digital twinning |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114311609A (en) * | 2022-01-17 | 2022-04-12 | 安徽理工大学 | Extruding machine fault diagnosis system based on digital twinning |
| CN114519302A (en) * | 2022-01-25 | 2022-05-20 | 江苏科技大学 | Road traffic situation simulation method based on digital twin |
| CN114563988A (en) * | 2022-01-26 | 2022-05-31 | 浙江中控信息产业股份有限公司 | Water plant intelligent PAC adding method and system based on random forest algorithm |
| CN115081508A (en) * | 2022-04-26 | 2022-09-20 | 同济大学 | Traffic running risk parallel simulation system based on traffic digital twins |
| CN115329493A (en) * | 2022-08-17 | 2022-11-11 | 兰州理工大学 | Impeller mechanical fault detection method based on centrifugal pump digital twin model |
-
2022
- 2022-11-21 CN CN202211457614.3A patent/CN115718466B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114311609A (en) * | 2022-01-17 | 2022-04-12 | 安徽理工大学 | Extruding machine fault diagnosis system based on digital twinning |
| CN114519302A (en) * | 2022-01-25 | 2022-05-20 | 江苏科技大学 | Road traffic situation simulation method based on digital twin |
| CN114563988A (en) * | 2022-01-26 | 2022-05-31 | 浙江中控信息产业股份有限公司 | Water plant intelligent PAC adding method and system based on random forest algorithm |
| CN115081508A (en) * | 2022-04-26 | 2022-09-20 | 同济大学 | Traffic running risk parallel simulation system based on traffic digital twins |
| CN115329493A (en) * | 2022-08-17 | 2022-11-11 | 兰州理工大学 | Impeller mechanical fault detection method based on centrifugal pump digital twin model |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116224905A (en) * | 2023-03-02 | 2023-06-06 | 广东工业大学 | Machine tool thermal error prediction method and system based on joint distribution self-adaption |
| CN116224905B (en) * | 2023-03-02 | 2023-10-20 | 广东工业大学 | Machine tool thermal error prediction method and system based on joint distribution self-adaption |
| CN116861204A (en) * | 2023-09-05 | 2023-10-10 | 山东山森数控技术有限公司 | Intelligent manufacturing equipment data management system based on digital twinning |
| CN116861204B (en) * | 2023-09-05 | 2023-12-08 | 山东山森数控技术有限公司 | Intelligent manufacturing equipment data management system based on digital twinning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115718466B (en) | 2024-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115718466B (en) | Digital twin workshop fault prediction method based on random forest and analytic hierarchy process | |
| CN111553590B (en) | Radar embedded health management system | |
| Chenchala et al. | Predictive Maintenance and Resource Optimization in Inventory Identification Tool Using ML | |
| CN109902954B (en) | Flexible job shop dynamic scheduling method based on industrial big data | |
| CN112446526B (en) | Production scheduling system and method | |
| CN107909126A (en) | A kind of MES system for motor automated production | |
| CN117389236B (en) | Propylene oxide production process optimization method and system | |
| CN114418177B (en) | New product material distribution prediction method based on digital twin workshops for generating countermeasure network | |
| CN113469241A (en) | Product quality control method based on process network model and machine learning algorithm | |
| CN113506001B (en) | Smart management and control auxiliary decision-making method for safety risk lean of operation site | |
| CN115688016A (en) | Integrated method for intelligent operation and maintenance of large database | |
| Kodali et al. | Performance value analysis for the justification of world-class manufacturing systems | |
| CN115115213A (en) | Method and device for retrospective analysis of quality characteristics of steel products | |
| CN115114856A (en) | Intelligent manufacturing production line operation system based on digital twin | |
| CN114862267A (en) | Evaluation method and system of oil and gas pipeline alarm management system | |
| CN114529204A (en) | Modularized production process control and management method and system | |
| CN112559591B (en) | Outlier detection system and detection method for cold roll manufacturing process | |
| CN117140186A (en) | Online monitoring system and method for machining workshop based on artificial intelligence | |
| Vishwakarma et al. | Uncertainty analysis of an industrial system using intuitionistic fuzzy set theory | |
| CN116339266A (en) | Composite monitoring method and system for pipe production | |
| CN116205622A (en) | Intelligent fault early warning and maintenance decision method for smoke machine equipment | |
| CN114139102A (en) | Numerical control machining quality risk early warning method | |
| CN111784064A (en) | Power plant equipment intelligent prediction maintenance method and system based on big data | |
| Lige et al. | Road machinery fault prediction based on big data and machine learning | |
| CN111176174A (en) | Multifunctional supervision system for stamping workshop |
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 |