CN115700363B - Method and system for diagnosing faults of rolling bearing of coal mining machine, electronic equipment and storage medium - Google Patents
Method and system for diagnosing faults of rolling bearing of coal mining machine, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115700363B CN115700363B CN202211384584.8A CN202211384584A CN115700363B CN 115700363 B CN115700363 B CN 115700363B CN 202211384584 A CN202211384584 A CN 202211384584A CN 115700363 B CN115700363 B CN 115700363B
- Authority
- CN
- China
- Prior art keywords
- rolling bearing
- fault diagnosis
- firefly
- model
- target
- 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
Landscapes
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention provides a fault diagnosis method and system for a rolling bearing of a coal mining machine, electronic equipment and a storage medium, wherein the method comprises the following steps: based on a target coal cutter rolling bearing, establishing a digital twin model of the target coal cutter rolling bearing and a corresponding rolling bearing fault diagnosis model; the rolling bearing fault diagnosis model is determined based on a probabilistic neural network; determining a target rolling bearing fault diagnosis model according to a firefly optimization algorithm based on the digital twin model and the rolling bearing fault diagnosis model; and determining a fault result of the rolling bearing of the target coal mining machine based on the fault diagnosis model of the target rolling bearing. The accuracy of predictive fault diagnosis of the rolling bearing of the coal mining machine can be effectively improved, and the running cost of the coal mining machine is reduced.
Description
Technical Field
The invention relates to the technical field of process industry, in particular to a fault diagnosis method and system for a rolling bearing of a coal mining machine, electronic equipment and a storage medium.
Background
Along with the continuous improvement of integration, intellectualization and automation degree, production equipment in a process industrial production line is more and more complex and precise, and the difficulty of equipment maintenance and fault treatment is also increased. The method has the advantages of accurately grasping important parameters of the equipment, analyzing the generation reason of the fault and predicting potential fault hidden trouble of the equipment, greatly helping field production, reducing the running cost of the equipment and reducing the shutdown time of a production line due to the fault.
The working environment of the coal mining machine is complex and severe, the load change is large, overload is easy to occur at some key parts in normal work, and abnormality occurs. The traction traveling chain wheel of the coal mining machine has large load and uneven load, and the bearing of the traction traveling chain wheel is easy to wear or crack rolling bodies. In the case of mild injury, it is not easily found by the staff. Serious damage to the bearings may affect the sprocket shaft, sprocket and other parts engaged therewith, thereby causing damage to the other parts. When the faults develop to serious incapacity of working, the faults are perceived to cause waste of manpower and financial resources. The production efficiency can be effectively improved by diagnosing faults of the coal mining machine in advance.
However, the most important difficulty in the process industry is modeling difficulty, so that prediction and optimization are difficult. The method for diagnosing the predictive faults of the rolling bearing of the coal mining machine in the prior art is low in accuracy.
Therefore, how to provide a fault diagnosis method and system for the rolling bearing of the coal mining machine, electronic equipment and storage medium, so that the accuracy of predictive fault diagnosis of the rolling bearing of the coal mining machine is effectively improved, and the running cost of the coal mining machine is reduced.
Disclosure of Invention
Aiming at the defects in the prior art, the embodiment of the invention provides a fault diagnosis method and system for a rolling bearing of a coal mining machine, electronic equipment and a storage medium.
The invention provides a fault diagnosis method for a rolling bearing of a coal mining machine, which comprises the following steps:
based on a target coal cutter rolling bearing, establishing a digital twin model of the target coal cutter rolling bearing and a corresponding rolling bearing fault diagnosis model; the rolling bearing fault diagnosis model is determined based on a probabilistic neural network;
determining a target rolling bearing fault diagnosis model according to a firefly optimization algorithm based on the digital twin model and the rolling bearing fault diagnosis model;
and determining a fault result of the rolling bearing of the target coal mining machine based on the fault diagnosis model of the target rolling bearing.
According to the fault diagnosis method for the rolling bearing of the coal mining machine, provided by the invention, based on a digital twin model and a fault diagnosis model for the rolling bearing, a fault diagnosis model for a target rolling bearing is determined according to a firefly optimization algorithm, and the method specifically comprises the following steps:
determining a fault sample training set according to the fault sample data based on the digital twin model;
training a rolling bearing fault diagnosis model based on the fault sample training set;
optimizing the probability neural network smoothing factor according to a firefly algorithm, and determining an optimal smoothing factor;
and determining a target rolling bearing fault diagnosis model based on the optimal smoothing factor.
According to the fault diagnosis method for the rolling bearing of the coal mining machine, provided by the invention, a target rolling bearing fault diagnosis model is determined based on an optimal smoothing factor, and the method specifically comprises the following steps:
determining an optimized probability neural network according to the optimal smoothing factor;
testing the optimized probability neural network based on a fault sample testing set, and judging whether the optimized probability neural network can accurately perform fault diagnosis;
if the optimized probability neural network cannot accurately perform fault diagnosis, repeating the steps of training and testing the rolling bearing fault diagnosis model based on the fault sample training set until the optimized probability neural network can accurately perform fault diagnosis, and determining a target probability neural network;
and determining a target rolling bearing fault diagnosis model based on the target probability neural network.
According to the fault diagnosis method for the rolling bearing of the coal mining machine, provided by the invention, the probability neural network smoothing factor is optimized according to the firefly algorithm, and the optimal smoothing factor is determined, and the method specifically comprises the following steps:
optimizing the probability neural network smoothing factor according to the improved firefly algorithm, and determining the optimal smoothing factor;
wherein, the improved firefly algorithm adds inertial weight in the standard firefly algorithm;
The location update formula for firefly i attracted to move toward firefly j in the modified firefly algorithm is:
x i (t+1)＝w(t)x i (t)+β(x j (t)-x i (t))+α new (rand-0.5)；
in the above, x i (t) and x j (t) is the position of firefly i and firefly j after the t-th shift in space, w (t) is the inertial weight, α new Beta is the attraction degree of firefly j to firefly i as step factor, and rand is [0,1]Applying random factors subject to uniform distribution;
the inertial weight calculation formula is:
in the above, w max Is the maximum inertial weight, w min And T is the maximum iteration number for the minimum inertia weight.
According to the fault diagnosis method for the rolling bearing of the coal mining machine, the improved firefly algorithm is to add inertia weight and improve step factors in a standard firefly algorithm;
the step factor calculation formula is:
in the above formula, t is the current iteration number, a 0 Is an initial step size factor.
According to the fault diagnosis method for the rolling bearing of the coal mining machine, provided by the invention, the probability neural network smoothing factor is optimized according to the improved firefly algorithm, and the optimal smoothing factor is determined, and the method specifically comprises the following steps:
initializing basic parameters of fireflies, and taking a probability neural network smoothing factor as a firefly individual;
calculating the fitness value of the firefly individual according to the initial position of the firefly;
Comparing the brightness of the firefly based on the fitness value, determining the brightest position as a new position of the firefly, and updating the position of the firefly according to a position updating formula;
and iteratively updating the fitness value and the position of the firefly until the preset optimizing condition is met, outputting the optimal position of the firefly, and determining the optimal smoothing factor.
According to the fault diagnosis method for the rolling bearing of the coal mining machine, provided by the invention, the preset optimizing conditions comprise:
the iteration times are larger than a preset iteration threshold; or (b)
The result of the objective function is smaller than a preset expected threshold;
wherein, the objective function formula is:
in the above, E i For actual output, R i For desired output, N is the total number of fireflies.
The invention also provides a fault diagnosis system of the rolling bearing of the coal mining machine, which comprises the following steps: the system comprises a model building unit, a model determining unit and a fault diagnosis unit;
the model building unit is used for building a digital twin model of the target coal cutter rolling bearing and a corresponding rolling bearing fault diagnosis model based on the target coal cutter rolling bearing;
the model determining unit is used for determining a target rolling bearing fault diagnosis model according to a firefly optimization algorithm based on the digital twin model and the rolling bearing fault diagnosis model; the rolling bearing fault diagnosis model is determined based on a probabilistic neural network;
And the fault diagnosis unit is used for determining a fault result of the rolling bearing of the target coal mining machine based on the fault diagnosis model of the target rolling bearing.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the steps of any of the fault diagnosis methods of the rolling bearing of the coal mining machine when executing the program.
The invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of a method for diagnosing a shearer rolling bearing fault as described in any one of the above.
According to the fault diagnosis method and system for the rolling bearing of the coal mining machine, the electronic equipment and the storage medium, the digital twin model of the rolling bearing of the coal mining machine in the process industry is constructed, the digital twin technology is combined with the probabilistic neural network to construct the fault diagnosis model of the rolling bearing, and the firefly algorithm is adopted to optimize the model, so that the rapid training of the model is realized, and the problem of low accuracy of a prediction result caused by inaccurate modeling is effectively solved. Predictive fault diagnosis of the rolling bearing is realized through the rolling bearing fault diagnosis model, the accuracy of predictive fault diagnosis of the rolling bearing of the coal mining machine can be effectively improved, and the running cost of the coal mining machine is reduced.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a fault diagnosis method for a rolling bearing of a coal mining machine;
FIG. 2 is a schematic diagram of a digital twin model structure provided by the invention;
FIG. 3 is a schematic diagram of a fault diagnosis flow of a rolling bearing of a coal mining machine;
FIG. 4 is a schematic flow chart of a fault diagnosis method for a rolling bearing of a coal mining machine;
FIG. 5 is a graph of the predictive effect of a probabilistic neural network based on optimization of firefly algorithm provided by the invention;
FIG. 6 is a schematic diagram of a probabilistic neural network training error based on firefly algorithm optimization provided by the invention;
FIG. 7 is a graph of the predictive effects of a probabilistic neural network based on improved firefly algorithm optimization provided by the present invention;
FIG. 8 is a schematic diagram of the training error of the probabilistic neural network based on improved firefly algorithm optimization provided by the invention;
FIG. 9 is a schematic diagram of a fault diagnosis system for a rolling bearing of a coal mining machine;
fig. 10 is a schematic diagram of an entity structure of an electronic device according to the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The digital twin technology has virtual-real interaction capability, can correlate and map data acquired in real time into a digital twin body, and predicts and analyzes the behavior of an analog object and performs fault diagnosis and early warning through the digital twin body. The method comprises the steps of constructing a digital twin model of the rolling bearing of the coal mining machine in the process industry, and realizing the functions of accurate prediction and control of the production process, full life cycle management of equipment and the like through parallel operation, real-time interaction and iterative optimization of the digital twin model and equipment entities so as to greatly improve the production quality and efficiency in the process industry production line.
Fig. 1 is a flowchart of a fault diagnosis method for a rolling bearing of a coal cutter, provided by the invention, as shown in fig. 1, the invention provides a fault diagnosis method for a rolling bearing of a coal cutter, comprising the following steps:
step S1, based on a target coal cutter rolling bearing, establishing a digital twin model of the target coal cutter rolling bearing and a corresponding rolling bearing fault diagnosis model; the rolling bearing fault diagnosis model is determined based on a probabilistic neural network;
step S2, determining a target rolling bearing fault diagnosis model according to a firefly optimization algorithm based on the digital twin model and the rolling bearing fault diagnosis model;
and step S3, determining a target coal cutter rolling bearing fault result based on the target rolling bearing fault diagnosis model.
Specifically, fig. 2 is a schematic structural diagram of a digital twin model structure provided by the invention, and as shown in fig. 2, in order to ensure the accuracy of modeling a target rolling bearing of a coal mining machine, the actual running condition of the rolling bearing needs to be analyzed first, and a digital twin model is established.
In step S1, a digital twin model of the shearer rolling bearing is built using Unity3D based on the target shearer rolling bearing. The digital twin model of the rolling bearing of the coal mining machine comprises a geometric model, a physical model, a behavior model and a rule model.
The geometric model of the rolling bearing of the coal mining machine comprises parameters such as geometric dimensions, shapes and position relations among equipment of all parts; the physical model is the physical attribute of the rolling bearing, such as strain force, damage and the like, and maps the physical state of the rolling bearing in real time; the behavior model comprises the action response of the rolling bearing to the internal and external environment and the system instruction, so that the digital twin can super-write the actual simulation running condition and perform fault diagnosis analysis; the rule model is based on expert knowledge to summarize experience, historical data, real-time data and the running state of the equipment, and the fault rule of the equipment is mined, so that a fault prediction function is provided.
Based on a digital twin model of the target coal cutter rolling bearing, combining expert knowledge, machine learning and the like, a corresponding rolling bearing fault diagnosis model is established. It is understood that the rolling bearing fault diagnosis model is determined based on a probabilistic neural network (Probabilistic Neural Network, PNN) and is used for realizing predictive fault diagnosis of the rolling bearing of the target coal mining machine.
It should be noted that, in the present invention, the specific construction method and the actual structure of the digital twin model and the corresponding rolling bearing fault diagnosis model may be adjusted according to the actual application requirement of the present invention, which is not limited in this invention.
In step S2, based on the digital twin model and the rolling bearing fault diagnosis model, the initial rolling bearing fault diagnosis model is optimized according to a firefly optimization algorithm, and a target rolling bearing fault diagnosis model is determined.
It can be understood that the digital twin model is a real-time mapping of physical entities in a virtual model, monitors the running state of the rolling bearing entities in real time, and transmits simulation data thereof to a database in real time, so as to provide sample data for training of the rolling bearing fault diagnosis model.
After the failure diagnosis model is successfully trained, in step S3, based on the target rolling bearing failure diagnosis model, predictive failure diagnosis is carried out on the rolling bearing according to the data information of the target rolling bearing when the diagnosis is needed, and a target coal mining machine rolling bearing failure result is determined.
It can be understood that when fault diagnosis is performed, current actual data information of the target rolling bearing can be used for performing real-time fault prediction, analog data obtained by a digital twin model can also be used for performing fault detection, and specific diagnosis data types can be adjusted according to actual requirements.
According to the fault diagnosis method for the rolling bearing of the coal mining machine, provided by the invention, the digital twin model of the rolling bearing of the coal mining machine in the process industry is constructed, the digital twin technology is combined with the probability neural network to construct the fault diagnosis model of the rolling bearing, and the firefly algorithm is adopted to optimize the model, so that the rapid training of the model is realized, and the problem of low accuracy of a prediction result caused by inaccurate modeling is effectively solved. Predictive fault diagnosis of the rolling bearing is realized through the rolling bearing fault diagnosis model, the accuracy of predictive fault diagnosis of the rolling bearing of the coal mining machine can be effectively improved, and the running cost of the coal mining machine is reduced.
Optionally, according to the fault diagnosis method for the rolling bearing of the coal mining machine provided by the invention, based on the digital twin model and the fault diagnosis model for the rolling bearing, the fault diagnosis model for the target rolling bearing is determined according to a firefly optimization algorithm, and the method specifically comprises the following steps:
determining a fault sample training set according to the fault sample data based on the digital twin model;
training a rolling bearing fault diagnosis model based on the fault sample training set;
optimizing the probability neural network smoothing factor according to a firefly algorithm, and determining an optimal smoothing factor;
and determining a target rolling bearing fault diagnosis model based on the optimal smoothing factor.
Specifically, fig. 3 is a schematic diagram of a fault diagnosis flow of a rolling bearing of a coal mining machine, and as shown in fig. 3, a physical entity is composed of real production equipment and a sensor, and the sensor acquires running data of the rolling bearing in real time and transmits the running data to a twin database for storage; the digital twin model is the real-time mapping of physical entities in the virtual model, monitors the running state of the rolling bearing entities in real time, and transmits the simulation data thereof to the database in real time. The twin database stores historical data and real-time data of physical entities of the production facility and data of the digital twin model. The connection between the parts can realize the real-time updating iteration of the data, and optimize the digital twin model to be more similar to a physical entity.
And when the fault diagnosis model of the target rolling bearing is trained and determined. Firstly, determining a fault sample training set according to fault sample data stored in a twin database based on a digital twin model.
It can be understood that the actual fault sample data may have insufficient data quantity, and the digital twin model can acquire simulation data to expand the fault sample data, so as to improve the accuracy of the model.
And inputting the fault sample training set into a rolling bearing fault diagnosis model, training the model, optimizing the probability neural network smoothing factor according to a firefly algorithm, and determining the optimal smoothing factor.
It can be understood that the probabilistic neural network is a feed-forward neural network based on bayesian decision, and the network training speed is high, and for complex classification problems, the optimal solution under the bayesian criterion can be ensured to be obtained. Compared with other methods, the probabilistic neural network does not need to be trained for a plurality of times, only needs to adjust the smoothing factors, and has more advantages in practice. The invention realizes the improvement of the accuracy of predictive fault diagnosis by optimizing the smoothing factor through the firefly algorithm. The specific implementation of the firefly algorithm is not described in detail herein.
And determining a target rolling bearing fault diagnosis model based on the optimal smoothing factor, and realizing predictive diagnosis of faults according to the target rolling bearing fault diagnosis model.
According to the fault diagnosis method for the rolling bearing of the coal mining machine, provided by the invention, the fault diagnosis model of the rolling bearing is built by building the digital twin model of the rolling bearing of the coal mining machine in the process industry, combining the digital twin technology with the probability neural network, mapping the real-time acquired data into the digital twin model in a correlated manner, determining the fault diagnosis model of the target rolling bearing through sample data provided by the digital twin model, and predicting and analyzing the behavior of an analog object, diagnosing faults and early warning, so that the accuracy of fault diagnosis is improved. The accuracy of predictive fault diagnosis of the rolling bearing of the coal mining machine is effectively improved in a mode of combining a digital twin technology and a probabilistic neural network, and the running cost of the coal mining machine is reduced.
Optionally, according to the fault diagnosis method for the rolling bearing of the coal mining machine provided by the invention, the fault diagnosis model of the target rolling bearing is determined based on the optimal smoothing factor, and specifically comprises the following steps:
determining an optimized probability neural network according to the optimal smoothing factor;
Testing the optimized probability neural network based on a fault sample testing set, and judging whether the optimized probability neural network can accurately perform fault diagnosis;
if the optimized probability neural network cannot accurately perform fault diagnosis, repeating the steps of training and testing the rolling bearing fault diagnosis model based on the fault sample training set until the optimized probability neural network can accurately perform fault diagnosis, and determining a target probability neural network;
and determining a target rolling bearing fault diagnosis model based on the target probability neural network.
Specifically, in order to further improve the accuracy of the fault diagnosis model of the target rolling bearing, the fault sample data is normalized, divided into a training set and a testing set, and transmitted to the digital twin model. The training set is used for training the model, and the testing set is used for testing the training result of the model, so that the training result is suitable for meeting the requirements.
Fig. 4 is a schematic flow chart of a fault diagnosis method for a rolling bearing of a coal mining machine, as shown in fig. 4, and the step of determining a fault diagnosis model for a target rolling bearing based on an optimal smoothing factor specifically includes:
and determining an optimized probability neural network according to the optimal smoothing factor determined by the firefly algorithm, testing the optimized probability neural network by using a fault sample testing set, and judging whether the optimized probability neural network can accurately perform fault diagnosis.
If the optimized probability neural network is determined to be capable of accurately performing fault diagnosis, performing a next sample method test until samples in a fault sample test set are determined to be capable of accurately diagnosing.
If the optimized probability neural network cannot accurately perform fault diagnosis, repeating the steps of training and testing the rolling bearing fault diagnosis model based on the fault sample training set, relearning fault information, updating the fault diagnosis model until the optimized probability neural network can accurately perform fault diagnosis, and determining the target probability neural network.
And determining a target rolling bearing fault diagnosis model based on the target probability neural network.
According to the fault diagnosis method for the rolling bearing of the coal mining machine, the digital twin model of the rolling bearing of the coal mining machine in the process industry is constructed, the digital twin technology is combined with the probabilistic neural network to construct the fault diagnosis model of the rolling bearing, the firefly algorithm is adopted to optimize the model, the rapid training of the model is realized, the test set is combined to verify the detection effect of the model, the accurate and effective learning fault rule of the model is ensured, the problem that the accuracy of a prediction result is low due to inaccurate modeling is effectively solved, and the accuracy of the fault detection of the model is further improved.
Optionally, according to the fault diagnosis method for the rolling bearing of the coal mining machine provided by the invention, the probability neural network smoothing factor is optimized according to the firefly algorithm, and the optimal smoothing factor is determined, which specifically comprises the following steps:
optimizing the probability neural network smoothing factor according to the improved firefly algorithm, and determining the optimal smoothing factor;
wherein, the improved firefly algorithm adds inertial weight in the standard firefly algorithm;
the location update formula for firefly i attracted to move toward firefly j in the modified firefly algorithm is:
x i (t+1)＝w(t)x i (t)+β(x j (t)-x i (t))+α new (rand-0.5)；
in the above, x i (t) and x j (t) is the position of firefly i and firefly j after the t-th shift in space, w (t) is the inertial weight, α new Beta is the attraction degree of firefly j to firefly i as step factor, and rand is [0,1]Applying random factors subject to uniform distribution;
the inertial weight calculation formula is:
in the above, w max Is the maximum inertial weight, w min And T is the maximum iteration number for the minimum inertia weight.
Specifically, as the traditional firefly algorithm has the problems of low later convergence speed, poor solving precision, easy sinking into local optimum and the like, the invention provides an improved firefly algorithm (Modification Firefly Algorithm, MFA), inertia weight is added in a standard firefly algorithm (Firefly Algorithm, FA), the convergence speed and the solving precision of the algorithm are improved, and the accuracy of fault diagnosis is improved.
And optimizing the probability neural network smoothing factor according to the improved firefly algorithm, and determining the optimal smoothing factor.
The location update formula for firefly i attracted to move toward firefly j in the modified firefly algorithm is:
x i (t+1)＝w(t)x i (t)+β(x j (t)-x i (t))+α new (rand-0.5)；
in the above, x i (t) and x j (t) is the position of firefly i and firefly j after the t-th shift in space, w (t) is the inertial weight, α new Beta is the attraction degree of firefly j to firefly i as step factor, and rand is [0,1]Applying random factors subject to uniform distribution;
the inertial weight calculation formula is:
in the above, w max Is the maximum inertial weight, w min And T is the maximum iteration number, and T is the current iteration number. For example, in practical applications, t=200, w may be set min ＝0.2，w max The specific values of the parameters may be adjusted according to actual requirements, which is not limited in the present invention.
It can be understood that the optimization method of the improved firefly algorithm for the probabilistic neural network smoothing factor is similar to the optimization method of the standard firefly algorithm, and only the firefly position update formula needs to be replaced, and specific steps are not repeated here.
According to the fault diagnosis method for the rolling bearing of the coal mining machine, the digital twin model of the rolling bearing of the coal mining machine in the process industry is constructed, the digital twin technology is combined with the probabilistic neural network to construct the fault diagnosis model of the rolling bearing, and compared with a traditional firefly algorithm, the improved firefly algorithm is adopted to optimize the model, so that the adjustment of inertia weight can be realized, the convergence speed and the solving precision of the firefly algorithm are improved, and the diagnosis accuracy of the model is further improved while the rapid training of the model is realized.
Optionally, according to the fault diagnosis method for the rolling bearing of the coal mining machine provided by the invention, the improved firefly algorithm is to add inertial weight and improve step factors in a standard firefly algorithm;
the step factor calculation formula is:
in the above formula, t is the current iteration number, a 0 Is an initial step size factor.
Specifically, sinx was found to be 1 when x= 1.5707, and decreases as x decreases, thus introducing a sine function into the step size to enhance global search capability. The improved firefly algorithm is to add inertial weights and improve step factors in the standard firefly algorithm.
The step factor calculation formula is:
in the above formula, t is the current iteration number, a 0 And T is the maximum iteration number for the initial step factor.
According to the fault diagnosis method for the rolling bearing of the coal mining machine, the digital twin model of the rolling bearing of the coal mining machine in the process industry is constructed, the digital twin technology is combined with the probabilistic neural network to construct the fault diagnosis model of the rolling bearing, and an improved firefly algorithm is adopted to optimize the model, compared with a traditional firefly algorithm, the improved firefly algorithm adds inertia weight and improves step factors in a standard firefly algorithm, so that the convergence speed and the solving precision of the firefly algorithm are improved, the global searching capability is enhanced, and the diagnosis accuracy of the model is further improved while the rapid training of the model is realized.
Optionally, according to the fault diagnosis method for the rolling bearing of the coal mining machine provided by the invention, the probability neural network smoothing factor is optimized according to the improved firefly algorithm, and the optimal smoothing factor is determined, which specifically comprises the following steps:
initializing basic parameters of fireflies, and taking a probability neural network smoothing factor as a firefly individual;
calculating the fitness value of the firefly individual according to the initial position of the firefly;
comparing the brightness of the firefly based on the fitness value, determining the brightest position as a new position of the firefly, and updating the position of the firefly according to a position updating formula;
and iteratively updating the fitness value and the position of the firefly until the preset optimizing condition is met, outputting the optimal position of the firefly, and determining the optimal smoothing factor.
Specifically, the method optimizes the probability neural network smoothing factor according to the improved firefly algorithm, and determines the optimal smoothing factor, specifically including:
initializing basic parameters of fireflies, including a firefly initial population scale N, the position of the fireflies, a light absorption coefficient gamma, a step factor alpha, a suction degree beta, the maximum iteration number T and the like, taking a probability neural network smoothing factor as a firefly individual, initializing a probability neural network, and carrying out normalization processing on fault sample data.
According to the initial position of the firefly, calculating the fitness value of the firefly individual according to a firefly relative brightness formula, wherein the fitness value reflects the brightness of the firefly.
The relative brightness I formula of firefly is:
in the above, I 0 The fluorescence brightness when the firefly distance is 0, namely the brightness of the brightest firefly; gamma represents the light absorption coefficient; r is (r) ij Representing the distance between fireflies i and j. Comparing the brightness of the firefly based on the fitness value, determining the brightest position as a new position of the firefly, and updating the position of the firefly according to a position updating formula;
iteratively updating the fitness value and the position of the firefly until the preset optimizing condition is met, outputting the optimal position of the firefly, and obtaining an optimal smoothing factor obtained by an improved firefly algorithm.
According to the fault diagnosis method for the rolling bearing of the coal mining machine, the digital twin model of the rolling bearing of the coal mining machine in the process industry is constructed, the digital twin technology is combined with the probabilistic neural network to construct the fault diagnosis model of the rolling bearing, and an improved firefly algorithm is adopted to optimize the model, compared with a traditional firefly algorithm, the improved firefly algorithm adds inertia weight and improves step factors in a standard firefly algorithm, so that the convergence speed and the solving precision of the firefly algorithm are improved, the global searching capability is enhanced, and the diagnosis accuracy of the model is further improved while the rapid training of the model is realized.
Optionally, according to the method for diagnosing a fault of a rolling bearing of a coal mining machine provided by the invention, preset optimizing conditions include:
the iteration times are larger than a preset iteration threshold; or (b)
The result of the objective function is smaller than a preset expected threshold;
wherein, the objective function formula is:
in the above, E i For actual output, R i For desired output, N is the total number of fireflies.
Specifically, as shown in fig. 4, when the improved firefly algorithm is used to determine the optimal smoothing factor, a preset optimizing condition is set.
The iteration times are larger than a preset iteration threshold; or (b)
The result of the objective function is smaller than a preset expected threshold;
when the objective function is PNN network effect detection, the mean square error MSE of the output value and the true value is calculated, and the formula of the objective function is as follows:
in the above, E i For actual output, R i For desired output, N is the total number of fireflies.
And adopting an improved firefly algorithm to obtain a smoothing factor and giving the smoothing factor to the probabilistic neural network, and recording the current position and brightness value of the firefly when the fault diagnosis accuracy is highest, namely the objective function result is smaller than a preset expected threshold value or the maximum iteration number is reached, so as to obtain the optimal smoothing factor.
According to the fault diagnosis method for the rolling bearing of the coal mining machine, the digital twin model of the rolling bearing of the coal mining machine in the process industry is constructed, the digital twin technology is combined with the probabilistic neural network to construct the fault diagnosis model of the rolling bearing, and an improved firefly algorithm is adopted to optimize the model, compared with a traditional firefly algorithm, the improved firefly algorithm adds inertia weight and improves step factors in a standard firefly algorithm, so that the convergence speed and the solving precision of the firefly algorithm are improved, the global searching capability is enhanced, and the diagnosis accuracy of the model is further improved while the rapid training of the model is realized.
In order to further illustrate the practical effect of the invention, matlab2020b software is used for performing simulation verification of performance comparison of the FA method and the MFA method.
Taking uncertainty into consideration, setting the population number of fireflies to 30, the maximum iteration number T=200, and the initial step factor alpha 0 =0.97, initial attraction degree β 0 =0.8, minimum attraction degree β min =0.2, light absorption coefficient γ=1.
Through repeated debugging, fig. 5 is a graph of the prediction effect of the probabilistic neural network based on the optimization of the firefly algorithm, and fig. 6 is a graph of the training error of the probabilistic neural network based on the optimization of the firefly algorithm, wherein the prediction effect and the training error of the PNN network optimized by adopting the FA algorithm are shown in fig. 5-6.
Fig. 7 is a graph of the prediction effect of the probabilistic neural network based on the improved firefly algorithm optimization provided by the invention, fig. 8 is a schematic diagram of the training error of the probabilistic neural network based on the improved firefly algorithm optimization provided by the invention, and the prediction effect and the training error of the PNN network optimized by the MFA algorithm are shown in fig. 7-8.
In fig. 5 and 7, the abscissa indicates the sample number, the ordinate indicates the prediction result, pre indicates the prediction value, and Real indicates the true value. In fig. 6 and 8, the abscissa indicates the sample number, and the ordinate indicates the sample type error. The results show that compared with the traditional FA algorithm, the improved MFA algorithm provided by the invention has obviously lower prediction error rate and greatly improves the accuracy of fault diagnosis.
Fig. 9 is a schematic structural diagram of a fault diagnosis system for a rolling bearing of a coal cutter, and as shown in fig. 9, the invention also provides a fault diagnosis system for a rolling bearing of a coal cutter, which comprises: a model construction unit 901, a model determination unit 902, and a failure diagnosis unit 903;
the model building unit 901 is used for building a digital twin model of the target coal cutter rolling bearing and a corresponding rolling bearing fault diagnosis model based on the target coal cutter rolling bearing;
a model determining unit 902, configured to determine a target rolling bearing fault diagnosis model according to a firefly optimization algorithm based on the digital twin model and the rolling bearing fault diagnosis model; the rolling bearing fault diagnosis model is determined based on a probabilistic neural network;
a fault diagnosis unit 903, configured to determine a fault result of the target shearer rolling bearing based on the target rolling bearing fault diagnosis model.
Fig. 2 is a schematic structural diagram of a digital twin model structure provided by the invention, and as shown in fig. 2, in order to ensure the modeling accuracy of a target coal cutter rolling bearing, the actual running condition of the rolling bearing needs to be analyzed first, and a digital twin model is built.
The model building unit 901 is used for building a digital twin model of the coal cutter rolling bearing by utilizing Unity3D based on the target coal cutter rolling bearing. The digital twin model of the rolling bearing of the coal mining machine comprises a geometric model, a physical model, a behavior model and a rule model.
The geometric model of the rolling bearing of the coal mining machine comprises parameters such as geometric dimensions, shapes and position relations among equipment of all parts; the physical model is the physical attribute of the rolling bearing, such as strain force, damage and the like, and maps the physical state of the rolling bearing in real time; the behavior model comprises the action response of the rolling bearing to the internal and external environment and the system instruction, so that the digital twin can super-write the actual simulation running condition and perform fault diagnosis analysis; the rule model is based on expert knowledge to summarize experience, historical data, real-time data and the running state of the equipment, and the fault rule of the equipment is mined, so that a fault prediction function is provided.
Based on a digital twin model of the target coal cutter rolling bearing, combining expert knowledge, machine learning and the like, a corresponding rolling bearing fault diagnosis model is established. It is understood that the rolling bearing fault diagnosis model is determined based on a probabilistic neural network (Probabilistic Neural Network, PNN) and is used for realizing predictive fault diagnosis of the rolling bearing of the target coal mining machine.
It should be noted that, in the present invention, the specific construction method and the actual structure of the digital twin model and the corresponding rolling bearing fault diagnosis model may be adjusted according to the actual application requirement of the present invention, which is not limited in this invention.
The model determining unit 902 is configured to determine a target rolling bearing fault diagnosis model by optimizing an initial rolling bearing fault diagnosis model according to a firefly optimization algorithm based on the digital twin model and the rolling bearing fault diagnosis model.
It can be understood that the digital twin model is a real-time mapping of physical entities in a virtual model, monitors the running state of the rolling bearing entities in real time, and transmits simulation data thereof to a database in real time, so as to provide sample data for training of the rolling bearing fault diagnosis model.
After the failure diagnosis model is successfully trained, the failure diagnosis unit 903 is configured to perform predictive failure diagnosis on the rolling bearing according to data information when the target rolling bearing needs to be diagnosed based on the failure diagnosis model of the target rolling bearing, and determine a failure result of the rolling bearing of the target coal mining machine.
It can be understood that when fault diagnosis is performed, current actual data information of the target rolling bearing can be used for performing real-time fault prediction, analog data obtained by a digital twin model can also be used for performing fault detection, and specific diagnosis data types can be adjusted according to actual requirements.
According to the fault diagnosis system for the rolling bearing of the coal mining machine, provided by the invention, the digital twin model of the rolling bearing of the coal mining machine in the process industry is constructed, the digital twin technology is combined with the probability neural network to construct the fault diagnosis model of the rolling bearing, and the firefly algorithm is adopted to optimize the model, so that the rapid training of the model is realized, and the problem of low accuracy of a prediction result caused by inaccurate modeling is effectively solved. Predictive fault diagnosis of the rolling bearing is realized through the rolling bearing fault diagnosis model, the accuracy of predictive fault diagnosis of the rolling bearing of the coal mining machine can be effectively improved, and the running cost of the coal mining machine is reduced.
It should be noted that, the fault diagnosis system for the rolling bearing of the coal mining machine provided by the invention is used for executing the fault diagnosis method for the rolling bearing of the coal mining machine, and the specific implementation mode and the implementation mode of the method are consistent and are not repeated here.
Fig. 10 is a schematic diagram of an entity structure of an electronic device according to the present invention, as shown in fig. 10, the electronic device may include: a processor (processor) 101, a communication interface (communication interface) 102, a memory (memory) 103, and a communication bus 104, wherein the processor 101, the communication interface 102, and the memory 103 perform communication with each other through the communication bus 104. The processor 101 may invoke logic instructions in the memory 103 to perform a shearer rolling bearing fault diagnosis method comprising: based on a target coal cutter rolling bearing, establishing a digital twin model of the target coal cutter rolling bearing and a corresponding rolling bearing fault diagnosis model; the rolling bearing fault diagnosis model is determined based on a probabilistic neural network; determining a target rolling bearing fault diagnosis model according to a firefly optimization algorithm based on the digital twin model and the rolling bearing fault diagnosis model; and determining a fault result of the rolling bearing of the target coal mining machine based on the fault diagnosis model of the target rolling bearing.
Further, the logic instructions in the memory 103 may be implemented in the form of software functional units and may be stored in a computer readable storage medium when sold or used as a stand alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method of the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-only memory (ROM), a random access memory (RAM, randomAccessMemory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform the method for diagnosing faults of a rolling bearing of a shearer provided by the above methods, the method comprising: based on a target coal cutter rolling bearing, establishing a digital twin model of the target coal cutter rolling bearing and a corresponding rolling bearing fault diagnosis model; the rolling bearing fault diagnosis model is determined based on a probabilistic neural network; determining a target rolling bearing fault diagnosis model according to a firefly optimization algorithm based on the digital twin model and the rolling bearing fault diagnosis model; and determining a fault result of the rolling bearing of the target coal mining machine based on the fault diagnosis model of the target rolling bearing.
In yet another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform the above provided shearer rolling bearing fault diagnosis methods, the method comprising: based on a target coal cutter rolling bearing, establishing a digital twin model of the target coal cutter rolling bearing and a corresponding rolling bearing fault diagnosis model; the rolling bearing fault diagnosis model is determined based on a probabilistic neural network; determining a target rolling bearing fault diagnosis model according to a firefly optimization algorithm based on the digital twin model and the rolling bearing fault diagnosis model; and determining a fault result of the rolling bearing of the target coal mining machine based on the fault diagnosis model of the target rolling bearing.
The apparatus embodiments described above are merely illustrative, wherein elements illustrated as separate elements may or may not be physically separate, and elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on such understanding, the foregoing technical solutions may be embodied essentially or in part in the form of a software product, which may be stored in a computer-readable storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform the various embodiments or methods of some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (6)
1. The fault diagnosis method for the rolling bearing of the coal mining machine is characterized by comprising the following steps of:
based on a target coal cutter rolling bearing, establishing a digital twin model of the target coal cutter rolling bearing and a corresponding rolling bearing fault diagnosis model; the rolling bearing fault diagnosis model is determined based on a probabilistic neural network;
determining a target rolling bearing fault diagnosis model according to a firefly optimization algorithm based on the digital twin model and the rolling bearing fault diagnosis model;
determining a fault result of the target coal cutter rolling bearing based on the fault diagnosis model of the target rolling bearing;
the method for determining the target rolling bearing fault diagnosis model based on the digital twin model and the rolling bearing fault diagnosis model according to a firefly optimization algorithm specifically comprises the following steps:
determining a fault sample training set according to fault sample data based on the digital twin model;
training the rolling bearing fault diagnosis model based on the fault sample training set;
optimizing the probability neural network smoothing factor according to a firefly algorithm, and determining an optimal smoothing factor;
determining a target rolling bearing fault diagnosis model based on the optimal smoothing factor;
The determining a target rolling bearing fault diagnosis model based on the optimal smoothing factor specifically comprises the following steps:
determining an optimized probability neural network according to the optimal smoothing factor;
testing the optimized probability neural network based on a fault sample test set, and judging whether the optimized probability neural network can accurately perform fault diagnosis;
if the optimized probability neural network cannot accurately perform fault diagnosis, repeating the steps of training and testing the rolling bearing fault diagnosis model based on the fault sample training set until the optimized probability neural network is determined to accurately perform fault diagnosis, and determining a target probability neural network;
determining a target rolling bearing fault diagnosis model based on the target probability neural network;
the method for optimizing the probability neural network smoothing factor according to the firefly algorithm comprises the following steps of:
optimizing the probability neural network smoothing factor according to an improved firefly algorithm, and determining an optimal smoothing factor;
wherein the improved firefly algorithm is to add inertial weight to a standard firefly algorithm;
The position update formula of the improved firefly algorithm that firefly i is attracted to move towards firefly j is:
x i (t+1)＝w(t)x i (t)+β(x j (t)-x i (t))+α new (rand-0.5)；
in the above, x i (t) and x j (t) is the position of firefly i and firefly j after the t-th shift in space, w (t) is the inertial weight, α new Beta is the attraction degree of firefly j to firefly i as step factor, and rand is [0,1]Applying random factors subject to uniform distribution;
the inertial weight calculation formula is as follows:
in the above, w max Is the maximum inertial weight, w min The minimum inertia weight is adopted, and T is the maximum iteration number;
wherein, the improved firefly algorithm adds inertial weight and improves step size factor in standard firefly algorithm;
the step factor calculation formula is as follows:
in the above formula, t is the current iteration number, a 0 Is an initial step size factor.
2. The method for diagnosing a fault in a rolling bearing of a coal mining machine according to claim 1, wherein the optimizing the probabilistic neural network smoothing factor according to the modified firefly algorithm, determining an optimal smoothing factor, specifically comprises:
initializing basic parameters of fireflies, and taking the probabilistic neural network smoothing factors as firefly individuals;
calculating the fitness value of the firefly individual according to the initial position of the firefly;
Comparing the brightness of the firefly based on the fitness value, determining the brightest position as a new position of the firefly, and updating the position of the firefly according to the position updating formula;
iteratively updating the fitness value and the position of the firefly until the preset optimizing condition is met, outputting the optimal position of the firefly, and determining the optimal smoothing factor.
3. The method for diagnosing a fault in a rolling bearing of a coal mining machine according to claim 2, wherein the preset optimizing condition includes:
the iteration times are larger than a preset iteration threshold; or (b)
The result of the objective function is smaller than a preset expected threshold;
wherein, the objective function formula is:
in the above, E i For actual output, R i For desired output, N is the total number of fireflies.
4. A shearer rolling bearing failure diagnosis system according to any one of claims 1 to 3, characterized by comprising: the system comprises a model building unit, a model determining unit and a fault diagnosis unit;
the model construction unit is used for establishing a digital twin model of the target coal cutter rolling bearing and a corresponding rolling bearing fault diagnosis model based on the target coal cutter rolling bearing;
The model determining unit is used for determining a target rolling bearing fault diagnosis model according to a firefly optimization algorithm based on the digital twin model and the rolling bearing fault diagnosis model; the rolling bearing fault diagnosis model is determined based on a probabilistic neural network;
the fault diagnosis unit is used for determining a fault result of the target rolling bearing of the coal mining machine based on the fault diagnosis model of the target rolling bearing.
5. An electronic device comprising a memory and a processor, said processor and said memory completing communication with each other via a bus; the memory stores program instructions executable by the processor, the processor invoking the program instructions capable of performing the shearer rolling bearing fault diagnosis method as claimed in any one of claims 1 to 3.
6. A non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor, implements the shearer rolling bearing fault diagnosis method of any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211384584.8A CN115700363B (en) | 2022-11-07 | 2022-11-07 | Method and system for diagnosing faults of rolling bearing of coal mining machine, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211384584.8A CN115700363B (en) | 2022-11-07 | 2022-11-07 | Method and system for diagnosing faults of rolling bearing of coal mining machine, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115700363A CN115700363A (en) | 2023-02-07 |
| CN115700363B true CN115700363B (en) | 2023-08-08 |
Family
ID=85121015
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211384584.8A Active CN115700363B (en) | 2022-11-07 | 2022-11-07 | Method and system for diagnosing faults of rolling bearing of coal mining machine, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115700363B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116183231B (en) * | 2023-04-28 | 2023-07-11 | 安徽大学 | Bearing fault diagnosis method based on digital twin |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110363277A (en) * | 2019-07-15 | 2019-10-22 | 南京工业大学 | Method for diagnosing fault of power transformer and system based on improved glowworm swarm algorithm optimization probabilistic neural network |
| CN110567721A (en) * | 2019-10-28 | 2019-12-13 | 齐鲁工业大学 | rolling bearing fault diagnosis method and system |
| CN113128561A (en) * | 2021-03-22 | 2021-07-16 | 南京航空航天大学 | Machine tool bearing fault diagnosis method |
| CN113988124A (en) * | 2021-10-25 | 2022-01-28 | 武汉理工大学 | Fault diagnosis method and device for rotary mechanical equipment and electronic equipment |
| CN114201920A (en) * | 2021-12-15 | 2022-03-18 | 苏州华光智控电子科技有限公司 | Laser cutting numerical control system fault diagnosis method based on digital twinning and deep transfer learning |
| CN115292834A (en) * | 2022-07-20 | 2022-11-04 | 北自所(北京)科技发展股份有限公司 | Method, device and system for diagnosing faults of digital twin equipment |
-
2022
- 2022-11-07 CN CN202211384584.8A patent/CN115700363B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110363277A (en) * | 2019-07-15 | 2019-10-22 | 南京工业大学 | Method for diagnosing fault of power transformer and system based on improved glowworm swarm algorithm optimization probabilistic neural network |
| CN110567721A (en) * | 2019-10-28 | 2019-12-13 | 齐鲁工业大学 | rolling bearing fault diagnosis method and system |
| CN113128561A (en) * | 2021-03-22 | 2021-07-16 | 南京航空航天大学 | Machine tool bearing fault diagnosis method |
| CN113988124A (en) * | 2021-10-25 | 2022-01-28 | 武汉理工大学 | Fault diagnosis method and device for rotary mechanical equipment and electronic equipment |
| CN114201920A (en) * | 2021-12-15 | 2022-03-18 | 苏州华光智控电子科技有限公司 | Laser cutting numerical control system fault diagnosis method based on digital twinning and deep transfer learning |
| CN115292834A (en) * | 2022-07-20 | 2022-11-04 | 北自所(北京)科技发展股份有限公司 | Method, device and system for diagnosing faults of digital twin equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115700363A (en) | 2023-02-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111124840B (en) | Method and device for predicting alarm in business operation and maintenance and electronic equipment | |
| US11650968B2 (en) | Systems and methods for predictive early stopping in neural network training | |
| Shuai et al. | Hybrid software obsolescence evaluation model based on PCA-SVM-GridSearchCV | |
| JP2008536219A (en) | Diagnosis and prediction method and system | |
| CN116448419A (en) | Zero sample bearing fault diagnosis method based on depth model high-dimensional parameter multi-target efficient optimization | |
| US20210216386A1 (en) | Time-sequential data diagnosis device, additional learning method, and recording medium | |
| CN111325403B (en) | Method for predicting residual life of electromechanical equipment of highway tunnel | |
| CN115700363B (en) | Method and system for diagnosing faults of rolling bearing of coal mining machine, electronic equipment and storage medium | |
| Bao et al. | A Deep Transfer Learning Network for Structural Condition Identification with Limited Real‐World Training Data | |
| CN111079348B (en) | Method and device for detecting slowly-varying signal | |
| CN114444582A (en) | Mechanical equipment fault diagnosis method based on convolutional neural network and Bayesian network | |
| CN110750455B (en) | Intelligent online self-updating fault diagnosis method and system based on system log analysis | |
| CN114266278A (en) | Dual-attention-network-based method for predicting residual service life of equipment | |
| Ren et al. | Fault diagnosis of electric rudder based on self-organizing differential hybrid biogeography algorithm optimized neural network | |
| CN112668749B (en) | Coal mine gas early warning method based on class mark weighting extreme learning machine | |
| CN111400964B (en) | Fault occurrence time prediction method and device | |
| CN117407665A (en) | Retired battery time sequence data missing value filling method based on generation countermeasure network | |
| CN110348005B (en) | Distribution network equipment state data processing method and device, computer equipment and medium | |
| Guo et al. | Data mining and application of ship impact spectrum acceleration based on PNN neural network | |
| Li et al. | SRVM: A Similarity-based Relevance Vector Machine for Remaining Useful Lifetime Prediction in IIOT | |
| US20200380446A1 (en) | Artificial Intelligence Based Job Wages Benchmarks | |
| CN115292820A (en) | Method for predicting residual service life of urban rail train bearing | |
| Jiang | Research on software defect prediction technology based on deep learning | |
| Kumari et al. | Remaining useful life prediction using hybrid neural network and genetic algorithm approaches | |
| CN112560252A (en) | Prediction method for residual life of aircraft engine |
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 |