Disclosure of Invention
The present invention is directed to solving, at least to some extent, one of the technical problems in the art described above.
Therefore, an object of the present invention is to provide a fault prediction method for a coal mining machine, which is capable of performing fuzzification processing on target parameters of a monitoring signal set of the coal mining machine to generate a state representation of the monitoring signal set, inputting the state representation to a target fault prediction model, and outputting a prediction probability of the coal mining machine in each fault category by the target fault prediction model. Therefore, the fuzzy theory and the prediction model can be combined to realize the fault prediction of the coal mining machine, the prediction probability of various fault categories can be obtained, the fault prediction of the coal mining machine is more comprehensive, the operation safety of the coal mining machine is improved, and the personal safety of a user is guaranteed.
A second object of the present invention is to provide a failure prediction apparatus for a coal mining machine.
A third object of the invention is to propose an electronic device.
A fourth object of the invention is to propose a computer-readable storage medium.
The embodiment of the first aspect of the invention provides a fault prediction method for a coal mining machine, which comprises the following steps: acquiring target parameters of a monitoring signal set of a coal mining machine, wherein the monitoring signal set comprises a plurality of monitoring signals; fuzzification processing is carried out on the target parameters to generate state representation of the monitoring signal set; and inputting the state representation into a target fault prediction model, performing fault prediction on the coal mining machine by using the target fault prediction model, and outputting the prediction probability of the coal mining machine under each fault category.
According to the fault prediction method of the coal mining machine, the target parameters of the monitoring signal set of the coal mining machine can be fuzzified, the state representation of the monitoring signal set is generated, the state representation is input into the target fault prediction model, and the prediction probability of the coal mining machine under each fault category is output by the target fault prediction model. Therefore, the fuzzy theory and the prediction model can be combined to realize the fault prediction of the coal mining machine, the prediction probability of various fault categories can be obtained, the fault prediction of the coal mining machine is more comprehensive, the operation safety of the coal mining machine is improved, and the personal safety of a user is guaranteed.
In addition, the fault prediction method for the coal mining machine provided by the embodiment of the invention can also have the following additional technical characteristics:
in an embodiment of the present invention, the fuzzifying the target parameter to generate the state representation of the monitoring signal set includes: acquiring at least one preset membership grade and a membership function corresponding to each membership grade; inputting any target parameter to a membership function corresponding to any membership grade, and acquiring a membership value of the any target parameter under the any membership grade; generating a candidate state representation of any target parameter according to the membership value of any target parameter under each membership grade; generating a state representation of the set of monitored signals from the candidate state representation of each of the target parameters.
In one embodiment of the invention, the number of membership grade is 4.
In one embodiment of the invention, the membership function is a trapezoidal membership function.
In one embodiment of the invention, the method further comprises: acquiring a training sample set obtained based on a fuzzy rule, wherein the training sample set comprises a sample state representation of a sample monitoring signal set and a sample fault category of the coal mining machine corresponding to the sample monitoring signal set; and training a fault prediction model according to the training sample set until a model training end condition is reached, and generating the target fault prediction model.
In one embodiment of the invention, the method further comprises: inputting the training sample set into a model generator, wherein the model generator comprises models of different categories, and the score of each category of model corresponding to the training sample set is output by the model generator and is used for representing the performance of the model; and determining the type of the model corresponding to the maximum score as the type of the fault prediction model.
In one embodiment of the invention, the monitoring signal comprises at least one of temperature, current and voltage.
In one embodiment of the invention, the target parameter comprises at least one of a mean, a standard deviation, a crest factor, a barycentric frequency.
An embodiment of a second aspect of the present invention provides a failure prediction apparatus for a coal mining machine, including: the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring target parameters of a monitoring signal set of the coal mining machine, and the monitoring signal set comprises a plurality of monitoring signals; the fuzzy module is used for fuzzifying the target parameters to generate state representation of the monitoring signal set; and the prediction module is used for inputting the state representation into a target fault prediction model, performing fault prediction on the coal mining machine by using the target fault prediction model, and outputting the prediction probability of the coal mining machine under each fault category.
The fault prediction device of the coal mining machine provided by the embodiment of the invention can fuzzify the target parameters of the monitoring signal set of the coal mining machine, generate the state representation of the monitoring signal set, input the state representation into the target fault prediction model, and output the prediction probability of the coal mining machine under each fault category through the target fault prediction model. Therefore, the fuzzy theory and the prediction model can be combined to realize the fault prediction of the coal mining machine, the prediction probability of various fault categories can be obtained, the fault prediction of the coal mining machine is more comprehensive, the operation safety of the coal mining machine is improved, and the personal safety of a user is guaranteed.
In addition, the failure prediction device of the coal mining machine according to the above embodiment of the present invention may further have the following additional technical features:
in an embodiment of the present invention, the obfuscation module is further configured to: acquiring at least one preset membership grade and a membership function corresponding to each membership grade; inputting any target parameter to a membership function corresponding to any membership grade, and acquiring a membership value of the any target parameter under the any membership grade; generating a candidate state representation of any target parameter according to the membership value of any target parameter under each membership grade; generating a state representation of the set of monitored signals from the candidate state representation of each of the target parameters.
In one embodiment of the invention, the number of membership grade is 4.
In one embodiment of the invention, the membership function is a trapezoidal membership function.
In an embodiment of the present invention, the failure prediction apparatus of a coal mining machine further includes: a training module to: acquiring a training sample set obtained based on a fuzzy rule, wherein the training sample set comprises a sample state representation of a sample monitoring signal set and a sample fault category of the coal mining machine corresponding to the sample monitoring signal set; and training a fault prediction model according to the training sample set until a model training end condition is reached, and generating the target fault prediction model.
In an embodiment of the present invention, the training module is further configured to: inputting the training sample set into a model generator, wherein the model generator comprises models of different categories, and the score of each category of model corresponding to the training sample set is output by the model generator and is used for representing the performance of the model; and determining the type of the model corresponding to the maximum score as the type of the fault prediction model.
In one embodiment of the invention, the monitoring signal comprises at least one of temperature, current and voltage.
In one embodiment of the invention, the target parameter comprises at least one of a mean, a standard deviation, a crest factor, a barycentric frequency.
An embodiment of a third aspect of the present invention provides an electronic device, including: the system comprises a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to realize the method for predicting the fault of the coal mining machine according to the embodiment of the first aspect of the invention.
The electronic equipment of the embodiment of the invention can perform fuzzification processing on target parameters of a monitoring signal set of the coal mining machine by executing a computer program stored in a memory through a processor, generates state representation of the monitoring signal set, inputs the state representation into a target fault prediction model, and outputs the prediction probability of the coal mining machine under each fault category through the target fault prediction model. Therefore, the fuzzy theory and the prediction model can be combined to realize the fault prediction of the coal mining machine, the prediction probability of various fault categories can be obtained, the fault prediction of the coal mining machine is more comprehensive, the operation safety of the coal mining machine is improved, and the personal safety of a user is guaranteed.
An embodiment of a fourth aspect of the present application provides a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements a method for predicting a failure of a shearer according to an embodiment of the first aspect of the present invention.
The computer-readable storage medium of the embodiment of the invention can perform fuzzification processing on target parameters of a monitoring signal set of a coal mining machine by storing a computer program and executing the computer program by a processor, generates state representation of the monitoring signal set, inputs the state representation into a target fault prediction model, and outputs the prediction probability of the coal mining machine under each fault category by the target fault prediction model. Therefore, the fuzzy theory and the prediction model can be combined to realize the fault prediction of the coal mining machine, the prediction probability of various fault categories can be obtained, the fault prediction of the coal mining machine is more comprehensive, the operation safety of the coal mining machine is improved, and the personal safety of a user is guaranteed.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
The failure prediction method, the failure prediction apparatus, the electronic device, and the storage medium of the shearer according to the embodiments of the present invention are described below with reference to the accompanying drawings.
Fig. 1 is a schematic flow chart of a fault prediction method of a coal mining machine according to an embodiment of the present invention.
As shown in fig. 1, the method for predicting the failure of the coal mining machine according to the embodiment of the present invention includes:
s101, acquiring target parameters of a monitoring signal set of the coal mining machine, wherein the monitoring signal set comprises a plurality of monitoring signals.
In an embodiment of the invention, a monitoring signal set of the coal mining machine can be obtained, wherein the monitoring signal set comprises a plurality of monitoring signals. It should be noted that the type of the coal mining machine, the acquisition area of the monitoring signal and the type of the monitoring signal are not limited too much. In one embodiment, the shearer loader is a shearer loader, the collection area of the monitoring signal includes at least one of the drum, cutting unit, traction unit, loading unit, motor, etc. on the shearer, and the monitoring signal includes at least one of temperature, current, and voltage, for example, the monitoring signal may be drum temperature.
In one embodiment, the monitoring signal set may be acquired by installing sensors on the shearer. The sensor includes, but is not limited to, a temperature sensor, a current sensor, a voltage sensor, etc.
In one embodiment, monitoring signals of the shearer can be periodically acquired, and a monitoring signal set can be generated based on the acquired monitoring signals. The acquisition period may be set according to actual conditions, and is not limited herein, for example, it may be set to 2 seconds.
In the embodiment of the invention, after the monitoring signal set of the coal mining machine is obtained, the target parameters of the monitoring signal set can also be obtained. It should be noted that the type of the target parameter is not limited too much. In one embodiment, the target parameter includes at least one of a mean, a standard deviation, a crest factor, and a barycentric frequency.
For example, the set of monitoring signals is I ═ { I ═ I1,I2,I3……InIn the time of the preceding step, the number of the monitoring signals in the monitoring signal set is n, where n is a natural number, and the obtaining of the target parameter of the monitoring signal set I can be achieved by the following formula:
where μ is the mean, σ is the standard deviation, c
fIn order to be the peak value factor,
for the barycentric frequency, max (-) is the function of the maximum.
And S102, fuzzifying the target parameters to generate state representation of the monitoring signal set.
In the embodiment of the present invention, the specific manner of the fuzzification processing is not limited too much, and the fuzzification processing may be performed in a membership function, a threshold, and the like.
In one embodiment, the fuzzifying the target parameter may include obtaining a membership grade of the target parameter according to a magnitude relationship between the target parameter and a threshold.
Optionally, the number of membership grades is 4, which may include smaller, normal, larger, and larger.
Accordingly, the number of thresholds may be 3, and may include a first threshold, a second threshold, and a third threshold. The first threshold is smaller than the second threshold, and the second threshold is smaller than the third threshold. It is understood that the first threshold, the second threshold, and the third threshold can be set according to practical situations, and are not limited herein.
Optionally, obtaining the membership grade of the target parameter according to the magnitude relationship between the target parameter and the threshold may include identifying that the target parameter is smaller than or equal to a first threshold, and obtaining the membership grade of the target parameter is smaller, or identifying that the target parameter is greater than the first threshold and smaller than or equal to a second threshold, and obtaining the membership grade of the target parameter is normal, or identifying that the target parameter is greater than the second threshold and smaller than or equal to a third threshold, and obtaining the membership grade of the target parameter is larger, or identifying that the target parameter is greater than the third threshold, and obtaining the membership grade of the target parameter is larger.
In the embodiment of the invention, after the target parameter is fuzzified, the state representation of the monitoring signal set can be generated according to the fuzzification processing result. The form of the state representation is not limited to a large number, and may be a number, for example.
In one embodiment, the state representation corresponding to each target parameter may be generated according to the membership grade corresponding to the target parameter, and further, the state representation of the monitoring signal set may be generated according to the state representation corresponding to each target parameter.
Optionally, the membership grade may include smaller, normal, larger, and larger, the state corresponding to each target parameter is represented as a 4-bit state bit composed of 0 or 1, the states that the target parameter belongs to the states that the membership grade is smaller, normal, larger, and larger are sequentially represented from left to right, the state bit value of 0 represents that the target parameter does not belong to the membership grade corresponding to the state bit, and the state bit value of 1 represents that the target parameter belongs to the membership grade corresponding to the state bit. For example, if the degree of membership of a certain target parameter is smaller, the state corresponding to the target parameter is represented as 1000.
Correspondingly, the state of the monitoring signal set is represented as 16-bit state bits consisting of 0 or 1, and from left to right, each 4-bit state bits are represented as states corresponding to the average value, the standard deviation, the peak factor and the barycentric frequency. For example, if the membership level corresponding to the average value, the standard deviation, the crest factor, and the center of gravity frequency is small, normal, and normal, respectively, and the status indications corresponding to the average value, the standard deviation, the crest factor, and the center of gravity frequency are 1000, 0100, and 0100, respectively, the status indication of the monitoring signal set may be 1000100001000100.
S103, inputting the state representation into a target fault prediction model, performing fault prediction on the coal mining machine by using the target fault prediction model, and outputting the prediction probability of the coal mining machine under each fault category.
In the embodiment of the present invention, the target failure prediction model may be set according to an actual situation, which is not limited herein, and may be set as a Neural Network (NNS) model, for example.
In the embodiment of the present invention, the failure category may be set according to actual conditions, and is not limited herein, for example, the failure category includes, but is not limited to, abnormal temperature, excessive noise, excessive vibration intensity, slow drum rotation speed, communication failure, and the like.
In one embodiment, after the predicted probabilities of the shearer under each fault category are output, an early warning signal for warning a user of the safety state of the shearer may be generated in response to at least one of the predicted probabilities being greater than a preset probability threshold. The preset probability threshold may be set according to actual situations, and is not limited herein, and may be set to 70%, for example. It should be noted that the type of the warning signal is not limited too much, for example, the warning signal includes, but is not limited to, a light signal, a voice signal, a text signal, and the like.
In summary, according to the fault prediction method for the coal mining machine provided by the embodiment of the invention, the target parameters of the monitoring signal set of the coal mining machine can be fuzzified to generate the state representation of the monitoring signal set, the state representation is input into the target fault prediction model, and the prediction probability of the coal mining machine under each fault category is output by the target fault prediction model. Therefore, the fuzzy theory and the prediction model can be combined to realize the fault prediction of the coal mining machine, the prediction probability of various fault categories can be obtained, the fault prediction of the coal mining machine is more comprehensive, the operation safety of the coal mining machine is improved, and the personal safety of a user is guaranteed.
On the basis of any of the above embodiments, as shown in fig. 2, the step S102 of performing fuzzification processing on the target parameter to generate a state representation of the monitoring signal set includes:
s201, obtaining at least one preset membership grade and a membership function corresponding to each membership grade.
In the embodiment of the invention, the membership grade and the corresponding membership function can be set according to actual conditions.
In one embodiment, the number of membership levels is 4, which may include small, normal, large.
In one embodiment, the membership function is a trapezoidal membership function.
For example, the membership function with the membership grade of smaller, normal, larger and larger is fJS(x)、fJN(x)、fJM(x)、fJB(x),fJS(x)、fJN(x)、fJM(x)、fJB(x) The corresponding equations are as follows:
wherein, a0、a1、a2、a3、b0、b1、b2、b3、c1、c2、d1、d2Are all parameters which can be set according to actual conditions, and 0<a0<b0,a1<b1<c1<d1,a2<b2<c2<d2,a3<b3。
In one embodiment, 0<a1<a0<b0<b1<c1<a2<d1<b2<a3<c2<b3<d2Membership grade is a membership function f corresponding to smaller, normal, larger and larger membership gradeJS(x)、fJN(x)、fJM(x)、fJB(x) Is shown in figure 3.
S202, inputting any target parameter to a membership function corresponding to any membership grade, and acquiring a membership value of any target parameter at any membership grade.
In the embodiment of the present invention, any target parameter may be input to the membership function corresponding to any membership grade, and the membership value of any target parameter at any membership grade is obtained, so that the number of the membership values corresponding to any target parameter is the number of the membership functions (i.e. the number of the membership grades). For example, the membership grade is a membership function f corresponding to smaller, normal, larger and larger membership gradeJS(x)、fJN(x)、fJM(x)、fJB(x) Then a certain target parameter may be input to f in sequenceJS(x)、fJN(x)、fJM(x)、fJB(x) And obtaining the membership grade of the target parameter which is smaller, normal, larger or larger.
It is understood that a smaller degree of membership indicates that the target parameter belongs to a lower degree of membership grade, and a larger degree of membership indicates that the target parameter belongs to a higher degree of membership grade.
Continuing to use the membership function as fJS(x)、fJN(x)、fJM(x)、fJB(x) For example, it can be seen that the membership value ranges from 0 to 1. The closer the membership value is to 0, the lower the degree of the target parameter belonging to the membership grade, and the closer the membership value is to 1, the higher the degree of the target parameter belonging to the membership grade.
For example, the average value, standard deviation, peak factor, and barycentric frequency may be input to fJS(x)、fJN(x)、fJM(x)、fJB(x) The obtained average values are respectively 0.5, 0 and 0 in the membership grade, the obtained standard deviation is respectively 1, 0.2, 0 and 0 in the membership grade, the obtained peak value factors are respectively 0, 1, 0 and 0 in the membership grade, and the obtained gravity center frequency is respectively 0, 0 and 1 in the membership grade.
And S203, generating a candidate state representation of any target parameter according to the membership value of any target parameter under each membership grade.
In one embodiment, the membership values of any one target parameter at each membership level may be combined to generate a candidate state representation of any one target parameter.
In one embodiment, the membership level may include smaller, normal, larger, continuing with the membership function as fJS(x)、fJN(x)、fJM(x)、fJB(x) For example, it can be seen that the membership value ranges from 0 to 1. Correspondingly, the candidate state corresponding to each target parameter is represented as a 4-bit state composed of 0 to 1And the value of each state bit is a membership value, and the target parameters belong to the states with smaller, normal, larger and larger membership grades from left to right in sequence. For example, if the membership degree of a certain target parameter is smaller, normal, larger, and the membership degree values are 0.5, 0, and 0, respectively, the candidate state corresponding to the target parameter is represented as 0.50.500.
S204, generating the state representation of the monitoring signal set according to the candidate state representation of each target parameter.
In one embodiment, the candidate state representations for each target parameter may be combined to generate a state representation of the monitoring signal set.
Optionally, the state of the monitoring signal set is represented by 16-bit state bits composed of 0 to 1, and each 4-bit state bits from left to right are represented by candidate states corresponding to an average value, a standard deviation, a peak factor, and a barycentric frequency. For example, if the candidate state representations corresponding to the mean, standard deviation, crest factor, and barycentric frequency are 0.50.500, 10.200, 0100, and 0001, respectively, the state representation of the monitor signal set may be 0.50.50010.20001000001.
Therefore, any target parameter can be input to the membership function corresponding to any membership grade, the membership value of any target parameter in any membership grade is obtained, the candidate state representation of any target parameter is generated according to the membership value of any target parameter in each membership grade, and the state representation of the monitoring signal set is generated according to the candidate state representation of each target parameter.
On the basis of any of the above embodiments, as shown in fig. 4, the obtaining of the target failure prediction model in step S103 includes:
s401, a training sample set obtained based on a fuzzy rule is obtained, wherein the training sample set comprises a sample state representation of a sample monitoring signal set and a sample fault category of a coal mining machine corresponding to the sample monitoring signal set.
In an embodiment of the invention, the training sample set comprises a plurality of sample state representations and their corresponding sample failure classes.
In embodiments of the invention, the fuzzy rules may include rules on how to generate sample fault classes based on the sample state representation. In one embodiment, the fuzzy rule can be set manually, for example, the fuzzy rule can be established according to the fault experience of the coal mining machine.
In one embodiment, acquiring a training sample set obtained based on a fuzzy rule may include acquiring sample state representations, acquiring sample state representations corresponding to the sample state representations based on the fuzzy rule, regarding each sample state representation and its corresponding sample fault class as a set of training samples, and generating the training sample set based on a plurality of sets of training samples.
S402, training the fault prediction model according to the training sample set until the model training end condition is reached, and generating the target fault prediction model.
In the embodiment of the invention, the model training end condition can be set according to the actual situation, and is not limited too much here. For example, the model training ending condition includes, but is not limited to, the model precision reaching a preset precision threshold, the number of times of model training reaching a preset number threshold, and the like.
In one embodiment, the sample state representation may be input to the fault prediction model, the fault prediction model outputs a sample prediction probability of the coal mining machine under each fault category, the corresponding sample fault category is represented based on the sample prediction probability under each fault category and the sample state, the fault prediction model is trained until a model training end condition is reached, and the fault prediction model obtained by the last training is used as a target fault prediction model.
Therefore, the method can obtain the training sample set obtained based on the fuzzy rule, a large amount of sample data can be obtained without performing a fault experiment of the coal mining machine, the difficulty of obtaining the sample data is reduced, the method is beneficial to obtaining the large amount of sample data, the fault prediction model is trained by using the training sample set to generate the target fault prediction model, and the method is beneficial to improving the model training precision.
On the basis of any one of the above embodiments, the obtaining of the category of the fault prediction model includes inputting a training sample set into a model generator, where the model generator includes models of different categories, outputting, by the model generator, a score of the model of each category corresponding to the training sample set, where the score is used to characterize performance of the model, and determining the category of the model corresponding to the largest score as the category of the fault prediction model.
It is understood that a higher score characterizes better model performance.
In one embodiment, the score of the model may include a score of a plurality of evaluation indexes, wherein the evaluation indexes may be set according to actual conditions, such as, but not limited to, accuracy, robustness, and the like.
In one embodiment, determining the category of the model corresponding to the maximum score as the category of the fault prediction model may include obtaining a score and a value of at least one target evaluation index of the model, and determining the category of the model corresponding to the maximum score and the value as the category of the fault prediction model. Wherein, the target evaluation index can be set according to the actual situation. Therefore, the method can determine the type of the fault prediction model according to the maximum score of the partial evaluation index of the model and the type of the model corresponding to the value.
In one embodiment, the class of fault prediction models is the standard Maximum Entropy multivariate (Sdca Maximum Entropy index Multi) model.
Therefore, the method can obtain the grade of the model of each category through the model generator, determine the category of the model corresponding to the maximum grade as the category of the fault prediction model, realize the selection of the category of the fault prediction model through the model generator, realize the rapid determination of the category of the fault prediction model, and contribute to the acceleration of the training speed of the fault prediction model.
In order to realize the embodiment, the invention further provides a fault prediction device of the coal mining machine.
Fig. 5 is a schematic structural diagram of a fault prediction apparatus of a shearer according to an embodiment of the present invention.
As shown in fig. 5, a failure prediction apparatus 100 of a coal mining machine according to an embodiment of the present invention includes: an acquisition module 110, a blur module 120, and a prediction module 130.
The acquisition module 110 is configured to acquire a target parameter of a monitoring signal set of a coal mining machine, where the monitoring signal set includes a plurality of monitoring signals;
the fuzzy module 120 is configured to perform fuzzification processing on the target parameter to generate a state representation of the monitoring signal set;
the prediction module 130 is configured to input the state representation into a target fault prediction model, perform fault prediction on the coal mining machine by using the target fault prediction model, and output a prediction probability of the coal mining machine under each fault category.
In one embodiment of the present invention, the obfuscation module 120 is further configured to: acquiring at least one preset membership grade and a membership function corresponding to each membership grade; inputting any target parameter to a membership function corresponding to any membership grade, and acquiring a membership value of the any target parameter under the any membership grade; generating a candidate state representation of any target parameter according to the membership value of any target parameter under each membership grade; generating a state representation of the set of monitored signals from the candidate state representation of each of the target parameters.
In one embodiment of the invention, the number of membership grade is 4.
In one embodiment of the invention, the membership function is a trapezoidal membership function.
In an embodiment of the present invention, the failure prediction apparatus of a coal mining machine further includes: a training module to: acquiring a training sample set obtained based on a fuzzy rule, wherein the training sample set comprises a sample state representation of a sample monitoring signal set and a sample fault category of the coal mining machine corresponding to the sample monitoring signal set; and training a fault prediction model according to the training sample set until a model training end condition is reached, and generating the target fault prediction model.
In an embodiment of the present invention, the training module is further configured to: inputting the training sample set into a model generator, wherein the model generator comprises models of different categories, and the score of each category of model corresponding to the training sample set is output by the model generator and is used for representing the performance of the model; and determining the type of the model corresponding to the maximum score as the type of the fault prediction model.
In one embodiment of the invention, the monitoring signal comprises at least one of temperature, current and voltage.
In one embodiment of the invention, the target parameter comprises at least one of a mean, a standard deviation, a crest factor, a barycentric frequency.
It should be noted that details that are not disclosed in the fault prediction apparatus of the coal mining machine according to the embodiment of the present invention refer to details that are disclosed in the fault prediction method of the coal mining machine according to the embodiment of the present invention, and are not described herein again.
To sum up, the fault prediction apparatus for a coal mining machine according to the embodiment of the present invention can perform fuzzification processing on target parameters of a monitoring signal set of the coal mining machine to generate a state representation of the monitoring signal set, input the state representation to a target fault prediction model, and output a prediction probability of the coal mining machine in each fault category by the target fault prediction model. Therefore, the fuzzy theory and the prediction model can be combined to realize the fault prediction of the coal mining machine, the prediction probability of various fault categories can be obtained, the fault prediction of the coal mining machine is more comprehensive, the operation safety of the coal mining machine is improved, and the personal safety of a user is guaranteed.
In order to implement the above embodiment, as shown in fig. 6, an embodiment of the present invention provides an electronic device 200, including: the fault prediction method of the shearer comprises a memory 210, a processor 220 and a computer program which is stored on the memory 210 and can run on the processor 220, wherein when the processor 220 executes the program, the fault prediction method of the shearer is realized.
The electronic equipment of the embodiment of the invention can perform fuzzification processing on target parameters of a monitoring signal set of the coal mining machine by executing a computer program stored in a memory through a processor, generates state representation of the monitoring signal set, inputs the state representation into a target fault prediction model, and outputs the prediction probability of the coal mining machine under each fault category through the target fault prediction model. Therefore, the fuzzy theory and the prediction model can be combined to realize the fault prediction of the coal mining machine, the prediction probability of various fault categories can be obtained, the fault prediction of the coal mining machine is more comprehensive, the operation safety of the coal mining machine is improved, and the personal safety of a user is guaranteed.
In order to implement the above embodiments, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the method for predicting a failure of a coal mining machine as described above.
The computer-readable storage medium of the embodiment of the invention can perform fuzzification processing on target parameters of a monitoring signal set of a coal mining machine by storing a computer program and executing the computer program by a processor, generates state representation of the monitoring signal set, inputs the state representation into a target fault prediction model, and outputs the prediction probability of the coal mining machine under each fault category by the target fault prediction model. Therefore, the fuzzy theory and the prediction model can be combined to realize the fault prediction of the coal mining machine, the prediction probability of various fault categories can be obtained, the fault prediction of the coal mining machine is more comprehensive, the operation safety of the coal mining machine is improved, and the personal safety of a user is guaranteed.
In the description of the present invention, it is to be understood that the terms "central," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," "circumferential," and the like are used in the orientations and positional relationships indicated in the drawings for convenience in describing the invention and to simplify the description, and are not intended to indicate or imply that the referenced device or element must have a particular orientation, be constructed and operated in a particular orientation, and are not to be considered limiting of the invention.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
In the present invention, unless otherwise expressly stated or limited, the terms "mounted," "connected," "secured," and the like are to be construed broadly and can, for example, be fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; either directly or indirectly through intervening media, either internally or in any other relationship. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
In the present invention, unless otherwise expressly stated or limited, the first feature "on" or "under" the second feature may be directly contacting the first and second features or indirectly contacting the first and second features through an intermediate. Also, a first feature "on," "over," and "above" a second feature may be directly or diagonally above the second feature, or may simply indicate that the first feature is at a higher level than the second feature. A first feature being "under," "below," and "beneath" a second feature may be directly under or obliquely under the first feature, or may simply mean that the first feature is at a lesser elevation than the second feature.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.