CN112418474A

CN112418474A - Method and device for predicting fault handling deadline

Info

Publication number: CN112418474A
Application number: CN201910770125.5A
Authority: CN
Inventors: 李金诺
Original assignee: Beijing Gridsum Technology Co Ltd
Current assignee: Beijing Gridsum Technology Co Ltd
Priority date: 2019-08-20
Filing date: 2019-08-20
Publication date: 2021-02-26

Abstract

The application discloses a method and a device for predicting a fault handling deadline. The preset prediction model is obtained by training according to the historical equipment parameters and the historical fault handling time limit corresponding to the historical equipment parameters, so that after the current equipment parameters are input into the preset prediction model, the preset prediction model can accurately predict the fault handling time limit of the target equipment without the participation of maintenance personnel, the occurrence of determining the wrong fault handling time limit due to human errors is avoided, the accuracy of the fault handling time limit is improved, the equipment can be maintained in time, and the safety of the equipment is improved.

Description

Method and device for predicting fault handling deadline

Technical Field

The present application relates to the field of big data technologies, and in particular, to a method and an apparatus for predicting a failure handling deadline.

Background

At present, due to time-consuming fault maintenance of oilfield equipment (e.g., power equipment such as pumps, compressors, and fans), when multiple pieces of oilfield equipment need to be subjected to fault maintenance, the multiple pieces of oilfield equipment generally need to be subjected to scheduled maintenance. The planned maintenance means that when a plurality of devices are subjected to failure early warning, a failure processing period needs to be reasonably arranged for each failed device so that a subsequent maintenance worker can maintain the failed device within the failure processing period. The fault handling deadline is a time interval between an occurrence time point of equipment fault early warning and an occurrence time point of equipment which cannot work due to fault damage. For example, if a target device is failure-early-warned in 1/10: 30 in 2019 and the target device is unable to work due to failure damage in 1/8/10: 30 in 2019, the failure processing period of the target device is 7 days between 1/10: 30 in 2019 and 8/10: 30 in 2019.

However, the failure handling deadlines for different failure devices are different; furthermore, in the prior art, the fault handling deadline corresponding to each faulty equipment is usually determined by an experienced service person by looking at the equipment on site, which results in a high requirement for the service person determining the fault handling deadline. In addition, because the failure handling time limit is determined manually, the subjectivity of the failure handling time limit determination process is high, and the error failure handling time limit is easily determined due to human errors (for example, due to insufficient experience or incomplete consideration factors), so that the equipment is damaged due to failure or even explodes due to untimely maintenance of the equipment.

Disclosure of Invention

In order to solve the technical problems in the prior art, the application provides a method and a device for predicting a fault handling deadline, which can accurately determine the fault handling deadline of a fault device, do not need maintenance personnel to participate, avoid the occurrence of determining a wrong fault handling deadline due to human errors, improve the accuracy of the fault handling deadline, enable the device to be maintained in time, and improve the safety of the device.

In order to achieve the above purpose, the technical solutions provided in the embodiments of the present application are as follows:

the embodiment of the application provides a method for predicting a fault handling deadline, which comprises the following steps:

after receiving fault early warning information of target equipment, acquiring current equipment parameters of the target equipment; the current equipment parameters comprise at least one of working condition parameters, fault alarm parameters and equipment performance parameters;

predicting the fault handling time limit of the target equipment by using a preset prediction model according to the current equipment parameters to obtain the fault handling time limit of the target equipment; the preset prediction model is obtained by training according to historical equipment parameters and historical fault processing time limit corresponding to the historical equipment parameters.

Optionally, the preset prediction model includes at least one of a convolutional neural network model CNN, a recurrent neural network model RNN, a deep neural network model DNN, a random forest model, and a support vector machine SVM.

Optionally, the operating condition parameter includes at least one of a frequency spectrum, a current, a voltage, a flow rate, and a temperature;

and/or the presence of a gas in the gas,

the fault alarm parameters comprise at least one of fault types, alarm types, total values of fault alarm quantities and total values of alarm quantities;

and/or the presence of a gas in the gas,

the device performance parameters include at least one of device age and device component aging parameters.

Optionally, the training process of the preset prediction model specifically includes:

acquiring historical equipment parameters and historical fault processing time limit corresponding to the historical equipment parameters; the historical device parameters include: historical device parameters of the target device and/or historical device parameters of other devices of the same type as the target device;

and training an initial prediction model by using the historical equipment parameters and the historical fault processing time limit corresponding to the historical equipment parameters to obtain a preset prediction model.

Optionally, the method further includes:

and updating the preset prediction model according to the current equipment parameters of the target equipment and the fault processing time limit of the target equipment.

Optionally, the method further includes:

acquiring fault analysis information of the target equipment;

the updating the preset prediction model according to the current device parameter of the target device and the fault handling deadline of the target device specifically includes:

and updating the preset prediction model according to the current equipment parameters of the target equipment, the fault processing deadline of the target equipment and the fault analysis information of the target equipment.

Optionally, the method further includes:

after the target equipment is maintained, acquiring maintenance information of the target equipment;

and updating the preset prediction model according to the current equipment parameters of the target equipment, the fault processing deadline of the target equipment and the maintenance information of the target equipment.

An embodiment of the present application further provides a device for predicting a failure handling deadline, including:

the device parameter acquiring unit is used for acquiring the current device parameters of the target device after receiving the fault early warning information of the target device; the current equipment parameters comprise at least one of working condition parameters, fault alarm parameters and equipment performance parameters;

the processing time limit predicting unit is used for predicting the fault processing time limit of the target equipment by using a preset predicting model according to the current equipment parameters to obtain the fault processing time limit of the target equipment; the preset prediction model is obtained by training according to historical equipment parameters and historical fault processing time limit corresponding to the historical equipment parameters.

An embodiment of the present application further provides a storage medium, where the storage medium includes a stored program, and the program executes any one of the above-described methods for predicting a failure handling deadline.

The embodiment of the present application further provides a processor, where the processor is configured to execute a program, where the program executes any one of the above embodiments of the method for predicting a failure handling deadline when running.

Compared with the prior art, the embodiment of the application has at least the following advantages:

according to the method for predicting the fault handling time limit provided by the embodiment of the application, after fault early warning information of the target equipment is received, current equipment parameters of the target equipment are firstly obtained, and then the fault handling time limit of the target equipment is predicted by using a preset prediction model according to the current equipment parameters, so that the fault handling time limit of the target equipment is obtained. The preset prediction model is obtained by training according to the historical equipment parameters and the historical fault handling time limit corresponding to the historical equipment parameters, so that after the current equipment parameters are input into the preset prediction model, the preset prediction model can accurately predict the fault handling time limit of the target equipment without the participation of maintenance personnel, the occurrence of determining the wrong fault handling time limit due to human errors is avoided, the accuracy of the fault handling time limit is improved, the equipment can be maintained in time, and the safety of the equipment is improved.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art without creative efforts.

Fig. 1 is a flowchart of a method for predicting a failure handling deadline according to an embodiment of the present application;

fig. 2 is a flowchart of a training process of a preset prediction model according to an embodiment of the present disclosure;

fig. 3 is a flowchart of a method for predicting a failure handling deadline according to an embodiment of the present application;

fig. 4 is a flowchart of another method for predicting a failure handling deadline according to an embodiment of the present application;

fig. 5 is a flowchart of another method for predicting a failure handling deadline according to an embodiment of the present application;

fig. 6 is a flowchart of a method for predicting a failure handling deadline according to an embodiment of the present application;

fig. 7 is a schematic structural diagram of a failure handling deadline prediction apparatus according to an embodiment of the present application;

fig. 8 is a schematic structural diagram of an apparatus provided in an embodiment of the present application.

Detailed Description

In order to solve the technical problem in the background art, an embodiment of the present application provides a method for predicting a failure handling deadline, including: after receiving fault early warning information of target equipment, acquiring current equipment parameters of the target equipment; predicting the fault handling time limit of the target equipment by using a preset prediction model according to the current equipment parameters to obtain the fault handling time limit of the target equipment; the current equipment parameters comprise at least one of working condition parameters, fault alarm parameters and equipment performance parameters; the preset prediction model is obtained by training according to the historical equipment parameters and the historical fault processing time limit corresponding to the historical equipment parameters.

According to the method for predicting the fault handling time limit provided by the embodiment of the application, after fault early warning information of the target equipment is received, current equipment parameters of the target equipment are firstly obtained, and then the fault handling time limit of the target equipment is predicted by using a preset prediction model according to the current equipment parameters, so that the fault handling time limit of the target equipment is obtained. The preset prediction model is obtained by training according to the historical equipment parameters and the historical fault handling time limit corresponding to the historical equipment parameters, so that after the current equipment parameters are input into the preset prediction model, the preset prediction model can accurately predict the fault handling time limit of the target equipment without the participation of maintenance personnel, the occurrence of determining the wrong fault handling time limit due to human errors is avoided, the accuracy of the fault handling time limit is improved, the equipment can be maintained in time, the equipment is prevented from being damaged or even exploded due to faults caused by untimely maintenance, and the safety of the equipment is improved.

In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

Method embodiment one

Referring to fig. 1, a flowchart of a method for predicting a failure handling deadline according to an embodiment of the present application is shown.

The method for predicting the fault handling deadline provided by the embodiment of the application comprises the following steps of S11-S12:

s11: and after receiving the fault early warning information of the target equipment, acquiring the current equipment parameters of the target equipment.

The target equipment refers to equipment needing fault processing; furthermore, the target device is not limited in the embodiments of the present application, for example, the target device may be any kind of mobile device, where the mobile device may be a rotating device driven by a driving machine, such as a pump, a compressor, or a fan.

The failure early warning information is information for performing early warning prompt aiming at a failure to be generated by the target equipment before the failure is generated by the target equipment. It should be noted that after receiving the failure early warning information of the target device, it indicates that the target device is about to fail, and it is necessary to perform failure processing on the target device in time, so as to prevent the target device from failing to work or even exploding due to a failure.

The current equipment parameters are used for representing equipment related parameters of the target equipment at the current moment; moreover, the embodiment of the present application does not limit the specific content of the current device parameter, for example, the current device parameter may include at least one of an operating condition parameter, a fault alarm parameter, and a device performance parameter.

The working condition parameters are used for representing the working state information of the target equipment at the current moment; moreover, the embodiments of the present application do not limit the specific content of the operating condition parameters, for example, the operating condition parameters may include at least one of frequency spectrum, current, voltage, flow rate, and temperature.

The fault alarm parameters are used for representing the fault related information and the alarm related information of the target equipment at the current moment; moreover, the specific content of the fault alarm parameter is not limited in the embodiments of the present application, for example, the fault alarm parameter may include at least one of a fault type, an alarm type, a total value of the number of fault alarms, and a total value of the number of alarm alarms.

The equipment performance parameters are used for representing the service performance of the target equipment at the current moment; moreover, the embodiment of the present application does not limit the specific content of the device performance parameter, for example, the device performance parameter includes at least one of the age of the device and the aging degree of the device component.

In addition, the embodiment of the present application does not limit the obtaining manner of the current device parameters, for example, after the data signals are collected by various collecting devices installed on the target device and various collecting devices (that is, self-test devices in the target device) configured in the target device from the factory, the collected data signals may be sent to the processing device executing the method for predicting the failure processing deadline provided in the embodiment of the present application according to a preset manner, or the data signals may be directly obtained from the collecting devices by the processing device executing the method for predicting the failure processing deadline provided in the embodiment of the present application, or the data signals may be directly obtained from the storage device storing the collected data signals by the processing device executing the method for predicting the failure processing deadline provided in the embodiment of the present application. The preset mode may be a communication mode, for example, a wireless communication mode or a wired communication mode.

It should be noted that, this embodiment of the present application further provides a communication link for acquiring data from a self-test device, where the communication link includes a sensor (i.e., a self-test device in a target device) → a Remote Terminal Unit (RTU) → a Programmable Logic Controller (PLC) → a Distributed Control System (DCS) → a processing device that executes the method for predicting a failure handling deadline provided in this embodiment of the present application.

The above is the content related to step S11.

S12: and predicting the fault handling time limit of the target equipment by using a preset prediction model according to the current equipment parameters to obtain the fault handling time limit of the target equipment.

In the embodiment of the application, after the current device parameter is obtained, the current device parameter may be input into the preset prediction model, so that the preset prediction model can predict the fault handling deadline of the target device according to the current device parameter, thereby obtaining the fault handling deadline of the target device, so that a subsequent device maintenance worker can complete maintenance and treatment on the target device within the fault handling deadline, and the target device is prevented from being damaged or even exploded due to faults because of untimely maintenance of the target device, thereby ensuring the safety of the target device.

In the embodiment of the application, the preset prediction model is obtained by training according to historical equipment parameters and historical fault processing time limit corresponding to the historical equipment parameters; in addition, the execution time of training the preset prediction model is not limited in the embodiment of the present application, and the preset prediction model only needs to be trained before executing step S12.

In addition, the embodiment of the present application further provides a training process of the preset prediction model, which is explained and explained below with reference to fig. 2.

Referring to fig. 2, it is a flowchart of a training process of the predictive model according to an embodiment of the present disclosure.

The training process of the preset prediction model provided by the embodiment of the application comprises the following steps of S21-S22:

s21: and acquiring historical equipment parameters and historical fault processing time limit corresponding to the historical equipment parameters.

The historical device parameters are used for representing the device-related historical parameters before the current moment; moreover, the specific content of the historical device parameters is not limited in the embodiments of the present application, for example, the historical device parameters may include at least one of historical operating condition parameters, historical fault alarm parameters, and historical device performance parameters.

In addition, the data source of the historical device parameters is not limited in the embodiment of the application, the historical device parameters can be provided by the target device, and at this time, the historical device parameters include the historical device parameters of the target device; the historical device parameters may also be provided by other devices of the same type as the target device, and in this case, the historical device parameters include historical device parameters of other devices of the same type as the target device; the historical device parameters may also be provided by the target device and other devices of the same type as the target device, and in this case, the historical device parameters include: historical device parameters of the target device and historical device parameters of other devices of the same type as the target device.

The historical fault processing time limit corresponding to the historical equipment parameters is used for recording reasonable time limit information for carrying out fault processing on the equipment with the historical equipment parameters before the current moment; moreover, for the equipment with historical equipment parameters, as long as fault processing is completed within the historical fault processing period, the equipment can be prevented from being incapable of working or even exploding due to fault occurrence.

It should be noted that, in the embodiment of the present application, a source of a historical failure handling deadline corresponding to a historical device parameter is not limited, for example, the historical failure handling deadline corresponding to the historical device parameter may be obtained from a device failure handling record in an actual application process, may also be obtained by prediction of a prediction model, and may also be provided by an experienced maintenance person.

S22: and training the initial prediction model by using the historical equipment parameters and the historical fault processing time limit corresponding to the historical equipment parameters to obtain a preset prediction model.

The initial prediction model is a prediction model needing to be trained; moreover, the embodiments of the present application do not limit the specific implementation of the initial prediction model, for example, the initial prediction model may be a prediction model without any training, or may be a prediction model after at least one round of training.

In the embodiment of the application, after the historical device parameters and the historical fault handling time limit corresponding to the historical device parameters are obtained, the initial prediction model can be trained by using the historical device parameters and the historical fault handling time limit corresponding to the historical device parameters, so that the preset prediction model is obtained. Wherein the training targets of the training process are: and the difference between the predicted fault handling time limit obtained by prediction of the prediction model according to the historical equipment parameters and the historical fault handling time limit corresponding to the historical equipment parameters is lower than a preset difference value, namely, the predicted fault handling time limit can approach to the maximum extent and even reach the historical fault handling time limit corresponding to the historical equipment parameters. The preset difference value is preset, and especially can be set according to an application scene.

The above is the relevant content of the training process of the preset prediction model provided in the embodiment of the present application.

In addition, the embodiment of the present application does not limit the model structure of the preset prediction model, for example, the preset prediction model includes at least one of a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), a Deep Neural Network (DNN), a random forest model, and a Support Vector Machine (SVM).

The above is the content related to step S12.

In this embodiment, after receiving the failure warning information of the target device, the current device parameter of the target device is obtained, and then the failure handling deadline of the target device is predicted by using a preset prediction model according to the current device parameter, so as to obtain the failure handling deadline of the target device. The preset prediction model is obtained by training according to the historical equipment parameters and the historical fault handling time limit corresponding to the historical equipment parameters, so that after the current equipment parameters are input into the preset prediction model, the preset prediction model can accurately predict the fault handling time limit of the target equipment without the participation of maintenance personnel, the occurrence of determining the wrong fault handling time limit due to human errors is avoided, the accuracy of the fault handling time limit is improved, the equipment can be maintained in time, and the safety of the equipment is improved.

In addition, in order to improve the prediction accuracy of the fault handling deadline, the preset prediction model may be updated by using the current device parameter of the target device and/or other parameters of the target device, so that the updated preset prediction model can more accurately predict the fault handling deadline of the target device. Thus, the embodiment of the present application also provides another implementation of the method for predicting the failure handling deadline, which is explained and explained below with reference to the drawings.

Method embodiment two

For the sake of brevity, the same parts in the first method embodiment and the second method embodiment are not described again.

Referring to fig. 3, it is a flowchart of a method for predicting a failure handling deadline according to an embodiment of the present application.

The method for predicting the fault handling deadline provided by the embodiment of the application comprises the following steps of S31-S33:

s31: and after receiving the fault early warning information of the target equipment, acquiring the current equipment parameters of the target equipment.

It should be noted that step S31 may be implemented by any implementation manner of step S11, and for brevity, details are not repeated here, and please refer to step S11 of the first method embodiment for technical details.

S32: and predicting the fault handling time limit of the target equipment by using a preset prediction model according to the current equipment parameters to obtain the fault handling time limit of the target equipment.

It should be noted that step S32 may be implemented by any implementation manner of step S12, and for brevity, details are not repeated here, and please refer to step S12 of the first method embodiment for technical details.

S33: and updating the preset prediction model according to the current equipment parameters of the target equipment and the fault processing time limit of the target equipment.

In this embodiment of the present application, when updating the preset prediction model according to the current device parameter of the target device and the fault handling deadline of the target device, first, the training data of the preset prediction model needs to be updated by using the current device parameter of the target device and the fault handling deadline of the target device, and at this time, the training data may include the current device parameter of the target device and the fault handling deadline of the target device, a part of or all of the historical device parameters, and the historical fault handling deadline corresponding to the historical device parameter. And then, performing update training on the preset prediction model by using the updated training data so as to obtain an updated preset prediction model. Wherein the training targets of the update training process are: and the difference between the predicted failure processing time limit predicted by the updated prediction model according to the current equipment parameter (or the historical equipment parameter) of the target equipment and the failure processing time limit of the target equipment (or the historical failure processing time limit corresponding to the historical equipment parameter) is lower than a preset difference value, namely, the predicted failure processing time limit can be maximally close to or even reach the failure processing time limit corresponding to the current equipment parameter (or the historical failure processing time limit corresponding to the historical equipment parameter) of the target equipment.

In the embodiment of the present application, when the preset prediction model is updated, multiple types of parameters may be updated, for example, at least one of a model parameter of the preset prediction model, related information of a device parameter corresponding to a target device, and a data source of a historical device parameter may be updated. For ease of understanding and explanation, the following description is made in conjunction with three examples.

As a first example, when the preset prediction model is updated, the model parameters of the preset prediction model may be updated. The model parameters refer to model structure parameters of a preset prediction model.

As a second example, when the preset prediction model is updated, the related information of the device parameter corresponding to the target device may be updated. The device parameters are used for representing the parameters of the device characteristics of the device at a certain moment; furthermore, the device parameters are not limited in the embodiments of the present application, and for example, the device parameters may include: at least one of a condition parameter, a fault alarm parameter, and a device performance parameter.

The embodiment of the present application does not limit the related information of the device parameter corresponding to the target device, for example, the related information of the device parameter corresponding to the target device may include at least one of a parameter dimension of the device parameter corresponding to the target device and a parameter weight of the device parameter corresponding to the target device. The following describes the update procedure of the related information of these two device parameters in turn.

When the preset prediction model is updated, the parameter dimension of the device parameter corresponding to the target device may be updated, so that various parameters included in the device parameter are influence factors capable of influencing the prediction accuracy of the failure handling deadline, and the updating process may specifically be: and adding parameters capable of influencing the prediction accuracy of the fault processing deadline, and removing the parameters which do not influence the prediction accuracy of the fault processing deadline. Therefore, redundant parameters can be eliminated, the fault processing time limit with higher accuracy can be obtained by using the least equipment parameters as possible, and the prediction efficiency is improved.

When the preset prediction model is updated, the parameter weight of the device parameter corresponding to the target device can be updated, so that various parameters included in the device parameter can influence the prediction of the fault handling deadline by the influence weight according with the actual influence effect, and the updating process specifically comprises the following steps: and adjusting the parameter weight of the equipment parameter corresponding to the target equipment, so that the adjusted parameter weight of the equipment parameter corresponding to the target equipment is as close as possible to even reach the weight corresponding to the actual influence effect of the parameter.

It should be noted that the parameter weight of the device parameter is used to represent the degree of influence of the device parameter on the prediction of the fault handling deadline when the prediction model predicts the fault handling deadline according to the device parameter.

As a third example, the data source of historical device parameters may be updated as the pre-set predictive model is updated. Wherein, the data source refers to a device for providing historical device parameters.

In the practical application process, in other devices of the same type as the target device, the historical device parameters provided by some devices can influence the prediction accuracy of the preset prediction model, and the historical device parameters provided by some devices cannot influence the prediction accuracy of the preset prediction model, so that the historical device parameters provided by the devices for providing the historical device parameters which do not influence the prediction accuracy of the preset prediction model can be omitted in order to improve the training efficiency of the prediction model. Meanwhile, in order to improve the prediction accuracy of the prediction model, historical device parameters provided by new devices for providing historical device parameters which can affect the prediction accuracy of the preset prediction model can be used.

It should be noted that, the three examples described above are described by taking, as an example, a model parameter for updating a preset prediction model, information related to a device parameter corresponding to a target device, and a data source of a historical device parameter. However, in the embodiment of the present application, other parameters may also be updated, and this is not specifically limited in the embodiment of the present application.

In this embodiment, after the current device parameter of the target device and the fault handling deadline are obtained, the preset prediction model may be updated according to the current device parameter of the target device and the fault handling deadline of the target device, so that the preset prediction model can more accurately predict the fault handling deadline, and the prediction accuracy of the fault handling deadline is improved.

In addition, in order to further improve the prediction accuracy of the preset prediction model, the preset prediction model may be updated by using the fault analysis information of the target device. As described above, the present embodiment provides another implementation of the method for predicting the failure handling deadline, and as shown in fig. 4, in this implementation, the method for predicting the failure handling deadline includes steps S41-S44:

s41: and after receiving the fault early warning information of the target equipment, acquiring the current equipment parameters of the target equipment.

It should be noted that step S41 may be implemented by any implementation manner of step S11, and for brevity, details are not repeated here, and please refer to step S11 of the first method embodiment for technical details.

S42: and predicting the fault handling time limit of the target equipment by using a preset prediction model according to the current equipment parameters to obtain the fault handling time limit of the target equipment.

It should be noted that step S42 may be implemented by any implementation manner of step S12, and for brevity, details are not repeated here, and please refer to step S12 of the first method embodiment for technical details.

S43: and acquiring fault analysis information of the target equipment.

The fault analysis information is used for recording information obtained by performing fault analysis on the target equipment after the fault early warning information of the target equipment is received.

The specific content of the fault analysis information is not limited in the embodiment of the present application, for example, the fault analysis information may include information such as a location where a fault occurs in the target device, an influence degree of the fault on the target device, a fault type, and an actual fault handling deadline.

The source of the fault analysis information is not limited in the embodiments of the present application, for example, the fault analysis information may be provided by a fault analysis device or may be provided by a maintenance person.

S44: and updating the preset prediction model according to the current equipment parameters of the target equipment, the fault processing deadline of the target equipment and the fault analysis information of the target equipment.

In the embodiment of the present application, the current device parameter of the target device, the failure processing deadline of the target device, and the failure analysis information of the target device are all used to represent the failure related information of the target device, and the current device parameter of the target device, the failure processing deadline of the target device, and the failure analysis information of the target device have a one-to-one correspondence relationship.

In the embodiment of the application, when the preset prediction model is updated according to the current device parameters of the target device, the fault processing time limit of the target device, and the fault analysis information of the target device, the fault analysis information of the target device may be used to correct and/or fill the current device parameters of the target device, so that the corrected and/or filled current device parameters of the target device can more comprehensively and more accurately represent the relevant parameter information of the target device; moreover, the fault analysis information of the target device can also be used for correcting the fault processing time limit of the target device, so that the corrected fault processing time limit of the target device can more accurately represent the actual fault processing time limit of the target device. The "filling the current device parameters of the target device" refers to adding new parameter features to the current device parameters of the target device. The "correcting the current device parameter of the target device" refers to correcting an existing parameter in the current device parameter of the target device.

Based on the above analysis, the present application provides an implementation manner of step S44, in which step S44 may specifically include steps S441 to S442:

s441: updating the current equipment parameters of the target equipment by using the fault analysis information of the target equipment; and/or updating the fault processing deadline of the target equipment by using the fault analysis information of the target equipment.

For ease of understanding and explanation of step S441, the following description is made in conjunction with three examples.

As a first example, step S441 specifically is: and updating the current equipment parameters of the target equipment by using the fault analysis information of the target equipment.

In a first example, in some cases, the directly obtained current device parameters of the target device may not comprehensively represent the relevant parameters of the target device, and at this time, in order to improve the comprehensiveness of the current device parameters of the target device, the current device parameters of the target device may be filled and updated by using the fault analysis information of the target device, so that the updated current device parameters of the target device may comprehensively represent the relevant parameters of the target device.

In addition, in some cases, the directly obtained current device parameter of the target device has an error, and at this time, in order to improve the accuracy of the current device parameter of the target device, the current device parameter of the target device may be corrected and updated by using the fault analysis information of the target device, so that the updated current device parameter of the target device can more accurately represent the relevant parameter of the target device.

In addition, in some cases, the directly obtained current device parameters of the target device have errors, and the related parameters of the target device cannot be comprehensively characterized, and at this time, in order to improve the accuracy and the comprehensiveness of the current device parameters of the target device, the current device parameters of the target device may be subjected to parameter correction and padding update by using the fault analysis information of the target device, so that the updated current device parameters of the target device can accurately characterize the related parameters of the target device and comprehensively characterize the related parameters of the target device.

The above is the relevant content of the first example.

As a second example, step S441 specifically is: and updating the fault processing deadline of the target equipment by using the fault analysis information of the target equipment.

In the second example, in some cases, the predicted failure handling deadline of the target device has an error, and at this time, in order to improve accuracy of the failure handling deadline of the target device, the failure handling deadline of the target device may be corrected and updated by using the failure analysis information of the target device, so that the updated failure handling deadline of the target device can be closer to an actual failure handling deadline of the target device, and thus, the prediction model can be subsequently updated by using the more accurate failure handling deadline of the target device, which is beneficial to improving prediction accuracy of the prediction model.

The above is the related contents of the second example.

As a third example, step S441 specifically includes steps S4411 to S4412:

s4411: and updating the current equipment parameters of the target equipment by using the fault analysis information of the target equipment.

It should be noted that the content of step S4411 is the same as that of the first example, and for brevity, detailed description is omitted here, and please refer to the first example for technical details.

S4412: and updating the fault processing deadline of the target equipment by using the fault analysis information of the target equipment.

It should be noted that the content of step S4412 is the same as that of the second example, and for brevity, detailed description is omitted here, and please refer to the second example for technical details.

It should be noted that the execution sequence of steps S4411 and S4412 is not limited in the embodiment of the present application, and steps S4411 and S4412 may be executed sequentially, steps S4412 and S4411 may be executed sequentially, and steps S4411 and S4412 may be executed simultaneously.

S442: and updating the preset prediction model according to the current equipment parameters of the target equipment and the fault processing time limit of the target equipment.

It should be noted that the content of step S442 is the same as that of step S33, and for brevity, detailed description is omitted here, and please refer to step S33 for technical details.

The above is the relevant content of one embodiment of step S44.

In the present embodiment, step S44 may be implemented by any of the embodiments of step S33, and only "the current device parameter of the target device and the failure processing deadline of the target device" in step S33 needs to be replaced with "the current device parameter of the target device, the failure processing deadline of the target device, and the failure analysis information of the target device", and please refer to step S33 for detailed technical details.

It should be noted that, in the embodiment of the present application, the execution time of step S43 is not limited, and the execution is completed only before step S44 is executed. For example, step S43 may be performed after performing the action "after receiving the failure warning information of the target device" and before performing the action "acquiring the current device parameter of the target device", after performing step S41 and before performing step S42, after performing step S42 and before performing step S44, and simultaneously with step S41 or S42.

In another implementation manner of the method for predicting a failure handling deadline provided by the embodiment of the present application, in the implementation manner, after the current device parameter, the failure handling deadline, and the failure analysis information of the target device are obtained, the preset prediction model may be updated according to the current device parameter, the failure handling deadline, and the failure analysis information of the target device, so that the preset prediction model can more accurately predict the failure handling deadline, and thus the prediction accuracy of the failure handling deadline is improved. The fault analysis information records relevant fault information of the target device, and the fault analysis information can be used for updating current device parameters and/or fault processing time limit of the target device, so that the updated current device parameters of the target device are more comprehensive and accurate, and/or the updated fault processing time limit of the target device is more accurate, therefore, after the preset prediction model is updated by using the fault analysis information, the updated preset prediction model can more accurately predict the fault processing time limit of the target device, and the prediction accuracy of the preset prediction model is further improved.

In addition, in order to further improve the prediction accuracy of the preset prediction model, the preset prediction model may be updated with the maintenance information of the target device. As described above, the present embodiment provides another implementation of the method for predicting a failure handling deadline, and as shown in fig. 5, in this implementation, the method for predicting a failure handling deadline includes steps S51-S54:

s51: and after receiving the fault early warning information of the target equipment, acquiring the current equipment parameters of the target equipment.

It should be noted that step S51 may be implemented by any implementation manner of step S11, and for brevity, details are not repeated here, and please refer to step S11 of the first method embodiment for technical details.

S52: and predicting the fault handling time limit of the target equipment by using a preset prediction model according to the current equipment parameters to obtain the fault handling time limit of the target equipment.

It should be noted that step S52 may be implemented by any implementation manner of step S12, and for brevity, details are not repeated here, and please refer to step S12 of the first method embodiment for technical details.

S53: and after the target equipment is maintained, acquiring the maintenance information of the target equipment.

And the maintenance information is used for recording corresponding maintenance information when the target equipment is maintained after the fault early warning information of the target equipment is received.

The embodiment of the present application does not limit the specific content of the repair information, for example, the repair information may include information such as replacement information of a component in the target device, repair information of the target device, trimming information of a component of the target device, failure-related information of the target device, and information on an actual failure handling deadline.

S54: and updating the preset prediction model according to the current equipment parameters of the target equipment, the fault processing deadline of the target equipment and the maintenance information of the target equipment.

In the embodiment of the present application, the current device parameter of the target device, the failure handling deadline of the target device, and the maintenance information of the target device are all used to represent the failure related information of the target device, and the current device parameter of the target device, the failure handling deadline of the target device, and the maintenance information of the target device have a one-to-one correspondence relationship.

In the embodiment of the application, when the preset prediction model is updated according to the current device parameters of the target device, the fault handling time limit of the target device, and the maintenance information of the target device, the maintenance information of the target device can be used for correcting and/or filling the current device parameters of the target device, so that the corrected and/or filled current device parameters of the target device can more comprehensively and more accurately represent the relevant parameter information of the target device; moreover, the maintenance information of the target device can also be used for correcting the fault handling time limit of the target device, so that the corrected fault handling time limit of the target device can more accurately represent the actual fault handling time limit of the target device.

Based on the foregoing analysis, an implementation manner of step S54 is further provided in the examples of the present application, and in this implementation manner, step S54 may specifically include steps S541-S542:

s541: updating the current equipment parameters of the target equipment by using the maintenance information of the target equipment; and/or updating the failure processing deadline of the target equipment by using the maintenance information of the target equipment.

For ease of understanding and explanation of step S541, the following description is made in conjunction with three examples.

As a first example, step S541 specifically is: and updating the current equipment parameters of the target equipment by using the maintenance information of the target equipment.

In a first example, in some cases, the directly obtained current device parameters of the target device may not comprehensively represent the relevant parameters of the target device, and at this time, in order to improve the comprehensiveness of the current device parameters of the target device, the current device parameters of the target device may be filled and updated by using the maintenance information of the target device, so that the updated current device parameters of the target device may comprehensively represent the relevant parameters of the target device.

In the first example, in order to further improve the comprehensiveness of the current device parameters of the target device, replacement information of parts in the repair information, repair information of the target device, trimming information of parts of the target device, and the like may be filled in the current device parameters of the target device, so that the current device parameters of the target device can comprehensively represent not only relevant parameters before the target device is repaired but also relevant parameters after the target device is repaired.

In addition, in some cases, the directly obtained current device parameters of the target device have errors, and at this time, in order to improve the accuracy of the current device parameters of the target device, the current device parameters of the target device may be corrected and updated by using the maintenance information of the target device, so that the updated current device parameters of the target device can accurately represent the relevant parameters of the target device.

In addition, in some cases, the directly obtained current device parameters of the target device have errors, and cannot comprehensively represent the relevant parameters of the target device, and at this time, in order to improve the accuracy and comprehensiveness of the current device parameters of the target device, the current device parameters of the target device may be subjected to parameter correction and filling update by using the maintenance information of the target device, so that the updated current device parameters of the target device can accurately represent the relevant parameters of the target device and comprehensively represent the relevant parameters of the target device.

The above is the relevant content of the first example.

As a second example, step S541 specifically is: and updating the failure processing deadline of the target equipment by using the maintenance information of the target equipment.

In the second example, in some cases, the predicted failure handling deadline of the target device has an error, and at this time, in order to improve accuracy of the failure handling deadline of the target device, the failure handling deadline of the target device may be corrected and updated by using the maintenance information of the target device, so that the updated failure handling deadline of the target device can be closer to an actual failure handling deadline of the target device, and thus the prediction model can be subsequently updated by using the more accurate failure handling deadline of the target device, which is beneficial to improving prediction accuracy of the prediction model.

The above is the related contents of the second example.

As a third example, step S541 specifically includes steps S5411-S5412:

s5411: and updating the current equipment parameters of the target equipment by using the maintenance information of the target equipment.

It should be noted that the content of step S5411 is the same as that of the first example, and for brevity, detailed description is omitted here, and please refer to the first example for technical details.

S5412: and updating the failure processing deadline of the target equipment by using the maintenance information of the target equipment.

It should be noted that the content of step S5412 is the same as that of the second example, and for brevity, detailed description is omitted here, and please refer to the second example for technical details.

It should be noted that the execution order of steps S5411 and S5412 is not limited in the embodiment of the present application, and steps S5411 and S5412 may be executed in sequence, steps S5412 and S5411 may be executed in sequence, and steps S5411 and S5412 may be executed at the same time.

S542: and updating the preset prediction model according to the current equipment parameters of the target equipment and the fault processing time limit of the target equipment.

It should be noted that the content of step S542 is the same as that of step S33, and for brevity, detailed description is omitted here, and please refer to step S33 for technical details.

The above is the relevant content of one embodiment of step S54.

In the present embodiment, step S54 may be implemented by any of the embodiments of step S33, and only "the current device parameter of the target device and the failure processing deadline of the target device" in step S33 needs to be replaced with "the current device parameter of the target device, the failure processing deadline of the target device, and the maintenance information of the target device", and refer to step S33 for detailed technical details.

In the above still another implementation manner of the method for predicting a failure handling deadline provided by the embodiment of the present application, after the current device parameter, the failure handling deadline, and the maintenance information of the target device are obtained, the preset prediction model may be updated according to the current device parameter, the failure handling deadline, and the maintenance information of the target device, so that the preset prediction model can more accurately predict the failure handling deadline, and thus the prediction accuracy of the failure handling deadline is improved. The maintenance information is recorded with relevant fault information of the target device, and the maintenance information can be used for updating current device parameters and/or fault handling time limit of the target device, so that the updated current device parameters of the target device are more comprehensive and accurate, and/or the updated fault handling time limit of the target device is more accurate, therefore, after the preset prediction model is updated by using the maintenance information, the updated preset prediction model can more accurately predict the fault handling time limit of the target device, and the prediction accuracy of the preset prediction model is further improved. In addition, the maintenance related information of the target equipment is recorded in the maintenance information, so that the maintained equipment performance parameter information of the target equipment can be accurately determined according to the maintenance information, and therefore, after the preset prediction model is updated by using the maintenance information, the updated preset prediction model is more suitable for predicting the fault handling time limit of the maintained target equipment, and the prediction accuracy of the preset prediction model is further improved.

Based on the two embodiments of the method for predicting the failure handling deadline, in order to further improve the prediction accuracy of the preset prediction model, the preset prediction model may be updated by using the failure analysis information and the maintenance information of the target device. Thus, the present embodiment provides yet another implementation of the method for predicting a failure handling deadline, and as shown in fig. 6, in this implementation, the method for predicting a failure handling deadline includes steps S61-S65:

s61: and after receiving the fault early warning information of the target equipment, acquiring the current equipment parameters of the target equipment.

It should be noted that step S61 may be implemented by any implementation manner of step S11, and for brevity, details are not repeated here, and please refer to step S11 of the first method embodiment for technical details.

S62: and predicting the fault handling time limit of the target equipment by using a preset prediction model according to the current equipment parameters to obtain the fault handling time limit of the target equipment.

It should be noted that step S62 may be implemented by any implementation manner of step S12, and for brevity, details are not repeated here, and please refer to step S12 of the first method embodiment for technical details.

S63: and acquiring fault analysis information of the target equipment.

It should be noted that the content of step S63 is the same as that of step S43, and for brevity, detailed description is omitted here, and please refer to step S43 for technical details.

S64: and after the target equipment is maintained, acquiring the maintenance information of the target equipment.

It should be noted that the content of step S64 is the same as that of step S53, and for brevity, detailed description is omitted here, and please refer to step S53 for technical details.

S65: and updating the preset prediction model according to the current equipment parameters of the target equipment, the fault processing deadline of the target equipment, the fault analysis information of the target equipment and the maintenance information of the target equipment.

In the embodiment of the present application, the current device parameter of the target device, the failure processing deadline of the target device, the failure analysis information of the target device, and the maintenance information of the target device are all used to represent the failure related information of the target device, and a one-to-one correspondence relationship exists between the current device parameter of the target device, the failure processing deadline of the target device, the failure analysis information of the target device, and the maintenance information of the target device.

In the embodiment of the application, when the preset prediction model is updated according to the current device parameter of the target device, the fault handling deadline of the target device, the fault analysis information of the target device, and the maintenance information of the target device, the fault analysis information of the target device and the maintenance information of the target device may be used to correct and/or fill the current device parameter of the target device, so that the corrected and/or filled current device parameter of the target device can more comprehensively and more accurately represent the relevant parameter information of the target device; moreover, the fault analysis information of the target device and the maintenance information of the target device can also be used for correcting the fault handling deadline of the target device, so that the corrected fault handling deadline of the target device can more accurately represent the actual fault handling deadline of the target device.

Based on the above analysis, the present application provides an implementation manner of step S65, in which step S65 may specifically include steps S651-S652:

s651: updating the current equipment parameters of the target equipment by using the fault analysis information of the target equipment and the maintenance information of the target equipment; and/or updating the fault processing deadline of the target equipment by using the fault analysis information of the target equipment and the maintenance information of the target equipment.

For ease of understanding and explanation of step S651, the following description is made in conjunction with three examples.

As a first example, step S651 is specifically: and updating the current equipment parameters of the target equipment by using the fault analysis information of the target equipment and the maintenance information of the target equipment.

In a first example, in some cases, the directly obtained current device parameters of the target device may not comprehensively represent the relevant parameters of the target device, and at this time, in order to improve the comprehensiveness of the current device parameters of the target device, the current device parameters of the target device may be filled and updated by using the fault analysis information of the target device and the maintenance information of the target device, so that the updated current device parameters of the target device may comprehensively represent the relevant parameters of the target device.

In addition, in some cases, the directly obtained current device parameters of the target device have errors, and at this time, in order to improve the accuracy of the current device parameters of the target device, the current device parameters of the target device may be corrected and updated by using the fault analysis information of the target device and the maintenance information of the target device, so that the updated current device parameters of the target device can accurately represent the relevant parameters of the target device.

In addition, in some cases, the directly obtained current device parameters of the target device have errors, and cannot comprehensively represent the relevant parameters of the target device, and at this time, in order to improve the accuracy and comprehensiveness of the current device parameters of the target device, the current device parameters of the target device may be subjected to parameter correction and filling update by using the fault analysis information of the target device and the maintenance information of the target device, so that the updated current device parameters of the target device can accurately represent the relevant parameters of the target device, and can comprehensively represent the relevant parameters of the target device.

The above is the relevant content of the first example.

As a second example, step S651 is specifically: and updating the fault processing deadline of the target equipment by using the fault analysis information of the target equipment and the maintenance information of the target equipment.

In the second example, in some cases, the predicted failure handling deadline of the target device has an error, and at this time, in order to improve accuracy of the failure handling deadline of the target device, the failure handling deadline of the target device may be corrected and updated by using the failure analysis information of the target device and the maintenance information of the target device, so that the updated failure handling deadline of the target device can be closer to an actual failure handling deadline of the target device, and thus, the prediction model can be subsequently updated by using the more accurate failure handling deadline of the target device, which is beneficial to improving prediction accuracy of the prediction model.

The above is the related contents of the second example.

As a third example, step S651 specifically includes steps S6511-S6512:

s6511: and updating the current equipment parameters of the target equipment by using the fault analysis information of the target equipment and the maintenance information of the target equipment.

It should be noted that the content of step S6511 is the same as that of the first example, and for the sake of brevity, detailed description is omitted here, and please refer to the first example for technical details.

S6512: and updating the fault processing deadline of the target equipment by using the fault analysis information of the target equipment and the maintenance information of the target equipment.

It should be noted that the content of step S6512 is the same as that of the second example, and for brevity, detailed description is omitted here, and please refer to the second example for technical details.

In the embodiment of the present application, the execution order of steps S6511 and S6512 is not limited, and steps S6511 and S6512 may be executed in sequence, steps S6512 and S6511 may be executed in sequence, and steps S6511 and S6512 may be executed at the same time.

S652: and updating the preset prediction model according to the current equipment parameters of the target equipment and the fault processing time limit of the target equipment.

It should be noted that the content of step S652 is the same as that of step S33 described above, and for brevity, detailed description is omitted here, and please refer to step S33 for technical details.

The above is the relevant content of one embodiment of step S65.

In the present embodiment, step S65 may be implemented by any of the embodiments of step S33, and the technical details of step S33 may be referred to simply by replacing "the current device parameters of the target device and the failure processing deadline of the target device" in step S33 with "the current device parameters of the target device, the failure processing deadline of the target device, the failure analysis information of the target device, and the maintenance information of the target device".

It should be noted that, in the embodiment of the present application, the execution time of step S63 is not limited, and the execution is completed only before step S65 is executed. The embodiment of the present application also does not limit the execution time of step S64, and the execution is completed only before step S65 is executed.

In the embodiment, after the current device parameter, the fault handling deadline, the fault analysis information, and the maintenance information of the target device are obtained, the preset prediction model may be updated according to the current device parameter, the fault handling deadline, the fault analysis information, and the maintenance information of the target device, so that the preset prediction model can more accurately predict the fault handling deadline, and the prediction accuracy of the fault handling deadline is improved. The fault analysis information and the maintenance information are recorded with relevant fault information of the target equipment, and the fault analysis information and the maintenance information can be used for updating current equipment parameters and/or fault processing time limit of the target equipment, so that the updated current equipment parameters of the target equipment are more comprehensive and accurate, and/or the updated fault processing time limit of the target equipment is more accurate, therefore, after the preset prediction model is updated by using the fault analysis information and the maintenance information, the updated preset prediction model can more accurately predict the fault processing time limit of the target equipment, and the prediction accuracy of the preset prediction model is further improved. In addition, the maintenance related information of the target equipment is recorded in the maintenance information, so that the maintained equipment performance parameter information of the target equipment can be accurately determined according to the maintenance information, and therefore, after the preset prediction model is updated by using the maintenance information, the updated preset prediction model is more suitable for predicting the fault handling time limit of the maintained target equipment, and the prediction accuracy of the preset prediction model is further improved.

It should be noted that the present application embodiment does not limit the execution subject of the failure handling deadline prediction method provided in the foregoing method embodiment one and method embodiment two, for example, the execution subject of the failure handling deadline prediction method provided in the foregoing method embodiment may be a server (for example, a big data model training platform), or may be a terminal device.

Based on any implementation of the method for predicting the failure handling deadline provided in the first method embodiment and the second method embodiment, an embodiment of the present application further provides a device for predicting the failure handling deadline, which is explained and explained below with reference to the drawings.

Device embodiment

For technical details of the prediction apparatus for a failure handling deadline provided in the apparatus embodiment, please refer to the method embodiment described above.

Referring to fig. 7, this figure is a schematic structural diagram of a failure handling deadline prediction apparatus according to an embodiment of the present application.

The prediction device of failure handling deadline that this application embodiment provided includes:

the device parameter acquiring unit 71 is configured to acquire a current device parameter of a target device after receiving fault early warning information of the target device; the current equipment parameters comprise at least one of working condition parameters, fault alarm parameters and equipment performance parameters;

a processing deadline predicting unit 72, configured to predict, according to the current device parameter, a failure processing deadline of the target device by using a preset prediction model, so as to obtain the failure processing deadline of the target device; the preset prediction model is obtained by training according to historical equipment parameters and historical fault processing time limit corresponding to the historical equipment parameters.

As an embodiment, in order to improve the accuracy of the predicted fault handling deadline, the preset prediction model includes at least one of a convolutional neural network model CNN, a cyclic neural network model RNN, a deep neural network model DNN, a random forest model, and a support vector machine SVM.

As an embodiment, in order to improve the accuracy of the predicted fault handling deadline, the operating condition parameter includes at least one of a frequency spectrum, a current, a voltage, a flow rate, and a temperature;

and/or the presence of a gas in the gas,

As an embodiment, in order to improve the accuracy of the predicted failure handling deadline, the training process of the preset prediction model specifically includes:

As an embodiment, in order to improve the accuracy of the failure handling deadline predicted, the failure handling deadline predicting apparatus further includes:

and the prediction model updating unit is used for updating the preset prediction model according to the current equipment parameters of the target equipment and the fault processing time limit of the target equipment.

a fault information acquisition unit configured to acquire fault analysis information of the target device;

the prediction model updating unit is specifically configured to:

a maintenance information acquisition unit configured to acquire maintenance information of the target device after the target device is maintained;

the prediction model updating unit is specifically configured to: and updating the preset prediction model according to the current equipment parameters of the target equipment, the fault processing deadline of the target equipment and the maintenance information of the target equipment.

In the above specific implementation of the prediction apparatus for a failure handling deadline provided by the embodiment of the present application, in this implementation, after receiving the failure warning information of the target device, the device parameter obtaining unit 71 obtains the current device parameter of the target device, so that the handling deadline predicting unit 72 predicts the failure handling deadline of the target device according to the current device parameter by using a preset prediction model, and obtains the failure handling deadline of the target device. The preset prediction model is obtained by training according to the historical equipment parameters and the historical fault handling time limit corresponding to the historical equipment parameters, so that after the current equipment parameters are input into the preset prediction model, the preset prediction model can accurately predict the fault handling time limit of the target equipment without the participation of maintenance personnel, the occurrence of determining the wrong fault handling time limit due to human errors is avoided, the accuracy of the fault handling time limit is improved, the equipment can be maintained in time, and the safety of the equipment is improved.

The failure processing deadline predicting device comprises a processor and a memory, wherein the device parameter acquiring unit 71, the processing deadline predicting unit 72 and the like are stored in the memory as program units, and the program units stored in the memory are executed by the processor to realize corresponding functions.

The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. One or more than one kernel can be set, the fault processing time limit of the fault equipment is accurately determined by adjusting kernel parameters, and the accuracy of the fault processing time limit is improved.

An embodiment of the present invention provides a storage medium on which a program is stored, the program implementing the method for predicting a failure processing deadline when executed by a processor.

The embodiment of the invention provides a processor, which is used for running a program, wherein the method for predicting the failure processing deadline is executed when the program runs.

The embodiment of the present invention provides a device 80, where the device 80 includes at least one processor 81, at least one memory 82 connected to the processor 81, and a bus 83; the processor 81 and the memory 82 complete communication with each other through the bus 83; the processor 81 is used to call program instructions in the memory to perform the above-mentioned method of predicting the deadline for failure handling. The device 80 herein may be a server, a PC, a PAD, a cell phone, etc.

The present application further provides a computer program product adapted to perform a program for initializing the following method steps when executed on a data processing device:

and/or the presence of a gas in the gas,

Optionally, the method further includes:

acquiring fault analysis information of the target equipment;

Optionally, the method further includes:

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a device includes one or more processors (CPUs), memory, and a bus. The device may also include input/output interfaces, network interfaces, and the like.

The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip. The memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for predicting a failure handling deadline, comprising:

2. The method of claim 1, wherein the preset prediction model comprises at least one of a convolutional neural network model (CNN), a recurrent neural network model (RNN), a deep neural network model (DNN), a random forest model, and a Support Vector Machine (SVM).

3. The method of claim 1, wherein the operating condition parameters include at least one of frequency spectrum, current, voltage, flow, and temperature;

and/or the presence of a gas in the gas,

4. The method according to claim 1, wherein the training process of the predetermined prediction model specifically includes:

5. The method of claim 1, further comprising:

6. The method of claim 5, further comprising:

acquiring fault analysis information of the target equipment;

7. The method of claim 5, further comprising:

8. An apparatus for predicting a failure processing deadline, comprising:

9. A storage medium characterized by comprising a stored program, wherein the program executes the failure processing deadline predicting method according to any one of claims 1 to 7.

10. A processor configured to execute a program, wherein the program executes the method for predicting the processing deadline for the failure according to any one of claims 1 to 7.