CN117932437A

CN117932437A - Method, apparatus and storage medium for predicting equipment failure

Info

Publication number: CN117932437A
Application number: CN202410114932.2A
Authority: CN
Inventors: 于小海; 张伟健
Original assignee: Nanqi Xiance Nanjing High Tech Co ltd
Current assignee: Nanqi Xiance Nanjing High Tech Co ltd
Priority date: 2024-01-26
Filing date: 2024-01-26
Publication date: 2024-04-26

Abstract

The invention discloses a method, a device and a storage medium for predicting equipment faults. The method comprises the following steps: for each device, acquiring device operation data of the current device at the current moment in the operation process of the current device; processing equipment operation data based on an environmental model obtained through pre-training to obtain predicted operation data in predicted duration; the environment model is used for simulating the running environment of the current equipment; analyzing and processing the predicted operation data based on the prediction model, and determining whether the current equipment has faults or not; if the current equipment has faults, generating early warning information and sending the early warning information to the equipment management system so as to maintain the current equipment based on a user corresponding to the equipment management system. The problem of low accuracy of predicting equipment faults is solved, and accuracy of predicting equipment faults is improved.

Description

Method, apparatus and storage medium for predicting equipment failure

Technical Field

The present invention relates to the field of data processing technologies, and in particular, to a method, an apparatus, and a storage medium for predicting equipment failure.

Background

At present, the operation state of the equipment is obtained mainly by analyzing the acquired operation data of the equipment; and generating a fault library according to expert experience to predict equipment faults based on the fault library matching. However, this method depends on the perfection degree of the fault library, and the running state of the equipment is affected by various factors, so that the prediction result is easy to deviate.

Disclosure of Invention

The invention provides a method, a device and a storage medium for predicting equipment faults, which are used for improving the accuracy of predicting the equipment faults.

According to an aspect of the present invention, there is provided a method of predicting a device failure, the method comprising:

For each device, acquiring device operation data of the current device at the current moment in the operation process of the current device;

processing the equipment operation data based on an environment model obtained through pre-training to obtain predicted operation data in predicted duration; the environment model is used for simulating the running environment of the current equipment;

Analyzing and processing the predicted operation data based on a prediction model, and determining whether the current equipment has a fault;

if the current equipment has faults, generating early warning information and sending the early warning information to an equipment management system so as to maintain the current equipment based on a user corresponding to the equipment management system.

Further, the obtaining the device operation data of the current device at the current moment includes:

Collecting equipment operation data of the current equipment based on at least one sensor arranged on the current equipment, and collecting production data of the current equipment based on a PLC (programmable logic controller) and taking the production data as the equipment operation data;

And transmitting the equipment operation data in real time so that the environment model corresponding to the current equipment processes the equipment operation data.

Further, the processing the device operation data based on the environmental model obtained by pre-training to obtain predicted operation data within a predicted time length includes:

Simulating the running environment of the current equipment based on the environment model obtained through pre-training so as to process the equipment running data under the running environment to obtain the predicted running data in the predicted time length.

Further, the analyzing and processing the predicted operation data based on the prediction model, determining whether the current device has a fault, includes:

and inputting the predicted operation data into the prediction model, and determining whether the predicted operation data has faults or not under the current strategy of the current equipment.

Further, the method further comprises:

Acquiring a plurality of sample data, wherein the sample data comprise historical operation data of equipment at a first moment and actual historical operation data in corresponding prediction time length, and the prediction time length corresponds to the first moment;

Training a pre-constructed environmental model and the predictive model based on the plurality of sample data; wherein the pre-built environmental model is determined based on the operating environment of the device;

The prediction historical operation data and the actual historical operation data in the prediction duration outputted by the environment model are inputted into the prediction model, and a fault prediction result is obtained;

and correcting model parameters in the environment model and the prediction model based on the fault prediction result and the actual historical operation data.

Further, the method further comprises:

And determining a deviation threshold corresponding to the actual historical operation data, and correcting model parameters in the prediction model based on the deviation threshold.

Further, in the case that the current device has a fault, the method further includes:

And outputting the fault point position of the current equipment to generate early warning information based on the fault point position.

Further, the method further comprises:

taking the current equipment as equipment operation data and actual operation data in a fault state as training samples;

model parameters of the environmental model and the predictive model are updated based on the training samples.

According to another aspect of the present invention, there is provided an apparatus for predicting a malfunction of a device, the apparatus comprising:

The operation data acquisition module is used for acquiring the equipment operation data of the current equipment at the current moment in the operation process of the current equipment for each equipment;

The operation data prediction module is used for processing the equipment operation data based on an environment model obtained through pre-training to obtain predicted operation data in a predicted time length; the environment model is used for simulating the running environment of the current equipment;

the data processing module is used for analyzing and processing the predicted operation data based on a prediction model and determining whether the current equipment has faults or not;

And the early warning module is used for generating early warning information and sending the early warning information to the equipment management system if the current equipment has faults so as to maintain the current equipment based on a user corresponding to the equipment management system.

According to another aspect of the present invention, there is provided an electronic device including:

At least one processor; and

A memory communicatively coupled to the at least one processor; wherein,

The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of predicting device failure of any one of the embodiments of the present invention.

According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to execute a method of predicting device failure according to any one of the embodiments of the present invention.

According to the technical scheme of the embodiment of the invention, for each device, in the running process of the current device, the device running data of the current device at the current moment is obtained; processing equipment operation data based on an environmental model obtained through pre-training to obtain predicted operation data in predicted duration; the environment model is used for simulating the running environment of the current equipment; analyzing and processing the predicted operation data based on the prediction model, and determining whether the current equipment has faults or not; if the current equipment has faults, generating early warning information and sending the early warning information to the equipment management system so as to maintain the current equipment based on a user corresponding to the equipment management system. The problem of low accuracy of predicting equipment faults is solved, and accuracy of predicting equipment faults is improved.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of a method of predicting equipment failure provided in accordance with an embodiment of the present invention;

FIG. 2 is a flow chart of a specific method of predicting equipment failure provided in accordance with an embodiment of the present invention;

FIG. 3 is a schematic flow chart of a specific predictive equipment failure according to an embodiment of the invention;

FIG. 4 is a block diagram of an apparatus for predicting equipment failure according to an embodiment of the present invention;

Fig. 5 is a block diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.

It is noted that the terms "comprises" and "comprising," and any variations thereof, in the description and claims of the present invention and in the foregoing figures, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.

Fig. 1 is a flowchart of a method for predicting a device failure according to an embodiment of the present invention, where the embodiment is applicable to a scenario of predicting a device failure based on an environmental model, and may be executed by an apparatus for predicting a device failure, where the apparatus for predicting a device failure may be implemented in a form of hardware and/or software and configured in a processor of an electronic device.

As shown in fig. 1, the method of predicting equipment failure includes the steps of:

s110, for each device, acquiring device operation data of the current device at the current moment in the operation process of the current device.

It will be appreciated that the operational status of the device is different and the operational data is different from that of a device that is operating normally, and therefore, in order to determine whether each device is operating normally, data associated with the operation of the device may be obtained to determine the operational status of each device based on the data, so as to implement fault prediction.

The device is a device needing fault prediction, for example, the device may be a device in a target system, and the device may be in an upstream-downstream relationship.

Device operational data is a series of data of a device during operation.

It will be appreciated that, considering that the device operational data is related to a specific application scenario, the operational data may be determined according to the specific application scenario. For example, for a vehicle, the operating data includes parameters related to vehicle operation, which may include vehicle real-time position, travel trajectory, engine start and shut-off times, engine temperature, engine speed, throttle opening, gearbox gear information, gearbox shift pattern, and vehicle travel speed; for electrical devices, the operational data may include the current, voltage, etc. of the device.

In this embodiment, obtaining device operation data of a current device at a current time includes: collecting equipment operation data of the current equipment based on at least one sensor arranged on the current equipment, collecting production data of the current equipment based on the PLC, and taking the production data as the equipment operation data; and transmitting the equipment operation data in real time so that the environment model corresponding to the current equipment processes the equipment operation data.

The equipment operation data includes equipment operation data and production data.

It will be appreciated that in order to establish a correspondence between faults and equipment operational data, a quantitative indicator corresponding to equipment performance may be determined. Therefore, the measurement data of the device can be acquired based on the sensor as a quantization index corresponding to the performance of the functional module.

The device operation data may be measurement data, which is a physical quantity that can be obtained by measurement.

Alternatively, the measurement data may be input data and/or output data of the device, and correspondingly, for each functional module of the current device, the input data and/or output data of all functional modules are used as device operation data of the current device.

A programmable logic controller (Programmable Logic Controller, PLC) is a digital operation operating electronic system designed specifically for use in an industrial environment, the PLC collecting production data based on a programmable memory, by storing operating instructions (e.g., instructions to perform operations such as logic operations, sequence control, timing, counting, and arithmetic operations) within the memory to control various types of equipment or production processes through digital or analog input and output.

The production data may include equipment status and equipment tooling data, for example, the equipment status data may include real-time data such as on-off status, alarm data, equipment operating pressure, speed, temperature, etc. of the equipment, and time data corresponding to the equipment status data, and the equipment tooling data may include usage information such as model number, service life, etc. of the tooling mold.

Optionally, collecting production data of the current device based on the PLC includes: the PLC is connected with the equipment, so that the current value of the production data of the equipment can be acquired, and the production data can be statistically analyzed. Considering that the PLC also has a data recording unit, the data acquired by the PLC can be acquired based on the data recording unit. The PLC has the advantage of more self-checking signals, so that the production data can be acquired based on the PLC, the self-diagnosis type equipment monitoring can be realized, faults are reduced, and the reliability of the equipment is improved.

S120, processing the equipment operation data based on the environment model obtained through pre-training to obtain the predicted operation data in the predicted time length.

It will be appreciated that, given that some of the operational data of a device is susceptible to environmental variables, which in turn lead to deviations in the predicted results, an environmental model is built to simulate the operational environment of the device.

The predicted operation data may include operation data of each time within a predicted time period after the current time, or may include only operation data of a future time corresponding to the predicted time period after the current time.

Optionally, the environmental model includes a neural network model for predicting based on the device operational data and the device operational environment to obtain predicted operational data.

Alternatively, the environment model may include a device simulation model corresponding to the current device and an environment parameter model corresponding to the environment in which the current device is located, where the simulation model may be a physical model corresponding to the current device or a mathematical model suitable for computational processing. This has the advantage that the device operation data can be directly obtained to predict a device failure based on the device operation data.

It will be appreciated that the environmental model may need to be trained prior to processing the device operational data based on the environmental model.

Training the environmental model includes: acquiring a plurality of sample data, wherein the sample data comprise historical operation data of equipment at a first moment and actual historical operation data in corresponding prediction time length, and the prediction time length corresponds to the first moment; training a pre-constructed environmental model and a prediction model based on a plurality of sample data; wherein the pre-built environmental model is determined based on the operating environment of the device; the prediction historical operation data and the actual historical operation data in the prediction duration outputted by the environment model are inputted into the prediction model, and a fault prediction result is obtained; and correcting the environment model and model parameters in the prediction model based on the fault prediction result and actual historical operation data.

It is understood that the plurality of sample data may be historical operation data corresponding to each time within a period of time, each time may be regarded as a first time, the operation data at each time may be one sample data, and the corresponding actual historical operation data may include operation data at each historical time corresponding to a predicted time period after the first time.

Alternatively, the sample data may include operation data in a fault state of the apparatus and operation data in a normal operation state of the apparatus.

Optionally, the historical operation data at the first moment is taken as an input sample corresponding to the current sample data, and the actual historical operation data in the corresponding prediction duration is taken as the label data corresponding to the input sample. Correspondingly, training the pre-constructed environmental model and the predictive model based on the plurality of sample data includes: for each sample data, input samples (i.e. historical operation data of the equipment at the first moment) in the current sample data are input into the environment model, and output data (i.e. prediction historical operation data in a prediction time period) corresponding to the input samples are obtained.

The prediction model is used for carrying out fault prediction based on the prediction historical operation data to obtain a fault prediction result corresponding to the prediction historical operation data.

Alternatively, the fault prediction result may include an operation state of the device, the operation state including normal operation and a fault. Correspondingly, based on the fault prediction result and the actual historical operation data, the correction of the environmental model and the model parameters in the prediction model comprises the following steps: determining an actual equipment operation state corresponding to the actual historical operation data, and if the actual operation state is inconsistent with the fault prediction result, correcting model parameters in the environment model and the prediction model so as to enable the actual operation state to be consistent with the fault prediction result; and stopping training when the actual running state is consistent with the fault prediction result, and obtaining an environment model and a prediction model. This has the advantage that overfitting can be prevented.

Optionally, training the prediction model includes: for each device, acquiring operation data of the device in a fault state and operation data in a normal working state, taking the operation data as an input sample in a prediction training sample, taking a real operation state corresponding to the operation data as tag data corresponding to the input sample, and taking each input sample and the tag data corresponding to the input sample as a prediction training sample to obtain a plurality of prediction training samples; for each prediction training sample, inputting an input sample in the current prediction training sample into a prediction model, and outputting a prediction running state corresponding to the current input sample; determining a loss value corresponding to a current input sample based on the predicted running state, the tag data in the current training sample and a preset loss function; correcting model parameters of the prediction model based on the loss value so as to reduce the loss value; and stopping training when the loss function converges to obtain a prediction model.

In this embodiment, training the prediction model further includes: and determining a deviation threshold corresponding to the actual historical operating data, so as to correct model parameters in the prediction model based on the deviation threshold.

Wherein the deviation threshold is used to determine a maximum degree of deviation between the predicted historical operational data and the actual historical operational data. Correspondingly, determining the deviation threshold corresponding to the actual historical operating data to correct the model parameters in the predictive model based on the deviation threshold includes: determining an actual deviation between the predicted historical operating data and the actual historical operating data; if the actual deviation exceeds the deviation threshold, correcting model parameters in the prediction model so as to reduce the deviation; and stopping training when the deviation is converged, and obtaining a prediction model.

It will be appreciated that the operational data may include various types of data, and that the device status may be different for different degrees of deviation of the data, and therefore, for each type of data, a corresponding deviation threshold is set, which has the advantage that the accuracy of the prediction may be improved.

Alternatively, the deviation may comprise a statistical deviation, which may comprise at least one of an absolute deviation, a relative deviation, a standard deviation, and a relative average deviation.

Further, processing the device operation data based on the environmental model obtained by pre-training to obtain predicted operation data within a predicted time length, including: and simulating the running environment of the current equipment based on the environment model obtained by pre-training so as to process the equipment running data under the running environment and obtain the predicted running data in the predicted time length.

Specifically, the equipment operation data is input into the environment model obtained by pre-training, so that the equipment operation data is processed based on the operation environment to obtain the predicted operation data in the predicted time period corresponding to the equipment operation data.

S130, analyzing and processing the predicted operation data based on the prediction model, and determining whether the current equipment has faults or not.

Optionally, considering that the device types are different, the operation data of different devices are different; also, different types of operational data may be included for the same device, and thus, predictive models corresponding to the device may be trained for different devices and/or predictive models corresponding to the data types may be trained for different data types.

Alternatively, the prediction model may be a classification model, for determining an operation state of the device, and correspondingly, determining whether a fault exists in the current device based on analysis processing of the prediction operation data by the prediction model, including: inputting the predicted operation data into a predicted model obtained by pre-training, and processing the predicted operation data to obtain an operation state corresponding to the operation data of the equipment, and if the analysis result of the predicted model is that the equipment is normally operated, determining that the current equipment has no fault; if the analysis result shows that the equipment has faults, determining that the current equipment has no faults.

Optionally, the prediction model is used for determining a fault type, correspondingly, based on analysis and processing of prediction operation data by the prediction model, determining whether the current device has a fault or not includes: inputting the predicted operation data into a predicted model obtained by pre-training, and processing the predicted operation data to obtain an analysis result corresponding to the equipment operation data, wherein the analysis result comprises a fault type, and if the analysis result of the predicted model is that the equipment normally operates, determining that the current equipment has no fault; if the analysis result is a specific fault type, determining that the current equipment has the fault of the type.

In this embodiment, the determining whether the current device has a fault based on the analysis processing of the prediction operation data by the prediction model includes: and inputting the predicted operation data into the prediction model, and determining whether the predicted operation data has faults or not under the current strategy by the current equipment.

The current policy may include, among other things, the presence of the current device. Alternatively, the parameter may be at least one of input data of each functional module, an attribute parameter of the functional module, and an environmental parameter in the environmental model.

It can be understood that, in order to obtain the operation data of the current device, the parameter setting of the environmental model can be adjusted to obtain operation data corresponding to various strategies, which has the advantage that the corresponding relation among the strategy, the predicted operation data and the working state of the device can be determined based on the simulation data corresponding to the strategy, so that the fault prediction accuracy is improved.

Optionally, the predicted operation data is input into the prediction model, and whether the predicted operation data has faults or not under the current strategy of the current device is determined: comprising the following steps: and adjusting the entering parameters to obtain the predicted operation data corresponding to the current entering parameters, inputting the predicted operation data into a prediction model to obtain a data analysis processing result corresponding to the predicted operation data, and determining whether the current equipment has faults or not based on the data analysis processing result.

Optionally, the policy may include a maintenance policy, and correspondingly, the method includes inputting the predicted operation data into the prediction model, and determining whether the predicted operation data has a fault under the current policy by the current device includes: after detecting that the equipment has faults, generating a maintenance strategy corresponding to the equipment, so that a worker maintains the equipment based on the maintenance strategy, and obtaining predicted operation data corresponding to the maintenance strategy.

And S140, if the current equipment has faults, generating early warning information and sending the early warning information to the equipment management system so as to maintain the current equipment based on a user corresponding to the equipment management system.

The early warning information can be any form of early warning information and is used for reminding a user that equipment is in a fault state, and the advantage of the early warning information is that the user can intervene in time, so that the equipment management efficiency is improved, and the safety is enhanced.

Optionally, early warning information about the current device is generated to prompt the staff that the current device is faulty and the specific fault type is generated.

The equipment management system is used for managing all the equipment, and when the equipment management system receives the early warning information corresponding to at least one piece of equipment, the man-machine interaction module based on the equipment management system processes the early warning information so as to inform a user, so that the user can repair the equipment in time.

It will be appreciated that the device includes at least one functional module, and that it may be determined whether the functional module has failed based on the operational data of the functional module to determine whether each functional module in the current device is operating properly. Therefore, in order to predict the fault of the functional module, a plurality of detection points may be set for the current device, for acquiring operation data corresponding to the functional module, for determining an operation state of each functional module based on the data, for determining whether the current device has a fault based on the module operation data, and for outputting the fault point of the current device under the condition that the current device has a fault, for generating the early warning information based on the fault point.

Wherein, fault potential can be set up in each functional module of the present equipment for detecting the operation data of this module.

Specifically, under the condition that the current equipment is determined to have a fault, determining a fault function module corresponding to the operation data of the fault state, taking the fault function module as the fault potential of the current equipment, and outputting early warning information corresponding to the fault function module.

Optionally, the operation data of the functional module includes a module identifier corresponding to the functional module, and under the condition that the current device has a fault, the module identifier corresponding to the operation data is determined based on the operation data, and a fault point location of the current device is output based on the module identifier, so as to generate the early warning information based on the fault point location.

It will be appreciated that given that the nature of the prediction problem may change over time, resulting in the validity of the model prediction decaying over time, this may be due to the fact that real devices may experience faults that are not involved in the training samples, so that the assumptions used and captured in the model change or are no longer valid, and thus the device operational data and the actual operational data for the current device in the faulty state may be taken as training samples; model parameters of the environmental model and the predictive model are updated based on the training samples, that is, the training samples are updated based on the plant operational data to update train the environmental model and the predictive model.

Alternatively, the training samples may include only new data, or may include both new data and old data. Correspondingly, model parameters can be updated in the two modes, and an updating strategy of the training sample is determined based on the training sample with higher prediction accuracy.

According to the technical scheme, equipment operation data are predicted through an environment model, equipment states are predicted through the prediction model, real-time warning is achieved through early warning information, maintenance personnel are assisted to work, and early predictive maintenance of fault equipment is achieved.

Fig. 2 is a flowchart of a specific method for predicting an equipment failure according to an embodiment of the present invention, which is configured in the present embodiment and applicable to a scenario for predicting an equipment failure based on an environmental model and a prediction model.

As shown in fig. 2, the method for predicting equipment failure includes the steps of:

S210, for each device, collecting device operation data of the current device based on at least one sensor deployed on the current device, and collecting production data of the current device based on the PLC and taking the production data as the device operation data in the operation process of the current device.

Referring to fig. 3, detection data of a current device is collected based on a sensor, and device data of the current device is collected based on a PLC to obtain operation data of the device and device data related to upstream and downstream process flows, and the detection data and the device data are used as device operation data of the device.

S220, transmitting the equipment operation data in real time so that the environment model corresponding to the current equipment processes the equipment operation data.

Referring to fig. 3, device operation data is transmitted in real time to a fault prediction device configured with the method of predicting device faults.

S230, simulating the running environment of the current equipment based on the environment model obtained through pre-training so as to process the equipment running data in the running environment to obtain the predicted running data in the predicted time length, inputting the predicted running data into the prediction model, and determining whether the predicted running data of the current equipment has faults under the current strategy.

Referring to fig. 3, training the environmental model and the predictive model includes: and predicting the received equipment operation data based on the environment model to obtain prediction historical operation data corresponding to a future time set for a time length (for example, 2 hours) from the current time, training the environment model and the prediction model based on the prediction historical operation data and actual historical operation data of the future time set for the time length (for example, 2 hours) from the current time to obtain a normal state operation trend of the current detection potential and an operation trend of fault data, and determining a deviation threshold corresponding to the normal state operation data.

Optionally, in the case where sufficient operational data for the fault condition is accumulated, the predictive model is supervised and learned based on the operational data, and the specific fault function module of the device is determined based on the predictive model.

Further, the environment model and the prediction model are applied to the real production environment for real-time detection, and if the running state trend of the point location and the normal state deviation degree in the environment model are found to exceed the deviation threshold value, the point location is indicated to be abnormal, and the equipment fails.

And S240, if the current equipment has a fault, generating early warning information and sending the early warning information to the equipment management system so as to maintain the current equipment based on a user corresponding to the equipment management system.

Referring to fig. 3, if the current device has a fault, early warning information is generated and sent to a device management system, and the device management system generates a corresponding maintenance plan or maintenance plan to enable a worker to perform fault detection, maintenance and/or repair on the current device so as to continuously collect device operation data, update a training sample based on the device operation data, and update and train an environment model and a prediction model.

According to the technical scheme provided by the embodiment of the invention, on the basis of actual equipment operation data and the technological process of the equipment, an intelligent decision technology is fully utilized, the equipment environment model and the prediction model are constructed to determine the fault equipment, the equipment is predictably maintained, the intelligent maintenance level can be comprehensively improved, and the expert experience dependence is reduced; performing deep global data analysis on the equipment operation data, and completing equipment maintenance decision analysis in a higher dimension; and the method is cooperated with production business, so that the overall maintenance efficiency is improved, the loss caused by equipment faults is reduced, and the production safety is ensured.

Fig. 4 is a block diagram of an apparatus for predicting equipment failure according to an embodiment of the present invention, where the embodiment may be applicable to a scenario in which equipment failure is predicted based on a simulation model, and the apparatus may be implemented in a form of hardware and/or software, and integrated into a processor of an electronic device having an application development function.

As shown in fig. 4, the apparatus for predicting a device failure includes: an operation data obtaining module 401, configured to obtain, for each device, device operation data of a current device at a current moment in a current device operation process; an operation data prediction module 402, configured to process the device operation data based on an environmental model obtained by training in advance, to obtain predicted operation data within a predicted duration; the environment model is used for simulating the running environment of the current equipment; a data processing module 403, configured to analyze and process the predicted operation data based on a prediction model, and determine whether the current device has a fault; and the early warning module 404 is configured to generate early warning information and send the early warning information to the device management system if the current device has a fault, so as to maintain the current device based on a user corresponding to the device management system. The problem of low accuracy of predicting equipment faults is solved, and accuracy of predicting equipment faults is improved.

Optionally, the operation data acquisition module 401 is specifically configured to:

Optionally, the operation data prediction module 402 is specifically configured to:

Optionally, the data processing module 403 is specifically configured to:

Optionally, the apparatus further comprises a model training module for:

Optionally, the model training module includes a parameter correction unit, where the parameter correction unit is configured to:

Optionally, the device further includes a fault point location output module, where the fault point location output module is configured to:

Optionally, the apparatus further includes a model parameter updating module, where the model parameter updating module is configured to:

The device for predicting the equipment failure provided by the embodiment of the invention can execute the method for predicting the equipment failure provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

Fig. 5 is a block diagram of an electronic device according to an embodiment of the present invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 5, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.

Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as a method of predicting equipment failure.

In some embodiments, the method of predicting device failure may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the method of predicting device failure described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the method of predicting device failure in any other suitable manner (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable apparatus for predicting device failure, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.

The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved.

The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.

Claims

1. A method of predicting equipment failure, comprising:

2. The method of claim 1, wherein the obtaining device operation data of the current device at the current time comprises:

3. The method of claim 1, wherein the processing the device operation data based on the pre-trained environmental model to obtain predicted operation data for a predicted duration comprises:

4. The method of claim 1, wherein the determining whether the current device has a fault based on predictive model analysis of the predicted operational data comprises:

5. The method as recited in claim 1, further comprising:

6. The method as recited in claim 5, further comprising:

7. The method of claim 1, wherein in the event of a failure of the current device, the method further comprises:

8. The method according to claim 1, wherein the method further comprises:

9. An apparatus for predicting equipment failure, comprising:

10. A computer readable storage medium storing computer instructions for causing a processor to perform the method of predicting equipment failure of any one of claims 1-8.