CN117271195A

CN117271195A - Equipment maintenance method, device, equipment and storage medium

Info

Publication number: CN117271195A
Application number: CN202311408395.4A
Authority: CN
Inventors: 蔡奕聪; 周坤梅; 郭紫旭
Original assignee: Shenzhen Invic Software Technology Co ltd
Current assignee: Shenzhen Invic Software Technology Co ltd
Priority date: 2023-10-26
Filing date: 2023-10-26
Publication date: 2023-12-22

Abstract

The invention discloses a device maintenance method, a device, a system and a storage medium, wherein the method comprises the steps of obtaining an upgrade file of a device to be maintained; the upgrade file is sent to the equipment to be maintained for upgrade; acquiring a data record file of equipment to be maintained; and analyzing the data record file by using a preconfigured equipment mechanism model, and determining fault data indicating the fault position.

Description

Equipment maintenance method, device, equipment and storage medium

Technical Field

The present invention relates to the field of simulation technologies, and in particular, to a method and an apparatus for maintaining a device, and a device computer readable storage medium.

Background

The traditional technology can only solve the maintenance and upgrading among single-layer systems, and has limitation in multi-stage systems, so that when field personnel maintain, the maintenance is frequently required to be disassembled, and a great deal of time is spent. For on-site air conditioning system upgrade, maintenance personnel often need to find corresponding upgrade firmware in a database through the bar code of the whole air conditioning system, and if the maintenance personnel need to upgrade and maintain various air conditioning systems at one trip, a plurality of upgrade firmware are usually prepared at the same time. Often after arriving at the site, the system operates abnormally due to the firmware lifting error.

When problems in hardware (such as controllers) are involved in the field, the problems often cannot be solved quickly and effectively based on the professional knowledge of after-sales maintenance personnel, and certain information collection is needed to be carried out frequently and then the information is sent to research and development personnel for processing. For software anomalies on some devices, it sometimes takes a long time or under specific conditions to trigger a problem, which can take a lot of time and effort if the problem is reproduced by an after-market or research personnel squatting on site.

Disclosure of Invention

In order to solve the existing technical problems, the embodiment of the invention provides a device maintenance method, a system, a device and a computer readable storage medium, which can enable maintenance personnel to acquire required data records and locate fault positions on site, thereby being convenient for the maintenance personnel to quickly solve faults.

In a first aspect, there is provided an apparatus maintenance method, comprising:

acquiring an upgrade file of equipment to be maintained;

the upgrade file is sent to the equipment to be maintained for upgrade;

acquiring a data record file of equipment to be maintained;

and analyzing the data record file by using a preconfigured equipment mechanism model, and determining fault data indicating the fault position.

In a second aspect, there is provided an equipment maintenance device comprising:

The acquisition module is used for acquiring an upgrade file of the equipment to be maintained;

the sending module is used for sending the upgrade file to the equipment to be maintained for upgrading;

the acquisition module is also used for acquiring a data record file of the equipment to be maintained;

the determining module is used for analyzing the data record file by utilizing a preconfigured equipment mechanism model and determining fault data indicating a fault position.

In a third aspect, an intelligent maintenance apparatus is provided, including a memory and a processor, where the memory stores a computer program, where the computer program, when executed by the processor, causes the processor to execute the steps of the apparatus maintenance method provided in the embodiments of the present application.

In a fourth aspect, a storage medium is provided, in which a computer program is stored, which when executed by a processor causes the processor to perform the steps of the device maintenance method provided in the embodiments of the present application.

In the above embodiment, the equipment to be maintained is upgraded by the upgrade file, and after the equipment to be maintained is upgraded, the data record file of the equipment to be maintained can be obtained, so that maintenance personnel can conveniently obtain required data, after-sales or on-site squat reproduction of research personnel is avoided, time cost is saved, the required data is formed into the data record file, the data record file is used as input data of a pre-configured equipment mechanism model, the pre-configured equipment mechanism model analyzes the data record file, and therefore, the fault position and abnormal data at the fault position are output, and the maintenance personnel can conveniently and rapidly solve the fault.

Drawings

FIG. 1 is a diagram of an application environment of a method of device maintenance in one embodiment;

FIG. 2 is a schematic diagram of a smart maintenance device according to an embodiment;

FIG. 3 is a flow chart of a method of equipment maintenance in one embodiment;

FIG. 4 is a schematic diagram of an upgrade to a device to be maintained in one embodiment;

FIG. 5 is a flow chart of a method for acquiring a preconfigured device mechanism model in a device maintenance method according to one embodiment;

FIG. 6 is a schematic diagram of fault detection of equipment to be maintained in an embodiment;

FIG. 7 is a flow chart of fault detection in a method of equipment maintenance in one embodiment;

FIG. 8 is a schematic diagram of maintenance of multiple sites in an apparatus maintenance method according to an embodiment;

FIG. 9 is a schematic diagram of maintenance on a plurality of devices to be maintained in a device maintenance method according to an embodiment;

FIG. 10 is a schematic diagram of maintenance of a plurality of devices to be maintained in a device maintenance method according to yet another embodiment;

FIG. 11 is a schematic diagram of a device maintenance apparatus in an embodiment;

FIG. 12 is a schematic diagram of equipment maintenance equipment in one embodiment.

Detailed Description

The technical scheme of the invention is further elaborated below by referring to the drawings in the specification and the specific embodiments.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the scope of the invention. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.

In the following description, reference is made to the expression "some embodiments" which describe a subset of all possible embodiments, but it should be understood that "some embodiments" may be the same subset or a different subset of all possible embodiments and may be combined with each other without conflict.

Referring to fig. 1, an application environment diagram of a device maintenance method in an embodiment is shown. The application environment map data system may include a server 100, an intelligent maintenance device 101, and a device to be maintained 102. Wherein the intelligent maintenance apparatus 101 may communicate with the server 100 and the device to be maintained 102 communicates with the intelligent maintenance apparatus 101. Wherein the server 100 may be a cloud server, or a server farm in which a plurality of servers are integrated, or the like. The device to be maintained 101 includes a main controller 1021, N sub-devices 1022, and a corresponding plurality of collectors 1023 under each sub-device, where there are M collectors 1023, for example, two collectors under a first sub-device, a first collector, and a second collector. Each of the sub-devices 1022 has a different functional module and is capable of operating independently, and the collector 1023 is configured to collect operation status data of the sub-device corresponding to the device 101 to be maintained. For example, the device 101 to be maintained is an air conditioner, and the number of sub-devices 1022 may be two, i.e., an indoor host and an outdoor host. Wherein the collector 1023 of the indoor unit may include an indoor unit controller, a transformer, a temperature sensor, etc. The outdoor unit's collector 1023 may include an outdoor unit controller, a blower motor, a compressor, etc. The intelligent maintenance device 101 can obtain an upgrade file for upgrading the device 101 to be maintained from the server 100, after the device 101 to be maintained is upgraded according to the upgrade file, the main controller 1021 can communicate with the sub-devices 1022, and when a plurality of sub-devices 1022 are provided, each sub-device 1022 communicates with the main controller 1021 according to a corresponding communication port, and can identify the sub-device. After the upgrade is completed, each sub-device 1022 can communicate with each collector 1023, and can identify the identity of the collector 1023 when the collector 1023 is multiple. After the upgrade is completed, the data collected by the collector 1023 under each sub-device 1022 can be sent to the corresponding sub-device 1022, the sub-device 1022 can send the running state data of itself to the main controller 1021, and the main controller 1021 generates a data record file and sends the data record file to the intelligent maintenance device 101, so that the intelligent maintenance device 101 can analyze the data.

As shown in fig. 2, fig. 2 is a schematic structural diagram of an intelligent maintenance device in an embodiment, where the intelligent maintenance device 101 includes a core component 1011, a communication component 1012, a computing power and storage component 1013, and a man-machine interaction component 1014. Wherein the intelligent maintenance apparatus 101 may further comprise other components, such as other hardware circuits, sensors, chips, etc., and is not limited to the components in this embodiment. The functions of the core component 1011 include upgrades, fault diagnostics. The communication component 1012 is a component that extends a remote communication function, and can upgrade the device to be maintained 102 into a remote controlled form. The computing power and storage unit 1013 is used to store more data, and when the system is complex and bulky, the storage unit can be expanded to store more data, and to compute more complex air conditioning models. The human-computer interaction component 1014 is a functional component that displays the operating status of the device 102 to be maintained and related parameters. The communication unit 1012, the power and storage unit 1013, and the man-machine interaction unit 1014 may be a device in which a hardware circuit, a sensor, and a chip that realize a certain function are integrated. For example, the communication component 1012 may be an integrated communication chip, and the communication chip is inserted into the device to be maintained 102 through a communication interface, so that the device to be maintained 102 is provided with an extended remote communication function. The computing and storage unit 1013 may be a chip with a computing function and a storage function, and the computing function and the storage function can be provided to the device to be maintained 102 by accessing the chip with the computing function and the storage function into the device to be maintained 102. The human-machine interaction component 1014 can be a display device, and the human-machine interaction can be realized by enabling the device 102 to be maintained to have the function of displaying data by accessing the display device into the device 102 to be maintained. For different application scenarios, maintenance personnel can freely assemble the intelligent maintenance equipment 101 in a modularized form, so that the flexibility of the maintenance equipment is improved.

Referring to fig. 3, a flowchart of an apparatus maintenance method according to an embodiment of the present application is shown. The equipment maintenance method is applied to intelligent maintenance equipment and comprises the following steps:

s11, acquiring an upgrade file of the equipment to be maintained.

In this embodiment, the upgrade file includes a communication configuration file, an upgrade package of each sub-device, and an upgrade package of the collector corresponding to each sub-device. Wherein the communication profile is used to configure communication parameters between the main controller 1021 and each of the sub-devices 1022 such that the main controller 1021 can identify each of the sub-devices 1022. For example, the main controller is connected with the sub-device a and the sub-device B, and different communication ports can be respectively configured for the sub-device a and the sub-device B through the communication configuration file, and the sub-device a corresponds to the communication port C and the sub-device B corresponds to the communication port D, so that when receiving data, the main controller 1021 recognizes the data sent by the communication port C, and can recognize the data sent by the sub-device a. The communication profile is also used to configure communication parameters between each sub-device 1022 and the collector 1023 corresponding to each sub-device 1022 so that each sub-device 1022 can identify the collector 1023 corresponding to each sub-device 1022. For example, the sub-device a includes a collector A1 and a collector A2, where the collector A1 corresponds to the communication port B1, the collector A2 corresponds to the communication port B2, and thus when the sub-device a receives data, it recognizes the data sent by the communication port B1, and can recognize the data sent by the collector A1. After the device 102 to be maintained is upgraded by the communication configuration file, the main controller 1021 can identify the sub-device 1022 and each collector 1023, so that the acquired data record file has the data identifier, and a specific sub-device and a specific collector can be located. Moreover, when the equipment is maintained, maintenance personnel can obtain needed data in a targeted manner, so that the maintenance efficiency is improved.

As shown in fig. 4, fig. 4 is a schematic diagram of upgrading a device to be maintained in an embodiment, where the device to be maintained 102 is an air conditioner, and the intelligent maintenance device 101 includes a core component 1011 and a communication component 1012. The intelligent maintenance apparatus 101 also communicates with a user terminal via a communication component 1012, for example via bluetooth for data transmission with the user terminal. The maintainer obtains the device identifier of the device to be maintained 102 by using the user terminal, and sends the device identifier to the server 100 through the user terminal so as to request the server 100 for an upgrade file corresponding to the device identifier. The user terminal sends the upgrade file corresponding to the device identifier to the intelligent maintenance device 101, and the intelligent maintenance device 101 sends the upgrade file to the device to be maintained 102. The device to be maintained 102 completes the upgrade according to the upgrade file. After the upgrade is completed, the main controller 1021 can identify the sub-device 1022 and each collector 1023, so that the acquired data record file has the data identifier, and can be positioned to the specific sub-device and the specific collector.

In some embodiments, when an upgrade file corresponding to the device identifier is requested, the user terminal may also request the server 100 for the upgrade file for the intelligent maintenance device 101, and after receiving the upgrade file for the intelligent maintenance device 101, the user terminal sends the upgrade file to the intelligent maintenance device 101. The intelligent maintenance device 101 upgrades according to the file to complete the update.

S12, the upgrade file is sent to equipment to be maintained.

In some embodiments, as shown in fig. 4, the user terminal sends the upgrade file corresponding to the device identifier to the intelligent maintenance device 101, and the intelligent maintenance device 101 sends the upgrade file to the device to be maintained 102. In other embodiments, the intelligent maintenance apparatus 101 includes a core component 1011, a communication component 1012, and a human-machine interaction component 1014. The user inputs the device identifier of the device to be maintained 102 through the man-machine interaction component 1014, the intelligent maintenance device 101 requests the file corresponding to the device identifier from the server 100 through the communication component 1012, and after the intelligent maintenance device 101 obtains the upgrade file corresponding to the device identifier, the upgrade file is sent to the device to be maintained 102.

In some embodiments, the intelligent maintenance device 101 may also request its own upgrade file from the server 100 for upgrade to itself.

In some embodiments, the communication parameters include an identification of the communication port, including, but not limited to, a number, an IP address, a communication protocol, and the like. The device to be maintained 102 allocates communication ports, each identifying one of the sub-devices 1022, to a plurality of sub-devices 1022 connected to the main controller 1021 according to a communication profile. The main controller 1021 sends the communication profile of each sub-device to each sub-device 1022, respectively, where the communication profile of each sub-device includes the communication port of the collector under each sub-device. Each sub-device 1022, upon receiving its corresponding communication profile, communicates ports to its corresponding collector 1023, respectively, such that under each sub-device, each communication port identifies one collector 1023. After the device 102 to be maintained is upgraded, each collector 1023 sends the data to the corresponding sub-device 1022 through its corresponding communication port, and the sub-device 1022 sends the data to the main controller 1021 through its communication port, so that the main controller 1021 can identify the main body of the data to be sent, and thus can locate the specific sub-device and the specific collector. After the upgrade, the intelligent maintenance equipment 101 can record and acquire any one piece of sub equipment according to the configured communication parameters and acquire the acquired data of any one collector 1023, so that maintenance personnel can acquire the required data in a targeted manner, the data record of the whole equipment to be maintained is not required, and the problem can be timely checked.

S13, acquiring a data record file sent by the equipment to be maintained.

The data record file is used for indicating the operation state of the equipment to be maintained, wherein the data record file can comprise the operation state of the sub-equipment, the operation state of the collector and the like. The data record file may include, but is not limited to, any one or more of the following: operational data of one or more sub-devices 1022, collected data of one or more collectors 1023.

In some embodiments, the human-computer interaction component 1014 provides a user interface, where a subset option and a collector option are provided, through which a user can select a subset of the subset that needs to obtain data, and through which the user can obtain a collector of the selected subset that needs to obtain data. The child device option and collector option may be drop down boxes, hook boxes, and the like. The main controller 1021 sends a request to the selected sub-device according to the communication port of the selected sub-device, the request is sent to obtain the data record file of the selected sub-device, after the selected sub-device receives the request sent by the main controller 1021, the data record file of the main controller 1021 is sent to the main controller 1021 through the communication port communicated with the main controller 1021, after the main controller 1021 receives the data, the data record file sent by the selected sub-device can be identified according to the communication port, and the main controller 1021 sends the data record file of the selected sub-device to the intelligent maintenance device 101. The maintainer can also test the collectors on site, and through selecting one collector at the collector option, the main controller 1021 can acquire the data collected by the selected collector, so that whether the subsequent analysis collector is normal or not is facilitated, the main controller 1021 acquires the data collected by the selected collector, generates the data record file from the collected data, and sends the generated data record file to the intelligent maintenance equipment 101. For example, the user interface selects the data currently collected in real time by the collector B under the sub-device a, the communication port between the sub-device a and the main controller 1021 is C, the communication port between the sub-device a and the collector B is D, after the main controller 1021 obtains the collector B under the sub-device a selected by the user on the user interface, the main controller 1021 sends a data request to the sub-device a according to the communication port C after configuration of the upgrade file, so as to request the data collected in real time by the collector B, and the sub-device a generates an instruction to the collector B through the communication port D to control the collector B to collect the data in real time. The sub-equipment A acquires the data acquired by the acquirer B in real time through the communication port D, forms the data acquired by the acquirer B into a data record file after the acquisition is finished, sends the data record file to the main controller 1021 through the communication port C, and the main controller 1021 sends the data record file to the intelligent maintenance equipment 101. The man-machine interaction assembly 1014 can provide a user interface to facilitate the user to select data to be analyzed, any one piece of sub-equipment can be recorded and acquired according to the configured communication parameters, and the acquired data of any one of the collectors 1023 can be acquired, so that maintenance personnel can acquire required data in a targeted manner, the data record of the whole equipment to be maintained is not required, problems can be timely checked, and maintenance personnel can analyze the acquired data in a targeted manner, and the maintenance efficiency is improved.

S14, analyzing the data record file by using a preconfigured equipment mechanism model, and determining fault data.

In this embodiment, the plant mechanism model is an accurate mathematical model built from the object, the internal mechanism of the production process, or the delivery mechanism of the material flow. Fault data can be identified by the plant mechanism model. For example, the equipment to be maintained 102 is an air conditioning equipment, and an air conditioning equipment mechanism model is built according to the cooling principle of the air conditioning equipment.

In some embodiments, the data record file indicates operational data of the plurality of sub-devices, the data record file is input into a pre-configured device mechanism model, and fault data is output. The fault data includes fault location and abnormal data at the fault location, such as outputting the fault location as a certain sub-device, outputting the fault location as a collector of a certain sub-device, outputting the fault location as a certain program module, outputting the fault location as a main controller, etc. The fault point at a specific fault location can be located by the abnormal data at the fault location, for example, when the output main controller 1021 is the fault location, the abnormal data at the fault location indicates abnormal communication of the main controller 1021. Therefore, when the equipment to be maintained fails, maintenance personnel can acquire the operation data of a plurality of pieces of sub-equipment without knowing the failure cause, and the operation data of the plurality of pieces of sub-equipment are directly input into the configured model, so that the failure position and the failure point at the failure position can be directly positioned, thereby being convenient for the maintenance personnel to quickly solve the failure.

Further, communication parameters are distributed to a plurality of sub-devices connected with a main controller according to a communication configuration file, each communication parameter identifies a sub-device, each sub-device gives a corresponding collector communication parameter, so that under each sub-device, each communication parameter identifies a collector, the main controller can identify each sub-device and the collector under each sub-device, and accordingly can locate a specific sub-device and a specific collector, recording and acquisition can be carried out on any sub-device according to the configured communication parameters, data acquired by any collector can be acquired, maintenance personnel can conveniently acquire required data, the required data form a data record file, the data record file serves as input data of a pre-configured device mechanism model, the pre-configured device mechanism model analyzes the data record file, abnormal data at a fault position and a fault position are output, and maintenance personnel can conveniently and rapidly solve the fault.

In some embodiments, the method further comprises obtaining a preconfigured device mechanism model. As shown in fig. 5, fig. 5 is a flowchart of acquiring a preconfigured device mechanism model in a device maintenance method according to an embodiment, where the flowchart includes:

s51, acquiring a training sample set.

In this embodiment, each training sample includes a sample record file indicating device operation data and a tag corresponding to the sample record file, where the tag is used to indicate a device operation state corresponding to the sample record file. The sample record file may be a data record file in a fault state or a data record file in a normal state. When the sample record file is a data record file in a fault state, the label of the sample record file indicates the fault state, and when the sample record file is a data record file in a normal state, the label of the sample record file indicates the normal state, for example, a label 0 indicates the fault state, a label 1 indicates the normal state, and the like. When the sample record files are collected, the data record files of the equipment of the same type as the equipment to be maintained in various fault states can be collected, the more the samples are, the stronger the model identification capability is after subsequent training and learning.

S52, establishing an initial equipment mechanism model.

In this embodiment, the number of the initial device mechanism models may be plural, and the initial device mechanism models include an initial linear mechanism model and an initial nonlinear mechanism model. The parameters in the linear mechanism model are linear relations, and the parameters in the pre-configured nonlinear mechanism model are nonlinear relations. In other embodiments, the linear and nonlinear mechanism models may be integrated into an initial plant mechanism model.

S53, inputting the training sample set into an initial equipment mechanism model, and training the initial equipment mechanism model until a training termination condition is reached, so as to obtain a trained equipment mechanism model.

In this embodiment, in each step of iterative training, the training sample set is input into an initial device mechanism model for training, and parameters in the initial device mechanism model are continuously updated in the training process. And when each iteration is performed, calculating a loss value between the input training sample and a label corresponding to the training sample based on a loss function, if the loss value is larger than a preset error value, continuing to randomly select the training sample from the training sample set, inputting the training sample into an initial equipment mechanism model after the current iteration is updated, optimizing parameters in the initial equipment mechanism model after the update, performing the next iteration training, iterating and reciprocating, continuously optimizing parameters of a deep learning gene prediction model, and stopping iterating training until the loss value calculated by the current iteration is smaller than or equal to the preset error or the iteration times is larger than the preset times, and stopping the iterating current equipment mechanism model to obtain the trained equipment mechanism model. The linear mechanism model after iteration stopping is a trained linear mechanism model, and the nonlinear mechanism model after iteration stopping is a trained nonlinear mechanism model.

S54, correcting the trained equipment mechanism model to obtain a corrected equipment mechanism model.

In this embodiment, for correcting a trained linear mechanism model, a trained linear mechanism model and historical linear sample data are obtained, and the trained linear mechanism model is corrected by using a linear regression method, so as to obtain a corrected linear mechanism model, wherein each historical linear sample data includes a parameter value of a linear parameter and a model target value corresponding to the linear parameter.

And for correcting the trained nonlinear mechanism model, acquiring the trained nonlinear mechanism model and historical nonlinear sample data, and correcting the trained nonlinear mechanism model by using a neural network learning method to obtain a corrected nonlinear mechanism model, wherein each historical nonlinear sample data comprises a parameter value of a nonlinear parameter and a model target value corresponding to the nonlinear parameter. The neural network learning method comprises, but is not limited to, a convolutional neural network-based learning method, a cyclic neural network-based learning method and an attention mechanism-based learning method.

In the above embodiment, for the linear mechanism model, based on historical data, the trained linear mechanism model is corrected by using a linear regression method, so that the relation between parameters can be rapidly and accurately described by using a straight line, the model is simple, and the calculated amount is small. For the nonlinear mechanism model, because the nonlinear parameter model relation is complex, the trained nonlinear mechanism model is corrected by inputting historical data and re-learning based on a neural network learning method, so that the follow-up fault recognition accuracy of the nonlinear mechanism model is improved.

S55, simplifying the corrected equipment mechanism model, and taking the simplified equipment mechanism model as a preconfigured equipment mechanism model.

In this embodiment, a parameter relation training sample set is obtained, each training sample includes sample data indicating a parameter relation and a label corresponding to the sample data, where the label is used to indicate the parameter relation corresponding to the sample data, the parameter relation training sample set is input into a corrected device mechanism model, and training is continuously iteratively updated until a condition that the training is finished is reached, where the device mechanism model after the training is a simplified device mechanism model, and the simplified device mechanism model is used as a preconfigured device mechanism model.

In the above embodiment, the initial device mechanism model is trained based on a large number of training samples to obtain a trained device mechanism model, then the trained device mechanism model is corrected by using the historical data, and finally the corrected device mechanism model is simplified to learn the relation between parameters to obtain a preconfigured device mechanism model, so that when the preconfigured device mechanism model is used for fault detection, the calculation speed can be improved, and the accuracy of fault detection can be improved.

In some embodiments, the method further comprises:

acquiring communication signal data of the acquired equipment to be maintained and an upper computer;

according to the collected communication signal data, when the communication between the equipment to be maintained and the upper computer is abnormal, prompting the abnormality; and according to the acquired communication signal data, when the equipment to be maintained is determined to be communicated with the upper computer normally, acquiring serial port data, matching the acquired serial port data with a preset communication protocol, and prompting abnormality if the acquired serial port data is not matched with the preset communication protocol.

Optionally, if the acquired serial data is not matched with the preset communication protocol, matching an abnormal communication protocol model preset by the acquired serial data, determining an abnormal type, and prompting an abnormal reason.

Specifically, as shown in fig. 6, fig. 6 is a schematic diagram illustrating fault detection of a device to be maintained in an embodiment; as shown in fig. 7, fig. 7 is a flowchart illustrating fault detection in the device maintenance method according to an embodiment, and the process of fault detection is described below with reference to fig. 6 and 7. The upper computer 103 is a computing device for monitoring one or more devices to be maintained, the upper computer 103 is in communication connection with the devices to be maintained 102, and a serial port line (such as a serial port AB line) of the intelligent maintenance device 101 is connected in parallel to a communication bus between the upper computer 103 and the devices to be maintained 102.

S71, acquiring communication signal data of the acquired equipment to be maintained 102 and the upper computer 103. Communication signal data of the equipment 102 to be maintained and the upper computer 103 are collected according to a preset time interval, wherein the communication signal data comprise, but are not limited to, differential pressure on an AB line, namely level voltage data of a high-frequency collection communication point.

S72, judging whether the acquired communication signal data is abnormal, and if so, prompting the abnormality; if the collected communication signal data are normal, executing S73, specifically, if the collected pressure difference on the AB line exceeds the preset pressure difference value range, executing S77, prompting communication abnormality, and returning to continue to collect data; if the pressure difference on the collected AB line is within the preset pressure difference value range, the collected communication signal data are normal.

S73, acquiring serial port data from the acquired communication signal data. Specifically, when the acquired communication signal data reach the preset quantity, the preset quantity of communication signal data are used as the acquired serial port data.

S74, judging whether the acquired serial data is matched with a preset communication protocol, if the acquired serial data is matched with the preset communication protocol, communicating normally, and if the acquired serial data is not matched with the preset communication protocol, executing S75.

And S75, judging whether the acquired serial data is matched with a preset communication protocol abnormality model, and if the acquired serial data is matched with the preset communication protocol abnormality model, executing S76 and prompting the abnormality type. If the acquired serial port data is matched with a preset communication protocol abnormality model, prompting abnormality. If the acquired serial port data is not matched with the preset communication protocol abnormality model, executing S77, and prompting communication abnormality.

In the above embodiment, the intelligent maintenance device is connected in parallel to the communication bus of the site, and the level voltage data of the communication point is collected through high frequency. By checking the electrical characteristics of the communication point whether or not there is an out-of-range communication signal, when the communication signal data of the communication point is abnormal, the communication abnormality is presented. When the communication signal data is normal, the communication signal data of the communication point can be judged whether to accord with a preset communication protocol, when the communication signal data of the communication point does not accord with the preset communication protocol, the communication signal data is matched with a preset communication protocol abnormality model to prompt an abnormality type, when maintenance personnel perform field detection, the communication diagnosis is performed on equipment to be maintained by connecting the intelligent maintenance equipment in parallel to a field communication bus, and when the communication abnormality occurs, the primary determination of the reason of the communication abnormality can be determined, so that the field maintenance efficiency is improved.

In some embodiments, the device to be maintained is one or more devices under at least one site, each site corresponds to a plurality of devices, each site corresponds to at least one intelligent maintenance device, and the intelligent maintenance devices in each site are used for maintaining the plurality of devices corresponding to each site.

As shown in fig. 8, taking the to-be-maintained device 102 as an air conditioner for example, the server 100 communicates with a plurality of sites, and as shown in fig. 8, there are n sites, where a plurality of air conditioners are disposed at each site, and one intelligent maintenance device 101 may perform maintenance on a plurality of air conditioners at one site at the same time by using the device maintenance method in the embodiment of the present application. For example, in the energy storage application scenario, each station is a container, a plurality of battery assemblies and a plurality of air conditioners in the container, wherein the plurality of air conditioners are used for cooling the battery assemblies. In this scenario, intelligent maintenance device 101 may include core component 1011, communication component 1012, computing power and storage component 1013. By configuring intelligent maintenance equipment at each site, a plurality of equipment to be maintained of one site can be maintained simultaneously, so that the automatic maintenance equipment can be intelligent, and the maintenance efficiency can be improved.

In some embodiments, uploading the fault data to a server to cause the server to optimize a preconfigured device mechanism model according to the fault data;

and acquiring the optimized equipment mechanism model sent by the server.

For example, as shown in fig. 8, the device maintenance method in the embodiment of the present application is used to maintain that a plurality of air conditioners are provided at each site, and failure data of the air conditioners at the plurality of sites can be obtained, so that the failure data is uploaded to the server 100, and the status of the air conditioners at all sites is displayed in the background of the server 100. The server 100 performs optimization updating on the pre-configured device mechanism model by taking the acquired fault data as a new training sample to obtain an optimized device mechanism model, and then sends the optimized device mechanism model to the intelligent maintenance device 101.

In the above embodiment, the device mechanism model can be optimized according to a plurality of fault data collected at the maintenance site, so that the fault detection capability of the device mechanism model is stronger and more intelligent.

FIG. 9 is a schematic diagram of maintenance on a plurality of devices to be maintained in a device maintenance method according to an embodiment; the to-be-maintained device 102 may be a plurality of to-be-maintained devices, for example, the to-be-maintained device is an air conditioner, the intelligent maintenance device 101 is physically connected with the plurality of air conditioners through a communication line, performs data acquisition on the plurality of air conditioners through the communication line, and then performs maintenance by using the device maintenance method provided by the embodiment of the present application, so as to determine fault data of the plurality of air conditioners. The intelligent maintenance equipment 101 is also communicated with the upper computer 103, and the intelligent maintenance equipment 101 sends the collected data and the determined fault data to the upper computer 103, so that the background real-time monitoring is facilitated. In this application scenario, the intelligent maintenance device 101 may include a core component 101 and a computing and storage component 103.

As shown in fig. 10, fig. 10 is a schematic diagram of maintenance on a plurality of devices to be maintained in a device maintenance method according to another embodiment; the to-be-maintained device 102 may be a plurality of to-be-maintained devices, for example, the to-be-maintained device is an air conditioner, the intelligent maintenance device 101 is physically connected with the plurality of air conditioners through a communication line, performs data acquisition on the plurality of air conditioners through the communication line, and then performs maintenance by using the device maintenance method provided by the embodiment of the present application, so as to determine fault data of the plurality of air conditioners. In this application scenario, the intelligent maintenance device 101 may include a core component 101, a computing and storing component 103, and a man-machine interaction component 104, where fault data of a plurality of air conditioners are displayed on a user interface through the man-machine interaction component 104, so that maintenance personnel can intuitively see the fault data result on site, thereby improving maintenance efficiency.

Referring to fig. 11, an embodiment of the present application provides an apparatus maintenance device, including:

an obtaining module 21, configured to obtain an upgrade file of a device to be maintained, where the device to be maintained includes a main controller, and at least one sub-device connected to the main controller, and each sub-device includes at least one collector, and the upgrade file includes a communication configuration file, where the communication configuration file is used to configure communication parameters of communication between the main controller and each sub-device, so that the main controller can identify each sub-device, and is used to configure communication parameters of communication between each sub-device and a collector corresponding to each sub-device, so that each sub-device can identify a collector corresponding to each sub-device;

The sending module 22 is configured to send the upgrade file to the device to be maintained for upgrading, so that the main controller can identify each piece of equipment, and each piece of equipment can identify a collector corresponding to each piece of equipment;

the obtaining module 21 is further configured to obtain a data record file of the device to be maintained, where the data record file includes: generating a record file of each piece of sub-equipment according to the data acquired by the corresponding collector of each piece of sub-equipment;

the determining module 23 is configured to analyze the data record file using a preconfigured device mechanism model to determine fault data indicative of a fault location.

Optionally, the training module 24 is configured to obtain a training sample set, where each training sample includes a sample record file indicating device operation data and a label corresponding to the sample record file, where the label is configured to indicate a device operation state corresponding to the sample record file;

establishing an initial equipment mechanism model;

inputting the training sample set into an initial equipment mechanism model, and training the initial equipment mechanism model until reaching a training termination condition to obtain a trained equipment mechanism model;

correcting the trained equipment mechanism model to obtain a corrected equipment mechanism model;

Simplifying the corrected equipment mechanism model, and taking the simplified equipment mechanism model as a preconfigured equipment mechanism model.

Optionally, the preconfigured device mechanism model includes a preconfigured linear mechanism model, and a preconfigured nonlinear mechanism model, where parameters in the linear mechanism model are linear relationships, and parameters in the preconfigured nonlinear mechanism model are nonlinear relationships, and the training module 24 is further configured to:

acquiring a trained linear mechanism model and historical linear sample data, and correcting the trained linear mechanism model by using a regression method to obtain a corrected linear mechanism model, wherein each historical linear sample data comprises a parameter value of a linear parameter and a model target value corresponding to the linear parameter;

and acquiring a trained nonlinear mechanism model and historical nonlinear sample data, and correcting the trained nonlinear mechanism model by using a neural network learning method to obtain a corrected nonlinear mechanism model, wherein each historical nonlinear sample data comprises a parameter value of a nonlinear parameter and a model target value corresponding to the nonlinear parameter.

Optionally, the determining module 23 is further configured to acquire collected communication signal data of the device to be maintained and the upper computer;

Optionally, the determining module 23 is further configured to match the acquired serial port data with a preset communication protocol anomaly model, prompt an anomaly type, and prompt an anomaly cause if the acquired serial port data is not matched with the preset communication protocol.

Optionally, the device to be maintained is one or more devices under at least one site, each site corresponds to a plurality of devices, each site corresponds to at least one intelligent maintenance device, and the intelligent maintenance devices in each site are used for maintaining the plurality of devices corresponding to each site.

Optionally, the determining module 23 is further configured to upload the fault data to a server, so that the server optimizes a preconfigured device mechanism model according to the fault data;

and acquiring the optimized equipment mechanism model sent by the server.

It will be appreciated by those skilled in the art that the structure of the device maintenance apparatus in fig. 11 does not constitute a limitation of the device maintenance apparatus, and the respective modules may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or independent of a controller in a computer device, or may be stored in software in a memory in the computer device, so that the controller may call and execute operations corresponding to the above modules. In other embodiments, more or fewer modules than shown may be included in the equipment maintenance device.

Referring to fig. 12, in another aspect of the embodiments of the present application, there is further provided an intelligent maintenance apparatus 101, including a memory 3011 and a processor 3012, where the memory 3011 stores a computer program, and the computer program when executed by the processor causes the processor 212 to execute the steps of the apparatus maintenance method provided in any of the embodiments of the present application. The smart maintenance device 101 may include a computing device (e.g., desktop computer, laptop computer, tablet computer, handheld computer, smart speaker, server, etc.), mobile phone (e.g., smart phone, wireless phone, etc.), wearable device (e.g., a pair of smart glasses or smart watch), or the like.

Where the processor 3012 is a control center, various interfaces and lines are utilized to connect various portions of the overall computer device, perform various functions of the computer device and process data by running or executing software programs and/or modules stored in the memory 3011, and invoking data stored in the memory 3011. Optionally, the processor 3012 may include one or more processing cores; preferably, the processor 3012 may integrate an application processor and a modem processor, wherein the application processor primarily handles operating systems, user pages, applications, etc., and the modem processor primarily handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 3012.

The memory 3011 may be used to store software programs and modules, and the processor 3012 executes various functional applications and data processing by executing the software programs and modules stored in the memory 3011. The memory 3011 may mainly include a storage program area that may store an operating system, application programs required for at least one function (such as a sound playing function, an image playing function, etc.), and a storage data area; the storage data area may store data created according to the use of the computer device, etc. In addition, memory 3011 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 3011 may also include a memory controller to provide access to the memory 3011 by the processor 3012.

In another aspect of the embodiments of the present application, there is further provided a storage medium storing a computer program, where the computer program when executed by a processor causes the processor to perform the steps of the apparatus maintenance method provided in any of the foregoing embodiments of the present application.

Those skilled in the art will appreciate that implementing all or part of the processes of the methods provided in the above embodiments may be accomplished by computer programs stored on a non-transitory computer readable storage medium, which when executed, may comprise processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.

The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. The scope of the invention is to be determined by the appended claims.

Claims

1. The equipment maintenance method is applied to intelligent maintenance equipment and is characterized by comprising the following steps of:

acquiring an upgrade file of equipment to be maintained;

the upgrade file is sent to the equipment to be maintained for upgrade;

acquiring a data record file of equipment to be maintained;

2. The device maintenance method of claim 1, wherein the device to be maintained comprises a main controller, at least one sub-device connected to the main controller, each sub-device comprising at least one collector, the upgrade file comprising a communication profile, wherein the communication profile is used to configure communication parameters for communication between the main controller and each sub-device, such that the main controller can identify each sub-device, and to configure communication parameters for communication between each sub-device and a collector corresponding to each sub-device, such that each sub-device can identify a collector corresponding to each sub-device, wherein the data record file comprises: and generating a record file of each piece of sub-equipment according to the data acquired by the corresponding collector of each piece of sub-equipment.

3. The equipment maintenance method of claim 1, wherein the method further comprises:

acquiring training sample sets, wherein each training sample comprises a sample record file indicating equipment operation data and a label corresponding to the sample record file, and the label is used for indicating the equipment operation state corresponding to the sample record file;

establishing an initial equipment mechanism model;

4. The equipment maintenance method as in claim 2, wherein the preconfigured equipment mechanism model comprises a preconfigured linear mechanism model, and a preconfigured nonlinear mechanism model, wherein parameters in the linear mechanism model are linear relationships, parameters in the preconfigured nonlinear mechanism model are nonlinear relationships, and the correcting the trained equipment mechanism model to obtain the corrected equipment mechanism model comprises:

5. The equipment maintenance method of claim 1, wherein the method further comprises:

acquiring collected communication signal data of the equipment to be maintained and an upper computer;

according to the collected communication signal data, when the communication between the equipment to be maintained and the upper computer is abnormal, prompting the abnormality; according to the collected communication signal data, when the equipment to be maintained is determined to be communicated with the upper computer normally, serial port data are obtained, the obtained serial port data are matched with a preset communication protocol, and if the obtained serial port data are not matched with the preset communication protocol, abnormality is prompted;

And if the acquired serial data is not matched with the preset communication protocol, matching the acquired serial data with a preset communication protocol abnormality model, prompting an abnormality type and prompting an abnormality reason.

6. The device maintenance method according to claim 1, wherein the device to be maintained is one or more devices under at least one site, each site corresponds to a plurality of devices, each site corresponds to at least one intelligent maintenance device, and the intelligent maintenance devices in each site are used for maintaining the plurality of devices corresponding to each site.

7. The equipment maintenance method of any one of claims 1 to 6, further comprising:

uploading the fault data to a server so that the server optimizes a preconfigured equipment mechanism model according to the fault data;

and acquiring the optimized equipment mechanism model sent by the server.

8. An equipment maintenance device, comprising:

9. A smart maintenance device comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of the method of any one of claims 1 to 7.

10. A computer readable storage medium storing a computer program, which when executed by a processor causes the processor to perform the steps of the method according to any one of claims 1 to 7.