CN112596486A

CN112596486A - Big data and edge computing-based remote information processing method and cloud server

Info

Publication number: CN112596486A
Application number: CN202011531107.0A
Authority: CN
Inventors: 陆银华
Original assignee: Individual
Current assignee: Individual
Priority date: 2020-12-22
Filing date: 2020-12-22
Publication date: 2021-04-02

Abstract

The embodiment of the application discloses a big data and edge computing based remote information processing method and a cloud server, wherein the big data and edge computing based remote information processing method comprises the following steps: the method comprises the steps of analyzing historical state information in an equipment state alarm record to determine state alarm indicating information, updating production index safety data to obtain a target state information set, and further determining an equipment operation monitoring index which has time sequence relevance with the equipment state alarm record.

Description

Big data and edge computing-based remote information processing method and cloud server

Technical Field

The application relates to the technical field of big data and edge computing, in particular to a remote information processing method based on big data and edge computing and a cloud server.

Background

The advent of the big data age has driven the industrial internet towards more intelligent. Modern manufacturing is also gradually upgrading from manual management to remote management. Such as chip semiconductor manufacturing, automobile manufacturing, food production, and cosmetic production, are almost all shifting to "unattended production mode".

With the increasing scale and complexity of industrial equipment devices and engineering control systems, it is very urgent and important to monitor and diagnose the abnormal state of industrial equipment in time and effectively by reliable state monitoring technology in order to ensure the safety and stability of the production process, thereby reducing the loss caused by equipment failure to the maximum extent.

Disclosure of Invention

One of the embodiments of the present application provides a telematics method based on big data and edge calculation, where the method includes: acquiring a historical state information set corresponding to the production condition of an equipment state alarm record, wherein the historical state information comprises industrial equipment state tracks corresponding to different production indexes; identifying the classification result of the production index data in the equipment state alarm record through a historical state information set corresponding to the production condition of the equipment state alarm record, and determining state alarm indication information of the classification result of the production index data in the equipment state alarm record; screening the production index safety data and the production index abnormal data of the historical state information according to the classification result of the production index data in the equipment state alarm record; locking abnormal production index data in the historical state information, and updating production indexes of the production index safety data in the historical state information to form a target state information set; and identifying the equipment state alarm record through the target state information set, determining an equipment operation monitoring index having time sequence correlation with the equipment state alarm record, monitoring the equipment state information to be monitored through the state alarm indication information and the equipment operation monitoring index, and determining corresponding equipment state fault information.

One of the embodiments of the present application provides a cloud server, including a processing engine, a network module, and a memory; the processing engine and the memory communicate through the network module, and the processing engine reads the computer program from the memory and operates to perform the above-described method.

One of the embodiments of the present application provides a computer storage medium, on which a computer program is stored, where the computer program is executed to implement the method described above.

In the description that follows, additional features will be set forth, in part, in the description. These features will be in part apparent to those skilled in the art upon examination of the following and the accompanying drawings, or may be learned by production or use. The features of the present application may be realized and attained by practice or use of various aspects of the methodologies, instrumentalities and combinations particularly pointed out in the detailed examples that follow.

Drawings

The present application will be further explained by way of exemplary embodiments, which will be described in detail by way of the accompanying drawings. These embodiments are not intended to be limiting, and in these embodiments like numerals are used to indicate like structures, wherein:

FIG. 1 is a block diagram of an exemplary big data and edge computing based telematics system, according to some embodiments of the present invention;

FIG. 2 is a schematic diagram of the hardware and software components in an exemplary cloud server, according to some embodiments of the invention;

FIG. 3 is a flow diagram illustrating an exemplary big data and edge computation based telematics method and/or process according to some embodiments of the present invention; and

FIG. 4 is a block diagram of an exemplary big data and edge computation based telematics device, according to some embodiments of the present invention.

Detailed Description

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings used in the description of the embodiments will be briefly introduced below. It is obvious that the drawings in the following description are only examples or embodiments of the application, from which the application can also be applied to other similar scenarios without inventive effort for a person skilled in the art. Unless otherwise apparent from the context, or otherwise indicated, like reference numbers in the figures refer to the same structure or operation.

It should be understood that "system", "device", "unit" and/or "module" as used herein is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, other words may be substituted by other expressions if they accomplish the same purpose.

As used in this application and the appended claims, the terms "a," "an," "the," and/or "the" are not intended to be inclusive in the singular, but rather are intended to be inclusive in the plural unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that steps and elements are included which are explicitly identified, that the steps and elements do not form an exclusive list, and that a method or apparatus may include other steps or elements.

Flow charts are used herein to illustrate operations performed by systems according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in the exact order in which they are performed. Rather, the various steps may be processed in reverse order or simultaneously. Meanwhile, other operations may be added to the processes, or a certain step or several steps of operations may be removed from the processes.

The inventor finds through research and analysis that most of common production state monitoring technologies for industrial equipment are carried out through pre-specified monitoring rules or monitoring standards, so that a good fault monitoring effect can be achieved at the initial stage of equipment operation, but with the continuous increase of the accumulated operation time of the equipment, the inducement of equipment faults is also increased, the state monitoring of the industrial equipment is mechanically carried out through a fixed monitoring mode, not only the time delay of fault monitoring can be caused, but also the missing detection can occur, and thus serious production accidents can be caused.

Aiming at the problems, the inventor provides a remote information processing method and a cloud server based on big data and edge calculation in a targeted manner, historical state information in an equipment state alarm record is analyzed, so that state alarm indication information is determined based on different working conditions, and screening of production index safety data and production index abnormal data is realized through a classification result of the production index data in the equipment state alarm record, so that the production index safety data can be updated to obtain a target state information set, and further an equipment operation monitoring index having time sequence correlation with the equipment state alarm record is determined, so that real-time reliable monitoring of the equipment state information to be monitored can be realized based on the state alarm indication information and the equipment operation monitoring index, and the equipment operation monitoring index takes the accumulated operation time of industrial equipment into account, therefore, the time sequence synchronism of state monitoring can be ensured, the fault inducement of the industrial equipment is taken into consideration as much as possible, the timeliness of fault monitoring is ensured, and meanwhile, missing detection is avoided, so that serious production accidents are avoided.

First, a telematics method based on big data and edge calculation is exemplarily described, referring to fig. 1, which is a flowchart illustrating an exemplary telematics method and/or process based on big data and edge calculation according to some embodiments of the present invention, and the telematics method based on big data and edge calculation may include the technical solutions described in the following steps S1-S4.

Step S1, obtaining a historical state information set corresponding to the production condition of the equipment state alarm record, wherein the historical state information includes industrial equipment state tracks corresponding to different production indexes. For example, the device status alarm record may include previous status failure monitoring information, and the production conditions may have differences in different time periods, so that the industrial device status tracks in the historical status information may also have differences in different production indexes. Further, the production index may be adaptively set according to production requirements, such as a product shipment rate, a processing time of the product at each node, and the like, and is not limited herein. The industrial device status trace can include a status trace of the industrial device on multiple levels (e.g., a current travel trace, a voltage travel trace, a mechanical device depreciation trace, etc.).

Step S2, identifying the classification result of the production index data in the equipment status alarm record through the historical status information set corresponding to the production condition of the equipment status alarm record, and determining status alarm indication information of the classification result of the production index data in the equipment status alarm record. For example, the classification result of the production index data may be obtained by classifying and summarizing different types of production index data, and the production index data may be classified according to, for example, a time-based production index, a production-based production index, and a facility-based production index, or may be classified according to other manners, which is not limited herein. The status alarm indication information is used to indicate how an alarm should be made when an abnormal state or a fault state occurs, for example, at what time and in what manner the node should make an alarm.

Step S3, screening the production index safety data and the production index abnormal data of the historical state information according to the classification result of the production index data in the equipment state alarm record; locking abnormal production index data in the historical state information, and updating production indexes of the production index safety data in the historical state information to form a target state information set. Further, the screening of the production index safety data and the production index abnormal data may be performed according to data tags carried by the production index safety data and the production index abnormal data, which are not described herein again. For example, the production index safety data is used for representing that the equipment operation data in the historical state information is normal, the production index abnormal data is used for representing that the equipment operation data in the historical state information is abnormal, the production index safety data and the production index abnormal data of the historical state information are screened, the production index safety data can be analyzed in a targeted mode, the accumulated operation duration of the industrial equipment is considered when the production index safety data are analyzed, the production index safety data are updated, and therefore the historical state information can be optimized to obtain the target state information.

Step S4, identifying the equipment state alarm record through the target state information set, determining an equipment operation monitoring index having time sequence correlation with the equipment state alarm record, monitoring the equipment state information to be monitored through the state alarm indication information and the equipment operation monitoring index, and determining corresponding equipment state fault information. For example, the time sequence correlation can be understood as that the time sequence synchronism and the time sequence continuity exist between the equipment operation monitoring index and the equipment state alarm record, that is, when the equipment state alarm record changes along with the lapse of time, the equipment operation monitoring index is also updated along with the lapse of time, so that the equipment operation monitoring index can be ensured to be matched with the actual industrial production state. The state information of the equipment to be monitored can be real-time state information of certain industrial equipment, and the state monitoring is carried out based on the state alarm indication information and the equipment operation monitoring index, so that the time sequence synchronism of the state monitoring can be ensured to ensure the real-time performance and the reliability of the equipment state fault information, the fault inducement of the industrial equipment is considered as far as possible, the timeliness of the fault monitoring is ensured, and meanwhile, the missing detection is avoided, so that the serious production accident is avoided.

In the following, some alternative embodiments will be described, which should be understood as examples and not as technical features essential for implementing the present solution.

In some embodiments, the step of obtaining the historical state information set corresponding to the production condition of the equipment state alarm record described in the step S1 may include the following steps S11-S14.

And step S11, acquiring the equipment state track generated by the edge monitoring equipment corresponding to the production condition of the equipment state alarm record. For example, the edge monitoring device may be an intelligent device capable of relevant operational data acquisition and processing. The device state trajectory may be a trajectory curve or a trajectory data list, and is not limited herein.

And step S12, performing track denoising processing on the equipment state track.

And step S13, determining a corresponding equipment state label through the equipment state monitoring model based on the track denoising processing result, and determining an equipment state track comprising a production line interaction track. For example, the device status monitoring model may be a neural network model, and is not limited herein. A line interaction trajectory may be understood as a state trajectory corresponding to line switching, adjustment and scheduling.

Step S14, extracting the state information of the equipment state track including the production line interaction track according to the fault category statistical result of the equipment state alarm record, and using the extracted corresponding area track description information as any historical state information in the historical state information set corresponding to the production condition of the equipment state alarm record. For example, the area track description information may be understood as information corresponding to the state tracks of different time periods.

By designing in this way, based on the steps S11 to S14, the generation process of the device status track can be performed by sinking to the edge, so that not only the accuracy of acquiring the historical status information but also the real-time performance of acquiring the historical status information can be ensured, and the processing pressure of the cloud server can be reduced.

In other possible embodiments, the method may further include: determining index type data of corresponding production indexes according to historical state information corresponding to the production working conditions of the equipment state alarm records; and combining the production indexes of the production index statistical results of the equipment state alarm records according to the index type data of the production indexes to obtain a production index combined result, judging the production index type to which the received equipment state track belongs according to the production index combined result, and determining the production index type to which the received equipment state track belongs.

In some embodiments, in order to ensure that the processing indication for the related fault can be completely reflected by the status alarm indication information, the step S2 identifies the classification result of the production index data in the equipment status alarm record through the historical status information set corresponding to the production condition of the equipment status alarm record, and the status alarm indication information for determining the classification result of the production index data in the equipment status alarm record may include the following steps S21-S24.

And step S21, determining corresponding equipment mechanical state information and equipment communication state information through the historical state information set corresponding to the production condition of the equipment state alarm record. For example, the device mechanical state information can reflect a connection state or a hardware loss state of the industrial device in terms of a mechanical structure, and the device communication state information can reflect a state of the industrial device at a data information transmission level.

And step S22, adjusting the historical state information corresponding to different equipment mechanical states in the historical state information set and the production index safety data in the historical state information corresponding to the equipment communication state according to the production line flow information corresponding to the historical production line by using a normal index classification sub-result in the classification result of the production index data to form the adjusted state alarm index data. For example, the historical production line may be a production line corresponding to a previous production demand or a production manner, and the production line flow information may be operation flow information of the entire plant. The status alarm indicator data is used for determining status alarm indication information.

And step S23, performing mean filtering processing on the adjusted state alarm index data according to the abnormal index classification sub-result in the classification result of the production index data to obtain a mean filtering processing result. For example, the abnormal index may be some error index caused by an unexpected production situation, and the mean filtering may implement the correction and optimization of the state alarm index data.

Step S24, when obtaining the trajectory alarm index data of different production index data of the same equipment state based on the mean value filtering processing result, determining the state alarm indication information of the classification result of the production index data in the equipment state alarm record according to the trajectory alarm index data.

By implementing the steps S21-S24, the device mechanical state information and the device communication state information can be considered, and the corresponding correction and optimization can be realized when the state alarm index data is determined, so that the state alarm indication information can completely reflect the processing indication of the related fault.

For some possible embodiments, on the basis of the above steps S21-S24, the following steps S25-S28 may be further included.

And step S25, determining corresponding mechanical fault type information based on the equipment mechanical state information.

And step S26, determining corresponding communication fault type information based on the equipment communication state information.

Step S27, when determining the status alarm indication information of the classification result of the production index data in the equipment status alarm record, determining the comprehensive fault category information corresponding to the adjusted status alarm index data according to the fault category statistical result of the equipment status alarm record.

Step S28, comparing the mechanical fault category information or the communication fault category information with the comprehensive fault category information to determine the data update state of the abnormal production indicator data in the historical state information corresponding to the different mechanical states of the equipment and the historical state information corresponding to the communication states of the equipment.

In some examples, the locking of the abnormal production indicator data in the historical status information and the production indicator updating of the safety production indicator data in the historical status information to form the target status information set, which are described in step S3, may be implemented by one of the following two implementations.

In a first implementation mode, abnormal production index data in the historical state information is locked, missing value filling is performed on production index safety data in the historical state information by adopting a minimum neighbor method, and a target state information set is formed.

In a second embodiment, production index abnormal data in the historical state information is locked, and bicubic interpolation processing or bilinear interpolation processing is performed on production index safety data in the historical state information to form a target state information set.

In some possible embodiments, the identifying the device status alarm record according to the target status information set in step S4, determining a device operation monitoring indicator having a time sequence relationship with the device status alarm record, monitoring the device status information to be monitored according to the status alarm indication information and the device operation monitoring indicator, and determining corresponding device status failure information may include the following steps S41-S43.

And step S41, identifying the equipment state alarm record according to the target state information set, and determining an equipment operation monitoring index of the production equipment energy consumption statistical result in the equipment state alarm record.

And step S42, identifying the equipment state alarm record according to the target state information set, and determining the equipment operation monitoring index of the product yield statistical result in the equipment state alarm record.

And step S43, monitoring the state information of the equipment to be monitored through the equipment operation monitoring index of the production equipment energy consumption statistical result and the equipment operation monitoring index of the product yield statistical result, and determining the equipment state fault information corresponding to the state information of the equipment to be monitored.

It can be understood that, through the above steps S41-S43, the monitoring of the status information of the device to be monitored can be realized through the device energy consumption level and the product yield level, so that the time sequence synchronization of the status monitoring can be ensured to ensure the real-time performance and reliability of the status fault information of the device, and the fault inducement of the industrial device is taken into consideration as much as possible, thereby ensuring the timeliness of the fault monitoring, and simultaneously avoiding the occurrence of missing detection to avoid causing serious production accidents.

Further, the identifying the device status alarm record according to the target status information set and determining the device operation monitoring indicator of the production device energy consumption statistical result in the device status alarm record described in step S41 may include the following steps S411 to S413.

Step S411, classifying the state information of the target state information set according to a time sequence order according to the energy consumption statistical result of the production equipment in the equipment state alarm record, so as to determine a local energy consumption monitoring index of the energy consumption statistical result of the production equipment.

Step S412, responding to the local energy consumption monitoring index of the production equipment energy consumption statistical result, classifying the state information of the target state information set according to the time sequence precedence order through the production equipment energy consumption statistical result, and determining the global energy consumption monitoring index of the production equipment energy consumption statistical result.

Step S413, according to the global energy consumption monitoring index of the production equipment energy consumption statistical result, performing gradient iteration processing on the energy consumption monitoring index of the production equipment energy consumption statistical result through the target state information set, so as to determine energy consumption alarm index data of each target state information in the target state information set.

By adopting the design, the local energy consumption and the global energy consumption of the industrial equipment can be analyzed in time sequence order by applying the steps S411 to S413, so that the accuracy and the real-time performance of the energy consumption alarm index data of the target state information are ensured by gradient iteration processing.

In this embodiment, the code related to the model of the gradient iteration process is as follows, and it is needless to say that, in the specific implementation, the adaptive adjustment may be performed according to the actual situation, and is not limited herein.

import torch

import matplotlib.pyplot as plt

%matplotlib inline

x = torch. tenasor ([100 ]) # trained alone and not requiring a gradient

y = torch.tensor([110.])

Tenasor ([1 ], require _ grad = True) # modeled network parameters

lr = 0.00001 # learning rate

arr = []

for i in range(10):

pred = x * w

loss = (pred-y) × (pred-y) # square error

Backsward () # calculated gradient

print("real", y.item(), "pred", pred.item(), "loss", loss.item())

print("w.data", w.data.item(), "w.grad", w.grad.item())

Modulating parameters according to learning rate in w.data = w.data-lr. w.grad #

Gradient 0, otherwise the gradient will be accumulated continuously

arr.append(loss.item())

plt.plot(arr)

Further, the local energy consumption monitoring index responding to the production equipment energy consumption statistical result, which is described in step S412, may include the following contents, where the status information of the target status information set is classified according to a time sequence order according to the production equipment energy consumption statistical result, and the global energy consumption monitoring index of the production equipment energy consumption statistical result is determined: inputting different target state information in the target state information set into an energy consumption prediction neural network corresponding to the energy consumption statistical result of the production equipment; and determining the global energy consumption monitoring index corresponding to the energy consumption statistical result of the production equipment when the energy consumption prediction neural network meets the corresponding convergence condition.

For example, the relevant processing procedure of the energy consumption prediction neural network is as follows.

% empty Environment variable

clc

clear

% network parameter configuration

load traffic_flux input output input_test output_test

M = size (input, 2);% input energy consumption predicted node number

N = size (output, 2)% output energy consumption predicted node number

n = 6%

lr1= 0.01% learning probability

lr2= 0.001%

maxgen = 100;% number of iterations

% weight initialization

Wjk=randn(n,M);Wjk_1=Wjk;Wjk_2=Wjk_1;

Wij=randn(N,n);Wij_1=Wij;Wij_2=Wij_1;

a=randn(1,n);a_1=a;a_2=a_1;

b=randn(1,n);b_1=b;b_2=b_1;

% node initialization

y=zeros(1,N);

net=zeros(1,n);

net_ab=zeros(1,n);

% weight learning increment initialization

d_Wjk=zeros(n,M);

d_Wij=zeros(N,n);

d_a=zeros(1,n);

d_b=zeros(1,n);

% input output data normalization

[inputn,inputps]=mapminmax(input');

[outputn,outputps]=mapminmax(output');

inputn=inputn';

outputn=outputn';

error=zeros(1,maxgen);

% network training

for i=1:maxgen

% error accumulation

error(i)=0;

% cycle training

for kk=1:size(input,1)

x=inputn(kk,:);

yqw=outputn(kk,:);

for j=1:n

for k=1:M

net(j)=net(j)+Wjk(j,k)*x(k);

net_ab(j)=(net(j)-b(j))/a(j);

end

temp=mymorlet(net_ab(j));

for k=1:N

y = y + Wij (k, j) × temp;% wavelet function

end

% calculation error sum

error(i)=error(i)+sum(abs(yqw-y));

% weight adjustment

for j=1:n

% calculation d _ Wij

temp=mymorlet(net_ab(j));

for k=1:N

d_Wij(k,j)=d_Wij(k,j)-(yqw(k)-y(k))*temp;

end

% calculation d _ Wjk

temp=d_mymorlet(net_ab(j));

for k=1:M

for l=1:N

d_Wjk(j,k)=d_Wjk(j,k)+(yqw(l)-y(l))*Wij(l,j) ;

end

d_Wjk(j,k)=-d_Wjk(j,k)*temp*x(k)/a(j);

end

% calculation d _ b

for k=1:N

d_b(j)=d_b(j)+(yqw(k)-y(k))*Wij(k,j);

end

d_b(j)=d_b(j)*temp/a(j);

% calculation d _ a

for k=1:N

d_a(j)=d_a(j)+(yqw(k)-y(k))*Wij(k,j);

end

d_a(j)=d_a(j)*temp*((net(j)-b(j))/b(j))/a(j);

end

% weight parameter update

Wij=Wij-lr1*d_Wij;

Wjk=Wjk-lr1*d_Wjk;

b=b-lr2*d_b;

a=a-lr2*d_a;

d_Wjk=zeros(n,M);

d_Wij=zeros(N,n);

d_a=zeros(1,n);

d_b=zeros(1,n);

y=zeros(1,N);

net=zeros(1,n);

net_ab=zeros(1,n);

Wjk_1=Wjk;Wjk_2=Wjk_1;

Wij_1=Wij;Wij_2=Wij_1;

a_1=a;a_2=a_1;

b_1=b;b_2=b_1;

end

% network prediction

% predicted input normalization

x=mapminmax('apply',input_test',inputps);

x=x';

yuce=zeros(92,1);

% network prediction

for i=1:92

x_test=x(i,:)

for j=1:1:n

for k=1:1:M

net(j)=net(j)+Wjk(j,k)*x_test(k);

net_ab(j)=(net(j)-b(j))/a(j);

end

temp=mymorlet(net_ab(j));

for k=1:N

y(k)=y(k)+Wij(k,j)*temp ;

end

yuce(i)=y(k);

y=zeros(1,N);

net=zeros(1,n);

net_ab=zeros(1,n);

end

% predicted output inverse normalization

ynn=mapminmax('reverse',yuce,outputps);

% results analysis

figure(1)

plot(ynn,'r*:')

hold on

plot(output_test,'bo--')

title ('predictive device energy consumption', 'fontsize',12)

legend ('predicted device energy consumption', 'actual device energy consumption', 'fontsize',12)

xlabel ('time point')

ylabel ('Equipment energy consumption')

Further, the step S413 of performing gradient iteration processing on the energy consumption monitoring index of the statistical result of the energy consumption of the production equipment through the target state information set according to the global energy consumption monitoring index of the statistical result of the energy consumption of the production equipment to determine the energy consumption alarm index data of each target state information in the target state information set may include: determining an energy consumption prediction neural network corresponding to the energy consumption statistical result of the production equipment; performing gradient iteration processing on the energy consumption monitoring index of the energy consumption statistical result of the production equipment according to the global energy consumption monitoring index of the energy consumption statistical result of the production equipment; until the energy consumption prediction neural network of the production equipment energy consumption statistical result reaches a corresponding convergence condition, and based on the energy consumption monitoring index in the production equipment energy consumption statistical result, extracting energy consumption warning index data of each target state information in the target state information set.

For some possible embodiments, the step S43 of monitoring the state information of the device to be monitored through the device operation monitoring index of the production device energy consumption statistical result and the device operation monitoring index of the product yield statistical result, and determining the device state fault information corresponding to the device state information to be monitored may include the following steps S431 to S434.

Step S431, acquiring monitoring label information of the device operation monitoring index of the production device energy consumption statistical result and monitoring label information of the device operation monitoring index of the product yield statistical result, wherein the monitoring label information of the device operation monitoring index of the production device energy consumption statistical result includes a state fault label of the device operation monitoring index of the production device energy consumption statistical result, and the monitoring label information of the device operation monitoring index of the product yield statistical result includes a state fault label of the device operation monitoring index of the product yield statistical result;

step S432, inputting the monitoring label information of the equipment operation monitoring index of the production equipment energy consumption statistical result and the monitoring label information of the equipment operation monitoring index of the product yield statistical result into a preset neural network model to obtain an energy consumption fault identification result of the monitoring label information of the equipment operation monitoring index of the production equipment energy consumption statistical result and a production fault identification result of the monitoring label information of the equipment operation monitoring index of the product yield statistical result; the preset neural network model is obtained by training a neural network model to be trained through a training sample set of monitoring label information, the training sample set of the monitoring label information comprises a plurality of non-updatable sample monitoring label information and a plurality of updatable sample monitoring label information obtained by processing the plurality of non-updatable sample monitoring label information, the plurality of non-updatable sample monitoring label information collectively comprise a plurality of different sample state fault labels, the plurality of updatable sample monitoring label information collectively comprise a plurality of different sample state fault labels, the preset neural network model meets a set training condition, the set training condition comprises that the clustering center degree of a monitoring index clustering result of a device operation monitoring index of a production device energy consumption statistical result corresponding to each sample state fault label is smaller than the pre-updated degree of a device operation monitoring index of a production device energy consumption statistical result Setting a centrality;

step S433, processing the energy consumption fault recognition result of the monitoring label information of the equipment operation monitoring index of the production equipment energy consumption statistical result and the production fault recognition result of the monitoring label information of the equipment operation monitoring index of the product yield statistical result through the preset neural network model to obtain a global recognition result, the global identification result is used for indicating a state fault label of the equipment operation monitoring index of the production equipment energy consumption statistical result in the monitoring label information of the equipment operation monitoring index of the production equipment energy consumption statistical result and a state fault label of the equipment operation monitoring index of the product yield statistical result in the monitoring label information set of the equipment operation monitoring index of the product yield statistical result, wherein the state fault labels are matched state fault labels or unmatched state fault labels;

step S434, when the global identification result indicates that the status failure tag of the device operation monitoring index of the device operation monitoring result of the production device energy consumption statistical result and the status failure tag of the device operation monitoring index of the product yield statistical result in the monitoring tag information set of the device operation monitoring index of the production device energy consumption statistical result are matched status failure tags, monitoring the status information of the device to be monitored by using the global identification result, and determining the device status failure information corresponding to the status information of the device to be monitored; the equipment state fault information comprises an operating current fault, an operating voltage fault, an operating power fault, a communication delay fault and a mechanical structure damage fault.

Therefore, based on the steps S431 to S434, the monitoring label information of the device operation monitoring index of the production device energy consumption statistical result and the monitoring label information of the device operation monitoring index of the product yield statistical result can be processed, and the device state fault information corresponding to the device state information to be monitored is determined based on the obtained global identification result, so that different fault conditions can be monitored to avoid missing detection, and complete and reliable fault state monitoring is realized.

In addition, before the monitoring label information of the device operation monitoring index of the production device energy consumption statistical result and the monitoring label information of the device operation monitoring index of the product yield statistical result are input into the preset neural network model in step S432, the method further includes a training process for the preset neural network model, which is further described as follows: acquiring a training sample set of the monitoring label information, wherein the training sample set of the monitoring label information comprises i non-updatable sample monitoring label information and i corresponding updatable sample monitoring label information, the i non-updatable sample monitoring label information comprises j different sample state fault labels in total, the i updatable sample monitoring label information comprises j different sample state fault labels in total, each sample state fault label appears in k sample monitoring label information in the i updatable sample monitoring label information and k sample monitoring label information in the updatable sample monitoring label information, and i, j and k are integers greater than 1; and training the neural network model to be trained by using the training sample set of the monitoring label information to obtain the preset neural network model meeting the target monitoring index clustering result.

For some further embodiments, obtaining a training sample set of the monitoring tag information comprises: performing interpolation processing on each piece of non-updatable monitoring label information in the training sample set of monitoring label information to obtain a training sample set of target monitoring label information of an equipment operation monitoring index of a production equipment energy consumption statistical result, wherein each piece of monitoring label information in the training sample set of target monitoring label information is marked; acquiring a set number of updatable tag attributes; and randomly loading the updatable label attribute into each piece of non-updatable monitoring label information to obtain a training sample set of target monitoring label information of the equipment operation monitoring index of the product yield statistical result, wherein the training sample set of the monitoring label information comprises the target training monitoring label information set of the equipment operation monitoring index of the product yield statistical result.

For some possible embodiments, on the basis of step S4, the following step S5 is further included: determining a shutdown maintenance strategy of a target production area according to the equipment state fault information; the equipment state fault information comprises an operating current fault, an operating voltage fault, an operating power fault, a communication delay fault and a mechanical structure damage fault. Therefore, the shutdown maintenance strategy is determined, so that the influence of shutdown maintenance can be minimized in the later period of shutdown maintenance, the production efficiency of a target production area or other production areas is improved, the phenomenon that the normal production progress is delayed due to maintenance is avoided, and secondary faults caused by maintenance are also avoided.

In some alternative embodiments, before the step S432 inputs the monitoring label information of the device operation monitoring indicators of the production device energy consumption statistics and the monitoring label information of the device operation monitoring indicators of the product yield statistics into the preset neural network model, the method may further include the following steps S61-S64.

Step S61, inputting the non-updatable monitoring label information and the corresponding updatable status fault label in the training sample set of the monitoring label information into the neural network to be trained, and obtaining the monitoring label evaluation result of each sample monitoring label information through the neural network model to be trained.

And step S62, obtaining the cluster centrality of the monitoring index clustering result of the equipment operation monitoring index of the production equipment energy consumption statistical result according to the monitoring label evaluation result of the state fault label of the non-updatable monitoring label information.

And step S63, obtaining the cluster center degree and the cluster association degree of the cluster result of the monitoring index cluster result of the equipment operation monitoring index of the product yield statistical result according to the monitoring label evaluation result of the state fault label capable of updating the monitoring label information.

Step S64, determining that the neural network model to be trained meets the target monitoring index clustering result under the condition that the clustering center degree of the monitoring index clustering result of the equipment operation monitoring index of the production equipment energy consumption statistical result meets the energy consumption clustering evaluation condition of the equipment operation monitoring index of the production equipment energy consumption statistical result, the clustering center degree of the monitoring index clustering result of the equipment operation monitoring index of the product yield statistical result meets the production clustering evaluation condition of the equipment operation monitoring index of the product yield statistical result, and the clustering set association degree meets the set association condition.

In some alternative embodiments, the processing, by the preset neural network model, the energy consumption fault recognition result of the monitoring label information of the device operation monitoring indicator of the production device energy consumption statistics result and the production fault recognition result of the monitoring label information of the device operation monitoring indicator of the product yield statistics result to obtain a global recognition result may include the following contents described in steps S4331 to S4333.

Step S4331, performing similarity analysis on the energy consumption fault identification result of the monitoring label information of the equipment operation monitoring index of the production equipment energy consumption statistical result and the production fault identification result of the monitoring label information of the equipment operation monitoring index of the product yield statistical result through the preset neural network model, and obtaining the cosine distance between the monitoring label information of the equipment operation monitoring index of the production equipment energy consumption statistical result and the monitoring label information of the equipment operation monitoring index of the product yield statistical result.

Step S4332, when the cosine distance is greater than or equal to the set cosine distance, determining that the status failure tag of the device operation monitoring index of the product yield statistical result in the target monitoring tag information and the status failure tag of the device operation monitoring index of the production device energy consumption statistical result in the monitoring tag information are matched.

Step S4333, when the cosine distance is smaller than the set cosine distance, determining that the status failure tag of the device operation monitoring index of the product yield statistical result in the target monitoring tag information is not matched with the status failure tag of the device operation monitoring index of the device energy consumption statistical result in the monitoring tag information of the device operation monitoring index of the production device energy consumption statistical result.

In some alternative embodiments, the step of determining the shutdown maintenance strategy of the target production area according to the equipment state fault information described in the step S5 may include the following steps S51-S55.

And S51, determining the fault category statistical result of the equipment state fault information.

And S52, respectively performing equipment operation log analysis and equipment maintenance log analysis on the associated industrial equipment corresponding to the plurality of fault types in the fault type statistical results to obtain an equipment operation log analysis result sequence and an equipment maintenance log analysis result sequence.

And S53, performing production line analysis on the equipment operation log analysis result sequence through presetting capacity demand information to obtain a first production time period comprising production abnormity prompt information.

And S54, performing shutdown indication analysis on the equipment overhaul log analysis result sequence through preset production line restart information to obtain a second production period comprising overhaul shutdown prompt information.

S55, matching production periods based on the first production period and the second production period to obtain a shutdown overhaul period corresponding to the fault category statistical result, determining equipment identifiers of the to-be-shutdown industrial equipment for overhauling each fault category in the fault category statistical result according to the shutdown overhaul period, and determining a shutdown overhaul strategy of the target production region according to region information corresponding to the equipment identifiers.

By the design, through the content described in the steps S51 to S55, the equipment operation log and the equipment maintenance log are analyzed, and different production time intervals are considered, so that the influence of the shutdown maintenance can be minimized in the later period of the shutdown maintenance, the production efficiency of a target production area or other production areas is improved, the normal production progress is prevented from being delayed due to the maintenance, and the secondary fault caused by the maintenance is also avoided.

Secondly, for the above-mentioned telematics method based on big data and edge calculation, the embodiment of the present invention further provides an exemplary telematics device based on big data and edge calculation, and as shown in fig. 2, the telematics device 200 based on big data and edge calculation may include the following functional modules.

The information obtaining module 210 is configured to obtain a historical state information set corresponding to a production condition of the device state alarm record, where the historical state information includes industrial device state tracks corresponding to different production indexes.

The information determining module 220 is configured to identify a classification result of the production index data in the equipment state alarm record through a historical state information set corresponding to the production condition of the equipment state alarm record, and determine state alarm indication information of the classification result of the production index data in the equipment state alarm record.

The information updating module 230 is configured to screen the production index safety data and the production index abnormal data of the historical state information according to the classification result of the production index data in the equipment state alarm record; locking abnormal production index data in the historical state information, and updating production indexes of the production index safety data in the historical state information to form a target state information set.

The information monitoring module 240 is configured to identify the device state alarm record through the target state information set, determine a device operation monitoring index having a time sequence correlation with the device state alarm record, monitor the device state information to be monitored through the state alarm indication information and the device operation monitoring index, and determine corresponding device state fault information.

Then, based on the above method embodiment and apparatus embodiment, the embodiment of the present invention further provides a system embodiment, that is, a telematics system based on big data and edge computing, please refer to fig. 3, where the telematics system 30 based on big data and edge computing may include a cloud server 10 and an edge monitoring device 20. Where the cloud server 10 and the edge monitoring device 20 communicate to implement the above method, further, the functionality of the telematics system 30 based on big data and edge computing is described below.

A telematics system based on big data and edge computing comprises a cloud server and an edge monitoring device which are communicated with each other;

the edge monitoring device is configured to: generating a device state trajectory for the industrial device; the cloud server is configured to: acquiring a historical state information set corresponding to the production condition of an equipment state alarm record, wherein the historical state information comprises industrial equipment state tracks corresponding to different production indexes; identifying the classification result of the production index data in the equipment state alarm record through a historical state information set corresponding to the production condition of the equipment state alarm record, and determining state alarm indication information of the classification result of the production index data in the equipment state alarm record; screening the production index safety data and the production index abnormal data of the historical state information according to the classification result of the production index data in the equipment state alarm record; locking abnormal production index data in the historical state information, and updating production indexes of the production index safety data in the historical state information to form a target state information set; and identifying the equipment state alarm record through the target state information set, determining an equipment operation monitoring index having time sequence correlation with the equipment state alarm record, monitoring the equipment state information to be monitored through the state alarm indication information and the equipment operation monitoring index, and determining corresponding equipment state fault information.

Further, referring to fig. 4 in combination, the cloud server 10 may include a processing engine 110, a network module 120, and a memory 130, wherein the processing engine 110 and the memory 130 communicate through the network module 120.

Processing engine 110 may process the relevant information and/or data to perform one or more of the functions described herein. For example, in some embodiments, processing engine 110 may include at least one processing engine (e.g., a single core processing engine or a multi-core processor). By way of example only, the Processing engine 110 may include a Central Processing Unit (CPU), an Application-Specific Integrated Circuit (ASIC), an Application-Specific Instruction Set Processor (ASIP), a Graphics Processing Unit (GPU), a Physical Processing Unit (PPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), a controller, a microcontroller Unit, a Reduced Instruction Set Computer (RISC), a microprocessor, or the like, or any combination thereof.

Network module 120 may facilitate the exchange of information and/or data. In some embodiments, the network module 120 may be any type of wired or wireless network or combination thereof. Merely by way of example, the Network module 120 may include a cable Network, a wired Network, a fiber optic Network, a telecommunications Network, an intranet, the internet, a Local Area Network (LAN), a Wide Area Network (WAN), a Wireless Local Area Network (WLAN), a Metropolitan Area Network (MAN), a Public Switched Telephone Network (PSTN), a bluetooth Network, a Wireless personal Area Network, a Near Field Communication (NFC) Network, and the like, or any combination thereof. In some embodiments, the network module 120 may include at least one network access point. For example, the network module 120 may include wired or wireless network access points, such as base stations and/or network access points.

The Memory 130 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like. The memory 130 is used for storing a program, and the processing engine 110 executes the program after receiving the execution instruction.

It is to be understood that the configuration shown in fig. 4 is merely illustrative, and that cloud server 10 may include more or fewer components than shown in fig. 4, or have a different configuration than shown in fig. 4. The components shown in fig. 4 may be implemented in hardware, software, or a combination thereof.

It should be understood that, for the above, a person skilled in the art can deduce from the above disclosure to determine the meaning of the related technical term without doubt, for example, for some values, coefficients, weights, indexes, factors, and other terms, a person skilled in the art can deduce and determine from the logical relationship between the above and the following, and the value range of these values can be selected according to the actual situation, for example, 0 to 1, for example, 1 to 10, and for example, 50 to 100, which are not limited herein.

The skilled person can unambiguously determine some preset, reference, predetermined, set and target technical features/terms, such as threshold values, threshold intervals, threshold ranges, etc., from the above disclosure. For some technical characteristic terms which are not explained, the technical solution can be clearly and completely implemented by those skilled in the art by reasonably and unambiguously deriving the technical solution based on the logical relations in the previous and following paragraphs. Prefixes of unexplained technical feature terms, such as "first", "second", "previous", "next", "current", "history", "latest", "best", "target", "specified", and "real-time", etc., can be unambiguously derived and determined from the context. Suffixes of technical feature terms not to be explained, such as "list", "feature", "sequence", "set", "matrix", "unit", "element", "track", and "list", etc., can also be derived and determined unambiguously from the foregoing and the following.

The foregoing disclosure of embodiments of the present invention will be apparent to those skilled in the art. It should be understood that the process of deriving and analyzing technical terms, which are not explained, by those skilled in the art based on the above disclosure is based on the contents described in the present application, and thus the above contents are not an inventive judgment of the overall scheme.

It should be appreciated that the system and its modules shown above may be implemented in a variety of ways. For example, in some embodiments, the system and its modules may be implemented in hardware, software, or a combination of software and hardware. Wherein the hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory for execution by a suitable instruction execution system, such as a microprocessor or specially designed hardware. Those skilled in the art will appreciate that the methods and systems described above may be implemented using computer executable instructions and/or embodied in processor control code, such code being provided, for example, on a carrier medium such as a diskette, CD-or DVD-ROM, a programmable memory such as read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of the present application may be implemented not only by hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but also by software executed by various types of processors, for example, or by a combination of the above hardware circuits and software (e.g., firmware).

The beneficial effects that may be brought by the embodiments of the present application include, but are not limited to: (1) by determining the state alarm indication information of the classification result of the production index data in the equipment state alarm record, the previous fault processing mode can be taken into account, so that a decision basis is provided for the subsequent fault monitoring processing; (2) the production index safety data and the production index abnormal data of the historical state information are screened, the production index safety data can be analyzed in a targeted manner, the accumulated operation time of industrial equipment is considered when the production index safety data are analyzed, the production index safety data are updated, and therefore the historical state information can be optimized to obtain target state information; (3) the time sequence relevance between the equipment operation monitoring index and the equipment state alarm record is considered when the equipment operation monitoring index is determined, the equipment operation monitoring index can be matched with the actual industrial production state, the time sequence synchronism of state monitoring is further ensured so as to ensure the real-time performance and the reliability of equipment state fault information, and the fault inducement of the industrial equipment is considered as far as possible, so that the timeliness of fault monitoring is ensured, and meanwhile, the missing detection is avoided, and the serious production accident is avoided.

It is to be noted that different embodiments may produce different advantages, and in different embodiments, any one or combination of the above advantages may be produced, or any other advantages may be obtained.

Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be considered merely illustrative and not restrictive of the broad application. Various modifications, improvements and adaptations to the present application may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present application and thus fall within the spirit and scope of the exemplary embodiments of the present application.

Also, this application uses specific language to describe embodiments of the application. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the present application is included in at least one embodiment of the present application. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the present application may be combined as appropriate.

Moreover, those skilled in the art will appreciate that aspects of the present application may be illustrated and described in terms of several patentable species or situations, including any new and useful combination of processes, machines, manufacture, or materials, or any new and useful improvement thereon. Accordingly, various aspects of the present application may be embodied entirely in hardware, entirely in software (including firmware, resident software, micro-code, etc.) or in a combination of hardware and software. The above hardware or software may be referred to as "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the present application may be represented as a computer product, including computer readable program code, embodied in one or more computer readable media.

The computer storage medium may comprise a propagated data signal with the computer program code embodied therewith, for example, on baseband or as part of a carrier wave. The propagated signal may take any of a variety of forms, including electromagnetic, optical, etc., or any suitable combination. A computer storage medium may be any computer-readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code located on a computer storage medium may be propagated over any suitable medium, including radio, cable, fiber optic cable, RF, or the like, or any combination of the preceding.

Computer program code required for the operation of various portions of the present application may be written in any one or more programming languages, including an object oriented programming language such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C + +, C #, VB.NET, Python, and the like, a conventional programming language such as C, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, a dynamic programming language such as Python, Ruby, and Groovy, or other programming languages, and the like. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any network format, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or in a cloud computing environment, or as a service, such as a software as a service (SaaS).

Additionally, the order in which elements and sequences of the processes described herein are processed, the use of alphanumeric characters, or the use of other designations, is not intended to limit the order of the processes and methods described herein, unless explicitly claimed. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments herein. For example, although the system components described above may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.

Similarly, it should be noted that in the preceding description of embodiments of the application, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. This method of disclosure, however, is not intended to require more features than are expressly recited in the claims. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.

Numerals describing the number of components, attributes, etc. are used in some embodiments, it being understood that such numerals used in the description of the embodiments are modified in some instances by the use of the modifier "about", "approximately" or "substantially". Unless otherwise indicated, "about", "approximately" or "substantially" indicates that the numbers allow for adaptive variation. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximations that may vary depending upon the desired properties of the individual embodiments. In some embodiments, the numerical parameter should take into account the specified significant digits and employ a general digit preserving approach. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of the range are approximations, in the specific examples, such numerical values are set forth as precisely as possible within the scope of the application.

The entire contents of each patent, patent application publication, and other material cited in this application, such as articles, books, specifications, publications, documents, and the like, are hereby incorporated by reference into this application. Except where the application is filed in a manner inconsistent or contrary to the present disclosure, and except where the claim is filed in its broadest scope (whether present or later appended to the application) as well. It is noted that the descriptions, definitions and/or use of terms in this application shall control if they are inconsistent or contrary to the statements and/or uses of the present application in the material attached to this application.

Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments of the present application. Other variations are also possible within the scope of the present application. Thus, by way of example, and not limitation, alternative configurations of the embodiments of the present application can be viewed as being consistent with the teachings of the present application. Accordingly, the embodiments of the present application are not limited to only those embodiments explicitly described and depicted herein.

Claims

1. A method for telematics based on big data and edge computation, the method comprising:

acquiring a historical state information set corresponding to the production condition of an equipment state alarm record, wherein the historical state information comprises industrial equipment state tracks corresponding to different production indexes;

identifying the classification result of the production index data in the equipment state alarm record through a historical state information set corresponding to the production condition of the equipment state alarm record, and determining state alarm indication information of the classification result of the production index data in the equipment state alarm record;

screening the production index safety data and the production index abnormal data of the historical state information according to the classification result of the production index data in the equipment state alarm record; locking abnormal production index data in the historical state information, and updating production indexes of the production index safety data in the historical state information to form a target state information set;

and identifying the equipment state alarm record through the target state information set, determining an equipment operation monitoring index having time sequence correlation with the equipment state alarm record, monitoring the equipment state information to be monitored through the state alarm indication information and the equipment operation monitoring index, and determining corresponding equipment state fault information.

2. The method of claim 1, wherein obtaining a set of historical state information corresponding to production conditions for a device state alarm record comprises:

acquiring an equipment state track generated by the edge monitoring equipment corresponding to the production working condition of the equipment state alarm record;

carrying out track denoising processing on the equipment state track;

determining a corresponding equipment state label through an equipment state monitoring model based on a track denoising processing result, and determining an equipment state track comprising a production line interaction track;

extracting state information of the equipment state track comprising the production line interaction track according to the fault category statistical result of the equipment state alarm record, and taking the corresponding extracted area track description information as any historical state information in a historical state information set corresponding to the production condition of the equipment state alarm record;

wherein the method further comprises:

determining index type data of corresponding production indexes according to historical state information corresponding to the production working conditions of the equipment state alarm records;

and combining the production indexes of the production index statistical results of the equipment state alarm records according to the index type data of the production indexes to obtain a production index combined result, judging the production index type to which the received equipment state track belongs according to the production index combined result, and determining the production index type to which the received equipment state track belongs.

3. The method according to claim 1, wherein the identifying the classification result of the production index data in the equipment status alarm record through the historical status information set corresponding to the production condition of the equipment status alarm record, and determining the status alarm indication information of the classification result of the production index data in the equipment status alarm record comprises:

determining corresponding equipment mechanical state information and equipment communication state information through a historical state information set corresponding to the production condition of the equipment state alarm record;

according to a normal index classification sub-result in the classification result of the production index data, historical state information corresponding to different equipment mechanical states in the historical state information set and production index safety data in the historical state information corresponding to the equipment communication state are adjusted according to production line flow information corresponding to a historical production line to form adjusted state alarm index data;

performing mean filtering processing on the adjusted state alarm index data according to an abnormal index classification sub-result in the classification result of the production index data to obtain a mean filtering processing result;

when track alarm index data of different production index data of the same equipment state are obtained based on the mean value filtering processing result, state alarm indicating information of a classification result of the production index data in the equipment state alarm record is determined according to the track alarm index data;

wherein the method further comprises:

determining corresponding mechanical fault category information based on the equipment mechanical state information;

determining corresponding communication fault category information based on the equipment communication state information;

when state alarm indication information of a classification result of the production index data in the equipment state alarm record is determined, determining comprehensive fault category information corresponding to the adjusted state alarm index data according to a fault category statistical result of the equipment state alarm record;

comparing the mechanical fault category information or the communication fault category information with the comprehensive fault category information to determine the data updating state of the abnormal production index data in the historical state information corresponding to the mechanical states of different equipment and the historical state information corresponding to the communication states of the equipment.

4. The method of claim 1, wherein locking production index abnormal data in the historical status information and performing production index update on production index safety data in the historical status information to form a target status information set comprises:

locking abnormal production index data in the historical state information, and filling missing values of the production index safety data in the historical state information by adopting a minimum neighbor method to form a target state information set;

or locking abnormal production index data in the historical state information, and performing bicubic interpolation processing or bilinear interpolation processing on the production index safety data in the historical state information to form a target state information set.

5. The method according to claim 1, wherein the identifying the device status alarm record through the target status information set, determining a device operation monitoring indicator having a time sequence correlation with the device status alarm record, monitoring the device status information to be monitored through the status alarm indication information and the device operation monitoring indicator, and determining corresponding device status failure information includes:

identifying the equipment state alarm record according to the target state information set, and determining an equipment operation monitoring index of a production equipment energy consumption statistical result in the equipment state alarm record;

identifying the equipment state alarm record according to the target state information set, and determining an equipment operation monitoring index of a product yield statistical result in the equipment state alarm record;

monitoring the state information of the equipment to be monitored through the equipment operation monitoring index of the production equipment energy consumption statistical result and the equipment operation monitoring index of the product yield statistical result, and determining equipment state fault information corresponding to the equipment state information to be monitored;

identifying the equipment state alarm record according to the target state information set, and determining an equipment operation monitoring index of a production equipment energy consumption statistical result in the equipment state alarm record, wherein the method comprises the following steps:

classifying the state information of the target state information set according to a time sequence order according to the energy consumption statistical result of the production equipment in the equipment state alarm record so as to determine a local energy consumption monitoring index of the energy consumption statistical result of the production equipment;

in response to the local energy consumption monitoring index of the production equipment energy consumption statistical result, classifying the state information of the target state information set according to the time sequence order through the production equipment energy consumption statistical result, and determining the global energy consumption monitoring index of the production equipment energy consumption statistical result;

according to the global energy consumption monitoring index of the production equipment energy consumption statistical result, performing gradient iteration processing on the energy consumption monitoring index of the production equipment energy consumption statistical result through the target state information set to determine energy consumption warning index data of each target state information in the target state information set;

wherein, the local energy consumption monitoring index responding to the production equipment energy consumption statistical result classifies the state information of the target state information set according to the time sequence order through the production equipment energy consumption statistical result, and the global energy consumption monitoring index determining the production equipment energy consumption statistical result includes:

inputting different target state information in the target state information set into an energy consumption prediction neural network corresponding to the energy consumption statistical result of the production equipment; determining the global energy consumption monitoring index corresponding to the energy consumption statistical result of the production equipment when the energy consumption prediction neural network meets the corresponding convergence condition;

wherein, according to the global energy consumption monitoring index of the energy consumption statistical result of the production equipment, performing gradient iteration processing on the energy consumption monitoring index of the energy consumption statistical result of the production equipment through the target state information set to determine energy consumption alarm index data of each target state information in the target state information set, includes:

determining an energy consumption prediction neural network corresponding to the energy consumption statistical result of the production equipment; performing gradient iteration processing on the energy consumption monitoring index of the energy consumption statistical result of the production equipment according to the global energy consumption monitoring index of the energy consumption statistical result of the production equipment;

until the energy consumption prediction neural network of the production equipment energy consumption statistical result reaches a corresponding convergence condition, and based on the energy consumption monitoring index in the production equipment energy consumption statistical result, extracting energy consumption warning index data of each target state information in the target state information set.

6. The method of claim 1, wherein the monitoring the status information of the device to be monitored through the device operation monitoring index of the production device energy consumption statistical result and the device operation monitoring index of the product yield statistical result, and determining the device status failure information corresponding to the device status information to be monitored comprises:

acquiring monitoring label information of equipment operation monitoring indexes of the production equipment energy consumption statistical result and monitoring label information of equipment operation monitoring indexes of the product yield statistical result, wherein the monitoring label information of the equipment operation monitoring indexes of the production equipment energy consumption statistical result comprises state fault labels of the equipment operation monitoring indexes of the production equipment energy consumption statistical result, and the monitoring label information of the equipment operation monitoring indexes of the product yield statistical result comprises state fault labels of the equipment operation monitoring indexes of the product yield statistical result;

inputting the monitoring label information of the equipment operation monitoring index of the production equipment energy consumption statistical result and the monitoring label information of the equipment operation monitoring index of the product yield statistical result into a preset neural network model to obtain an energy consumption fault identification result of the monitoring label information of the equipment operation monitoring index of the production equipment energy consumption statistical result and a production fault identification result of the monitoring label information of the equipment operation monitoring index of the product yield statistical result; the preset neural network model is obtained by training a neural network model to be trained through a training sample set of monitoring label information, the training sample set of the monitoring label information comprises a plurality of non-updatable sample monitoring label information and a plurality of updatable sample monitoring label information obtained by processing the plurality of non-updatable sample monitoring label information, the plurality of non-updatable sample monitoring label information collectively comprise a plurality of different sample state fault labels, the plurality of updatable sample monitoring label information collectively comprise a plurality of different sample state fault labels, the preset neural network model meets a set training condition, the set training condition comprises that the clustering center degree of a monitoring index clustering result of a device operation monitoring index of a production device energy consumption statistical result corresponding to each sample state fault label is smaller than the pre-updated degree of a device operation monitoring index of a production device energy consumption statistical result Setting a centrality;

processing the energy consumption fault recognition result of the monitoring label information of the equipment operation monitoring index of the production equipment energy consumption statistical result and the production fault recognition result of the monitoring label information of the equipment operation monitoring index of the product yield statistical result through the preset neural network model to obtain a global recognition result, the global identification result is used for indicating a state fault label of the equipment operation monitoring index of the production equipment energy consumption statistical result in the monitoring label information of the equipment operation monitoring index of the production equipment energy consumption statistical result and a state fault label of the equipment operation monitoring index of the product yield statistical result in the monitoring label information set of the equipment operation monitoring index of the product yield statistical result, wherein the state fault labels are matched state fault labels or unmatched state fault labels;

when the global identification result indicates that the state fault label of the equipment operation monitoring index of the production equipment energy consumption statistical result in the monitoring label information of the equipment operation monitoring index of the production equipment energy consumption statistical result and the state fault label of the equipment operation monitoring index of the product yield statistical result in the monitoring label information set of the equipment operation monitoring index of the product yield statistical result are matched state fault labels, monitoring the state information of the equipment to be monitored by using the global identification result, and determining the equipment state fault information corresponding to the state information of the equipment to be monitored; the equipment state fault information comprises an operating current fault, an operating voltage fault, an operating power fault, a communication delay fault and a mechanical structure damage fault.

7. The method of claim 6, wherein before inputting the monitoring label information of the equipment operation monitoring index of the production equipment energy consumption statistical result and the monitoring label information of the equipment operation monitoring index of the product yield statistical result into a preset neural network model, the method comprises:

acquiring a training sample set of the monitoring label information, wherein the training sample set of the monitoring label information comprises i non-updatable sample monitoring label information and i corresponding updatable sample monitoring label information, the i non-updatable sample monitoring label information comprises j different sample state fault labels in total, the i updatable sample monitoring label information comprises j different sample state fault labels in total, each sample state fault label appears in k sample monitoring label information in the i updatable sample monitoring label information and k sample monitoring label information in the updatable sample monitoring label information, and i, j and k are integers greater than 1;

training the neural network model to be trained by using the training sample set of the monitoring label information to obtain the preset neural network model meeting the target monitoring index clustering result;

wherein, obtaining the training sample set of the monitoring label information includes:

performing interpolation processing on each piece of non-updatable monitoring label information in the training sample set of monitoring label information to obtain a training sample set of target monitoring label information of an equipment operation monitoring index of a production equipment energy consumption statistical result, wherein each piece of monitoring label information in the training sample set of target monitoring label information is marked;

acquiring a set number of updatable tag attributes;

and randomly loading the updatable label attribute into each piece of non-updatable monitoring label information to obtain a training sample set of target monitoring label information of the equipment operation monitoring index of the product yield statistical result, wherein the training sample set of the monitoring label information comprises the target training monitoring label information set of the equipment operation monitoring index of the product yield statistical result.

8. The method of claim 1, wherein after determining the device status failure information, the method further comprises:

determining a shutdown maintenance strategy of a target production area according to the equipment state fault information; the equipment state fault information comprises an operating current fault, an operating voltage fault, an operating power fault, a communication delay fault and a mechanical structure damage fault.

9. A cloud server comprising a processing engine, a network module, and a memory; the processing engine and the memory communicate through the network module, the processing engine reading a computer program from the memory and operating to perform the method of any of claims 1-8.

10. A computer storage medium, having stored thereon a computer program which, when executed, implements the method of any one of claims 1-8.