CN115827411B - On-line monitoring and operation and maintenance assessment system and method for automation equipment - Google Patents
On-line monitoring and operation and maintenance assessment system and method for automation equipment Download PDFInfo
- Publication number
- CN115827411B CN115827411B CN202211572912.7A CN202211572912A CN115827411B CN 115827411 B CN115827411 B CN 115827411B CN 202211572912 A CN202211572912 A CN 202211572912A CN 115827411 B CN115827411 B CN 115827411B
- Authority
- CN
- China
- Prior art keywords
- loss
- historical
- equipment
- information
- maintenance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012423 maintenance Methods 0.000 title claims abstract description 128
- 238000012544 monitoring process Methods 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000011156 evaluation Methods 0.000 claims abstract description 89
- 238000005457 optimization Methods 0.000 claims abstract description 45
- 238000012545 processing Methods 0.000 claims abstract description 30
- 238000000605 extraction Methods 0.000 claims description 21
- 238000012549 training Methods 0.000 claims description 19
- 230000005670 electromagnetic radiation Effects 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 9
- 239000013074 reference sample Substances 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 8
- 239000000523 sample Substances 0.000 claims description 8
- 238000003062 neural network model Methods 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 6
- 230000008439 repair process Effects 0.000 abstract description 6
- 230000003245 working effect Effects 0.000 abstract description 4
- 230000009286 beneficial effect Effects 0.000 description 11
- 238000006243 chemical reaction Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000003491 array Methods 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 239000003245 coal Substances 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000011272 standard treatment Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention provides an on-line monitoring and operation and maintenance assessment system and method for automation equipment. The system comprises: and an online monitoring module: real-time equipment information of each automation equipment in the current state is monitored on line; and the operation and maintenance evaluation module: the method comprises the steps of constructing a corresponding operation and maintenance assessment index based on monitored real-time equipment information, and carrying out operation and maintenance assessment on the automatic equipment; and the optimizing and early warning module is used for: and the system is used for carrying out optimization processing on equipment which is qualified in operation and maintenance evaluation and carrying out early warning reminding on equipment which is unqualified in operation and maintenance evaluation based on the operation and maintenance evaluation result. Through the on-line monitoring to automation equipment, can guarantee the timely operation and maintenance and the aassessment to automation equipment, optimize the adjustment to the qualified automation equipment of aassessment, can guarantee automation equipment working property's superiority, carry out timely early warning to the unqualified equipment of aassessment and handle, can in time guarantee automation equipment repair efficiency.
Description
Technical Field
The invention relates to the technical field of online monitoring and operation and maintenance assessment, in particular to an online monitoring and operation and maintenance assessment system and method for automatic equipment.
Background
In the existing automation equipment, the equipment is generally maintained after the equipment fails to alarm and remind, or the equipment is manually detected on time, if the equipment fails to alarm and remind, the equipment is maintained, and by adopting the method, the timely evaluation of the automation equipment can be reduced, so that the equipment fails to solve the problem and repair rapidly, the working efficiency of the automation equipment is affected, and the working performance of the equipment is deteriorated.
Accordingly, the present invention is directed to an online monitoring and operation and maintenance assessment system and method for an automated device.
Disclosure of Invention
The invention provides an on-line monitoring and operation and maintenance assessment system and method for automation equipment, which are used for ensuring the timely operation and maintenance and assessment of the automation equipment, optimizing and adjusting the qualified automation equipment, ensuring the superiority of the working performance of the automation equipment, performing timely early warning treatment on unqualified equipment and timely ensuring the repair efficiency of the automation equipment through the on-line monitoring of the automation equipment.
The invention provides an on-line monitoring and operation and maintenance evaluation system for automation equipment, which comprises:
And an online monitoring module: real-time equipment information of each automation equipment in the current state is monitored on line;
and the operation and maintenance evaluation module: the operation and maintenance evaluation method is used for calculating corresponding operation and maintenance evaluation indexes based on the monitored real-time equipment information and performing operation and maintenance evaluation on the automatic equipment;
and the optimizing and early warning module is used for: and the system is used for carrying out optimization processing on equipment which is qualified in operation and maintenance evaluation and carrying out early warning reminding on equipment which is unqualified in operation and maintenance evaluation based on the operation and maintenance evaluation result.
Preferably, the online monitoring module includes:
an acquisition unit: the device component monitoring system is used for monitoring and acquiring current working information of the device component to be monitored of each automation device on line;
and a processing unit: the operation and maintenance evaluation module is used for carrying out standardization processing on the acquired current working information to obtain a first data set and transmitting the first data set to the operation and maintenance evaluation module;
all standardized processing results contained in the first data set are corresponding real-time equipment information.
Preferably, the operation and maintenance evaluation module includes:
a calculation unit: the operation and maintenance evaluation index calculation module is used for carrying out one-to-one mapping on the basis of the first data set and the preset standard set and calculating operation and maintenance evaluation indexes of corresponding automation equipment on the basis of a mapping result;
wherein ,
evaluating an index for the operation and maintenance of the corresponding automation device; />
The number of the equipment parts to be monitored corresponding to the first data set; />
For the first data set +.>
Working values after the working information corresponding to the equipment parts to be monitored is subjected to standardized processing; />
Is the +.>
Standard values after standardized treatment are carried out on standard information corresponding to the equipment components to be monitored; />
For the first data set +.>
Weight value of each equipment component to be monitored.
Preferably, the on-line monitoring and operation and maintenance evaluation system for an automation device comprises:
and the information extraction module is used for: for retrieving, based on the history database, history wear information corresponding to the automation device being in a history environment similar to the current operating environment;
model construction module: the probability prediction model is used for constructing a corresponding automation device based on the historical loss information;
probability prediction module: the method comprises the steps of obtaining loss occurrence probability and loss occurrence grade of each part to be monitored based on the probability prediction model and combining the environmental parameters of the current working environment and standard processing information of the corresponding part to be monitored;
auxiliary optimization module: and the operation and maintenance evaluation results are subjected to auxiliary optimization according to the loss occurrence probability and loss occurrence level of each part to be monitored.
Preferably, the information extraction module includes:
function determination unit: for determining all the history working environments contained in the history database, and setting a first environment index function S1 (y 1, x1, z 1) for each history working environment according to a preset specified index, and simultaneously setting a second environment index function S2 (y 2, x2, z 2) for the corresponding current working environment;
a first extraction unit: for extracting a first work environment from all historical work environments when y1=y2, x1=x2 and z1=z2 are satisfied;
a first determination unit: the first loss information of all the first working environments is used as historical loss information when the extraction quantity of the first working environments is larger than or equal to the reference sample quantity r 1;
a second extraction unit: for, when the number of the extracted first working environments is smaller than the reference sample number r1, according to
，/>
and />
Extracting a second working environment from all the historical working environments;
a second determination unit: according to the extracted first working environment and the extracted second loss information corresponding to the second working environment, the second loss information is used as historical loss information;
a third extraction unit: for when y1=y2, x1=x2 and z1=z2 are not satisfied, according to the following 
，/>
and />
Extracting a third working environment from all the historical working environments;
a third determination unit: according to the extracted third loss information corresponding to the third working environment, the third loss information is used as historical loss information;
wherein b1, b2, b3, b4 are range adjustment coefficients, an
Greater than b2 +>
Less than b1;
wherein y1 represents the humidity in the corresponding historical operating environment, x1 represents the temperature in the corresponding historical operating environment, and z1 represents the electromagnetic radiation in the corresponding historical operating environment;
y2 represents the humidity in the current working environment, x2 represents the temperature in the current working environment, and z2 represents the electromagnetic radiation in the current working environment.
Preferably, the model building module includes:
array construction unit: the method is used for constructing a historical loss array of each component to be monitored based on the historical loss information, wherein each element in the historical loss array represents a corresponding loss array under the extracted historical working environment, and the loss array comprises: whether the loss occurs a result or not and a loss level corresponding to the result;
training unit: and the method is used for determining the loss probability of different loss levels of the component to be monitored, which occurs historically, according to the historical loss array, and training the neural network model as a training sample to obtain a probability prediction model.
Preferably, the optimizing and early warning module comprises:
and a comparison unit: comparing the operation and maintenance evaluation result with a standard operation and maintenance result;
a first instruction issuing unit: if the comparison result meets the optimization standard, issuing an optimization reminding instruction to the corresponding automation equipment;
the second instruction issuing unit: and if the comparison result does not meet the optimization standard, issuing an early warning reminding instruction to the corresponding automation equipment.
Preferably, the optimizing and early warning module further comprises:
a judging unit: the method comprises the steps of after an early warning and reminding instruction is issued, obtaining a difference result between the operation and maintenance evaluation result and a standard operation and maintenance result, and analyzing and judging whether the difference result can form equipment faults or not based on a pre-trained fault analysis model;
a type determination unit: if equipment faults can be formed, at the moment, comparing the difference result with a preset fault comparison table, acquiring the fault type of the corresponding automatic equipment, and outputting a reminder.
Preferably, an on-line monitoring and operation and maintenance assessment method for an automation device includes:
step 1: on-line monitoring real-time equipment information of each automation equipment in the current state;
Step 2: based on the monitored real-time equipment information, calculating a corresponding operation and maintenance evaluation index, and performing operation and maintenance evaluation on the automatic equipment;
step 3: and on the basis of the operation and maintenance evaluation result, optimizing the equipment with qualified operation and maintenance evaluation, and carrying out early warning reminding on the equipment with unqualified operation and maintenance evaluation.
Compared with the prior art, the beneficial effects of the application are as follows:
through the on-line monitoring to automation equipment, can guarantee the timely operation and maintenance and the aassessment to automation equipment, optimize the adjustment to the qualified automation equipment of aassessment, can guarantee automation equipment working property's superiority, carry out timely early warning to the unqualified equipment of aassessment and handle, can in time guarantee automation equipment repair efficiency.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a block diagram of an on-line monitoring and operation and maintenance assessment system for an automation device in accordance with an embodiment of the present invention;
FIG. 2 is a block diagram of an information extraction module for an on-line monitoring and operation and maintenance assessment system for an automated device in accordance with an embodiment of the present invention;
FIG. 3 is a flow chart of an on-line monitoring and operation and maintenance assessment method for an automated device according to an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
Example 1:
an embodiment of the present invention provides an online monitoring and operation and maintenance evaluation system for an automation device, as shown in fig. 1, including:
and an online monitoring module: real-time equipment information of each automation equipment in the current state is monitored on line;
and the operation and maintenance evaluation module: the operation and maintenance evaluation method is used for calculating corresponding operation and maintenance evaluation indexes based on the monitored real-time equipment information and performing operation and maintenance evaluation on the automatic equipment;
And the optimizing and early warning module is used for: and the system is used for carrying out optimization processing on equipment which is qualified in operation and maintenance evaluation and carrying out early warning reminding on equipment which is unqualified in operation and maintenance evaluation based on the operation and maintenance evaluation result.
In this embodiment, the current state of the automation device refers to the state in which the device is in an operating condition.
In this embodiment, the real-time device information is obtained after normalization processing based on the monitored original monitoring information, and is related to the operation conditions of each component of the device, for example, voltage, current, logs generated in the working process of the device, and various calculation results obtained by normalization processing for each parameter (current, voltage, and characteristic) in the current information of the same component are the real-time device information.
In this embodiment, what functions each automation device needs to have, what work each component needs to perform in the automation device is factory-set, the component characteristics of each component are determined according to the factory-set condition of the component, the characteristics of the component are manually given to be good in advance, and information such as current, voltage, operating characteristics and the like of the factory-set component is used as standard information.
In this embodiment, the operation and maintenance evaluation index is mainly determined based on real-time equipment information of the automation equipment and preset standard equipment information, and is obtained by multiplying the ratio of the actual information of different components to the standard information by the weight of the corresponding component, and finally subtracting the accumulated sum of all index results from 1.
In this embodiment, the operation and maintenance evaluation result is mainly determined based on an operation and maintenance evaluation index of the automation device;
when the operation and maintenance evaluation index is larger than or equal to the preset index, the automation equipment is unqualified and needs to be operated and maintained, and when the operation and maintenance evaluation index is smaller than the preset index, the automation equipment is qualified and can be optimized, and the preset index generally takes a value of 0.4.
In this embodiment, the optimization processing refers to an upgrade processing or the like of some program performed on the device for the combination.
In this embodiment, the early warning alert is to facilitate the timely maintenance of the failed device by personnel.
The beneficial effects of the technical scheme are as follows: through the on-line monitoring to automation equipment, can guarantee the timely operation and maintenance and the aassessment to automation equipment, optimize the adjustment to the qualified automation equipment of aassessment, can guarantee automation equipment working property's superiority, carry out timely early warning to the unqualified equipment of aassessment and handle, can in time guarantee automation equipment repair efficiency.
Example 2:
based on embodiment 1, the online monitoring module includes:
an acquisition unit: the device component monitoring system is used for monitoring and acquiring current working information of the device component to be monitored of each automation device on line;
and a processing unit: and the operation and maintenance evaluation module is used for carrying out standardization processing on the acquired current working information to obtain a first data set and transmitting the first data set to the operation and maintenance evaluation module.
In this embodiment, all the standardized processing results included in the first data set are corresponding real-time device information.
In this embodiment, the current operation information is the operation information of the monitored equipment component of the automation equipment in the current state, including the current and the voltage to be monitored, the characteristic parameters corresponding to the main operation characteristics of the component, and the like, for example, if the component is a coal mine transportation device, the amount of the coal mine transportation and the transportation speed in the transportation process need to be monitored.
In this embodiment, the normalization processing of the current work information is to enable unified calculation when calculating the operation and maintenance evaluation parameters.
In this embodiment, the automation device includes a device that can be normally operated and a device that is not operated for a long time, wherein the device that can be normally operated includes a device that is being operated and a device that is stopped.
In this embodiment, the monitoring methods for the automation devices are different based on the different operation conditions of the automation devices; such as: and a method of real-time monitoring is adopted for equipment which can normally operate, and a method of periodic monitoring is adopted for equipment which does not operate for a long time.
The beneficial effects of the technical scheme are as follows: through the on-line monitoring to automation equipment minute condition, can reduce the work load of manual monitoring work, practice thrift the manual monitoring cost, also guaranteed the automation equipment better performance of different states to a certain extent based on the processing of different state minute condition simultaneously.
Example 3:
based on embodiment 2, the operation and maintenance evaluation module includes:
a calculation unit: the operation and maintenance evaluation index calculation module is used for carrying out one-to-one mapping on the basis of the first data set and the preset standard set and calculating operation and maintenance evaluation indexes of corresponding automation equipment on the basis of a mapping result;
wherein ,
evaluating an index for the operation and maintenance of the corresponding automation device; />
The number of the equipment parts to be monitored corresponding to the first data set; />
For the first data set +.>
Working information corresponding to each equipment part to be monitored is standardizedThe processed working value; />
Is the +. >
Standard values after standardized treatment are carried out on standard information corresponding to the equipment components to be monitored; />
For the first data set +.>
Weight value of each equipment component to be monitored.
The working value is obtained by carrying out standardization processing according to different working information, and the method specifically comprises the following steps:
determining working parameters of working information of the same component;
calculating the working value of the same component;
wherein ,
representing the number of working parameters corresponding to the same component; />
Representing the parameter value of the j1 working parameter in the same component after nonstandard treatment; />
Representing the parameter conversion coefficient corresponding to the j1 th working parameter in the same component, and the corresponding same component is +>
A plurality of equipment components to be monitored; />
Representation ofCorresponding to the j 1-th working parameter standard processed parameter value in the same component;
calculating the standard value of the same component;
wherein ,
representing the number of factory-set standard parameters corresponding to the same component; />
Representing standard parameter values which correspond to the j2 th factory-set standard parameters in the same component and are not subjected to standard treatment; />
A parameter conversion coefficient representing a standard parameter corresponding to the j2 th factory setting in the same component and the corresponding same component is +>
The equipment parts to be monitored. / >
And the parameter value after standardized processing of the standard parameter corresponding to the j2 th factory setting in the same component is represented.
In the process of determining different working values and standard values, the obtained parameter values are all obtained by converting standard coefficients.
It should be noted that what functions are performed by the automation device, what functions are performed by each component in the automation device are factory-set, what components on each device need to be monitored, what parameters of the components need to be monitored, the number of monitoring components of the device needs to be monitored, and the important roles that each monitoring component plays for the device are represented by weights, where m01 and m02 are equal values, and the number of working parameters for the same component is consistent.
It should be noted that, because each component includes what working parameters are set by factory, in order to facilitate calculation, conversion coefficients of the respective parameters are set at factory to achieve the purpose of calculating working values and standard values, and because different components in the automation device play different roles in different execution flows, the involved components participate in different numbers, that is, the number of components to be monitored is different, and the monitoring parameters of the monitored components need to be obtained are also different, the device 1 includes components 1, 2 and 3, when executing the flow 1, parameters related to the components 1 and 2 need to be obtained to obtain operation and maintenance evaluation indexes, at this time, the weight of the component 1 is 0.5, the weight of the component 2 is 0.3, that is, the total weight of all components included in the automation device is 1.
In this embodiment, the preset standard data set includes standard device information corresponding to a current model determined based on a model of the current automation device.
In this embodiment, the number of standard device information in the preset standard set is the same as the number of real-time device information in the first data set.
In this embodiment, the arrangement order of the standard device information in the preset standard set is consistent with the arrangement order of the real-time device information in the first data set.
In this embodiment, the operation and maintenance evaluation index is comprehensively determined based on the number of the equipment components to be monitored, the working value obtained after the working information corresponding to the equipment components to be monitored is standardized, the standard value obtained after the standard information corresponding to the equipment components to be monitored is standardized, and the weight value of the equipment components to be monitored.
In this embodiment, for example, the device component to be monitored includes: the device comprises a transmission part, a driving part, a sensor, a plurality of electronic elements, a fixture clamp, an air pressure cylinder and the like.
In this embodiment, the weight value of the equipment component to be monitored is the influence condition of the equipment component on the current operation and maintenance evaluation capability of the automation equipment; such as: the weight value of a certain sensor component of the equipment to be monitored is 0.1, namely the influence of the sensor on the operation and maintenance evaluation capability of the current automation equipment is 0.1.
The beneficial effects of the technical scheme are as follows: the operation and maintenance assessment indexes of the current automation equipment are calculated by processing and calculating the equipment parts of the automation equipment, so that the operation and maintenance assessment capacity of the current automation equipment is judged in a quantized mode, the current automation equipment is adjusted, the current automation equipment is ensured to work more efficiently, and the working performance of the automation equipment is improved.
Example 4:
based on embodiment 1, the on-line monitoring and operation and maintenance evaluation system for an automation device includes:
and the information extraction module is used for: for retrieving, based on the history database, history wear information corresponding to the automation device being in a history environment similar to the current operating environment;
model construction module: the probability prediction model is used for constructing a corresponding automation device based on the historical loss information;
probability prediction module: the method comprises the steps of obtaining loss occurrence probability and loss occurrence grade of each part to be monitored based on the probability prediction model and combining the environmental parameters of the current working environment and standard processing information of the corresponding part to be monitored;
auxiliary optimization module: and the operation and maintenance evaluation results are subjected to auxiliary optimization according to the loss occurrence probability and loss occurrence level of each part to be monitored.
In this embodiment, the history database is a database where the history loss information of the device consistent with the current automation device model is stored, and the history database includes the same automation device model, and the automation device of the same model is in a loss under different working environments, and the different working environments refer to a loss condition of the device itself under different combinations of humidity, temperature and electromagnetic radiation, which is described to indicate that the temperature, humidity and electromagnetic radiation can cause a certain loss, such as corrosion loss, radiation loss, and the like, to the device itself, thereby causing an operation loss to the device itself.
In the process of determining whether the working environments are similar, the identical historical environments and the similar historical environments are matched according to the current working environment, humidity, temperature and electromagnetic radiation of the automatic equipment, and further, the historical loss information of the similar historical environments of the current working environment can be obtained.
In this embodiment, the historical wear information is the wear condition of each component in the corresponding device when the corresponding device is in a historical environment similar to the current working environment of the device.
In this embodiment, the probability prediction model is used for judging the loss condition of each component correspondingly contained in the current automation device under the similar working environment based on the historical loss information.
In this embodiment, the standard processing information of the component to be monitored is information after the standard processing is performed on the standard information corresponding to the component to be monitored.
In this embodiment, the loss occurrence probability of the component to be monitored is a predicted loss occurrence probability obtained by the component to be monitored based on the current working environment and based on a probability prediction model.
In this embodiment, in the process of constructing the prediction model, after the history loss information of the similar history environment is acquired, the losses occurring in each component in the same model device in the same history environment are counted.
According to the statistical result, determining the occurrence probability of the loss of the same component and the corresponding loss occurrence level when the loss occurs each time, wherein the loss occurrence levels are determined according to the loss degree when the loss occurs, the loss occurrence levels corresponding to different loss degrees are different, and the loss degree and the loss occurrence level are constructed based on the same preset table.
Probability of loss occurrence = total number of occurrences of loss in the same environment/total number of occurrences in the same environment.
The beneficial effects of the technical scheme are as follows: the loss occurrence conditions of different equipment parts of the current equipment to be monitored are calculated based on the historical loss information, the loss occurrence probability and the loss occurrence level of the current equipment parts are obtained, and the operation and maintenance evaluation data can be further optimized, so that the operation and maintenance evaluation result based on the current equipment to be monitored is more accurate, the automation equipment can be timely adjusted, and the working effectiveness of the automation equipment is ensured.
Example 5:
based on embodiment 4, the information extraction module, as shown in fig. 2, includes:
function determination unit: for determining all the history working environments contained in the history database, and setting a first environment index function S1 (y 1, x1, z 1) for each history working environment according to a preset specified index, and simultaneously setting a second environment index function S2 (y 2, x2, z 2) for the corresponding current working environment;
a first extraction unit: for extracting a first work environment from all historical work environments when y1=y2, x1=x2 and z1=z2 are satisfied;
a first determination unit: the first loss information of all the first working environments is used as historical loss information when the extraction quantity of the first working environments is larger than or equal to the reference sample quantity r 1;
A second extraction unit: for, when the number of the extracted first working environments is smaller than the reference sample number r1, according to
，/>
and />
Extracting a second working environment from all the historical working environments;
a second determination unit: according to the extracted first working environment and the extracted second loss information corresponding to the second working environment, the second loss information is used as historical loss information;
a third extraction unit: for when y1=y2, x1=x2 and z1=z2 are not satisfiedWhen according to
，/>
and />
Extracting a third working environment from all the historical working environments;
a third determination unit: according to the extracted third loss information corresponding to the third working environment, the third loss information is used as historical loss information;
wherein b1, b2, b3, b4 are range adjustment coefficients, an
Greater than b2 +>
Less than b1;
wherein y1 represents the humidity in the corresponding historical operating environment, x1 represents the temperature in the corresponding historical operating environment, and z1 represents the electromagnetic radiation in the corresponding historical operating environment;
y2 represents the humidity in the current working environment, x2 represents the temperature in the current working environment, and z2 represents the electromagnetic radiation in the current working environment.
In this embodiment, the values of b4 and b2 are smaller than 1, and the values of b3 and b1 are larger than 1.
In this embodiment, the first environmental indicator function is a function determined according to a preset specified indicator based on a certain historical operating environment condition.
In this embodiment, the second environmental indicator function is a function determined by the current automation device according to a preset specified indicator based on the current working environment.
In this embodiment, the first working environment is a working environment consistent with the current working environment based on a preset specified index, that is, the humidity, the temperature and the electromagnetic radiation, among all the historical working environments.
In this embodiment, the reference sample number is a preset first working environment number. In order to ensure the accuracy of model training, the number r1 of the set reference samples is 300, and under the condition of ensuring enough samples, the trained model is ensured to be more accurate.
In this embodiment, the first loss information is information of loss conditions of the automation device corresponding to the selected first working environment in the corresponding working environment.
In this embodiment, when the number of samples is insufficient, the second working environment is similar to the current working environment of the automation device, which is obtained by screening the historical database to expand the matching range of the working environment based on the adjustment coefficient, so as to expand the number of reference samples.
In this embodiment, the second loss information is determined based on the loss information of the automation device corresponding to the first working environment and the loss information of the automation device corresponding to the second working environment when the number of samples is insufficient.
In this embodiment, the third working environment refers to a working environment which is screened to meet the requirement of the expanded working environment by expanding the requirement of the environment based on the adjustment coefficient when the requirement of the current working environment cannot be completely met in the history database.
In this embodiment, the third loss information is loss information based on the automation device corresponding to the third operating environment.
The beneficial effects of the technical scheme are as follows: by extracting the historical loss information of the automation equipment corresponding to the working environment which is the same as or similar to the working environment of the current automation equipment under the condition of the preset specified index in the historical database, training is performed based on a large amount of the historical loss information, a probability prediction model with higher precision is obtained, the automation equipment can be optimized more accurately, and the working efficiency and the working performance superiority of the automation equipment are ensured.
Example 6:
based on embodiment 5, the model building module includes:
array construction unit: the method is used for constructing a historical loss array of each component to be monitored based on the historical loss information, wherein each element in the historical loss array represents a corresponding loss array under the extracted historical working environment, and the loss array comprises: whether the loss occurs a result or not and a loss level corresponding to the result;
Training unit: and the method is used for determining the loss probability of different loss levels of the component to be monitored, which occurs historically, according to the historical loss array, and training the neural network model as a training sample to obtain a probability prediction model.
In this embodiment, the historical wear array is constructed based on the historical wear information corresponding to each component to be monitored.
In this embodiment, each element in the historical wear array represents a corresponding wear array under the extracted historical operating environment.
In this embodiment, the loss array includes: whether the loss occurs as a result and the level of loss to which the result corresponds.
In this embodiment, each element represents a loss array, after obtaining the loss array, since the loss array includes whether loss occurs or not and the corresponding loss level, the damage probability is obtained according to the number of the corresponding loss results of the same level, if 110 groups of loss do not occur in the array, the loss level is 0, 190 groups of loss occur, wherein 100 of the loss levels are primary, 90 of the loss levels are secondary, at this time, the probability of the loss level is 11/30, the probability of the loss level is 100/300, and the probability of the loss level is 90/300, at this time, after determining the explicit probability, samples are obtained for model training.
In this embodiment, training of the neural network model is common knowledge, that is, the historical loss array is taken as input, the loss probabilities of different loss levels are taken as output, and further input and output samples are formed, so that the neural network model is trained, the number of training samples is greater than 10000, and finally, the probability prediction model can be obtained.
In this embodiment, the determination of the loss level is obtained by matching a preset mapping table, and the preset mapping table is obtained by performing a number of loss tests before shipping, including the same historical operating environment, whether the loss matched with the historical operating environment occurs, the loss result corresponding to the loss, and the loss level matched with the loss result.
The beneficial effects of the technical scheme are as follows: through optimizing the evaluation result of the current automation equipment, the operation and maintenance evaluation condition of the automation equipment is accurately judged, the efficiency of operation and maintenance evaluation work can be increased, the accuracy of the operation and maintenance evaluation result is improved, and the effectiveness of the operation of the automation equipment is ensured.
Example 7:
based on embodiment 1, the optimizing and early warning module includes:
and a comparison unit: comparing the operation and maintenance evaluation result with a standard operation and maintenance result;
A first instruction issuing unit: if the comparison result meets the optimization standard, issuing an optimization reminding instruction to the corresponding automation equipment;
the second instruction issuing unit: and if the comparison result does not meet the optimization standard, issuing an early warning reminding instruction to the corresponding automation equipment.
In this embodiment, the optimization criteria are preset parameters criteria corresponding to the current automation device when optimization is required, and are criteria that are planned in advance.
In this embodiment, the optimization reminding instruction is an instruction for combining the number corresponding to the automation equipment and the equipment optimization condition, which is based on the automation equipment to be optimized.
In this embodiment, the early warning and reminding instruction is an instruction for combining the number corresponding to the automation equipment with the equipment early warning condition based on the automation equipment which does not need to be optimized.
The beneficial effects of the technical scheme are as follows: the optimization or early warning condition of the current automation equipment is determined by comparing operation and maintenance evaluation results, and different instruction information is obtained based on different conditions, so that the corresponding automation equipment is processed based on different instructions, the superiority of the working performance of the automation equipment can be ensured, and meanwhile, the effectiveness of the working of the automation equipment can be timely ensured based on the automation equipment needing early warning treatment.
Example 8:
based on embodiment 1, the optimizing and early warning module includes:
a judging unit: the method comprises the steps of after an early warning and reminding instruction is issued, obtaining a difference result between the operation and maintenance evaluation result and a standard operation and maintenance result, and analyzing and judging whether the difference result can form equipment faults or not based on a pre-trained fault analysis model;
a type determination unit: if equipment faults can be formed, at the moment, comparing the difference result with a preset fault comparison table, acquiring the fault type of the corresponding automatic equipment, and outputting a reminder.
In the embodiment, the fault analysis model is obtained by training whether equipment faults can be formed or not based on matching of different operation and maintenance difference results and corresponding difference results, wherein the difference results are input, whether the equipment faults are formed or not is a sample formed by output, and the number of the samples is more than 1000, and at the moment, the fault analysis model is obtained based on training of a neural network model;
the input of the difference result of the sample is obtained by comparing the results, and when the difference result is used as a sample, an expert judges and determines whether the difference result is enough to be an equipment failure or not to obtain an input and output sample.
The difference result between the operation and maintenance evaluation result and the standard operation and maintenance result is as follows: the current was 3-fold different, corresponding to the following: the equipment fault can be formed, and the difference result between the operation and maintenance evaluation result and the standard operation and maintenance result is as follows: the voltage is 1.1 times different, and the corresponding result is: equipment failure, etc. cannot be constituted.
In this embodiment, the preset fault comparison table includes different difference results and fault types matched to the difference results, and the fault types of the automated equipment faults include, but are not limited to, power supply faults, sensor position offset faults, control valve faults, circuit loop faults, and the like.
In this embodiment, the difference results may be primarily directed to differences in the operation and maintenance assessment index.
Inputting the difference result into the fault analysis model to obtain an output result, wherein the output result is as follows: constituting a device failure or not constituting a device failure.
The beneficial effects of the technical scheme are as follows: the fault type of the automatic equipment can be timely judged by analyzing the early warning equipment, the automatic equipment is timely processed based on the fault type, and the working effectiveness of the automatic equipment can be ensured.
Example 9:
Based on embodiment 1, an on-line monitoring and operation and maintenance evaluation module for an automation device further includes: the re-optimizing module is used for continuously carrying out fine optimization again on the optimized equipment after optimizing the qualified automatic equipment, and comprises the following steps:
an information processing unit: the method comprises the steps of obtaining a second data set of the optimizing equipment, sending the second data set to an operation and maintenance database, and comparing the second data set with a preset standard set in the operation and maintenance database;
difference information acquisition unit: the difference information is used for acquiring difference information between each piece of information of the second data set and corresponding standard information in a preset standard set;
the difference level locking unit is used for acquiring a critical threshold value table corresponding to each piece of difference information and locking the difference level of each piece of difference information according to the critical threshold value table;
the monitoring array construction unit is used for constructing a monitoring array based on the component weights of the components to be monitored corresponding to each difference grade and the corresponding difference information;
the difference array construction unit is used for constructing a first difference array corresponding to the automation equipment based on all the acquired monitoring arrays;
a level determining unit configured to determine an optimization level based on the first difference array;
wherein ,
representing the component weights in the u1 st monitor array; />
A standard conversion value representing difference information in the u1 st monitoring array; />
Representing the total number of the monitoring arrays; max represents the maximum symbol; />
Representing from->
Personal->
The maximum value obtained;
acquiring a corresponding optimization level based on the value-level matching list;
the scheme obtaining unit is used for obtaining a first scheme generating model based on the left optimizing range to obtain a first solution and obtaining a second scheme generating model based on the right optimizing range to obtain a second solution when the optimizing level is on a critical line of the optimizing range;
the first optimizing unit is used for comparing the solution reliability of the first solution with the solution reliability of the second solution, screening solutions with large solution reliability and optimizing the optimizing equipment again;
and the second optimizing unit is used for obtaining a third solution based on a third solution generating model of the corresponding optimizing range when the optimizing level is in the corresponding optimizing range, and re-optimizing the optimizing equipment.
In this embodiment, the second data set is acquired based on the optimized device information of the optimized device.
In this embodiment, the preset standard set is a set of standard device information acquired when the current automation device is in a normal running state.
In this embodiment, the difference information is information based on a result of a difference between each piece of information of the second data set and corresponding standard information in the preset standard set.
In this embodiment, the critical threshold table is a table based on preset corresponding threshold settings based on whether the current automation device is optimized or not.
In this embodiment, the difference level is a corresponding difference level obtained by dividing the current query information based on a preset threshold value table.
In this embodiment, the monitoring array includes: whether to optimize, optimize the corresponding optimization level, etc.
In this embodiment, the first differential array is a comparison array of the monitoring arrays corresponding to the current automation device.
In this embodiment, the standard conversion value is a corresponding value which is easy to calculate, which is obtained by standard conversion based on the difference information.
In this embodiment, the first solution and the second solution refer to different solutions obtained based on different model situations on two sides of a corresponding critical line based on the equipment in the critical line of the optimization level.
In this embodiment, the solution reliability is based on the solution reliability corresponding to the solution reliability of the smoother operation of the automation device after the optimization according to the current solution, and is mainly aimed at the optimization degree of the device after the optimization according to the solution and before the re-optimization.
In this embodiment, when
Corresponding level and optimization scope [ a1, a2 ]]When a1 in the two ranges is equal, the obtained base ranges are [ a1, a2 ]]A second solution of the second solution generation model of (a) and obtaining a range-based [ a0, a1 ]]Is used for generating a model according to a first scheme of the systemIs a first solution of (a).
In this embodiment, the solution generating models are obtained by training the samples based on the corresponding optimization ranges and various optimization solutions matched by the optimization ranges, and the optimization solutions corresponding to different optimization ranges are different and are set in advance.
In this embodiment, the value-level matching list includes different values
And the corresponding level.
The beneficial effects of the technical scheme are as follows: the solution is compared and calculated on the automation equipment at the optimization boundary, so that the optimization situation more suitable for the current automation equipment is obtained, the equipment working performance is more superior, the operation is smoother, and the high efficiency of the automation equipment operation is ensured.
Example 10:
based on the embodiment 1, an on-line monitoring and operation and maintenance assessment method for an automation device, as shown in fig. 3, includes:
step 1: on-line monitoring real-time equipment information of each automation equipment in the current state;
step 2: based on the monitored real-time equipment information, calculating a corresponding operation and maintenance evaluation index, and performing operation and maintenance evaluation on the automatic equipment;
step 3: and on the basis of the operation and maintenance evaluation result, optimizing the equipment with qualified operation and maintenance evaluation, and carrying out early warning reminding on the equipment with unqualified operation and maintenance evaluation.
The beneficial effects of the technical scheme are as follows: through the on-line monitoring to automation equipment, can guarantee the timely operation and maintenance and the aassessment to automation equipment, optimize the adjustment to the qualified automation equipment of aassessment, can guarantee automation equipment working property's superiority, carry out timely early warning to the unqualified equipment of aassessment and handle, can in time guarantee automation equipment repair efficiency.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (6)
1. An on-line monitoring and operation assessment system for an automation device, comprising:
and an online monitoring module: real-time equipment information of each automation equipment in the current state is monitored on line;
and the operation and maintenance evaluation module: the operation and maintenance evaluation method is used for calculating corresponding operation and maintenance evaluation indexes based on the monitored real-time equipment information and performing operation and maintenance evaluation on the automatic equipment;
and the optimizing and early warning module is used for: the method is used for carrying out optimization processing on equipment with qualified operation and maintenance evaluation and carrying out early warning reminding on equipment with unqualified operation and maintenance evaluation based on operation and maintenance evaluation results;
wherein, still include:
and the information extraction module is used for: for retrieving, based on the history database, history wear information corresponding to the automation device being in a history environment similar to the current operating environment;
model construction module: the probability prediction model is used for constructing a corresponding automation device based on the historical loss information;
probability prediction module: the method comprises the steps of obtaining loss occurrence probability and loss occurrence grade of each part to be monitored based on the probability prediction model and combining the environmental parameters of the current working environment and standard processing information of the corresponding part to be monitored;
auxiliary optimization module: the operation and maintenance evaluation result is subjected to auxiliary optimization according to the loss occurrence probability and loss occurrence level of each part to be monitored;
Wherein, the information extraction module includes:
function determination unit: the method comprises the steps of determining all historical working environments contained in a historical database, setting a first environment index function S1 (y 1, x1, z 1) for each historical working environment according to preset specified indexes, and simultaneously setting a second environment index function S2 (y 2, x2, z 2) for the corresponding current working environment;
a first extraction unit: for extracting a first work environment from all historical work environments when y1=y2, x1=x2 and z1=z2 are satisfied;
a first determination unit: the first loss information of all the first working environments is used as historical loss information when the extraction quantity of the first working environments is larger than or equal to the reference sample quantity r 1;
a second extraction unit: for, when the number of the extracted first working environments is smaller than the reference sample number r1, according to
，/>
and />
Extracting a second working environment from all the historical working environments;
a second determination unit: according to the extracted first working environment and the extracted second loss information corresponding to the second working environment, the second loss information is used as historical loss information;
a third extraction unit: for when y1=y2, x1=x2 and z1=z2 are not satisfied, according to the following 
，
and />
Extracting a third working environment from all the historical working environments;
a third determination unit: according to the extracted third loss information corresponding to the third working environment, the third loss information is used as historical loss information;
wherein b1, b2, b3, b4 are range adjustment coefficients, an
Greater than b2 +>
Less than b1;
wherein y1 represents the humidity in the corresponding historical operating environment, x1 represents the temperature in the corresponding historical operating environment, and z1 represents the electromagnetic radiation in the corresponding historical operating environment;
y2 represents the humidity in the current working environment, x2 represents the temperature in the current working environment, and z2 represents the electromagnetic radiation in the current working environment;
wherein, the model construction module includes:
array construction unit: the method is used for constructing a historical loss array of each component to be monitored based on the historical loss information, wherein each element in the historical loss array represents a corresponding loss array under the extracted historical working environment, and the loss array comprises: whether the loss occurs a result or not and a loss level corresponding to the result;
training unit: and the method is used for determining the loss probability of different loss levels of the component to be monitored, which occurs historically, according to the historical loss array, and training the neural network model as a training sample to obtain a probability prediction model.
2. An on-line monitoring and operation and maintenance assessment system for an automation device according to claim 1, wherein said on-line monitoring module comprises:
an acquisition unit: the device component monitoring system is used for monitoring and acquiring current working information of the device component to be monitored of each automation device on line;
and a processing unit: the operation and maintenance evaluation module is used for carrying out standardization processing on the acquired current working information to obtain a first data set and transmitting the first data set to the operation and maintenance evaluation module;
all standardized processing results contained in the first data set are corresponding real-time equipment information.
3. An on-line monitoring and operation and maintenance assessment system for an automation device according to claim 2, wherein said operation and maintenance assessment module comprises:
a calculation unit: the operation and maintenance evaluation index calculation module is used for carrying out one-to-one mapping on the basis of the first data set and the preset standard set and calculating operation and maintenance evaluation indexes of corresponding automation equipment on the basis of a mapping result;
wherein ,
evaluating an index for the operation and maintenance of the corresponding automation device; />
The number of the equipment parts to be monitored corresponding to the first data set; />
For the first data set +.>
Working values after the working information corresponding to the equipment parts to be monitored is subjected to standardized processing; / >
Is the +.>
Standard values after standardized treatment are carried out on standard information corresponding to the equipment components to be monitored; />
For the first data set +.>
To be monitoredWeight value of equipment component.
4. The on-line monitoring and operation-and-maintenance-assessment system for an automation device according to claim 1, wherein said optimization and pre-warning module comprises:
and a comparison unit: comparing the operation and maintenance evaluation result with a standard operation and maintenance result;
a first instruction issuing unit: if the comparison result meets the optimization standard, issuing an optimization reminding instruction to the corresponding automation equipment;
the second instruction issuing unit: and if the comparison result does not meet the optimization standard, issuing an early warning reminding instruction to the corresponding automation equipment.
5. The on-line monitoring and operation-and-maintenance-assessment system for an automated device according to claim 4, wherein said optimization and pre-warning module further comprises:
a judging unit: the method comprises the steps of after an early warning and reminding instruction is issued, obtaining a difference result between the operation and maintenance evaluation result and a standard operation and maintenance result, and analyzing and judging whether the difference result can form equipment faults or not based on a pre-trained fault analysis model;
A type determination unit: if equipment faults can be formed, at the moment, comparing the difference result with a preset fault comparison table, acquiring the fault type of the corresponding automatic equipment, and outputting a reminder.
6. An on-line monitoring and operation and maintenance assessment method for an automation device, comprising:
step 1: on-line monitoring real-time equipment information of each automation equipment in the current state;
step 2: based on the monitored real-time equipment information, calculating a corresponding operation and maintenance evaluation index, and performing operation and maintenance evaluation on the automatic equipment;
step 3: based on the operation and maintenance evaluation result, optimizing the equipment with qualified operation and maintenance evaluation, and performing early warning reminding on the equipment with unqualified operation and maintenance evaluation;
wherein the method further comprises:
retrieving, based on the historical database, historical wear information corresponding to the automation device in a historical environment similar to the current operating environment;
constructing a probability prediction model of the corresponding automation equipment based on the historical loss information;
based on the probability prediction model, and combining the environmental parameters of the current working environment and standard processing information of the corresponding parts to be monitored, obtaining loss occurrence probability and loss occurrence level of each part to be monitored;
Performing auxiliary optimization on the operation and maintenance evaluation result according to the loss occurrence probability and loss occurrence level of each part to be monitored;
wherein retrieving, based on the historical database, historical wear information for the corresponding automation device in a historical environment similar to the current operating environment, comprises:
determining all the historical working environments contained in the historical database, setting a first environment index function S1 (y 1, x1, z 1) to each historical working environment according to a preset specified index, and simultaneously setting a second environment index function S2 (y 2, x2, z 2) to the corresponding current working environment;
extracting a first work environment from all the historical work environments when y1=y2, x1=x2, and z1=z2 are satisfied;
when the extraction quantity of the first working environments is larger than or equal to the reference sample quantity r1, taking the first loss information of all the extracted first working environments as historical loss information;
when the extraction number of the first working environment is smaller than the reference sample number r1, according to
，
and />
Extracting a second working environment from all the historical working environments;
according to the extracted first working environment and the extracted second loss information corresponding to the second working environment, the second loss information is used as historical loss information;
When y1=y2, x1=x2 and z1=z2 are not satisfied, the following applies
，/>
and />
Extracting a third working environment from all the historical working environments;
according to the extracted third loss information corresponding to the third working environment, the third loss information is used as historical loss information;
wherein b1, b2, b3, b4 are range adjustment coefficients, an
Greater than b2 +>
Less than b1;
wherein y1 represents the humidity in the corresponding historical operating environment, x1 represents the temperature in the corresponding historical operating environment, and z1 represents the electromagnetic radiation in the corresponding historical operating environment;
y2 represents the humidity in the current working environment, x2 represents the temperature in the current working environment, and z2 represents the electromagnetic radiation in the current working environment;
wherein constructing a probabilistic predictive model for the automation device based on the historical wear information comprises:
constructing a historical loss array of each component to be monitored based on the historical loss information, wherein each element in the historical loss array represents a corresponding loss array under an extracted historical working environment, and the loss array comprises: whether the loss occurs a result or not and a loss level corresponding to the result;
and determining loss probabilities of different loss levels of the to-be-monitored component in history according to the history loss array, and training the neural network model as a training sample to obtain a probability prediction model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211572912.7A CN115827411B (en) | 2022-12-08 | 2022-12-08 | On-line monitoring and operation and maintenance assessment system and method for automation equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211572912.7A CN115827411B (en) | 2022-12-08 | 2022-12-08 | On-line monitoring and operation and maintenance assessment system and method for automation equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115827411A CN115827411A (en) | 2023-03-21 |
| CN115827411B true CN115827411B (en) | 2023-05-16 |
Family
ID=85545492
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211572912.7A Active CN115827411B (en) | 2022-12-08 | 2022-12-08 | On-line monitoring and operation and maintenance assessment system and method for automation equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115827411B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117234160B (en) * | 2023-09-13 | 2024-03-08 | 广东汇博机器人技术有限公司 | Automatic production remote control system and method |
| CN117667585B (en) * | 2023-12-05 | 2024-06-04 | 江苏省工商行政管理局信息中心 | Operation and maintenance efficiency evaluation method and system based on operation and maintenance quality management database |
| CN117455080B (en) * | 2023-12-25 | 2024-04-05 | 深圳市宏大联合实业有限公司 | Production workshop environment optimization method and system based on Internet of things |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018035087A1 (en) * | 2016-08-15 | 2018-02-22 | Massachusetts Institute Of Technology | System and method for estimating and predicting vehicle trip energy consumption |
| KR102092185B1 (en) * | 2019-10-07 | 2020-05-26 | 팩트얼라이언스 주식회사 | Platform for analyzing electric motor health and analysis method using the same |
| CN114936725A (en) * | 2021-10-19 | 2022-08-23 | 贵州电网有限责任公司 | Large power grid risk assessment and differentiation operation and maintenance system |
| CN114638476A (en) * | 2022-02-18 | 2022-06-17 | 国电南京自动化股份有限公司 | Water conservancy integrated operation and maintenance management method and system |
| CN115034578A (en) * | 2022-05-20 | 2022-09-09 | 中国电建集团华东勘测设计研究院有限公司 | Intelligent management construction method and system for hydraulic metal structure equipment based on digital twinning |
-
2022
- 2022-12-08 CN CN202211572912.7A patent/CN115827411B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115827411A (en) | 2023-03-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115827411B (en) | On-line monitoring and operation and maintenance assessment system and method for automation equipment | |
| CN110320892B (en) | Sewage treatment equipment fault diagnosis system and method based on L asso regression | |
| CN109240244B (en) | Data-driven equipment running state health degree analysis method and system | |
| Lin et al. | Time series prediction algorithm for intelligent predictive maintenance | |
| CN104595170B (en) | A kind of air compressor machine monitoring and diagnosis system and method for self-adaptive kernel gauss hybrid models | |
| CN111412579B (en) | Air conditioning unit fault type diagnosis method and system based on big data | |
| Roemer et al. | An overview of selected prognostic technologies with application to engine health management | |
| CN111581597A (en) | Wind turbine generator gearbox bearing temperature state monitoring method based on self-organizing kernel regression model | |
| JP5025776B2 (en) | Abnormality diagnosis filter generator | |
| CN109740859A (en) | Transformer condition evaluation and system based on Principal Component Analysis and support vector machines | |
| Li et al. | Preventive maintenance decision model of urban transportation system equipment based on multi-control units | |
| CN114169254A (en) | Abnormal energy consumption diagnosis method and system based on short-term building energy consumption prediction model | |
| CN116226469B (en) | Intelligent diagnosis method and system for energy storage equipment faults | |
| CN113408659A (en) | Building energy consumption integrated analysis method based on data mining | |
| CN117354171B (en) | Platform health condition early warning method and system based on Internet of things platform | |
| CN117523793A (en) | Power plant equipment fault early warning method and computer equipment | |
| CN116562158A (en) | Method for estimating residual life of air circuit component of aeroengine based on interpretable attention mechanism | |
| CN116151799A (en) | BP neural network-based distribution line multi-working-condition fault rate rapid assessment method | |
| CN114400776A (en) | Substation automation equipment state diagnosis method and system based on digital mirror image | |
| Wang et al. | Maintenance decision based on data fusion of aero engines | |
| CN112378651A (en) | Data-driven-based equipment dynamic reliability assessment method | |
| CN118089287B (en) | Water chiller energy efficiency optimizing system based on intelligent algorithm | |
| Alimohammadi et al. | Predict the remaining useful life in HVAC filters using a hybrid strategy | |
| CN116227995B (en) | Index analysis method and system based on machine learning | |
| CN114970709B (en) | Improved GA-based data-driven AHU multi-fault diagnosis feature selection method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |