CN114066274A - Equipment performance early warning method and device - Google Patents
Equipment performance early warning method and device Download PDFInfo
- Publication number
- CN114066274A CN114066274A CN202111385924.4A CN202111385924A CN114066274A CN 114066274 A CN114066274 A CN 114066274A CN 202111385924 A CN202111385924 A CN 202111385924A CN 114066274 A CN114066274 A CN 114066274A
- Authority
- CN
- China
- Prior art keywords
- equipment
- early warning
- performance
- model
- data
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 230000007423 decrease Effects 0.000 claims abstract description 9
- 238000012545 processing Methods 0.000 claims description 37
- 230000002159 abnormal effect Effects 0.000 claims description 30
- 238000012549 training Methods 0.000 claims description 20
- 238000004422 calculation algorithm Methods 0.000 claims description 11
- 230000008859 change Effects 0.000 claims description 11
- 238000012360 testing method Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 239000011159 matrix material Substances 0.000 claims description 9
- 230000009467 reduction Effects 0.000 claims description 9
- 238000012795 verification Methods 0.000 claims description 8
- 238000010801 machine learning Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 7
- 238000001514 detection method Methods 0.000 description 27
- 238000003745 diagnosis Methods 0.000 description 21
- 230000015556 catabolic process Effects 0.000 description 16
- 238000006731 degradation reaction Methods 0.000 description 16
- 230000008569 process Effects 0.000 description 11
- 230000005856 abnormality Effects 0.000 description 10
- 229910000831 Steel Inorganic materials 0.000 description 9
- 239000010959 steel Substances 0.000 description 9
- 230000005540 biological transmission Effects 0.000 description 5
- 230000006835 compression Effects 0.000 description 5
- 238000007906 compression Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 230000009471 action Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 4
- 238000009826 distribution Methods 0.000 description 4
- 238000005096 rolling process Methods 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 3
- 230000007774 longterm Effects 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 230000000903 blocking effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 239000013072 incoming material Substances 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 230000001502 supplementing effect Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- 241000277275 Oncorhynchus mykiss Species 0.000 description 1
- 239000002253 acid Substances 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 239000003595 mist Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Educational Administration (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Development Economics (AREA)
- Software Systems (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Game Theory and Decision Science (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to the technical field of equipment early warning, in particular to a method and a device for early warning equipment performance, wherein the method comprises the following steps: acquiring historical operating data of equipment; obtaining model parameters for predicting equipment states based on the historical operating data; collecting online data of the equipment in real time; obtaining an early warning model for predicting the state of the equipment based on the online data and the model parameters; and based on various performance parameter thresholds of the equipment and the early warning model, the performance of the equipment is early warned, so that the data of the equipment can be effectively monitored, the performance decline trend is early warned in time, the performance of the equipment is detected abnormally, and the purpose of real-time monitoring is achieved.
Description
Technical Field
The invention relates to the technical field of equipment early warning, in particular to a method and a device for early warning equipment performance.
Background
During the operation of the existing equipment, various data are generated, for example, process data, equipment data, production process data, planning data, operation data, and the like are classified. The angle of data acquisition includes high frequency data, low frequency data, statistical data, and the like. From the aspect of data format, there are structured data and unstructured data.
The performance status of the device cannot be obtained by any single data.
Therefore, in the operation process of the existing equipment, the data of the equipment cannot be effectively monitored, so that the early warning cannot be timely carried out when the equipment fails or the performance is degraded.
Disclosure of Invention
In view of the above, the present invention has been made to provide a method and apparatus for device pre-warning that overcomes or at least partially solves the above-mentioned problems.
In a first aspect, the present invention provides a method for device performance early warning, including:
acquiring historical operating data of equipment;
obtaining model parameters for predicting equipment states based on the historical operating data;
collecting online data of the equipment in real time;
obtaining an early warning model for predicting the state of the equipment based on the online data and the model parameters;
and early warning the performance of the equipment based on various performance parameter thresholds of the equipment and the early warning model.
Preferably, after the obtaining of the historical operating data of the device, the method further includes:
and performing characteristic processing on the historical operating data, wherein the characteristic processing comprises statistical processing on the historical operating data, filling processing of missing or null values and dimension reduction processing.
Preferably, the obtaining of model parameters for predicting the state of the equipment based on the historical operating data includes:
obtaining a feature matrix of the historical operating data based on the historical operating data;
dividing the feature matrix into a training set, a verification set and a test set;
and obtaining model parameters for predicting the state of the equipment based on the training of the training set, the verification set and the test set.
Preferably, the obtaining an early warning model for predicting the state of the equipment based on the online data and the model parameters includes:
and obtaining an early warning model for predicting the state of the equipment by adopting a machine learning algorithm based on the online data and the model parameters.
Preferably, the early warning model is specifically an equipment performance variation trend curve.
Preferably, the pre-warning of the performance of the device based on the pre-warning model and various performance parameter thresholds of the device includes:
judging whether the online data of the equipment collected in real time exceeds a corresponding performance parameter threshold value or not based on the equipment performance change trend curve, and if so, early warning the performance decline trend of the equipment;
and early warning the abnormal condition of the performance of the equipment based on the equipment performance change trend curve.
Preferably, the device is specifically any one of the following: motor, converter, transformer, switch.
In a second aspect, the present invention further provides an apparatus for device performance early warning, including:
the acquisition module is used for acquiring historical operating data of the equipment;
the construction module is used for obtaining model parameters for predicting the equipment state based on the historical operating data;
the acquisition module is used for acquiring online data of the equipment in real time;
an obtaining module, configured to obtain an early warning model for predicting a device state based on the online data and the model parameter;
and the early warning module is used for early warning the performance of the equipment based on various performance parameter thresholds of the equipment and the early warning model.
In a third aspect, the present invention also provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the above-mentioned method steps when executing the program.
In a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the above-mentioned method steps.
One or more technical solutions in the embodiments of the present invention have at least the following technical effects or advantages:
the invention provides a method for early warning equipment, which comprises the following steps: the method comprises the steps of obtaining model parameters for predicting the state of equipment according to historical operation data of the equipment, then collecting online data of the equipment in real time, obtaining an early warning model for predicting the state of the equipment based on the online data and the model parameters, and finally early warning the performance of the equipment based on various performance parameter thresholds of the equipment and the early warning model, so that the data of the equipment can be effectively monitored, early warning is timely carried out on performance decline trends, abnormal detection is carried out on the performance of the equipment, and the purpose of real-time monitoring is achieved.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a flow chart illustrating steps of a method for device performance early warning according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of an apparatus for device performance early warning according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a computer device for implementing the method for device performance early warning in the embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Example one
The invention provides a method for early warning equipment performance, which comprises the following steps as shown in figure 1:
s101, acquiring historical operating data of equipment;
s102, obtaining model parameters for predicting the equipment state based on historical operation data;
s103, acquiring online data of the equipment in real time;
s104, obtaining an early warning model for predicting the equipment state based on the online data and the model parameters;
and S105, early warning the performance of the equipment based on various performance parameter thresholds and early warning models of the equipment.
In a specific embodiment, S101 is executed to obtain historical operation data of the device, where the device is a motor, the historical operation data may be motor transmission speed, current, torque, load, and the like, and where the device is a switch, the historical operation data may be actions, positions, and the like of various valves.
After S101, the method further includes: and performing characteristic processing on the historical operating data, wherein the characteristic processing comprises statistical processing on the historical operating data, filling processing of missing or null values and dimension reduction processing.
Specifically, the characteristic processing of the historical data includes data reasonableness checking and noise reduction processing in the early stage, so as to eliminate working condition records and abnormal data records which do not meet the algorithm requirements in the data, wherein the reasonableness checking usually adopts a rule-based method, for example, whether the data is in a preset value range is checked, and when the working condition records meet the algorithm requirements, the flag bits in the PL data are required to be used for judgment.
The characteristic processing of the historical data mainly comprises statistical processing, missing or null value supplementing processing and dimension reduction processing of the historical operating data.
The statistical processing will generally take into account, according to expert experience, data that may have an effect on the operating state of the plant, irrespective of the magnitude of the effect, for example, taking into account the current, torque, rotational speed, etc. of the electric machine. Further, the data influencing the running state of the equipment is subjected to calculation of statistical indexes such as mean value, average amplitude value, limit value, variance, root mean square, kurtosis and the like in a preset interval.
The missing or null value filling processing mainly includes data filling processing of missing and null values in the collected data, and continuous processing of some special data such as characters, time and date according to a certain method.
In the running process of the device, the data volume in the normal state is much larger than that in the abnormal state, and at this time, the weight of the data in the abnormal state needs to be increased.
And (4) dimension reduction processing, namely performing dimension reduction on the overlarge feature matrix through Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) to shorten the training time of the model.
After the above-described characteristic processing is performed on the historical operation data, S102 is performed to obtain model parameters for predicting the state of the plant based on the historical operation data.
Specifically, firstly, a feature matrix of historical operating data is obtained according to the historical operating data after the feature processing; then, dividing the characteristic matrix into a training set, a verification set and a test set; based on the training of the training set, the validation set and the test set, model parameters for predicting the state of the equipment are obtained.
The training set is used for training the model, the verification set is used for verifying the result, and when the experiment is successful, final evaluation is conducted on the test set. Different data are adopted in the processing processes of different stages so as to improve the accuracy of the obtained model parameters for predicting the equipment state.
Of course, cross-validation may also be used for the training and validation sets to avoid the randomness of the partitioned data sets. Thereby, model parameters for predicting the state of the plant are obtained.
After model parameters for predicting the state of the device are obtained, S103 is executed to collect online data of the device in real time.
After the online data of the device is acquired in real time, the above feature processing needs to be performed on the online data, which is not described herein again.
Then, S104 is executed, and an early warning model for predicting the equipment state is obtained based on the online data and the model parameters.
In an optional implementation, an early warning model for predicting the state of the equipment is obtained by adopting a machine learning algorithm based on the online data and the model parameters. The obtained early warning model is a device performance change trend curve constructed by online data and model parameters. According to the equipment performance change trend curve, the performance state of the equipment corresponding to the operation data of the equipment can be seen.
The performance state of the device includes a trend state of performance deterioration or a trend state of better performance, and of course, an abnormal state of the running data of the device can be seen, and monitoring of the running state of the device by a user can be greatly facilitated by analyzing the performance state of the device.
In the process of obtaining the early warning model for predicting the equipment state by adopting the machine learning algorithm, abnormal detection condition data of various equipment needs to be considered, so that the early warning model for predicting the equipment state is obtained through machine learning training according to model parameters of the equipment state marked in historical operating data.
In the following, motor torque anomaly detection is taken as an example, and three different modeling strategies are adopted to realize an early warning model for predicting the state of equipment.
The method comprises the steps of firstly, modeling based on abnormal detection of a historical baseline model, mainly aiming at the condition that no torque abnormal sample exists and process parameter combinations are more in the model training process, utilizing a sample which normally runs, taking working condition parameters (rotating speed, tension and the like) as characteristics, taking torque abnormal characteristics as a prediction target, training a regression model of the working condition parameters fitting the torque abnormal characteristics by adopting a Support Vector Machine (SVM) algorithm, and measuring the abnormal risk degree of the prediction sample by utilizing the prediction residual error (the difference between model prediction and a real result) of the regression model when the torque abnormality is actually detected on line. Since there may be no torque anomaly samples during training, an anomaly threshold may be calculated using a mahalanobis distance or fitted residual distribution based method.
Second, anomaly detection modeling based on cluster comparison. Because each type of monitored motor may have a plurality of motors in the same working condition, the abnormal detection can be performed by adopting a cluster comparison method, namely, the difference between the torque distribution of a single motor and the overall torque distribution of a plurality of motors of the same type is compared, and the abnormal risk degree of the motor torque is measured through the distribution difference.
Thirdly, an abnormal finding expert rule model is established by utilizing expert knowledge, the method can be used as a supplement of a data modeling method, and can be used as an alternative scheme when the data modeling method is not good in effect or is inapplicable, for example, when a brand-new working condition with large difference is met, a previously trained model may fail, and according to the prediction result of the model, the following post-processing is carried out so as to obtain a final motor torque abnormality prediction result.
In S105, the performance of the device is warned based on various performance parameter thresholds and the warning model of the device.
In an optional implementation manner, whether the online data of the device collected in real time exceeds the corresponding performance parameter threshold is judged based on the device performance change trend curve, and if the online data exceeds the corresponding performance parameter threshold, the performance degradation trend of the device is warned.
In an optional implementation manner, based on the device performance variation trend curve, a warning is given to the condition that the performance of the device is abnormal.
When the above two or more abnormality detection models are used to perform abnormality prediction, it is necessary to perform comprehensive judgment on the prediction results of different abnormality detection models, and the judgment rule here may be that when the results of two or more abnormality detection models are both abnormal, the abnormal result is determined, that is, the logical and, or when the result of any one abnormality detection model is abnormal, the abnormal result is determined, that is, the logical or.
Of course, in order to reduce the false alarm rate, the abnormality prediction may be performed according to the number of points exceeding the abnormality threshold in the past period of time at the present time, and the abnormality may be determined when the number of detected abnormal points is greater than the preset value.
When the equipment degradation trend is early warned, whether the data acquired in real time exceeds the performance parameter threshold or not can be judged on the equipment performance change trend curve according to the preset performance parameter threshold, if so, the point corresponding to the data is determined to be an inflection point for early warning the equipment performance degradation trend, and therefore, when the data is acquired, the equipment performance degradation trend is early warned.
For different devices, the device performance degradation trend can be independent of the working condition and can also be related to the working condition. And when the equipment performance degradation trend is unrelated to the working condition, directly carrying out abnormity detection according to the equipment performance change trend curve, and carrying out early warning when the performance parameter threshold is exceeded. And when the equipment performance degradation trend is related to the working condition, carrying out abnormal detection on the equipment performance degradation trend curve of the current working condition or the similar working condition, or carrying out abnormal detection on the equipment performance degradation trend curve of any specified working condition, and carrying out early warning when the performance parameter threshold is exceeded.
And for more than one same device, performing abnormity detection on the device performance degradation trend curve of the current working condition or the similar working condition of each device or the device performance degradation trend curve of any specified working condition of each device, and performing early warning if the performance parameter exceeds the threshold value.
Regarding the display of the performance degradation trend, for the equipment with the performance degradation trend unrelated to the working condition, a performance degradation trend curve is directly displayed, namely longitudinal slice comparison.
And for the equipment with the performance decline trend related to the industrial and mining, displaying the performance decline trend curve of the current working condition or the similar working condition, or displaying any specified working condition, acquiring data under various working conditions, and uniformly calculating the equipment performance decline trend curve of the abnormal threshold working condition, namely comparing longitudinal slices.
And for more than one same device, simultaneously displaying the device performance degradation trend curve of the current working condition or the similar working condition of each device, or simultaneously displaying the device performance degradation trend curve of any specified working condition of each device, namely comparing the longitudinal slice with the transverse slice.
The equipment performance variation trend curve can be displayed with a short-term trend and can also be displayed with a long-term trend, wherein the short-term trend can adopt a 10s time interval and is used for displaying short-term performance variation or abnormity; the long-term trend may take a 1 day time interval for trend display of long-term performance changes.
Because the model parameters obtained by historical data, namely the model parameters obtained by the test, are adopted in the scheme, and the difference exists between the test environment and the actual production environment, the obtained model parameters need to be continuously optimized in an iterative manner, and the following two ways are mainly adopted for optimization:
and (3) offline manual optimization, namely performing offline evaluation on algorithm performance at the initial stage of putting the obtained early warning model into use, and manually selecting data close to the current time to retrain and optimize the model.
And (3) performing online automatic optimization, namely detecting the performance of the algorithm in real time online after the obtained early warning model is put into use for a certain time, and automatically selecting data close to the current time to retrain and optimize the early warning model.
The above mentioned device is specifically any one of the following: the embodiments of the present invention are not limited to the motor, the inverter, the transformer, and the switch.
The early warning model can also carry out diagnosis and early warning on equipment faults, and comprises the following categories of diagnosis and early warning:
valve + sensor diagnostic model:
most equipment of the unit runs by using equipment driving and sensor detection, models of the equipment are built, time for equipment action and sensor detection in place is automatically counted, and fault diagnosis and potential fault diagnosis (sensor abnormity, valve action abnormity, clamping and the like) of the equipment such as valve action and sensor detection are realized. And for the alarm of definite faults, quick push or directional voice alarm is realized.
Steel coil trolley fault diagnosis model:
the transverse movement of the steel coil trolley is generally driven by a motor, a strip encoder, a strip position detection proximity switch and an elevation switch with zone judgment. Meanwhile, the steel coil trolley needs to treat a safety cover plate, transport steel coils, coil up and also has the functions of lifting, lifting position detection, upper and lower limit position detection and the like.
By establishing a steel coil trolley transverse motor detection model, a belt load (according to different steel coil weights) current model and a no-load current model, fault diagnosis is realized under the condition of abnormal load.
And (3) establishing diagnosis of the detection of the transverse moving encoder and the sensor of the steel coil trolley, for example, between 1200 mm and 1250mm, detecting a high switch only, and the like, if not, indicating that a problem occurs in the proximity switch or the position detection, and providing an alarm log.
And establishing a diagnosis model for lifting of the steel coil trolley and detection of the sensor.
Decoiler driving system diagnosis model
The uncoiler is divided into speed control and tension saturation control, an ACR control mode is used when the uncoiler normally runs, meanwhile, the feedback speed of the ACR control mode is always consistent with the speed of an inlet tension roller, and when the speed is abnormal (the speed is suddenly changed, if the linear speed is obviously lower than the speed of the tension roller or the speed is obviously higher than the speed of the tension roller, and the tail-flick coil diameter is smaller than a certain value, the ACR control mode is used for diagnosing whether equipment exists or abnormal control exists.
Diagnostic model of tension roller set driving system
The general speed closed-loop control of the tension roller group, the load value of the estimated tension roller group is set according to the thickness, the width, the strength and the front and back tension of the strip steel, and the possibility of actual load feedback and equipment (reduction gearbox) abnormity diagnosis are compared; and diagnosing the speed deviation between the roller sets, the speed given deviation and the actual deviation, and realizing the fault diagnosis of the tension roller set encoder.
Loop driving system diagnosis model:
the control of the loop driving motor generally uses indirect tension control, and according to the deviation of speed setting and feedback, the setting and feedback of indirect tension value, the monitoring of indirect tension speed compensation value, the estimation of the possibility of transmission failure.
The acid cleaning section does not have the diagnosis model of blocking of transmission compression roller:
in order to prevent the compression roller from blocking rotation, a proximity switch is added to the compression roller, whether the compression roller blocks rotation or not is detected by combining the unit speed, and the compression roller is sent to a point detection terminal in an alarming mode.
Rolling mill process diagnosis model (high frequency, 10ms, urgent handsome diagnosis)
The method comprises the following steps: the system comprises an incoming material rear difference aridity diagnosis model, an incoming material deviation correction abnormity model, a tension deviation abnormity diagnosis model and a rolling force deviation abnormity diagnosis model.
Main transmission diagnosis model:
the method comprises the following steps: the self-learning model comprises a main motor load and temperature rise curve self-learning model, a main motor speed, rolling force, tension and load curve self-learning model, and a main motor non-belt roller correcting and leader positioning current detection model.
Hydraulic tank diagnosis model:
after the oil is initially filled, a model for monitoring the oil level abnormity in the hydraulic and running processes of the oil tank and an oil tank temperature monitoring model are automatically recorded and used for achieving different evaluation indexes for different environmental temperatures.
Diagnosis model of mist exhaust fan of rolling mill:
and diagnosing the state model of the fog exhaust fan according to the rotating speed and the load.
Full-line CPC diagnostic model: the device is used for diagnosing the state of the deviation correcting device according to the position of the CPC oil cylinder and the position of the strip steel head and appropriately reminding the position of key equipment.
One or more technical solutions in the embodiments of the present invention have at least the following technical effects or advantages:
the invention provides a method for early warning equipment, which comprises the following steps: the method comprises the steps of obtaining model parameters for predicting the state of equipment according to historical operation data of the equipment, then collecting online data of the equipment in real time, obtaining an early warning model for predicting the state of the equipment based on the online data and the model parameters, and finally early warning the performance of the equipment based on various performance parameter thresholds of the equipment and the early warning model, so that the data of the equipment can be effectively monitored, early warning is timely carried out on performance decline trends, abnormal detection is carried out on the performance of the equipment, and the purpose of real-time monitoring is achieved.
Example two
Based on the same inventive concept, an embodiment of the present invention further provides an apparatus for early warning of device performance, as shown in fig. 2, including:
an obtaining module 201, configured to obtain historical operating data of a device;
a construction module 202, configured to obtain a model parameter for predicting a device state based on the historical operating data;
the acquisition module 203 is used for acquiring online data of the equipment in real time;
an obtaining module 204, configured to obtain, based on the online data and the model parameter, an early warning model for predicting a device state;
the early warning module 205 is configured to perform early warning on the performance of the device based on various performance parameter thresholds of the device and the early warning model.
In an optional embodiment, the method further comprises: and the characteristic processing module is used for carrying out characteristic processing on the historical operating data, wherein the characteristic processing comprises statistical processing, missing or null value supplementing processing and dimension reduction processing on the historical operating data.
In an alternative embodiment, the building model includes:
the first obtaining unit is used for obtaining a feature matrix of the historical operating data based on the historical operating data;
the dividing unit is used for dividing the characteristic matrix into a training set, a verification set and a test set;
and the second obtaining unit is used for obtaining model parameters for predicting the equipment state based on the training of the training set, the verification set and the test set.
In an optional implementation, the obtaining module 204 is configured to obtain an early warning model for predicting a device state by using a machine learning algorithm based on the online data and the model parameter.
In an optional implementation manner, the early warning model is specifically an equipment performance variation trend curve.
In an alternative embodiment, the early warning module 205 includes:
the first early warning unit is used for judging whether the online data of the equipment collected in real time exceeds a corresponding performance parameter threshold value or not based on the equipment performance change trend curve, and if the online data exceeds the corresponding performance parameter threshold value, early warning the performance decline trend of the equipment;
and the second early warning unit is used for early warning the abnormal condition of the performance of the equipment based on the equipment performance change trend curve.
In an optional embodiment, the apparatus is specifically any one of the following: motor, converter, transformer, switch.
EXAMPLE III
Based on the same inventive concept, the third embodiment of the present invention provides a computer device, as shown in fig. 3, including a memory 304, a processor 302, and a computer program stored on the memory 304 and executable on the processor 302, where the processor 302 implements the steps of the above-mentioned method for device performance warning when executing the program.
Where in fig. 3 a bus architecture (represented by bus 300), bus 300 may include any number of interconnected buses and bridges, bus 300 linking together various circuits including one or more processors, represented by processor 302, and memory, represented by memory 304. The bus 300 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 306 provides an interface between the bus 300 and the receiver 301 and transmitter 303. The receiver 301 and the transmitter 303 may be the same element, i.e., a transceiver, providing a means for communicating with various other apparatus over a transmission medium. The processor 302 is responsible for managing the bus 300 and general processing, and the memory 304 may be used for storing data used by the processor 302 in performing operations.
Example four
Based on the same inventive concept, a fourth embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the method for device performance early warning.
The algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. Moreover, the present invention is not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components of the apparatus, computer device, and apparatus for performance alerting according to embodiments of the present invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
Claims (10)
1. A method for device performance early warning, comprising:
acquiring historical operating data of equipment;
obtaining model parameters for predicting equipment states based on the historical operating data;
collecting online data of the equipment in real time;
obtaining an early warning model for predicting the state of the equipment based on the online data and the model parameters;
and early warning the performance of the equipment based on various performance parameter thresholds of the equipment and the early warning model.
2. The method of claim 1, after the obtaining historical operational data for the device, further comprising:
and performing characteristic processing on the historical operating data, wherein the characteristic processing comprises statistical processing on the historical operating data, filling processing of missing or null values and dimension reduction processing.
3. The method of claim 1, wherein deriving model parameters for predicting a state of a device based on the historical operating data comprises:
obtaining a feature matrix of the historical operating data based on the historical operating data;
dividing the feature matrix into a training set, a verification set and a test set;
and obtaining model parameters for predicting the state of the equipment based on the training of the training set, the verification set and the test set.
4. The method of claim 1, wherein deriving an early warning model for predicting a state of a device based on the online data and the model parameters comprises:
and obtaining an early warning model for predicting the state of the equipment by adopting a machine learning algorithm based on the online data and the model parameters.
5. The method of claim 1, wherein the early warning model is specifically a device performance trend curve.
6. The method of claim 5, wherein pre-warning the performance of the device based on the pre-warning model for various performance parameter thresholds of the device comprises:
judging whether the online data of the equipment collected in real time exceeds a corresponding performance parameter threshold value or not based on the equipment performance change trend curve, and if so, early warning the performance decline trend of the equipment;
and early warning the abnormal condition of the performance of the equipment based on the equipment performance change trend curve.
7. The method according to claim 1, wherein the device is specifically any one of: motor, converter, transformer, switch.
8. An apparatus for device performance early warning, comprising:
the acquisition module is used for acquiring historical operating data of the equipment;
the construction module is used for obtaining model parameters for predicting the equipment state based on the historical operating data;
the acquisition module is used for acquiring online data of the equipment in real time;
an obtaining module, configured to obtain an early warning model for predicting a device state based on the online data and the model parameter;
and the early warning module is used for early warning the performance of the equipment based on various performance parameter thresholds of the equipment and the early warning model.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method steps of any of claims 1-7 when executing the program.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method steps of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111385924.4A CN114066274A (en) | 2021-11-22 | 2021-11-22 | Equipment performance early warning method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111385924.4A CN114066274A (en) | 2021-11-22 | 2021-11-22 | Equipment performance early warning method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114066274A true CN114066274A (en) | 2022-02-18 |
Family
ID=80278855
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111385924.4A Pending CN114066274A (en) | 2021-11-22 | 2021-11-22 | Equipment performance early warning method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114066274A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115169505A (en) * | 2022-09-06 | 2022-10-11 | 杭州浅水数字技术有限公司 | Early warning method and early warning system for mechanical fault of special equipment moving part |
| CN116467835A (en) * | 2023-02-07 | 2023-07-21 | 山东申东发酵装备有限公司 | Beer fermentation tank monitoring system |
| CN116990683A (en) * | 2023-09-26 | 2023-11-03 | 临沂科锐电子有限公司 | Driving motor locked rotor detection system and detection method based on electric variable |
| WO2024099022A1 (en) * | 2022-11-07 | 2024-05-16 | 中广核太阳能德令哈有限公司 | Method and system for testing rotation performance of heat collector |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104091070A (en) * | 2014-07-07 | 2014-10-08 | 北京泰乐德信息技术有限公司 | Rail transit fault diagnosis method and system based on time series analysis |
| CN108537464A (en) * | 2018-04-23 | 2018-09-14 | 国家电网公司 | Early warning based on cloud platform and method for evaluating state and system |
| CN112629585A (en) * | 2020-12-02 | 2021-04-09 | 三门核电有限公司 | Equipment on-line monitoring method and device based on multi-dimensional parameter estimation |
| CN113313365A (en) * | 2021-05-14 | 2021-08-27 | 华能重庆珞璜发电有限责任公司 | Degradation early warning method and device for primary air fan |
-
2021
- 2021-11-22 CN CN202111385924.4A patent/CN114066274A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104091070A (en) * | 2014-07-07 | 2014-10-08 | 北京泰乐德信息技术有限公司 | Rail transit fault diagnosis method and system based on time series analysis |
| CN108537464A (en) * | 2018-04-23 | 2018-09-14 | 国家电网公司 | Early warning based on cloud platform and method for evaluating state and system |
| CN112629585A (en) * | 2020-12-02 | 2021-04-09 | 三门核电有限公司 | Equipment on-line monitoring method and device based on multi-dimensional parameter estimation |
| CN113313365A (en) * | 2021-05-14 | 2021-08-27 | 华能重庆珞璜发电有限责任公司 | Degradation early warning method and device for primary air fan |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115169505A (en) * | 2022-09-06 | 2022-10-11 | 杭州浅水数字技术有限公司 | Early warning method and early warning system for mechanical fault of special equipment moving part |
| WO2024099022A1 (en) * | 2022-11-07 | 2024-05-16 | 中广核太阳能德令哈有限公司 | Method and system for testing rotation performance of heat collector |
| CN116467835A (en) * | 2023-02-07 | 2023-07-21 | 山东申东发酵装备有限公司 | Beer fermentation tank monitoring system |
| CN116467835B (en) * | 2023-02-07 | 2024-01-26 | 山东申东发酵装备有限公司 | Beer fermentation tank monitoring system |
| CN116990683A (en) * | 2023-09-26 | 2023-11-03 | 临沂科锐电子有限公司 | Driving motor locked rotor detection system and detection method based on electric variable |
| CN116990683B (en) * | 2023-09-26 | 2023-12-29 | 临沂科锐电子有限公司 | Driving motor locked rotor detection system and detection method based on electric variable |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114066274A (en) | Equipment performance early warning method and device | |
| US20220137613A1 (en) | Method and system for predicting failure of mining machine crowd system | |
| CN112580153B (en) | Health state management system and method for vehicle running gear monitoring component | |
| US11521105B2 (en) | Machine learning device and machine learning method for learning fault prediction of main shaft or motor which drives main shaft, and fault prediction device and fault prediction system including machine learning device | |
| US10410440B2 (en) | Distributed system and method for monitoring vehicle operation | |
| CN104992270B (en) | Power transmission and transformation equipment state overhauling aid decision-making system and method | |
| CN113077172A (en) | Equipment state trend analysis and fault diagnosis method | |
| WO2022134495A1 (en) | Deep learning-based device anomaly detection method and system, and computer medium | |
| CN112924205B (en) | Work machine fault diagnosis method and device, work machine and electronic equipment | |
| CN110414154B (en) | Fan component temperature abnormity detection and alarm method with double measuring points | |
| Van Tung et al. | Machine fault diagnosis and prognosis: The state of the art | |
| KR102102346B1 (en) | System and method for condition based maintenance support of naval ship equipment | |
| CN111098463A (en) | Injection molding machine fault diagnosis system and diagnosis method | |
| CN106650157A (en) | Method, device and system for vehicle part fault probability estimation | |
| KR20190081933A (en) | Method for sensing and diagnosing abnormality of manufacture equipment | |
| CN114021846A (en) | Industrial enterprise equipment state early warning method and system | |
| CN114220189A (en) | Monitoring method, prediction system, electronic device and storage medium | |
| CN109784127B (en) | Equipment health state early warning method and system thereof | |
| KR102108975B1 (en) | Apparatus and method for condition based maintenance support of naval ship equipment | |
| CN117350377A (en) | Knowledge graph driving-based equipment fault diagnosis method and device | |
| CN113955149B (en) | Health diagnosis method and device for motor system | |
| Byington et al. | False alarm mitigation of vibration diagnostic systems | |
| Zhang | Comparison of data-driven and model-based methodologies of wind turbine fault detection with SCADA data | |
| CN117911012B (en) | Equipment health management system based on equipment ecological detection and running state evaluation | |
| Wasif et al. | Condition monitoring system for process industries a business approach |
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 |