CN111931323B - Memory, hydrocracking equipment fault prediction method, device and equipment - Google Patents
Memory, hydrocracking equipment fault prediction method, device and equipment Download PDFInfo
- Publication number
- CN111931323B CN111931323B CN201910351709.9A CN201910351709A CN111931323B CN 111931323 B CN111931323 B CN 111931323B CN 201910351709 A CN201910351709 A CN 201910351709A CN 111931323 B CN111931323 B CN 111931323B
- Authority
- CN
- China
- Prior art keywords
- data
- monitoring data
- monitoring
- time period
- vibration
- 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
- 238000004517 catalytic hydrocracking Methods 0.000 title claims abstract description 51
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000012544 monitoring process Methods 0.000 claims abstract description 161
- 238000012549 training Methods 0.000 claims description 27
- 238000013145 classification model Methods 0.000 claims description 16
- 238000012360 testing method Methods 0.000 claims description 13
- 238000001914 filtration Methods 0.000 claims description 10
- 230000001133 acceleration Effects 0.000 claims description 8
- 238000006073 displacement reaction Methods 0.000 claims description 8
- 238000011156 evaluation Methods 0.000 claims description 6
- 238000003066 decision tree Methods 0.000 claims description 4
- 238000012417 linear regression Methods 0.000 claims description 4
- 238000007477 logistic regression Methods 0.000 claims description 4
- 238000003062 neural network model Methods 0.000 claims description 4
- 238000012706 support-vector machine Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000035939 shock Effects 0.000 claims 3
- 238000004519 manufacturing process Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000013480 data collection Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 239000003208 petroleum Substances 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 241000282414 Homo sapiens Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 239000013064 chemical raw material Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000004989 laser desorption mass spectroscopy Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005504 petroleum refining Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention discloses a memory, a method, a device and equipment for predicting the fault of hydrocracking equipment, wherein the method comprises the following steps: acquiring historical monitoring data of a monitored object; determining various data acquisition unified data acquisition time points in the monitoring data according to a preset time period; performing data sorting on various monitoring data according to data acquisition time points in a preset time period so as to synchronize the acquisition time points of the various monitoring data; associating the vibration data and the working condition data in the monitoring data according to the unified data acquisition time point in the preset time period to construct modeling data; determining the vibration data and the working condition data as independent variables; determining the probability and/or the fault type of equipment faults as target variables; establishing a prediction model; and taking the monitoring data of the monitored object acquired in real time as parameters, and acquiring a prediction result through a prediction model. The invention can improve the timeliness and accuracy of the prediction of the hydrocracking equipment fault.
Description
Technical Field
The invention relates to the field of petrochemical industry, in particular to a method, a device and equipment for predicting faults of a storage and hydrocracking equipment.
Background
Petroleum is an important energy source and a high-quality chemical raw material, is an important strategic material related to the national estimated population, and the petroleum industry is an important basic industry of national economy. With the rapid development of economy, the demand of human beings for energy is increasing.
With the development of information technology, the informatization degree of petroleum refining production devices is higher and higher, and mass production data is accumulated along with the informatization degree; the data hides a large amount of important production information, and big data technology is the most effective means for mining and utilizing the information. The method is characterized in that large data are subjected to specialized processing, so that the internal rules of the data are found, each link in the production flow is pre-judged, and the production decision is supported.
The staff is based on long-term work experience. The fault or fault hidden danger of the equipment can be judged in advance by identifying the vibration characteristic of the equipment during operation, so that the loss caused by the equipment fault can be reduced.
The inventor finds that the prior art at least has the following defects through a manual prediction mode:
because the manual judgment is not only poor in timeliness, but also has certain subjectivity and uncertainty, the missed judgment and the misjudgment of equipment faults are easily caused.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a memory, a hydrocracking equipment failure prediction method, a hydrocracking equipment failure prediction device and equipment. The invention can improve the timeliness and accuracy of the prediction of the hydrocracking equipment failure.
The invention provides a hydrocracking equipment fault prediction method, which comprises the following steps:
s11, acquiring historical monitoring data of the monitored object; the monitoring data comprises vibration data, working condition data and fault records of the monitored object; the vibration data comprises vibration displacement data, speed data and vibration acceleration data; the working condition data comprises temperature data, pressure data and flow data of the monitored object; the monitored object comprises a pump or a compressor;
s12, determining various data acquisition unified data acquisition time points in the monitoring data according to a preset time period;
s13, performing data sorting on each monitoring data according to the data collection time point in the preset time period, so as to synchronize the collection time points of each monitoring data, including: filtering the monitoring data of which the time period of original data acquisition is less than the preset time period, and deleting the monitoring data inconsistent with the data acquisition time point in the preset time period; performing data filling according to the monitoring data of which the time period of original data acquisition is greater than the preset time period, and performing data filling when monitoring data are lost at the data acquisition time point in the preset time period;
S14, correlating the vibration data and the working condition data in the monitoring data according to the unified data acquisition time points in the preset time period to construct modeling data;
s15, determining the vibration data and the working condition data as independent variables of a prediction model;
determining the probability and/or the fault type of equipment fault as a target variable of the prediction model;
s16, performing model training on the modeling data through a classification model according to the target variable and the independent variable to establish a prediction model for acquiring the fault probability of the hydrocracking equipment;
and S17, taking the monitoring data of the monitored object acquired in real time as parameters, and acquiring a prediction result through a prediction model.
Preferably, in the present invention, the data padding performed when the monitoring data is missing at the data acquisition time point in the preset time period includes:
defining other monitoring data within a preset time from a certain data acquisition time point as the adjacent monitoring data of the data acquisition time point;
when monitoring data are lost at a certain data acquisition time point and the data acquisition time point has adjacent monitoring data, taking the adjacent monitoring data closest to the time as the monitoring data of the data acquisition time;
Preferably, in the present invention, the method further comprises:
and when monitoring data are missed at a certain data acquisition time point and the data acquisition time is not close to the monitoring data, performing mean value calculation on the monitoring data in a preset time period to generate the monitoring data of the data acquisition time.
Preferably, in the present invention, the method further comprises:
and when the monitoring data are vibration data, respectively establishing a pair of linear models of each type of vibration data, and carrying out second data filling on the vibration data with the fitting degree larger than a preset value.
Preferably, in the present invention, the vibration data further includes vibration intensity and/or vibration frequency.
Preferably, in the present invention, the training of the classification model on the modeling data includes:
s21, dividing the modeling data into training data and testing data according to a preset proportion;
s22, modeling by using the training data, and evaluating by using the test data;
s23, when the evaluation result does not reach the preset value, adjusting the parameter items and/or the iteration times during modeling, and returning to the step S21; and when the evaluation result reaches a preset value, finishing modeling.
Preferably, in the present invention, the classification model includes one of a general linear regression model, a logistic regression model, a decision tree model, a support vector machine model, a discriminant model and a neural network model, and any combination thereof.
In another aspect of the embodiments of the present invention, there is also provided a hydrocracking apparatus failure prediction apparatus, including:
a history data acquisition unit for acquiring historical monitoring data of the monitored object; the monitoring data comprises vibration data, working condition data and fault records of the monitored object; the vibration data comprises vibration displacement data, speed data and vibration acceleration data; the working condition data comprises temperature data, pressure data and flow data of the monitored object; the monitored object comprises a pump or a compressor;
the synchronization unit is used for determining various data acquisition unified data acquisition time points in the monitoring data according to a preset time period;
the data arrangement unit is used for carrying out data arrangement on each monitoring data according to the data acquisition time point in the preset time period so as to synchronize the acquisition time points of each monitoring data, and comprises: filtering the monitoring data of which the time period of original data acquisition is less than the preset time period, and deleting the monitoring data inconsistent with the data acquisition time point in the preset time period; performing data filling according to the monitoring data of which the time period for acquiring the original data is greater than the preset time period, and performing data filling when the monitoring data is lost at the data acquisition time point in the preset time period;
The association unit is used for associating the vibration data and the working condition data in the monitoring data according to the unified data acquisition time point in the preset time period to construct modeling data;
the parameter determining unit is used for determining the vibration data and the working condition data as independent variables of a prediction model; determining the probability and/or the fault type of equipment fault as a target variable of the prediction model;
the model generation unit is used for carrying out model training on the modeling data through a classification model according to the target variable and the independent variable so as to establish a prediction model for acquiring the fault probability of the hydrocracking equipment;
and the result generation unit is used for acquiring the monitoring data of the monitored object acquired in real time as parameters and acquiring a prediction result through the prediction model.
In another aspect of the embodiments of the present invention, there is also provided a memory including a software program adapted to be executed by a processor for the steps of the above-described hydrocracking plant failure prediction method.
In another aspect of the embodiments of the present invention, there is also provided a hydrocracking apparatus failure prediction apparatus, which includes a computer program stored on a memory, the computer program including program instructions, which, when executed by a computer, cause the computer to perform the method according to the above aspects, and achieve the same technical effects.
Therefore, in the invention, the incidence relation between the monitoring data and the equipment fault is pre-judged by using the vibration data and the working condition data in the historical monitoring data in a mode of setting a prediction model; when modeling data of a prediction model is constructed, various monitoring data with inconsistent acquisition periods are subjected to data sorting in the modes of data filtering, data filling and the like, so that the various monitoring data have uniform acquisition periods and acquisition time points, and various monitoring data can be synchronously associated by taking the acquisition time points as association points.
According to the embodiment of the invention, the monitoring data of the vibration data including the working condition data can have better correspondence, so that the prediction accuracy of the established prediction model of the hydrocracking equipment failure probability can be more accurate. Therefore, the monitoring object is monitored by taking the monitoring data acquired in real time as parameters through the prediction model, so that the alarm response and the fault type of the equipment which is about to or has failed can be timely and accurately judged. That is, the invention can find the equipment abnormity in advance in a certain time, help the equipment maintenance personnel to find the equipment abnormity as early as possible, find and process the equipment abnormity as early as possible, reduce the economic loss, reduce the equipment maintenance cost and obtain the indirect benefit.
Furthermore, in the invention, for the missing vibration data, the vibration data with the fitting degree larger than the preset value is obtained by respectively establishing a pair of linear models of each vibration data, and the second data filling is carried out, so that the accuracy and effectiveness of the data filling are improved, and the prediction result can be more accurate.
Furthermore, in the invention, the prediction effect of the prediction model can be verified and improved by dividing the modeling data into the training data and the test data according to the preset proportion when the classification model training is carried out on the modeling data, so that the prediction accuracy of the prediction model established by the method is more accurate.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic diagram of the steps of a hydrocracking plant failure prediction process according to the present invention;
FIG. 2 is a schematic diagram of a hydrocracking plant failure prediction unit according to the present invention;
FIG. 3 is a schematic diagram of a hydrocracking plant failure prediction plant according to the present invention.
Detailed Description
In order to make those skilled in the art better understand the technical solution of the present invention, the technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to improve timeliness and accuracy of a hydrocracking equipment fault prediction, as shown in fig. 1, an embodiment of the present invention provides a hydrocracking equipment fault prediction method, including the steps of:
s11, acquiring historical monitoring data of the monitored object; the monitoring data comprises vibration data, working condition data and fault records of the monitored object; the vibration data comprises vibration displacement data, speed data and vibration acceleration data; the working condition data comprises temperature data, pressure data and flow data of the monitored object; the monitored object comprises a pump or a compressor;
In the embodiment of the invention, the equipment fault prediction is based on the existing monitoring data such as vibration data, working condition data, fault records and the like, a prediction model of the incidence relation between the production running condition and the equipment fault is established by a big data analysis method, and then the acquired real-time monitoring data is taken as a parameter to monitor and alarm possible abnormal states according to the prediction model. The monitoring data can be obtained from LIMS, real-time data acquisition systems (including DCS), ERP (including EM equipment technology files), and monitoring systems corresponding to each monitored object, such as a pump monitoring system or a compressor monitoring system.
The vibration data in the embodiment of the invention can comprise key data such as vibration displacement data, speed data, vibration acceleration data and the like; the further vibration data can also comprise vibration intensity and vibration frequency, and the types of independent variables in the process of modeling data can be increased through the enrichment of the types of the vibration data, so that the prediction effect and the precision of the prediction model can be optimized.
S12, determining various data acquisition unified data acquisition time points in the monitoring data according to a preset time period;
the monitoring data in the embodiment of the invention are respectively from different monitoring devices, and each detection device has a specific data acquisition period, so that different monitoring data have different acquisition periods and acquisition time points. It should be noted that, in the embodiment of the present invention, regarding the determination of the preset time period, a person skilled in the art may obtain the determination according to actual needs or limited experiments, and the determination is not limited specifically herein.
S13, performing data sorting on each monitoring data according to the data collection time point in the preset time period, so as to synchronize the collection time points of each monitoring data, including: filtering the monitoring data of which the time period of original data acquisition is less than the preset time period, and deleting the monitoring data inconsistent with the data acquisition time point in the preset time period; performing data filling according to the monitoring data of which the time period of original data acquisition is greater than the preset time period, and performing data filling when monitoring data are lost at the data acquisition time point in the preset time period;
after a preset time period and various data acquisition unified data acquisition time points are determined, historical data need to be correspondingly sorted; for monitoring data with too high data acquisition frequency and too large data quantity, only data needs to be thinned in a data filtering mode;
in practical application, due to the limitation of storage space of some monitoring objects (such as a pump monitoring system), existing historical data monitoring data of the monitoring objects are often diluted data, and the time period of original data acquisition is larger than a preset time period; in this case, the data acquisition time period and the acquisition time point are consistent with the preset time period only by performing data filling according to the preset filling rule; the preset filling rule in the embodiment of the present invention may be obtained by calculating an average value of the monitoring data values at the nearest time points on both sides of the time point of the missing monitoring data, or may be other conventional data filling manners.
Because of the way of calculating the mean value of the monitoring data values of the nearest time points at both sides of the time point of the missing monitoring data to generate the monitoring data of the data missing point, it may be possible that the deviation of the result of the mean value calculation is too large because a plurality of monitoring data missing points are also arranged at one side of the monitoring data missing point, and therefore, for the embodiment of the present invention, the preferable data filling scheme may include defining other monitoring data within a preset time from a certain data acquisition time point as the adjacent monitoring data of the data acquisition time point; when monitoring data are lost at a certain data acquisition time point and the data acquisition time point has adjacent monitoring data, the adjacent monitoring data closest to the time point are taken as the monitoring data of the data acquisition time. That is, when monitoring data is missing at a certain data acquisition time point, whether other data acquisition time points closest to the time point are near monitoring data is judged, and if so, the near monitoring data is used as the missing monitoring data to fill the missing point. In this way, the effectiveness of data filling is improved by preferentially filling the monitoring data with the closest distance.
Further, the preset filling rule may further include a step of secondary filling, specifically, when the monitored data is vibration data, a pair of linear models of each type of vibration data is respectively established, and the vibration data with the fitting degree larger than a preset value is subjected to secondary data filling. In this way, the filled monitoring data is further corrected through a verification process for increasing the fitting degree, so that the effectiveness of data filling is further improved.
S14, correlating the vibration data and the working condition data in the monitoring data according to the unified data acquisition time points in the preset time period to construct modeling data;
after the time periods (i.e. time point interval granularity) of various monitoring data acquisition are kept consistent, the corresponding relation among the monitoring data can be established, and modeling data is constructed. In practical application, each parameter item of various monitoring data (such as vibration data, working condition data and fault records) at a certain time point can be included in the strip records of the wide table in a mode of establishing the wide table; when the wide table comprises a large number of records, modeling data can be constructed, namely, the wide table is generated according to the time corresponding relation of various monitoring data; the wide table is used for storing the values of all parameter items in all kinds of monitoring data at the same time point in an associated mode.
S15, determining the vibration data and the working condition data as independent variables of a prediction model;
determining the probability and/or the fault type of equipment fault as a target variable of the prediction model;
in the embodiment of the invention, the prediction model needs to pre-judge the fault occurrence rate of the equipment according to the numerical composition relationship of various vibration data and various working condition data at different time points, so that the vibration data and the working condition data can be determined as independent variables of the prediction model, and the fault occurrence rate and the fault type of the equipment are determined as target variables of the prediction model.
S16, performing model training on the modeling data through a classification model according to the target variable and the independent variable to establish a prediction model for acquiring the fault probability of the hydrocracking equipment;
after the target variable and the independent variable are determined, training of data and construction of a model can be carried out through the data of the independent variable and the data of the target variable; specifically, the classification model may be selected from a general linear regression model, a logistic regression model, a decision tree model, a support vector machine model, a discriminant model, a neural network model, and the like, as long as the target variable can be predicted by the independent variable.
In practical application, in order to make the prediction result more accurate, modeling data can be further divided into training data and test data according to a preset proportion to perform modeling, specifically:
training modeling data through a classification model according to a target variable and an independent variable, and specifically comprises the following steps:
s21, dividing the modeling data into training data and testing data according to a preset proportion;
in practical applications, the preset ratio may be set to 7 to 3, that is, 70% of the data is used as training data, and the other 30% of the data is used as test data. It should be noted that, in the embodiment of the present invention, the numerical value of the preset ratio may be adjusted and set according to the needs of those skilled in the art, and is not limited specifically herein.
S22, modeling by using training data, and evaluating by using test data;
modeling through training data to construct an equipment prediction model; in practical applications, the classification model used in the embodiment of the present invention may be a general linear regression model, a logistic regression model, a decision tree model, a support vector machine model, a discriminant model, or a neural network model, or two or more of the models may be used for mutual verification and correction.
The test data may be evaluated during the modeling process to verify the accuracy and validity of the predictive model.
S23, when the evaluation result does not reach the preset requirement, adjusting the parameter items and/or the iteration times during modeling, and returning to the step S21; and when the evaluation result reaches the preset requirement, finishing modeling.
In the embodiment of the invention, the preset requirement can be a requirement for the fitting degree between the training result and the test data; in the process of data training and modeling, the accuracy of the established model can be evaluated by comparing the fitting degree of the training result and the test data, so that a prediction model with a more accurate prediction result can be established.
And S17, taking the monitoring data of the monitored object acquired in real time as parameters, and acquiring a prediction result through a prediction model.
By the embodiment of the invention, a real-time monitoring system of each pump or compressor in the hydrocracking equipment can be established, so that when the hydrocracking equipment is likely to have equipment failure or has failed, the monitoring data obtained in real time can be used as a judgment basis, and the corresponding pre-judgment result is obtained in real time by the failure prediction method in the invention, so that the corresponding alarm signal is generated in time. Namely, the invention can timely react to the fault of the equipment or the fault about to occur, thereby improving the timeliness and the accuracy of equipment fault prejudgment. Therefore, the invention can discover in advance for a certain time, help the equipment maintainer to discover the equipment abnormality as soon as possible, discover and treat the equipment abnormality as early as possible, reduce the economic loss, reduce the equipment maintenance cost and obtain indirect benefits.
In summary, the embodiment of the present invention utilizes the vibration data and the working condition data in the historical monitoring data, and pre-judges the association relationship between the monitoring data and the equipment failure by setting up a prediction model; when modeling data of a prediction model is constructed, the embodiment of the invention carries out data sorting on various monitoring data with inconsistent acquisition periods through data filtering, data filling and other modes, so that the various monitoring data have uniform acquisition periods and acquisition time points, and various monitoring data can be synchronously associated by taking the acquisition time points as association points.
According to the embodiment of the invention, the monitoring data of the vibration data including the working condition data has better correspondence, so that the prediction accuracy of the established prediction model of the hydrocracking equipment failure probability is more accurate.
Further, in the invention, for the missing vibration data, the vibration data with the fitting degree larger than the preset value is obtained by respectively establishing a pair of linear models of each vibration data, and the second data filling is carried out, so that the accuracy and effectiveness of the data filling are improved, and the prediction result can be more accurate.
Furthermore, in the invention, the prediction effect of the prediction model can be verified and improved by dividing the modeling data into the training data and the test data according to the preset proportion when the classification model training is carried out on the modeling data, so that the prediction accuracy of the prediction model established by the method is more accurate.
In an embodiment of the present invention, a hydrocracking apparatus failure prediction apparatus is further provided, and fig. 2 shows a schematic structural diagram of the hydrocracking apparatus failure prediction apparatus provided in the embodiment of the present invention, where the hydrocracking apparatus failure prediction apparatus is an apparatus corresponding to the hydrocracking apparatus failure prediction method in the embodiment corresponding to fig. 1, that is, the hydrocracking apparatus failure prediction method in the embodiment corresponding to fig. 1 is implemented by using a virtual apparatus, and each virtual module constituting the hydrocracking apparatus failure prediction apparatus may be executed by an electronic device, such as a network device, a terminal device, or a server.
Specifically, the hydrocracking equipment failure prediction device in the embodiment of the present invention includes:
a history data obtaining unit 01, configured to obtain historical monitoring data of a monitored object; the monitoring data comprises vibration data, working condition data and fault records of the monitored object; the vibration data comprises vibration displacement data, speed data and vibration acceleration data; the working condition data comprises temperature data, pressure data and flow data of the monitored object; the monitored object comprises a pump or a compressor;
the synchronization unit 02 determines various data acquisition unified data acquisition time points in the monitoring data according to a preset time period;
the data sorting unit 03 is configured to perform data sorting on each monitoring data according to a data acquisition time point in the preset time period, so as to synchronize the acquisition time points of each monitoring data, and includes: filtering the monitoring data of which the time period of original data acquisition is less than the preset time period, and deleting the monitoring data inconsistent with the data acquisition time point in the preset time period; performing data filling according to the monitoring data of which the time period of original data acquisition is greater than the preset time period, and performing data filling when monitoring data are lost at the data acquisition time point in the preset time period;
The association unit 04 is used for associating the vibration data and the working condition data in the monitoring data according to the unified data acquisition time points in the preset time period to construct modeling data;
the parameter determining unit 05 is used for determining the vibration data and the working condition data as independent variables of a prediction model; determining the probability and/or the fault type of equipment fault as a target variable of the prediction model;
and the model generation unit 06 is used for performing model training on the modeling data through a classification model according to the target variable and the independent variable so as to establish a prediction model for acquiring the fault probability of the hydrocracking equipment.
And a result generating unit 07, configured to obtain a prediction result through the prediction model by using the monitoring data of the monitoring target obtained in real time as a parameter.
Since the working principle and the beneficial effects of the hydrocracking equipment failure prediction device in the embodiment of the present invention have been described and illustrated in the hydrocracking equipment failure prediction method in embodiment 1, they may be referred to each other and are not described herein again.
In an embodiment of the present invention, there is further provided a memory, wherein the memory includes a software program, and the software program is adapted to be executed by the processor to perform each step of the hydrocracking equipment failure prediction method corresponding to fig. 1.
The embodiment of the present invention can be implemented by means of a software program, that is, by writing a software program (and an instruction set) for implementing each step in the method for predicting the failure of the hydrocracking apparatus corresponding to fig. 1, the software program is stored in a storage device, and the storage device is disposed in a computer device, so that the software program can be called by a processor of the computer device to implement the purpose of the embodiment of the present invention.
The embodiment of the invention provides a hydrocracking equipment failure prediction device, wherein a memory included in the hydrocracking equipment failure prediction device comprises a corresponding computer program product, and program instructions included in the computer program product can enable the computer to execute the hydrocracking equipment failure prediction method in the aspects and realize the same technical effect when the program instructions are executed by the computer.
Fig. 3 is a schematic diagram of a hardware structure of a hydrocracking plant failure prediction device as an electronic device according to an embodiment of the present invention, and as shown in fig. 3, the device includes one or more processors 610 and a memory 620. Take a processor 610 as an example. Preferably, the apparatus may further include: an input device 630 and an output device 640.
The processor 610, the memory 620, the input device 630, and the output device 640 may be connected by a bus or other means, and are exemplified by a bus in fig. 3.
The memory 620, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and modules. The processor 610 executes various functional applications and data processing of the electronic device, i.e., the processing method of the above-described method embodiment, by executing the non-transitory software programs, instructions and modules stored in the memory 620.
The memory 620 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data and the like. Further, the memory 620 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 620 optionally includes memory located remotely from the processor 610, which may be connected to the processing device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 630 may receive input numeric or character information and generate a signal input. The output device 640 may include a display device such as a display screen.
The one or more modules are stored in the memory 620 and, when executed by the one or more processors 610, perform:
s11, acquiring historical monitoring data of the monitored object; the monitoring data comprises vibration data, working condition data and fault records of the monitored object; the vibration data comprises vibration displacement data, speed data and vibration acceleration data; the working condition data comprises temperature data, pressure data and flow data of the monitored object; the monitored object comprises a pump or a compressor;
s12, determining various data acquisition unified data acquisition time points in the monitoring data according to a preset time period;
s13, performing data sorting on each monitoring data according to the data collection time point in the preset time period, so as to synchronize the collection time points of each monitoring data, including: filtering the monitoring data of which the time period of original data acquisition is less than the preset time period, and deleting the monitoring data inconsistent with the data acquisition time point in the preset time period; performing data filling according to the monitoring data of which the time period of original data acquisition is greater than the preset time period, and performing data filling when monitoring data are lost at the data acquisition time point in the preset time period;
S14, correlating the vibration data and the working condition data in the monitoring data according to the unified data acquisition time points in the preset time period to construct modeling data;
s15, determining the vibration data and the working condition data as independent variables of a prediction model;
determining the probability and/or the fault type of equipment fault as a target variable of the prediction model;
s16, performing model training on the modeling data through a classification model according to the target variable and the independent variable to establish a prediction model for acquiring the fault probability of the hydrocracking equipment;
and S17, taking the monitoring data of the monitored object acquired in real time as parameters, and acquiring a prediction result through a prediction model.
The product can execute the method provided by the embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method. For technical details that are not described in detail in this embodiment, reference may be made to the method provided by the embodiment of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage device and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage device includes: a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a ReRAM, an MRAM, a PCM, a NAND Flash, a NOR Flash, a Memory, a magnetic disk, an optical disk, or other various media that can store program codes.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A hydrocracking equipment failure prediction method is characterized by comprising the following steps:
s11, acquiring historical monitoring data of the monitored object; the monitoring data comprises vibration data, working condition data and fault records of the monitored object; the vibration data comprises vibration displacement data, speed data and vibration acceleration data; the working condition data comprises temperature data, pressure data and flow data of the monitored object; the monitored object comprises a pump or a compressor;
s12, determining various data acquisition unified data acquisition time points in the monitoring data according to a preset time period;
s13, performing data sorting on each monitoring data according to the data collecting time point in the preset time period, so as to synchronize the collecting time points of each monitoring data, including: filtering the monitoring data of which the time period of original data acquisition is less than the preset time period, and deleting the monitoring data inconsistent with the data acquisition time point in the preset time period; performing data filling according to the monitoring data of which the time period of original data acquisition is greater than the preset time period, and performing data filling when monitoring data are lost at the data acquisition time point in the preset time period;
S14, correlating the vibration data and the working condition data in the monitoring data according to the unified data acquisition time points in the preset time period to construct modeling data;
s15, determining the vibration data and the working condition data as independent variables of a prediction model;
determining the probability and/or the fault type of equipment fault as a target variable of the prediction model;
s16, performing model training on the modeling data through a classification model according to the target variable and the independent variable to establish a prediction model for acquiring the fault probability of the hydrocracking equipment;
and S17, taking the monitoring data of the monitored object acquired in real time as parameters, and acquiring a prediction result through a prediction model.
2. The method for predicting the failure of the hydrocracking equipment as claimed in claim 1, wherein the data filling in the absence of the monitoring data at the data collecting time point in the predetermined time period comprises:
defining other monitoring data within a preset time from a certain data acquisition time point as the adjacent monitoring data of the data acquisition time point;
when monitoring data are lost at a certain data acquisition time point and the data acquisition time point has adjacent monitoring data, the adjacent monitoring data closest to the time point are taken as the monitoring data of the data acquisition time.
3. The hydrocracking plant failure prediction method as set forth in claim 2, further comprising:
and when monitoring data are missed at a certain data acquisition time point and the data acquisition time is not close to the monitoring data, performing mean value calculation on the monitoring data in a preset time period to generate the monitoring data of the data acquisition time.
4. The hydrocracking apparatus failure prediction method according to claim 3, further comprising:
and when the monitoring data are vibration data, respectively establishing a pair of linear models of each type of vibration data, and carrying out second data filling on the vibration data with the fitting degree larger than a preset value.
5. The hydrocracking plant fault prediction method of claim 1, wherein the shock data further comprises shock intensity and/or shock frequency.
6. The hydrocracking plant fault prediction method of claim 1, wherein the classification model training of the modeling data comprises:
s21, dividing the modeling data into training data and testing data according to a preset proportion;
s22, modeling by using the training data, and evaluating by using the test data;
S23, when the evaluation result does not reach the preset value, adjusting the parameter items and/or the iteration times during modeling, and returning to the step S21; and when the evaluation result reaches a preset value, finishing modeling.
7. The method of claim 6, wherein the classification model comprises one of a general linear regression model, a logistic regression model, a decision tree model, a support vector machine model, a discriminant model, and a neural network model, and any combination thereof.
8. A hydrocracking plant failure prediction apparatus characterized by comprising:
a history data acquisition unit for acquiring historical monitoring data of the monitored object; the monitoring data comprises vibration data, working condition data and fault records of the monitored object; the vibration data comprises vibration displacement data, speed data and vibration acceleration data; the working condition data comprises temperature data, pressure data and flow data of the monitored object; the monitored object comprises a pump or a compressor;
the synchronization unit is used for determining various data acquisition unified data acquisition time points in the monitoring data according to a preset time period;
the data arrangement unit is used for carrying out data arrangement on each monitoring data according to the data acquisition time point in the preset time period so as to synchronize the acquisition time points of each monitoring data, and comprises: filtering the monitoring data of which the time period of original data acquisition is less than the preset time period, and deleting the monitoring data inconsistent with the data acquisition time point in the preset time period; performing data filling according to the monitoring data of which the time period of original data acquisition is greater than the preset time period, and performing data filling when monitoring data are lost at the data acquisition time point in the preset time period;
The association unit is used for associating the vibration data and the working condition data in the monitoring data according to the unified data acquisition time point in the preset time period to construct modeling data;
the parameter determining unit is used for determining the vibration data and the working condition data as independent variables of a prediction model; determining the probability and/or the fault type of equipment fault as a target variable of the prediction model;
the model generation unit is used for carrying out model training on the modeling data through a classification model according to the target variable and the independent variable so as to establish a prediction model for acquiring the fault probability of the hydrocracking equipment;
and the result generation unit is used for acquiring the monitoring data of the monitored object which is acquired in real time as a parameter and acquiring a prediction result through the prediction model.
9. A memory comprising a software program adapted to be executed by a processor for performing the steps of the method of any one of claims 1 to 7.
10. A hydrocracking plant failure prediction apparatus comprising a bus, a processor and a memory as claimed in claim 9;
the bus is used for connecting the memory and the processor;
The processor is configured to execute a set of instructions in the memory.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910351709.9A CN111931323B (en) | 2019-04-28 | 2019-04-28 | Memory, hydrocracking equipment fault prediction method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910351709.9A CN111931323B (en) | 2019-04-28 | 2019-04-28 | Memory, hydrocracking equipment fault prediction method, device and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111931323A CN111931323A (en) | 2020-11-13 |
| CN111931323B true CN111931323B (en) | 2022-08-12 |
Family
ID=73282600
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910351709.9A Active CN111931323B (en) | 2019-04-28 | 2019-04-28 | Memory, hydrocracking equipment fault prediction method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111931323B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112434064B (en) * | 2020-11-19 | 2023-09-29 | 脸萌有限公司 | Data processing method, device, medium and electronic equipment |
| CN113280854A (en) * | 2021-04-02 | 2021-08-20 | 无锡先导智能装备股份有限公司 | Monitoring method and device for induction heating device, computer equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106708016A (en) * | 2016-12-22 | 2017-05-24 | 中国石油天然气股份有限公司 | Failure monitoring method and failure monitoring device |
| CN107642347A (en) * | 2017-09-11 | 2018-01-30 | 中国石油大学(北京) | Accident forecast method for early warning and device under shale gas fractured well |
-
2019
- 2019-04-28 CN CN201910351709.9A patent/CN111931323B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106708016A (en) * | 2016-12-22 | 2017-05-24 | 中国石油天然气股份有限公司 | Failure monitoring method and failure monitoring device |
| CN107642347A (en) * | 2017-09-11 | 2018-01-30 | 中国石油大学(北京) | Accident forecast method for early warning and device under shale gas fractured well |
Non-Patent Citations (1)
| Title |
|---|
| 基于深度学习的故障预测技术研究;吴立金等;《计算机测量与控制》;20180225(第02期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111931323A (en) | 2020-11-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108375715B (en) | Power distribution network line fault risk day prediction method and system | |
| CN110489314B (en) | Model anomaly detection method and device, computer equipment and storage medium | |
| CN111539493B (en) | Alarm prediction method and device, electronic equipment and storage medium | |
| KR20190021560A (en) | Failure prediction system using big data and failure prediction method | |
| Hall et al. | The state of machine learning methodology in software fault prediction | |
| CN111931323B (en) | Memory, hydrocracking equipment fault prediction method, device and equipment | |
| CN112308273A (en) | Memory, petrochemical enterprise pollution discharge management method, device and equipment | |
| CN111177655B (en) | Data processing method and device and electronic equipment | |
| CN115759357B (en) | PSCADA data-based power supply equipment safety prediction method, system, equipment and medium | |
| Ekundayo | Wrapper feature selection based heterogeneous classifiers for software defect prediction | |
| Chouliaras et al. | Real-time anomaly detection of NoSQL systems based on resource usage monitoring | |
| CN115952081A (en) | Software testing method, device, storage medium and equipment | |
| CN111849544B (en) | Hydrocracking product quality automatic control method, device and storage | |
| CN108306997B (en) | Domain name resolution monitoring method and device | |
| JP2020140252A (en) | Management evaluation device, management evaluation method and program for the same | |
| CN112380759B (en) | Smart electric meter service life prediction method based on deep learning and CoxPH model | |
| CN111849545B (en) | Hydrocracking product quality prediction method, device and memory | |
| JP7062505B2 (en) | Equipment management support system | |
| US10689965B2 (en) | Field development plan selection system, method and program product | |
| CN107121616B (en) | Method and device for fault positioning of intelligent instrument | |
| CN112398706B (en) | Data evaluation standard determining method and device, storage medium and electronic equipment | |
| CN110597729B (en) | Pressure testing method, device and system based on dimension | |
| CN109726845B (en) | Hydrocracking product yield prediction method, model establishing method and storage device | |
| CN113283076A (en) | Method and device for researching electricity utilization abnormity and computer readable storage medium | |
| Friederich et al. | A Framework for Validating Data-Driven Discrete-Event Simulation Models of Cyber-Physical Production Systems |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231102 Address after: 100728 No. 22 North Main Street, Chaoyang District, Beijing, Chaoyangmen Patentee after: CHINA PETROLEUM & CHEMICAL Corp. Patentee after: Sinopec (Dalian) Petrochemical Research Institute Co.,Ltd. Address before: 100728 No. 22 North Main Street, Chaoyang District, Beijing, Chaoyangmen Patentee before: CHINA PETROLEUM & CHEMICAL Corp. Patentee before: DALIAN RESEARCH INSTITUTE OF PETROLEUM AND PETROCHEMICALS, SINOPEC Corp. |
|
| TR01 | Transfer of patent right |