CN115718901A - Data processing method and device based on converter valve and computer equipment - Google Patents
Data processing method and device based on converter valve and computer equipment Download PDFInfo
- Publication number
- CN115718901A CN115718901A CN202211432477.8A CN202211432477A CN115718901A CN 115718901 A CN115718901 A CN 115718901A CN 202211432477 A CN202211432477 A CN 202211432477A CN 115718901 A CN115718901 A CN 115718901A
- Authority
- CN
- China
- Prior art keywords
- data
- predicted
- converter valve
- determining
- data set
- 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
- 238000003672 processing method Methods 0.000 title abstract description 26
- 230000002159 abnormal effect Effects 0.000 claims abstract description 145
- 238000000034 method Methods 0.000 claims abstract description 38
- 238000012545 processing Methods 0.000 claims description 39
- 238000004590 computer program Methods 0.000 claims description 27
- 238000012216 screening Methods 0.000 claims description 25
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000007405 data analysis Methods 0.000 abstract description 2
- 230000000875 corresponding effect Effects 0.000 description 121
- 238000010586 diagram Methods 0.000 description 14
- 238000004364 calculation method Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 6
- 230000001174 ascending effect Effects 0.000 description 5
- 238000001816 cooling Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 239000003990 capacitor Substances 0.000 description 2
- 238000013016 damping Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 229910052731 fluorine Inorganic materials 0.000 description 1
- 125000001153 fluoro group Chemical group F* 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Landscapes
- Testing And Monitoring For Control Systems (AREA)
Abstract
The present application relates to the field of data analysis technologies, and in particular, to a data processing method and apparatus based on a converter valve, and a computer device. The method comprises the following steps: determining the initial weight of the data set to be predicted relative to the actual temperature data of the converter valve according to abnormal data in the data set to be predicted; the data set to be predicted is a set of data generated by equipment which is mutually associated with the converter valve in the operation process; determining predicted converter valve temperature data according to the initial weight and a data set to be predicted; determining a deviation value between the actual converter valve temperature data and the predicted converter valve temperature data, and adjusting the initial weight according to the deviation value to obtain a target weight; the target weight is used to predict whether a temperature anomaly exists for the converter valve. The application provides a data processing method and device based on a converter valve and computer equipment, wherein the data processing method and device can be used for rapidly determining the influence weight of each influence factor on the temperature of the converter valve.
Description
Technical Field
The present application relates to the field of data analysis technologies, and in particular, to a data processing method and apparatus based on a converter valve, and a computer device.
Background
Because the converter valve has a complex internal structure and contains more components, the converter station can generate a large amount of heat in the application process, and the converter valve needs to be ensured to be timely and effectively cooled for ensuring the long-term stable operation of the converter valve.
Because the factors influencing the temperature of the converter valve are more, in order to ensure that the temperature of the converter valve is effectively known, the weights corresponding to the factors influencing the temperature of the converter valve can be determined, and whether the temperature of the converter valve is abnormal or not can be further determined according to the weights corresponding to the influencing factors and the data corresponding to the influencing factors; in the prior art, factors influencing the temperature of the converter valve need to be manually checked step by step, and then the influence weight of each influencing factor on the temperature of the converter valve is determined.
However, the operation of determining the influence weight of each influencing factor on the temperature of the converter valve in the prior art is complicated and takes a long time.
Disclosure of Invention
Based on this, it is necessary to provide a converter valve-based data processing method, apparatus and computer device capable of quickly determining an influence weight of each influence factor on the temperature of the converter valve.
In a first aspect, the present application provides a converter valve based data processing method. The method comprises the following steps:
determining the initial weight of the data set to be predicted relative to the actual temperature data of the converter valve according to abnormal data in the data set to be predicted; the data set to be predicted is a set of data generated by equipment which is mutually associated with the converter valve in the operation process;
determining predicted converter valve temperature data according to the initial weight and a data set to be predicted;
determining a deviation value between the actual converter valve temperature data and the predicted converter valve temperature data, and adjusting the initial weight according to the deviation value to obtain a target weight; the target weight is used to predict whether a temperature anomaly exists for the converter valve.
In one embodiment, adjusting the initial weight according to the deviation value to obtain the target weight includes:
determining relevant categories of a data set to be predicted and actual converter valve temperature data;
and adjusting the initial weight according to the relevant category and the deviation value based on the prediction model to obtain the target weight.
In one embodiment, according to the distance between data to be predicted in a data set to be predicted, determining a normal interval range corresponding to the data set to be predicted and a neighborhood circle radius value corresponding to the data set to be predicted;
performing first screening on a data set to be predicted based on the normal interval range to obtain first abnormal data in the abnormal data;
and performing second screening on the data set to be predicted based on the neighborhood circle radius value to obtain second abnormal data in the abnormal data.
In one embodiment, performing a second screening on the data set to be predicted based on the neighborhood circle radius value to obtain second abnormal data in the abnormal data includes:
taking each data to be predicted in the data set to be predicted as the center of a neighborhood circle, and determining a neighborhood circle corresponding to each data to be predicted according to the center of the neighborhood circle and the radius value of the neighborhood circle;
and determining whether each piece of data to be predicted is second abnormal data or not based on the data quantity of the data to be predicted contained in the neighborhood circle corresponding to each piece of data to be predicted.
In one embodiment, determining the initial weight of the data set to be predicted relative to the actual converter valve temperature data according to abnormal data in the data set to be predicted comprises the following steps:
determining the discrete degree and the expected value corresponding to the abnormal data and the discrete degree and the expected value corresponding to the actual converter valve temperature data;
and determining an initial weight of the data set to be predicted corresponding to the actual converter valve temperature data based on the discrete degree and the expected value corresponding to the abnormal data and the discrete degree and the expected value corresponding to the actual converter valve temperature data.
In one embodiment, determining a deviation value between actual converter valve temperature data and predicted converter valve temperature data comprises:
obtaining an initial value of deviation;
and carrying out iterative updating on the initial value of the deviation according to the abnormal data and the initial weight based on the preset iteration times to obtain an iteratively updated deviation value.
In a second aspect, the application further provides a data processing device based on the converter valve. The device includes:
the first determining module is used for determining the initial weight of the data set to be predicted relative to the actual converter valve temperature data according to abnormal data in the data set to be predicted; the data set to be predicted is a set of data generated by equipment which is mutually associated with the converter valve in the operation process;
the second determination module is used for determining predicted converter valve temperature data according to the initial weight and the data set to be predicted;
the third determining module is used for determining a deviation value between the actual converter valve temperature data and the predicted converter valve temperature data, and adjusting the initial weight according to the deviation value to obtain a target weight; the target weight is used to predict whether a temperature anomaly exists for the converter valve.
In one embodiment, the third determining module further includes:
the first determination unit is used for determining the related categories of the data set to be predicted and the actual converter valve temperature data;
and the adjusting unit is used for adjusting the initial weight according to the relevant category and the deviation value based on the prediction model to obtain the target weight.
In a third aspect, the present application also provides a computer device. The computer arrangement comprises a memory in which a computer program is stored and a processor which, when executing the computer program, implements the converter valve based data processing method according to any of the embodiments of the first aspect as described above.
In a fourth aspect, the present application further provides a computer-readable storage medium. A computer-readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, carries out the method for converter valve based data processing according to any of the embodiments of the first aspect as described above.
According to the technical scheme, the initial weight is obtained by obtaining the abnormal data in the data set to be predicted, the target weight can be obtained by adjusting the initial weight subsequently, a data basis is provided for determining the target weight, and the accuracy of obtaining the target weight is ensured; by determining the predicted converter valve temperature, the follow-up deviation value can be determined according to the actual converter valve temperature data, and the follow-up adjustment operation on the initial weight is smoothly carried out; the initial weight is adjusted through the deviation value, the accuracy of the target weight is guaranteed, the target weight is more fit with the actual situation, the operation difficulty required by determining the target weight is reduced, and the process of determining the target weight is simplified.
Drawings
Fig. 1 is an application environment diagram of a converter valve-based data processing method according to an embodiment of the present application;
fig. 2 is a flowchart of a data processing method based on a converter valve according to an embodiment of the present application;
FIG. 3 is a flowchart of a step of determining target weights according to an embodiment of the present application;
FIG. 4 is a flowchart of a step of determining abnormal data according to an embodiment of the present application;
FIG. 5 is a flowchart of a step of determining initial weights according to an embodiment of the present application;
FIG. 6 is a flowchart illustrating a step of determining a deviation value according to an embodiment of the present application;
FIG. 7 is a flow chart of another converter valve based data processing method according to an embodiment of the present application;
fig. 8 is a block diagram of a first converter valve-based data processing apparatus according to an embodiment of the present disclosure;
fig. 9 is a block diagram of a second converter valve-based data processing apparatus according to an embodiment of the present application;
fig. 10 is a block diagram of a third converter valve-based data processing apparatus according to an embodiment of the present application;
fig. 11 is a block diagram illustrating a fourth converter valve-based data processing apparatus according to an embodiment of the present disclosure;
fig. 12 is a block diagram of a fifth converter valve-based data processing apparatus according to an embodiment of the present application;
fig. 13 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad application.
It should be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad application. In the description of the present application, reference to the description of the terms "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
The converter valve consists of a thyristor, a damping capacitor, a voltage-sharing capacitor, a damping resistor, a voltage-sharing resistor, a saturable reactor, a thyristor control unit and other parts. In addition, the converter valve has a complex internal structure, so a large amount of heat can be generated in the operation process, and in order to ensure that the converter valve can operate stably for a long time, timely and effective cooling operation needs to be ensured on the converter valve, and the main heat dissipation method comprises water circulation cooling and environmental cooling.
Because the factors influencing the temperature of the converter valve are more, in order to ensure that the temperature of the converter valve can be effectively obtained, whether the temperature of the converter valve is abnormal or not can be determined by determining the weights corresponding to the factors influencing the temperature of the converter valve respectively and further according to the weights corresponding to the influencing factors and the data corresponding to the influencing factors; however, in the prior art, factors influencing the temperature of the converter valve need to be manually checked step by step, and then the influence weight of each influencing factor on the temperature of the converter valve is determined.
However, in the prior art, the operation of determining the influence weight of each influence factor on the temperature of the converter valve is complicated, and a long time is consumed.
The data processing method based on the converter valve provided by the embodiment of the application can be applied to the application environment shown in fig. 1. In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 1. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operating system and the computer program to run on the non-volatile storage medium. The database of the computer device is used for storing acquired data of the converter valve based data processing. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of converter valve based data processing.
The application discloses a data processing method and device based on a converter valve and computer equipment. Determining the initial weight of the data set to be predicted by a computer of a worker according to abnormal data in the data set to be predicted; determining predicted converter valve temperature data according to the initial weight and a data set to be predicted; and adjusting the initial weight according to the predicted converter valve temperature data and the actual converter valve temperature data to obtain the target weight.
In an embodiment, as shown in fig. 2, fig. 2 is a flowchart of a converter valve-based data processing method provided by an embodiment of the present application, and provides a converter valve-based data processing method, and the converter valve-based data processing method executed by the computer device in fig. 1 may include the following steps:
The data set to be predicted is a set of data generated by equipment which is correlated with the converter valve in the operation process.
It should be noted that, the data in the data set to be predicted may be screened according to a preset screening condition, so as to determine abnormal data in the data set to be predicted; the preset screening conditions may include, but are not limited to: the normal data belongs to a safety value range corresponding to a preset data set to be predicted, the normal data is not larger than a preset abnormal data threshold value, and the data difference between the normal data and other data is smaller than a preset data difference threshold value. In summary, there are many methods for determining abnormal data in the data set to be predicted, and the following three methods for determining abnormal data in the data set to be predicted will be described in detail:
as an implementation manner, when abnormal data in a data set to be predicted needs to be determined, a safety value range corresponding to the data set to be predicted is determined in advance, whether each data in the data set to be predicted belongs to the safety value range or not is judged according to the safety value range corresponding to the data set to be predicted, and if the data belongs to the safety value range corresponding to the data set to be predicted, the data is normal data; and if the data does not belong to the safety value range corresponding to the data set to be predicted, the data is abnormal data.
As an implementation manner, when abnormal data in a data set to be predicted needs to be determined, an abnormal data threshold value is predetermined; judging the size relation between each data in the data set to be predicted and the abnormal data threshold according to the abnormal data threshold, wherein if the data is greater than the abnormal data threshold, the data is abnormal data; and if the data is less than or equal to the abnormal data threshold value, the data is normal data.
As an implementation manner, when abnormal data in a data set to be predicted needs to be determined, a data difference threshold value is predetermined, a data difference of each data in the data set to be predicted relative to other data is determined, whether a certain data difference is greater than or equal to the data difference threshold value exists in the data difference corresponding to the data is judged, and if the certain data difference exists in the data, the data is the abnormal data; if the data does not have a data difference larger than or equal to the data difference threshold value, the data is the normal data.
It should be noted that the initial weight is used to represent the influence degree of the abnormal data in the data set to be predicted on the temperature of the converter valve. Therefore, when the initial weight corresponding to the data set to be predicted needs to be determined, the target similarity can be determined by determining the data distribution curve corresponding to the data set to be predicted, acquiring the data distribution curve corresponding to the actual converter valve temperature data, and calculating the similarity between the data distribution curve corresponding to the data set to be predicted and the data distribution curve corresponding to the actual converter valve temperature data; the initial weight can be determined according to the target similarity.
In one embodiment of the present application, when the initial weight is determined by the target similarity; the target similarity can be assigned according to the historical experience and the actual situation of workers, so that the initial weight is determined; for example, if the similarity between the data set to be predicted and the actual converter valve temperature data is known to be higher according to the target similarity, the initial weight corresponding to the data set to be predicted is higher; if the similarity between the data set to be predicted and the actual converter valve temperature data is low according to the target similarity, the initial weight corresponding to the data set to be predicted is low.
And step 202, determining predicted converter valve temperature data according to the initial weight and the data set to be predicted.
It should be noted that, the initial weight is used for reflecting the influence degree of the abnormal data in the data set to be predicted on the temperature of the converter valve, and thus, the initial weight is determined by the actual temperature data of the converter valve and the data in the data set to be predicted; therefore, the predicted converter valve temperature data corresponding to the initial weight can be derived through the initial weight and the data in the data set to be predicted; further, the accuracy of the initial weight may be determined by predicting a difference between the converter valve temperature data and the actual converter valve temperature data.
In one embodiment of the application, when the predicted converter valve temperature data needs to be determined, the corresponding relation between the abnormal data and the actual converter valve temperature data can be determined by acquiring the abnormal data in the data set to be predicted and according to the initial weight; and determining and predicting the temperature data of the converter valve based on the corresponding relation and the abnormal data.
And 203, determining a deviation value between the actual converter valve temperature data and the predicted converter valve temperature data, and adjusting the initial weight according to the deviation value to obtain a target weight.
The target weight is used for predicting whether the converter valve has temperature abnormity or not.
It should be noted that, when the initial weight needs to be adjusted, the difference between the initial weight and the target weight can be determined according to the deviation value; adjusting the initial weight according to the difference to obtain a target weight; further, if the deviation value is larger, it indicates that the difference between the initial weight and the target weight is larger, and the initial weight needs to be adjusted greatly; if the deviation value is smaller, it means that the difference between the initial weight and the target weight is smaller, and it is necessary to make a smaller adjustment to the initial weight.
Further, the offset values may include positive offset values and negative offset values; the positive deviation value represents that the data set to be predicted and the actual converter valve temperature data are in positive correlation; a negative offset value indicates a negative correlation between the data set to be predicted and the actual converter valve temperature data. The positive correlation relationship means that the larger the abnormal data of the data set to be predicted is, the higher the actual temperature data of the converter valve is; the smaller the abnormal data of the data set to be predicted is, the lower the actual temperature data of the converter valve is; the negative correlation relation means that the larger the abnormal data of the data set to be predicted is, the lower the actual converter valve temperature data is; the smaller the abnormal data of the data set to be predicted is, the higher the actual converter valve temperature data is.
According to the data processing method based on the converter valve, the initial weight is obtained by obtaining the abnormal data in the data set to be predicted, the target weight can be obtained by adjusting the initial weight subsequently, a data base is provided for determining the target weight, and the accuracy of obtaining the target weight is ensured; by determining the predicted converter valve temperature, the follow-up deviation value can be determined according to the actual converter valve temperature data, and the follow-up adjustment operation on the initial weight is smoothly carried out; the initial weight is adjusted through the deviation value, so that the accuracy of the target weight is guaranteed, the target weight is more fit with the actual situation, the operation difficulty required for determining the target weight is reduced, and the process of determining the target weight is simplified.
It should be noted that the initial weight may be adjusted according to the relevant categories of the data set to be predicted and the actual converter valve temperature data, so as to obtain the target weight. Optionally, as shown in fig. 3, fig. 3 is a flowchart of a step of determining a target weight according to an embodiment of the present application; specifically, determining the target weight may include the following steps:
in step 301, the relevant categories of the data set to be predicted and the actual converter valve temperature data are determined.
The relevant categories may include: positive correlation, negative correlation and uncorrelated; further, if the correlation type is positive correlation, the larger the abnormal data of the data set to be predicted is, the higher the actual converter valve temperature data is; the smaller the abnormal data of the data set to be predicted is, the lower the actual converter valve temperature data is; if the correlation type is negative correlation, the larger the abnormal data of the data set to be predicted is, the lower the actual converter valve temperature data is; the smaller the abnormal data of the data set to be predicted is, the higher the actual converter valve temperature data is; and if the relevant category is irrelevant, indicating that no corresponding relation exists between the data set to be predicted and the actual converter valve temperature data.
It should be noted that the relevant categories of the data set to be predicted and the actual converter valve temperature data can be determined according to the data distribution curve of the data set to be predicted and the data distribution curve of the actual converter valve temperature data; specifically, the method comprises the following steps: if the data distribution curve of the data set to be predicted is in an ascending trend, the data distribution curve of the actual converter valve temperature data is also in an ascending trend; if the data distribution curve of the data set to be predicted is in a descending trend, the data distribution curve of the actual converter valve temperature data is in a descending trend, and the correlation category of the data set to be predicted and the actual converter valve temperature data is in positive correlation; if the data distribution curve of the data set to be predicted is in an ascending trend, the data distribution curve of the actual converter valve temperature data is in a descending trend; if the data distribution curve of the data set to be predicted is in a descending trend and the data distribution curve of the actual converter valve temperature data is in an ascending trend, the correlation type of the data set to be predicted and the actual converter valve temperature data is negative correlation; if the data distribution curve of the data set to be predicted is in an ascending trend, the data distribution curve of the actual converter valve temperature data is in a stable trend; and/or if the data distribution curve of the data set to be predicted is in a descending trend, the data distribution curve of the actual converter valve temperature data is in a stable trend, and the relevant categories of the data set to be predicted and the actual converter valve temperature data are irrelevant.
And 302, adjusting the initial weight according to the relevant category and the deviation value based on the prediction model to obtain the target weight.
It should be noted that, the result of the mean square error calculation formula (1) is minimized by inputting the correlation type, the initial weight and the deviation value into the prediction model, and continuously adjusting the initial weight and the deviation according to the mean square error calculation formula (1); further, when the mean square error value is the minimum, the fact that the deviation between the predicted converter valve temperature data and the actual converter valve temperature data is small can be determined; and the corresponding weight is the target weight when the mean square error value is minimum.
The mean square error is calculated as follows:
wherein w refers to an initial weight; x is an X-axis value corresponding to input data; b is a deviation value between actual converter valve temperature data and predicted converter valve temperature data; n is the total amount of input data; and Y is a Y-axis value corresponding to the input data.
Further, a plurality of sample data of converter valve temperature abnormity are input into the prediction model for training, so that the prediction model can determine the reason of the converter valve temperature abnormity according to the abnormal temperature of the converter valve; the converter valve temperature abnormality sample data at least comprises but is not limited to: converter valve temperature, converter valve temperature anomaly reasons, converter valve temperature change curves and the like.
According to the converter valve-based data processing method, the determined related categories ensure that an adjustment direction is provided for the subsequent adjustment of the initial weight, the accuracy of determining the target weight is ensured, and the target weight can accurately reflect the relation between the data set to be predicted and the actual temperature data of the converter valve; through the prediction model, the target weight is rapidly determined, the efficiency of determining the target weight is improved, and the accuracy of determining the target weight is further ensured.
It should be noted that the abnormal data may be determined by performing a first screening and a second screening on the data set to be predicted. Optionally, as shown in fig. 4, fig. 4 is a flowchart of a step of determining abnormal data according to an embodiment of the present application; specifically, determining the abnormal data may include the following steps:
It should be noted that the determination of the normal interval range may be performed according to the data distribution condition corresponding to the data set to be predicted, and further, an area in which the data distribution in the data set to be predicted is concentrated may be determined as the normal interval range; and relatively, determining the area with dispersed data distribution in the data set to be predicted as the abnormal interval range.
In an embodiment of the present application, a to-be-predicted data set may be calculated by a knn (K Nearest Neighbors, K Nearest Neighbors algorithm) algorithm, and an upper data limit and a lower data limit corresponding to the to-be-predicted data set are determined; the region between the upper data limit and the lower data limit is the normal interval range.
It should be noted that the neighborhood circle radius value corresponding to the data set to be predicted can be determined according to the data distribution condition of the data set to be predicted; if the data distribution of the data set to be predicted is scattered, the radius value of the neighborhood circle can be relatively large; if the data distribution of the data set to be predicted is concentrated, the radius value of the neighborhood circle can be relatively small; further, the selection of the neighborhood circle radius value corresponding to the data set to be predicted can be judged according to the historical experience of the staff, and the selection of the neighborhood circle radius value is not limited.
In an embodiment of the application, when the data set to be predicted needs to be subjected to the first screening, whether each piece of data in the data set to be predicted is located in a normal interval range can be judged, and if the piece of data is located in the normal interval range, the piece of data is normal data; if the data is not in the range of the normal interval, the data is the first abnormal data in the abnormal data.
And 403, performing second screening on the data set to be predicted based on the radius value of the neighborhood circle to obtain second abnormal data in the abnormal data.
When the data set to be predicted is subjected to the second screening, each data set to be predicted in the data set to be predicted is used as the center of a neighborhood circle, and a neighborhood circle corresponding to each data set to be predicted is determined according to the center of the neighborhood circle and the radius value of the neighborhood circle; and determining whether each data to be predicted is second abnormal data or not based on the data quantity of the data to be predicted contained in the neighborhood circle corresponding to each data to be predicted.
In one embodiment of the application, a quantity threshold of data to be predicted contained in a neighborhood circle can be preset, and if the data quantity of the data to be predicted contained in the neighborhood circle is larger than or equal to the quantity threshold, the data to be predicted as the circle center of the neighborhood circle is represented as abnormal data; if the data volume of the data to be predicted contained in the neighborhood circle is smaller than the quantity threshold, the data to be predicted as the circle center of the neighborhood circle is normal data. For example, if the preset number threshold is 6, assuming that each to-be-predicted data in the to-be-predicted data set is used as the center of a neighborhood circle, determining a neighborhood circle corresponding to each to-be-predicted data according to the center of the neighborhood circle and the radius value of the neighborhood circle; the data volume of the data to be predicted contained in the three neighborhood circles is 10, 5 and 3; according to the quantity threshold value, the circle center of the field circle containing 10 data to be predicted is known as abnormal data.
According to the data processing method based on the converter valve, the determination of the subsequent initial weight is ensured by determining the abnormal data corresponding to the data set to be predicted, the data basis provided for the determined initial weight ensures that the initial weight is more fit with the actual condition of the data set to be predicted, and the accuracy of determining the abnormal data is ensured through the first screening and the second screening.
It should be noted that the initial weight may be determined by the degree of dispersion and the expected value corresponding to the abnormal data. Optionally, as shown in fig. 5, fig. 5 is a flowchart of a step of determining an initial weight according to an embodiment of the present application; specifically, determining the initial weight may include the following steps:
and step 501, determining the discrete degree and the expected value corresponding to the abnormal data and the discrete degree and the expected value corresponding to the actual converter valve temperature data.
It should be noted that, when the discrete degree corresponding to the abnormal data and the discrete degree corresponding to the actual converter valve temperature data need to be determined; the variance, the range, the standard deviation, the mean deviation and the like of the abnormal data and the actual converter valve temperature data can be determined, so that the discrete degree corresponding to the abnormal data and the discrete degree corresponding to the actual converter valve temperature data can be determined.
When the expected value corresponding to the abnormal data and the expected value corresponding to the actual converter valve temperature data need to be determined, the expected value corresponding to the abnormal data and the expected value corresponding to the actual converter valve temperature data can be determined by substituting the abnormal data and the actual converter valve temperature data into a standard deviation calculation formula.
And 502, determining an initial weight of the data set to be predicted corresponding to the actual converter valve temperature data based on the discrete degree and the expected value corresponding to the abnormal data and the discrete degree and the expected value corresponding to the actual converter valve temperature data.
It should be noted that the similarity between the abnormal data in the data set to be predicted and the actual converter valve temperature data can be determined, so that the initial weight can be determined according to the similarity; further, the covariance corresponding to the abnormal data and the actual converter valve temperature data can be determined according to the expected value corresponding to the abnormal data, the expected value corresponding to the actual converter valve temperature data, the abnormal data and the actual converter valve temperature data; and determining a standard deviation corresponding to the abnormal data and the actual converter valve temperature data according to the discrete degree corresponding to the abnormal data, the discrete degree corresponding to the actual converter valve temperature data, the abnormal data and the actual converter valve temperature data.
The standard deviation corresponding to the abnormal data and the actual converter valve temperature data and the covariance corresponding to the abnormal data and the actual converter valve temperature data can be substituted into a Pearson correlation calculation formula (2); and determining the similarity between the abnormal data in the data set to be predicted and the actual temperature data of the converter valve.
Wherein, the pilson correlation calculation formula (2) is shown as the following formula:
wherein rho X and Y refer to the similarity corresponding to the input abnormal data and the actual converter valve temperature data; cov (X, Y) refers to the covariance of the input anomaly data corresponding to the actual converter valve temperature data; the sigma X sigma Y refers to a standard deviation of input abnormal data corresponding to actual converter valve temperature data; x and Y respectively refer to abnormal data and actual converter valve temperature data; μ X refers to the mean corresponding to the abnormal data; μ Y refers to the corresponding mean of the actual converter valve temperature data.
According to the data processing method based on the converter valve, the discrete degree and the expected value corresponding to the abnormal data and the discrete degree and the expected value corresponding to the actual temperature data of the converter valve are determined; the initial weight is obtained, and the initial weight is ensured to be more fit with the actual situation of the data set to be predicted; the accuracy of the subsequent target weight determination based on the initial weight is improved.
Note that, the updated offset value can be obtained from the offset initial value. Alternatively, as shown in fig. 6, fig. 6 is a flowchart illustrating a step of determining a deviation value according to an embodiment of the present application; specifically, determining the deviation value may include the following steps:
It should be noted that the obtaining of the initial deviation value may be determined according to experience of a worker and historical data, and it may be understood that the setting of the initial deviation value needs to meet the requirement of meeting the actual situation to ensure the accuracy of the subsequent determination of the deviation value, and the method for obtaining the initial deviation value is not limited herein.
And step 602, based on the preset iteration times, performing iterative update on the initial value of the deviation according to the abnormal data and the initial weight to obtain an iteratively updated deviation value.
In an embodiment of the present application, when a deviation value needs to be obtained, a plurality of sets of data to be predicted and initial weights corresponding to the sets of data to be predicted can be obtained; substituting a certain abnormal data in the multiple groups of data sets to be predicted, and the corresponding initial weight and the corresponding initial deviation value into a deviation value calculation formula (3); the output result of the deviation value calculation formula (3) is the deviation value after being updated once; when the deviation initial values need to be subjected to iterative processing, the deviation values after being updated once can be used as new deviation initial values, and a certain abnormal data in a plurality of groups of data sets to be predicted, the corresponding initial weights of the abnormal data and the new deviation initial values are substituted into the deviation value calculation formula (3) again, so that iterative updating of the deviation values is realized.
Further, the iterative update times of the deviation value can be determined according to the historical experience and the actual requirement of the worker.
Wherein, the deviation value calculation formula (3) is as follows:
b 2 ＝g( W m1x 1+ W m2 x 2 + W m3 x 3 +b 1 )……( 3 )
in addition, b is 2 Means the offset value after one update; w is a group of m1 、W m2 And W m3 The initial weights corresponding to the first group, the second group and the third group of data sets to be predicted respectively during the mth round of updating; x is a radical of a fluorine atom 1 、x 2 And x 3 The m-th round of updating, abnormal data respectively corresponding to the first group, the second group and the third group of data sets to be predicted, b 1 The offset initial value corresponding to the current update is referred to.
According to the data processing method based on the converter valve, the deviation initial value is obtained and is subjected to iterative updating, so that the accuracy of the deviation value after updating is guaranteed, a data basis is provided for subsequent adjustment of the initial weight, and the accuracy of subsequent target weight determination is guaranteed.
In an embodiment of the present application, as shown in fig. 7, fig. 7 is a flowchart of another converter valve-based data processing method provided in the embodiment of the present application, and when processing data of a converter valve:
And 703, taking each data to be predicted in the data set to be predicted as the center of a neighborhood circle, and determining a neighborhood circle corresponding to each data to be predicted according to the center of the neighborhood circle and the radius value of the neighborhood circle.
And step 706, determining an initial weight of the data set to be predicted corresponding to the actual converter valve temperature data based on the discrete degree and the expected value corresponding to the abnormal data and the discrete degree and the expected value corresponding to the actual converter valve temperature data.
And step 707, determining the predicted converter valve temperature data according to the initial weight and the data set to be predicted.
At step 708, an initial value of the deviation is obtained.
And 709, iteratively updating the initial value of the deviation according to the abnormal data and the initial weight based on the preset iteration times to obtain an iteratively updated deviation value.
At step 710, the relevant categories of the data set to be predicted and the actual converter valve temperature data are determined.
And 711, adjusting the initial weight according to the relevant category and the deviation value based on the prediction model to obtain the target weight.
According to the data processing method based on the converter valve, the initial weight is obtained by obtaining the abnormal data in the data set to be predicted, the target weight can be obtained by adjusting the initial weight subsequently, a data basis is provided for determining the target weight, and the accuracy of obtaining the target weight is ensured; by determining the predicted converter valve temperature, the follow-up deviation value can be determined according to the actual converter valve temperature data, and the follow-up adjustment operation on the initial weight is smoothly carried out; the initial weight is adjusted through the deviation value, the accuracy of the target weight is guaranteed, the target weight is more fit with the actual situation, the operation difficulty required by determining the target weight is reduced, and the process of determining the target weight is simplified.
It should be understood that, although the steps in the flowcharts related to the embodiments are shown in sequence as indicated by the arrows, the steps are not necessarily executed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the flowcharts related to the above embodiments may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the steps or stages is not necessarily sequential, but may be performed alternately or alternately with other steps or at least a part of the steps or stages in other steps.
Based on the same inventive concept, the embodiment of the present application further provides a converter valve-based data processing apparatus for implementing the converter valve-based data processing method mentioned above. The implementation scheme for solving the problem provided by the apparatus is similar to the implementation scheme described in the method, so specific limitations in one or more embodiments of the converter valve-based data processing apparatus provided below may refer to the limitations on the converter valve-based data processing method in the foregoing, and details are not described here again.
In an embodiment, as shown in fig. 8, fig. 8 is a block diagram of a first converter valve-based data processing apparatus according to an embodiment of the present application, and provides a converter valve-based data processing apparatus including: a first determination module 10, a second determination module 20, and a third determination module 30, wherein:
the first determining module 10 is configured to determine an initial weight of the data set to be predicted relative to actual converter valve temperature data according to abnormal data in the data set to be predicted; the data set to be predicted is a set of data generated during operation by a device associated with the converter valve.
And the second determination module 20 is used for determining the predicted converter valve temperature data according to the initial weight and the data set to be predicted.
The third determining module 30 is configured to determine a deviation value between the actual converter valve temperature data and the predicted converter valve temperature data, and adjust the initial weight according to the deviation value to obtain a target weight; the target weight is used for predicting whether the converter valve has temperature abnormity.
According to the data processing device based on the converter valve, the initial weight is obtained by obtaining the abnormal data in the data set to be predicted, the target weight can be obtained by adjusting the initial weight subsequently, a data base is provided for determining the target weight, and the accuracy of obtaining the target weight is ensured; by determining the predicted converter valve temperature, the follow-up deviation value can be determined according to the actual converter valve temperature data, and the follow-up adjustment operation on the initial weight is smoothly carried out; the initial weight is adjusted through the deviation value, the accuracy of the target weight is guaranteed, the target weight is more fit with the actual situation, the operation difficulty required by determining the target weight is reduced, and the process of determining the target weight is simplified.
In an embodiment, as shown in fig. 9, fig. 9 is a block diagram of a second converter valve-based data processing apparatus provided in an embodiment of the present application, and provides a converter valve-based data processing apparatus, where the third determining module 30 in the converter valve-based data processing apparatus includes: a first determining unit 31 and an adjusting unit 32, wherein:
a first determination unit 31 for determining a category of correlation of the data set to be predicted and the actual converter valve temperature data.
And the adjusting unit 32 is configured to adjust the initial weight according to the relevant category and the deviation value based on the prediction model, so as to obtain the target weight.
According to the converter valve-based data processing device, the determined related categories ensure that an adjustment direction is provided for the subsequent adjustment of the initial weight, the accuracy of determining the target weight is ensured, and the target weight can accurately reflect the relation between the data set to be predicted and the actual temperature data of the converter valve; through the prediction model, the target weight is rapidly determined, the efficiency of determining the target weight is improved, and the accuracy of determining the target weight is further ensured.
In an embodiment, as shown in fig. 10, fig. 10 is a block diagram of a third converter valve-based data processing apparatus provided in an embodiment of the present application, and provides a converter valve-based data processing apparatus, where the converter valve-based data processing apparatus further includes: a fourth determination module 40, a fifth determination module 50, and a sixth determination module 60, wherein:
and a fourth determining module 40, configured to determine, according to a distance between data to be predicted in the data set to be predicted, a normal interval range corresponding to the data set to be predicted, and a neighborhood circle radius value corresponding to the data set to be predicted.
The fifth determining module 50 is configured to perform first screening on the data set to be predicted based on the normal interval range, so as to obtain first abnormal data in the abnormal data.
And a sixth determining module 60, configured to perform a second screening on the data set to be predicted based on the neighborhood circle radius value, to obtain second abnormal data in the abnormal data.
It should be noted that, each data to be predicted in the data set to be predicted is taken as the center of a neighborhood circle, and a neighborhood circle corresponding to each data to be predicted is determined according to the center of the neighborhood circle and the radius value of the neighborhood circle; and determining whether each data to be predicted is second abnormal data or not based on the data quantity of the data to be predicted contained in the neighborhood circle corresponding to each data to be predicted.
According to the data processing device based on the converter valve, the determination of the subsequent initial weight is guaranteed by determining the abnormal data corresponding to the data set to be predicted, the data basis provided for the determined initial weight guarantees that the initial weight is more fit with the actual situation of the data set to be predicted, and the accuracy of determining the abnormal data is guaranteed through the first screening and the second screening.
In an embodiment, as shown in fig. 11, fig. 11 is a block diagram of a fourth converter valve-based data processing apparatus provided in an embodiment of the present application, and provides a converter valve-based data processing apparatus, where a first determining module 10 in the converter valve-based data processing apparatus includes: a second determining unit 11 and a third determining unit 12, wherein:
and the second determining unit 11 is used for determining the discrete degree and the expected value corresponding to the abnormal data and the discrete degree and the expected value corresponding to the actual converter valve temperature data.
And the third determining unit 12 is used for determining an initial weight of the data set to be predicted corresponding to the actual converter valve temperature data based on the discrete degree and the expected value corresponding to the abnormal data and the discrete degree and the expected value corresponding to the actual converter valve temperature data.
According to the data processing device based on the converter valve, the discrete degree and the expected value corresponding to the abnormal data and the discrete degree and the expected value corresponding to the actual temperature data of the converter valve are determined; the initial weight is obtained, and the initial weight is ensured to be more fit with the actual condition of the data set to be predicted; the accuracy of the subsequent target weight determination based on the initial weight is improved.
In an embodiment, as shown in fig. 12, fig. 12 is a block diagram of a fifth converter valve-based data processing apparatus provided in an embodiment of the present application, and provides a converter valve-based data processing apparatus, where the third determining module 30 in the converter valve-based data processing apparatus includes: an acquisition unit 33 and an update unit 34, wherein:
an obtaining unit 33 is used for obtaining the initial value of the deviation.
And the updating unit 34 is configured to perform iterative updating on the initial deviation value according to the abnormal data and the initial weight based on a preset iteration number, so as to obtain an iteratively updated deviation value.
According to the data processing device based on the converter valve, the deviation initial value is obtained, iterative updating is carried out on the deviation initial value, the accuracy of the deviation value after updating is guaranteed, a data basis is provided for follow-up initial weight adjustment, and the accuracy of follow-up target weight determination is guaranteed.
The various modules in the converter valve based data processing arrangement described above may be implemented in whole or in part by software, hardware and combinations thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 13. The computer apparatus includes a processor, a memory, an input/output interface, a communication interface, a display unit, and an input device. The processor, the memory and the input/output interface are connected by a system bus, and the communication interface, the display unit and the input device are connected by the input/output interface to the system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program to run on the non-volatile storage medium. The input/output interface of the computer device is used for exchanging information between the processor and an external device. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a method of converter valve based data processing. The display unit of the computer device is used for forming a visual visible picture, and can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on a shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 13 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
determining the initial weight of the data set to be predicted relative to the actual temperature data of the converter valve according to abnormal data in the data set to be predicted; the data set to be predicted is a set of data generated by equipment which is mutually associated with the converter valve in the operation process;
determining predicted converter valve temperature data according to the initial weight and a data set to be predicted;
determining a deviation value between the actual converter valve temperature data and the predicted converter valve temperature data, and adjusting the initial weight according to the deviation value to obtain a target weight; the target weight is used to predict whether a temperature anomaly exists for the converter valve.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
determining relevant categories of a data set to be predicted and actual converter valve temperature data;
and adjusting the initial weight according to the relevant category and the deviation value based on the prediction model to obtain the target weight.
In one embodiment, the processor when executing the computer program further performs the steps of:
determining a normal interval range corresponding to a data set to be predicted and a neighborhood circle radius value corresponding to the data set to be predicted according to the distance between data to be predicted in the data set to be predicted;
performing first screening on a data set to be predicted based on the normal interval range to obtain first abnormal data in the abnormal data;
and performing second screening on the data set to be predicted based on the neighborhood circle radius value to obtain second abnormal data in the abnormal data.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
taking each data to be predicted in the data set to be predicted as the center of a neighborhood circle, and determining a neighborhood circle corresponding to each data to be predicted according to the center of the neighborhood circle and the radius value of the neighborhood circle;
and determining whether each piece of data to be predicted is second abnormal data or not based on the data quantity of the data to be predicted contained in the neighborhood circle corresponding to each piece of data to be predicted.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
determining the discrete degree and the expected value corresponding to the abnormal data and the discrete degree and the expected value corresponding to the actual converter valve temperature data;
and determining an initial weight of the data set to be predicted corresponding to the actual converter valve temperature data based on the discrete degree and the expected value corresponding to the abnormal data and the discrete degree and the expected value corresponding to the actual converter valve temperature data.
In one embodiment, the processor when executing the computer program further performs the steps of:
obtaining an initial value of deviation;
and carrying out iterative updating on the initial value of the deviation according to the abnormal data and the initial weight based on the preset iteration times to obtain an iteratively updated deviation value.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
determining the initial weight of the data set to be predicted relative to the actual temperature data of the converter valve according to abnormal data in the data set to be predicted; the data set to be predicted is a set of data generated by equipment which is mutually associated with the converter valve in the operation process;
determining predicted converter valve temperature data according to the initial weight and a data set to be predicted;
determining a deviation value between the actual converter valve temperature data and the predicted converter valve temperature data, and adjusting the initial weight according to the deviation value to obtain a target weight; the target weight is used to predict whether a temperature anomaly exists for the converter valve.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining relevant categories of a data set to be predicted and actual converter valve temperature data;
and adjusting the initial weight according to the relevant category and the deviation value based on the prediction model to obtain the target weight.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining a normal interval range corresponding to a data set to be predicted and a neighborhood circle radius value corresponding to the data set to be predicted according to the distance between data to be predicted in the data set to be predicted;
performing first screening on a data set to be predicted based on the normal interval range to obtain first abnormal data in the abnormal data;
and performing second screening on the data set to be predicted based on the neighborhood circle radius value to obtain second abnormal data in the abnormal data.
In one embodiment, the computer program when executed by the processor further performs the steps of:
taking each data to be predicted in the data set to be predicted as the center of a neighborhood circle, and determining a neighborhood circle corresponding to each data to be predicted according to the center of the neighborhood circle and the radius value of the neighborhood circle;
and determining whether each piece of data to be predicted is second abnormal data or not based on the data quantity of the data to be predicted contained in the neighborhood circle corresponding to each piece of data to be predicted.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining the discrete degree and the expected value corresponding to the abnormal data and the discrete degree and the expected value corresponding to the actual converter valve temperature data;
and determining an initial weight of the data set to be predicted corresponding to the actual converter valve temperature data based on the discrete degree and the expected value corresponding to the abnormal data and the discrete degree and the expected value corresponding to the actual converter valve temperature data.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring an initial value of the deviation;
and performing iterative updating on the initial value of the deviation according to the abnormal data and the initial weight based on the preset iterative times to obtain an iteratively updated deviation value.
It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) referred to in the present application are information and data authorized by the user or fully authorized by each party, and the collection, use and processing of the related data need to comply with the relevant laws and regulations and standards of the relevant countries and regions.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include a Read-Only Memory (ROM), a magnetic tape, a floppy disk, a flash Memory, an optical Memory, a high-density embedded nonvolatile Memory, a resistive Random Access Memory (ReRAM), a Magnetic Random Access Memory (MRAM), a Ferroelectric Random Access Memory (FRAM), a Phase Change Memory (PCM), a graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), for example. The databases referred to in various embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the various embodiments provided herein may be, without limitation, general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, or the like.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.
Claims (10)
1. A method of converter valve based data processing, the method comprising:
determining the initial weight of the data set to be predicted relative to the actual temperature data of the converter valve according to abnormal data in the data set to be predicted; the data set to be predicted is a set of data generated by equipment which is mutually associated with the converter valve in the operation process;
determining predicted converter valve temperature data according to the initial weight and the data set to be predicted;
determining a deviation value between the actual converter valve temperature data and the predicted converter valve temperature data, and adjusting the initial weight according to the deviation value to obtain a target weight; the target weight is used for predicting whether the converter valve has temperature abnormity.
2. The method of claim 1, wherein said adjusting the initial weight to obtain a target weight according to the deviation value comprises:
determining a relevant category of the data set to be predicted and the actual converter valve temperature data;
and adjusting the initial weight according to the relevant category and the deviation value on the basis of a prediction model to obtain the target weight.
3. The method of claim 1, further comprising:
determining a normal interval range corresponding to the data set to be predicted and a neighborhood circle radius value corresponding to the data set to be predicted according to the distance between the data to be predicted in the data set to be predicted;
performing first screening on the data set to be predicted based on the normal interval range to obtain first abnormal data in the abnormal data;
and performing second screening on the data set to be predicted based on the neighborhood circle radius value to obtain second abnormal data in the abnormal data.
4. The method according to claim 3, wherein the second screening of the data set to be predicted based on the neighborhood circle radius value to obtain second abnormal data in the abnormal data comprises:
taking each data to be predicted in the data set to be predicted as the center of a neighborhood circle, and determining a neighborhood circle corresponding to each data to be predicted according to the center of the neighborhood circle and the radius value of the neighborhood circle;
and determining whether each piece of data to be predicted is second abnormal data or not based on the data volume of the data to be predicted contained in the neighborhood circle corresponding to each piece of data to be predicted.
5. The method of claim 1, wherein determining an initial weight of the data set to be predicted relative to actual converter valve temperature data based on abnormal data in the data set to be predicted comprises:
determining the discrete degree and the expected value corresponding to the abnormal data and the discrete degree and the expected value corresponding to the actual converter valve temperature data;
and determining the initial weight of the data set to be predicted corresponding to the actual converter valve temperature data based on the discrete degree and the expected value corresponding to the abnormal data and the discrete degree and the expected value corresponding to the actual converter valve temperature data.
6. The method of claim 1, wherein determining a deviation value between the actual converter valve temperature data and the predicted converter valve temperature data comprises:
acquiring an initial value of the deviation;
and carrying out iterative updating on the initial value of the deviation according to the abnormal data and the initial weight based on the preset iteration times to obtain the value of the deviation after iterative updating.
7. A converter valve based data processing apparatus, characterized in that the apparatus comprises:
the device comprises a first determining module, a second determining module and a third determining module, wherein the first determining module is used for determining the initial weight of a data set to be predicted relative to the actual converter valve temperature data according to abnormal data in the data set to be predicted; the data set to be predicted is a set of data generated by equipment which is mutually associated with the converter valve in the operation process;
the second determination module is used for determining predicted converter valve temperature data according to the initial weight and the data set to be predicted;
the third determining module is used for determining a deviation value between the actual converter valve temperature data and the predicted converter valve temperature data, and adjusting the initial weight according to the deviation value to obtain a target weight; the target weight is used for predicting whether the converter valve has temperature abnormity.
8. The apparatus of claim 7, wherein the third determining module further comprises:
a first determination unit for determining a correlation category of the data set to be predicted and the actual converter valve temperature data;
and the adjusting unit is used for adjusting the initial weight according to the relevant category and the deviation value on the basis of a prediction model to obtain the target weight.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 6.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211432477.8A CN115718901A (en) | 2022-11-15 | 2022-11-15 | Data processing method and device based on converter valve and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211432477.8A CN115718901A (en) | 2022-11-15 | 2022-11-15 | Data processing method and device based on converter valve and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115718901A true CN115718901A (en) | 2023-02-28 |
Family
ID=85255237
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211432477.8A Pending CN115718901A (en) | 2022-11-15 | 2022-11-15 | Data processing method and device based on converter valve and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115718901A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106548270A (en) * | 2016-09-30 | 2017-03-29 | 许昌许继软件技术有限公司 | A kind of photovoltaic plant power anomalous data identification method and device |
| CN108172301A (en) * | 2018-01-31 | 2018-06-15 | 中国科学院软件研究所 | A kind of mosquito matchmaker's epidemic Forecasting Methodology and system based on gradient boosted tree |
| CN109753991A (en) * | 2018-12-06 | 2019-05-14 | 中科恒运股份有限公司 | Abnormal deviation data examination method and device |
| CN110766200A (en) * | 2019-09-23 | 2020-02-07 | 广东工业大学 | Method for predicting generating power of wind turbine generator based on K-means mean clustering |
| CN111125470A (en) * | 2019-12-25 | 2020-05-08 | 成都康赛信息技术有限公司 | Method for improving abnormal data mining and screening |
| CN111460610A (en) * | 2020-02-27 | 2020-07-28 | 中国南方电网有限责任公司超高压输电公司广州局 | Converter valve TVM plate heating prediction method, system, device and medium |
| TW202142815A (en) * | 2020-04-30 | 2021-11-16 | 得意節能科技股份有限公司 | Monitoring method of cool system and monitoring device thereof |
| CN114580747A (en) * | 2022-03-04 | 2022-06-03 | 西安交通大学 | Abnormal data prediction method and system based on data correlation and fuzzy system |
| CN114841429A (en) * | 2022-04-28 | 2022-08-02 | 南京南瑞继保电气有限公司 | BP neural network-based air cooler fan input quantity prediction method |
-
2022
- 2022-11-15 CN CN202211432477.8A patent/CN115718901A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106548270A (en) * | 2016-09-30 | 2017-03-29 | 许昌许继软件技术有限公司 | A kind of photovoltaic plant power anomalous data identification method and device |
| CN108172301A (en) * | 2018-01-31 | 2018-06-15 | 中国科学院软件研究所 | A kind of mosquito matchmaker's epidemic Forecasting Methodology and system based on gradient boosted tree |
| CN109753991A (en) * | 2018-12-06 | 2019-05-14 | 中科恒运股份有限公司 | Abnormal deviation data examination method and device |
| CN110766200A (en) * | 2019-09-23 | 2020-02-07 | 广东工业大学 | Method for predicting generating power of wind turbine generator based on K-means mean clustering |
| CN111125470A (en) * | 2019-12-25 | 2020-05-08 | 成都康赛信息技术有限公司 | Method for improving abnormal data mining and screening |
| CN111460610A (en) * | 2020-02-27 | 2020-07-28 | 中国南方电网有限责任公司超高压输电公司广州局 | Converter valve TVM plate heating prediction method, system, device and medium |
| TW202142815A (en) * | 2020-04-30 | 2021-11-16 | 得意節能科技股份有限公司 | Monitoring method of cool system and monitoring device thereof |
| CN114580747A (en) * | 2022-03-04 | 2022-06-03 | 西安交通大学 | Abnormal data prediction method and system based on data correlation and fuzzy system |
| CN114841429A (en) * | 2022-04-28 | 2022-08-02 | 南京南瑞继保电气有限公司 | BP neural network-based air cooler fan input quantity prediction method |
Non-Patent Citations (2)
| Title |
|---|
| X.H. WANG: "Research on the prediction-model of the surface-temperature of large oil-immersed power transformer", 2005 INTERNATIONAL CONFERENCE ON ELECTRICAL MACHINES AND SYSTEMS, pages 2216 - 2219 * |
| 张春等: "电加热渐进成形工艺参数优化及成形温度预测", 热加工工艺, vol. 48, no. 19, pages 100 - 103 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110334735B (en) | Multitask network generation method and device, computer equipment and storage medium | |
| CN113887845B (en) | Extreme event prediction method, device, equipment and storage medium | |
| US10445341B2 (en) | Methods and systems for analyzing datasets | |
| CN112767074A (en) | Module machine model selection method and device, computer equipment and storage medium | |
| CN115689018A (en) | Material demand prediction method, device, equipment, storage medium and program product | |
| CN117454668A (en) | Method, device, equipment and medium for predicting failure probability of parts | |
| CN115718901A (en) | Data processing method and device based on converter valve and computer equipment | |
| CN111626789A (en) | House price prediction method, device, equipment and storage medium | |
| CN117037482A (en) | Real-time road traffic running state sensing method, system, equipment and storage medium | |
| CN114501518B (en) | Flow prediction method, flow prediction device, flow prediction apparatus, flow prediction medium, and program product | |
| CN115759742A (en) | Enterprise risk assessment method and device, computer equipment and storage medium | |
| CN115564152A (en) | Carbon emission prediction method and device based on STIRPAT model | |
| CN112528500B (en) | Evaluation method and evaluation equipment for scene graph construction model | |
| CN115238931A (en) | Method and device for planning worn parts, computer equipment and storage medium | |
| CN111428182B (en) | Evaluation index processing method, device, computer equipment and storage medium | |
| CN114492905A (en) | Customer appeal rate prediction method and device based on multi-model fusion and computer equipment | |
| CN111340276A (en) | Method and system for generating prediction data | |
| CN116128289A (en) | Risk prediction method and device for guest group, computer equipment and storage medium | |
| CN117829892A (en) | Three-dimensional model supply and demand analysis method, device, computer equipment and storage medium | |
| CN115660786A (en) | Service recommendation method, device, computer equipment, storage medium and program product | |
| CN115827977A (en) | Training method and device of user preference prediction model and computer equipment | |
| CN116781536A (en) | Traffic prediction method, traffic prediction device, traffic prediction apparatus, traffic prediction device, traffic prediction program product, and traffic prediction program product | |
| CN112949888A (en) | Component prediction model training and component prediction method, device and computer equipment | |
| CN117474174A (en) | Scheduling rule optimization method, scheduling rule optimization device, computer equipment, storage medium and product | |
| CN116681203A (en) | Enterprise management consultation method and system based on big data analysis |
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 |