Electrostatic precipitator abnormality detection method and device

Abstract

The present application provides a method and device for detecting abnormality of an electrostatic precipitator, the method comprising: obtaining the secondary voltage to be analyzed and the secondary current to be analyzed of the electric field in the electrostatic precipitator; obtaining the volt-ampere normal area corresponding to the most recently determined electric field, the volt-ampere normal area being a coordinate area in the volt-ampere coordinate plane that characterizes the absence of abnormality in the electric field, the volt-ampere coordinate plane being a coordinate plane that represents the secondary voltage with the horizontal coordinate and the secondary current with the vertical coordinate, the volt-ampere normal area corresponding to the electric field being determined based on the historical secondary voltage and the historical secondary current at multiple historical moments in the historical time period before the current moment; determining the positional relationship information between the target coordinate point of the secondary current to be analyzed and the secondary voltage to be analyzed on the volt-ampere coordinate plane and the volt-ampere normal area; based on the positional relationship information, determining the abnormal state of the electric field in the electrostatic precipitator. The scheme of the present application can more accurately detect the abnormality of the electrostatic precipitator.

Description

Technical Field

[0001] The present application relates to the technical field of equipment monitoring, and in particular to a method and device for detecting abnormality of an electrostatic precipitator. Background Art

[0002] Electrostatic precipitator is an essential environmental protection equipment in thermal power plants and chemical plants. The function of electrostatic precipitator is to remove dust from industrial smoke emitted by factories, thereby greatly reducing the amount of smoke discharged into the atmosphere and reducing environmental pollution.

[0003] If the electrostatic precipitator fails, it will affect the dust removal effect. In order to ensure the dust removal effect, it is necessary to accurately determine the possibility of failure of the electrostatic precipitator and discover the failure of the electrostatic precipitator in time. Summary of the invention

[0004] The present application provides a method for detecting abnormality of an electrostatic precipitator, so as to more accurately detect abnormality existing in the electrostatic precipitator.

[0005] A method for detecting abnormality of an electrostatic precipitator includes:

[0006] Obtaining a secondary voltage to be analyzed and a secondary current to be analyzed of an electric field in an electrostatic precipitator;

[0007] Obtaining the volt-ampere normal area corresponding to the electric field determined most recently, the volt-ampere normal area being a coordinate area in a volt-ampere coordinate plane that characterizes that the electric field does not have an abnormality, the volt-ampere coordinate plane being a coordinate plane in which the abscissa represents the secondary voltage and the ordinate represents the secondary current, the volt-ampere normal area corresponding to the electric field being determined based on the historical secondary voltage and the historical secondary current at multiple historical moments in a historical time period before the current moment;

[0008] Determine the positional relationship information between the target coordinate points of the secondary current to be analyzed and the secondary voltage to be analyzed on the volt-ampere coordinate plane and the volt-ampere normal area;

[0009] Based on the positional relationship information, an abnormal state of the electric field in the electrostatic precipitator is determined.

[0010] In a possible implementation, determining the abnormal state of the electric field in the electrostatic precipitator based on the position relationship information includes:

[0011] If the position relationship information indicates that the target coordinate point is located in the normal volt-ampere area, determining that there is no abnormality in the electric field;

[0012] If the positional relationship information indicates that the target coordinate point is outside the normal volt-ampere region, the risk level of abnormality in the electric field is determined based on the distance between the target coordinate point and the boundary of the normal volt-ampere region.

[0013] In another possible implementation, determining the risk level of abnormality in the electric field based on the distance between the target coordinate point and the boundary of the normal volt-ampere area includes:

[0014] Determine a risk control area corresponding to the normal volt-ampere area in the volt-ampere coordinate plane, wherein the risk control area is a coordinate area determined based on the normal volt-ampere area, indicating that the electric field may be abnormal, and the risk control area includes the normal volt-ampere area and is larger than the normal volt-ampere area;

[0015] If the target coordinate point is outside the normal volt-ampere area and within the risk control area, determining the risk level of abnormality of the electric field based on a first shortest distance between the target coordinate point and a boundary of the normal volt-ampere area and a second shortest distance between the target coordinate point and a boundary of the risk control area;

[0016] If the target coordinate point is outside the risk control area, it is determined that there is an abnormality in the electric field.

[0017] In another possible implementation, the volt-ampere normal region corresponding to the electric field is obtained by:

[0018] Obtaining historical secondary voltages and historical secondary currents of the electric field at multiple historical moments in a historical time period before a current moment;

[0019] Taking the historical secondary voltage and the historical secondary current at each historical moment as a historical coordinate point on the volt-ampere coordinate plane, based on the distribution of multiple historical coordinate points corresponding to multiple historical moments on the volt-ampere coordinate plane, determine the coordinate point distribution area whose distribution density of the historical coordinate points meets the requirements, and determine the coordinate point distribution area as the volt-ampere normal area.

[0020] In yet another possible implementation, after determining the coordinate point distribution area as a normal volt-ampere area, the method further includes:

[0021] Determine a first boundary coordinate point set and a second boundary coordinate point set in a normal volt-ampere region, wherein the first boundary coordinate point set includes a plurality of historical coordinate points for representing a first boundary line of the normal volt-ampere region, and the second boundary coordinate point set includes a plurality of historical coordinate points for representing a second boundary line of the normal volt-ampere region, wherein the first boundary line is a boundary line in the normal volt-ampere region close to a ordinate axis of the volt-ampere coordinate plane, and the second boundary line is a boundary line in the normal volt-ampere region far from the ordinate axis;

[0022] Performing data cleaning on the first boundary coordinate point set and the second boundary coordinate point set based on the Laida criterion to obtain the first boundary coordinate point set and the second boundary coordinate point set after data cleaning;

[0023] Based on the first boundary coordinate point set after data cleaning, a function expression of the first boundary line is fitted using the least squares method;

[0024] Based on the second boundary coordinate point set after data cleaning, the function expression of the second boundary line is fitted using the least squares method.

[0025] In another possible implementation, obtaining the secondary voltage to be analyzed and the secondary current to be analyzed of the electric field in the electrostatic precipitator includes:

[0026] Determine the volt-ampere change rate of the electric field based on the historical secondary voltage and the historical secondary current in the electric field within a set time interval, wherein the volt-ampere change rate represents the change rate of the secondary current and the secondary voltage in the electric field;

[0027] Obtaining the current secondary voltage and the current secondary current of the electric field in the electrostatic precipitator at the current moment;

[0028] Based on the volt-ampere change rate of the electric field, the current secondary voltage and the current secondary current, determine the future secondary voltage and the future secondary current of the electric field at a target future time, determine the future secondary voltage as the secondary voltage to be analyzed, and determine the future secondary current as the secondary current to be analyzed, and the target future time is the time reached by the target time length after the current time;

[0029] The determining, based on the position relationship information, the abnormal state of the electric field in the electrostatic precipitator comprises:

[0030] Based on the positional relationship information, an abnormal state of the electric field in the electrostatic precipitator at the target future time is determined.

[0031] On the other hand, the present application also provides an electrostatic precipitator abnormality detection device, comprising:

[0032] A volt-ampere acquisition unit is used to obtain a secondary voltage to be analyzed and a secondary current to be analyzed of the electric field in the electrostatic precipitator;

[0033] A normal area obtaining unit, used for obtaining a volt-ampere normal area corresponding to the electric field determined most recently, wherein the volt-ampere normal area is a coordinate area in a volt-ampere coordinate plane that characterizes that the electric field does not have an abnormality, wherein the volt-ampere coordinate plane is a coordinate plane in which the horizontal coordinate represents the secondary voltage and the vertical coordinate represents the secondary current, and the volt-ampere normal area corresponding to the electric field is determined based on the historical secondary voltage and the historical secondary current of the electric field at multiple historical moments in a historical time period before the current moment;

[0034] A position relationship determination unit, used to determine position relationship information between a target coordinate point of the secondary current to be analyzed and the secondary voltage to be analyzed on the volt-ampere coordinate plane and the volt-ampere normal area;

[0035] An abnormal state determining unit is used to determine the abnormal state of the electric field in the electrostatic precipitator based on the position relationship information.

[0036] From the above, it can be seen that in the embodiment of the present application, the volt-ampere normal area in the volt-ampere coordinate plane that characterizes the electric field in a normal state will be determined based on the historical secondary voltage and historical secondary current of the electric field at multiple historical moments. Therefore, the volt-ampere normal area can characterize the distribution of the secondary voltage and secondary current in the electric field in a normal state. Based on this, after determining the target coordinate points of the secondary voltage to be analyzed and the secondary current to be analyzed of the electric field in the electrostatic precipitator on the volt-ampere coordinate plane, the present application can accurately judge the abnormal state of the electric field in the electrostatic precipitator based on the positional relationship information between the target coordinate points and the volt-ampere normal area, thereby being able to more accurately detect the abnormalities in the electric field, which is naturally conducive to timely discovery of faults in the electric field. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0038] Figure 1 A schematic diagram of a process flow of an electrostatic precipitator abnormality detection method provided in an embodiment of the present application is shown;

[0039] Figure 2 A schematic diagram of a process for constructing an electric field in a volt-ampere normal region of a volt-ampere coordinate plane in an embodiment of the present application is shown;

[0040] Figure 3 A schematic diagram showing the distribution of historical coordinate points corresponding to historical secondary voltages and historical secondary currents at historical moments in the electric field in the present application on the volt-ampere coordinate plane;

[0041] Figure 4 A schematic diagram of an implementation flow of a function expression for determining the boundary line of the normal volt-ampere region in an embodiment of the present application is shown;

[0042] Figure 5 Another schematic diagram of a flow chart of an electrostatic precipitator abnormality detection method provided in an embodiment of the present application is shown;

[0043] Figure 6 Another schematic diagram of a flow chart of an electrostatic precipitator abnormality detection method provided in an embodiment of the present application is shown;

[0044] Figure 7 A schematic diagram of the composition structure of an electrostatic precipitator abnormality detection device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0045] The solution of the embodiment of the present application is suitable for monitoring an electrostatic precipitator to accurately detect abnormal conditions that may exist in the electric field of the electrostatic precipitator.

[0046] Among them, the electrostatic precipitator is used to remove the smoke and dust emitted by factories such as chemical plants and thermal power plants. Among them, the electrostatic precipitator is composed of multiple electric fields, through which the smoke and dust can be adsorbed. The electric field can include components such as transformers, and there is no restriction on this.

[0047] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0048] like Figure 1 As shown, it shows a flow chart of an electrostatic precipitator abnormality detection method provided in an embodiment of the present application. The method of this embodiment may include:

[0049] S101, obtaining a secondary voltage to be analyzed and a secondary current to be analyzed of an electric field in an electrostatic precipitator.

[0050] In the present application, each electric field in the electrostatic precipitator can be monitored separately to detect whether there is any abnormality in the electric field.

[0051] It is understandable that when the electric field is abnormal, at least one of the secondary voltage and the secondary current of the electric field will also be abnormal. Based on this, the present application will analyze whether the electric field is abnormal in combination with the secondary voltage and the secondary current of the electric field.

[0052] For the sake of distinction, the secondary voltage corresponding to the moment when abnormality detection analysis is to be performed in the electric field is called the secondary voltage to be analyzed, and the secondary current corresponding to the electric field at the moment when abnormality analysis is to be performed is called the secondary current to be analyzed.

[0053] In a possible implementation, in order to be able to analyze in real time whether there is an abnormality in the electric field at present, the present application can obtain that the secondary voltage to be analyzed and the secondary current to be analyzed can be the secondary voltage and secondary current at the current moment in the electric field. For ease of distinction, the current secondary voltage and secondary current of the electric field can be referred to as the current secondary voltage and the current secondary current, respectively. On this basis, the current secondary voltage and the current secondary current of the electric field can be determined as the secondary voltage to be analyzed and the secondary current to be analyzed of the electric field, respectively.

[0054] In another possible implementation, the present application can also estimate the future secondary voltage and future secondary current of the electric field at a future moment after the current moment based on the secondary voltage and secondary current of the electric field over a certain period of time, and use the future secondary voltage as the secondary voltage to be analyzed and the future secondary current as the secondary current to be analyzed, so as to predict the abnormal state of the electric field at that future moment after the current moment.

[0055] S102, obtaining the volt-ampere normal area corresponding to the electric field determined most recently.

[0056] The volt-ampere normal area is a coordinate area in the volt-ampere coordinate plane that represents the absence of abnormalities in the electric field. The volt-ampere coordinate plane is a coordinate plane in which the horizontal axis represents the secondary voltage and the vertical axis represents the secondary current. In other words, the volt-ampere coordinate plane is a two-dimensional plane, the horizontal axis of the volt-ampere coordinate plane represents the secondary voltage, and the vertical axis represents the secondary current.

[0057] The volt-ampere normal area corresponding to the electric field is determined based on the historical secondary voltage and the historical secondary current of the electric field at multiple historical moments in the historical time period before the current moment.

[0058] There are many possible ways to specifically determine the normal volt-ampere area, and this application does not limit this. For example, based on the historical secondary voltages and historical secondary currents at multiple historical moments in the electric field under normal conditions, the coordinate points of the historical secondary voltages and historical secondary currents at each historical moment in the electric field on the volt-ampere coordinate plane can be determined, and the area composed of the coordinate points corresponding to each historical moment can be determined as the normal volt-ampere area.

[0059] It can be understood that since the normal volt-ampere area is a coordinate area that represents the absence of electric field abnormalities, the secondary voltage and secondary current corresponding to each coordinate point in the normal volt-ampere area can be considered as the secondary voltage and secondary current under normal electric field conditions.

[0060] It is understandable that, in the present application, for an electric field, considering that the electric field under normal conditions may have dynamic changes in its secondary voltage and secondary current, the present application may update the volt-ampere normal area of ​​the electric field at regular intervals. Each time the volt-ampere normal area of ​​the electric field is updated, the historical secondary voltage and historical secondary current in the most recently set historical time period may be used to re-determine the volt-ampere normal area.

[0061] S103, determining the position relationship information between the target coordinate point of the secondary current to be analyzed and the secondary voltage to be analyzed on the volt-ampere coordinate plane and the volt-ampere normal area.

[0062] The positional relationship information represents the positional relationship between the secondary current to be analyzed and the target coordinate point on the volt-ampere coordinate plane mapped to the secondary current to be analyzed, relative to the coverage area of ​​the volt-ampere normal area.

[0063] For example, the position relationship information can at least ensure whether the target coordinate point is within the normal V-ampere area. Of course, the position relationship information can also ensure the distance and orientation of the target position point from the normal V-ampere area, etc., without limitation.

[0064] S104, determining the abnormal state of the electric field based on the position relationship information.

[0065] The abnormal state is at least used to characterize whether the electric field is abnormal. Of course, the abnormal state may also characterize the possibility or risk level of the electric field being abnormal.

[0066] For example, if the position relationship information indicates that the target coordinate point is located in the normal volt-ampere region, it is determined that there is no abnormality in the electric field. If the position relationship information indicates that the target coordinate point is outside the volt-ampere coordinate region, it is determined that there is an abnormality in the electric field.

[0067] It can be understood that, when the secondary voltage to be analyzed and the secondary current to be analyzed are the current secondary voltage and current secondary current of the electric field, then what is determined in step S104 is the abnormal state of the electric field at the current moment. If the secondary voltage to be analyzed and the secondary current to be analyzed are the secondary voltage and secondary current of the electric field at a future moment after the current moment, then step S104 is actually the predicted abnormal state of the electric field at a future moment.

[0068] The inventors of the present application have discovered through research that the current abnormality detection of electrostatic precipitators usually sets an abnormality threshold for the secondary voltage or secondary current of the electric field, and analyzes whether there is an abnormality in the electric field of the electrostatic precipitator based solely on the secondary voltage or secondary current. However, considering only a single dimension of the secondary voltage or secondary current can easily lead to misjudgment, resulting in inaccurate abnormality detection results. Moreover, since the abnormality threshold is fixed, it is also easy to cause inaccurate retrieval results due to abnormal threshold settings.

[0069] Based on this, the present application actually detects the abnormality of the electric field from two dimensions, the secondary voltage and the secondary current of the electric field, which is more conducive to accurately discovering the abnormality of the electric field. Moreover, compared with a fixed single abnormal threshold, the volt-ampere normal area used to detect abnormalities in the present application is a two-dimensional plane area and the volt-ampere normal area can be dynamically updated. Each time, the abnormality detection is performed based on the most recently determined volt-ampere normal area, which is conducive to reducing the errors in abnormal detection caused by the failure of the abnormal threshold, etc.

[0070] From the above, it can be seen that in the embodiment of the present application, the volt-ampere normal area in the volt-ampere coordinate plane that characterizes the electric field in a normal state will be determined based on the historical secondary voltage and historical secondary current of the electric field at multiple historical moments. Therefore, the volt-ampere normal area can characterize the distribution of the secondary voltage and secondary current in the electric field in a normal state. Based on this, after determining the target coordinate points of the secondary voltage to be analyzed and the secondary current to be analyzed of the electric field in the electrostatic precipitator on the volt-ampere coordinate plane, the present application can accurately judge the abnormal state of the electric field in the electrostatic precipitator based on the positional relationship information between the target coordinate points and the volt-ampere normal area, thereby being able to more accurately detect the abnormalities in the electric field, which is naturally conducive to timely discovery of faults in the electric field.

[0071] It can be understood that, for an electric field, there are many ways to construct a normal volt-ampere region based on the secondary voltage and the secondary voltage of the electric field in a certain historical time period before the current moment.

[0072] A possible implementation is described below.

[0073] like Figure 2 As shown, it shows a schematic diagram of a process flow for constructing a volt-ampere normal region of an electric field in an embodiment of the present application. The method of this embodiment may include:

[0074] S201, obtaining the historical secondary voltage and the historical secondary current of the electric field at multiple historical moments in a historical time period before the current moment.

[0075] The historical time period can be selected as needed.

[0076] For example, the historical time period may be a time period corresponding to the most recent set time period before the current moment. The set time period may be set as required, for example, the set time period may be one week, and the historical time period may be within one week before the current moment.

[0077] For another example, the historical time period may be a time period before the current moment, a first set time period from the current moment, and a time period of a second set time period. For example, a month before one week from the current moment is used as the historical time period.

[0078] Of course, there may be other ways to select the historical time period, and there is no restriction on this.

[0079] For ease of distinction, this application refers to the secondary voltage corresponding to each historical moment in the historical time period as the historical secondary voltage, and the secondary current at the historical moment as the historical secondary current.

[0080] S202, taking the historical secondary voltage and the historical secondary current at each historical moment as a historical coordinate point on the volt-ampere coordinate plane, based on the distribution of multiple historical coordinate points corresponding to multiple historical moments on the volt-ampere coordinate plane, determine the coordinate point distribution area whose distribution density of the historical coordinate points meets the requirements, and determine the coordinate point distribution area as the volt-ampere normal area.

[0081] As mentioned above, the volt-ampere coordinate plane is a two-dimensional coordinate plane in which the horizontal axis represents the secondary voltage and the vertical axis represents the secondary current. The details are as described above and will not be repeated here.

[0082] Among them, for any historical moment in the historical time period, this application needs to determine the coordinate point of the historical secondary voltage and historical secondary current at the historical moment on the volt-ampere coordinate plane. For the sake of distinction, this coordinate point is called a historical coordinate point. On this basis, after determining the historical secondary voltage and historical secondary current of all historical moments in the historical time period, the distribution diagram of the historical coordinate points corresponding to each historical moment on the volt-ampere coordinate plane can be obtained. Figure 3 As shown, it shows a schematic diagram of the distribution of historical coordinate points in the volt-ampere coordinate plane in this application. Figure 3 The horizontal axis represents the secondary voltage U2, and the vertical axis represents the secondary current I2.

[0083] It is understandable that, under the condition of normal operation of the electric field, the coordinate points of the secondary voltage and the secondary current at different times in the electric field on the volt-ampere coordinate plane should be densely distributed in a small area. Therefore, the application can determine the coordinate point distribution area where the historical coordinate point distribution density meets the requirements as the volt-ampere normal area. Among them, the requirements that the coordinate point distribution density needs to meet can be set as needed, and there is no restriction on this.

[0084] It can be understood that by determining the coordinate point distribution area where the historical coordinate point distribution density meets the requirements, each historical coordinate point in the coordinate point distribution area can be determined as the normal coordinate point corresponding to the secondary voltage and the second current under normal operation of the electric field, and the discrete points deviating from the coordinate point distribution area can be determined as the abnormal coordinate point corresponding to the moment when the electric field is abnormal. Figure 3 As shown in the figure, the area with dense coordinate points can be finally determined as the normal volt-ampere area. Figure 3 The discrete points that deviate from the black area will not be classified as the normal volt-ampere area.

[0085] In particular, in order to make the normal volt-ampere area of ​​the electric field more accurately reflect the distribution of coordinate points corresponding to the secondary current and secondary voltage under normal operation of the electric field, the historical time period selected in this application can be a historical time period under normal operation of the electric field.

[0086] certainly, Figure 2 This is merely an example of a method for determining the normal volt-ampere region of the electric field. In practical applications, there may be other methods for determining the normal volt-ampere region, and there is no limitation to this.

[0087] It is understandable that after determining the normal volt-ampere area of ​​the electric field, the boundary of the normal volt-ampere area can be constructed according to actual needs, so as to facilitate comparison of whether the target coordinate points corresponding to the secondary voltage and secondary current to be analyzed are within the normal volt-ampere area.

[0088] In practical applications, in order to determine the positional relationship information between the target coordinate point and the normal volt-ampere area, the present application can also fit the function expression of the boundary of the normal volt-ampere area. The following is an example of an implementation method of determining the function expression of the boundary of the normal volt-ampere area.

[0089] like Figure 4 , which shows a schematic diagram of an implementation flow of a function expression for determining the boundary line of the normal volt-ampere region in an embodiment of the present application. The method of this embodiment may include:

[0090] S401, obtaining the historical secondary voltage and the historical secondary current of the electric field at multiple historical moments in a historical time period before the current moment.

[0091] S402, taking the historical secondary voltage and historical secondary current at each historical moment as a historical coordinate point on the volt-ampere coordinate plane, based on the distribution of multiple historical coordinate points corresponding to multiple historical moments on the volt-ampere coordinate plane, determine the coordinate point distribution area whose distribution density of the historical coordinate points meets the requirements, and determine the coordinate point distribution area as the volt-ampere normal area.

[0092] Steps S401 and S402 are described by taking an example of an implementation method for determining the normal volt-ampere region of the electric field. In practical applications, if the normal volt-ampere region is determined by other methods, it is also applicable to this embodiment.

[0093] S403, determining a first boundary coordinate point set and a second boundary coordinate point set in the normal volt-ampere area.

[0094] The first boundary coordinate point set includes a plurality of historical coordinate points for representing a first boundary line of the normal volt-ampere region. The first boundary line is a boundary line in the normal volt-ampere region close to the ordinate axis of the volt-ampere coordinate plane.

[0095] The second boundary coordinate point set includes a plurality of historical coordinate points for representing a second boundary line of the normal volt-ampere region. The second boundary line is a boundary line in the normal volt-ampere region that is away from the ordinate axis.

[0096] like Figure 3 As shown in FIG. 3 , the determined normal volt-ampere region 301 is not a regular region. On this basis, in order to more reliably characterize the boundary of the normal volt-ampere region, in this embodiment, only one boundary line on the left side and one boundary line on the right side of the normal volt-ampere region can be focused on. The left side here refers to the irregular boundary line in the normal volt-ampere region close to the ordinate axis. Similarly, the right boundary line is Figure 3 The normal area of ​​medium volt-ampere is located on the right side, that is, away from the irregular boundary line of the ordinate axis.

[0097] As for the upper and lower boundary lines, the maximum secondary current value and the minimum secondary current value on the ordinate axis can be set as needed to limit the secondary current value within the normal volt-ampere area.

[0098] The first boundary coordinate point set is a set of historical coordinate points in the normal volt-ampere region that can be considered to be on or close to the first boundary line and can represent the distribution of the first boundary line. Similarly, the second boundary coordinate point set is a set of historical coordinate points selected from the normal volt-ampere region that can represent the second boundary line.

[0099] For example, in a possible implementation, the first boundary coordinate point set and the second boundary coordinate point set may be determined in the following manner:

[0100] First, according to a set first unit length, a plurality of horizontal segmentation lines perpendicular to the ordinate axis in the volt-ampere coordinate plane are constructed to determine a plurality of horizontal regions divided by the plurality of horizontal segmentation lines from the volt-ampere normal region.

[0101] The distance between adjacent horizontal dividing lines and the distance between the horizontal dividing line closest to the horizontal axis and the horizontal axis are both the first unit length. The first unit length can be set as needed, for example, the first unit length can be set to 100V.

[0102] like Figure 3 As shown, the volt-ampere coordinate plane uses every 100V as a dividing point, and draws out multiple horizontal dividing lines from the vertical axis. Correspondingly, the area between any two adjacent dividing lines in the normal volt-ampere area is a horizontal area. At the same time, the area between the first dividing line from bottom to top in the normal volt-ampere area and the horizontal axis is also a horizontal area.

[0103] Then, for each horizontal area in the normal volt-ampere area, the first historical coordinate points in the horizontal area are sorted in ascending order according to the historical secondary current, and the first number of first historical coordinate points with the highest sorting and the second number of second historical coordinate points with the lowest sorting are selected.

[0104] The first number and the second number can be set as needed. For example, for each horizontal area in the normal volt-ampere area, the historical coordinate points in the first 1 / 4 of the horizontal area can be selected as the first historical coordinate points according to the order of the secondary current from small to large. Similarly, the historical coordinate points in the last 1 / 4 of the horizontal area can be selected as the second historical coordinate points.

[0105] Secondly, according to the set second unit length, a plurality of vertical dividing lines perpendicular to the horizontal axis in the volt-ampere coordinate plane are constructed to determine a plurality of vertical regions in the volt-ampere normal region divided by the plurality of vertical dividing lines.

[0106] The second unit length can also be set as needed. It is understandable that, considering that the numerical dividing line is used to divide the first number of first historical coordinate points and the second number of second historical coordinate points, the value of the second unit length can be set relatively small.

[0107] Again, for each vertical region, the first historical coordinate points in the vertical region are sorted in order of historical secondary voltages from small to large, and the third number of first historical coordinate points in the sorting order are used as first boundary coordinate points and stored in the first boundary coordinate point set.

[0108] For example, the first historical coordinate point ranked in the first 4 / 1 in the vertical area may be selected as the first boundary coordinate point.

[0109] Finally, for each vertical region, the second historical coordinate points in the vertical region are sorted in order of historical secondary voltage from small to large, and the fourth number of second historical coordinate points in the top order are used as second boundary coordinate points and stored in the second boundary coordinate point set.

[0110] For example, the second historical coordinate point ranked in the last 4 / 1 in the vertical area may be selected as the second boundary coordinate point.

[0111] Of course, the above is an example of a method for selecting the first boundary coordinate point and the second boundary coordinate point. In practical applications, there may be other possible methods for selecting the first boundary coordinate point and the second boundary coordinate point, and there is no limitation on this.

[0112] S404, performing data cleaning on the first boundary coordinate point set and the second boundary coordinate point set based on the Laida criterion to obtain the first boundary coordinate point set and the second boundary coordinate point set after data cleaning.

[0113] Among them, the Laida criterion can also be called the 3sigm principle, which can be used to filter out abnormal points in a set of data to achieve data cleaning.

[0114] It is understandable that this embodiment is described by taking the data cleaning after screening out the first boundary coordinate point set and the second boundary coordinate point set as an example. In practical applications, data cleaning can be performed in the process of screening out the first boundary coordinate point set and the second boundary coordinate point set. For example, before selecting the first number of first historical coordinate points and the second number of second historical coordinate points, the historical coordinate points of each horizontal area in the volt-ampere normal area can be cleaned first. Correspondingly, after determining each vertical area, a data request can also be executed first and then the historical coordinate points can be selected.

[0115] S405, based on the first boundary coordinate point set after data cleaning, use the least square method to fit the function expression of the first boundary line.

[0116] S406, based on the second boundary coordinate point set after data cleaning, use the least square method to fit a function expression of the second boundary line.

[0117] When the horizontal coordinate and vertical coordinate of each first boundary coordinate point in the first boundary coordinate point set are known, the specific process of fitting the boundary line using the least squares method can be conventional data processing. The process of fitting the boundary of the second boundary line is similar and will not be repeated here.

[0118] For ease of understanding, the following is a brief introduction to the process of boundary line fitting based on the least squares method:

[0119] First, the approximate function expression of constructing a boundary line (such as the first boundary line or the second boundary line) can be expressed as the following formula 1:

[0120] f(x)≈p n (x) = a 0 +a 1 (xx 0 )+a 2 (xx 0 ) 2 +...+a n (xx 0 ) n (Formula 1);

[0121] Wherein, n can be a preset value, such as 5. x can be the horizontal coordinate value of a historical coordinate point located on the boundary line (such as a historical coordinate point in the first boundary coordinate point set or the second boundary coordinate point set), i.e., the historical secondary current, and f(x) is used to obtain the vertical coordinate value corresponding to the historical coordinate point located on the boundary line.

[0122] Secondly, the square of the result of the polynomial function is subtracted from the true ordinate value of the historical coordinate point on the boundary line to express the error relationship between the true value and the polynomial function of the formula, which can be expressed as the following formula 2:

[0123]

[0124] Again, let x 0 =0, then the error expressed by the least squares method, that is, the objective function can be expressed as the following formula 3:

[0125]

[0126] Finally, in order to optimize the objective function, the partial derivative of each coefficient in Formula 3 is set to zero, and the gradient descent method is used to solve each coefficient, and the coefficient is substituted into Formula 1 to obtain the function expression of the boundary line.

[0127] For example, taking the coefficient a in formula 3 0 、a 1 and a 2 The partial derivative can be expressed as 0 as follows:

[0128]

[0129]

[0130]

[0131] The same is true for other coefficients. Based on formula 4, each coefficient can be solved using the gradient descent method.

[0132] It can be understood that in the embodiments of the present application, an example is taken in which the normal volt-ampere area is determined as an area surrounded by multiple boundary lines. In actual applications, the boundary of the normal volt-ampere area can also be regarded as a boundary line to determine the function expression, etc., and there is no limitation on this.

[0133] It can be understood that in the above embodiments of the present application, since the normal volt-ampere zone corresponding to the electric field is used to characterize the secondary voltage and the distribution of the secondary voltage when the electric field is in a normal state, whether the electric field is abnormal can be analyzed based on whether the target coordinate points of the secondary voltage to be analyzed and the secondary current to be analyzed on the volt-ampere coordinate plane are within the normal volt-ampere zone.

[0134] Furthermore, in the present application, when the target coordinate point is outside the normal volt-ampere zone, the present application can also combine the positional relationship information between the target coordinate point and the normal volt-ampere zone to determine the risk level of the electric field abnormality, and the risk level represents the possibility of the electric field abnormality or the degree of abnormality of the electric field abnormality.

[0135] For example, in a possible implementation, if the position relationship information indicates that the target coordinate point is outside the normal volt-ampere area, the risk level of abnormality in the electric field can be determined based on the distance between the target coordinate point and the boundary of the normal volt-ampere area.

[0136] The distance between the target coordinate point and the boundary of the normal volt-ampere region may be the shortest distance between the target coordinate point and the boundary of the normal volt-ampere region.

[0137] It can be understood that the farther the target coordinate point is from the normal volt-ampere area, the greater the risk that the target coordinate point is an abnormal coordinate point representing an abnormal electric field, and therefore, the greater the degree of abnormality of the abnormal electric field.

[0138] Based on this possible implementation method, the following is an example of an implementation method for determining the risk level. Figure 5 As shown, it shows another flow chart of an electrostatic precipitator abnormality detection method provided in an embodiment of the present application. The method of this embodiment may include:

[0139] S501, obtaining a secondary voltage to be analyzed and a secondary current to be analyzed of the electric field in the electrostatic precipitator.

[0140] S502, obtaining the volt-ampere normal area corresponding to the electric field determined most recently.

[0141] The normal volt-ampere region is a coordinate region in the volt-ampere coordinate plane that indicates that the electric field does not have abnormality. The normal volt-ampere region can be found in the above related introduction and will not be described here.

[0142] S503, determining the position relationship information between the target coordinate point of the secondary current to be analyzed and the secondary voltage to be analyzed on the volt-ampere coordinate plane and the volt-ampere normal area.

[0143] S503: If the position relationship information indicates that the target coordinate point is located in a normal volt-ampere area, it is determined that there is no abnormality in the electric field.

[0144] S504: If the position relationship information indicates that the target coordinate point is outside the normal volt-ampere area, determine a risk control area corresponding to the normal volt-ampere area in the volt-ampere coordinate plane.

[0145] The risk control area is determined based on the normal volt-ampere area, indicating a coordinate area where the electric field may be abnormal. The risk control area includes the normal volt-ampere area and is larger than the normal volt-ampere area.

[0146] The risk control area can be set as needed, such as expanding outward based on the normal volt-ampere area based on experience to obtain the risk control area, etc. Of course, the risk control area can also be determined in other ways.

[0147] For example, taking the first boundary line and the second boundary line of the normal volt-ampere zone of the electric field determined above as an example, assuming that the first boundary line is closer to the vertical axis, then the first intersection point of the first boundary line and the horizontal axis of the volt-ampere coordinate plane, and the second intersection point of the second boundary line and the horizontal axis of the volt-ampere coordinate plane can be determined, and then the intersection distance d between the first intersection point and the second intersection point is determined, and then the first boundary line of the normal volt-ampere zone is translated along the negative direction of the horizontal axis by the intersection distance d to obtain the third boundary line, and the second boundary line of the normal volt-ampere zone is translated along the positive direction of the horizontal axis by the intersection distance d to obtain the fourth boundary line, and the area composed of the third boundary line, the fourth boundary line, the upper boundary line corresponding to the maximum secondary current value set on the vertical axis, and the lower boundary line corresponding to the minimum secondary current value set on the vertical axis is determined as the risk control area.

[0148] S505, if the target coordinate point is within the risk control area, determine the risk level of abnormality in the electric field based on the first shortest distance between the target coordinate point and the boundary of the normal volt-ampere area and the second shortest distance between the target coordinate point and the boundary of the risk control area.

[0149] For example, combined Figure 3For illustration, assuming that the target coordinate point is located on the left side of the normal volt-ampere area, the target coordinate point is closer to the first boundary line on the left side of the normal volt-ampere area, and is relatively far from the second boundary line on the right side of the normal volt-ampere area. Therefore, the distance between the target coordinate point and the first boundary line can be calculated as the first shortest distance. Correspondingly, the distance between the target coordinate point and the boundary line on the left side of the risk control area is determined as the second shortest distance.

[0150] It is understandable that the distance from the coordinate point to the boundary (ie, the boundary line) can be calculated using the calculation formula for the distance from a point to a line, and there is no limitation to this.

[0151] It is understandable that there are many ways to determine the risk level by combining the first shortest distance and the second shortest distance. Generally, the greater the distance to the first shortest distance and the smaller the distance to the second shortest distance, the greater the risk of abnormality in the electric field.

[0152] S506: If the target coordinate point is outside the risk control area, it is determined that the electric field is abnormal.

[0153] Among them, if the target coordinate point is located outside the risk control area, it can be determined that there must be an abnormality in the electric field.

[0154] For ease of understanding, an implementation method for determining the risk level is described below as an example. For example, the risk level T of abnormal electric field in this application can be determined by the following formula 5.

[0155]

[0156] Among them, t represents the target coordinate point, D represents the volt-ampere normal area of ​​the electric field, and D n represents the risk control area, t∈(D n -D) indicates that the target coordinate point t is between the normal volt-ampere area and the risk control area.

[0157] In Formula 5, the higher the risk level, the smaller the value indicating the risk level. For example, if the target coordinate point belongs to the normal volt-ampere area, the risk level is 1, which indicates that the electric field has no abnormality to the greatest extent, and the electric field is determined to be in a normal state. Correspondingly, if the target coordinate point is not in the risk control area, that is, outside the risk control area, the risk level is 0, indicating that the probability that the electric field has no abnormality is 0, and there is an abnormal fault in the electric field.

[0158] Among them, E dir Indicates the first shortest distance, E sdir Indicates the second shortest distance.

[0159] As shown in Formula 5 above, the risk level is a value between 1 and 0. In practical applications, it can also be assumed that the risk level is represented by a number between 0 and 1, where the higher the risk level, the greater the value of the risk level. When the target coordinate point is outside the risk control area, it can be determined that the risk level of abnormal electric field is 1.

[0160] It can be understood that in the above embodiments of the present application, after determining the abnormal state of each electric field in the electrostatic precipitator, in order to determine the comprehensive state of the electrostatic precipitator, the present application can also determine the overall abnormal state of the electrostatic precipitator based on the abnormal states of different electric fields in the electrostatic precipitator.

[0161] For example, when the abnormal state of the electric field is characterized by the risk level of the electric field being abnormal, the present application can determine the weight coefficient of each electric field, wherein the higher the importance of the electric field, the greater its weight coefficient. On this basis, the weighted value of the risk level of all electric fields can be calculated based on the value of the risk level corresponding to each electric field, and the weighted value is a quantitative value characterizing the presence of an abnormality in the electrostatic precipitator.

[0162] It can be understood that the method of the present application can be used to determine whether there is a current abnormal condition such as a fault based on the current secondary voltage and secondary current of the electric field; it can also be based on the secondary voltage and secondary current at a certain moment after the current moment to predict the abnormal state of the electric field at a certain moment after the current moment.

[0163] In order to predict the abnormal state of the electric field at a certain moment after the current moment, it is necessary to first predict the secondary voltage and secondary current of the electric field at that moment after the current moment. The following is an introduction to the solution of this application in conjunction with an implementation method for predicting the secondary voltage and secondary current of the electric field at a certain moment after the current moment.

[0164] like Figure 6 As shown, it shows another flow chart of an electrostatic precipitator abnormality detection method provided in an embodiment of the present application. The method of this embodiment may include:

[0165] S601, for any electric field in the electrostatic precipitator, determine the volt-ampere change rate of the electric field based on the historical secondary voltage and historical secondary current in the electric field within a set time interval.

[0166] The volt-ampere change rate represents the change rate of the secondary current and the secondary voltage in the electric field.

[0167] The time interval may be set to be a period of time before the current moment, and the length of the time interval may be set as required.

[0168] It can be understood that when the historical secondary voltage and the historical secondary current at the starting point of a set time interval, as well as the historical secondary voltage and the historical secondary current at the end point of the set time interval are determined, the velocity vector of the historical secondary voltage and the historical secondary current of the electric field within the set time interval can be determined by combining the calculation formula between distance, speed and time.

[0169] For example, assuming that within the time interval tv, the initial historical secondary voltage and the historical secondary current are represented by (x1, y1) at the first historical coordinate point of the volt-ampere coordinate plane, and the final historical secondary voltage and the historical secondary current are represented by ((x2, y2)) at the second historical coordinate point of the volt-ampere coordinate plane, then the distance calculation formula can be used to calculate the moving distance of the historical coordinate point of the electric field within the time interval, that is, the calculation formula of the volt-ampere distance d can be as follows: Formula 6:

[0170]

[0171] Correspondingly, using the formula that speed equals distance divided by time, dividing the volt-ampere distance by the length of the set time interval can obtain the volt-ampere velocity vector within the time interval, which includes the historical secondary voltage change rate and the historical secondary current change rate.

[0172] It should be noted that step S601 may be executed each time the electric field abnormality at a future moment is predicted, or the volt-ampere change rate may be considered to be one time within a period of time, so if the most recently calculated volt-ampere change rate is within the validity period, there is no need to calculate the volt-ampere change rate again.

[0173] S602, obtaining the current secondary voltage and the current secondary current of the electric field at the current moment.

[0174] The order of the above steps S601 and S602 may not be limited to Figure 6 As shown, if the set time interval is a time interval including the current time, then step S602 may be performed first, and then step S601 may be performed. Of course, these two steps may also be performed simultaneously.

[0175] S603, based on the volt-ampere change rate of the electric field, the current secondary voltage and the current secondary current, determine the future secondary voltage and the future secondary current of the electric field at the target future time, determine the future secondary voltage as the secondary voltage to be analyzed, and determine the future secondary current as the secondary current to be analyzed.

[0176] The target future time is the time reached by the target duration after the current time. The target duration can be set according to actual prediction needs. For example, if the abnormal situation of the electric field after the current 24 hours needs to be predicted, the target duration is 24 hours.

[0177] It is understandable that when the volt-ampere change rate is known, the moving distance of the historical coordinate point in the electric field within the target time can be calculated. On this basis, based on the historical coordinate points of the current secondary voltage and secondary current on the volt-ampere coordinate plane and the moving distance, combined with the calculation formula for the distance between points, the historical coordinate points of the future secondary voltage and future secondary current in the electric field on the volt-ampere coordinate plane at the target future moment can be determined, and naturally the future secondary voltage and future secondary current are obtained.

[0178] S604, obtaining the most recently determined volt-ampere normal region corresponding to the electric field.

[0179] The normal volt-ampere region is a coordinate region in the volt-ampere coordinate plane that indicates that the electric field does not have abnormality. The normal volt-ampere region can be found in the above related introduction and will not be described here.

[0180] S605, determining the position relationship information between the target coordinate point of the secondary current to be analyzed and the secondary voltage to be analyzed on the volt-ampere coordinate plane and the volt-ampere normal area.

[0181] S606: Determine the abnormal state of the electric field at the target at a future time based on the position relationship information.

[0182] For steps S604 to S606, reference may be made to the related introduction of the previous embodiment and will not be repeated here.

[0183] It can be understood that in the embodiment of the present application, when it is determined that there is an abnormality in the electric field, that is, the electric field is not in a normal state, such as the risk level of the abnormality in the electric field characterizes that there is an abnormality in the electric field or the possibility of an abnormality, the present application can also combine the relative position relationship of the target coordinate points of the secondary voltage to be analyzed and the secondary current to be analyzed on the volt-ampere coordinate plane relative to the volt-ampere normal area to determine the abnormality type of the electric field abnormality.

[0184] For example, the correspondence between different relative position relationships and abnormal types of abnormalities may be preconfigured, and by querying the correspondence, the abnormal type that may cause the abnormality when there is a possibility of abnormality in the electric field may be determined.

[0185] For example, combining Figure 3 Note: Assuming that the electric field is abnormal based on the relative position of the target coordinate point to the normal volt-ampere area, the abnormal type of the electric field can be determined by querying the following table:

[0186]

[0187] From the above table, it can be seen that if the target coordinate point is outside the normal volt-ampere area and is Figure 3On the upper left side of the normal volt-ampere area, relative to the normal volt-ampere area, the secondary voltage represented by the target coordinate point will be higher and the secondary current represented by the target coordinate point will be significantly reduced. Therefore, through this table, it can be found that the type of abnormality that causes the abnormality may be: high dust concentration and failure of the rapping device.

[0188] Similarly, if the target coordinate point is outside the normal volt-ampere area and on the right side of the normal volt-ampere area, then the abnormality type may be back corona or short circuit.

[0189] It can be understood that in the above embodiments of the present application, in order to further reduce misjudgment, after determining that the electric field in the electrostatic precipitator is currently abnormal, the present application can also use the current secondary voltage and the current secondary current as an abnormal volt-ampere data pair to detect whether the abnormal volt-ampere data pair exists in the temporary verification library. The temporary verification library can store abnormal volt-ampere data pairs that the device considers to be abnormal but the user corrects to be not abnormal.

[0190] If the abnormal volt-ampere data pair does not exist in the temporary verification library, an abnormal reminder is output, and the abnormal reminder is used to prompt that the electric field is abnormal, and the abnormal reminder indicates that there is an abnormal secondary voltage and abnormal secondary current in the electric field. On the contrary, if the abnormal volt-ampere data pair exists in the temporary verification library, it means that the user has previously set the abnormal volt-ampere data pair as a normal volt-ampere data pair, and it can be considered that the abnormal volt-ampere data pair does not belong to abnormal data, and there is no need to output an abnormal reminder.

[0191] Furthermore, after the abnormal reminder is output, if a confirmation operation of the user confirming that the abnormal secondary voltage and the abnormal secondary current are a normal volt-ampere data pair is detected, the abnormal secondary voltage and the abnormal secondary current can be stored as a volt-ampere data pair in a temporary verification library.

[0192] It is understandable that the present application can update the normal volt-ampere area of ​​the electric field from time to time. In particular, the present application can also combine each pair of secondary current and secondary voltage in the volt-ampere verification library to temporarily add, translate or rotate the normal volt-ampere area to update the normal volt-ampere area. For example, translation is to translate a certain volt-ampere boundary curve of the normal volt-ampere area in the x-axis direction to increase or decrease the normal volt-ampere area; rotation is to rotate at a small angle with the boundary point on the x-axis of the normal volt-ampere area as the center.

[0193] Of course, after updating the normal volt-ampere area, the boundary line of the normal volt-ampere area may be refitted.

[0194] Corresponding to an electrostatic precipitator abnormality detection method of the present application, the present application also provides an electrostatic precipitator abnormality detection device.

[0195] like Figure 7As shown, it shows an electrostatic precipitator abnormality detection device provided by the present application, the device comprising:

[0196] A volt-ampere acquisition unit 701 is used to obtain a secondary voltage to be analyzed and a secondary current to be analyzed of the electric field in the electrostatic precipitator;

[0197] A normal area obtaining unit 702 is used to obtain a volt-ampere normal area corresponding to the electric field determined most recently, wherein the volt-ampere normal area is a coordinate area in a volt-ampere coordinate plane that indicates that the electric field does not have an abnormality, wherein the volt-ampere coordinate plane is a coordinate plane in which the horizontal coordinate represents the secondary voltage and the vertical coordinate represents the secondary current, and the volt-ampere normal area corresponding to the electric field is determined based on the historical secondary voltage and the historical secondary current of the electric field at multiple historical moments in a historical time period before the current moment;

[0198] A position relationship determination unit 703, used to determine position relationship information between the target coordinate point of the secondary current to be analyzed and the secondary voltage to be analyzed on the volt-ampere coordinate plane and the volt-ampere normal area;

[0199] The abnormal state determination unit 704 is used to determine the abnormal state of the electric field in the electrostatic precipitator based on the position relationship information.

[0200] In a possible implementation, the abnormal state determining unit includes:

[0201] A first state determination unit, configured to determine that there is no abnormality in the electric field if the position relationship information indicates that the target coordinate point is located in the normal volt-ampere area;

[0202] The second state determination unit is used to determine the risk level of abnormality of the electric field based on the distance between the target coordinate point and the boundary of the normal volt-ampere area if the position relationship information indicates that the target coordinate point is outside the normal volt-ampere area.

[0203] In a possible implementation, the second state determining unit includes:

[0204] a sealed area determination unit, configured to determine a risk control area corresponding to the normal V-A area in the V-A coordinate plane, wherein the risk control area is a coordinate area determined based on the normal V-A area, indicating that the electric field may be abnormal, and the risk control area includes the normal V-A area and is larger than the normal V-A area;

[0205] an abnormality degree determination unit, configured to determine the risk degree of abnormality of the electric field based on a first shortest distance between the target coordinate point and a boundary of the normal volt-ampere zone and a second shortest distance between the target coordinate point and a boundary of the risk control zone if the target coordinate point is outside the normal volt-ampere zone and within the risk control zone;

[0206] An abnormality determination unit is used to determine that there is an abnormality in the electric field if the target coordinate point is outside the risk control area.

[0207] In another possible implementation, the volt-ampere region construction unit is used to obtain the volt-ampere normal region of the electric field in the following manner:

[0208] Obtaining historical secondary voltages and historical secondary currents of the electric field at multiple historical moments in a historical time period before a current moment;

[0209] Taking the historical secondary voltage and the historical secondary current at each historical moment as a historical coordinate point on the volt-ampere coordinate plane, based on the distribution of multiple historical coordinate points corresponding to multiple historical moments on the volt-ampere coordinate plane, determine the coordinate point distribution area whose distribution density of the historical coordinate points meets the requirements, and determine the coordinate point distribution area as the volt-ampere normal area.

[0210] The volt-ampere construction unit is further configured to perform the following operations after determining the coordinate point distribution area as the volt-ampere normal area:

[0211] Determine a first boundary coordinate point set and a second boundary coordinate point set in a normal volt-ampere region, wherein the first boundary coordinate point set includes a plurality of historical coordinate points for representing a first boundary line of the normal volt-ampere region, and the second boundary coordinate point set includes a plurality of historical coordinate points for representing a second boundary line of the normal volt-ampere region, wherein the first boundary line is a boundary line in the normal volt-ampere region close to a ordinate axis of the volt-ampere coordinate plane, and the second boundary line is a boundary line in the normal volt-ampere region far from the ordinate axis;

[0212] Performing data cleaning on the first boundary coordinate point set and the second boundary coordinate point set based on the Laida criterion to obtain the first boundary coordinate point set and the second boundary coordinate point set after data cleaning;

[0213] Based on the first boundary coordinate point set after data cleaning, a function expression of the first boundary line is fitted using the least squares method;

[0214] Based on the second boundary coordinate point set after data cleaning, the function expression of the second boundary line is fitted using the least squares method.

[0215] In yet another possible implementation, the volt-ampere obtaining unit includes:

[0216] A first volt-ampere obtaining unit is used to obtain a current secondary voltage and a current secondary current of the electric field in the electrostatic precipitator, and determine the current secondary voltage and the current secondary current of the electric field as the secondary voltage and the secondary current to be analyzed of the electric field;

[0217] The abnormal state determination unit includes:

[0218] The first abnormality detection unit is used to determine the current abnormal state of the electric field in the electrostatic precipitator based on the position relationship information.

[0219] In yet another possible implementation, the volt-ampere obtaining unit includes:

[0220] A speed determination unit, configured to determine a volt-ampere change speed of the electric field based on a historical secondary voltage and a historical secondary current in the electric field within a set time interval, wherein the volt-ampere change speed represents a change speed of a secondary current and a secondary voltage in the electric field;

[0221] A second volt-ampere obtaining unit is used to obtain a current secondary voltage and a current secondary current of the electric field in the electrostatic precipitator at a current moment;

[0222] A third volt-ampere obtaining unit is used to determine the future secondary voltage and future secondary current of the electric field at a target future time based on the volt-ampere change rate of the electric field, the current secondary voltage and the current secondary current, determine the future secondary voltage as the secondary voltage to be analyzed, and determine the future secondary current as the secondary current to be analyzed, and the target future time is the time reached by the target time length after the current time;

[0223] The abnormal state determination unit includes:

[0224] The second abnormality detection unit is used to determine the abnormal state of the electric field in the electrostatic precipitator at the target future time based on the position relationship information.

[0225] In yet another possible implementation, the device further includes:

[0226] A comprehensive state determination unit is used to determine the overall abnormal state of the electrostatic precipitator based on the abnormal states of different electric fields in the electrostatic precipitator.

[0227] In yet another possible implementation, the device further includes:

[0228] A data verification unit, for detecting whether there is an abnormal volt-ampere data pair in a temporary verification library by taking the current secondary voltage and the current secondary current as an abnormal volt-ampere data pair after the abnormal state determination unit determines that the electric field in the electrostatic precipitator is currently abnormal;

[0229] an abnormality reminder unit, used for outputting an abnormality reminder if the abnormal volt-ampere data pair does not exist in the temporary verification library, wherein the abnormality reminder is used to prompt that the electric field is abnormal, and the abnormality reminder indicates that there is an abnormal secondary voltage and an abnormal secondary current in the electric field;

[0230] The data storage unit is used to store the abnormal secondary voltage and abnormal secondary current in the temporary verification library if a confirmation operation of the user confirming that the abnormal secondary voltage and abnormal secondary current are a normal volt-ampere data pair is detected.

[0231] It should be noted that each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the embodiments can be referred to each other. At the same time, the features recorded in the embodiments in this specification can be replaced or combined with each other, so that professionals in the field can implement or use this application. For device embodiments, since they are basically similar to method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0232] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0233] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0234] The above are only preferred implementations of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for detecting abnormality of an electrostatic precipitator, characterized in that: include: Obtaining a secondary voltage to be analyzed and a secondary current to be analyzed of an electric field in an electrostatic precipitator; Obtaining the volt-ampere normal area corresponding to the electric field determined most recently, the volt-ampere normal area being a coordinate area in a volt-ampere coordinate plane that characterizes that the electric field does not have an abnormality, the volt-ampere coordinate plane being a coordinate plane in which the abscissa represents the secondary voltage and the ordinate represents the secondary current, the volt-ampere normal area corresponding to the electric field being determined based on the historical secondary voltage and the historical secondary current at multiple historical moments in a historical time period before the current moment; Determine the positional relationship information between the target coordinate points of the secondary current to be analyzed and the secondary voltage to be analyzed on the volt-ampere coordinate plane and the volt-ampere normal area; Based on the positional relationship information, determining an abnormal state of the electric field in the electrostatic precipitator; The volt-ampere normal region corresponding to the electric field is obtained by the following method: Obtaining historical secondary voltages and historical secondary currents of the electric field at multiple historical moments in a historical time period before a current moment; Taking the historical secondary voltage and the historical secondary current at each historical moment as a historical coordinate point on the volt-ampere coordinate plane, based on the distribution of multiple historical coordinate points corresponding to multiple historical moments on the volt-ampere coordinate plane, determining a coordinate point distribution area where the distribution density of the historical coordinate points meets the requirements, and determining the coordinate point distribution area as a volt-ampere normal area; After determining the coordinate point distribution area as a normal volt-ampere area, the method further includes: Determine a first boundary coordinate point set and a second boundary coordinate point set in a normal volt-ampere region, wherein the first boundary coordinate point set includes a plurality of historical coordinate points for representing a first boundary line of the normal volt-ampere region, and the second boundary coordinate point set includes a plurality of historical coordinate points for representing a second boundary line of the normal volt-ampere region, wherein the first boundary line is a boundary line in the normal volt-ampere region close to a ordinate axis of the volt-ampere coordinate plane, and the second boundary line is a boundary line in the normal volt-ampere region far from the ordinate axis; Performing data cleaning on the first boundary coordinate point set and the second boundary coordinate point set based on the Laida criterion to obtain the first boundary coordinate point set and the second boundary coordinate point set after data cleaning; Based on the first boundary coordinate point set after data cleaning, a function expression of the first boundary line is fitted using the least squares method; Based on the second boundary coordinate point set after data cleaning, the function expression of the second boundary line is fitted using the least squares method.

2. The method according to claim 1, characterized in that The determining, based on the position relationship information, the abnormal state of the electric field in the electrostatic precipitator comprises: If the position relationship information indicates that the target coordinate point is located in the normal volt-ampere area, determining that there is no abnormality in the electric field; If the positional relationship information indicates that the target coordinate point is outside the normal volt-ampere region, the risk level of abnormality in the electric field is determined based on the distance between the target coordinate point and the boundary of the normal volt-ampere region.

3. The method according to claim 2, characterized in that The step of determining the risk level of abnormality of the electric field based on the distance between the target coordinate point and the boundary of the normal volt-ampere area includes: Determine a risk control area corresponding to the normal volt-ampere area in the volt-ampere coordinate plane, wherein the risk control area is a coordinate area determined based on the normal volt-ampere area, indicating that the electric field may be abnormal, and the risk control area includes the normal volt-ampere area and is larger than the normal volt-ampere area; If the target coordinate point is outside the normal volt-ampere area and within the risk control area, determining the risk level of abnormality of the electric field based on a first shortest distance between the target coordinate point and a boundary of the normal volt-ampere area and a second shortest distance between the target coordinate point and a boundary of the risk control area; If the target coordinate point is outside the risk control area, it is determined that an abnormality exists in the electric field.

4. The method according to any one of claims 1 to 3, characterized in that: The method of obtaining the secondary voltage to be analyzed and the secondary current to be analyzed of the electric field in the electrostatic precipitator comprises: Obtaining a current secondary voltage and a current secondary current of the electric field in the electrostatic precipitator, and determining the current secondary voltage and the current secondary current of the electric field as the secondary voltage and the secondary current to be analyzed of the electric field; The determining, based on the position relationship information, the abnormal state of the electric field in the electrostatic precipitator comprises: Based on the positional relationship information, a current abnormal state of the electric field in the electrostatic precipitator is determined.

5. The method according to claim 1, characterized in that The method of obtaining the secondary voltage to be analyzed and the secondary current to be analyzed of the electric field in the electrostatic precipitator comprises: Determine the volt-ampere change rate of the electric field based on the historical secondary voltage and the historical secondary current in the electric field within a set time interval, wherein the volt-ampere change rate represents the change rate of the secondary current and the secondary voltage in the electric field; Obtaining the current secondary voltage and the current secondary current of the electric field in the electrostatic precipitator at the current moment; Based on the volt-ampere change rate of the electric field, the current secondary voltage and the current secondary current, determine the future secondary voltage and the future secondary current of the electric field at a target future time, determine the future secondary voltage as the secondary voltage to be analyzed, and determine the future secondary current as the secondary current to be analyzed, and the target future time is the time reached by the target time length after the current time; The determining, based on the position relationship information, the abnormal state of the electric field in the electrostatic precipitator comprises: Based on the positional relationship information, an abnormal state of the electric field in the electrostatic precipitator at the target future time is determined.

6. The method according to any one of claims 1 to 3, characterized in that: Also includes: Based on the abnormal states of different electric fields in the electrostatic precipitator, the overall abnormal state of the electrostatic precipitator is determined.

7. The method according to claim 4, characterized in that Also includes: After determining that the electric field in the electrostatic precipitator is currently abnormal, taking the current secondary voltage and the current secondary current as an abnormal volt-ampere data pair, and detecting whether the abnormal volt-ampere data pair exists in a temporary verification library; If the abnormal volt-ampere data pair does not exist in the temporary verification library, an abnormal reminder is output, wherein the abnormal reminder is used to prompt that the electric field is abnormal, and the abnormal reminder indicates that there is an abnormal secondary voltage and an abnormal secondary current in the electric field; If a confirmation operation of the user confirming that the abnormal secondary voltage and the abnormal secondary current are a normal volt-ampere data pair is detected, the abnormal secondary voltage and the abnormal secondary current are stored in the temporary verification library.

8. An electrostatic precipitator abnormality detection device, characterized in that: include: A volt-ampere acquisition unit is used to obtain a secondary voltage to be analyzed and a secondary current to be analyzed of the electric field in the electrostatic precipitator; A normal area obtaining unit, used for obtaining a volt-ampere normal area corresponding to the electric field determined most recently, wherein the volt-ampere normal area is a coordinate area in a volt-ampere coordinate plane that characterizes that the electric field does not have an abnormality, wherein the volt-ampere coordinate plane is a coordinate plane in which the horizontal coordinate represents the secondary voltage and the vertical coordinate represents the secondary current, and the volt-ampere normal area corresponding to the electric field is determined based on the historical secondary voltage and the historical secondary current of the electric field at multiple historical moments in a historical time period before the current moment; A position relationship determination unit, used to determine position relationship information between a target coordinate point of the secondary current to be analyzed and the secondary voltage to be analyzed on the volt-ampere coordinate plane and the volt-ampere normal area; an abnormal state determining unit, configured to determine an abnormal state of the electric field in the electrostatic precipitator based on the position relationship information; The volt-ampere normal region corresponding to the electric field is obtained by the following method: Obtaining historical secondary voltages and historical secondary currents of the electric field at multiple historical moments in a historical time period before a current moment; Taking the historical secondary voltage and the historical secondary current at each historical moment as a historical coordinate point on the volt-ampere coordinate plane, based on the distribution of multiple historical coordinate points corresponding to multiple historical moments on the volt-ampere coordinate plane, determining a coordinate point distribution area where the distribution density of the historical coordinate points meets the requirements, and determining the coordinate point distribution area as a volt-ampere normal area; After determining the coordinate point distribution area as the normal volt-ampere area, the device is further used for: Determine a first boundary coordinate point set and a second boundary coordinate point set in a normal volt-ampere region, wherein the first boundary coordinate point set includes a plurality of historical coordinate points for representing a first boundary line of the normal volt-ampere region, and the second boundary coordinate point set includes a plurality of historical coordinate points for representing a second boundary line of the normal volt-ampere region, wherein the first boundary line is a boundary line in the normal volt-ampere region close to a ordinate axis of the volt-ampere coordinate plane, and the second boundary line is a boundary line in the normal volt-ampere region far from the ordinate axis; Performing data cleaning on the first boundary coordinate point set and the second boundary coordinate point set based on the Laida criterion to obtain the first boundary coordinate point set and the second boundary coordinate point set after data cleaning; Based on the first boundary coordinate point set after data cleaning, a function expression of the first boundary line is fitted using the least squares method; Based on the second boundary coordinate point set after data cleaning, the function expression of the second boundary line is fitted using the least squares method.

Images