CN116774749B - Intelligent temperature-control electric power cabinet - Google Patents
Intelligent temperature-control electric power cabinet Download PDFInfo
- Publication number
- CN116774749B CN116774749B CN202311078670.0A CN202311078670A CN116774749B CN 116774749 B CN116774749 B CN 116774749B CN 202311078670 A CN202311078670 A CN 202311078670A CN 116774749 B CN116774749 B CN 116774749B
- Authority
- CN
- China
- Prior art keywords
- value
- operation parameter
- classification
- historical data
- cabinet
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000003066 decision tree Methods 0.000 claims abstract description 25
- 230000007613 environmental effect Effects 0.000 claims abstract description 18
- 238000004458 analytical method Methods 0.000 claims abstract description 16
- 238000005192 partition Methods 0.000 claims description 29
- 238000012549 training Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000000034 method Methods 0.000 claims description 3
- 230000008878 coupling Effects 0.000 claims description 2
- 238000010168 coupling process Methods 0.000 claims description 2
- 238000005859 coupling reaction Methods 0.000 claims description 2
- 241000883990 Flabellum Species 0.000 claims 2
- 238000004891 communication Methods 0.000 claims 1
- 230000005611 electricity Effects 0.000 claims 1
- 238000001816 cooling Methods 0.000 description 6
- 230000001276 controlling effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 239000011810 insulating material Substances 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Landscapes
- Air Conditioning Control Device (AREA)
Abstract
The invention provides an intelligent temperature control electric power cabinet, creatively adopts a decision tree form to comb historical data, determines the priority order of the influence of three parameters on an environmental temperature result through comparing the information gains of the three parameters of relative humidity, motor rotating speed and condensate flow speed, and greatly reduces the operation amount. Further, the power cabinet of the invention can send field data to be fed back to the remote processor after operation, and the field data is integrated into historical data, thereby further perfecting a historical database and providing important reference for next decision analysis of the remote processor.
Description
Technical Field
The invention relates to an electric power cabinet capable of intelligently controlling temperature.
Background
The power cabinet is the last-stage device of the power distribution system. The power cabinet is a generic term for motor control centers. The power cabinet is used in the occasions with scattered load and less loops; the motor control center is used for occasions with concentrated load and more loops. They distribute the power of a circuit of the upper-level distribution equipment to nearby loads. This class of equipment should provide protection, monitoring and control of the load.
The electric components in the electric power cabinet are always in a long-time continuous running state, a large amount of heat is inevitably generated when the electric device in the electric power cabinet is operated, the heating of the electric power cabinet often has serious influence on the rubber insulating material in the electric power cabinet, the ageing of the rubber insulating material is accelerated, the insulating performance is reduced, and the phenomenon of short circuit of the internal electric components possibly caused when the electric power cabinet is seriously aged can cause accidents. Therefore, it is an urgent task to cool the power cabinet and thereby control the internal temperature of the power cabinet.
However, the control concept of the current power cabinet temperature control system is still rough. Many power cabinets only use cooling devices such as fans or condensers to cool the power cabinets, and technicians often can only judge the operation of the fans or the condensers according to experience, which results in unreasonable temperature control. Once the output of the cooling device is insufficient, the temperature is still too high, and damage is still caused to materials in the electric cabinet; and once the cooling device excessively outputs, the temperature becomes too low, and the energy consumption for cooling on the cooling device is too high, so that the service life of the cooling device is influenced, and the long-term operation of the electric cabinet is not facilitated.
Disclosure of Invention
The invention provides an intelligent temperature-control electric power cabinet which can carry out remote intelligent adjustment on the temperature in the electric power cabinet, thereby ensuring that the temperature in the electric power cabinet is in a proper range and solving the problems in the prior art.
The invention provides an intelligent temperature control electric power cabinet, wherein one or more motors are fixed on the side wall of a cabinet body of the electric power cabinet, fan blades are fixed on each motor through a coupler, each fan blade is arranged in the cabinet body, a data acquisition controller, a condenser and a humidity regulator are further arranged in the cabinet body, a temperature sensor for sensing the internal environment temperature of the cabinet body is further arranged in the cabinet body, the data acquisition controller is respectively and electrically connected to the temperature sensor, the motors, the condenser and the humidity regulator, the data acquisition controller is remotely and communicatively connected to a remote processor, the remote processor utilizes N groups of historical data to carry out analysis decision, wherein each group of historical data comprises three operation parameter values, namely a result parameter value of the internal environment temperature value of the cabinet body, a relative humidity value, a motor rotation speed value and a condensate flow speed value, and the analysis decision process is as follows: n environmental temperature values in the N groups of historical data are used as training sets to be expanded and analyzed to form a decision tree, the average value of the N environmental temperature values is K, each operating parameter value is provided with N operating parameter historical data, for each operating parameter value, the N operating parameter historical data are equally divided into three equal parts according to the interval between the maximum value and the minimum value of the N operating parameter historical data, the three classifying intervals are sequentially a low value interval, a median interval and a high value interval, the information gains of the three operating parameter values in the decision tree are respectively calculated, the three operating parameter values are sequentially arranged into a first operating parameter value, a second operating parameter value and a third operating parameter value according to the order of the information gains from large to small, the first operating parameter value is used as a root node of a decision tree to classify the N groups of historical data according to the three classifying intervals, the classifying partition of which the average value of the environmental temperature is closest to the K is recorded as a first classifying partition, the average value of all the first operating parameter values in the N1 groups of historical data in the first classifying interval is taken as a first operating parameter value which is less than or equal to 0N < 1 >; the first classification partition is classified by the second operation parameter value according to three classification partitions, the classification partition with the average value of the ambient temperature and the nearest K in the three classification partitions is recorded as the second classification partition, and the average value of all second operation parameter values in N2 groups of historical data in the second classification partition is taken as a second operation parameter output value, wherein N2 is more than 0 and less than or equal to N1; the second classification partition is classified by the third operation parameter value according to three classification partitions, the classification partition with the average value of the ambient temperature and the nearest K in the three classification partitions is marked as the third classification partition, and the average value of all third operation parameter values in N3 groups of historical data in the third classification partition is taken as a third operation parameter output value, wherein N3 is more than 0 and less than or equal to N2; the first, second and third operating parameter output values are sent to the data acquisition controller by the remote processor, thereby controlling the operation of the motor, the condenser and the humidity regulator, in which case the temperature sensor senses the latest environmental temperature value in the cabinet, which is transmitted back to the remote processor; the latest environmental temperature value, the first operation parameter output value, the second operation parameter output value and the third operation parameter output value are combined into a latest set of historical data in the remote processor, and the latest set of historical data and the N sets of historical data form updated N+1 sets of historical data together for the next analysis decision of the remote processor.
Preferably, the empirical entropy of the decision tree is calculated by the following formula:
，
wherein K represents the number of basic major classes into which the ambient temperature set itself can be divided, D represents the total number of samples of the training data set, C k For the corresponding number of samples under each basic subclass,
the calculation formula for calculating the empirical condition entropy with any one of three operation parameter values as a root node is:
，
where H (D|A) represents the empirical conditional entropy under a particular feature A of any of the three operating parameter values, di represents the number of each class under the particular feature A, dik represents the number of samples of each class under the class according to feature A,
the information gain under feature A is thus determined by subtracting the empirical condition entropy from the empirical entropy.
Preferably, if the information gain under the motor speed value classification is the largest, the information gain under the relative humidity value classification is the second, and the information gain under the condensate flow speed value classification is the smallest, the first operation parameter value is the motor speed value, the second operation parameter value is the relative humidity value, and the third operation parameter value is the condensate flow speed value.
Alternatively, n=14.
Alternatively, n1=6, n2=4, n3=2.
The invention creatively adopts the form of decision tree to comb the historical data, and determines the priority order of the influence of three parameters on the environmental temperature result by comparing the information gains of the relative humidity, the motor rotating speed and the condensate flow speed, thereby greatly reducing the operation quantity. Further, the invention sends the field data back to the remote processor after operation, and the field data is integrated into the history data, thereby further perfecting the history database and providing important reference for the next decision analysis of the remote processor.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following discussion will discuss the embodiments or the drawings required in the description of the prior art, and it is obvious that the technical solutions described in connection with the drawings are only some embodiments of the present invention, and that other embodiments and drawings thereof can be obtained according to the embodiments shown in the drawings without inventive effort for a person skilled in the art.
Fig. 1 shows a schematic diagram of the general structure of an intelligent temperature-controlled power cabinet according to the present invention.
Fig. 2 illustrates a general schematic of a decision tree based decision analysis of a remote processor of an intelligent temperature controlled power cabinet according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made in detail with reference to the accompanying drawings, wherein it is apparent that the embodiments described are only some, but not all embodiments of the present invention. All other embodiments, which can be made by a person of ordinary skill in the art without the need for inventive faculty, are within the scope of the invention, based on the embodiments described in the present invention.
The invention provides an intelligent temperature-controlled power cabinet, which is shown in figure 1. Fig. 1 shows a schematic diagram of the general structure of an intelligent temperature-controlled power cabinet according to the present invention.
In the power cabinet shown in fig. 1, one or more motors are fixed on the side wall of the cabinet body 1, each motor is fixed with a fan blade through a coupling, the fan blades are arranged in the cabinet body 1, for example, in fig. 1, two motors are arranged, a first motor 2 is fixed with a first fan blade 3, and a second motor 4 is fixed with a second fan blade 5. A temperature sensor 6 is also arranged in the cabinet body 1 and is used for sensing the ambient temperature in the cabinet body 1. In addition, one or more condensers are also provided in the cabinet 1, for example, 3 condensers 7 are provided up and down in fig. 1. Meanwhile, one or more humidity regulators 10 are further arranged in the cabinet body 1 and used for regulating the ambient humidity in the cabinet body 1. A data acquisition controller 8 is additionally arranged in the cabinet body 1, and the data acquisition controller 8 is respectively and electrically connected to a temperature sensor, a motor, a condenser and a humidity regulator. The data acquisition controller 8 is remotely communicatively connected to a remote processor 9.
In operation, if it is desired to regulate the ambient temperature within the cabinet 1, the remote processor 9 remotely sends an operating command to the data acquisition controller 8, the data acquisition controller 8 sends a rotational speed parameter in the operating command to the motor and starts the motor, a condensate flow speed parameter in the operating command to the condenser and starts the condenser, and a humidity regulation parameter in the operating command to the humidity regulator and starts the humidity regulator.
The ambient temperature in the cabinet 1 is closely related to the fan rotation speed, the condensate flow speed and the ambient humidity, so that the ambient temperature in the cabinet 1 can be effectively controlled within a reasonable range by controlling the motor rotation speed for controlling the fan rotation speed (thereby determining the fan rotation speed), the condensate flow speed parameter in the condenser and the humidity regulated by the humidity regulator.
The remote processor 9 of the invention uses the historical data analysis and the decision tree to determine the decision sequence of the parameters, and determines the specific values of the related parameters on the basis of the decision sequence so as to send the specific values to the data acquisition controller 8 to control the related components according to the specific values of the related parameters to adjust the environmental temperature in the cabinet 1.
The relevant history data is for example as follows:
| sequence number | Ambient temperature (. Degree. C.) | Relative humidity (% RH) | Motor rotation speed (rotating/separating) | Condensate flow rate (m/s) |
| 1 | 19.2 | 67.3 | 494 | 0.87 |
| 2 | 19.3 | 67.2 | 492 | 0.84 |
| 3 | 19.3 | 66.8 | 490 | 0.56 |
| 4 | 19.6 | 66.6 | 489 | 0.77 |
| 5 | 20.0 | 66.6 | 489 | 0.56 |
| 6 | 20.3 | 66.5 | 488 | 0.67 |
| 7 | 20.4 | 66.4 | 488 | 0.54 |
| 8 | 20.5 | 66.4 | 487 | 0.52 |
| 9 | 20.7 | 66.2 | 486 | 0.65 |
| 10 | 20.9 | 65.8 | 485 | 0.67 |
| 11 | 21.2 | 65.4 | 485 | 0.74 |
| 12 | 21.4 | 65.3 | 483 | 0.56 |
| 13 | 21.5 | 65.2 | 483 | 0.60 |
| 14 | 21.6 | 65.0 | 481 | 0.75 |
It should be noted that during actual operation, due to the long-term use of the power cabinet, thousands of sets of data may be collected for analysis by the remote processor 9, so that a more comprehensive analysis result may be obtained, and only 14 sets of data are provided in the table, which is purely for convenience of description and space saving.
In the analysis process of the remote processor 9, the collected environmental temperature in all groups of history data is equally divided into three equal parts, namely a low temperature zone, a proper temperature zone and a high temperature zone, between the highest value and the lowest value of the collected environmental temperature.
For example, in the 14 sets of data, the highest value of the ambient temperature is 21.6 ℃, the lowest value is 19.2 ℃, the average of the temperature is three equal parts between the highest value and the lowest value, the low temperature interval is [19.2 ℃,20.0 ℃, the moderate temperature interval is [20.0 ℃,20.8 ℃) and the high temperature interval is [20.8 ℃,21.6 ℃.
Therefore, the historical data are respectively classified into a low temperature zone, a proper temperature zone and a high temperature zone according to different environmental temperatures. For example, the data set in table 14 includes 4 data sets included in the low temperature range, 5 data sets included in the moderate temperature range, and 5 data sets included in the high temperature range.
Based on which a decision tree can be constructed. And constructing a decision tree by taking the environmental temperature data as a training data set and the relative humidity, the motor rotating speed and the condensate flow rate as a characteristic set.
Firstly, calculating the empirical entropy of the decision tree, wherein the formula is as follows:
，
wherein K represents the number of basic major classes into which the ambient temperature set itself can be divided, D represents the total number of samples of the training data set, C k For each basic subclass, a corresponding number of samples.
In the example of the above list, the set of environmental temperatures is divided into three basic major classes of high temperature, moderate temperature and low temperature, so k=3, the total number of samples of the training data set is 14, so d=14, and the corresponding number of samples under each basic major class is 4, 4 and 5, respectively, so that the empirical entropy is H (D) =1.563.
Next, the relative humidity in the list is equally divided into three sections between its highest and lowest values, respectively into a high humidity section, a medium humidity section, and a low humidity section. For example, in the above table, the high humidity interval is [67.3,66.5 ], the medium humidity interval is [66.5,65.7), and the low humidity interval is [65.7,65.0].
The number of samples in the high humidity zone is 5, wherein 4 samples are in the low temperature zone, and 1 sample is in the temperature-adaptive zone; the number of samples in the medium humidity zone is 5, the 4 samples are in the temperature-adaptive zone, and the 1 sample is in the high temperature zone; the number of samples in the low humidity zone is 4, and these 4 samples are in the high temperature zone.
Whereas the empirical condition entropy is calculated with a specific feature a as the root node, the formula is as follows:
，
where H (D|A) represents the entropy of the empirical condition under a particular feature, di represents the number of each class under a particular feature A and Dik represents the number of samples of each class under a class according to feature A in the right of the equation ultimately presented.
Specifically, to describe the specific feature a as the relative humidity in the above example, d=14, d1=5, d2=5, d3=4, and accordingly, the empirical condition entropy at the relative humidity can be found to be 0.515. Thus, with relative humidity as a specific feature a, the information gain is 1.563-0.515=1.048.
If the motor rotation speed is taken as the specific characteristic a, the above formula can be also carried into, and the empirical condition entropy at the motor rotation speed is found to be 0.432, thereby taking the motor rotation speed as the specific characteristic a, the information gain is 1.563-0.432=1.131.
If the condensate flow rate is taken as the specific feature a, the above formula can be also carried into, and the empirical condition entropy at the condensate flow rate is found to be 1.275, thereby taking the condensate flow rate as the specific feature a, the information gain is 1.563-1.275=0.288.
From the above examples, it can be seen that from the point of view of information gain, the information gain obtained with the motor speed as the root node is the largest, the relative humidity is the second most, and the condensate flow rate is the least.
In other words, the change in motor speed most reflects the change in ambient temperature, the relative humidity is the second most, and the condensate flow rate is the least.
Thus, in constructing the decision tree, motor speed is selected as a characteristic of the decision tree root node, followed by relative humidity as an intermediate node and condensate flow rate as a leaf node, thereby forming the decision tree example shown in FIG. 2.
In the decision tree shown in fig. 2, with all the historical data as training sets, three classes, namely, a high-speed interval class, a medium-speed interval class and a low-speed interval class, are formed under the distinction of the root node 'motor rotation speed'.
Then, the ambient temperature in the history data of all the above groups is averaged by T. In the example, the ambient temperature average t=20.4 ℃ for 14 sets of historical data is taken. In the decision tree, the high-speed class includes the first three sets of data, the average value of the ambient temperature of the high-speed class is 19.3 ℃, the average value of the ambient temperature of the medium-speed class is 20.3 ℃, and the average value of the ambient temperature of the low-speed class is 21.1 ℃. As can be seen, the average value of the ambient temperature of the medium speed class is closest to the average value of the ambient temperature of the history data, and therefore, the average value of the rotational speed of the medium speed class is selected as the output value of the rotational speed of the motor of the remote processor 9.
Next, each set of historical data of the medium speed class is selected to be classified into a decision tree by relative humidity. In the decision tree of fig. 2, there are 6 sets of medium speed class history data, wherein 2 sets are in the high humidity interval and the other 4 sets are in the medium humidity interval. The average ambient temperature of the 4 sets of historical data in the medium humidity interval was calculated to be closer to the average of the ambient temperatures of all 14 sets than those 2 sets in the high humidity interval. Thus, the humidity average of these 4 sets of history data in the medium humidity interval is selected as the output value of the relative humidity of the remote processor 9.
It should be noted that in practice, the history data of the medium speed class is also generally divided into three kinds of intervals, i.e. a high humidity interval, a medium humidity interval, and a low humidity interval under the decision class classification of the relative humidity. Since the number of samples is limited in this example, the low humidity interval is not mentioned above, but does not indicate that the low humidity interval does not exist, and the low humidity interval may be counted as 0 sets of history data.
The 4 groups of historical data in the medium humidity interval are classified by a decision tree according to condensate flow velocity. Under classification, where 2 groups are in the medium flow interval and the other 2 groups are in the low flow interval, the average ambient temperature value of the 2 groups in the low flow interval is closer to the average value of the ambient temperature of the 14 sets of history data than the 2 groups in the medium flow interval, and therefore, the flow velocity average value of the two groups is selected as the output value of the condensate flow velocity of the remote processor 9.
Similarly as described above, the high flow rate interval is also referred to herein as 0 sets of history data, limited by the number of history data in this example, and thus the preceding paragraph is not mentioned, but does not indicate that the high flow rate interval does not exist, and the high flow rate interval may be referred to herein as 0 sets of history data.
Thus, through the decision tree assistance, the remote processor 9 derives the output values of the relative humidity, the motor rotation speed and the condensate flow rate according to the 14 sets of historical data, and the three output values are remotely sent to the data acquisition controller 8 in the cabinet 1 by the remote processor 9. The data acquisition controller 8 controls the operations of the humidity regulator 10, the motor and the condenser 7 based on the relative humidity output value, the motor rotation speed output value and the condensate flow speed output value, respectively, so as to regulate the ambient temperature in the cabinet 1.
In this case, the temperature sensor 6 will sense the latest temperature in the cabinet 1, and the latest temperature, together with the humidity output value, the motor rotation speed output value, and the condensate flow speed output value, will be collected by the data collection controller 8 to form a new set of history data, and the new set of history data is transmitted back to the remote processor 9, and combined with the original history data to form the latest history database for the next analysis processing by the remote processor 9.
For example, in the above example, 14 sets of history data originally exist, and 15 sets of history data will be formed after a new set of history data is formed and fed back to the remote processor 9. Then the next analysis decision by the remote processor 9 will be made based on these 15 sets of historical data.
The present invention has been described herein in general terms. It should be noted that the above examples are not meant to limit the invention. In particular, the gain factor of the motor rotation speed is determined to be maximum by the list data in the above example. However, in practice, it is entirely possible that the gain factor of other parameter characteristics is maximized, such as relative humidity. Moreover, only 14 sets of data are listed in the example, in practice, the historical data would be well above 1000 sets or even 10000 sets of data due to the inevitably long time frequent operation of the power cabinet. The description of the present invention enumerates only 14 sets of data, which is convenient for reasons of space and description only.
In the face of the potentially so much historical data, the invention creatively adopts a decision tree form to comb the historical data, and determines the priority order of the influence of three parameters on the environmental temperature result by comparing the information gains of the relative humidity, the motor rotating speed and the condensate flow speed, thereby greatly reducing the operation amount. Further, the invention sends the field data back to the remote processor after operation, and the field data is integrated into the history data, thereby further perfecting the history database and providing important reference for the next decision analysis of the remote processor.
The foregoing description of the exemplary embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any modifications, equivalents, and variations which fall within the spirit and scope of the invention are intended to be included in the scope of the invention.
Claims (4)
1. The utility model provides an intelligent temperature control's electric power cabinet, its characterized in that is fixed with one or more motors on the lateral wall of the cabinet body of electric power cabinet, every motor is fixed with the flabellum through the shaft coupling, the flabellum sets up in the cabinet body, the cabinet is internal still to set up data acquisition controller, the condenser, humidity control ware, the cabinet is internal still to set up the temperature sensor that is used for the internal ambient temperature of response cabinet, data acquisition controller is connected to temperature sensor respectively electricity, the motor, the condenser, the humidity control ware, data acquisition controller remote communication is connected to remote processor, remote processor utilizes N historical data of group to carry out analysis decision, wherein, all include this result parameter value of internal ambient temperature value of cabinet and relative humidity value, motor rotational speed value, the three kind of operating parameter value of condensate velocity value in each historical data, analysis decision's process is as follows:
n environmental temperature values in the N groups of historical data are used as training sets to develop decision tree analysis, the average value of the N environmental temperature values is M, each operation parameter value has N operation parameter historical data, for each operation parameter value, the N operation parameter historical data are equally divided into three equal parts according to the interval between the maximum value and the minimum value of the N operation parameter historical data, and the three classification intervals are sequentially a low value interval, a median interval and a high value interval,
respectively calculating the information gains of the three operation parameter values under the decision tree, wherein the three operation parameter values are sequentially arranged into a first operation parameter value, a second operation parameter value and a third operation parameter value according to the order of the information gains from big to small,
the first operation parameter value is used as a root node of the decision tree to classify the N groups of historical data according to three classification intervals, a classification partition with the average value of the ambient temperature closest to M in the three classification intervals is recorded as a first classification partition, and the average value of all the first operation parameter values in the N1 groups of historical data in the first classification partition is taken as a first operation parameter output value, wherein N is greater than 0 and less than or equal to N;
the first classification partition is classified by the second operation parameter value according to three classification partitions, the classification partition with the average value of the ambient temperature and M closest to the first classification partition is recorded as the second classification partition, and the average value of all second operation parameter values in N2 groups of historical data in the second classification partition is taken as a second operation parameter output value, wherein N2 is greater than 0 and less than or equal to N1;
the second classification partition is classified by the third operation parameter value according to three classification partitions, the classification partition with the average value of the ambient temperature and M closest to the average value of the ambient temperature in the three classification partitions is recorded as the third classification partition, and the average value of all third operation parameter values in N3 groups of historical data in the third classification partition is taken as a third operation parameter output value, wherein N3 is greater than 0 and less than or equal to N2;
the first, second and third operating parameter output values are sent to the data acquisition controller by the remote processor, thereby controlling the operation of the motor, the condenser and the humidity regulator, in which case the temperature sensor senses the latest environmental temperature value in the cabinet, which is transmitted back to the remote processor;
the latest environmental temperature value and the first, second and third operation parameter output values together form a latest set of historical data in the remote processor, the latest set of historical data and the N sets of historical data together form updated N+1 sets of historical data for the next analysis decision of the remote processor,
the calculation formula of the empirical entropy of the decision tree is as follows:
，
wherein K represents the number of basic major classes into which the ambient temperature set itself can be divided, D represents the total number of samples of the training data set, C k For the corresponding number of samples under each basic subclass,
the calculation formula for calculating the empirical condition entropy with any one of three operation parameter values as a root node is:
，
where H (D|A) represents the empirical conditional entropy under a particular feature A of any of the three operating parameter values, di represents the number of each class under the particular feature A, dik represents the number of samples of each class under the class according to feature A,
the information gain under feature A is thus determined by subtracting the empirical condition entropy from the empirical entropy.
2. The power cabinet of claim 1, wherein the first operating parameter value is a motor speed value, the second operating parameter value is a relative humidity value, and the third operating parameter value is a condensate flow rate value if the information gain under the motor speed value classification is greatest, the information gain under the relative humidity value classification is inferior, and the information gain under the condensate flow rate value classification is smallest.
3. The power cabinet of claim 1, wherein N = 14.
4. A power cabinet according to claim 3, characterized in that n1=6, n2=4, n3=2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311078670.0A CN116774749B (en) | 2023-08-25 | 2023-08-25 | Intelligent temperature-control electric power cabinet |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311078670.0A CN116774749B (en) | 2023-08-25 | 2023-08-25 | Intelligent temperature-control electric power cabinet |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116774749A CN116774749A (en) | 2023-09-19 |
| CN116774749B true CN116774749B (en) | 2023-11-03 |
Family
ID=87989974
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311078670.0A Active CN116774749B (en) | 2023-08-25 | 2023-08-25 | Intelligent temperature-control electric power cabinet |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116774749B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105956935A (en) * | 2016-05-06 | 2016-09-21 | 泉州亿兴电力有限公司 | Distribution network transformer threshold updating method and system |
| CN107734931A (en) * | 2017-10-27 | 2018-02-23 | 国家电网公司 | Electrical equipment component cabinet with accurate temperature control and independent humidity control function |
| CN208077035U (en) * | 2017-11-30 | 2018-11-09 | 中茵电力科技（苏州）有限公司 | A kind of transformation cabinet |
| CN108966448A (en) * | 2018-05-31 | 2018-12-07 | 淮阴工学院 | A kind of light dynamic regulation method based on adaptive fuzzy decision tree |
| CN111256428A (en) * | 2020-01-20 | 2020-06-09 | 连云港韬惠实业有限公司 | Self-adaptive fuzzy control method for temperature of refrigeration house |
| CN111649465A (en) * | 2020-06-05 | 2020-09-11 | 哈尔滨工业大学 | Automatic control method and system for air conditioning equipment |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090125155A1 (en) * | 2007-11-08 | 2009-05-14 | Thomas Hill | Method and System for Optimizing Industrial Furnaces (Boilers) through the Application of Recursive Partitioning (Decision Tree) and Similar Algorithms Applied to Historical Operational and Performance Data |
| US9200591B2 (en) * | 2011-07-06 | 2015-12-01 | Honeywell International Inc. | Automatic identification of operating parameters for power plants |
| US10825113B2 (en) * | 2018-03-16 | 2020-11-03 | Dalian University Of Technology | Method for short-term generation scheduling of cascade hydropower plants coupling cluster analysis and decision tree |
-
2023
- 2023-08-25 CN CN202311078670.0A patent/CN116774749B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105956935A (en) * | 2016-05-06 | 2016-09-21 | 泉州亿兴电力有限公司 | Distribution network transformer threshold updating method and system |
| CN107734931A (en) * | 2017-10-27 | 2018-02-23 | 国家电网公司 | Electrical equipment component cabinet with accurate temperature control and independent humidity control function |
| CN208077035U (en) * | 2017-11-30 | 2018-11-09 | 中茵电力科技（苏州）有限公司 | A kind of transformation cabinet |
| CN108966448A (en) * | 2018-05-31 | 2018-12-07 | 淮阴工学院 | A kind of light dynamic regulation method based on adaptive fuzzy decision tree |
| CN111256428A (en) * | 2020-01-20 | 2020-06-09 | 连云港韬惠实业有限公司 | Self-adaptive fuzzy control method for temperature of refrigeration house |
| CN111649465A (en) * | 2020-06-05 | 2020-09-11 | 哈尔滨工业大学 | Automatic control method and system for air conditioning equipment |
Non-Patent Citations (1)
| Title |
|---|
| 随机森林算法应用于锅炉燃料量预测的参数设定;蔡佳成;沈学强;;数字技术与应用(第02期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116774749A (en) | 2023-09-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109800066B (en) | Energy-saving scheduling method and system for data center | |
| CN108317670B (en) | Refrigeration system energy-saving control method and system based on machine learning | |
| CN111897261B (en) | Comprehensive management system and method for data center machine room environment | |
| CN105843189B (en) | A kind of efficient scheduling rule selection method for semiconductor production line based on simplified simulation model | |
| CN108105969B (en) | Intelligent air conditioner monitoring system and abnormal air conditioner operation efficiency detection method | |
| CN104121666A (en) | Hourly frequency conversion air supplying system and control method for central air conditioning ventilation system | |
| CN107143981B (en) | A kind of controlling system of central air conditioner and method | |
| CN115789856A (en) | On-line monitoring control system for ventilation equipment | |
| CN115498313A (en) | Abnormity early warning method for air-cooled lithium ion battery energy storage container thermal management system | |
| CN106969477A (en) | Air conditioning control method and air-conditioner controller | |
| CN114727570B (en) | Refrigerating unit water temperature adjusting method based on temperature change relation | |
| CN206771651U (en) | Air-conditioner controller and air-conditioner control system | |
| CN115843170A (en) | Energy-saving control system for air conditioner in machine room | |
| CN112070353A (en) | Method and system for accurately detecting energy efficiency of data center | |
| CN111306728A (en) | Air volume regulating and controlling method and device for air conditioning system and computer equipment | |
| EP4033169B1 (en) | Air-conditioning control device, air-conditioning system, air-conditioning control method, and air-conditioning control program | |
| CN113883698A (en) | Air conditioning system refrigeration station starting strategy optimization method and system and electronic equipment | |
| CN116774749B (en) | Intelligent temperature-control electric power cabinet | |
| CN115327930B (en) | Visual energy-saving control method and system | |
| CN203928297U (en) | For central air-conditioning wind system by time frequency conversion air feed system | |
| CN108917090B (en) | Performance test method for air conditioning unit | |
| CN110568257A (en) | continuous monitoring method and device for energy consumption of air conditioner | |
| CN112797017B (en) | Energy-saving space estimation method for energy-saving reconstruction of cooling circulating water | |
| CN115907138A (en) | Method, system and medium for predicting PUE value of data center | |
| CN112781181B (en) | Energy-saving control method and device for air conditioner group |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |