CN115962551A - Intelligent air conditioner control system and method for building automatic control - Google Patents
Intelligent air conditioner control system and method for building automatic control Download PDFInfo
- Publication number
- CN115962551A CN115962551A CN202310253244.XA CN202310253244A CN115962551A CN 115962551 A CN115962551 A CN 115962551A CN 202310253244 A CN202310253244 A CN 202310253244A CN 115962551 A CN115962551 A CN 115962551A
- Authority
- CN
- China
- Prior art keywords
- data
- day
- segment
- temperature
- current
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000008859 change Effects 0.000 claims abstract description 57
- 230000007774 longterm Effects 0.000 claims abstract description 45
- 238000012937 correction Methods 0.000 claims abstract description 33
- 238000004378 air conditioning Methods 0.000 claims abstract description 31
- 230000011218 segmentation Effects 0.000 claims description 22
- 238000010606 normalization Methods 0.000 claims description 6
- 230000003044 adaptive effect Effects 0.000 claims description 4
- 238000000354 decomposition reaction Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 4
- 230000008569 process Effects 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000005070 sampling Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000005265 energy consumption Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000009699 differential effect Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000009423 ventilation Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B30/00—Energy efficient heating, ventilation or air conditioning [HVAC]
- Y02B30/70—Efficient control or regulation technologies, e.g. for control of refrigerant flow, motor or heating
Landscapes
- Air Conditioning Control Device (AREA)
Abstract
The invention relates to the field of self-adaptive control systems, and provides an intelligent air conditioner control system and method for building automatic control, which comprises the following steps: collecting the data of the current day and historical data; time interval division is carried out on the historical data and the current day data, and the current day data and a plurality of reference data of each time interval are obtained; segmenting the data of the current day and the reference data according to data change, and acquiring the comprehensive similarity degree of the data of the current day of each segment and each reference data of the affiliated time period; according to the long-term distribution parameters of each segment of the comprehensive similarity degree, the short-term distribution parameters of each segment are obtained according to the long-term distribution parameters, the correction characteristic parameters of each segment are obtained, and the temperature prediction value is obtained; and setting a fuzzy rule according to the temperature predicted value and the temperature data at the current moment, and realizing the accurate control of the air conditioning system. The invention aims to solve the problem of poor control effect of an air conditioning system caused by hysteresis of temperature change and interference of a human flow factor.
Description
Technical Field
The invention relates to the field of self-adaptive control systems, in particular to an intelligent air conditioner control system and method for building automatic control.
Background
With the continuous development of economy and the improvement of the living standard of people, the intelligent building industry is rapidly developed and is a combination of the building industry, the automation industry, the computer industry and the network technology industry; the Building Automation System (BAS) is a main functional subsystem and comprises an air conditioning system, a ventilation system, a water supply and drainage system, a lighting system and the like, wherein the air conditioning system can cause unbalanced power supply and demand due to the influence on energy consumption, so that the air conditioning system in the building automation system is intelligently controlled, and the problem of energy consumption can be greatly relieved.
In the prior art, a fuzzy PID is generally adopted to control an air conditioning system, fuzzy PID control combines a fuzzy theory and a PID control algorithm, and a fuzzy rule is utilized to set PID parameters; the time lag characteristic exists in the indoor temperature change, and meanwhile, the indoor temperature change is interfered by factors such as the flow of people, and the like, so that the effect of the air conditioning system is poor in the control process; if a traditional fuzzy PID control algorithm is used to obtain PID parameters and further obtain the control quantity of the air conditioner parameters, the control quantity value which is wrong at the current moment can be obtained due to the hysteresis of temperature change and the corresponding people flow change; therefore, the change characteristics of the temperature data and the corresponding people flow change characteristics in the time period of the current time are required to be quantified, the characteristics of the current time in the input data of the traditional fuzzy PID are replaced by the characteristics of the current time period, and a more accurate predicted value of the current time period is obtained by combining a data prediction algorithm, so that the accurate control of the air conditioning system is realized.
Disclosure of Invention
The invention provides an intelligent air-conditioning control system and method for building automatic control, which aim to solve the problem that the control effect of an air-conditioning system is poor due to the hysteresis of the existing temperature change and the interference of a human flow factor, and adopts the following technical scheme:
in a first aspect, an embodiment of the present invention provides an intelligent air conditioner control method for building automatic control, including the following steps:
acquiring the current day temperature data and the current day pedestrian volume data in the current day data, and acquiring historical temperature data and historical pedestrian volume data in a plurality of calendar history data;
time interval division is carried out on the historical data and the current day data, and the current day data and a plurality of reference data of each time interval in the current day data are obtained;
acquiring the temperature data of the current day in the data of the current day in each time period and reference temperature data in the reference data, acquiring the segmentation time in the temperature data of the current day in each time period and the segmentation time in the reference temperature data according to the data change of adjacent times in the temperature data of the current day or the reference temperature data, segmenting the data of the current day according to the segmentation time in the temperature data of the current day in each time period to obtain a plurality of segmented data of the current day, and segmenting the reference data according to the segmentation time in each reference temperature data in each time period to obtain a plurality of segmented reference data;
acquiring the comprehensive similarity degree of the current data of each segment and the reference data of each reference data of the affiliated period according to the similarity of the current data of each segment and the reference data of different segments in the reference data of the affiliated period;
acquiring control parameters according to the temperature predicted value and the temperature data at the current moment, setting a basic domain and membership function of the control parameters, fuzzifying the control parameters, setting a PID parameter adaptive fuzzy rule and defuzzifying the control parameters to obtain an output value of a PID controller, and combining with air conditioner operation data to realize accurate control of an air conditioner system;
and setting a fuzzy rule according to the predicted temperature value and the temperature data at the current moment, so as to realize the accurate control of the air conditioning system.
Optionally, the acquiring the data of the current day and the plurality of reference data of each time period in the data of the current day includes a specific method that:
acquiring a plurality of day reference data of the current day data according to the distribution of the current day data and the historical data of each day in each week; dividing the data of the current day and the plurality of day reference data by preset time intervals to obtain the data of the current day of each time interval in the data of the current day, and taking the reference data of the same time interval in the reference data as the reference data of each time interval in the data of the current day to obtain the plurality of reference data of each time interval in the data of the current day.
Optionally, the obtaining of the segment time in the current-day temperature data and the segment time in the reference temperature data in each time interval includes a specific method that:
acquiring the current-day temperature data or reference temperature data of any time period as target temperature data, acquiring a target temperature curve of the target temperature data, and recording a trend term obtained by time series decomposition of the target temperature curve as a target temperature trend line;
and taking the ratio of the difference of the trend item data of the adjacent moments in the target temperature trend line to the time interval of the adjacent moments as the temperature change degree of the later moment in the adjacent moments, acquiring the temperature change degree of each moment in the target temperature trend line, carrying out linear normalization on the absolute values of all the temperature change degrees, recording the obtained result as the temperature change rate of each moment, and taking the moment when the temperature change rate is greater than a first preset threshold value as the segmentation moment of the target temperature data.
Optionally, the obtaining of the comprehensive similarity between the current-day data of each segment and each reference data of the affiliated period includes a specific method that:
get the firstIs at the ^ th or greater in a time interval>The present-day temperature profile of the individual section, corresponding to the ^ th ^ temperature>Gets the ^ th or ^ th on the day temperature trend line of the time period>The temperature trend line of the day of each segment is acquired>A reference temperature trend line for each segment of the plurality of reference temperature data for the time period;
get the firstIs at the ^ th or greater in a time interval>The temperature trend line of the day of each segment, and ^ h>A number of time periods>The DTW distance between the reference temperature trend lines of each segment in the reference temperature data takes the minimum value of all the DTW distances as the ^ th ^ or>Is at the ^ th or greater in a time interval>Present day temperature data and/or +for a segment>The first similar distance of the reference temperature data is expressed as, wherein />Indicates the fifth->Is at the ^ th or greater in a time interval>A segmented temperature profile line for the day>Indicates the corresponding fifth/fifth value of the DTW distance minimum>On a number of occasions>A segmented reference temperature trend line in the reference temperature data; will be provided withIs recorded as the second->Is at the ^ th or greater in a time interval>The present-day temperature data and the ^ th->A first degree of similarity of individual reference temperature data, wherein->Expressing an exponential function with a natural constant as a base;
the method comprises the steps of obtaining a first similarity degree of the temperature data of each segment on the day and each reference data of the period to which the temperature data of each segment belongs, obtaining a second similarity degree of the people flow data of each segment on the day and each reference data of the period to which the people flow data of each segment belongs, and taking the root of the square sum of the first similarity degree and the second similarity degree as the comprehensive similarity degree of the data of each segment on the day and each reference data of the period to which the people flow data of each segment belongs.
Optionally, the obtaining of the long-term distribution parameter of each segment in the current day data according to the comprehensive similarity degree includes a specific method that:
wherein ,indicates the fifth->The ^ th or ^ th of the segmented data point>Local reachable density under distance neighborhood>Is shown asA fifth of the segmented data points>Number of reference data points in distance neighborhood, <' >>Indicates the fifth->The ^ th or ^ th of the segmented data point>The ^ th or greater in the distance neighborhood>A reference data point, <' > based on the number of data points in the database>Indicates the fifth->Segmented data point and ^ th->The overall degree of similarity of the individual reference data points,indicates the fifth->Multiple reference data points at the fifth>The ^ th or ^ th of the segmented data point>Local reachable density under distance neighborhood>Indicates the fifth->A fifth of the segmented data points>Local outlier factors under the distance neighborhood;
will be firstThe ^ th or ^ th of the segmented data point>Local outlier factor under distance neighborhood as the ^ h->Long-term distribution parameters of individual segments.
Optionally, the obtaining of the short-term distribution parameter of each segment in the current day data according to the long-term distribution parameter includes the specific method that:
wherein ,indicates the ^ th or greater in the data of the current day>Short-term profile parameters of a segment, based on the number of segments in the segment, are selected>Indicates the ^ th or greater in the data of the current day>The number of other segments before a segment, based on the number of preceding segments>Indicates the ^ th or greater in the data of the current day>A number of other sections and a ^ th->A time interval of segments, said time interval being obtained by a difference of a first time of a subsequent segment and a last time of a preceding segment,indicates the ^ th or greater in the data of the current day>Long term profile parameters for several other segments>Represents a sign function>An exponential function with a natural constant as the base is shown.
Optionally, the obtaining of the correction characteristic parameter of each segment in the current day data according to the short-term distribution parameter by correcting the long-term distribution parameter includes the following specific steps:
wherein ,indicating a th in the data of the day>Correction characteristic parameter for a segment>Indicates the ^ th or greater in the data of the current day>Short-term profile parameters of a segment, based on the number of segments in the segment, are selected>Data of the dayIs/are>Long-term distribution parameters of individual segments.
In a second aspect, another embodiment of the present invention provides an intelligent air conditioner control system for building automatic control, the system including:
the data acquisition module is used for acquiring the temperature data and the flow data of the current day in the current day data and acquiring historical temperature data and historical flow data in a plurality of calendar history data;
a control parameter correction module: time interval division is carried out on the historical data and the current day data, and current day data and a plurality of reference data of each time interval in the current day data are obtained;
acquiring the current-day temperature data in the current-day data of each time interval and reference temperature data in the reference data, acquiring the segmentation time in the current-day temperature data of each time interval and the segmentation time in the reference temperature data according to the data change of adjacent time in the current-day temperature data or the reference temperature data, segmenting the current-day data according to the segmentation time in the current-day temperature data of each time interval to obtain a plurality of segmented current-day data, and segmenting the reference data according to the segmentation time in each reference temperature data of each time interval to obtain a plurality of segmented reference data;
acquiring the comprehensive similarity degree of the current data of each segment and the reference data of each reference data of the affiliated period according to the similarity of the current data of each segment and the reference data of different segments in the reference data of the affiliated period;
acquiring a long-term distribution parameter of each segment in the current day data according to the comprehensive similarity degree, acquiring a short-term distribution parameter of each segment in the current day data according to the long-term distribution parameter, correcting the long-term distribution parameter according to the short-term distribution parameter to acquire a correction characteristic parameter of each segment in the current day data, acquiring a temperature predicted value according to the correction characteristic parameter, and acquiring a control parameter according to the temperature predicted value and the temperature data at the current moment;
the control parameter fuzzification module is used for setting a basic domain and membership function of the control parameters and fuzzifying the control parameters;
the fuzzy rule setting module is used for setting a PID parameter self-adaptive fuzzy rule;
the PID parameter defuzzification module is used for defuzzifying the defuzzified control parameters through a fuzzy rule and a membership function to obtain an output value of the PID controller;
and the PID control module is used for combining air conditioner operation data according to the output value of the PID controller to realize accurate control of the air conditioning system.
The beneficial effects of the invention are: the method comprises the steps of substituting the characteristics of the current segment in the input data of the traditional fuzzy PID by the characteristics of the current segment by quantizing the temperature data change characteristics of the segment to which the current time belongs and the corresponding pedestrian volume change characteristics, combining a data prediction algorithm, and obtaining correction characteristic parameters according to the short-term distribution parameters of the data in the segment to which the current time belongs and the long-term distribution parameters obtained in the comparison process with historical data so as to obtain the temperature predicted value which is more accurate to the current time.
In the process of acquiring the correction characteristic parameters, a self-adaptive LOF local anomaly detection algorithm is adopted, and the acquired long-term distribution parameters are corrected under the condition that long-term data distribution characteristics in current segmented data and short-term data distribution characteristics of data on the same day are considered, so that the calculated correction characteristic parameters are more accurate; the problem of abnormal local abnormal factors caused by the hysteresis characteristic of temperature change and the accumulation process of the human flow when the local abnormal factors of the current segment are calculated is solved; the temperature value of the current segment obtained by prediction is more accurate, and further, when the PID parameters are obtained in the fuzzy PID control process, the problem that the wrong PID parameters are obtained due to temperature hysteresis and interference of factors such as people flow and the like is solved, and more accurate control can be realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a block diagram of an intelligent air conditioner control system for building automatic control according to an embodiment of the present invention;
fig. 2 is a flowchart of an intelligent air conditioner control method for building automatic control according to another embodiment of the present invention;
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a block diagram of an intelligent air conditioner control system for building automatic control according to an embodiment of the present invention is shown, where the system includes:
the existing fuzzy PID control combines a fuzzy theory and a PID control algorithm, and a PID parameter is set by using a fuzzy rule; the time lag characteristic exists in the indoor temperature change, and meanwhile, the indoor temperature change is interfered by factors such as the flow of people, and the like, so that the effect of the air conditioning system is poor in the control process; if the traditional fuzzy PID control algorithm is used for obtaining the PID parameters so as to obtain the control quantity of the air conditioner parameters, the control quantity value which is wrong at the current moment can be obtained due to the hysteresis of the temperature change and the corresponding people flow change; therefore, the change characteristics of the temperature data in the time period of the current time and the corresponding people flow change characteristics need to be quantized, so that the characteristics of the current time in the traditional control parameters of the fuzzy PID are replaced by the characteristics of the current time period, and then the more accurate control quantity of the current time period is obtained, and the accurate control of the air conditioning system is realized.
And the data acquisition module S101 is used for acquiring air conditioner operation data and acquiring temperature data and people flow data of the current day and history.
The control parameter correction module S102:
(1) Time interval division is carried out on the historical data and the current day data, and the current day data and a plurality of reference data of each time interval in the current day data are obtained;
(2) Segmenting the data of the current day and the reference data according to the change between the data, and acquiring the comprehensive similarity degree of the data of the current day of each segment and each reference data of the affiliated time period;
(3) The method comprises the steps of obtaining a long-term distribution parameter of each segment in the current day data according to the comprehensive similarity degree, obtaining a short-term distribution parameter of each segment in the current day data according to the long-term distribution parameter, obtaining a correction characteristic parameter of each segment in the current day data according to the short-term distribution parameter and the long-term distribution parameter, obtaining a temperature predicted value according to the correction characteristic parameter, and correcting a control parameter of the fuzzy PID according to the temperature predicted value.
And the control parameter fuzzification module S103 is used for setting the basic domain and membership function of the control parameters and fuzzifying the control parameters.
And a fuzzy rule setting module S104 for setting PID parameter adaptive fuzzy rules.
And the PID parameter defuzzifying module S105 defuzzifies the defuzzified control parameters through the fuzzy rule and the membership function to obtain the output value of the PID controller.
And the PID control module S106 is used for realizing accurate control of the air conditioning system by combining the air conditioning operation data according to the output value of the PID controller.
Referring to fig. 2, a flowchart of an intelligent air conditioner control method for building automatic control according to another embodiment of the present invention is shown, where the method includes the following steps:
step S201, collecting air conditioner operation data, and collecting temperature data and people flow data of the current day and history.
The purpose of this embodiment is to realize the accurate control to the air conditioning system, therefore need gather the air conditioning operation data at first, through arranging temperature sensor, humidity transducer, pressure sensor, ultrasonic flowmeter and power sensor in the air conditioning system, realize the collection to the air conditioning operation data; the types of the sensor and the detecting instrument are not limited in this embodiment, and the sampling time interval is 1 minute in this embodiment, so that the air conditioner operation data is obtained.
Furthermore, the purpose of controlling the air conditioner is to adjust the indoor temperature, and meanwhile, the indoor temperature is greatly influenced by the change of the flow of people in the building, so that temperature data and the flow of people need to be collected, wherein the temperature data are collected by installing a temperature sensor in the building, and the flow of people data are obtained in real time by installing a passenger flow counter at an entrance or a door of the building; sampling is carried out at the sampling time interval of 1 minute, so that temperature data and people flow data of the day are obtained; meanwhile, if reference is needed according to historical data, historical temperature data and people flow data are obtained, and the temperature data and the people flow data in nearly three months are collected as historical data; the current day data includes current day temperature data and current people data, and the historical data includes historical temperature data and current people data.
At this point, the air conditioner operation data, the temperature data of the current day and the history and the people flow data are collected.
Step S202, time interval division is carried out on the historical data and the current day data, and current day data and a plurality of reference data of each time interval in the current day data are obtained.
It should be noted that, temperature data and traffic data in a building have regular distribution characteristics in time dimension, for example, the traffic at the same time of a holiday is larger than the traffic at the same time of a working day, the traffic at the morning is smaller than the traffic at noon and at night, and the temperature is influenced by seasonal changes; therefore, time intervals of the historical data and the data of the current day are divided, wherein the time intervals comprise time intervals of each day in the history and the data of the current day, and the reference data in the historical data are obtained according to the day of the week to which the data of the current day belongs.
Specifically, data of each day in the historical data is divided to obtain historical data of a plurality of days, and data of each day and data of the current day are divided into data of each time period, wherein the data of the current day is divided by taking one hour as a preset time period to obtain data of the plurality of time periods in the data of the current day, and the data of the current day is recorded as data of the current day of each time period; and meanwhile, historical data of a plurality of time periods in the historical data are acquired.
Further, acquiring the day to which the current day data belongs, and taking historical data of a plurality of days in the historical data as reference data of the current day data; obtaining a plurality of reference data of each time period in the current day data according to the historical data of each time period in the current day data corresponding to the reference data and the corresponding relation of the time periods; it should be noted that the data of the current day includes temperature data and people flow data of corresponding time periods, and the reference data also includes temperature data and people flow data of corresponding time periods; for example, if the current day data is data of saturday, the historical data of all saturday in the historical data is used as reference data of the current day data, and the hourly data of the current saturday and the hourly data of all saturday in the historical data are subjected to time interval division, and the historical data of the same time interval is used as reference data of the current day data of each time interval.
So far, the data of the current day and a plurality of reference data of each time interval in the data of the current day are obtained.
Step S203, segmenting the data of the current day and the reference data according to the change between the data, and acquiring the comprehensive similarity degree of the data of the current day of each segment and each reference data of the belonged time period.
It should be noted that there are data points with large changes in the temperature data or the pedestrian volume data of each time interval, and the data of each time interval is divided into a plurality of segments through the data points; obtaining the comprehensive similarity degree between the data of the same day and different reference data in each time period according to the similarity between different sections in the data of the same day in each time period and different sections in a plurality of reference data in the same time period and the similarity between temperature data and people flow data; and then, providing reference for acquiring subsequent correction characteristic parameters by integrating the similarity degree.
Specifically, temperature data in the current-day data of each time period is recorded as the current-day temperature data of each time period, traffic data in the current-day data is recorded as the current-day traffic data of each time period, temperature data in the reference data is recorded as reference temperature data of each time period, and traffic data in the reference data is recorded as reference traffic data of each time period; taking the temperature data of the current day in any time interval as time sequence data, taking the temperature data of the current day in any time interval as an example, obtaining a temperature curve of the current day in the time interval by taking an abscissa as time and taking an ordinate as temperature data, performing STL time series decomposition on the temperature curve of the current day, and marking a trend term obtained by the decomposition as a temperature trend line of the current day in the time interval; it should be noted that the temperature trend line of the day represents the normal temperature change in the time period, and the interference of the possible abnormal value to the temperature change is avoided.
Further, the ratio of the difference of the trend item data of the adjacent moments in the temperature trend line of the current day to the time interval of the adjacent moments is used as the temperature change degree of the later moment in the adjacent moments, and the temperature change degree of each moment in the temperature trend line of the current day in the time period is obtained; it should be noted that, for the temperature change degree at the first moment in the time interval, the trend item data is filled up by adopting a quadratic linear interpolation method for obtaining; performing linear normalization on absolute values of all temperature change degrees, recording an obtained result as a temperature change rate of each moment, and giving a first preset threshold value for judging temperature change, wherein the first preset threshold value is calculated by adopting 0.58 in the embodiment, extracting the moment when the temperature change rate is greater than the first preset threshold value, recording the moment as a segmented moment of the current-day temperature curve of the time period, and segmenting the current-day temperature curve of the time period through the segmented moment to obtain a plurality of segmented current-day temperature curves and current-day temperature data of the time period; segmenting the current-day temperature data and the reference temperature data of all time periods according to the method, and acquiring the current-day temperature data of each segment in each time period and the reference temperature data of each segment in each reference temperature data; it should be noted that the segmented time is only applicable to the current-day temperature curve of the corresponding time interval, and the segmented time of the reference temperature data of the corresponding time interval needs to be recalculated.
Furthermore, as the people flow data is also time sequence data, and the people flow influences the temperature change, the people flow data of the same day in each time period is segmented according to the segmentation time of the temperature data of the same day in the corresponding time period, so that the people flow data of the same day in each time period is obtained; segmenting each piece of reference people flow data in each time period according to the segmentation time of the reference temperature data in the corresponding time period corresponding to the reference data, and obtaining the reference people flow data of each segment in each piece of reference people flow data.
It should be further noted that, taking the temperature data as an example, since there is a difference in the segmentation result of the current-day temperature data and the reference temperature data of each time interval, that is, there is a difference in the time range of the segmentation, the present embodiment obtains the first similarity degree between the current-day temperature data of each segment and the reference temperature data of the corresponding time interval by using the DTW distance analysis temperature trend line.
Specifically, obtaining the firstIs at the ^ th or greater in a time interval>The present-day temperature profile of the individual section, corresponding to the ^ th ^ temperature>Gets the ^ th or ^ th on the day temperature trend line of the time period>The temperature trend line of the day of each segment is acquired>A reference temperature trend line for each segment of the plurality of reference temperature data for the time period; get the fifth->Is at the ^ th or greater in a time interval>The temperature trend line of the day of each segment, and ^ h>A number of time periods>The DTW distance between the reference temperature trend lines of each segment in the reference temperature data takes the minimum value of all the DTW distances as the ^ th ^ or>Is at the ^ th or greater in a time interval>The present-day temperature data and the ^ th->A first similar distance, denoted as @, of the respective reference temperature data>, wherein />Indicates the fifth->Is at the ^ th or greater in a time interval>The temperature trend line of the day for each segment, <' >>Indicates the corresponding fifth/fifth value of the DTW distance minimum>A number of time periods>A segmented reference temperature trend line in the reference temperature data; will->Is recorded as the second->Is at the ^ th or greater in a time interval>The present-day temperature data and the ^ th->A first degree of similarity, expressed as ^ based on the reference temperature data>, wherein />An exponential function with a natural constant as a base is represented; it should be noted that this embodiment uses ^ R>The inverse proportion relation and normalization processing are presented, and an implementer can select other inverse proportion and normalization functions according to actual conditions; and acquiring a first similarity degree of the current-day temperature data of each segment and each reference data of the affiliated period according to the method. />
Further, as the daily pedestrian volume data and the reference pedestrian volume data of each time interval are segmented, the daily pedestrian volume data of each segment and the similarity of each reference pedestrian volume data of the time interval are recorded as the similarity of the daily pedestrian volume data of each segment and the reference pedestrian volume data of the time interval according to the calculation method of the first similarityA second degree of similarity; it should be noted that, in the second similarity degree calculation process, the DTW distance between the current-day pedestrian flow data of each segment and the reference pedestrian flow data of each segment in each reference pedestrian flow data still needs to be obtained, and the minimum value of the DTW distances is obtained to obtain the second similarity distance; to a first orderA number of time periods>A segment for example, the data on the day of the segment and the ^ H>A number of time periods>Integrated degree of similarity of individual reference data->The specific calculation method comprises the following steps:
wherein ,indicates the fifth->Is at the ^ th or greater in a time interval>The present-day temperature data and the ^ th->A first degree of similarity of individual reference temperature data->Indicates the fifth->Is at the ^ th or greater in a time interval>The current day traffic data and the ^ th of the individual segments>A second degree of similarity of the individual reference people flow data; and acquiring the comprehensive similarity degree of the current day data of each segment and each reference data of the affiliated period according to the method.
So far, the comprehensive similarity degree of the current-day data of each segment and each reference data of the affiliated time period is obtained and used for distance measurement in a subsequent LOF algorithm, and further long-term distribution parameters and short-term distribution parameters are obtained.
And S204, acquiring a long-term distribution parameter of each segment in the data of the current day according to the comprehensive similarity degree, acquiring a short-term distribution parameter of each segment in the data of the current day according to the long-term distribution parameter, correcting the long-term distribution parameter according to the short-term distribution parameter to acquire a correction characteristic parameter of each segment in the data of the current day, and acquiring a temperature prediction value according to the correction characteristic parameter.
It should be noted that after the comprehensive similarity between each segment of the current day data and the reference data is obtained, the long-term distribution parameters of each segment are quantified through the LOF local anomaly detection algorithm, so that the characteristics of each segment can be obtained by referring to the historical data.
Specifically, a distribution coordinate system is established by taking the abscissa as temperature data and the ordinate as pedestrian flow data; taking any segment in the current day data as an example, taking the mean value of the current day temperature data of the segment as an abscissa and the mean value of the current day people flow data as an ordinate to obtain a segment data point in a distribution coordinate system; acquiring a time period to which the segment belongs, taking the mean value of the reference temperature data of each reference data of the corresponding time period as an abscissa, and taking the mean value of the reference people flow data of each reference data as an ordinate, so as to obtain a plurality of reference data points in a distribution coordinate system; obtaining a distribution coordinate system corresponding to each segment according to the method, wherein each distribution coordinate system comprises a segment data point and a plurality of reference dataPoint; this embodiment employs a first of the segmented data pointsLOF local anomaly detection by data distribution features in distance neighborhoods, where the present embodiment employs +>Calculating; on the current day data>Taking the segment as an example, a specific calculation method for obtaining the long-term distribution parameters of the segment is as follows:
wherein ,indicates the fifth->A fifth of the segmented data points>Local reachable intensity below the distance neighborhood,. Sup.>Is shown asThe ^ th or ^ th of the segmented data point>Number of reference data points in distance neighborhood, <' >>Indicates the fifth->A fifth of the segmented data points>The ^ th or greater in the distance neighborhood>A plurality of reference data points, <' > based on>Indicates the fifth->Segmented data point and ^ th->Integrated degree of similarity of individual reference data points, <' > based on the comparison>Represents a fifth or fifth party>A reference data point at the ^ th ^ or ^ th>The ^ th or ^ th of the segmented data point>Local reachable intensity below the distance neighborhood,. Sup.>Represents a fifth or fifth party>The ^ th or ^ th of the segmented data point>Local outlier factors under the distance neighborhood; it should be noted that, obtaining a formula of a local outlier factor is a known technology, and only the traditional achievable distance metric is replaced by the comprehensive similarity degree for calculation, which is not described in detail in this embodiment of other existing parts; will make a fifth decision>The ^ th or ^ th of the segmented data point>Local outlier factors under a distance neighborhood are considered as first +>The long-term distribution parameters of the segments are quantified through the comprehensive similarity degree of the segments and the reference data, the influence of historical data in the same time period on the current day data is better referred, and the characteristic performance of the current day data and the historical data is better reflected; and acquiring the long-term distribution parameters of each segment in the data of the current day according to the method.
It should be further noted that the temperature change and the change of the flow of people in each segment in the current day data are processes that are continuously accumulated, and the temperature and the flow of people in each segment in the current day data are comprehensively influenced by other segments before each segment in the current day data, and the influence is recorded as a short-term distribution parameter; the longer the long-term distribution parameters of other segments are, namely the larger the local outlier factor is, the larger the current-day data change in the corresponding segment is, and the larger the influence on the short-term distribution parameters of each segment is; the smaller the time difference between other subsections and each subsection, the larger the influence of the change brought by the long-term distribution parameters on each subsection, and the larger the influence of the short-term distribution parameters; therefore, the short-term distribution parameters of each segment need to be obtained by combining the long-term distribution parameters of other segments in the data of the current day, and the correction characteristic parameters of each segment are obtained by correcting the long-term distribution parameters according to the short-term distribution parameters.
Specifically, the date of the dayTaking a segment as an example, a short-term distribution parameter @ of the segment is obtained>The specific calculation method comprises the following steps:
wherein ,indicates the ^ th or greater in the data of the current day>The number of other segments before a segment, based on the number of preceding segments>Indicating a th in the data of the day>A number of other segments and the ^ th->A time interval of segments, which is determined by the difference between the first time of the following segment and the last time of the preceding segment, is greater than or equal to>Indicates the ^ th or greater in the data of the current day>Long term profile parameters for several other segments>Represents a sign function, in particular->,/>Expressing an exponential function with a natural constant as a base; the smaller the time interval is, the greater the influence on the short-term distribution parameters is; the longer-term distribution parameter of a further segment which is greater than 1 and greater indicates that the segment has a greater difference with the corresponding reference data in respect of a +>Short-term distribution of segmentsThe greater the parameter impact; the long-term profile parameter of the other segment is less than 1, which itself varies less for the ^ th ^ or ^ th>The influence of the short-term distribution parameters of the individual segments is small.
Further, the correction characteristic parameter of each segment in the current day data is obtained according to the short-term distribution parameter correction long-term distribution parameter, so as to obtain the correction characteristic parameter of the current day dataTaking a segment as an example, a correction characteristic parameter->The calculation method comprises the following steps:
wherein ,indicates the ^ th or greater in the data of the current day>Short-term profile parameters of a segment, based on the number of segments in the segment, are selected>Indicates the ^ th or greater in the data of the current day>Long-term distribution parameters of the segments; and acquiring the correction characteristic parameters of each segment in the current day data according to the method.
It should be further noted that after the correction characteristic parameters of each segment in the current day data are obtained, a temperature change curve is obtained by performing weighted fitting on the current day temperature data, and then a temperature prediction value is obtained.
Specifically, acquiring a correction characteristic parameter of each segment in the current day data, acquiring a mean value of the current day temperature data of each segment as a comprehensive temperature value of each segment, performing softmax normalization on the correction characteristic parameters of all the segments, taking an obtained result as a weight of the comprehensive temperature value of the corresponding segment, performing weighted curve fitting on the comprehensive temperature value of each segment in the current day data by a least square method to obtain a temperature change curve, and acquiring a temperature predicted value of the last segment by the temperature change curve; the weighted curve fitting is prior art, and is not described in detail in this embodiment.
And then, acquiring a temperature predicted value of the last segment in the data of the current day, wherein the current time belongs to the last segment, and correcting the control parameters of the fuzzy PID according to the temperature predicted value and the temperature data of the current time to complete the accurate control of the air conditioning system.
Step S205, obtaining control parameters according to the temperature predicted value and the temperature data at the current moment, setting a basic domain and membership function of the control parameters, fuzzifying the control parameters, setting a PID parameter adaptive fuzzy rule and defuzzifying the control parameters to obtain an output value of a PID controller, and combining with air conditioner operation data to realize accurate control of the air conditioner system.
It should be noted that in step S004, the temperature predicted value is obtained by correcting the characteristic parameter, and the precise control is implemented according to the change difference between the temperature predicted value and the temperature data at the current time by combining with the fuzzy inference in the fuzzy PID control.
Specifically, the temperature data of the day acquired in step S001 includes temperature data of the current time, and a difference obtained by subtracting the temperature data of the current time from the predicted temperature value is used as a temperature variationThe ratio of the amount of temperature change to the sampling time interval is taken as the temperature change rate->Taking the temperature variation and the temperature variation rate as input data of a fuzzy PID controller; setting temperature variation amount>Has a basic argument of->The rate of change of temperature->Has a basic discourse field of->Then fuzzified to obtain a corresponding fuzzy domain determining the amount and rate of temperature change, wherein the fuzzy subset is set to >>Respectively correspond to>: is negative big and is taken up or taken off>: "negative middle">"negative small">: a "zero" value,: "Positive small">: "median", "is present>: "Positive big" is defined as(ii) a The membership function set in this embodiment is a gaussian function, and the actual implementation process can be set according to the specific implementation situation of the implementer.
Further, in the fuzzy PID control, mainlyBy fuzzy reasoning on three parameters in the PID controller, i.e.、/>And/or>Make a correction in which>、/>And/or>Are respectively->、/>And(ii) a The embodiment sets fuzzy control rules according to actual conditions: at the initial stage of control, a larger value is set>Value increases response speed, sets smaller->The value prevents integration saturation and sets a greater->The value is increased and the differential action is avoided from overshooting; in the middle control period, the smaller is set>The value ensures a small overshoot and ensures a response speed, the setting is moderate->Value and less->The value (or remains constant) ensures stability; in the later period of control, the larger is set>Value sum>Value decreases the static difference, sets a smaller->Value reduction braking action; please refer to FIG. 3, FIG. 4 and FIG. 5, which show the combination of ^ and/or on/off device in this embodiment>、/>And &>Fuzzy rule for three parameter settings, where FIG. 3 shows the parameter @>Fuzzy rule of (4), fig. 4 is->Fuzzy rule of (5), fig. 5 is>The fuzzy rule of (1).
Further, membership values of the output values to the fuzzy subsets are obtained according to fuzzy rules, defuzzification is carried out according to a weighted average method, and three parameters of the PID controller are obtained、/>And &>(ii) a Then the parameter after parameter setting is greater or less>,/>,/>And obtaining an output value of the PID controller, and further combining with the air conditioner operation data according to the output value to realize accurate control of the air conditioning system, wherein the specific control is the prior art, and the details are not repeated in this embodiment.
Therefore, the correction characteristic parameters of each time interval in the data of the current day are obtained according to the historical data, the temperature predicted value of the current time interval is further obtained, and the air conditioning system is accurately controlled through fuzzy PID control and fuzzy rules according to the temperature predicted value and the temperature data of the current time.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (8)
1. The intelligent air conditioner control method for building automatic control is characterized by comprising the following steps of:
acquiring the current day temperature data and the current day pedestrian volume data in the current day data, and acquiring historical temperature data and historical pedestrian volume data in a plurality of calendar history data;
time interval division is carried out on the historical data and the current day data, and current day data and a plurality of reference data of each time interval in the current day data are obtained;
acquiring the current-day temperature data in the current-day data of each time interval and reference temperature data in the reference data, acquiring the segmentation time in the current-day temperature data of each time interval and the segmentation time in the reference temperature data according to the data change of adjacent time in the current-day temperature data or the reference temperature data, segmenting the current-day data according to the segmentation time in the current-day temperature data of each time interval to obtain a plurality of segmented current-day data, and segmenting the reference data according to the segmentation time in each reference temperature data of each time interval to obtain a plurality of segmented reference data;
acquiring the comprehensive similarity degree of the current data of each segment and the reference data of each reference data of the affiliated period according to the similarity of the current data of each segment and the reference data of different segments in the reference data of the affiliated period;
acquiring a long-term distribution parameter of each segment in the current day data according to the comprehensive similarity degree, acquiring a short-term distribution parameter of each segment in the current day data according to the long-term distribution parameter, correcting the long-term distribution parameter according to the short-term distribution parameter to acquire a correction characteristic parameter of each segment in the current day data, and acquiring a temperature prediction value according to the correction characteristic parameter;
the method comprises the steps of obtaining control parameters according to a temperature predicted value and temperature data at the current moment, setting a basic domain and a membership function of the control parameters, fuzzifying the control parameters, setting a PID parameter adaptive fuzzy rule and defuzzifying the control parameters to obtain an output value of a PID controller, and combining air conditioner operation data to realize accurate control of an air conditioner system.
2. The intelligent air-conditioning control method for building automatic control as claimed in claim 1, wherein the acquiring of the data of the current day and a plurality of reference data of each time interval in the data of the current day comprises the following specific methods:
acquiring a plurality of day reference data of the current day according to the data of the current day and the distribution of the historical data of each day in each week; dividing the data of the current day and the plurality of day reference data by preset time intervals to obtain the data of the current day of each time interval in the data of the current day, and taking the reference data of the same time interval in the reference data as the reference data of each time interval in the data of the current day to obtain the plurality of reference data of each time interval in the data of the current day.
3. The intelligent air-conditioning control method for building automatic control according to claim 1, wherein the acquiring of the segmented time in the temperature data of the day and the segmented time in the reference temperature data of each time interval comprises the following specific methods:
acquiring the current-day temperature data or reference temperature data of any time period as target temperature data, acquiring a target temperature curve of the target temperature data, and recording a trend term obtained by time series decomposition of the target temperature curve as a target temperature trend line;
and taking the ratio of the difference of the trend item data of the adjacent moments in the target temperature trend line to the time interval of the adjacent moments as the temperature change degree of the later moment in the adjacent moments, acquiring the temperature change degree of each moment in the target temperature trend line, carrying out linear normalization on the absolute values of all the temperature change degrees, recording the obtained result as the temperature change rate of each moment, and taking the moment when the temperature change rate is greater than a first preset threshold value as the segmentation moment of the target temperature data.
4. The intelligent air-conditioning control method for building automatic control as claimed in claim 3, wherein the obtaining of the comprehensive similarity degree of the data of the current day of each segment and the reference data of the affiliated time period comprises the following specific methods:
get the firstIs at the ^ th or greater in a time interval>The present-day temperature profile of the individual section, corresponding to the ^ th ^ temperature>Gets the ^ th or ^ th on the day temperature trend line of the time period>The day of the segmentA temperature trend line is obtained>A reference temperature trend line for each segment of the plurality of reference temperature data for the time period; />
Get the firstIs at the ^ th or greater in a time interval>The temperature trend line of the day of each segment, and ^ h>A number of time periods>The DTW distance between the reference temperature trend lines of each segment in the reference temperature data takes the minimum value of all the DTW distances as the ^ th ^ or>On a number of time periods>The present-day temperature data and the ^ th->The first similar distance of the reference temperature data is expressed as, wherein />Indicates the fifth->On a number of time periods>A segmented temperature profile line for the day>Indicates the corresponding fifth or fifth tone of the DTW distance minimum>A number of time periods>A segmented reference temperature trend line in the reference temperature data; will be provided withIs recorded as the second->On a number of time periods>The present-day temperature data and the ^ th->A first degree of similarity of individual reference temperature data, wherein->Expressing an exponential function with a natural constant as a base;
the method comprises the steps of obtaining a first similarity degree of the temperature data of each segment on the day and each reference data of the period to which the temperature data of each segment belongs, obtaining a second similarity degree of the people flow data of each segment on the day and each reference data of the period to which the people flow data of each segment belongs, and taking the root of the square sum of the first similarity degree and the second similarity degree as the comprehensive similarity degree of the data of each segment on the day and each reference data of the period to which the people flow data of each segment belongs.
5. The intelligent air-conditioning control method for building automatic control according to claim 1, wherein the obtaining of the long-term distribution parameters of each segment in the data of the day according to the comprehensive similarity degree comprises the following specific methods:
wherein ,/>Indicates the fifth->The ^ th or ^ th of the segmented data point>Local reachable density under distance neighborhood>Indicates the fifth->The ^ th or ^ th of the segmented data point>Number of reference data points in distance neighborhood, <' >>Represents a fifth or fifth party>The ^ th or ^ th of the segmented data point>A fifth in a distant neighborhood>A reference data point, <' > based on the number of data points in the database>Indicates the fifth->Segmented data point and ^ th->Aggregate similarity of multiple reference data points, <' > based on a comparison of the similarity, and>indicates the fifth->A reference data point at the ^ th ^ or ^ th>The ^ th or ^ th of the segmented data point>Local reachable density under distance neighborhood>Represents a fifth or fifth party>A fifth of the segmented data points>Local outlier factors under the distance neighborhood; will be ^ based>The ^ th or ^ th of the segmented data point>Local outlier factor under distance neighborhood as the ^ h->Long-term distribution parameters of individual segments.
6. The intelligent air-conditioning control method for building automatic control as claimed in claim 1, wherein the short-term distribution parameters of each segment in the data of the day are obtained according to the long-term distribution parameters, including the specific methods of:
wherein ,/>Indicates the ^ th or greater in the data of the current day>Short-term profile parameters of a segment, based on the number of segments in the segment, are selected>Indicating a th in the data of the day>The number of other segments that precede a segment,indicates the ^ th or greater in the data of the current day>A number of other segments and the ^ th->Time interval of a segment, which is determined by the difference between the first time of the following segment and the last time of the preceding segment, based on the comparison of the time interval of the preceding segment and the time interval of the following segment, based on the comparison of the time interval of the following segment and the time interval of the preceding segment, based on the comparison of the time interval of the following segment and the time interval of the succeeding segment, based on the comparison of the time interval of the succeeding segment and the time interval of the succeeding segment>Indicates the ^ th or greater in the data of the current day>A long-term profile parameter of a further segment>Represents a symbol function, <' > based on>An exponential function with a natural constant as the base is shown.
7. The intelligent air-conditioning control method for building automatic control as claimed in claim 1, wherein the obtaining of the correction characteristic parameter of each segment in the data of the day by correcting the long-term distribution parameter according to the short-term distribution parameter comprises the following specific steps:
wherein ,/>Indicating a th in the data of the day>Correction characteristic parameter for a segment>Indicates the ^ th or greater in the data of the current day>Short-term profile parameters of a segment, based on the number of segments in the segment, are selected>Indicates the ^ th or greater in the data of the current day>Long-term distribution parameters of individual segments.
8. An intelligent air conditioning control system for building automatic control, the system comprising:
the data acquisition module is used for acquiring the temperature data and the flow data of the current day in the current day data and acquiring historical temperature data and historical flow data in a plurality of calendar history data;
a control parameter correction module: time interval division is carried out on the historical data and the current day data, and current day data and a plurality of reference data of each time interval in the current day data are obtained;
acquiring the temperature data of the current day in the data of the current day in each time period and reference temperature data in the reference data, acquiring the segmentation time in the temperature data of the current day in each time period and the segmentation time in the reference temperature data according to the data change of adjacent times in the temperature data of the current day or the reference temperature data, segmenting the data of the current day according to the segmentation time in the temperature data of the current day in each time period to obtain a plurality of segmented data of the current day, and segmenting the reference data according to the segmentation time in each reference temperature data in each time period to obtain a plurality of segmented reference data;
acquiring the comprehensive similarity degree of the current-day data of each segment and the reference data of each reference data of the affiliated period according to the similarity of the current-day data of each segment and the reference data of different segments in the reference data of the affiliated period;
acquiring a long-term distribution parameter of each segment in the data of the current day according to the comprehensive similarity degree, acquiring a short-term distribution parameter of each segment in the data of the current day according to the long-term distribution parameter, correcting the long-term distribution parameter according to the short-term distribution parameter to acquire a correction characteristic parameter of each segment in the data of the current day, acquiring a temperature predicted value according to the correction characteristic parameter, and acquiring a control parameter according to the temperature predicted value and the temperature data of the current moment;
the control parameter fuzzification module is used for setting a basic domain and membership function of the control parameters and fuzzifying the control parameters;
the fuzzy rule setting module is used for setting a PID parameter self-adaptive fuzzy rule;
the PID parameter defuzzification module is used for defuzzifying the defuzzified control parameters through a fuzzy rule and a membership function to obtain an output value of the PID controller;
and the PID control module is used for combining air conditioner operation data according to the output value of the PID controller to realize accurate control of the air conditioning system.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310253244.XA CN115962551B (en) | 2023-03-16 | 2023-03-16 | Intelligent air conditioner control system and method for building automatic control |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310253244.XA CN115962551B (en) | 2023-03-16 | 2023-03-16 | Intelligent air conditioner control system and method for building automatic control |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115962551A true CN115962551A (en) | 2023-04-14 |
CN115962551B CN115962551B (en) | 2023-05-26 |
Family
ID=85905182
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310253244.XA Active CN115962551B (en) | 2023-03-16 | 2023-03-16 | Intelligent air conditioner control system and method for building automatic control |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115962551B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116772285A (en) * | 2023-08-28 | 2023-09-19 | 山东国能智能科技有限公司 | Intelligent building heating load safety real-time monitoring method |
CN117435874A (en) * | 2023-12-21 | 2024-01-23 | 河北雄安睿天科技有限公司 | Abnormal data detection method and system for water supply and drainage equipment |
CN117572137A (en) * | 2024-01-17 | 2024-02-20 | 山东海纳智能装备科技股份有限公司 | Seven-level ANPC high-voltage frequency converter remote monitoring system |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008241160A (en) * | 2007-03-27 | 2008-10-09 | Matsushita Electric Works Ltd | Air conditioning control system |
EP2704367A1 (en) * | 2012-08-30 | 2014-03-05 | EnBW Energie Baden-Württemberg AG | Energy consumer control method and control device based on an energy consumption profile |
CN104279713A (en) * | 2014-10-24 | 2015-01-14 | 珠海格力电器股份有限公司 | Air conditioner control method and system and air conditioner controller |
CN104729024A (en) * | 2015-04-08 | 2015-06-24 | 南京优助智能科技有限公司 | Air conditioning load prediction method based on indoor average temperature |
CN106338127A (en) * | 2016-09-20 | 2017-01-18 | 珠海格力电器股份有限公司 | Load forecast and control system and method for metro heat ventilation and air-conditioning system |
CN108826620A (en) * | 2018-08-06 | 2018-11-16 | 南京邮电大学 | The distributed control method of extensive heating ventilation air-conditioning system in the building of campus |
US20200352002A1 (en) * | 2019-04-05 | 2020-11-05 | Artemide S.P.A. | Method for controlling a lighting system |
CN113706337A (en) * | 2021-09-06 | 2021-11-26 | 天津宏达瑞信科技有限公司 | Heat supply load prediction method based on similar time periods |
CN114811857A (en) * | 2022-06-27 | 2022-07-29 | 深圳市森辉智能自控技术有限公司 | Cold station system operation optimization method |
-
2023
- 2023-03-16 CN CN202310253244.XA patent/CN115962551B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008241160A (en) * | 2007-03-27 | 2008-10-09 | Matsushita Electric Works Ltd | Air conditioning control system |
EP2704367A1 (en) * | 2012-08-30 | 2014-03-05 | EnBW Energie Baden-Württemberg AG | Energy consumer control method and control device based on an energy consumption profile |
CN104279713A (en) * | 2014-10-24 | 2015-01-14 | 珠海格力电器股份有限公司 | Air conditioner control method and system and air conditioner controller |
CN104729024A (en) * | 2015-04-08 | 2015-06-24 | 南京优助智能科技有限公司 | Air conditioning load prediction method based on indoor average temperature |
CN106338127A (en) * | 2016-09-20 | 2017-01-18 | 珠海格力电器股份有限公司 | Load forecast and control system and method for metro heat ventilation and air-conditioning system |
CN108826620A (en) * | 2018-08-06 | 2018-11-16 | 南京邮电大学 | The distributed control method of extensive heating ventilation air-conditioning system in the building of campus |
US20200352002A1 (en) * | 2019-04-05 | 2020-11-05 | Artemide S.P.A. | Method for controlling a lighting system |
CN113706337A (en) * | 2021-09-06 | 2021-11-26 | 天津宏达瑞信科技有限公司 | Heat supply load prediction method based on similar time periods |
CN114811857A (en) * | 2022-06-27 | 2022-07-29 | 深圳市森辉智能自控技术有限公司 | Cold station system operation optimization method |
Non-Patent Citations (1)
Title |
---|
王小刚等: "基于相似日搜索的空调短期负荷预测方法", 华中科技大学学报(自然科学版) * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116772285A (en) * | 2023-08-28 | 2023-09-19 | 山东国能智能科技有限公司 | Intelligent building heating load safety real-time monitoring method |
CN116772285B (en) * | 2023-08-28 | 2023-11-07 | 山东国能智能科技有限公司 | Intelligent building heating load safety real-time monitoring method |
CN117435874A (en) * | 2023-12-21 | 2024-01-23 | 河北雄安睿天科技有限公司 | Abnormal data detection method and system for water supply and drainage equipment |
CN117435874B (en) * | 2023-12-21 | 2024-03-12 | 河北雄安睿天科技有限公司 | Abnormal data detection method and system for water supply and drainage equipment |
CN117572137A (en) * | 2024-01-17 | 2024-02-20 | 山东海纳智能装备科技股份有限公司 | Seven-level ANPC high-voltage frequency converter remote monitoring system |
CN117572137B (en) * | 2024-01-17 | 2024-03-29 | 山东海纳智能装备科技股份有限公司 | Seven-level ANPC high-voltage frequency converter remote monitoring system |
Also Published As
Publication number | Publication date |
---|---|
CN115962551B (en) | 2023-05-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111222698B (en) | Internet of things-oriented ponding water level prediction method based on long-time and short-time memory network | |
CN115962551A (en) | Intelligent air conditioner control system and method for building automatic control | |
Zhang et al. | Wind power prediction based on PSO-SVR and grey combination model | |
Hao et al. | A novel clustering algorithm based on mathematical morphology for wind power generation prediction | |
CN111967688B (en) | Power load prediction method based on Kalman filter and convolutional neural network | |
CN111310789B (en) | Wind power interval prediction method based on nuclear density estimation and implementation system thereof | |
CN111626518A (en) | Urban daily water demand online prediction method based on deep learning neural network | |
CN109242265B (en) | Urban water demand combined prediction method based on least square sum of errors | |
CN111815065B (en) | Short-term power load prediction method based on long-short-term memory neural network | |
CN112070268B (en) | Power load prediction method and device based on hotel demand side response | |
CN113554466B (en) | Short-term electricity consumption prediction model construction method, prediction method and device | |
CN110033134A (en) | A kind of short-term load forecasting algorithm of segmentation day by day considering meteorologic factor | |
CN112101669A (en) | Photovoltaic power interval prediction method based on improved extreme learning machine and quantile regression | |
Maltais et al. | Predictability analysis of domestic hot water consumption with neural networks: From single units to large residential buildings | |
CN111461466A (en) | Heating household valve adjusting method, system and equipment based on L STM time sequence | |
CN111598328A (en) | Power load prediction method considering epidemic situation events | |
CN111723085A (en) | Electric energy consumption data cleaning method and system for air conditioner of public building | |
Wang et al. | Probabilistic power curve estimation based on meteorological factors and density LSTM | |
CN117435873A (en) | Data management method based on intelligent spraying dust fall | |
CN117200223A (en) | Day-ahead power load prediction method and device | |
CN113268929A (en) | Short-term load interval prediction method and device | |
CN115081681B (en) | Wind power prediction method based on propset algorithm | |
CN114936640A (en) | Online training method for new energy power generation intelligent prediction model | |
CN110009132A (en) | A kind of short-term electric load fining prediction technique based on LSTM deep neural network | |
CN115221800A (en) | Extended period runoff set prediction method integrating natural gas generator and deep learning |
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 |