CN106604496B - Parking lot lighting systems control method based on fuzzy technology - Google Patents
Parking lot lighting systems control method based on fuzzy technology Download PDFInfo
- Publication number
- CN106604496B CN106604496B CN201611062136.0A CN201611062136A CN106604496B CN 106604496 B CN106604496 B CN 106604496B CN 201611062136 A CN201611062136 A CN 201611062136A CN 106604496 B CN106604496 B CN 106604496B
- Authority
- CN
- China
- Prior art keywords
- fuzzy
- ambient light
- light illumination
- rule
- value
- 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
Classifications
-
- H—ELECTRICITY
- H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
- H05B—ELECTRIC HEATING; ELECTRIC LIGHT SOURCES NOT OTHERWISE PROVIDED FOR; CIRCUIT ARRANGEMENTS FOR ELECTRIC LIGHT SOURCES, IN GENERAL
- H05B47/00—Circuit arrangements for operating light sources in general, i.e. where the type of light source is not relevant
- H05B47/10—Controlling the light source
Abstract
The parking lot lighting systems control method based on fuzzy technology that the present invention provides a kind of.This method constructs adaptive Gauss background model to infrared image, isolates foreground pixel, and carry out brightness upright projection to it, obtains curve image;Identify peak of curve number M in curve image, the input as the second fuzzy controller FC2;Second fuzzy controller FC2 exports dimmer command according to the second fuzzy control rule.Wherein, peak of curve number M can be used to indicate that the number of people, the i.e. present invention are adjusted the lamplight brightness of each subregion according to the number of each subregion people.Through the invention, it solves the problems, such as that parking lot illuminance control method is inflexible, improves lighting system adjustability, intelligence.
Description
Technical field
The present invention relates to electric lighting fields, in particular to a kind of parking lot lighting systems control based on fuzzy technology
Method processed.
Background technique
In recent years, Living consumption increasingly improves, and the private vehicle of purchase is more and more, while having welcome garage construction
The problem of Lighting Design needs to pay attention in garage construction has been caused in peak period thereupon.Therefore the building in garage is directed to
Situation, requirement of Party A etc. comprehensively consider lamp installation mode, the mode of connection of illumination and the control of illumination of garage illumination
Mode, to reach energy-saving and environmental protection, economically and reasonably require.
Common Large Underground parking lot carries out energy conservation measure frequently with single control method, using low illuminance, but
It is that this method flexibility is small, when someone uses parking lot, brightness of illumination may be insufficient, and when nobody uses parking lot
When, lamp is still open, and is resulted in waste of resources.
Summary of the invention
The parking lot lighting systems control method based on fuzzy technology that the present invention provides a kind of, at least to solve related skill
The inflexible problem of parking lot illuminance control method in art.
According to an aspect of the invention, there is provided a kind of parking lot lighting systems control method based on fuzzy technology,
Include:
Step 1, the illuminance of each subregion in parking lot is detected, and each subregion illuminance is merged, obtains ambient light illumination L;
Step 2, when the ambient light illumination L is down to default ambient light illumination lower limit value LmAfterwards, by the ambient light illumination L and environment
Input of the illumination change rate dL/dt as the first fuzzy controller FC1, the first fuzzy controller FC1 are fuzzy according to first
Control rule output switch lamp operational order;When the ambient light illumination L is down to default ambient light illumination lower limit value LmWhen, start simultaneously
Second fuzzy controller FC2, the infrared thermoviewer for controlling each subregion installation are started to work, and are carried out to each subregion real
When infrared image record, obtain infrared image;
Step 3, adaptive Gauss background model is constructed to the infrared image, isolates foreground pixel, and carry out to it
Brightness upright projection, obtains curve image;
Step 4, peak of curve number M in the curve image is identified, as the defeated of the second fuzzy controller FC2
Enter;
Step 5, the second fuzzy controller FC2 exports dimmer command according to the second fuzzy control rule.
Optionally, the step 1 includes:
The digital optical sensor installed by each subregion in the parking lot, tests the illuminance of each subregion respectively,
And blunder error is rejected using multisensor Data Fusion technology, it is merged into the ambient light illumination L, as first Fuzzy Control
The input of device FC1 processed.
Optionally, the ambient light illumination L in the step 2 is calculated in the following manner:
If certain large parking lot is divided into n region, n digital optical sensor independently carries out illuminance at the m moment
Measurement, obtains n data, arranges from small to large ord, if measured value is Lmi, unit lx, 0≤i≤n;
If intermediate value LmM, upper quartile LOn m, lower quartile LUnder mWith its difference, then have
DL=LOn m-LUnder m
Wherein, the data L that certain moment all digital optical sensors measuremiWith intermediate value LmMAbsolute value of the difference greater than dL
The data of absolute value are that invalid data seeks arithmetic mean of instantaneous value to remaining data, obtain the environment after rejecting invalid data
Illumination L.
Optionally, first fuzzy control rule in the step 2 includes:
Rule 1: when the ambient light illumination L is less than 20lx and is greater than 15lx, start lighting system, and regulate and control illumination output
Power is 50% rated power;
Rule 2: when the ambient light illumination L is less than or equal to 15lx, regulation illumination output power is 100% specified function
Rate;
Rule 3: when the ambient light illumination L is greater than or equal to 20lx, lighting system is closed.
Optionally, work as the ambient light illumination L down to default ambient light illumination lower limit value L in the step 2mIt afterwards, will be described
Input of the ambient light illumination L and ambient light illumination change rate dL/dt as the first fuzzy controller FC1, first fuzzy controller
FC1 exports switch lamp operational order according to the first fuzzy control rule
The ambient light illumination change rate that ambient light illumination L and sampling are calculated the first fuzzy controller FC1As
Input;The membership function S to turn on light with illumination output power regulation as output;Ambient light illumination change rate functionT is the sampling period;
Definition corresponds to rule 1, rule 2 and rule 3 respectively on ambient light illumination change rate domain L={ l | 0≤l≤30 }
Fuzzy set " dark ", " dim ", " bright ";Membership function S uses Sigmoid type or bell, corresponds to rule 1, rule 2
Membership function with rule 3 is respectively following three formula:
In domainUpper definition { is born greatly for measuring the fuzzy set of ambient light illumination variation speed
NB bears small NS, zero O, just small PS, honest PB }, membership function uses triangle or trapezoidal;
In domainIt is upper definition for measure lighting system output power variation fuzzy set S10, N,
S01, S12, S02 }, wherein S10 expression turn off the light, i.e., output power be 30%~100% any value when, as long as ambient light illumination
When value is from 20 to 0lx, output power is transferred to 0;N indicates do-nothing operation;S01 expression is turned on light, and is 50% work with output power;
S12 indicates that output power becomes 100% work from 50%;S02 expression is turned on light and output power is 100% work;It is subordinate to
Function uses triangle.
Optionally, first fuzzy control rule includes:
Optionally, adaptive Gauss background model is constructed to the infrared image in the step 3, isolates prospect picture
Element includes:
Identification characteristic value in the infrared image is the brightness of pixel, by same position in continuous sequence infrared image
Pixel brightness in the time domain see a time series { X as1, X2,..., Xt, then the observation of current pixel probability uses
Mixed Gauss model can be expressed as:
Here ωi,tWeight for i-th of Gaussian Profile in time t, ui,t、σi,tThe mean value of respectively i-th Gaussian function
And standard deviation;K be gauss hybrid models included in Gaussian Profile number, size depend on system free memory and
The computing capability of system, η are Gaussian probability-density function;
Using above-mentioned model, initialization gauss hybrid models predetermined, high variance, k Gauss of small weight for mean value
Distribution;For a new pixel, when its characteristic value is located in 2.5 Standard deviation-Ranges of a certain Gaussian Profile, then it is assumed that
It is matched with the Gaussian Profile;Then all Gaussian Profile weights are updated by following formula according to pairing situation:
ωi,t=(1- α) ωi,t-1+α(Mi,t), i=1,2 ..., k
Wherein α is learning parameter, Mi,tMark then is matched for the Gaussian Profile of current pixel, if there is a Gauss point
Cloth and current pixel match then Mi,t=1, otherwise Mi,t=0;After being updated to weight, a series of newly-generated weights are returned
One changes, and the parameter for the Gaussian Profile matched updates are as follows:
μt=(1- ρ) μt-1+ρ(Xt)
HereThe parameter of other Gaussian Profiles is then constant;Match if there is no any
It is right, then the smallest Gaussian Profile of probability value is replaced with into the Gauss that a mean value is the pixel value newly observed, high variance, small weight
Distribution executes aforesaid operations to next frame image.
In order to judge the prospect or background type of the pixel newly observed, according to ω/σ value to k Gaussian Profile descending
Arrangement, since the pixel in background image has high weight and low variance, ratio between the two is bigger, belongs to background
Possibility is higher, and b Gaussian Profile of the foremost using weights sum greater than background threshold T be by as background model herein,
Have:
Background model determine after, can in image background pixel and foreground pixel classify;If new observation
Pixel and the b Gaussian Profile in some match, then it is assumed that it belongs to background, otherwise belongs to prospect.
Optionally, the step 5 includes:
Second fuzzy controller FC2 input quantity is to obtain the peak value number M of curve by brightness upright projection in each subregion,
M is divided into 4 grades, respectively { fewer, few, many, more } in domain [0,720];
For convenient for flexibly modifying fuzzy rule for different speed limit requirements, fuzzy set bear big NB, bear small NS, zero O,
Just small PS, honest PB } subset QC be changed to fuzzy number be { -1,0,1,2 };Its membership function chooses triangle and trapezoidal;Output
Control lighting system concrete operations are the regulation of output power, as output power U3Domain be [0,1], be divided into 8 etc.
Grade { 30%, 40%, 50%, 60%, 70%, 80%, 90%, 100% }, corresponding fuzzy number are { 0,1,2,3,4,5,6,7 },
Membership function chooses triangle.
Optionally, second fuzzy control rule includes:
Through the invention, adaptive Gauss background model is constructed using to infrared image, isolates foreground pixel, and to it
Brightness upright projection is carried out, curve image is obtained;Peak of curve number M in curve image is identified, as the second fuzzy control
The input of device FC2;Second fuzzy controller FC2 exports the mode of dimmer command according to the second fuzzy control rule;Wherein, curve
Peak value number M can be used to indicate the number of people, i.e., the present invention according to the number of each subregion people to the lamplight brightness of each subregion into
Row is adjusted, and is solved the problems, such as that parking lot illuminance control method is inflexible, is improved lighting system adjustability, intelligence.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes part of this application, this hair
Bright illustrative embodiments and their description are used to explain the present invention, and are not constituted improper limitations of the present invention.In the accompanying drawings:
Fig. 1 is the flow chart of the parking lot lighting systems control method according to an embodiment of the present invention based on fuzzy technology.
Specific embodiment
Hereinafter, the present invention will be described in detail with reference to the accompanying drawings and in combination with Examples.It should be noted that not conflicting
In the case of, the features in the embodiments and the embodiments of the present application can be combined with each other.
It should be noted that description and claims of this specification and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.
A kind of parking lot lighting systems control method based on fuzzy technology is provided in the present embodiment, and Fig. 1 is basis
The flow chart of the parking lot lighting systems control method based on fuzzy technology of the embodiment of the present invention, as shown in Figure 1, the process packet
Include following steps:
Step 1, each subregion illuminance detection, carries out multi-sensor information fusion, obtains ambient light illumination L;
Step 2, judgment module starts the first fuzzy controller FC1 and FC2 according to ambient light illumination L;
Step 3, when ambient light illumination L is down to default ambient light illumination lower limit value LmAfterwards, ambient light illumination L and ambient light illumination are changed
Input of the rate dL/dt as the first fuzzy controller FC1;
Step 4, the first fuzzy controller FC1 exports switch lamp operational order according to its first fuzzy control rule;
Step 5, meanwhile, when ambient light illumination L is down to after providing lower limit value, judgment module starts the second fuzzy controller FC2,
The infrared thermoviewer of subregion installation is started to work, and is carried out real-time infrared image record to one's respective area, is obtained infrared image;
Step 6, adaptive Gauss background model is constructed to infrared image, isolates foreground pixel, and brightness is carried out to it
Upright projection obtains curve image;
Step 7, peak of curve number (as number) M is automatically identified, is inputted as the second fuzzy controller FC2;
Step 8, the second fuzzy controller FC2 exports dimmer command according to its second fuzzy control rule;
Large Underground parking lot lighting systems are according to step 4 and step 8 method output switch and dimmer command to each area
Domain illumination is adjusted.
Optionally, the measurement ambient light illumination L of step 1, including TSL2561 (a kind of number of model installed to different zones
Word optical sensor) the illuminance test module that constitutes, test ambient illumination values respectively, and utilize multisensor Data Fusion technology
Blunder error is rejected, is merged into a final ambient light illumination L, the input as each the first fuzzy controller of region FC1 refers to
Mark.
Optionally, the judgment module of step 2 judges that process is as follows:
If certain Large Underground parking lot is divided into n region, m independently carries out illuminance measuring to n TSL2561 at a certain moment
Amount, obtains n data, arranges from small to large ord, if measured value is Lmi(unit lx;0≤i≤n), number in this method
The optical sensor working time across the parking lot working time, by taking the Large Underground parking lot of 24 HOUR ACCESS as an example, it is desirable that every 5 points
Clock reads one-shot measurement value, i.e. the value range of m is [1,288].
Judgment module judgment method: intermediate value L is setmM, upper quartile LOn m, lower quartile LUnder mWith its difference dL.Then have
DL=LOn m-LUnder m
Assert the data L that all digital optical sensors of a certain moment measuremiWith intermediate value LmMAbsolute value of the difference greater than dL
The data of absolute value are that invalid data seeks arithmetic mean of instantaneous value to remaining data and obtain L after rejecting invalid datam, as
The trigger data of the input data of one fuzzy controller FC1 and the second fuzzy controller FC2.
Optionally, the first fuzzy controller FC1 course of work of step 4 is as follows:
When ambient light illumination is less than 20lx, start lighting system, it is 50% specified that lighting system, which regulates and controls illumination output power,
Power, lighting system regulation illumination output power is 100% rated power when being less than 15lx;When ambient light illumination is greater than 21lx,
Lighting system is automatically closed.
Fuzzy controller becomes the ambient illumination values (unit: lx) that illuminance transducer measures and the illumination that sampling is calculated
Rate (unit: lx/s) as input, respectively with L andTwo variables indicate.It turns on light and dims as output membership function
(being indicated with S).Illumination change rate functionT=5 minutes, be the sampling period.
According to human visual perception and relevant criterion, when environment is released souls from purgatory less than 20lx when dusk, illumination is enabled, and with 50%
Power work.When less than 15lx, illumination is with the work of 100% power.When ambient light illumination reaches 20lx, lighting system is closed.In
It is ambiguity in definition collection " dark ", " dim ", " bright " on illumination function domain L={ l | 0≤l≤30 }.Membership function uses
Sigmoid type and bell, corresponding membership function are respectively following three formula.
According to experimental measurements, illumination change rateLess than 0.5lx/s;In domainIt is upper fixed
Justice { is born greatly (NB), is born small (NS), zero (O) is just small (PS), honest for measuring the fuzzy set of ambient light illumination variation speed
(PB) }, membership function is using triangle and trapezoidal, both function algorithms are simple, and processing speed is fast.
In domainIt is upper definition for measure lighting system output power variation fuzzy set S10, N,
S01, S12, S02 }, wherein S10 expression is turned off the light (changed power range is -0.3~-1), i.e., output power is 30%~100%
Any value when, as long as ambient illumination values are from 20 to 0lx, output power is transferred to 0.N indicates do-nothing operation.S01 expression is turned on light, and
It is 50% work with output power (changed power range is 0.35~0.45).S12 indicates that output power becomes 100% from 50%
Work (changed power range is 0.55~0.65).S02 expression is turned on light and output power is 100% work (changed power model
Enclose is 0.8~1).Its membership function uses triangle.
Optionally, the first fuzzy control rule of step 4 is as shown in table 1:
Table 1
Optionally, step 6 to infrared image construct adaptive Gauss background model, isolate foreground pixel, mathematics side
Method is as follows:
First, it is believed that characteristic value is the brightness of pixel in infrared image, by position same in continuous sequence infrared image
A time series { X is seen in the brightness of the pixel set in the time domain as1, X2, ..., Xt, then the observation of current pixel probability is adopted
It can be expressed as with mixed Gauss model
Here ωi,tWeight for i-th of Gaussian Profile in time t, ui,t、σi,tThe mean value of respectively i-th Gaussian function
And standard deviation.K be gauss hybrid models included in Gaussian Profile number, size depend on system free memory and
The computing capability of system, η are Gaussian probability-density function.
Using above-mentioned model, initialization gauss hybrid models predetermined, high variance, k Gauss of small weight for mean value
Distribution.For a new pixel, when its characteristic value is located in 2.5 Standard deviation-Ranges of a certain Gaussian Profile, then it is assumed that
It is matched with the Gaussian Profile.Then all Gaussian Profile weights are updated by following formula according to pairing situation
ωi,t=(1- α) ωi,t-1+α(Mi,t), i=1,2 ..., k
Wherein α is learning parameter, generally takes α=0.05, Mi,tThen the Gaussian Profile without current pixel matches mark, if
There are a Gaussian Profiles and current pixel to match then Mi,t=1, otherwise Mi,t=0.After being updated to weight, to newly-generated one
Serial weight is normalized, and the parameter for the Gaussian Profile matched is updated to
μt=(1- ρ) μt-1+ρ(Xt)
HereThen constant matches the parameter of other Gaussian Profiles if there is no any
It is right, then the smallest Gaussian Profile of probability value is replaced with into the Gauss that a mean value is the pixel value newly observed, high variance, small weight
Distribution executes aforesaid operations to next hardwood image.
In order to judge the type (prospect or background) for the pixel newly observed, k Gaussian Profile dropped according to the value of ω/σ
Sequence arrangement, since the pixel in background image has high weight and low variance, ratio between the two is bigger, belongs to background
A possibility that it is higher, herein using weights sum greater than background threshold T foremost b Gaussian Profile by as background mould
Type has
Background model determine after, if can in image background pixel and foreground pixel carry out classification newly observe
Pixel and the b Gaussian Profile in some pairing, then it is assumed that it belongs to background, otherwise belong to prospect pass through above-mentioned side
Method adaptively can learn background model and be updated.
Optionally, method the second fuzzy controller FC2 of step 8 exports light modulation life according to its second fuzzy control rule
It enables, including the second fuzzy controller FC2 sets judgment rule and judged according to the rule, to reach with fuzzy technology
The purpose of output control parking lot lighting systems brightness.Wherein, the second fuzzy controller FC2 specifically sets and sentences in Matlab
Disconnected rule is as follows:
Second fuzzy controller FC2 input quantity is to divide in region to obtain the peak value M of curve by brightness upright projection,
I.e. input quantity is number M, and flow of the people M is divided into 4 grades, respectively { fewer, few, many, more } in domain [0,720].
For convenient for flexibly modifying fuzzy rule for different speed limit requirements, it is { -1,0,1,2 } that fuzzy subset, which is changed to fuzzy number,.Its
Membership function chooses triangle and trapezoidal.Output control lighting system concrete operations are the regulation of output power, are as exported
Power U3Domain be [0,1], be divided into 8 grades { 30%, 40%, 50%, 60%, 70%, 80%, 90%, 100% }, it is right
Answering fuzzy number is { 0,1,2,3,4,5,6,7 }, and membership function chooses triangle.
Output power U3The second fuzzy control rule it is as shown in table 2 below.
Table 2
Optionally, Large Underground parking lot lighting systems are according to step 4 and step 8 method output switch and dimmer command pair
Each area illumination is adjusted, i.e., what step 4 and step 8 were mentioned uses the first fuzzy control according to brightness of illumination L and number M
Device FC1 and FC2 show that the changed power of output illumination is a kind of Large Underground parking lot lighting systems control based on fuzzy technology
The core content of method processed.
It through the above embodiments of the present invention, is the first fuzzy controller FC1 input with brightness of illumination L, it is fuzzy according to FC1
Judgment rule carries out fuzzy control, exports the power regulation control of illumination;It is the second fuzzy controller FC2 input, root with number M
Fuzzy control is carried out according to FC2 fuzzy Judgment rule, exports the power regulation control of illumination.Both of the above simultaneously to lighting system into
Row control, does not influence mutually, works independently.
The embodiment of the present invention is illustrated below by an example.
Referring to Fig.1, the method for this example citing includes the following steps:
Step 1, each subregion illuminance detection, carries out multi-sensor information fusion, obtains ambient light illumination L;
Step 2, judgment module starts fuzzy controller FC1 and FC2 according to ambient light illumination L;
Step 3, after ambient light illumination L is down to regulation lower limit value, ambient light illumination L and ambient light illumination change rateAs fuzzy
The input of controller FC1;
Step 4, fuzzy controller FC1 exports switch lamp operational order according to its fuzzy control rule;
Differential process input, 3 institute of simulation input tables of data are inputted and carried out after existing simulation numeral optical sensor acquisition data
Show, method response output result is with as shown in table 3:
Table 3
Step 5, meanwhile, when ambient light illumination L is down to after providing lower limit value, judgment module starts fuzzy controller FC2, subregion
The infrared thermoviewer of installation is started to work, and is carried out real-time infrared image record to one's respective area, is obtained infrared image;
Step 6, adaptive Gauss background model is constructed to infrared image, isolates foreground pixel, and brightness is carried out to it
Upright projection obtains curve image;
Step 7, peak of curve number (as number) M is automatically identified, is inputted as fuzzy controller FC2;
Step 8, fuzzy controller FC2 exports dimmer command according to its fuzzy control rule;
Now simulation receives infrared image and carries out foreground pixel processing and carry out the curve image that brightness upright projection obtains
It is inputted after peak counting M acquisition data, simulation input data are as shown in table 4, and method response output result is with as shown in table 4:
Table 4
Large Underground parking lot lighting systems are according to step 4 and step 8 method output switch and dimmer command to each area
Domain illumination is adjusted.
In conclusion existing lighting system control is also less to control it exploitation with fuzzy control technology.It is real
Complicated control problem can be effectively simplified as what a plurality of fuzzy control rule judged by the application of fuzzy technology on border
Mathematical problem.Through the above embodiments of the present invention or preferred embodiment, start with from energy conservation, economy and user satisfaction, mention
A kind of Large Underground parking lot lighting systems control method based on fuzzy technology is supplied, this control method is by complicated brightness tune
Section problem is converted, using fuzzy control into the mathematics decision problem of core, to simplify operating procedure, improving lighting system can
Tonality, intelligence.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (2)
1. a kind of parking lot lighting systems control method based on fuzzy technology, characterized by comprising:
Step 1, the illuminance of each subregion in parking lot is detected, and each subregion illuminance is merged, obtains ambient light illumination L;
Step 2, when the ambient light illumination L is down to default ambient light illumination lower limit value LmAfterwards, by the ambient light illumination L and ambient light illumination
Input of the change rate dL/dt as the first fuzzy controller FC1, the first fuzzy controller FC1 is according to the first fuzzy control
Rule output switch lamp operational order;When the ambient light illumination L is down to default ambient light illumination lower limit value LmWhen, while starting second
Fuzzy controller FC2, the infrared thermoviewer for controlling each subregion installation are started to work, and are carried out to each subregion red in real time
Outer image recording, obtains infrared image;
Step 3, adaptive Gauss background model is constructed to the infrared image, isolates foreground pixel, and brightness is carried out to it
Upright projection obtains curve image;
Step 4, peak of curve number M in the curve image is identified, the input as the second fuzzy controller FC2;
Step 5, the second fuzzy controller FC2 exports dimmer command according to the second fuzzy control rule;
Wherein:
The ambient light illumination L in the step 2 is calculated in the following manner:
If certain large parking lot is divided into n region, n digital optical sensor independently carries out illuminance measurement at the m moment,
N data are obtained, are arranged from small to large ord, if measured value is Lmi, unit lx, 0≤i≤n;
If intermediate value LmM, upper quartile LOn m, lower quartile LUnder mWith its difference, then have
DL=LOn m-LUnder m
Wherein, the data L that certain moment all digital optical sensors measuremiWith intermediate value LmMAbsolute value of the difference be greater than dL absolute value
Data be invalid data, reject invalid data after, arithmetic mean of instantaneous value is sought to remaining data, obtains the ambient light illumination L;
First fuzzy control rule in the step 2 includes:
Rule 1: when the ambient light illumination L is less than 20lx and is greater than 15lx, start lighting system, and regulate and control illumination output power
For 50% rated power;
Rule 2: when the ambient light illumination L is less than or equal to 15lx, regulation illumination output power is 100% rated power;
Rule 3: when the ambient light illumination L is greater than or equal to 20lx, lighting system is closed;
Work as the ambient light illumination L down to default ambient light illumination lower limit value L in the step 2mAfterwards, by the ambient light illumination L and ring
Input of the border illumination change rate dL/dt as the first fuzzy controller FC1, the first fuzzy controller FC1 is according to the first mould
Paste control rule exports switch lamp operational order and includes:
The ambient light illumination change rate that ambient light illumination L and sampling are calculated the first fuzzy controller FC1As input;
The membership function S to turn on light with illumination output power regulation as output;Ambient light illumination change rate functionΔ l (k)=[l (k)-
L (k-1)]/T, T is the sampling period;
Definition corresponds to the mould of rule 1, rule 2 and rule 3 respectively on ambient light illumination change rate domain L={ l | 0≤l≤30 }
Paste collection " dark ", " dim ", " bright ";Membership function S uses Sigmoid type or bell, corresponds to rule 1, rule 2 and rule
Then 3 membership function is respectively following three formula:
In domainUpper definition { is born NB greatly, is born for measuring the fuzzy set of ambient light illumination variation speed
Small NS, zero O, just small PS, honest PB }, membership function uses triangle or trapezoidal;
In domainIt is upper definition for measure lighting system output power variation fuzzy set S10, N, S01,
S12, S02 }, wherein S10 expression turn off the light, i.e., output power be 30%~100% any value when, as long as ambient illumination values from
When 20 to 0lx, output power is transferred to 0;N indicates do-nothing operation;S01 expression is turned on light, and is 50% work with output power;S12 table
Show that output power becomes 100% work from 50%;S02 expression is turned on light and output power is 100% work;Its membership function is adopted
Use triangle;
First fuzzy control rule includes:
Adaptive Gauss background model is constructed to the infrared image in the step 3, isolating foreground pixel includes:
Identification characteristic value in the infrared image is the brightness of pixel, by the picture of same position in continuous sequence infrared image
A time series { X is seen in the brightness of element in the time domain as1, X2..., Xt, then the observation of current pixel probability is high using mixing
This model tormulation are as follows:
Here ωi,tWeight for i-th of Gaussian Profile in time t, ui,t、σi,tThe mean value and mark of respectively i-th Gaussian function
It is quasi- poor;K is the number of Gaussian Profile included in gauss hybrid models, and size depends on system free memory and system
Computing capability, η is Gaussian probability-density function;
Using above-mentioned model, initialization gauss hybrid models predetermined, high variance, k Gaussian Profile of small weight for mean value;
For a new pixel, when its characteristic value is located in 2.5 Standard deviation-Ranges of a certain Gaussian Profile, then it is assumed that itself and this
Gaussian Profile pairing;Then all Gaussian Profile weights are updated by following formula according to pairing situation:
ωi,t=(1- α) ωi,t-1+α(Mi,t), i=1,2 ..., k
Wherein α is learning parameter, Mi,tThen for current pixel Gaussian Profile match mark, if there is a Gaussian Profile with
Current pixel matches then Mi,t=1, otherwise Mi,t=0;After being updated to weight, normalizing is carried out to a series of newly-generated weights
Change, the parameter for the Gaussian Profile matched updates are as follows:
μt=(1- ρ) μt-1+ρ(Xt)
HereThe parameter of other Gaussian Profiles is then constant;If there is no any pairing, then
The smallest Gaussian Profile of probability value is replaced with into the Gaussian Profile that a mean value is the pixel value newly observed, high variance, small weight,
Aforesaid operations are executed to next frame image;
In order to judge the prospect or background type of the pixel newly observed, k Gaussian Profile descending arranged according to the value of ω/σ,
Since the pixel in background image has high weight and low variance, ratio between the two is bigger, belongs to the possibility of background
Property it is higher, herein using weights sum greater than background threshold T foremost b Gaussian Profile by as background model, that is, have:
Background model determine after, can in image background pixel and foreground pixel classify;If the picture newly observed
Element and some pairing in the b Gaussian Profile, then it is assumed that it belongs to background, otherwise belongs to prospect;
The step 5 includes:
Second fuzzy controller FC2 input quantity is to obtain the peak value number M of curve by brightness upright projection in each subregion, and M exists
Domain [0,720] is divided into 4 grades, respectively { fewer, few, many, more };
For convenient for flexibly modifying fuzzy rule for different speed limit requirements, fuzzy set bear big NB, bear small NS, zero O, it is just small
PS, honest PB } subset QC be changed to fuzzy number be { -1,0,1,2 };Its membership function chooses triangle and trapezoidal;Output control
Lighting system concrete operations are the regulation of output power, as output power U3Domain be [0,1], be divided into 8 grades
{ 30%, 40%, 50%, 60%, 70%, 80%, 90%, 100% }, corresponding fuzzy number are { 0,1,2,3,4,5,6,7 }, are subordinate to
Membership fuction chooses triangle;
Second fuzzy control rule includes:
2. the method according to claim 1, wherein the step 1 includes:
The digital optical sensor installed by each subregion in the parking lot tests the illuminance of each subregion, and benefit respectively
Blunder error is rejected with multisensor Data Fusion technology, the ambient light illumination L is merged into, as first fuzzy controller
The input of FC1.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611062136.0A CN106604496B (en) | 2016-11-24 | 2016-11-24 | Parking lot lighting systems control method based on fuzzy technology |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611062136.0A CN106604496B (en) | 2016-11-24 | 2016-11-24 | Parking lot lighting systems control method based on fuzzy technology |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106604496A CN106604496A (en) | 2017-04-26 |
CN106604496B true CN106604496B (en) | 2019-04-05 |
Family
ID=58594921
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611062136.0A Active CN106604496B (en) | 2016-11-24 | 2016-11-24 | Parking lot lighting systems control method based on fuzzy technology |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106604496B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107883529A (en) * | 2017-10-30 | 2018-04-06 | 海南电网有限责任公司电力科学研究院 | A kind of central air conditioner system temprature control method based on fuzzy technology |
CN110262421A (en) * | 2019-06-21 | 2019-09-20 | 深圳市美兆环境股份有限公司 | The control method and device of production equipment |
CN117500126B (en) * | 2023-12-29 | 2024-03-22 | 深圳市拓安科技有限公司 | Method and system for realizing low-level illumination |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050069200A1 (en) * | 2003-09-30 | 2005-03-31 | Sharp Laboratories Of America, Inc. | Systems and methods for illuminant model estimation |
CN104144537A (en) * | 2013-05-08 | 2014-11-12 | 株式会社理光 | Intelligent lighting control method, device and system |
CN104869708A (en) * | 2015-05-13 | 2015-08-26 | 浙江名创光电科技有限公司 | Road tunnel LED self-adaptive illumination control system based on fuzzy control technology |
CN106028584A (en) * | 2016-05-23 | 2016-10-12 | 电子科技大学 | Gradient extremum search algorithm-based double closed-loop lighting energy-saving control method |
CN106028585A (en) * | 2016-05-23 | 2016-10-12 | 电子科技大学 | Newton extremum search algorithm-based double closed-loop lighting energy-saving control method |
-
2016
- 2016-11-24 CN CN201611062136.0A patent/CN106604496B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050069200A1 (en) * | 2003-09-30 | 2005-03-31 | Sharp Laboratories Of America, Inc. | Systems and methods for illuminant model estimation |
CN104144537A (en) * | 2013-05-08 | 2014-11-12 | 株式会社理光 | Intelligent lighting control method, device and system |
CN104869708A (en) * | 2015-05-13 | 2015-08-26 | 浙江名创光电科技有限公司 | Road tunnel LED self-adaptive illumination control system based on fuzzy control technology |
CN106028584A (en) * | 2016-05-23 | 2016-10-12 | 电子科技大学 | Gradient extremum search algorithm-based double closed-loop lighting energy-saving control method |
CN106028585A (en) * | 2016-05-23 | 2016-10-12 | 电子科技大学 | Newton extremum search algorithm-based double closed-loop lighting energy-saving control method |
Also Published As
Publication number | Publication date |
---|---|
CN106604496A (en) | 2017-04-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106604496B (en) | Parking lot lighting systems control method based on fuzzy technology | |
Wen et al. | Towards embedded wireless-networked intelligent daylighting systems for commercial buildings | |
CN105050246B (en) | A kind of method and mobile terminal of mobile terminal regulation lamplight brightness | |
WO2019237596A1 (en) | Scene-based intelligent lighting integrated control system and method | |
CN108419339B (en) | L oRa technology-based multifunctional L ED intelligent street lamp system | |
CN109951936A (en) | A kind of lighting control system and method adjusted according to different application scene intelligent | |
CN101393603A (en) | Method for recognizing and detecting tunnel fire disaster flame | |
CN105142288B (en) | The intelligent management system and method for a kind of classroom illumination | |
CN106842356B (en) | There is nobody detection method and detection system in a kind of interior | |
CN101711079B (en) | Classroom illumination wireless detection and control device and method | |
CN205029942U (en) | Classroom lighting system based on singlechip | |
CN106744091A (en) | A kind of elevator debugging method and system | |
CN107479388A (en) | A kind of classroom central air-conditioning and the energy-saving control system and control method of illumination | |
CN106028525A (en) | Differential evolution algorithm based adaptive indoor dimming method and system | |
CN110260371A (en) | Kitchen ventilator intelligence control system and method based on multisensor | |
CN115835463A (en) | Intelligent lighting control system | |
CN107168075A (en) | The control method of building control system and its electrical equipment, device | |
CN108282943A (en) | Illumination control method and device | |
Xiong et al. | Efficient learning of personalized visual preferences in daylit offices: An online elicitation framework | |
CN106681166A (en) | Energy-saving control system of building | |
CN104768276A (en) | 3D lighting monitoring method, 3D lighting monitoring device and 3D lighting monitoring system | |
CN201369859Y (en) | Street lamp-dimming energy-saving control system | |
CN109219206A (en) | A kind of intelligent home lamplight control system and method | |
CN108958056A (en) | Office building energy-saving control system and control method based on Internet of Things | |
CN115862315B (en) | Traffic light control method and device for smart city multi-source heterogeneous data stream |
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 | ||
CP03 | Change of name, title or address |
Address after: 570105 No. 23 Hairuihou Road, Longhua District, Haikou City, Hainan Province Co-patentee after: Nanjing Sifang Epower Electric Power Automation Co., Ltd. Patentee after: Hainan Electric Power Grid Co., Ltd. Electric Power Research Institute Address before: 570203 13th Floor, Xinheng Building, 123-8 Binhai Avenue, Haikou City, Hainan Province Co-patentee before: Nanjing Sifang Epower Electric Power Automation Co., Ltd. Patentee before: Hainan Power Technology Research Institute |
|
CP03 | Change of name, title or address |