Brightness self-adaptive adjusting method of bridge landscape lighting system

Abstract

The invention discloses a brightness adaptive adjustment method for a bridge landscape lighting system, and particularly relates to the technical field of brightness adaptive adjustment, and the method comprises the steps: obtaining an anomaly detection coefficient through processing a sensor data error coefficient and a power supply voltage fluctuation coefficient, and comparing the anomaly detection coefficient with an anomaly detection coefficient threshold value, and whether the brightness of the bridge landscape is adaptively adjusted or not is judged according to the comparison result, so that the operation fault of the bridge landscape lighting system can be detected in time, and once the operation fault of the bridge landscape lighting system is more obvious, the brightness of the bridge landscape can be automatically adjusted. The brightness of the bridge landscape can be accurately and adaptively adjusted through a fuzzy control algorithm, so that the bridge landscape lighting system has stability and reliability in an extreme environment, meanwhile, energy consumption is reduced, and the overall efficiency and safety of bridge lighting are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of adaptive brightness adjustment, and in particular to a method for adaptive brightness adjustment of a bridge landscape lighting system. Background Art

[0002] Bridge landscape lighting systems play an important role in urban infrastructure. They not only enhance the visual effects of bridges and the beauty of urban nightscapes, but also ensure the safety of nighttime driving and pedestrian traffic to a certain extent. However, traditional bridge landscape lighting systems generally have problems such as high energy consumption, lack of intelligent adjustment, and insufficient adaptability to changes in the external environment. Especially under extreme weather conditions, such as haze, heavy rain, strong winds, or power outages, the stability and functionality of traditional systems face severe challenges.

[0003] In actual applications, severe weather may cause ambient light sensors to fail or data to be inaccurate, making it impossible to accurately control light brightness. At the same time, large-scale power outages threaten the normal operation of the lighting system and may cause traffic and pedestrian safety hazards. In addition, the differences in brightness requirements under different weather conditions further exacerbate the need for intelligent adaptive adjustment functions. For example, higher brightness is required in foggy weather to penetrate low-visibility environments, while strong winds and rainstorms may damage the physical structure of the equipment. Summary of the invention

[0004] The purpose of the present invention is to solve the problem and propose a brightness adaptive adjustment method for a bridge landscape lighting system.

[0005] In a first aspect of the present invention, a method for adaptively adjusting brightness of a bridge landscape lighting system is first proposed, the method comprising the following steps:

[0006] Collecting sensor data error information of the bridge landscape lighting system, and obtaining a sensor data error coefficient according to the collected sensor data error information;

[0007] Collecting power supply voltage fluctuation information of the bridge landscape lighting system, and obtaining a power supply voltage fluctuation coefficient based on the collected power supply voltage fluctuation information;

[0008] The sensor data error coefficient and the power supply voltage fluctuation coefficient are processed, and an anomaly detection model is constructed to obtain an anomaly detection coefficient. The anomaly detection coefficient is compared with the anomaly detection coefficient threshold, and it is determined whether to adaptively adjust the brightness of the bridge landscape according to the comparison result;

[0009] When the brightness of the bridge landscape needs to be adaptively adjusted, the brightness of the bridge landscape is adaptively adjusted according to the fuzzy control algorithm.

[0010] Optionally, the sensor data error coefficient includes:

[0011] Get the actual uploaded data value and historical reference value of the sensor at different times in time T, and mark the actual uploaded data value and historical reference value as S 实 l and S 历 , l represents the number of the actual uploaded data value of the sensor at different times, l = 1, 2, 3, 4, ..., L, L is a positive integer;

[0012] According to S 实 l and S 历 The sensor data error coefficient CW is obtained, and the calculation formula is:

[0013] Optionally, the power supply voltage fluctuation coefficient includes:

[0014] Get the voltage signal data at different times within the time T, and mark the voltage signal data as

[0015] V(t), select the Daubechies wavelet basis function to perform J-layer wavelet decomposition on the voltage signal data V(t), as follows: In the formula, A J is the approximation coefficient of the last layer, representing the low-frequency part of the voltage signal, D j is the detail coefficient of the jth layer, representing the high-frequency part of the voltage signal at this scale, j = 1, 2, 3, 4, ..., J, where J is a positive integer;

[0016] Calculate the standard deviation of the wavelet coefficients using the formula:

[0017] In the formula, σD j is the standard deviation of the wavelet coefficients,

[0018] D j The average value, N j is the length of the j-th layer detail coefficient, i = 1, 2, 3, 4, ..., N j ;

[0019] Calculate the weighted voltage fluctuation coefficient using the following formula: In the formula,

[0020] C v is the weighted voltage fluctuation coefficient, w j is the weight coefficient of the j-th layer detail coefficient;

[0021] Calculate the power supply voltage fluctuation coefficient using the following formula: Where DY is the power supply voltage fluctuation coefficient, is the average value of the voltage signal.

[0022] Optionally, the sensor data error coefficient and the power supply voltage fluctuation coefficient are processed, and an abnormality detection model is constructed to obtain an abnormality detection coefficient. The specific formula is:

[0023]

[0024] Wherein, Yjcx is the abnormality detection coefficient, CW and DY are the sensor data error coefficient and the power supply voltage fluctuation coefficient, respectively, α and β are the preset proportional coefficients of the sensor data error coefficient and the power supply voltage fluctuation coefficient, respectively, and α and β are both greater than 0.

[0025] Optionally, the anomaly detection coefficient is compared with the anomaly detection coefficient threshold, and it is determined whether to adaptively adjust the brightness of the bridge landscape according to the comparison result;

[0026] If the anomaly detection coefficient is greater than or equal to the anomaly detection coefficient threshold, it means that the stability of the bridge landscape lighting system is poor. At this time, the brightness of the bridge landscape needs to be adaptively adjusted to ensure the normal operation of the bridge landscape lighting system and the safety of the equipment;

[0027] If the anomaly detection coefficient is less than the anomaly detection coefficient threshold, it means that the bridge landscape lighting system operates stably and there is no need to adaptively adjust the brightness of the bridge landscape.

[0028] Optionally, when the brightness of the bridge landscape needs to be adaptively adjusted, the brightness of the bridge landscape is adaptively adjusted according to a fuzzy control algorithm:

[0029] The sensor data error coefficient and the power supply voltage fluctuation coefficient are used as the input items of the fuzzy rules, and the brightness of the bridge landscape is used as the output item;

[0030] Fuzzify the input items and convert the exact input values ​​into fuzzy sets;

[0031] Define fuzzy rules based on the fuzzy sets of input items to map input items to output items;

[0032] According to the fuzzy rules, the input items are inferred to determine the fuzzy value of the output items;

[0033] For each rule, calculate the membership of its predecessor and take the minimum value as the activation of the rule;

[0034] Synthesize the results of all rules and calculate the fuzzy set of output items;

[0035] The fuzzy value of the output item is converted into an exact value, and the brightness of the bridge landscape is output according to the defuzzification result.

[0036] Beneficial effects of the present invention:

[0037] The present invention proposes a method for adaptively adjusting the brightness of a bridge landscape lighting system. The method obtains the sensor data error coefficient and the power supply voltage fluctuation coefficient for processing to obtain the abnormality detection coefficient, compares the abnormality detection coefficient with the abnormality detection coefficient threshold, and judges whether to adaptively adjust the brightness of the bridge landscape based on the comparison result. In this way, the operation failure of the bridge landscape lighting system can be detected in time. Once the operation failure of the bridge landscape lighting system is more significant, the brightness of the bridge landscape can be accurately adaptively adjusted through a fuzzy control algorithm, so that the bridge landscape lighting system has stability and reliability in extreme environments, while reducing energy consumption and improving the overall efficiency and safety of bridge lighting. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The present invention will be further described below in conjunction with the accompanying drawings.

[0039] Figure 1 A framework diagram of a brightness adaptive adjustment method for a bridge landscape lighting system provided by the present invention. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative work shall fall within the scope of protection of the present invention.

[0042] The embodiment of the present invention provides a method for adaptively adjusting the brightness of a bridge landscape lighting system. Figure 1 , Figure 1 A framework diagram of a brightness adaptive adjustment method for a bridge landscape lighting system provided by an embodiment of the present invention. The method comprises the following steps:

[0043] Collecting sensor data error information of the bridge landscape lighting system, and obtaining a sensor data error coefficient according to the collected sensor data error information;

[0044] Collecting power supply voltage fluctuation information of the bridge landscape lighting system, and obtaining a power supply voltage fluctuation coefficient based on the collected power supply voltage fluctuation information;

[0045] The sensor data error coefficient and the power supply voltage fluctuation coefficient are processed, and an anomaly detection model is constructed to obtain an anomaly detection coefficient. The anomaly detection coefficient is compared with the anomaly detection coefficient threshold, and it is determined whether to adaptively adjust the brightness of the bridge landscape according to the comparison result;

[0046] When the brightness of the bridge landscape needs to be adaptively adjusted, the brightness of the bridge landscape is adaptively adjusted according to the fuzzy control algorithm.

[0047] Based on the brightness adaptive adjustment method of a bridge landscape lighting system provided by an embodiment of the present invention, the sensor data error coefficient and the power supply voltage fluctuation coefficient are processed in the above manner to obtain the abnormal detection coefficient, and the abnormal detection coefficient and the abnormal detection coefficient threshold are compared, and it is determined whether to adaptively adjust the brightness of the bridge landscape according to the comparison result. In this way, the operation failure of the bridge landscape lighting system can be detected in time. Once the operation failure of the bridge landscape lighting system is more significant, the brightness of the bridge landscape can be accurately adaptively adjusted through the fuzzy control algorithm, so that the bridge landscape lighting system has stability and reliability in extreme environments, while reducing energy consumption and improving the overall efficiency and safety of bridge lighting. This method can not only dynamically adapt to environmental changes, but also maintain the basic functions of the lighting system through an independent energy storage system or a microgrid power supply architecture when power is off.

[0048] In one embodiment, the sensor data error coefficient includes:

[0049] Get the actual uploaded data value and historical reference value of the sensor at different times in time T, and mark the actual uploaded data value and historical reference value as S 实 l and S 历 , l represents the number of the actual uploaded data value of the sensor at different times, l = 1, 2, 3, 4, ..., L, L is a positive integer;

[0050] According to S 实 l and S 历 The sensor data error coefficient CW is obtained, and the calculation formula is:

[0051] It should be noted that the historical reference value is the long-term observed average under stable operation of the bridge landscape lighting system.

[0052] It should be noted that the smaller the sensor data error coefficient is, the smaller the sensor data error is, and the more stable the operation of the bridge landscape lighting system is; the larger the sensor data error coefficient is, the larger the sensor data error is, and the worse the operation status of the bridge landscape lighting system is.

[0053] It should be noted that the sensor data error coefficient refers to the indicator of the degree of deviation between the actual data collected by each sensor in the bridge landscape lighting system and the historical reference value. It is used to evaluate the stability of the system operation status and the reliability of the sensor data. The sensor data error coefficient reflects the accuracy of the real-time data collected by the sensor in the bridge landscape lighting system and the stability of the system operation status. It is mainly used for:

[0054] Anomaly detection: By monitoring the change in the error coefficient, it is possible to determine whether the sensor is malfunctioning or whether the environment has changed drastically.

[0055] Operation optimization: When the sensor data error coefficient is too large, the brightness adaptive adjustment mechanism can be triggered to dynamically adjust the system status to improve operation stability.

[0056] Long-term maintenance: Continuously high errors may indicate that the sensor needs calibration or the system needs repair.

[0057] Dynamic response to external environment: The sensor data error coefficient combined with the fuzzy control algorithm can quickly adjust the brightness according to actual lighting needs, avoiding the fixed mode of overbrightness or overdarkness of traditional lighting systems.

[0058] Enhanced adaptability: In complex weather conditions (such as haze, heavy rain) or power supply fluctuations, the brightness is adjusted through the sensor data error coefficient to ensure the safety of pedestrians and vehicles while reducing energy consumption.

[0059] Energy saving and emission reduction: By accurately evaluating the credibility of sensor data, brightness can be adjusted only when necessary to avoid excessive lighting and reduce energy waste.

[0060] Optimize resource allocation: Sensor data error coefficients can be used to evaluate the operating status of different areas or equipment, and prioritize maintenance or adjustments to areas with larger errors, thereby optimizing management and resource allocation.

[0061] In one embodiment, the power supply voltage fluctuation coefficient includes:

[0062] The voltage signal data at different times within the time T are obtained, the voltage signal data is marked as V(t), and the Daubechies wavelet basis function is selected to perform J-layer wavelet decomposition on the voltage signal data V(t), as follows: In the formula, A J is the approximation coefficient of the last layer, representing the low-frequency part of the voltage signal, D j is the detail coefficient of the jth layer, representing the high-frequency part of the voltage signal at this scale, j = 1, 2, 3, 4, ..., J, where J is a positive integer;

[0063] Calculate the standard deviation of the wavelet coefficients using the formula:

[0064] In the formula, σD j is the standard deviation of the wavelet coefficients,

[0065] D j The average value, N j is the length of the j-th layer detail coefficient, i = 1, 2, 3, 4, ..., N j ;

[0066] Calculate the weighted voltage fluctuation coefficient using the following formula: In the formula,

[0067] C v is the weighted voltage fluctuation coefficient, w j is the weight coefficient of the j-th layer detail coefficient;

[0068] Calculate the power supply voltage fluctuation coefficient using the following formula: Where DT is the power supply voltage fluctuation coefficient, is the average value of the voltage signal.

[0069] It should be noted that the weight coefficient is set according to actual conditions.

[0070] It should be noted that the smaller the power supply voltage fluctuation coefficient, the smaller the fluctuation degree of the power supply voltage, and the more stable the operation of the bridge landscape lighting system; the larger the power supply voltage fluctuation coefficient, the greater the fluctuation degree of the power supply voltage, and the worse the operating state of the bridge landscape lighting system.

[0071] It should be noted that the power supply voltage fluctuation coefficient refers to the stability of the power supply voltage in the bridge landscape lighting system. Voltage fluctuations may be affected by factors such as external power grid fluctuations and equipment load changes, which may limit the normal operation of the system. In order to ensure the reliability and stability of the system, it is necessary to monitor voltage fluctuations in real time and evaluate its impact on system operation by calculating the power supply voltage fluctuation coefficient. It is mainly used for:

[0072] Early warning function: By monitoring the voltage fluctuation coefficient, the system can detect the fluctuation of the power supply voltage in real time. If the voltage fluctuation coefficient exceeds the set threshold, it means that the voltage fluctuation is abnormal. The system can issue an alarm in advance to avoid equipment failure or damage due to abnormal voltage.

[0073] Adaptive adjustment: When the voltage fluctuates greatly (such as unstable power grid, voltage surge or drop), the working mode of systems such as bridge landscape lighting can be adjusted according to the voltage fluctuation coefficient. For example, by reducing the brightness or automatically adjusting the power supply voltage, the burden on the equipment is reduced and the system can be kept running stably.

[0074] Dynamically adjust brightness: When the voltage fluctuation coefficient is large, the system can use algorithms such as fuzzy control to automatically adjust the lighting brightness to avoid excessive consumption of electricity when the voltage is unstable. This can effectively reduce energy waste, especially during peak load periods, and maintain energy efficiency.

[0075] Dynamic response to external environment: The sensor data error coefficient combined with the fuzzy control algorithm can quickly adjust the brightness according to actual lighting needs, avoiding the fixed mode of overbrightness or overdarkness of traditional lighting systems.

[0076] Energy saving benefits: By adjusting the system operation mode according to voltage fluctuations, the system can avoid overload and reduce ineffective energy waste. Especially in bridge landscape lighting, dynamically adjusting the brightness according to the voltage fluctuation coefficient can achieve energy saving and extend the life of the equipment.

[0077] Power supply quality assessment: Voltage fluctuation coefficient can be used to assess power supply quality. If the voltage fluctuation coefficient is high, it may indicate that the power grid is unstable, such as frequent voltage drops and voltage surges. Through this assessment, power companies or relevant departments can adjust and optimize the power grid in a timely manner to improve the overall power supply quality.

[0078] Brightness adjustment: In applications such as bridge landscape lighting, changes in brightness directly affect user experience and visual effects. By precisely controlling the voltage fluctuation coefficient, the system can properly adjust the brightness when the voltage fluctuates greatly, ensuring that the lighting effect always remains at its best, and avoiding uneven or unstable lighting due to voltage fluctuations.

[0079] Reduce flicker and light pollution: Voltage fluctuations can cause flicker or irregular brightness changes in the lighting system, which not only affects the visual experience but may also cause light pollution. Real-time monitoring and adjustment of the voltage fluctuation coefficient can effectively reduce this situation and improve the overall user experience.

[0080] In one embodiment, the sensor data error coefficient and the power supply voltage fluctuation coefficient are processed, and an abnormality detection model is constructed to obtain an abnormality detection coefficient. The specific formula is:

[0081]

[0082] Wherein, Yjcx is the abnormality detection coefficient, CW and DY are the sensor data error coefficient and the power supply voltage fluctuation coefficient, respectively, α and β are the preset proportional coefficients of the sensor data error coefficient and the power supply voltage fluctuation coefficient, respectively, and α and β are both greater than 0.

[0083] The anomaly detection coefficient is compared with the anomaly detection coefficient threshold, and whether to adaptively adjust the brightness of the bridge landscape is determined according to the comparison result;

[0084] If the anomaly detection coefficient is greater than or equal to the anomaly detection coefficient threshold, it means that the stability of the bridge landscape lighting system is poor. At this time, the brightness of the bridge landscape needs to be adaptively adjusted to ensure the normal operation of the bridge landscape lighting system and the safety of the equipment;

[0085] If the anomaly detection coefficient is less than the anomaly detection coefficient threshold, it means that the bridge landscape lighting system operates stably and there is no need to adaptively adjust the brightness of the bridge landscape.

[0086] In one embodiment, when the brightness of the bridge landscape needs to be adaptively adjusted, the brightness of the bridge landscape is adaptively adjusted according to the fuzzy control algorithm:

[0087] The sensor data error coefficient and the power supply voltage fluctuation coefficient are used as the input items of the fuzzy rules, and the brightness of the bridge landscape is used as the output item;

[0088] Fuzzify the input items and convert the exact input values ​​into fuzzy sets;

[0089] Define fuzzy rules based on the fuzzy sets of input items to map input items to output items;

[0090] According to the fuzzy rules, the input items are inferred to determine the fuzzy value of the output items;

[0091] For each rule, calculate the membership of its predecessor and take the minimum value as the activation of the rule;

[0092] Synthesize the results of all rules and calculate the fuzzy set of output items;

[0093] The fuzzy value of the output item is converted into an exact value, and the brightness of the bridge landscape is output according to the defuzzification result.

[0094] It should be noted that the above steps are explained as follows:

[0095] 1. Take the sensor data error coefficient and the power supply voltage fluctuation coefficient as the input of the fuzzy rule, and the brightness of the bridge landscape as the output:

[0096] Input items: sensor data error coefficient and power supply voltage fluctuation coefficient. These two factors are used as input variables of fuzzy rules.

[0097] Output item: the brightness of the bridge landscape, which reflects the need for more accurate adaptive adjustment of the brightness of the bridge landscape when the stability of the bridge landscape lighting system is poor, and is the ultimate target output;

[0098] The relationship between these inputs and outputs is described and mapped by fuzzy rules. The design of fuzzy rules is based on experience or domain knowledge, and the purpose is to transform different input situations into appropriate output results.

[0099] 2. Fuzzify the input items and convert the exact input values ​​into fuzzy sets:

[0100] Fuzzification is the process of converting the precise numerical values ​​of input items into fuzzy sets; for example, sensor data error coefficients and power supply voltage fluctuation coefficients are usually precise numerical values ​​or range values ​​(such as "medium", "high", and "low"), while in fuzzy logic, they are divided into several fuzzy sets;

[0101] Fuzzy sets usually include levels such as "low", "medium" and "high". The specific classification criteria can be determined according to actual needs or data distribution; for example:

[0102] Sensor data error coefficients can be classified as "low", "medium" and "high";

[0103] The supply voltage fluctuation coefficient can be divided into "low", "medium" and "high";

[0104] The actual value of each input variable is converted to a certain membership degree in the fuzzy set according to its corresponding membership function; for example, a "sensor data error coefficient" may belong to the "medium" set with a membership degree of 0.6 and to the "high" set with a membership degree of 0.4;

[0105] 3. Define fuzzy rules based on the fuzzy sets of input items to map input items to output items:

[0106] Fuzzy rules are the bridge that maps input items to output items. According to the fuzzy set of input variables, appropriate rules are designed to describe the impact of each input on the output. For example:

[0107] If the sensor data error coefficient is "high" and the power supply voltage fluctuation coefficient is "high", the brightness of the bridge landscape is "high";

[0108] If the sensor data error coefficient is "low" and the power supply voltage fluctuation coefficient is "low", the brightness of the bridge landscape is "low";

[0109] These rules are expressed using fuzzy sets and form a series of rules; for example:

[0110] If the sensor data error coefficient is high and the power supply voltage fluctuation coefficient is high, the brightness of the bridge landscape is high;

[0111] If the sensor data error coefficient is low and the power supply voltage fluctuation coefficient is low, the brightness of the bridge landscape is low;

[0112] 4. According to the fuzzy rules, reason about the input items and determine the fuzzy value of the output items:

[0113] Fuzzy reasoning is the process of mapping the input fuzzy value to the output fuzzy set through rules; each rule will give an output result, but the output result is still fuzzy; the reasoning process is to determine the fuzzy value of the output item through the activation of the rules according to the fuzzy value of each input item;

[0114] The reasoning process matches the input value with the fuzzy rules to obtain the output corresponding to different rules; for example, if the "sensor data error coefficient" is "high", it meets the rule "sensor data error coefficient is high, power supply voltage fluctuation coefficient is high, then the brightness of the bridge landscape is high", and a "high" membership degree is inferred under this rule;

[0115] 5. For each rule, calculate the membership of its predecessor and take the minimum value as the activation of the rule:

[0116] For each rule, calculate the membership of its premise (input item); the membership usually refers to the degree to which the input value belongs to a fuzzy set, ranging from 0 to 1;

[0117] For example, if the membership of "sensor data error coefficient" to the "high" set is 0.8, and the membership of "supply voltage fluctuation coefficient" to the "medium" set is 0.6, then the activation degree of this rule is min(0.8,0.6)=0.6;

[0118] Activation reflects the strength of the rule, that is, the degree to which the rule contributes to the output;

[0119] 6. Synthesize the results of all rules and calculate the fuzzy set of output items:

[0120] The results of all rules need to be synthesized; synthesis means weighting and summing the output (fuzzy value) of each rule according to its activation degree to obtain the final output fuzzy set;

[0121] For example, if the activations of two rules are 0.6 and 0.8 respectively, and the outputs are “high” and “medium”, then according to the weighted average method, these two fuzzy values ​​are synthesized according to the activations to obtain the final output fuzzy set;

[0122] 7. Convert the fuzzy value of the output item to an exact value, and output the brightness of the bridge landscape based on the defuzzification result:

[0123] Defuzzification is the process of converting fuzzy sets into precise values; commonly used defuzzification methods include:

[0124] Centroid method: Get a specific value by calculating the centroid of the fuzzy set;

[0125] Maximum membership method: select the fuzzy value with the largest membership as the final precise value;

[0126] For example, the “center of gravity” of the fuzzy output set can be obtained as the final output result through the center of gravity method, which represents the brightness of the bridge landscape.

[0127] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A brightness adaptive adjustment method for a bridge landscape lighting system, characterized in that: The method comprises the following steps: Collecting sensor data error information of the bridge landscape lighting system, and obtaining a sensor data error coefficient according to the collected sensor data error information; Collecting power supply voltage fluctuation information of the bridge landscape lighting system, and obtaining a power supply voltage fluctuation coefficient based on the collected power supply voltage fluctuation information; The sensor data error coefficient and the power supply voltage fluctuation coefficient are processed, and an anomaly detection model is constructed to obtain an anomaly detection coefficient. The anomaly detection coefficient is compared with the anomaly detection coefficient threshold, and it is determined whether to adaptively adjust the brightness of the bridge landscape according to the comparison result; When the brightness of the bridge landscape needs to be adaptively adjusted, the brightness of the bridge landscape is adaptively adjusted according to the fuzzy control algorithm.

2. The brightness adaptive adjustment method of a bridge landscape lighting system according to claim 1 is characterized in that: The sensor data error coefficients include: Get the actual uploaded data value and historical reference value of the sensor at different times in time T, and mark the actual uploaded data value and historical reference value as and , Indicates the number of the actual uploaded data value of the sensor at different times. =1, 2, 3, 4, ..., , is a positive integer; according to and Get the sensor data error coefficient , the calculation formula is: .

3. The brightness adaptive adjustment method of a bridge landscape lighting system according to claim 1 is characterized in that: The power supply voltage fluctuation coefficient includes: Get the voltage signal data at different times within the time T, and mark the voltage signal data as , select Daubechies wavelet basis function for voltage signal data Perform J-layer wavelet decomposition as follows: , where is the approximation coefficient of the last layer, representing the low-frequency part of the voltage signal, is the detail coefficient of the jth layer, which represents the high-frequency part of the voltage signal at this scale. =1, 2, 3, 4, ..., , is a positive integer; Calculate the standard deviation of the wavelet coefficients using the formula: , where is the standard deviation of the wavelet coefficients, for The average value of is the length of the j-th layer detail coefficient, =1, 2, 3, 4, ..., ; Calculate the weighted voltage fluctuation coefficient using the following formula: , where is the weighted voltage fluctuation coefficient, is the weight coefficient of the j-th layer detail coefficient; Calculate the power supply voltage fluctuation coefficient using the following formula: , where is the power supply voltage fluctuation coefficient, is the average value of the voltage signal.

4. The brightness adaptive adjustment method of a bridge landscape lighting system according to claim 1 is characterized in that: The sensor data error coefficient and the power supply voltage fluctuation coefficient are processed, and an abnormality detection model is constructed to obtain an abnormality detection coefficient. The specific formula is: In the formula, is the anomaly detection coefficient, , They are the sensor data error coefficient and the power supply voltage fluctuation coefficient, are preset proportional coefficients of sensor data error coefficient and power supply voltage fluctuation coefficient respectively, and Both are greater than 0.

5. The brightness adaptive adjustment method of a bridge landscape lighting system according to claim 4 is characterized in that: The anomaly detection coefficient is compared with the anomaly detection coefficient threshold, and whether to adaptively adjust the brightness of the bridge landscape is determined according to the comparison result; If the anomaly detection coefficient is greater than or equal to the anomaly detection coefficient threshold, it means that the stability of the bridge landscape lighting system is poor. At this time, the brightness of the bridge landscape needs to be adaptively adjusted to ensure the normal operation of the bridge landscape lighting system and the safety of the equipment; If the anomaly detection coefficient is less than the anomaly detection coefficient threshold, it means that the bridge landscape lighting system operates stably and there is no need to adaptively adjust the brightness of the bridge landscape.

6. The brightness adaptive adjustment method of a bridge landscape lighting system according to claim 5 is characterized in that: When the brightness of the bridge landscape needs to be adaptively adjusted, the brightness of the bridge landscape is adaptively adjusted according to the fuzzy control algorithm: The sensor data error coefficient and the power supply voltage fluctuation coefficient are used as the input items of the fuzzy rules, and the brightness of the bridge landscape is used as the output item; Fuzzify the input items and convert the exact input values ​​into fuzzy sets; Define fuzzy rules based on the fuzzy sets of input items to map input items to output items; According to the fuzzy rules, the input items are inferred to determine the fuzzy value of the output items; For each rule, calculate the membership of its predecessor and take the minimum value as the activation of the rule; Synthesize the results of all rules and calculate the fuzzy set of output items; The fuzzy value of the output item is converted into an exact value, and the brightness of the bridge landscape is output according to the defuzzification result.

Images