Tunnel lighting intelligent control data analysis method and system based on cloud platform

Abstract

The present invention discloses a cloud platform-based tunnel lighting intelligent control data analysis method and system, which relates to the field of electric energy regulation technology and is used to solve the potential safety hazard problem of the light difference inside and outside the tunnel not being supplemented due to the instantaneous closure of transition lights. The method comprises collecting the grid load of the tunnel lighting area, obtaining the lighting standard of the lighting area, calculating the grid load schedulability of the tunnel transition lights, judging the grid load degree of the tunnel transition lights by the current of the tunnel transition lights, obtaining the tunnel length, using the K nearest neighbor algorithm to classify the tunnel potential, setting the road section for distance testing, obtaining the vehicle speed and swing frequency in the road section, analyzing the vehicle status and calculating the overall vehicle status in the tunnel, using fuzzy reasoning to comprehensively classify the tunnel potential and the overall vehicle status in the tunnel to determine whether the tunnel transition lights need to be closed, and calculating the continuous closing time of the tunnel transition lights in combination with the overall vehicle status in the tunnel and the grid load schedulability.

Description

Technical Field

[0001] The present invention relates to the field of electric energy regulation technology, and more specifically, to a cloud platform-based tunnel lighting intelligent control data analysis method and system. Background Art

[0002] Power regulation technology is an important means to optimize the generation, transmission and use of electric energy, aiming to improve the efficiency, reliability and sustainability of the power system. The application of power regulation technology in intelligent control of tunnel lighting can improve the safety of tunnel traffic.

[0003] The prior art has the following deficiencies:

[0004] In the past, tunnel transition lights were opened and closed based on tunnel flow, and the closing time was mostly instantaneous. When vehicles entered and exited the tunnel during low tunnel flow periods, they were prone to problems such as sudden closing of transition lights. Since the transition lights were closed, the light difference inside and outside the tunnel was not supplemented, which increased vehicle safety risks. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a cloud platform-based tunnel lighting intelligent control data analysis method, which analyzes whether the tunnel has the potential to adjust the tunnel transition lights by analyzing the adjustable amount of the tunnel power grid load and the vehicle status in the tunnel. If there is potential, the duration of the transition lights being turned off is calculated and set to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The cloud platform-based tunnel lighting intelligent control data analysis method includes the following steps:

[0008] Step S1: Divide the tunnel into a tunnel entrance and exit area and a tunnel lighting area, collect the grid load of the tunnel lighting area, obtain the lighting standard of the lighting area, and calculate the grid load dispatchability of the tunnel transition lamp based on the grid load of the lighting area and the lighting standard of the lighting area;

[0009] Step S2: Collect the current of the tunnel transition lamp to determine the load level of the power grid in the tunnel entrance and exit area, obtain the tunnel length, and classify the tunnel potential based on the tunnel length, the dispatchable power grid load, and the load level of the power grid at the tunnel entrance and exit;

[0010] Step S3: setting a road section for distance test, obtaining vehicle speed and vehicle swing frequency, analyzing vehicle status by integrating vehicle speed and vehicle swing frequency; calculating the overall vehicle status in the tunnel according to the vehicle status in the road section;

[0011] Step S4: Determine whether the tunnel transition light needs to be turned off based on the tunnel potential classification and the overall vehicle status in the tunnel. Combined with the overall vehicle status in the tunnel and the grid load, the duration for which the tunnel transition light should be turned off can be calculated.

[0012] In a preferred embodiment, in step S1, the power grid load of the lighting area is collected by a power analyzer, and the cloud database of the cloud platform is accessed to obtain the lighting standard of the tunnel lighting area. The lighting standard of the tunnel lighting area is the minimum power grid load required for the lighting area to meet the lighting requirements;

[0013] The grid load can be dispatched by subtracting the grid load in the lighting area from the lighting standard in the lighting area.

[0014] In a preferred embodiment, in step S2, the tunnel entrance and exit area distributes current by connecting tunnel transition lamps in series or in parallel, and uses a current sensor to obtain the current of each tunnel transition lamp in the tunnel entrance and exit area;

[0015] If the tunnel entrance and exit area distributes the current by connecting tunnel transition lights in series, the average current of the tunnel transition lights is calculated as the total current of the tunnel entrance and exit area;

[0016] If the tunnel entrance and exit area distributes the current by connecting tunnel transition lamps in parallel, the current of each tunnel transition lamp is summed to obtain the total current of the tunnel entrance and exit area;

[0017] The total current in the tunnel entrance and exit area is compared with the preset current threshold. When the total current in the tunnel entrance and exit area exceeds the current threshold, it is judged that the grid load in the tunnel entrance and exit area is low; when the total current in the tunnel entrance and exit area is lower than the current threshold, it is judged that the grid load in the tunnel entrance and exit area is high.

[0018] In a preferred embodiment, in step S2, when the grid load in the tunnel entrance and exit area is low, the cloud service management platform calls multiple tunnel lengths in a preset designated area to be merged into a tunnel length data set, wherein the tunnel length data set contains the current tunnel length.

[0019] In a preferred embodiment, in step S2, the tunnel length data set, the dispatchable power grid load, and the power grid load level at the tunnel entrance and exit are integrated to classify the tunnel potential, and the steps are as follows:

[0020] Determine the adjustability of the grid load: when the grid load can be dispatched to a positive number, the grid load adjustability is judged to be adjustable; when the grid load can be dispatched to a negative number, the grid load adjustability is judged to be non-adjustable;

[0021] Calculate tunnel potential: When the grid load is adjustable, the ratio of the total current in the tunnel entrance and exit area to the current threshold is used as the grid load factor, the current tunnel length is logarithmically transformed and standardized to obtain the tunnel length factor, and the difference between the tunnel length factor and the grid load factor is used as the tunnel potential index;

[0022] Set comparison threshold: Use K nearest neighbor algorithm to process the tunnel length data set to obtain the comparison threshold;

[0023] Perform potential classification: if the tunnel potential index of the current tunnel exceeds the comparison threshold, the current tunnel is judged to be a potential tunnel; if the tunnel potential index of the current tunnel is lower than the corresponding threshold, the current tunnel is judged to be a non-potential tunnel.

[0024] In a preferred embodiment, in step S3, a section of road is selected in the tunnel as a test section to perform a distance test, and the vehicle speed and the vehicle swing frequency are detected respectively;

[0025] When the vehicle enters the test section, the speed is recorded once, and when the vehicle exits the test section, the speed is recorded again, and the average of the two speeds is calculated as the vehicle speed of the corresponding vehicle;

[0026] Multiple nodes are set up in the test section to detect the distance between the vehicle and the nearest tunnel end. The distance is recorded every time the vehicle passes a node, and the median is selected as the benchmark. The number of nodes whose recorded distance values ​​are different from the benchmark is counted, and the ratio of the recorded distance value to the total number of nodes in the test section is used as the vehicle swing frequency.

[0027] In a preferred embodiment, in step S3, the vehicle state is determined using fuzzy reasoning, and the specific steps are as follows:

[0028] Step 1: Define the vehicle speed and vehicle swing frequency as input variables and divide them into different fuzzy sets;

[0029] Step 2: Define the vehicle state as the output variable and divide it into fuzzy sets;

[0030] Step 3: Formulate a set of fuzzy rules to describe the impact of input variables on output variables;

[0031] Step 4: Perform fuzzy reasoning according to fuzzy rules. When the output result Z is "Good", the vehicle state is judged to be a good vehicle state; when the output result Z is "Bad", the vehicle state is judged to be a general vehicle state;

[0032] When analyzing the overall vehicle status in the tunnel based on the vehicle status in the test section, the vehicles in the test section are monitored and counted in real time, and the ratio of the excellent vehicle status to the general vehicle status in the test section is calculated and used as the overall vehicle status index;

[0033] When the overall vehicle status index reaches above 1, the overall vehicle status in the tunnel is marked as excellent; when the overall vehicle status index is less than 1, the overall vehicle status in the tunnel is marked as fair.

[0034] In a preferred embodiment, in step S4, a rule is set to determine whether the tunnel transition light needs to be turned off:

[0035] If the current tunnel is a potential tunnel and the overall vehicle status in the tunnel is marked as normal, it is determined that the tunnel transition light is not turned off; otherwise, it is determined that the tunnel transition light is turned off;

[0036] When it is determined that the tunnel transition light is turned off, the standard turning-off time of the tunnel transition light is obtained, and the current tunnel power grid load schedulable is normalized by a decimal calibration normalization algorithm to obtain a power grid adjustable value;

[0037] The polynomial regression algorithm is used to calculate the transition light adjustment ratio based on the overall vehicle status index of the current tunnel and the adjustable value of the power grid: , where T is the transition light adjustment ratio, k is the overall vehicle status index, l is the grid adjustable value, and c is the preset adjustment parameter;

[0038] After calculating and obtaining the transition light adjustment ratio, the product of the standard off time of the tunnel transition light and the transition light adjustment ratio is used as the updated transition light continuous off time.

[0039] A cloud-based tunnel lighting intelligent control data analysis system, used to implement the cloud-based tunnel lighting intelligent control data analysis method, including a data acquisition module, a potential analysis module, a state evaluation module, and a time control module;

[0040] The data acquisition module is used to collect the grid load of the tunnel lighting area, the lighting standard of the lighting area, the tunnel transition lamp current and the tunnel length;

[0041] The potential analysis module calculates the grid load dispatchability of the tunnel transition lamp according to the grid load of the lighting area and the lighting standard of the lighting area, and classifies the tunnel potential by comprehensively considering the tunnel length, grid load dispatchability and tunnel transition lamp current;

[0042] The status assessment module conducts distance tests, obtains vehicle driving speed and vehicle swing frequency, analyzes vehicle status, and calculates the overall vehicle status in the tunnel;

[0043] The time control module is used to determine whether the tunnel transition lights need to be turned off and to calculate the duration of the tunnel transition lights being turned off in combination with the overall vehicle status in the tunnel and the grid load.

[0044] Technical effects and advantages of the cloud platform-based tunnel lighting intelligent control data analysis method and system of the present invention:

[0045] The present invention collects the grid load of the tunnel lighting area, obtains the lighting standard of the lighting area, calculates the grid load dispatchability of the tunnel transition lamp, calculates the grid load dispatchability for analyzing whether the tunnel has the ability to transfer the grid load, judges the grid load degree according to the current of the tunnel transition lamp, obtains the tunnel length, classifies the tunnel potential according to the comprehensive tunnel length, the tunnel transition lamp current and the grid load dispatchability, selects the tunnels with the potential to regulate the tunnel transition lamp, reduces the application area, reduces the cost, sets the road section for distance testing, obtains the vehicle speed and swing frequency in the road section, analyzes the vehicle status, calculates the overall vehicle status in the tunnel according to the vehicle status in the road section, determines whether the tunnel transition lamp needs to be turned off according to the comprehensive tunnel potential classification and the overall vehicle status in the tunnel, calculates the continuous turning off time of the tunnel transition lamp in combination with the overall vehicle status in the tunnel and the grid load dispatchability, and reduces the safety hazards of vehicles entering and exiting the tunnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a schematic diagram of the cloud platform-based tunnel lighting intelligent control data analysis method of the present invention.

[0047] Figure 2 This is a flow chart of the cloud platform-based tunnel lighting intelligent control data analysis system of the present invention. DETAILED DESCRIPTION

[0048] 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.

[0049] The present invention collects the grid load of the tunnel lighting area, obtains the lighting standard of the lighting area, calculates the grid load dispatchability of the tunnel transition lamp, judges the grid load degree according to the current of the tunnel transition lamp, obtains the tunnel length, classifies the tunnel potential by comprehensively considering the tunnel length, the current of the tunnel transition lamp and the dispatchability of the grid load, sets a road section for distance test, obtains the vehicle speed and swing frequency in the road section, analyzes the vehicle status, calculates the overall vehicle status in the tunnel according to the vehicle status in the road section, determines whether the tunnel transition lamp needs to be turned off according to the comprehensive tunnel potential classification and the overall vehicle status in the tunnel, calculates the continuous turning off time of the tunnel transition lamp in combination with the overall vehicle status in the tunnel and the dispatchability of the grid load, and reduces the safety hazard of vehicles entering and exiting the tunnel entrance.

[0050] Example 1, a cloud platform-based tunnel lighting intelligent control data analysis method, such as Figure 1 As shown, the following steps are included:

[0051] Step S1: Divide the tunnel into a tunnel entrance and exit area and a tunnel lighting area, collect the grid load of the tunnel lighting area, obtain the lighting standard of the lighting area, and calculate the grid load dispatchability of the tunnel transition lamp based on the grid load of the lighting area and the lighting standard of the lighting area;

[0052] Step S2: Collect the current of the tunnel transition lamp to determine the load level of the power grid in the tunnel entrance and exit area, obtain the tunnel length, and classify the tunnel potential based on the tunnel length, the dispatchable power grid load, and the load level of the power grid at the tunnel entrance and exit;

[0053] Step S3: setting a road section for distance test, obtaining vehicle speed and vehicle swing frequency, analyzing vehicle status based on vehicle speed and vehicle swing frequency; calculating the overall vehicle status in the tunnel according to the vehicle status in the road section;

[0054] Step S4: Determine whether the tunnel transition light needs to be turned off based on the tunnel potential classification and the overall vehicle status in the tunnel. Combined with the overall vehicle status in the tunnel and the grid load, the duration for which the tunnel transition light should be turned off can be calculated.

[0055] The specific implementation is as follows:

[0056] In step S1, the tunnel is divided into a tunnel entrance and exit area and a tunnel lighting area;

[0057] The tunnel entrance and exit areas are the entry and exit points of the tunnel and are the areas where vehicles enter and leave;

[0058] The tunnel lighting area is the main passage of the tunnel, providing real-time lighting to provide vision for driving vehicles and is the main driving area of ​​the tunnel;

[0059] The power grid load of the lighting area is collected through a power analyzer, and the cloud database of the cloud platform is accessed to obtain the lighting standard of the tunnel lighting area. The lighting standard of the tunnel lighting area is the minimum power grid load required for the lighting area to meet the lighting requirements;

[0060] The grid load can be dispatched by subtracting the grid load in the lighting area from the lighting standard in the lighting area.

[0061] It should be noted that the power analyzer is a device that measures and analyzes the power quality and power parameters in the power system, and is used to obtain the grid load in the lighting area; the cloud database is a database service provided by a cloud platform, which allows data to be stored, managed and processed in the cloud. This example is used to obtain the lighting standards of the tunnel lighting area.

[0062] In step S2, the tunnel entrance and exit area distributes current by connecting tunnel transition lamps in series or in parallel, and uses a current sensor to obtain the current of each tunnel transition lamp in the tunnel entrance and exit area;

[0063] If the tunnel entrance and exit area distributes the current by connecting tunnel transition lights in series, the average current of the tunnel transition lights is calculated as the total current of the tunnel entrance and exit area;

[0064] If the tunnel entrance and exit area distributes the current by connecting tunnel transition lamps in parallel, the current of each tunnel transition lamp is summed to obtain the total current of the tunnel entrance and exit area;

[0065] The total current in the tunnel entrance and exit area is compared with a preset current threshold. When the total current in the tunnel entrance and exit area exceeds the current threshold, it is judged that the grid load in the tunnel entrance and exit area is low; when the total current in the tunnel entrance and exit area is lower than the current threshold, it is judged that the grid load in the tunnel entrance and exit area is high;

[0066] It should be explained that, in the above, the current thresholds used for comparison are set by professionals in this field according to the series or parallel types of the tunnel entrance and exit areas, and will not be analyzed here.

[0067] When the grid load in the tunnel entrance and exit area is low, the cloud service management platform is used to call multiple tunnel lengths in the designated area and merge them into a tunnel length dataset, where the tunnel length dataset contains the current tunnel length;

[0068] The tunnel length dataset, the dispatchable grid load, and the grid load level at the tunnel entrance and exit are used to classify the tunnel potential. The specific steps are as follows:

[0069] Determine the adjustability of the grid load: when the grid load can be dispatched to a positive number, the grid load adjustability is judged to be adjustable; when the grid load can be dispatched to a negative number, the grid load adjustability is judged to be non-adjustable;

[0070] Calculate tunnel potential: When the grid load is adjustable, calculate the tunnel potential index, take the ratio of the total current in the tunnel entrance and exit area to the current threshold as the grid load factor, perform logarithmic transformation and standardization on the current tunnel length to obtain the tunnel length factor, and take the difference between the tunnel length factor and the grid load factor as the tunnel potential index;

[0071] Set the comparison threshold: Use the K nearest neighbor algorithm to process the tunnel length data set, mark the data in the tunnel length data set differently and make a difference between them to obtain multiple data intervals, select the minimum data interval as the classification standard, set the number of neighbors to K, select the K data intervals closest to the classification standard, and statistically calculate the number of data marks in the K data intervals closest to the classification standard. Select the data with the largest number of marks, perform logarithmic transformation and standardization, and then make a difference with the power grid load factor, and use the difference result as the comparison threshold;

[0072] Perform potential classification: if the tunnel potential index of the current tunnel exceeds the comparison threshold, the current tunnel is judged to be a potential tunnel; if the tunnel potential index of the current tunnel is lower than the corresponding threshold, the current tunnel is judged to be a non-potential tunnel.

[0073] The longer the tunnel length of the current tunnel, the lower the grid load factor, the greater the tunnel potential index, the longer the tunnel length, the longer the distance the vehicle travels in the tunnel, and the more light adaptation processing is needed at the entrance and exit; the lower the grid load factor, that is, the lower the total current in the tunnel entrance and exit area, the greater the need for power supplementation and adjusting the voltage amplitude to the tunnel entrance and exit area.

[0074] It should be noted that when setting the comparison threshold, the number of neighbors can be set according to actual conditions. For example, the number of neighbors k can be set to 6, etc., which will not be elaborated here.

[0075] In step S3, a section of road is selected in the tunnel as a test section for distance testing, and the vehicle speed and the vehicle swing frequency are detected in the test section by a speed sensor and a laser rangefinder;

[0076] When the vehicle enters the test section, the speed is recorded once, and when the vehicle exits the test section, the speed is recorded again, and the average of the two speeds is calculated as the vehicle speed of the corresponding vehicle;

[0077] Multiple nodes are set up in the test section to detect the distance of the vehicle from the near end of the tunnel. Each time the vehicle passes a node, the distance is recorded once, and the median is selected as the benchmark. The number of nodes whose recorded distance values ​​are different from the benchmark is counted, and the ratio of the recorded distance value to the total number of nodes in the test section is used as the vehicle swing frequency.

[0078] The vehicle state is determined by fuzzy reasoning using the vehicle speed and vehicle swing frequency of each vehicle entering the test section. The specific steps are as follows:

[0079] Step 1: Define the vehicle speed and vehicle swing frequency of the vehicle as input variables and divide them into different fuzzy sets; for example, "Fast", "Slow" for the vehicle speed of the vehicle, and "High", "Low" for the vehicle swing frequency;

[0080] Step 2: Define the vehicle status as the output variable and divide it into fuzzy sets; for example, "Good" and "Bad" for vehicle status;

[0081] Step 3: Formulate a set of fuzzy rules to describe the impact of input variables on output variables; for example, the vehicle speed of the vehicle is marked as V, the vehicle swing frequency of the vehicle is marked as B, and the vehicle state is defined as Z, then the following fuzzy rules can be defined

[0082] Rule1: IF (V is Fast) AND (B is High) THEN (Z is Bad)

[0083] Rule2: IF (V is Slow) AND (B is Low) THEN (Z is Good) ...

[0084] Step 4: Perform fuzzy reasoning according to fuzzy rules. When the output result Z is "Good", the vehicle state is judged to be an excellent vehicle state; when the output result Z is "Bad", the vehicle state is judged to be a general vehicle state.

[0085] When analyzing the overall vehicle status in the tunnel based on the vehicle status in the test section, the vehicles in the test section are monitored and counted in real time, and the ratio of the excellent vehicle status to the general vehicle status in the test section is calculated and used as the overall vehicle status index;

[0086] When the overall vehicle status index reaches above 1, the overall vehicle status in the tunnel is marked as excellent; when the overall vehicle status index is less than 1, the overall vehicle status in the tunnel is marked as fair.

[0087] It should be noted that the speed sensor is a device for measuring the speed of an object and is used to detect the speed of the vehicle in the test section; the photometric rangefinder is a device that uses laser technology to measure distance. In this example, it is used to detect the distance of the vehicle from the near end of the tunnel to analyze the vehicle's swing frequency.

[0088] In step S4, it is determined whether the tunnel transition light needs to be turned off according to the tunnel potential classification and the overall vehicle status in the tunnel. The specific rules are as follows:

[0089] If the current tunnel is a potential tunnel and the overall vehicle status in the tunnel is marked as normal, it is determined that the tunnel transition light is not turned off; otherwise, it is determined that the tunnel transition light is turned off;

[0090] When it is determined that the tunnel transition light is turned off, the signal light control system is accessed to obtain the standard turning off time of the tunnel transition light;

[0091] The standard off time of the tunnel transition light is the time period from when the tunnel transition light starts to reduce the power supply to when it completely loses power, that is, the time the tunnel transition light spends in the dimming process.

[0092] The decimal calibration normalization algorithm is used to normalize the current tunnel power grid load dispatchability to obtain the power grid adjustable value, which is shown as follows: ,in, The grid load of the current tunnel can be dispatched. is the adjustable value of the power grid of the current tunnel, j is the calibration index;

[0093] It should be explained that the calibration index is set according to the dispatchability of the power grid load. The calibration index is used to normalize the dispatchability of the power grid load of the current tunnel to a value between 0 and 1, and the value range of this value is strictly greater than or equal to 1.

[0094] The polynomial regression algorithm is used to calculate the transition light adjustment ratio based on the overall vehicle status index of the current tunnel and the adjustable value of the power grid: , where T is the transition light adjustment ratio, k is the overall vehicle status index, l is the grid adjustable value, and c is the adjustment parameter;

[0095] After calculating and obtaining the transition light adjustment ratio, the product of the standard off time of the tunnel transition light and the transition light adjustment ratio is used as the updated transition light continuous off time.

[0096] It should be noted that the traffic light control system is a system for managing traffic and controlling the passage of vehicles and pedestrians, which stores historical transition light data, including the standard off time of tunnel transition lights; in the above, the adjustment parameters are set by professionals in this field according to actual conditions, and the transition light off time is updated by calculating the transition light adjustment comparison through the adjustment parameters.

[0097] Example 2, a cloud platform-based tunnel lighting intelligent control data analysis system, such as Figure 2 As shown, it includes a data acquisition module, a potential analysis module, a state evaluation module and a time control module, and the signals between the modules are connected;

[0098] The data acquisition module is used to collect the grid load of the tunnel lighting area, the lighting standard of the lighting area, the tunnel transition lamp current, and the tunnel length;

[0099] The potential analysis module calculates the grid load dispatchability of the tunnel transition lamp according to the grid load of the lighting area and the lighting standard of the lighting area, and classifies the tunnel potential by comprehensively considering the tunnel length, grid load dispatchability and tunnel transition lamp current;

[0100] The status assessment module performs distance tests, obtains vehicle speed and vehicle swing frequency, analyzes vehicle status, and calculates the overall vehicle status in the tunnel;

[0101] The time control module is used to determine whether the tunnel transition lights need to be turned off and to calculate the duration for which the tunnel transition lights should be turned off in combination with the overall vehicle status and grid load in the tunnel.

[0102] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0103] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application of the technical solution and the invention constraints. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0104] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0105] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0106] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A cloud platform-based tunnel lighting intelligent control data analysis method, characterized in that: The following steps are included: Step S1: Divide the tunnel into a tunnel entrance and exit area and a tunnel lighting area, collect the grid load of the tunnel lighting area, obtain the lighting standard of the lighting area, and calculate the grid load dispatchability of the tunnel transition lamp based on the grid load of the lighting area and the lighting standard of the lighting area; Step S2: Collect the current of the tunnel transition lamp to determine the load level of the power grid in the tunnel entrance and exit area, obtain the tunnel length, and classify the tunnel potential based on the tunnel length, the dispatchable power grid load, and the load level of the power grid at the tunnel entrance and exit; Step S3: setting a road section for distance test, obtaining vehicle speed and vehicle swing frequency, and analyzing vehicle status by integrating vehicle speed and vehicle swing frequency; Calculate the overall vehicle status in the tunnel based on the vehicle status in the road section; Step S4: Determine whether the tunnel transition light needs to be turned off based on the tunnel potential classification and the overall vehicle status in the tunnel, and calculate the duration of the tunnel transition light being turned off in combination with the overall vehicle status in the tunnel and the grid load; In step S2, when the grid load in the tunnel entrance and exit area is low, multiple tunnel lengths in the preset demarcated area are merged into a tunnel length data set through the cloud service management platform, wherein the tunnel length data set contains the current tunnel length; In step S2, the tunnel length data set, the dispatchable grid load, and the grid load level at the tunnel entrance and exit are integrated to classify the tunnel potential. The steps are as follows: Determine the adjustability of the grid load: when the grid load can be dispatched to a positive number, the grid load adjustability is judged to be adjustable; when the grid load can be dispatched to a negative number, the grid load adjustability is judged to be non-adjustable; Calculate tunnel potential: When the grid load is adjustable, the ratio of the total current in the tunnel entrance and exit area to the current threshold is used as the grid load factor, the current tunnel length is logarithmically transformed and standardized to obtain the tunnel length factor, and the difference between the tunnel length factor and the grid load factor is used as the tunnel potential index; Set comparison threshold: Use K nearest neighbor algorithm to process the tunnel length data set to obtain the comparison threshold and then perform potential classification.

2. The cloud platform-based tunnel lighting intelligent control data analysis method according to claim 1, characterized in that: In step S1, the power grid load of the lighting area is collected by a power analyzer, and the cloud database of the cloud platform is accessed to obtain the lighting standard of the tunnel lighting area. The lighting standard of the tunnel lighting area is the minimum power grid load required for the lighting area to meet the lighting requirements; Subtract the grid load in the lighting area from the lighting standard in the lighting area to obtain the grid load dispatchability; The power analyzer is a device used to obtain the load of the power grid in the lighting area; the cloud database is a database for obtaining the lighting standards of the tunnel lighting area.

3. The cloud platform-based tunnel lighting intelligent control data analysis method according to claim 1 is characterized in that: In step S2, the tunnel entrance and exit area distributes current by connecting tunnel transition lamps in series or in parallel, and uses a current sensor to obtain the current of each tunnel transition lamp in the tunnel entrance and exit area; If the tunnel entrance and exit area distributes the current by connecting tunnel transition lights in series, the average current of the tunnel transition lights is calculated as the total current of the tunnel entrance and exit area; If the tunnel entrance and exit area distributes the current by connecting tunnel transition lamps in parallel, the current of each tunnel transition lamp is summed to obtain the total current of the tunnel entrance and exit area; The total current in the tunnel entrance and exit area is compared with the preset current threshold. When the total current in the tunnel entrance and exit area exceeds the current threshold, it is judged that the grid load in the tunnel entrance and exit area is low; when the total current in the tunnel entrance and exit area is lower than the current threshold, it is judged that the grid load in the tunnel entrance and exit area is high.

4. The cloud platform-based tunnel lighting intelligent control data analysis method according to claim 1, characterized in that: The cloud service management platform is a system for managing and optimizing cloud resources and services, which is used to call tunnel length.

5. The cloud platform-based tunnel lighting intelligent control data analysis method according to claim 1, characterized in that: In step S2, the specific potential classification rules are as follows: if the tunnel potential index of the current tunnel exceeds the comparison threshold, the current tunnel is judged to be a potential tunnel; if the tunnel potential index of the current tunnel is lower than the corresponding threshold, the current tunnel is judged to be a non-potential tunnel; Logarithmic transformation normalization is a data preprocessing technique used to compress the tunnel length to obtain the tunnel length coefficient; The K-nearest neighbor algorithm is a machine learning algorithm used to calculate contrast thresholds to classify tunnel potentials.

6. The cloud platform-based tunnel lighting intelligent control data analysis method according to claim 1, characterized in that: In step S3, a section of road is selected in the tunnel as a test section to perform a distance test, and the vehicle speed and the vehicle swing frequency are detected respectively; When the vehicle enters the test section, the speed is recorded once, and when the vehicle exits the test section, the speed is recorded again, and the average of the two speeds is calculated as the vehicle speed of the corresponding vehicle; Multiple nodes are set up in the test section to detect the distance between the vehicle and the nearest tunnel end. The distance is recorded every time the vehicle passes a node, and the median is selected as the benchmark. The number of nodes whose recorded distance values ​​are different from the benchmark is counted, and the ratio of the recorded distance value to the total number of nodes in the test section is used as the vehicle swing frequency.

7. The cloud platform-based tunnel lighting intelligent control data analysis method according to claim 6 is characterized in that: In step S3, the vehicle state is determined using fuzzy reasoning. The specific steps are as follows: Step 1: Define the vehicle speed and vehicle swing frequency as input variables and divide them into different fuzzy sets; Step 2: Define the vehicle state as the output variable and divide it into fuzzy sets; Step 3: Formulate a set of fuzzy rules to describe the impact of input variables on output variables; Step 4: Perform fuzzy reasoning according to fuzzy rules. When the output result Z is "Good", the vehicle state is judged to be a good vehicle state; when the output result Z is "Bad", the vehicle state is judged to be a general vehicle state; When analyzing the overall vehicle status in the tunnel based on the vehicle status in the test section, the vehicles in the test section are monitored and counted in real time, and the ratio of the excellent vehicle status to the general vehicle status in the test section is calculated and used as the overall vehicle status index; When the overall vehicle status index reaches above 1, the overall vehicle status in the tunnel is marked as excellent; when the overall vehicle status index is less than 1, the overall vehicle status in the tunnel is marked as fair.

8. The cloud platform-based tunnel lighting intelligent control data analysis method according to claim 7 is characterized in that: In step S4, a rule is set to determine whether the tunnel transition light needs to be turned off: If the current tunnel is a potential tunnel and the overall vehicle status in the tunnel is marked as normal, it is determined that the tunnel transition light is not turned off; Otherwise, it is determined that the tunnel transition light is turned off; When it is determined that the tunnel transition light is turned off, the standard turning-off time of the tunnel transition light is obtained, and the current tunnel power grid load schedulable is normalized by a decimal calibration normalization algorithm to obtain a power grid adjustable value; The polynomial regression algorithm is used to calculate the transition light adjustment ratio based on the overall vehicle status index of the current tunnel and the adjustable value of the power grid: , where T is the transition light adjustment ratio, k is the overall vehicle status index, l is the grid adjustable value, and c is the preset adjustment parameter; After calculating and obtaining the transition light adjustment ratio, the product of the standard off time of the tunnel transition light and the transition light adjustment ratio is used as the updated transition light continuous off time; The decimal scaling normalization algorithm is a data normalization algorithm that scales the data by moving the decimal point position.

9. A cloud platform-based tunnel lighting intelligent control data analysis system, based on the cloud platform-based tunnel lighting intelligent control data analysis method according to any one of claims 1 to 8, characterized in that: It includes data acquisition module, potential analysis module, status assessment module and time control module; The data acquisition module is used to collect the grid load of the tunnel lighting area, the lighting standard of the lighting area, the tunnel transition lamp current and the tunnel length; The potential analysis module calculates the grid load dispatchability of the tunnel transition lamp according to the grid load of the lighting area and the lighting standard of the lighting area, and classifies the tunnel potential by comprehensively considering the tunnel length, grid load dispatchability and tunnel transition lamp current; The status assessment module conducts distance tests, obtains vehicle driving speed and vehicle swing frequency, analyzes vehicle status, and calculates the overall vehicle status in the tunnel; The time control module is used to determine whether the tunnel transition lights need to be turned off and to calculate the duration of the tunnel transition lights being turned off in combination with the overall vehicle status in the tunnel and the grid load.

Images