Control method of mobile lighting lighthouse and related equipment

Abstract

The invention discloses a control method and related equipment for a mobile lighting lighthouse, and the method comprises the steps: firstly detecting environment data through a lighthouse sensor, and forming a sensor data set containing multi-dimensional information, such as light intensity, temperature and humidity; performing trend analysis to obtain an environment change prediction result containing future illumination requirements; and combining the prediction result and the current environment data to construct an illumination strategy model, and calculating an illumination control strategy. Thirdly, sensitivity analysis is conducted on illumination intensity in the illumination control strategy, the optimal illumination duration time is calculated, and then the strategy is optimized in combination with the lighthouse power limitation information; and finally, analyzing an instruction of the user based on the intelligent equipment end, and generating a control instruction in combination with the optimal strategy. According to the method, environment changes are mastered in real time by collecting and analyzing multi-dimensional environment data, and the unstable lighting effect is avoided. According to the invention, the lighting strategy can be dynamically adjusted, the light is flexibly adjusted according to the user demand, the individuation and intelligence level is improved, and an efficient, energy-saving and intelligent scheme is provided for outdoor lighting.

Description

Technical Field

[0001] The present application relates to the field of lighthouse control, and more specifically, to a control method and related equipment for a mobile lighting lighthouse. Background Art

[0002] In today's society, the demand for outdoor lighting is showing a trend of continuous growth, especially in key areas such as emergency rescue, construction and post-disaster recovery. Mobile lighting towers have become an indispensable and important lighting equipment. However, the current mobile lighting tower control technology on the market has obvious limitations. Its operating mode is basically a preset fixed scheme, which makes it difficult to perceive and respond to dynamic changes in environmental conditions in real time, and it is impossible to automatically and accurately adjust the lighting intensity according to actual conditions, resulting in fluctuating lighting effects, which is difficult to meet the complex and changeable actual use needs.

[0003] From the perspective of existing technologies, the control systems of mobile lighting towers mainly rely on manual operation or simple time scheduling programs, and fail to fully explore and use environmental data to achieve intelligent control. Although some systems are equipped with sensors to monitor environmental parameters, these systems generally lack the function of forward-looking prediction and analysis of environmental change trends. In addition, mobile lighting towers under existing technologies also have obvious shortcomings in intelligent user interaction functions. Most lighting control systems are difficult to make flexible and timely adjustments based on users' real-time needs. Especially in emergency situations, users' control needs are often urgent and changeable, while existing lighting control systems are still limited to fixed preset modes, or can only receive simple operating instructions, and seriously lack the ability to deeply analyze and customize user needs. As a result, there is often a disconnect between users' actual needs and lighting control strategies, which in turn leads to a series of problems such as unreasonable lighting time (too long or too short) and mismatched light intensity, which has a negative impact on lighting efficiency and effect.

[0004] Based on this, the present application provides a control solution for a mobile lighting tower, which overcomes the shortcomings of the prior art and effectively improves the lighting effect. Summary of the invention

[0005] In view of this, the present application provides a control method and related equipment for a mobile lighting tower, aiming to overcome the technical problem that the prior art cannot adjust the lighting intensity according to environmental conditions and user instructions, resulting in poor lighting effects.

[0006] A control method for a mobile lighting tower, comprising:

[0007] Using sensors on the mobile lighting tower to detect environmental data, a sensor data set is obtained, wherein the sensor data set includes multi-dimensional data combining light intensity and temperature and humidity;

[0008] Performing trend analysis on the sensor data set to obtain an environmental change prediction result, wherein the environmental change prediction result includes lighting demand information within a preset time in the future;

[0009] Building a lighting strategy model in combination with the environmental change prediction result and the current environmental data detected by the sensor, and calculating a lighting control strategy based on the lighting strategy model;

[0010] Performing a sensitivity analysis on the light intensity in the lighting control strategy to obtain an influence weight of the light intensity on the lighting control strategy, and calculating an optimal lighting duration based on the influence weight;

[0011] Acquire power limitation information of the mobile lighting tower, optimize the lighting control strategy based on the optimal lighting duration and the power limitation information, and obtain an optimal lighting control strategy;

[0012] A comprehensive calculation is performed based on the user demand information and the optimal lighting control strategy to generate a lighting control instruction, and the mobile lighting tower is controlled based on the lighting control instruction, wherein the user demand information is obtained by parsing the control instruction sent by the user based on the smart device.

[0013] Optionally, the detecting environmental data using a sensor on a mobile lighting tower to obtain a sensor data set includes:

[0014] Using the sensor on the mobile lighting tower to detect the light intensity data and temperature and humidity data of the environment;

[0015] The light intensity data is collected in layers to obtain light intensity data at multiple different heights and orientations, and integrated and weighted to obtain light intensity distribution data;

[0016] Perform multi-dimensional feature extraction on the temperature and humidity data to obtain independent contributions of temperature and humidity to light intensity changes, and build a regression model based on the interaction between temperature and humidity to obtain global temperature and humidity prediction data;

[0017] Classifying the environmental state at each moment according to the interactive relationship between the light intensity distribution data and the global temperature and humidity prediction data to obtain dynamic environmental state data;

[0018] The light intensity distribution data, the global temperature and humidity prediction data and the dynamic environmental status data are fused to obtain a sensor data set.

[0019] Optionally, trend analysis is performed on the sensor data set to obtain environmental change prediction results, including:

[0020] Performing time series decomposition processing on the light intensity data in the sensor data set to obtain a long-period trend component;

[0021] Performing dynamic state estimation on the temperature and humidity data in the sensor data set to obtain state estimation values ​​corresponding to the temperature and humidity data;

[0022] Performing spatiotemporal correlation analysis on the long-term trend component and the state estimation value to generate an environmental change trend;

[0023] The exponential smoothing method is used to predict the environmental change trend in a future time period to obtain the environmental change prediction result, wherein the environmental change prediction result includes lighting demand information within a future preset time period.

[0024] Optionally, building a lighting strategy model in combination with the environmental change prediction result and the current environmental data detected by the sensor, and calculating a lighting control strategy based on the lighting strategy model includes:

[0025] Performing joint modeling processing on the environmental change prediction result and the current environmental data detected by the sensor to obtain a joint model of environmental change and lighting demand;

[0026] The joint model is used to perform feature importance analysis on each input feature, calculate the contribution of each input feature to the lighting demand prediction result, and obtain the key factors affecting the lighting control strategy;

[0027] Based on the key factors, a dynamic weight allocation mechanism is constructed to obtain a lighting control strategy weight model;

[0028] The lighting control strategy weight model is optimized based on a particle swarm optimization algorithm to generate the lighting control strategy.

[0029] Optionally, performing a sensitivity analysis on the light intensity in the lighting control strategy to obtain an influence weight of the light intensity on the lighting control strategy, and calculating the optimal lighting duration based on the influence weight includes:

[0030] Performing weight distribution processing on the light intensity in the lighting control strategy based on the light intensity data to form a weight distribution result;

[0031] Performing a sensitivity evaluation on the weight distribution result, calculating the influence of the environmental factors in the weight distribution result on the lighting control strategy, and obtaining an analysis result, wherein the environmental factors include light intensity data and temperature and humidity data;

[0032] The influence weight of each environmental factor in the analysis result is multiplied by the lighting demand in the lighting control strategy to obtain the lighting intensity demand in each time period, and the optimal lighting duration is calculated according to the lighting intensity demand.

[0033] Optionally, obtaining power limit information of the mobile lighting tower, optimizing the lighting control strategy based on the optimal lighting duration and the power limit information to obtain an optimal lighting control strategy, includes:

[0034] Obtaining power limit information of the mobile lighting tower, wherein the power limit information includes at least current battery power, battery discharge curve, power consumption history, maximum output power of the device, and a predetermined operation time limit;

[0035] Extracting features from the power limitation information to obtain feature data of power consumption rate, power load fluctuation, remaining power prediction value and maximum working time, and forming a power limitation feature vector;

[0036] Performing weighted processing on each feature in the power limitation feature vector to form a power limitation condition, and obtaining a value range of an optimal lighting duration under the power limitation condition;

[0037] Generate a dynamic adjustment strategy according to the value range, adjust the lighting control strategy based on the dynamic adjustment strategy, and obtain a power scheduling function;

[0038] Timing adjustment is performed in a simulation environment according to the power scheduling function to obtain the optimal lighting control strategy.

[0039] Optionally, performing comprehensive calculation based on user demand information and the optimal lighting control strategy to generate a lighting control instruction, and controlling the mobile lighting tower based on the lighting control instruction, including:

[0040] Obtain control instructions sent by users based on smart devices, parse and extract key information in the control instructions, and form a demand data set;

[0041] Performing feature mapping on the demand data set to obtain a multi-dimensional user demand feature vector;

[0042] Based on the optimal lighting control strategy and the multi-dimensional user demand feature vector, a lighting control solution that meets the user demand is obtained through matching analysis;

[0043] Optimizing the optimal lighting control strategy according to the lighting control scheme to obtain an optimization result;

[0044] A lighting control instruction is generated according to the optimization result, and the mobile lighting tower is controlled based on the lighting control instruction.

[0045] A control device for a mobile lighting tower, comprising:

[0046] A collection module, used to detect environmental data using sensors on the mobile lighting tower to obtain a sensor data set, wherein the sensor data set includes multi-dimensional data combining light intensity and temperature and humidity;

[0047] An analysis module, configured to perform trend analysis on the sensor data set to obtain an environmental change prediction result, wherein the environmental change prediction result includes lighting demand information within a preset time in the future;

[0048] A construction module, used to construct a lighting strategy model in combination with the environmental change prediction result and the current environmental data detected by the sensor, and calculate a lighting control strategy based on the lighting strategy model;

[0049] A calculation module, configured to perform a sensitivity analysis on the light intensity in the lighting control strategy, obtain an influence weight of the light intensity on the lighting control strategy, and calculate an optimal lighting duration based on the influence weight;

[0050] An optimization module, configured to obtain power limitation information of the mobile lighting tower, and optimize the lighting control strategy based on the optimal lighting duration and the power limitation information to obtain an optimal lighting control strategy;

[0051] The control module is used to perform comprehensive calculations based on user demand information and the optimal lighting control strategy, generate lighting control instructions, and control the mobile lighting tower based on the lighting control instructions, wherein the user demand information is obtained by parsing the control instructions sent by the user based on the smart device.

[0052] A control device for a mobile lighting tower, comprising a memory and a processor;

[0053] The memory is used to store programs;

[0054] The processor is used to execute the program to implement each step of the control method of the mobile lighting tower as described in any of the above items.

[0055] A readable storage medium stores a computer program, which, when executed by a processor, implements the various steps of the control method of a mobile lighting tower as described in any one of the above items.

[0056] It can be seen from the above technical solutions that the control method and related equipment of a mobile lighting tower provided by the embodiment of the present application first use the sensors on the tower to detect environmental data to form a sensor data set containing multi-dimensional data such as light intensity, temperature and humidity. Then, a trend analysis is performed on these data to obtain environmental change prediction results containing lighting demand information within a preset time in the future. After that, a lighting strategy model is constructed by combining the environmental change prediction results with the current environmental data, and then the lighting control strategy is calculated. In order to optimize the lighting plan, a sensitivity analysis of the light intensity in the strategy is performed to determine its impact weight and calculate the optimal lighting duration. Then the power limit information of the tower is obtained, and the strategy is optimized in combination with the optimal lighting duration to obtain the optimal lighting control strategy. Finally, the control instructions sent by the user based on the smart device are analyzed to obtain user demand information, which is comprehensively calculated with the optimal lighting control strategy to generate lighting control instructions to control the tower.

[0057] This application can grasp the trend of environmental changes in real time by collecting and analyzing multi-dimensional environmental data such as light intensity, temperature and humidity, avoiding the problem of unstable lighting effects caused by existing technologies relying on fixed modes or manual adjustments. It dynamically adjusts the lighting strategy based on environmental change predictions and current environmental data, calculates the optimal lighting duration based on sensitivity analysis, and can parse user instructions and integrate user needs with the optimal strategy. It can flexibly adjust the lighting effect according to different scenarios and user needs, improving the personalization and intelligence level of the lighting system. In an emergency, it can quickly respond to real-time user needs, avoiding the problem of being unable to adjust the lighting mode in time, effectively improving lighting efficiency, effects and energy utilization, greatly improving the intelligence level of mobile lighting towers, and providing efficient, energy-saving and intelligent solutions for changing outdoor lighting needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0059] Figure 1 A flowchart of a control method for a mobile lighting tower disclosed in an embodiment of the present application;

[0060] Figure 2 A schematic diagram of the structure of a mobile lighting tower disclosed in an embodiment of the present application;

[0061] Figure 3 A schematic diagram of a control device for a mobile lighting tower disclosed in an embodiment of the present application;

[0062] Figure 4 This is a hardware structure block diagram of a control device for a mobile lighting tower disclosed in an embodiment of the present application. DETAILED DESCRIPTION

[0063] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0064] The present application can be used in many general or special computing device environments or configurations, such as personal computers, server computers, handheld or portable devices, tablet devices, multi-processor devices, distributed computing environments including any of the above devices or equipment, etc.

[0065] Next, the present application scheme is introduced. The present application proposes the following technical scheme, please see below for details.

[0066] Figure 1 This is a flow chart of a control method for a mobile lighting tower disclosed in an embodiment of the present application.

[0067] like Figure 1 As shown, the method may include:

[0068] Step S1, using the sensor on the mobile lighting tower to detect environmental data to obtain a sensor data set, wherein the sensor data set includes multi-dimensional data combining light intensity and temperature and humidity.

[0069] Specifically, ambient light intensity sensors mainly collect data by sensing light intensity. Such sensors are usually equipped with photoelectric sensor elements, which can keenly detect the light intensity generated by natural light or artificial light sources in the surrounding environment. Subsequently, the detected light intensity is converted into an electrical signal and transmitted to the control system after digital processing. The change in light intensity is closely related to factors such as time, weather, and seasonal changes, and can accurately reflect the current actual lighting needs.

[0070] The temperature and humidity sensor is responsible for monitoring the temperature and humidity data in the environment. It uses thermistors and hygrometers to detect the temperature and humidity of the surrounding air, and converts them into corresponding electrical signals, which are finally transmitted to the data processing unit.

[0071] During the entire detection process, the raw sensor data obtained will be integrated into a multidimensional data set in time series. Because the ambient light intensity and temperature and humidity data will continue to change over time, these data will be continuously recorded to form a multidimensional data set containing ambient light intensity and temperature and humidity values.

[0072] Step S2: Perform trend analysis on the sensor data set to obtain environmental change prediction results, wherein the environmental change prediction results include lighting demand information within a preset time in the future.

[0073] Specifically, trend analysis is a data processing technology that focuses on in-depth analysis of the historical records of raw sensor data to uncover potential patterns or trends. First, the raw data must be preprocessed, such as removing noise and filling missing values. Then, historical data is used to perform time series analysis to identify periodic fluctuations or sudden changes in the data.

[0074] For example, the sliding window technology can be used to analyze the data in segments, calculate the change pattern of light intensity, temperature and humidity in each period of time, and then infer the possible short-term and long-term trends. At the same time, it can also combine regression analysis, moving average, exponential smoothing and other methods to predict environmental changes in a certain period of time in the future.

[0075] In the process of trend analysis, by analyzing the changing trends of ambient light intensity and temperature and humidity, it is possible to estimate the lighting demand in the future preset time period. For example, if the light intensity is expected to drop significantly or the temperature and humidity values ​​are abnormal during the preset time period, it can be predicted that the lighting demand will increase; if the ambient light intensity is expected to rise or the temperature and humidity remain stable, then the lighting demand may decrease or remain at a low level. In order to make the prediction results more accurate, historical data and real-time environmental data can be combined for analysis, so that real-time adjustment and optimization of the prediction results can be achieved.

[0076] Step S3: construct a lighting strategy model in combination with the environmental change prediction result and the current environmental data detected by the sensor, and calculate a lighting control strategy based on the lighting strategy model.

[0077] Specifically, the current environmental data is derived from the sensor data set collected in step S1, including real-time ambient light intensity, temperature and humidity, etc. Combining the current environmental data with the prediction results of future environmental changes actually enables the lighting system to comprehensively and dynamically respond to different possible situations.

[0078] In actual operation, building a lighting strategy model requires comprehensive consideration of multiple factors. Mathematical modeling or artificial intelligence algorithms can be used to conduct in-depth analysis of current environmental data and prediction results to determine the key factors that affect lighting needs. For example, rising temperatures may reduce lighting needs, and increased humidity is also associated with changes in light needs. Based on these factors, a multi-factor mathematical model is constructed to use these input variables to predict the best lighting solution.

[0079] In order to improve the accuracy and adaptability of the model, a dynamic adjustment mechanism can be added to the model so that the lighting control strategy can respond to rapid changes in the environment in real time. In terms of model design, the intensity, time and energy consumption of lighting should be taken into account. For example, when the ambient light intensity is high, the lighting intensity should be appropriately reduced to reduce energy waste; while in an environment with low temperature and high humidity, the lighting duration may need to be extended to ensure sufficient brightness. Through such considerations, a set of lighting parameters to be adjusted can be calculated.

[0080] Based on the constructed lighting strategy model, the specific lighting control strategy can be calculated. This process is actually the result of model solution. The current environmental data and predicted change trends are input into the lighting strategy model to generate a set of specific control parameters, including lighting intensity, on and off time, lighting duration, etc. By calculating these control parameters, the lighting system can automatically adjust the lighting status according to environmental changes in the future, which can not only meet the established lighting needs, but also ensure the efficient use of energy.

[0081] Step S4: Perform sensitivity analysis on the light intensity in the lighting control strategy to obtain the influence weight of the light intensity on the lighting control strategy, and calculate the optimal lighting duration based on the influence weight.

[0082] Specifically, sensitivity analysis aims to explore how different light intensity parameters affect the effectiveness and energy efficiency of the overall lighting control strategy. This process uses mathematical and statistical methods to measure the impact of light intensity on lighting control strategies in different scenarios. By using indicators such as coefficient of variation and sensitivity index, the light intensity is gradually adjusted to observe changes in other elements of the lighting control strategy (such as energy consumption, lighting time, etc.).

[0083] For example, when the light intensity increases or decreases, it may change the lighting duration and even affect the power consumption efficiency. By gradually changing the light intensity, the system can quantify the contribution of each light intensity to the final control effect, thereby clarifying the weight of each change to the lighting control strategy.

[0084] After sensitivity analysis, an impact weight index can be obtained, which can reflect the actual impact of different light intensities on the overall lighting control strategy. Subsequently, optimization algorithms (such as genetic algorithms, particle swarm optimization, etc.) can be used to calculate the optimal lighting duration after simulating energy efficiency and lighting requirements under different light intensities.

[0085] In this way, lighting towers can save energy and extend the use time to the greatest extent while meeting lighting needs. They can even automatically adjust lighting strategies according to user needs and environmental conditions, and through continuous monitoring and feedback mechanisms, continuously adjust and optimize the lighting system to adapt to complex and changing actual environments.

[0086] Step S5: Obtain the power limit information of the mobile lighting tower, optimize the lighting control strategy based on the optimal lighting duration and the power limit information, and obtain the optimal lighting control strategy.

[0087] Specifically, power limit information refers to the maximum power output that a mobile lighting tower can support when it is working. It is determined by the hardware performance of the lighting tower, the battery capacity of the equipment, the energy supply conditions, and other external limiting factors. There are many ways to obtain power limit information, which can be directly detected by sensors or obtained with the help of set parameters and power dispatch models in the control system. This information usually covers data such as current battery power, power consumption mode, and maximum load power.

[0088] Based on this power limit information, the lighting control strategy needs to be further optimized. The optimal lighting duration is obtained through the previous light intensity sensitivity analysis. It is the ideal duration that can meet the lighting needs to the greatest extent without causing energy waste under specific environmental conditions. However, in actual situations, due to power resource limitations, this optimal lighting duration may not be directly applied and needs to be adjusted based on the power limit information.

[0089] For example, when the sensor detects that the battery power of the lighting tower is close to the lower limit, it is necessary to reduce the lighting intensity or shorten the lighting time according to the power limit information to ensure that the lighting tower continues to work and meets the minimum lighting requirements. In some special scenarios, if the environment changes drastically or user needs suddenly change, the lighting strategy needs to be dynamically adjusted to adapt to these changes. In the future, based on the current power limit conditions, it is necessary to calculate the optimal lighting time and lighting intensity that can be supported without exceeding the power resource limit.

[0090] Step S6: Perform comprehensive calculation based on the user demand information and the optimal lighting control strategy to generate a lighting control instruction, and control the mobile lighting tower based on the lighting control instruction, wherein the user demand information is obtained by parsing the control instruction sent by the user based on the smart device.

[0091] Specifically, the control instructions sent by users through smart devices (such as smartphones, tablets or other networked devices) must first be parsed. The control instructions sent by users to mobile lighting towers through these smart devices may involve adjustments to lighting intensity, lighting mode, switch status, etc. These control instructions usually carry clear demand parameters, such as the required light intensity, lighting on and off time.

[0092] Next, the user demand information is comprehensively calculated with the optimal lighting control strategy obtained previously. First, the user demand is converted into specific lighting control parameters, such as light intensity and duration, and then compared with the optimal light intensity and optimal lighting duration set in the lighting control strategy. If the user demand matches the existing strategy, the control instructions can be directly generated based on the optimal control strategy. If the user demand exceeds the scope supported by the strategy, the system will automatically adjust and recalculate the most appropriate lighting parameters, and then generate a lighting control instruction that includes adjusting the lighthouse's light intensity, switch status, operating time, etc. This instruction will directly drive the lighthouse to perform the corresponding lighting task.

[0093] In this way, the intelligent control method can ensure that the lighthouse automatically adjusts according to environmental conditions and flexibly responds to the real-time needs of users. This real-time interaction between users and the system significantly enhances the intelligence and flexibility of the lighting system.

[0094] It can be seen from the above technical solutions that the control method and related equipment of a mobile lighting tower provided by the embodiment of the present application first use the sensors on the tower to detect environmental data to form a sensor data set containing multi-dimensional data such as light intensity, temperature and humidity. Then, a trend analysis is performed on these data to obtain environmental change prediction results containing lighting demand information within a preset time in the future. After that, a lighting strategy model is constructed by combining the environmental change prediction results with the current environmental data, and then the lighting control strategy is calculated. In order to optimize the lighting plan, a sensitivity analysis of the light intensity in the strategy is performed to determine its impact weight and calculate the optimal lighting duration. Then the power limit information of the tower is obtained, and the strategy is optimized in combination with the optimal lighting duration to obtain the optimal lighting control strategy. Finally, the control instructions sent by the user based on the smart device are analyzed to obtain user demand information, which is comprehensively calculated with the optimal lighting control strategy to generate lighting control instructions to control the tower.

[0095] This application can grasp the trend of environmental changes in real time by collecting and analyzing multi-dimensional environmental data such as light intensity, temperature and humidity, avoiding the problem of unstable lighting effects caused by existing technologies relying on fixed modes or manual adjustments. It dynamically adjusts the lighting strategy based on environmental change predictions and current environmental data, calculates the optimal lighting duration based on sensitivity analysis, and can parse user instructions and integrate user needs with the optimal strategy. It can flexibly adjust the lighting effect according to different scenarios and user needs, improving the personalization and intelligence level of the lighting system. In an emergency, it can quickly respond to real-time user needs, avoiding the problem of being unable to adjust the lighting mode in time, effectively improving lighting efficiency, effects and energy utilization, greatly improving the intelligence level of mobile lighting towers, and providing efficient, energy-saving and intelligent solutions for changing outdoor lighting needs.

[0096] refer to Figure 2 In one embodiment, the mobile lighting tower includes a support leg 3, a generator 4, a lamp 1 and a lamp height adjustment member 2. The support leg 3 is connected to the base through a hydraulic lifting device, and the hydraulic lifting device can adjust the height and angle of the support leg 3 as needed.

[0097] The support leg 3 is connected to the lighthouse body 5 by a hinge connection. The hinge connection allows the support leg 3 to have a certain degree of rotational freedom in the vertical direction, so that when lifting, the support leg 3 can freely follow the movement of the lighthouse body 5 and ensure the stability of the lighthouse. During operation, the support leg 3 is connected to the lighthouse body 5 by a hinge, and can be quickly folded or unfolded as needed, which is convenient for transportation and deployment.

[0098] The generator 4 is connected to the electric control box through a multi-point bolt connection. This connection method provides strength and stability, ensuring that the generator 4 can be firmly connected to the electric control system during operation. Through this connection, the electric control box can monitor the working status of the generator 4 in real time, and adjust the power output according to actual needs to ensure the normal operation of the lamp 1 and other systems.

[0099] The lamp 1 is connected to the lamp height adjustment member 2 through a gear transmission device. The gear transmission device can accurately adjust the height and angle of the lamp 1, so that it can adjust the lighting direction and height according to environmental requirements. The adjustment member controls the vertical elevation of the lamp 1 by rotating the gear to ensure that the lighthouse can provide the best lighting effect.

[0100] Specifically, the lamp height adjustment member 2 is connected to the adjustment rod through an internal thread, and the lamp 1 is connected to the hole groove of the adjustment rod through a pin shaft. In this embodiment, the support leg 3 can be raised and lowered, the generator 4 can be turned on and off, and the lamp 1 can be turned on and off through the above-mentioned control instructions.

[0101] In addition, the mobile lighting tower also has fault self-detection and alarm functions. When a component of the tower, such as the generator 4, the lamp 1 or the lifting device, fails, the intelligent control system can quickly identify the type of fault and send an alarm message to the user through the intelligent device, detailing the fault location and possible solutions. This instant feedback mechanism greatly shortens the fault response time and improves the maintenance efficiency of the tower.

[0102] In some embodiments of the present application, step S1 is further introduced, which may specifically include:

[0103] Step S11, using the sensor on the mobile lighting tower to detect the light intensity data and temperature and humidity data of the environment;

[0104] Step S12, collecting the light intensity data in layers to obtain light intensity data at multiple different heights and orientations, and performing integration and weighted processing to obtain light intensity distribution data;

[0105] Step S13, performing multi-dimensional feature extraction on the temperature and humidity data to obtain independent contribution of temperature and humidity to light intensity change, and constructing a regression model based on the interaction between temperature and humidity to obtain global temperature and humidity prediction data;

[0106] Step S14, classifying the environmental state at each moment according to the interactive relationship between the light intensity distribution data and the global temperature and humidity prediction data to obtain dynamic environmental state data;

[0107] Step S15: fusing the light intensity distribution data, the global temperature and humidity prediction data, and the dynamic environmental status data to obtain a sensor data set.

[0108] Specifically, the mobile lighting tower is equipped with multiple sensors, which monitor and collect relevant data in the environment in real time. The light intensity sensor can accurately measure the light intensity at different positions and heights according to the environmental conditions; the temperature and humidity sensor can record the temperature and humidity levels of the environment.

[0109] When collecting light intensity data, data will be collected at different heights and azimuth angles. For example, the light intensity values ​​measured by sensors at three different heights, ground, mid-air, and top, may be different. When integrating this data, the impact of different locations on the overall ambient light will be fully considered. After the layered collection is completed, the data will be integrated and weighted to combine the light intensity data at different collection locations into a light intensity distribution data that can represent the entire area. Specifically, the light intensity data at different heights and directions can be weighted by the weight coefficient, and the allocation of the weight coefficient needs to be set according to the lighting characteristics and requirements in the actual environment.

[0110] Furthermore, a regression model will be established to explore the effects of temperature and humidity on light intensity, taking into account the independent effects and interactions of temperature and humidity on light intensity, that is, how the combination of temperature and humidity affects light. For example, low temperatures may increase air density, thereby affecting the refraction and propagation of light; high humidity may increase the water vapor content in the air, affecting the scattering and absorption of light. Through these feature extractions, global temperature and humidity prediction data can be obtained and classified. Analyze the environmental data at each moment to determine the current state of the environment, such as sufficient light, moderate temperature and humidity, or weak light.

[0111] Finally, all collected data, including light intensity distribution data, global temperature and humidity prediction data, and dynamic environmental status data, are fused to combine different types of data into a complete set of raw sensor data. This fusion process can be achieved through Bayesian fusion algorithms or neural networks to ensure that global environmental information can be obtained, thereby optimizing lighting effects and energy efficiency.

[0112] In some embodiments of the present application, step S2 is further introduced, which may specifically include:

[0113] Step S21, performing time series decomposition processing on the light intensity data in the sensor data set to obtain a long-period trend component;

[0114] Step S22, performing dynamic state estimation on the temperature and humidity data in the sensor data set to obtain state estimation values ​​corresponding to the temperature and humidity data;

[0115] Step S23, performing spatiotemporal correlation analysis on the long-term trend component and the state estimation value to generate an environmental change trend;

[0116] Step S24, using the exponential smoothing method to predict the environmental change trend for a future time period to obtain the environmental change prediction result, wherein the environmental change prediction result includes lighting demand information within a future preset time period.

[0117] Specifically, a time series decomposition process is performed on the ambient light intensity data in the original sensor data set. Time series analysis is a method specifically for analyzing data collected in chronological order. In this process, the original ambient light intensity data is broken down into several components as a whole, generally including a trend component, a seasonal component, and a residual component. In this embodiment, the focus is on the long-term trend component, which aims to obtain the long-term change pattern of light intensity, such as the long-term impact of seasonal changes, weather patterns and other factors on light intensity. For example, if the light intensity data in a certain area shows a gradually weakening trend, this may be due to the arrival of winter and the shortening of daylight hours. This trend is relatively stable and continuous. By performing time series decomposition processing on the light intensity data, this long-term trend can be accurately extracted.

[0118] Furthermore, it is necessary to perform dynamic state estimation on the temperature and humidity data to obtain the estimated state value. Dynamic state estimation is a method of inferring the current environmental state based on the temperature and humidity data that changes over time. The temperature and humidity data are processed through a specific model or algorithm to estimate the state changes at different time points. Common ones include Kalman filtering, particle filtering or other state estimation algorithms. These methods combine the temperature and humidity data with other factors in the environment to obtain the current estimated state value.

[0119] Spatiotemporal correlation analysis can capture the interdependence between environmental data by comprehensively considering spatial distribution and time series. Through spatiotemporal correlation analysis, the long-term trend of light intensity and the dynamic state estimation of temperature and humidity can be associated to find the correlation between them, thereby generating a comprehensive environmental change trend.

[0120] Finally, the exponential smoothing method is used to predict future environmental changes, so as to obtain the lighting demand information within the preset time period in the future. The exponential smoothing method is a time series prediction method that gradually estimates future trends by assigning different weights to historical data. The specific operation is to give a higher weight to recent data and a lower weight to long-term data. In the lighting demand forecast, the exponential smoothing method can effectively predict the lighting demand in the future time period based on the previous environmental change trend.

[0121] In some embodiments of the present application, step S3 is further introduced, which may specifically include:

[0122] Step S31, performing joint modeling processing on the environmental change prediction result and the current environmental data detected by the sensor to obtain a joint model of environmental change and lighting demand;

[0123] Step S32: using the joint model to perform feature importance analysis on each input feature, calculating the contribution of each input feature to the lighting demand prediction result, and obtaining the key factors affecting the lighting control strategy;

[0124] Step S33: construct a dynamic weight allocation mechanism based on the key factors to obtain a lighting control strategy weight model;

[0125] Step S34: Optimizing the lighting control strategy weight model based on a particle swarm optimization algorithm to generate the lighting control strategy.

[0126] Specifically, the environmental change prediction results are combined with the current environmental data to build a joint model. This model can integrate various environmental information such as light intensity, temperature and humidity, and time series trends, so as to achieve a more comprehensive lighting demand prediction. Based on this joint model, feature importance analysis is performed to evaluate the contribution of each input feature to the final prediction result. Each input feature is further sorted by the algorithm to analyze which factors have the most significant impact on lighting demand. For example, temperature changes may have a much greater impact on lighting demand than humidity changes, or changes in light intensity may have a more direct impact on lighting demand than other environmental data. Through such analysis, factors that have an important impact on optimizing lighting control strategies can be identified, and a dynamic weight allocation mechanism can be built based on these factors.

[0127] The core of the dynamic weight allocation mechanism is to dynamically adjust the weights of different factors in the lighting control strategy according to the degree of influence of each key factor. On this basis, this embodiment uses the particle swarm optimization (PSO) algorithm to optimize the weight model of the lighting control strategy. This algorithm simulates the flight process of particles in the search space to find the optimal solution. Its advantage is that it can handle complex problems in multiple dimensions and has a strong global search capability. In this embodiment, the particle swarm optimization algorithm mainly optimizes the effect of the lighting control strategy by adjusting the weight parameters. Through multiple iterative optimizations of the weights in the model, the particle swarm algorithm can find an optimal strategy to ensure that the lighting needs can be most effectively predicted and controlled under various environmental changes. In the particle swarm optimization process, each particle represents a potential solution. By simulating the mutual cooperation and information transmission between particles, the most appropriate weight combination is finally determined.

[0128] Furthermore, the calculation expression of the above embodiment is: ,

[0129] in, Represents the final lighting control strategy output (i.e. the predicted value of lighting demand), which will be used to determine the working state (on / off) of each lighting device and its brightness adjustment. represents the weight coefficient of the i-th feature, represents the functional form of the input feature i for the lighting requirement, and E is the environmental data vector. represents the dynamic adjustment factor of the i-th feature, and θ is the time parameter of environmental changes. Represents the correction factor of feature i under the current environmental state, where It is real-time environmental data. It is environmental forecast data. represents the optimized value in the i-th particle swarm optimization result, reflecting the adjustment effect of the particle swarm optimization algorithm on the strategy weight. The entire formula adjusts the weight of each feature through the particle swarm optimization algorithm, so that the lighting control strategy continuously optimizes itself with the changes of time and environment, ensuring the best lighting effect under any environmental conditions. In practical applications, this calculation formula will be calculated in real time through real-time environmental data (such as temperature, humidity, light intensity, etc. obtained by sensors) and pre-set environmental prediction data to continuously update the lighting control strategy.

[0130] In some embodiments of the present application, step S4 is further introduced, which may specifically include:

[0131] Step S41: performing weight distribution processing on the light intensity in the lighting control strategy based on the light intensity data to form a weight distribution result;

[0132] Step S42: performing sensitivity evaluation on the weight distribution result, calculating the influence of the environmental factors in the weight distribution result on the lighting control strategy, and obtaining an analysis result, wherein the environmental factors include light intensity data and temperature and humidity data;

[0133] Step S43: multiply the influence weight of each environmental factor in the analysis result by the lighting demand in the lighting control strategy to obtain the lighting intensity demand for each time period, and calculate the optimal lighting duration according to the lighting intensity demand.

[0134] Specifically, we must first clarify the impact of ambient light intensity in different time periods on the light intensity in the lighting control strategy based on real-time or preset ambient light intensity data. This requires modeling and analysis of ambient light intensity in different time periods. We can use regression analysis or other machine learning methods to build a functional relationship between ambient light intensity and indoor light intensity requirements.

[0135] Next, the preliminary weight distribution results are evaluated, and the specific impact of different environmental factors (such as ambient light intensity, temperature and humidity values) on the light intensity demand is analyzed in depth. For example, the impact of temperature and humidity on lighting demand is not direct, but changes in temperature and humidity will affect people's comfort, which in turn indirectly affects lighting demand. Through sensitivity analysis, the specific impact of each environmental factor on the lighting control strategy can be obtained, that is, the sensitivity index of each factor. For factors with higher sensitivity, they will be given a higher weight; for factors with lower sensitivity, their impact on the strategy will be reduced. Using this method, the lighting control strategy can be automatically adjusted according to changes in multiple factors such as ambient light intensity, temperature and humidity, thereby achieving accurate lighting demand prediction.

[0136] Finally, based on the light intensity requirements in each time period and the weight of the impact of environmental factors on the light demand, the required light intensity for each time period can be determined, and finally the most suitable lighting duration for each time period can be calculated.

[0137] In some embodiments of the present application, step S5 is further introduced, which may specifically include:

[0138] Step S51, obtaining power limitation information of the mobile lighting tower, wherein the power limitation information at least includes current battery power, battery discharge curve, power consumption history, maximum output power of the device and predetermined operation time limit;

[0139] Step S52: extracting features from the power limit information to obtain feature data of power consumption rate, power load fluctuation, remaining power prediction value and maximum working time, and forming a power limit feature vector;

[0140] Step S53: performing weighted processing on each feature in the power limitation feature vector to form a power limitation condition, and obtaining a value range of the optimal lighting duration under the power limitation condition;

[0141] Step S54: generating a dynamic adjustment strategy according to the value range, adjusting the lighting control strategy based on the dynamic adjustment strategy, and obtaining a power scheduling function;

[0142] Step S55: Perform timing adjustment in a simulation environment according to the power scheduling function to obtain the optimal lighting control strategy.

[0143] Specifically, the power limit information of the mobile lighting tower is first obtained. This data set covers the current battery power, battery discharge curve, device power consumption history, device maximum output power, and scheduled operation time limit. Then, feature extraction is performed on the power limit data set to generate a power limit feature vector. Feature extraction aims to extract representative parameters from the original power limit data, which are helpful for in-depth analysis of the relationship between battery power changes and device power output. The extracted features include at least power consumption rate, power load fluctuation, remaining power prediction value, and maximum working time.

[0144] The power consumption rate reflects the speed at which the device uses power under different load conditions; the power load fluctuation reflects the change in the power consumption of the device in different time periods, which is critical for dynamically adjusting the lighting duration, because the fluctuation of the power load may affect the discharge curve of the battery. The remaining power forecast value is a forecast of the remaining power of the battery in the future based on the existing data, which helps the system determine whether it can continue to provide lighting services. The maximum working time is the longest time that the device can continue to work, calculated based on the existing power and the power consumption rate.

[0145] Subsequently, each feature in the power limit feature vector is weighted, and different weights are assigned to each feature according to its influence on the final lighting duration during the optimization process. For example, the remaining battery power and the maximum working time are given higher weights because the power consumption rate and load fluctuation have relatively little impact on the battery life. Through weighted processing, the power limit condition obtained can accurately reflect the optimal range of lighting duration under specific battery status and device load conditions.

[0146] Based on these power constraints, a dynamic adjustment strategy is generated. This strategy adjusts the lighting control strategy according to the real-time changes in battery power, power consumption rate, and other influencing factors to meet lighting needs while avoiding battery exhaustion. The core advantage of the dynamic adjustment strategy lies in its flexibility and adaptability. Based on this strategy, a power scheduling function is generated. This function is the core tool for controlling the power allocation and adjustment of the lighting system in different time periods. It can adjust the power output in real time according to environmental changes and device status to ensure the most suitable lighting intensity under power constraints.

[0147] Finally, the optimal lighting control strategy is tested and optimized by performing timing adjustments in a simulation environment based on the power scheduling function.

[0148] In some embodiments of the present application, step S6 is further introduced, which may specifically include:

[0149] Step S61: Obtain control instructions sent by the user based on the smart device, parse and extract key information in the control instructions, and form a demand data set;

[0150] Step S62: performing feature mapping on the demand data set to obtain a multi-dimensional user demand feature vector;

[0151] Step S63: Based on the optimal lighting control strategy and the multi-dimensional user demand feature vector, a lighting control solution that meets the user demand is obtained through matching analysis;

[0152] Step S64: optimizing the optimal lighting control strategy according to the lighting control scheme to obtain an optimization result;

[0153] Step S65: Generate a lighting control instruction according to the optimization result, and control the mobile lighting tower based on the lighting control instruction.

[0154] Specifically, obtaining control instructions sent by users based on smart devices is the starting point of the entire process. Users can use applications, voice assistants or other means on smart devices to send control instructions to the lighting system. These instructions cover the user's lighting needs, such as brightness, lighting duration, lighting mode, etc. After extracting key information from the instructions, a demand data set is formed. The content of this set may include the light intensity requested by the user, the desired lighting time, the required lighting mode (such as constant light, gradual change, flashing, etc.) and other environmental requirements.

[0155] Next, feature mapping is performed on the demand data set to obtain a multi-dimensional user demand feature vector. The function of feature mapping is to convert user demand from the original control instructions into numerical features that can be quantified and processed. These feature vectors may include the range of light intensity required by the user, the upper and lower limits of the lighting duration, and the selected lighting mode. The feature mapping process can use standardization, normalization, and vectorization methods in machine learning to ensure that the generated feature vector can effectively reflect the multi-dimensional characteristics of user demand.

[0156] After that, the optimal lighting control strategy is matched with the user's needs and analyzed, and the differences between the user's demand feature vector and the various features in the optimal lighting control strategy are compared to determine whether the lighting control strategy needs to be adjusted. After the needs and strategies are matched, the optimal lighting control strategy is optimized to generate a final lighting control solution that meets the user's needs. The optimization process adjusts the lighting control strategy according to user needs. For example, if the user requires a longer lighting duration, the power output strategy needs to be adjusted to extend the lighting time; if the user's needs exceed the power output capacity of the device, the light intensity or lighting mode will be automatically adjusted to ensure the lighting effect while avoiding excessive battery consumption. The goal of optimization is to find a balance point to meet the user's lighting needs as much as possible without exceeding the power and battery limits of the device.

[0157] After optimization, the final lighting control instructions will contain specific lighting parameters, such as lighting intensity, duration and control mode, and the mobile lighting tower will be controlled according to the instructions. The generation of control instructions not only takes into account the actual needs of users, but also fully optimizes factors such as the power consumption and remaining power of the equipment to ensure the reliability and stability of the lighting system.

[0158] A control device for a mobile lighting tower provided in an embodiment of the present application is described below. The control device for a mobile lighting tower described below and the control method for a mobile lighting tower described above can be referenced to each other.

[0159] See also Figure 3 , Figure 3 A schematic diagram of a control device for a mobile lighting tower disclosed in an embodiment of the present application.

[0160] like Figure 3 As shown, the control device of the mobile lighting tower may include:

[0161] A collection module 110 is used to detect environmental data using sensors on the mobile lighting tower to obtain a sensor data set, wherein the sensor data set includes multi-dimensional data combining light intensity and temperature and humidity;

[0162] An analysis module 120 is used to perform trend analysis on the sensor data set to obtain an environmental change prediction result, wherein the environmental change prediction result includes lighting demand information within a preset time in the future;

[0163] A construction module 130, configured to construct a lighting strategy model in combination with the environmental change prediction result and the current environmental data detected by the sensor, and calculate a lighting control strategy based on the lighting strategy model;

[0164] A calculation module 140 is used to perform a sensitivity analysis on the light intensity in the lighting control strategy to obtain an influence weight of the light intensity on the lighting control strategy, and calculate an optimal lighting duration based on the influence weight;

[0165] An optimization module 150, configured to obtain power limitation information of the mobile lighting tower, and optimize the lighting control strategy based on the optimal lighting duration and the power limitation information to obtain an optimal lighting control strategy;

[0166] The control module 160 is used to perform comprehensive calculations based on the user demand information and the optimal lighting control strategy, generate lighting control instructions, and control the mobile lighting tower based on the lighting control instructions, wherein the user demand information is obtained by parsing the control instructions sent by the user based on the smart device. It can be seen from the above technical solutions that the control method and related equipment of a mobile lighting tower provided by the embodiment of the present application first use the sensor on the tower to detect environmental data to form a sensor data set containing multi-dimensional data such as light intensity, temperature and humidity. Then, trend analysis is performed on these data to obtain environmental change prediction results containing lighting demand information within a preset time in the future. After that, a lighting strategy model is constructed by combining the environmental change prediction results with the current environmental data, and then the lighting control strategy is calculated. In order to optimize the lighting scheme, a sensitivity analysis is performed on the light intensity in the strategy, its influence weight is determined, and the optimal lighting duration is calculated. Then the power limit information of the tower is obtained, and the strategy is optimized in combination with the optimal lighting duration to obtain the optimal lighting control strategy. Finally, the control instructions sent by the user based on the smart device are parsed to obtain user demand information, which is comprehensively calculated with the optimal lighting control strategy to generate lighting control instructions to control the tower.

[0167] This application can grasp the trend of environmental changes in real time by collecting and analyzing multi-dimensional environmental data such as light intensity, temperature and humidity, avoiding the problem of unstable lighting effects caused by existing technologies relying on fixed modes or manual adjustments. It dynamically adjusts the lighting strategy based on environmental change predictions and current environmental data, calculates the optimal lighting duration based on sensitivity analysis, and can parse user instructions and integrate user needs with the optimal strategy. It can flexibly adjust the lighting effect according to different scenarios and user needs, improving the personalization and intelligence level of the lighting system. In an emergency, it can quickly respond to real-time user needs, avoiding the problem of being unable to adjust the lighting mode in time, effectively improving lighting efficiency, effects and energy utilization, greatly improving the intelligence level of mobile lighting towers, and providing efficient, energy-saving and intelligent solutions for changing outdoor lighting needs.

[0168] The control device of the mobile lighting tower provided in the embodiment of the present application can be applied to the control equipment of the mobile lighting tower. Figure 4The hardware structure diagram of the control device of the mobile lighting tower is shown in FIG. Figure 4 , the hardware structure of the control device of the mobile lighting tower may include: at least one processor 10, at least one communication interface 20, at least one memory 30 and at least one communication bus 40;

[0169] In the embodiment of the present application, the number of the processor 10, the communication interface 20, the memory 30, and the communication bus 40 is at least one, and the processor 10, the communication interface 20, and the memory 30 communicate with each other through the communication bus 40;

[0170] The processor 1 may be a central processing unit CPU, or an application-specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present invention, etc.;

[0171] The memory 3 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), etc., such as at least one disk memory;

[0172] The memory stores a program, and the processor can call the program stored in the memory, wherein the program is used to:

[0173] Using sensors on the mobile lighting tower to detect environmental data, a sensor data set is obtained, wherein the sensor data set includes multi-dimensional data combining light intensity and temperature and humidity;

[0174] Performing trend analysis on the sensor data set to obtain an environmental change prediction result, wherein the environmental change prediction result includes lighting demand information within a preset time in the future;

[0175] Building a lighting strategy model in combination with the environmental change prediction result and the current environmental data detected by the sensor, and calculating a lighting control strategy based on the lighting strategy model;

[0176] Performing a sensitivity analysis on the light intensity in the lighting control strategy to obtain an influence weight of the light intensity on the lighting control strategy, and calculating an optimal lighting duration based on the influence weight;

[0177] Acquire power limitation information of the mobile lighting tower, optimize the lighting control strategy based on the optimal lighting duration and the power limitation information, and obtain an optimal lighting control strategy;

[0178] A comprehensive calculation is performed based on the user demand information and the optimal lighting control strategy to generate a lighting control instruction, and the mobile lighting tower is controlled based on the lighting control instruction, wherein the user demand information is obtained by parsing the control instruction sent by the user based on the smart device.

[0179] Optionally, the detailed functions and extended functions of the program may refer to the above description.

[0180] The embodiment of the present application further provides a readable storage medium, which may store a program suitable for execution by a processor, wherein the program is used to:

[0181] Using sensors on the mobile lighting tower to detect environmental data, a sensor data set is obtained, wherein the sensor data set includes multi-dimensional data combining light intensity and temperature and humidity;

[0182] Performing trend analysis on the sensor data set to obtain an environmental change prediction result, wherein the environmental change prediction result includes lighting demand information within a preset time in the future;

[0183] Building a lighting strategy model in combination with the environmental change prediction result and the current environmental data detected by the sensor, and calculating a lighting control strategy based on the lighting strategy model;

[0184] Performing a sensitivity analysis on the light intensity in the lighting control strategy to obtain an influence weight of the light intensity on the lighting control strategy, and calculating an optimal lighting duration based on the influence weight;

[0185] Acquire power limitation information of the mobile lighting tower, optimize the lighting control strategy based on the optimal lighting duration and the power limitation information, and obtain an optimal lighting control strategy;

[0186] A comprehensive calculation is performed based on the user demand information and the optimal lighting control strategy to generate a lighting control instruction, and the mobile lighting tower is controlled based on the lighting control instruction, wherein the user demand information is obtained by parsing the control instruction sent by the user based on the smart device.

[0187] Optionally, the detailed functions and extended functions of the program may refer to the above description.

[0188] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0189] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0190] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A control method for a mobile lighting tower, characterized in that: include: Using sensors on the mobile lighting tower to detect environmental data, a sensor data set is obtained, wherein the sensor data set includes multi-dimensional data combining light intensity and temperature and humidity; Performing trend analysis on the sensor data set to obtain an environmental change prediction result, wherein the environmental change prediction result includes lighting demand information within a preset time in the future; Building a lighting strategy model in combination with the environmental change prediction result and the current environmental data detected by the sensor, and calculating a lighting control strategy based on the lighting strategy model; Performing a sensitivity analysis on the light intensity in the lighting control strategy to obtain an influence weight of the light intensity on the lighting control strategy, and calculating an optimal lighting duration based on the influence weight; Acquire power limitation information of the mobile lighting tower, optimize the lighting control strategy based on the optimal lighting duration and the power limitation information, and obtain an optimal lighting control strategy; A comprehensive calculation is performed based on the user demand information and the optimal lighting control strategy to generate a lighting control instruction, and the mobile lighting tower is controlled based on the lighting control instruction, wherein the user demand information is obtained by parsing the control instruction sent by the user based on the smart device.

2. The method according to claim 1, characterized in that The sensor on the mobile lighting tower is used to detect environmental data to obtain a sensor data set, including: Using the sensor on the mobile lighting tower to detect the light intensity data and temperature and humidity data of the environment; The light intensity data is collected in layers to obtain light intensity data at multiple different heights and orientations, and integrated and weighted to obtain light intensity distribution data; Perform multi-dimensional feature extraction on the temperature and humidity data to obtain independent contributions of temperature and humidity to light intensity changes, and build a regression model based on the interaction between temperature and humidity to obtain global temperature and humidity prediction data; Classifying the environmental state at each moment according to the interactive relationship between the light intensity distribution data and the global temperature and humidity prediction data to obtain dynamic environmental state data; The light intensity distribution data, the global temperature and humidity prediction data and the dynamic environmental status data are fused to obtain a sensor data set.

3. The method according to claim 1, characterized in that Performing trend analysis on the sensor data set to obtain environmental change prediction results includes: Performing time series decomposition processing on the light intensity data in the sensor data set to obtain a long-period trend component; Performing dynamic state estimation on the temperature and humidity data in the sensor data set to obtain state estimation values ​​corresponding to the temperature and humidity data; Performing spatiotemporal correlation analysis on the long-term trend component and the state estimation value to generate an environmental change trend; The exponential smoothing method is used to predict the environmental change trend in a future time period to obtain the environmental change prediction result, wherein the environmental change prediction result includes lighting demand information within a future preset time period.

4. The method according to claim 1, characterized in that Combining the environmental change prediction result and the current environmental data detected by the sensor to build a lighting strategy model, and calculating a lighting control strategy based on the lighting strategy model, including: Performing joint modeling processing on the environmental change prediction result and the current environmental data detected by the sensor to obtain a joint model of environmental change and lighting demand; The joint model is used to perform feature importance analysis on each input feature, calculate the contribution of each input feature to the lighting demand prediction result, and obtain the key factors affecting the lighting control strategy; Based on the key factors, a dynamic weight allocation mechanism is constructed to obtain a lighting control strategy weight model; The lighting control strategy weight model is optimized based on a particle swarm optimization algorithm to generate the lighting control strategy.

5. The method according to claim 1, characterized in that Performing a sensitivity analysis on the light intensity in the lighting control strategy to obtain an influence weight of the light intensity on the lighting control strategy, and calculating an optimal lighting duration based on the influence weight, including: Performing weight distribution processing on the light intensity in the lighting control strategy based on the light intensity data to form a weight distribution result; Performing a sensitivity evaluation on the weight distribution result, calculating the influence of the environmental factors in the weight distribution result on the lighting control strategy, and obtaining an analysis result, wherein the environmental factors include light intensity data and temperature and humidity data; The influence weight of each environmental factor in the analysis result is multiplied by the lighting demand in the lighting control strategy to obtain the lighting intensity demand in each time period, and the optimal lighting duration is calculated according to the lighting intensity demand.

6. The method according to claim 1, characterized in that Acquiring power limit information of the mobile lighting tower, optimizing the lighting control strategy based on the optimal lighting duration and the power limit information, and obtaining an optimal lighting control strategy, including: Obtaining power limit information of the mobile lighting tower, wherein the power limit information includes at least current battery power, battery discharge curve, power consumption history, maximum output power of the device, and a predetermined operation time limit; Extracting features from the power limitation information to obtain feature data of power consumption rate, power load fluctuation, remaining power prediction value and maximum working time, and forming a power limitation feature vector; Performing weighted processing on each feature in the power limitation feature vector to form a power limitation condition, and obtaining a value range of an optimal lighting duration under the power limitation condition; Generate a dynamic adjustment strategy according to the value range, adjust the lighting control strategy based on the dynamic adjustment strategy, and obtain a power scheduling function; Timing adjustment is performed in a simulation environment according to the power scheduling function to obtain the optimal lighting control strategy.

7. The method according to claim 1, characterized in that Performing comprehensive calculations based on user demand information and the optimal lighting control strategy to generate lighting control instructions, and controlling the mobile lighting tower based on the lighting control instructions, including: Obtain control instructions sent by users based on smart devices, parse and extract key information in the control instructions, and form a demand data set; Performing feature mapping on the demand data set to obtain a multi-dimensional user demand feature vector; Based on the optimal lighting control strategy and the multi-dimensional user demand feature vector, a lighting control solution that meets the user demand is obtained through matching analysis; Optimizing the optimal lighting control strategy according to the lighting control scheme to obtain an optimization result; A lighting control instruction is generated according to the optimization result, and the mobile lighting tower is controlled based on the lighting control instruction.

8. A control device for a mobile lighting tower, characterized in that: include: A collection module, used to detect environmental data using sensors on the mobile lighting tower to obtain a sensor data set, wherein the sensor data set includes multi-dimensional data combining light intensity and temperature and humidity; An analysis module, configured to perform trend analysis on the sensor data set to obtain an environmental change prediction result, wherein the environmental change prediction result includes lighting demand information within a preset time in the future; A construction module, used to construct a lighting strategy model in combination with the environmental change prediction result and the current environmental data detected by the sensor, and calculate a lighting control strategy based on the lighting strategy model; A calculation module, configured to perform a sensitivity analysis on the light intensity in the lighting control strategy, obtain an influence weight of the light intensity on the lighting control strategy, and calculate an optimal lighting duration based on the influence weight; An optimization module, configured to obtain power limitation information of the mobile lighting tower, and optimize the lighting control strategy based on the optimal lighting duration and the power limitation information to obtain an optimal lighting control strategy; The control module is used to perform comprehensive calculations based on user demand information and the optimal lighting control strategy, generate lighting control instructions, and control the mobile lighting tower based on the lighting control instructions, wherein the user demand information is obtained by parsing the control instructions sent by the user based on the smart device.

9. A control device for a mobile lighting tower, characterized in that: including memory and processor; The memory is used to store programs; The processor is used to execute the program to implement each step of the control method of the mobile lighting tower as described in any one of claims 1-7.

10. A readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, each step of the control method of the mobile lighting tower as described in any one of claims 1 to 7 is implemented.

Images