Environment monitoring type unmanned car washer

Abstract

The invention discloses an environment monitoring type unmanned car washer, which relates to the technical field of unmanned car washers, and comprises an environment data acquisition module, an environment adaptability analysis module, a car washing strategy adjustment module, a delay compensation optimization module and an intelligent resource optimization module, and generating environment state parameters. According to the invention, through real-time monitoring, a delay compensation algorithm and machine learning optimization, intelligent and precise operation of the unmanned car washing system is realized. The system dynamically adjusts the water spraying amount, the drying time and resource allocation according to environmental conditions, water stain residues are prevented, and resource waste is reduced. The machine learning optimizes the use of detergent and water based on historical data, reduces cost and pollution, and ensures the cleaning effect at the same time. According to the intelligent and environment-friendly combined scheme, the user experience and the equipment stability are improved, and the green and sustainable development of the unmanned car washing technology is promoted.

Description

Technical Field

[0001] This invention relates to the field of unmanned car wash technology, specifically to an environmental monitoring type unmanned car wash. Background Technology

[0002] Environmental monitoring-based unmanned car wash machines are innovative devices that combine intelligent monitoring technology with automated car washing functions. By integrating an environmental monitoring system during the car wash process, they monitor and analyze the surrounding environment in real time, including factors such as air quality, water quality, temperature, and humidity, to ensure optimal environmental conditions for car washing operations. This system can not only automatically identify and adjust the car wash program—for example, automatically selecting the car wash mode based on the degree of dirt on the vehicle or weather changes—but also optimize water resource usage and reduce energy waste based on environmental monitoring data, initiating the car wash process when the environment meets preset safety standards. Simultaneously, environmental monitoring-based unmanned car wash machines provide data feedback and remote control functions, improving user experience and operational efficiency, and promoting the development of intelligent and environmentally friendly car wash technology.

[0003] The existing technology has the following shortcomings: Environmentally monitored unmanned car wash machines may experience a mismatch between actual operation and environmental conditions due to delays in environmental data processing or system response lags. This issue requires attention. Specifically, if the environmental data (such as temperature, humidity, and air pollution) collected in real-time by the monitoring system fails to adjust the car wash strategy or optimize resource usage in a timely manner due to errors or delays, it may lead to inappropriate car wash operations. For example, in excessively high humidity or low temperature conditions, water evaporates slowly from the vehicle surface, easily forming water stains or damaging the paint, potentially causing corrosion over time. Furthermore, excessive use of water and detergents not only reduces economic efficiency but may also violate environmental regulations, leading to environmental pollution and legal risks. Therefore, the real-time performance and accuracy of the environmental monitoring system are crucial to ensuring the efficient operation of the car wash machine, guaranteeing vehicle quality, and meeting environmental requirements.

[0004] The information disclosed in the background section is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] The purpose of this invention is to provide an environmentally monitored unmanned car wash machine. By introducing real-time monitoring, latency compensation algorithms, and machine learning optimization mechanisms, the unmanned car wash system achieves intelligent and precise car washing processes. Real-time optimization avoids erroneous decisions caused by data latency, such as reducing water spray volume and extending drying time in high humidity environments, effectively preventing water stains and conserving resources. Simultaneously, the machine learning algorithm intelligently adjusts the use of detergent, water, and energy based on historical data, minimizing costs and environmental pollution while ensuring cleaning effectiveness. This solution, combining intelligence and environmental protection, not only improves user experience and equipment operational stability but also promotes the sustainable development of green unmanned car wash technology, addressing the problems mentioned in the background technology.

[0006] To achieve the above objectives, the present invention provides the following technical solution: an environmental monitoring-type unmanned car wash machine, comprising an environmental data acquisition module, an environmental adaptability analysis module, a car wash strategy adjustment module, a delay compensation optimization module, and an intelligent resource optimization module: The environmental data acquisition module uses the environmental monitoring system to acquire environmental data in real time and generate environmental status parameters. The environmental adaptability analysis module compares environmental state parameters with preset environmental adaptability thresholds to generate car wash adaptability analysis results. The car wash strategy adjustment module adjusts the car wash process based on the results of the car wash adaptability analysis, including the selection of water volume, detergent usage, and car wash mode. The delay compensation optimization module uses a delay response compensation algorithm to dynamically correct the delay and error of environmental data, and generates a real-time optimized car wash instruction. The intelligent resource optimization module uses machine learning algorithms to combine historical environmental data, car wash data, and resource usage records to optimize resource allocation in car wash strategies, achieving efficient and environmentally friendly car wash operations.

[0007] Preferably, the specific steps for using an environmental monitoring system to acquire environmental data in real time and generate environmental status parameters are as follows: Arrange and calibrate environmental monitoring equipment properly to ensure that the collected environmental data is accurate and reliable; Environmental data is dynamically captured through high-frequency sampling by sensors; Data is transmitted using a communication module, and data integrity and accuracy are ensured through parsing and verification. The collected data is calculated and normalized to generate quantitative environmental status indicators for subsequent decision-making.

[0008] Preferably, the specific steps for comparing environmental state parameters with preset environmental adaptability thresholds to generate car wash adaptability analysis results are as follows: Verify and read the generated real-time environmental status parameters to ensure the real-time nature and validity of the data; Retrieve preset adaptive thresholds from the parameter database to provide a scientific basis for parameter comparison; The algorithm compares environmental parameters with threshold ranges to assess car wash suitability and generate an overall judgment result. The analysis results are generated and output synchronously, providing clear guidance for subsequent adjustments to car wash strategies.

[0009] Preferably, the specific steps for adjusting the car wash process based on the car wash adaptability analysis results, including the selection of water volume, detergent usage, and car wash mode, are as follows: Receive and interpret the results of the car wash adaptability analysis to determine the impact of the environment on the car wash process; Based on the analysis results and rule base, a dynamic car wash strategy is generated to adapt to different environmental conditions. The water volume, detergent ratio, and car wash mode are optimized in real time according to the adjustment strategy, and the operation is executed precisely. By monitoring the effects of adjustments and recording data, we can continuously optimize car wash strategies to improve long-term operational efficiency and Effect.

[0010] Preferably, the specific steps for using a delay response compensation algorithm to dynamically correct the delay and error of environmental data and generate real-time optimized car wash instructions are as follows: First, a time delay assessment is performed on the real-time acquired environmental data. The environmental data acquired by the sensors experiences time delays due to network transmission and device processing. To model the delay error, historical data is compared with the current data, and the delay factor is calculated. The calculation expression is as follows: , In the formula, This is the current delay error factor, used to describe the degree of deviation between historical data and current data. It is the sensor in time Environmental parameter values ​​collected in real time It is the detected delay time. It is the size of the data sampling window; In obtaining the delay error factor Then, the current sensor data is dynamically corrected based on... The filtering algorithm, combined with the prediction model, corrects the current environmental parameters by adjusting the delay error factor. To predict future environmental parameters and compensate for the impact of delays, the correction formula is as follows: , In the formula, These are the corrected environmental parameter values, used for subsequent decision-making. These are the currently collected environmental parameter values. These are predicted values ​​of environmental parameters. It is the gain factor, and its calculation expression is as follows: , In the formula, It is the measurement error covariance; After completing the environmental data correction, the corrected parameters will be... Input the optimization model to generate real-time car wash instructions. The instruction optimization formula is as follows: , In the formula, It is a car wash command that has been optimized in real time. It is the car wash resource allocation coefficient. It is the resource utilization rate. It is the environmental adaptability adjustment coefficient. It is the maximum tolerable delay error factor.

[0011] Preferably, the specific steps for applying machine learning algorithms to combine historical environmental data, car wash data, and resource usage records to optimize resource allocation in car wash strategies and achieve efficient and environmentally friendly car wash operations are as follows: Key features were extracted from historical data, including environmental data, car wash parameters, and records of resource consumption and cleaning effectiveness. Since the raw data contained noise and missing values, data cleaning techniques were applied. Feature scaling and dimensionality reduction techniques were used to extract the features most relevant to resource allocation optimization, which were then used to construct the training dataset. The formula is as follows: , In the formula, It is the extracted optimized feature vector. It is time Humidity value at any given time It is time Air quality index at any given time. It is time Water quality parameters at any given time , , They are time The amount of water, detergent, and car wash mode at any given time. and They are time The efficiency and resource cost of cleaning at all times; Based on the extracted optimized feature vector A resource allocation optimization model is constructed using reinforcement learning algorithms. The goal of this model is to maximize car wash efficiency, minimize resource consumption costs, and ensure minimal environmental impact. The model is trained using historical data to dynamically learn the optimal resource allocation strategy under different environmental conditions. The calculation expression is as follows: , In the formula, It is a state Take action below Long-term returns It's a discount factor, a weighted measure of future returns. The next state is... This is the current state, which is determined by the optimized feature vectors. express, This is the current resource allocation strategy. This is the resource allocation strategy to be adopted in the future. It provides immediate feedback, calculated by combining cleaning efficiency and resource consumption, using the following formula: , In the formula, It's about cleaning efficiency. It is a consumption of resources. It is an environmental impact. and These are all adjustable parameters used to balance cleaning efficiency. With resource consumption and environmental impact ; By using a trained reinforcement learning model, the optimal resource allocation strategy is predicted under the current environmental conditions. A feedback mechanism is used to monitor the actual execution effect in real time, comparing the real-time data with the prediction results and dynamically adjusting the allocation strategy to adapt to environmental changes. The formula is as follows: , In the formula, This is the optimized water usage value. This is the optimized detergent usage. It's an optimized car wash mode. This refers to the current environmental state. It is in state The following allocation strategy will be adopted. The predicted returns In a given state Next, find the function that makes Actions that reach the maximum value .

[0012] The technical effects and advantages provided by the present invention in the above technical solution are as follows: This invention, by introducing real-time monitoring, a delay compensation algorithm, and a dynamic adjustment mechanism, enables the unmanned car wash system to optimize the car wash process in real time according to complex environmental conditions. This intelligent operation ensures the accuracy of car wash decisions and avoids erroneous operations caused by delays or mismatches in environmental data. For example, under high humidity conditions, the system can automatically reduce the amount of water sprayed and extend the drying time, effectively preventing water stains and reducing resource waste. Simultaneously, the delay compensation algorithm further enhances the accuracy of car wash strategy adjustments by correcting for data lag, enabling the system to cope with rapidly changing environmental conditions. This effect not only improves car wash quality but also significantly enhances user experience and equipment operational stability, ensuring the system maintains high efficiency in various environments.

[0013] This invention utilizes machine learning algorithms to intelligently optimize resource usage, achieving a new balance in the allocation of detergent, water, and energy in the unmanned car wash system. Through continuous learning and optimization of historical data, the system can identify the optimal resource usage patterns under different environmental conditions, such as reducing detergent usage in lightly polluted environments and selecting a water-saving mode in high-humidity conditions. This data-driven optimization strategy not only reduces operating costs but also significantly reduces water waste and detergent emissions. Furthermore, the system analyzes the results after each wash operation, continuously improving resource usage strategies to ensure cleaning effectiveness while maximizing resource conservation. This approach aligns with current green and environmentally friendly principles, laying the foundation for the widespread adoption of intelligent unmanned car wash technology and promoting sustainable development in the industry. Attached Figure Description

[0014] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0015] Figure 1 This is a schematic diagram of the modules of the environmental monitoring unmanned car wash machine of the present invention. Detailed Implementation

[0016] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that the description of this disclosure will be more complete and fully convey the concept of the exemplary embodiments to those skilled in the art.

[0017] This invention provides, for example Figure 1The environmental monitoring-based unmanned car wash machine shown includes an environmental data acquisition module, an environmental adaptability analysis module, a car wash strategy adjustment module, a delay compensation optimization module, and an intelligent resource optimization module. The environmental data acquisition module uses the environmental monitoring system to acquire environmental data in real time and generate environmental status parameters. The specific steps for acquiring environmental data in real time using an environmental monitoring system and generating environmental status parameters are as follows: Arrange and calibrate environmental monitoring equipment properly to ensure that the collected environmental data is accurate and reliable; Various environmental monitoring devices, such as temperature and humidity sensors, air quality sensors, and water quality sensors, are deployed around or inside the car wash machine. These devices, through proper arrangement, cover the main environmental areas where the car wash machine operates. Deployment must consider the accuracy, response time, and adaptability of the sensors to ensure real-time and reliable data acquisition. Before starting the equipment, the sensors need to be initialized, including calibrating the equipment, setting the measurement range and thresholds, and checking equipment connectivity. For example, temperature and humidity sensors need to be calibrated using a reference environment to eliminate hardware errors; air quality sensors need to be initialized to filter out background noise to ensure measurement accuracy.

[0018] Environmental data such as air quality, temperature, humidity, and water quality are dynamically captured through high-frequency sampling by sensors. Once the environmental monitoring system is operational, various sensors work synchronously to collect key environmental data in real time, including air quality (such as PM2.5 concentration), temperature and humidity (such as relative humidity and air temperature), and water quality (such as pH value and turbidity). These sensors continuously acquire dynamically changing environmental information at a high sampling frequency and transmit the raw data to the data processing center via wired or wireless means. For example, the temperature and humidity sensor samples once per second, recording real-time changes in environmental temperature and humidity; the air quality sensor detects the concentration of suspended particulate matter using the principle of light scattering. Real-time acquisition ensures the dynamic updating of environmental data, providing an accurate foundation for subsequent processing.

[0019] Data is transmitted using a communication module, and data integrity and accuracy are ensured through parsing and verification. Environmental data collected is transmitted to the central processing unit of the environmental monitoring system via a communication module (such as Wi-Fi, Bluetooth, or industrial-grade IoT protocols). During transmission, to ensure data integrity and reliability, the system employs anti-interference coding technology and data verification algorithms. For example, if PM2.5 concentration data collected by the air quality sensor fluctuates, the transmission module compresses and encodes the data and adds a checksum to verify its accuracy at the receiving end. After the data reaches the central processing unit, the system decodes and classifies the multi-source data using a data parsing module, marking or removing abnormal data (such as values ​​exceeding reasonable ranges).

[0020] The collected data is calculated and normalized to generate quantitative environmental status indicators for subsequent decision-making. After centralized processing, the environmental data undergoes further calculation and analysis, transforming it into environmental state parameters. The system matches the collected real-time data with preset models, calculating various comprehensive indicators through algorithms. For example, it generates a humidity index from temperature and humidity data, and a pollution index from air quality data. To more intuitively reflect the current environmental state, the system also normalizes these parameters, representing them within a unified quantitative range (e.g., 0-100 points). Simultaneously, these parameters can be stored in a database as a reference for subsequent car wash strategy adjustments and historical data analysis. For example, if the air humidity exceeds 75%, the system-generated humidity index may be marked as "high humidity," suggesting that water consumption should be reduced during subsequent car washes.

[0021] The environmental adaptability analysis module compares environmental state parameters with preset environmental adaptability thresholds to generate car wash adaptability analysis results. The specific steps for comparing environmental state parameters with preset environmental adaptability thresholds to generate car wash adaptability analysis results are as follows: Verify and read the generated real-time environmental status parameters to ensure the real-time nature and validity of the data; In the environmental monitoring system, environmental state parameters serve as input to the adaptive analysis module. Using parameters generated in the previous stage (such as humidity index, air pollution index, and water quality level), the system automatically reads the latest environmental state data and verifies the data's timestamp and source to ensure the parameters used are real-time and valid. For example, if the humidity index shows high humidity (>75%), the system will mark the current environment as potentially unsuitable for car washing. This step, through parameter verification and classification, lays the data foundation for subsequent adaptive analysis and simultaneously establishes a seamless connection with the environmental data generation stage.

[0022] Retrieve preset adaptive thresholds from the parameter database to provide a scientific basis for parameter comparison; The system presets environmental adaptability thresholds based on different car wash conditions, and these thresholds are stored in a parameter database. For example, the suitable air humidity range for car washing might be 30%-70%, the air pollution index (PM2.5) threshold might be <75, and there are corresponding standards for water hardness and pH. When environmental parameters are input, the system retrieves these preset thresholds from the database and compares them one-to-one with the real-time parameters. For example, when the retrieved humidity adaptability threshold is 30%-70%, the system compares the humidity value of the environmental parameter (e.g., 80%) with this threshold to determine if it exceeds the range. The scientific rationality of the preset thresholds ensures the accuracy and reliability of the analysis results.

[0023] The algorithm compares environmental parameters with threshold ranges to assess car wash suitability and generate an overall judgment result. The environmental monitoring system performs an adaptive analysis by comparing environmental state parameters with preset thresholds. The system's built-in logical judgment algorithm evaluates each parameter to ensure it falls within the threshold range. For example, if the air humidity is 80%, exceeding the adaptive threshold, the system marks it as "unsuitable for car washing"; conversely, if the PM2.5 concentration is 50%, below the threshold, it is marked as "suitable for car washing." Simultaneously, the system generates an overall car washing adaptability level through comprehensive analysis of multiple parameters, such as "suitable," "unsuitable," or "mode adjustment needed." This algorithmic process ensures the comprehensiveness and accuracy of the analysis, providing a clear decision-making basis for subsequent steps.

[0024] The analysis results are generated and output synchronously, providing clear guidance for subsequent adjustments to car wash strategies. Based on parameter comparison and adaptability assessment results, the system generates a car wash adaptability analysis report and outputs the results in graphical or quantitative form. For example, the analysis results may indicate excessive humidity, suggesting delaying the car wash, or moderate air quality, suggesting starting the car wash. Simultaneously, these results are synchronized to the system interface or cloud via the communication module for operators or remote users to view. The system can also trigger subsequent adjustments based on the results, such as reducing water volume or pausing the car wash operation. Through the output adaptability analysis results, the car wash machine can take timely optimization measures to avoid starting the car wash process due to unsuitable environmental conditions, thereby ensuring car wash quality and equipment safety.

[0025] The car wash strategy adjustment module adjusts the car wash process based on the results of the car wash adaptability analysis, including the selection of water volume, detergent usage, and car wash mode. The specific steps for adjusting the car wash process based on the car wash adaptability analysis results, including the selection of water volume, detergent usage, and car wash mode, are as follows: Receive and interpret the results of the car wash adaptability analysis to determine the impact of the environment on the car wash process; After completing the car wash adaptability analysis, the system transmits the results to the car wash strategy adjustment module. This module receives the analysis results, including whether each environmental parameter exceeds the adaptability threshold and the corresponding adjustment suggestions. For example, if the humidity is high (e.g., >75%), the analysis result may be marked as "reduce water usage"; if the air pollution index is high (e.g., PM2.5 >75), it is recommended to increase the washing pressure and detergent usage. Based on the received results, the system interprets the impact of the current environment on the car wash process through logical judgment procedures and provides basic data for specific adjustments. This process ensures that the analysis results are accurately transmitted to the adjustment module, providing support for actual operation.

[0026] Based on the analysis results and rule base, a dynamic car wash strategy is generated to adapt to different environmental conditions. Based on the analysis results, the system calls upon its internal rule base and preset car wash strategy templates to generate specific adjustment plans. The car wash strategy templates are configured with multiple operating modes based on different adaptability conditions, such as standard mode, water-saving mode, and enhanced cleaning mode. For example, when humidity is high, the system will prioritize water-saving mode, reducing water spraying time; when air quality is poor, it will automatically select enhanced cleaning mode, increasing detergent usage and water pressure. Simultaneously, the strategy generation process also comprehensively considers the current operating status of the equipment and resource usage to avoid frequent mode switching or resource waste. Through automatically generated adjustment strategies, the system can dynamically adapt to the needs of different environmental conditions.

[0027] The water volume, detergent ratio, and car wash mode are optimized in real time according to the adjustment strategy, and the operation is executed precisely. The system adjusts the car wash process in real time based on the generated strategy. For example, it controls the water pump output to reduce water consumption or adjusts the spray pressure to adapt to air quality conditions. During execution, the ratio of water to detergent is precisely controlled by valves to ensure accuracy and consistency. Simultaneously, the switching of car wash modes is automatically completed by program logic, such as switching from standard mode to high-pressure cleaning mode to handle heavily soiled vehicles. During this stage, the system also monitors the car wash process in real time using sensors to verify whether the adjustments have achieved the expected results. If the deviation is too large, the system will immediately readjust to ensure the accurate execution of the car wash process.

[0028] By monitoring the effects of adjustments and recording data, we can continuously optimize car wash strategies to improve long-term operational efficiency and Effect; After the car wash process is completed, the system evaluates the adjustment effect and feeds relevant data back to the strategy optimization module. For example, a humidity sensor detects whether there is excessive residual moisture on the vehicle surface, or a visual sensor checks whether the cleanliness meets the standard. The feedback data is stored in the system's history and used to optimize subsequent car wash strategy templates. For example, if the water-saving mode is not effective under high humidity conditions, the system will appropriately increase water usage or extend drying time in subsequent optimizations. This closed-loop feedback mechanism not only improves the efficiency of the car wash process but also provides data support for continuous improvement in the long term.

[0029] The delay compensation optimization module uses a delay response compensation algorithm to dynamically correct the delay and error of environmental data, and generates a real-time optimized car wash instruction. The specific steps for using a delay response compensation algorithm to dynamically correct for delays and errors in environmental data and generate real-time optimized car wash instructions are as follows: First, a time delay assessment is performed on the real-time environmental data. Environmental data collected by sensors (such as air humidity, air quality index, and water quality index) experiences time delays due to network transmission and device processing. To model this delay error, historical data is compared with current data, and a delay factor is calculated. The calculation expression is as follows: , In the formula, This is the current delay error factor, used to describe the degree of deviation between historical data and current data. It is the sensor in time Environmental parameter values ​​collected in real time It is the detected delay time. This is the size of the data sampling window, used for cumulative error calculation; The delay error factor generated in this step It provides a quantitative description of the data latency problem for subsequent correction calculations.

[0030] In obtaining the delay error factor Then, the current sensor data is dynamically corrected based on... The filtering algorithm, combined with the prediction model, corrects the current environmental parameters by adjusting the delay error factor. To compensate for the impact of delays, future environmental parameters are predicted, and the corrected formula is as follows: , In the formula, These are the corrected environmental parameter values, used for subsequent decision-making. These are the currently collected environmental parameter values. These are predicted environmental parameters, calculated by combining current and historical data. It is the gain factor, and its calculation expression is as follows: , In the formula, It is the measurement error covariance; Corrected parameters It is more in line with real-world environmental conditions and will be used to generate subsequent car wash instructions, significantly improving real-time performance and accuracy.

[0031] After completing the environmental data correction, the corrected parameters will be... Input the optimization model to generate real-time car wash instructions. The optimized instructions are calculated based on resource utilization and adaptability to environmental conditions, aiming to ensure efficiency and environmental protection. The instruction optimization formula is as follows:

[0032] In the formula, It is a real-time optimized car wash command (such as water volume, detergent ratio, etc.). It is a car wash resource allocation coefficient, which balances water usage and detergent consumption. It represents resource utilization rate, with a value ranging from 0 to 1. It is an environmental adaptability adjustment factor used to enhance the system's tolerance to latency errors. It is the maximum tolerable delay error factor used to normalize the current delay error. Standardize it to a range of 0 to 1 so that it can be treated uniformly in optimization calculations.

[0033] The optimized car wash instructions are derived from the above steps. It can dynamically adjust car wash strategies, such as water volume and detergent usage, to adapt to current environmental conditions and optimize resources.

[0034] The intelligent resource optimization module uses machine learning algorithms to combine historical environmental data, car wash data, and resource usage records to optimize resource allocation in car wash strategies, achieving efficient and environmentally friendly car wash operations. The specific steps for optimizing resource allocation in car wash strategies by applying machine learning algorithms in conjunction with historical environmental data, car wash data, and resource usage records to achieve efficient and environmentally friendly car wash operations are as follows: Key features are extracted from historical data, including environmental data (such as temperature and humidity, air quality index, and water quality parameters), car wash parameters (such as water usage, detergent usage, and car wash mode), and records of resource consumption and cleaning effectiveness (such as cleaning efficiency and resource cost). Since the raw data contains noise and missing values, data cleaning techniques (such as mean imputation or interpolation) are applied. Feature scaling and dimensionality reduction techniques (such as principal component analysis, PCA) are used to extract the features most relevant to resource allocation optimization, which are then used to construct the training dataset. The formula is as follows: In the formula, These are the extracted optimized feature vectors, used for subsequent modeling. It is time Humidity value at any given time It is time Air quality index at any given time. It is time Water quality parameters at any given time , , They are time The amount of water, detergent, and car wash mode at any given time. and They are time The cleaning efficiency at any given time (such as cleanliness rating) and resource costs (such as the total cost of water, electricity, and detergent); Based on the extracted optimized feature vector A resource allocation optimization model is constructed using reinforcement learning algorithms (such as Deep Q-Network, DQN). The goal of this model is to maximize car wash efficiency, minimize resource consumption costs, and ensure minimal environmental impact. The model is trained using historical data to dynamically learn the optimal resource allocation strategy under different environmental conditions. The calculation expression is as follows: In the formula, It is a state Take action below Long-term returns It's a discount factor, a weighted measure of future returns. The next state is... This is the current state, which is determined by the optimized feature vectors. express, This is the current resource allocation strategy. This is the resource allocation strategy to be adopted in the future. It provides immediate feedback, calculated by combining cleaning efficiency and resource consumption, using the following formula: In the formula, It's about cleaning efficiency. It is a consumption of resources. It is an environmental impact. and These are all adjustable parameters used to balance cleaning efficiency. With resource consumption and environmental impact ; Using a trained reinforcement learning model, the optimal resource allocation strategy is predicted under the current environmental conditions. The prediction results include optimized water volume, detergent usage, and car wash mode. A feedback mechanism is used to monitor the actual execution effect in real time, comparing the real-time data with the prediction results and dynamically adjusting the allocation strategy to cope with environmental changes. The formula is as follows: In the formula, This is the optimized water usage value. This is the optimized detergent usage. It's an optimized car wash mode. It represents the current environmental state, derived from feature vectors. express, It is in state The following allocation strategy will be adopted. The predicted returns In a given state Next, find the function that makes Actions that reach the maximum value .

[0035] Implementation Method 1: The core of this implementation method lies in dynamically adjusting the car wash process through real-time monitoring of environmental data to cope with complex and ever-changing external environmental conditions. The unmanned car wash system first collects environmental data in real time using various sensor modules (such as air quality sensors, temperature and humidity sensors, and water quality sensors). These sensors are strategically placed around the car wash machine and inside the equipment, covering key areas during the car wash process, such as the water circulation system and spraying areas. The real-time collected air quality data (such as PM2.5 concentration), temperature and humidity data (such as air humidity and ambient temperature), and water quality data (such as water pH value and hardness) are transmitted to the central processing unit to generate environmental status parameters. These parameters are a quantitative expression of the current environmental state, providing a basis for subsequent decision-making and adjustments.

[0036] After environmental data collection is complete, the system compares the environmental parameters with preset adaptability thresholds. These thresholds are preset ranges based on a comprehensive consideration of factors such as car wash effectiveness, safety, and resource utilization efficiency. For example, suitable air humidity for car washing might be set between 30% and 70%, temperature between 10℃ and 35℃, and water pH between 6.5 and 8.5. If the air humidity exceeds 70%, the system classifies it as a high-humidity environment, where moisture on the vehicle surface is difficult to evaporate, potentially leading to water stains. Conversely, if the temperature is below 10℃, water may freeze, damaging the vehicle. Based on these assessments, the system generates a car wash adaptability analysis result, determining whether to initiate the car wash process or how to adjust the car wash mode.

[0037] Dynamic adjustment is a key aspect of this implementation method. Based on the results of adaptability analysis, the system automatically adjusts parameters in the car wash process, such as water volume, detergent dosage, and wash mode. For example, in high humidity environments, the system selects a water-saving mode, reducing the amount of water sprayed and the washing time, while optimizing the power of the drying system to accelerate the evaporation process; while when the air pollution index is high, the system selects an enhanced cleaning mode, increasing water pressure and detergent dosage to ensure cleaning effectiveness. Real-time adjustment also includes dynamically monitoring operating parameters such as spray water pressure, washing time, and drying time to ensure that each step of the operation is precisely matched with environmental conditions.

[0038] Furthermore, this implementation method also utilizes remote monitoring to synchronize real-time data and adjustment results during the car wash process to the user or management terminal, allowing users to easily check the car wash progress and system status at any time. Through an operational process based on real-time monitoring and dynamic adjustments, this implementation method significantly improves the safety and resource utilization of car wash operations, while also optimizing the user experience and equipment operational efficiency.

[0039] Implementation Method Two: In unmanned car wash systems, real-time performance is crucial for efficient operation. However, delays or errors may occur during data acquisition and transmission from the environmental monitoring system, potentially leading to a mismatch between the car wash operation and the actual environment. This implementation method introduces a delay compensation algorithm to dynamically correct the collected environmental data, ensuring the accuracy of car wash strategy adjustments.

[0040] The delay compensation algorithm works by combining historical data, real-time data, and predictive models. Environmental data acquisition modules may experience data lag due to sensor hardware limitations or communication network latency. For example, a temperature and humidity sensor might sample every second, while an air quality sensor updates every three seconds. In such cases, the data currently acquired by the system may lag behind the actual environmental conditions. To compensate for this lag, the delay compensation algorithm predicts the current environmental state based on historical data and environmental change trends. For instance, if humidity data is lagging by one second, the system will combine the humidity change trend over the past three seconds and predict the current humidity value through linear regression or time series analysis.

[0041] After the data is transmitted to the central processing unit, the system corrects the lagging data in real time and generates environmental state parameters from the corrected data. These parameters are then used for adaptive analysis and car wash strategy adjustments. For example, if the sensor reports a humidity of 60%, while the delay compensation algorithm predicts an actual humidity of 70%, the system will make judgments and adjustments based on the prediction. The corrected data not only improves the accuracy of the system's decisions but also avoids erroneous operations caused by data lag.

[0042] Furthermore, delay compensation algorithms can further improve prediction accuracy through cross-validation of multi-source data. For example, data from humidity sensors can be combined with particulate matter concentration data from air quality sensors for analysis, since high humidity is usually accompanied by a decrease in particulate matter concentration. Through multi-dimensional data fusion, delay compensation algorithms can generate more reliable environmental state parameters.

[0043] This implementation method solves the data lag problem in environmental monitoring systems, enabling unmanned car wash systems to make accurate and rapid decisions in complex environments. By combining delay compensation algorithms and real-time data processing technology, this approach significantly improves the accuracy of car wash operations and the intelligence level of the equipment.

[0044] Implementation Method 3: In the operation of an unmanned car wash system, efficient resource utilization is key to achieving both green environmental protection and economic benefits. This implementation method introduces machine learning algorithms to intelligently optimize resource allocation in the car wash process, thereby maximizing resource utilization and washing effectiveness.

[0045] The core of machine learning algorithms is to build optimization models through the accumulation and analysis of historical data. The system stores environmental data (such as temperature, humidity, and air quality), equipment data (such as water pump power and drying time), and resource usage records (such as water volume and detergent usage) for each car wash in a database. By extracting features from this data, the machine learning model can identify the relationship between resource usage efficiency and car wash results. For example, under low humidity and light pollution conditions, the model may find that reducing water usage has little impact on cleaning results, while under high humidity and heavy pollution conditions, it is necessary to appropriately increase water pressure and detergent usage to ensure cleaning quality.

[0046] Based on the model's predictive capabilities, the system dynamically adjusts resource allocation before each car wash. For example, in high-humidity environments, the system reduces water usage and increases drying time; in low-pollution environments, it reduces detergent usage and selects a low-pressure cleaning mode. Furthermore, the machine learning model can continuously optimize itself through real-time data updates. For instance, if a car wash shows unsatisfactory cleaning results, the system will readjust model parameters based on feedback data to improve the resource allocation strategy for the next wash.

[0047] This implementation also includes long-term strategy optimization. The system periodically performs batch analysis of historical data to uncover patterns in resource utilization efficiency. For example, the analysis results may show that a water-saving mode has the highest resource utilization rate under certain environmental conditions, and the system will add it to the strategy template for subsequent use. Through continuous learning and optimization, the system can minimize resource waste without affecting the quality of car washing.

[0048] This implementation method deeply integrates machine learning with unmanned car wash systems, achieving data-driven resource optimization and improving the system's economic and environmental performance. This not only enhances the market competitiveness of car wash machines but also provides important support for promoting the development of green and intelligent car wash technologies.

[0049] This invention, by introducing real-time monitoring, a delay compensation algorithm, and a dynamic adjustment mechanism, enables the unmanned car wash system to optimize the car wash process in real time according to complex environmental conditions. This intelligent operation ensures the accuracy of car wash decisions and avoids erroneous operations caused by delays or mismatches in environmental data. For example, under high humidity conditions, the system can automatically reduce the amount of water sprayed and extend the drying time, effectively preventing water stains and reducing resource waste. Simultaneously, the delay compensation algorithm further enhances the accuracy of car wash strategy adjustments by correcting for data lag, enabling the system to cope with rapidly changing environmental conditions. This effect not only improves car wash quality but also significantly enhances user experience and equipment operational stability, ensuring the system maintains high efficiency in various environments.

[0050] This invention utilizes machine learning algorithms to intelligently optimize resource usage, achieving a new balance in the allocation of detergent, water, and energy in the unmanned car wash system. Through continuous learning and optimization of historical data, the system can identify the optimal resource usage patterns under different environmental conditions, such as reducing detergent usage in lightly polluted environments and selecting a water-saving mode in high-humidity conditions. This data-driven optimization strategy not only reduces operating costs but also significantly reduces water waste and detergent emissions. Furthermore, the system analyzes the results after each wash operation, continuously improving resource usage strategies to ensure cleaning effectiveness while maximizing resource conservation. This approach aligns with current green and environmentally friendly principles, laying the foundation for the widespread adoption of intelligent unmanned car wash technology and promoting sustainable development in the industry.

[0051] The above formulas are all dimensionless numerical calculations, derived from software simulations using collected data to obtain the most recent real-world results. The preset parameters in the formulas can be set by those skilled in the art based on actual conditions. The above descriptions are merely illustrative of certain exemplary embodiments of the invention. Undoubtedly, those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the invention. Therefore, the above figures and descriptions are illustrative in nature and should not be construed as limiting the scope of the claims of this invention.

[0052] It should be noted that, in this document, the use of relational terms such as "first" and "second" is merely for distinguishing one entity or operation from another, and does not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0053] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0054] Those skilled in the art will appreciate that the units 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 and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0055] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0056] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0057] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0058] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0059] The foregoing has only described certain exemplary embodiments of the present invention by way of illustration. Undoubtedly, those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the foregoing drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. An environment-monitoring unmanned car washing machine, characterized in that: It includes environmental data collection module, environmental adaptability analysis module, car wash strategy adjustment module, delay compensation optimization module and intelligent resource optimization module: Environmental data acquisition module, which uses the environmental monitoring system to obtain environmental data in real time and generate environmental status parameters; The environmental adaptability analysis module compares the environmental state parameters with the preset environmental adaptability thresholds to generate a car wash adaptability analysis result; The car wash strategy adjustment module adjusts the car wash process according to the results of the car wash adaptability analysis, including the amount of water, detergent usage and the selection of the car wash mode; The delay compensation optimization module uses the delay response compensation algorithm to dynamically correct the delay and error of environmental data and generate real-time optimized car wash instructions; The intelligent resource optimization module applies machine learning algorithms to combine historical environmental data, car wash data and resource usage records to optimize resource allocation in car wash strategies and achieve efficient and environmentally friendly car wash operations.

2. The environment-monitoring unmanned car washing machine according to claim 1, characterized in that: The specific steps for using the environmental monitoring system to obtain environmental data in real time and generate environmental status parameters are as follows: Arrange and calibrate environmental monitoring equipment to ensure that the collected environmental data is accurate and reliable; Dynamically capture environmental data through high-frequency sampling of sensors; Use the communication module to transmit data and ensure data integrity and accuracy through analysis and verification; The collected data is calculated and normalized to generate quantitative environmental status indicators for subsequent decision-making.

3. The environment-monitoring unmanned car washing machine according to claim 1, characterized in that: The specific steps of comparing the environmental state parameters with the preset environmental adaptability threshold and generating the car wash adaptability analysis results are as follows: Verify and read the generated real-time environmental status parameters to ensure the real-time and validity of the data; Retrieve the preset adaptability threshold from the parameter database to provide a scientific basis for parameter comparison; The algorithm compares environmental parameters with the threshold range to evaluate the suitability of the car wash and generate an overall judgment result; Generate analysis results and output them synchronously to provide clear guidance for subsequent adjustments to car wash strategies.

4. The environment-monitoring unmanned car washing machine according to claim 1, characterized in that: The specific steps for adjusting the car wash process according to the results of the car wash adaptability analysis, including the selection of water volume, detergent usage and car wash mode, are as follows: Receive and interpret car wash suitability analysis results to determine environmental impacts on car wash processes; Generate dynamic car washing strategies that adapt to different environmental conditions based on analysis results and rule base; Optimize water volume, detergent ratio and car wash mode in real time according to the adjustment strategy, and execute operations accurately; By monitoring the adjustment effects and recording the data, we continuously optimize the car wash strategy to improve long-term operation efficiency and Effect.

5. The environment-monitoring unmanned car washing machine according to claim 1, characterized in that: The specific steps of using the delayed response compensation algorithm to dynamically correct the delay and error of environmental data and generate real-time optimized car wash instructions are as follows: First, the delay of the environmental data collected in real time is evaluated. The environmental data collected by the sensor has a time delay due to network transmission and device processing. In order to model the delay error, the historical data is compared with the current data, and the delay factor is calculated. The calculation expression is as follows: ， In the formula, is the current delay error factor, which is used to describe the degree of deviation between historical data and current data. is the sensor at time Environmental parameter values ​​collected at all times, is the detected delay time, is the data sampling window size; In order to obtain the delay error factor After that, the current sensor data is dynamically corrected based on The filtering algorithm, combined with the prediction model, corrects the current environmental parameters and delays the error factor , predict the future environmental parameters to compensate for the impact of delay, and the correction formula is as follows: ， In the formula, is the corrected environmental parameter value, which is used for subsequent decision making. is the currently collected environmental parameter value, is the predicted value of the environmental parameter, is the gain factor, and the calculation expression is as follows: ， In the formula, is the measurement error covariance; After completing the environmental data correction, the parameters will be corrected Input the optimization model to generate real-time car wash instructions. The instruction optimization formula is as follows: ， In the formula, It is a real-time optimized car wash instruction. is the car wash resource allocation coefficient, is the resource utilization rate, is the environmental adaptability adjustment coefficient, is the maximum tolerable delay error factor.

6. The environment-monitoring unmanned car washing machine according to claim 1, characterized in that: The specific steps for applying machine learning algorithms to combine historical environmental data, car wash data, and resource usage records to optimize resource allocation in car wash strategies and achieve efficient and environmentally friendly car wash operations are as follows: Key features are extracted from historical data, including environmental data, car wash parameters, and records of resource consumption and cleaning effects. The original data contains noise and missing values, so data cleaning technology is applied to process it. Through feature scaling and dimensionality reduction technology, the most relevant features for resource allocation optimization are extracted to construct a training data set. The formula is as follows: ， In the formula, is the extracted optimized feature vector, It's time The humidity value at the moment, It's time The air quality index at the moment, It's time Water quality parameters at all times, , , The time The amount of water, detergent and car wash mode at each moment. and The time Cleaning efficiency and resource costs at all times; Based on the extracted optimized feature vector The reinforcement learning algorithm is used to build a resource allocation optimization model. The goal of the resource allocation optimization model is to maximize the efficiency of car washing, minimize the cost of resource consumption, and ensure the minimum environmental impact. The model is trained through historical data to dynamically learn the optimal resource allocation strategy under different environmental conditions. The calculation expression is as follows: ， In the formula, Yes Status Take action long-term returns, is the discount factor, which weighs the future returns, is the next state, is the current state, respectively, by optimizing the eigenvector express, is the current resource allocation strategy, is the resource allocation strategy to be adopted in the future. It is an immediate return, which is calculated by combining cleaning efficiency and resource consumption. The calculation formula is as follows: ， In the formula, is the cleaning efficiency, It is resource consumption. It's the environmental impact. and These are adjustment parameters used to weigh cleaning efficiency. and resource consumption and environmental impact ; Through the trained reinforcement learning model, the best resource allocation strategy is predicted under the current environmental conditions. The feedback mechanism is used to monitor the actual execution effect in real time, compare the real-time data with the predicted results, and dynamically adjust the allocation strategy to cope with environmental changes. The formula is as follows: ， In the formula, is the optimized water usage value, is the optimized amount of detergent used, It is an optimized car wash mode. is the current state of the environment, is in state The allocation strategy The predicted return, is in a given state Next, find the function Maximum action .

Images