Intelligent self-service car washing system with photovoltaic power supply

Abstract

The invention discloses an intelligent self-service car washing system with photovoltaic power supply, and belongs to the technical field of distributed power dispatching control, the number of car washing people is predicted through an LSTM neural network, the busy degree proportion is calculated by dividing time periods, and continuous surplus and continuous loss time periods are distinguished in combination with photovoltaic power generation power prediction; then dynamically adjusting a power supply strategy based on a time period type, real-time electricity storage quantity, charging and discharging conversion efficiency and the like, specifically, in a surplus time period, preferentially supplying a photovoltaic direct supply car washing unit, intelligently distributing surplus electricity to energy storage or internet access, and avoiding overcharging of the stored energy; in the loss period, grading starting is carried out; energy storage power supply-energy storage and photovoltaic combined power supply-power grid power supply; and in a mode, setting a safety storage capacity lower limit and a recharging threshold to prevent the energy storage unit from overcharging and overdischarging. According to the invention, the direct supply proportion of photovoltaic power reaches 70-90%, and the carbon emission is reduced by more than 50%; the energy storage unit cooperates with the power grid for peak load shifting, extra income is created through a controllable power grid access strategy, and both economic and environmental benefits are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of distributed power dispatching and control, and specifically relates to a photovoltaic-powered intelligent self-service car washing system. Background Art

[0002] With the increasing popularity of new energy vehicles and stricter environmental protection policies, the high energy consumption of traditional car washes has become increasingly prominent. While photovoltaic-powered car wash systems are already in use, they still suffer from the following drawbacks: reliance on mains electricity, resulting in high energy costs; inability to operate in areas without grid coverage; use of traditional energy sources that do not meet environmental standards; and equipment operating time constraints. Car washes that combine new energy sources with batteries also face challenges: rigid power scheduling. Existing systems often employ fixed charging and discharging strategies (e.g., prioritizing photovoltaic power generation and switching to the grid when power is insufficient). These strategies fail to incorporate dynamic forecasting of real-time passenger flow and power generation, leading to frequent deep charging and discharging of energy storage units or surges in grid replenishment costs. Prediction accuracy is insufficient, and car wash demand fluctuates significantly. Traditional methods (such as historical averages) cannot accurately predict passenger flow by time period, easily leading to power redundancy or shortages, and a lack of response to abnormalities. Therefore, there is a need for an intelligent system that integrates a multi-dimensional prediction model with a dynamic power scheduling strategy to achieve efficient utilization of photovoltaic energy and safe equipment management. To achieve the above objectives, the present invention provides the following technical solutions. Summary of the Invention

[0003] The purpose of the present invention is to provide a photovoltaic-powered intelligent self-service car washing system to solve the problem of rigid power scheduling in the prior art, which leads to frequent deep charging and discharging of energy storage units or a surge in grid power replenishment costs.

[0004] The purpose of the present invention can be achieved through the following technical solutions: A photovoltaic-powered intelligent self-service car washing system, comprising: Photovoltaic power generation units, which convert sunlight into electricity; An energy storage unit, used to store the electricity input by the photovoltaic power generation unit; A sensing unit, used to detect the real-time power generation of the photovoltaic power generation unit and the real-time storage capacity of the energy storage unit; A car washing unit, used for cleaning the vehicle shell; Intelligent control unit for adjusting power supply strategy; The method for adjusting the power supply strategy comprises the following steps: Step 1: Predict the number of car washes. Divide the working hours of a car wash shop into k time periods, and then predict the number of car washes in each time period based on the predicted number of car washes in a day. Step 2, calculate the predicted electricity consumption of bicycle washing; Step 3: Predict the power generation of the photovoltaic power generation unit. Determine the continuous surplus period and continuous loss period based on the predicted power generation and the predicted power consumption in each time period. When entering a continuous period, obtain the actual storage capacity Ws of the energy storage unit at that time. For consecutive profit periods, first calculate the profit difference W11=W1-W2; For consecutive losing periods, first calculate the loss difference W22=W2-W1; Where W1 is the power generation in a continuous period, and W2 is the power consumption in a continuous period; During the continuous surplus period, if the real-time power generation of the photovoltaic power generation unit is sufficient to drive the car wash unit, the car wash unit will be powered by the photovoltaic power generation unit. At the same time, if W11×β>Wmax-Ws, the power generated by the photovoltaic power generation unit other than that for the car wash unit will be transmitted to the energy storage unit. The energy storage unit will be stably connected to the grid with a power of [(W11×β)-(Wmax-Ws)] / T. If W11×β≤Wmax-Ws, all the power generated by the photovoltaic power generation unit other than that for the car wash unit is transmitted to the energy storage unit, and the power of the energy storage unit is not connected to the grid; Where β is the charging conversion efficiency of the energy storage unit; Wmin is the lower limit of the safe storage capacity of the energy storage unit, and Wmax is the full-load storage capacity of the energy storage unit.

[0005] As a further solution of the present invention, a method for predicting the number of car washers in each time period based on the predicted value of the number of car washers in a day is as follows: Mark the time period as ti, where i ranges from 1 to k; Get the ratio of the number of car washes in each time period to the total number of car washes on that day, and thus get the busyness ratio fi corresponding to time period ti; Obtain all busyness percentage values ​​corresponding to the same time period in the past, and after cleaning these busyness percentage values, calculate the average of the remaining busyness percentage values, and use this average as the representative value of the busyness percentage of the corresponding time period in the past; Calculate the representative value of the busyness ratio of each time period in the past period in turn; Then, the calculated busyness ratio values ​​of each time period are normalized so that the sum of the busyness ratio values ​​of each time period is 1, and the normalized busyness ratio values ​​are used as the final predicted ratio values ​​of each time period.

[0006] As a further solution of the present invention, the method for calculating the predicted power consumption of bicycle washing is: The power consumption of each vehicle is recorded during washing to obtain a set of power consumption data. After the above power consumption data is cleaned, the average value of the remaining data is calculated as the predicted power consumption of the single vehicle washing.

[0007] As a further solution of the present invention, the method for determining the continuous profit period and the continuous loss period is: Calculating the predicted power generation of the photovoltaic power generation unit in each time period based on the predicted power generation of the photovoltaic power generation unit in each time period; The predicted power consumption in each time period is obtained based on the predicted number of car washers in each time period and the predicted power consumption of single car washing; When the corresponding predicted power generation is greater than the predicted power consumption, the corresponding time period is recorded as a surplus period; When the corresponding predicted electricity consumption is greater than the predicted power generation, the corresponding time period is recorded as a loss period; When the corresponding predicted power consumption is equal to the predicted power generation, the corresponding time period is recorded as the balance period; Record consecutive periods of profits as consecutive periods of profits; Record consecutive losing periods as consecutive losing periods; For a balance period, it is included in the previous continuous profit period or continuous loss period that is continuous with it in time series.

[0008] As a further solution of the present invention, in Step 3, if the real-time power generation of the photovoltaic power generation unit cannot drive the car washing unit to work directly, the car washing unit is powered by the energy storage unit. At the same time, if W1×β-W2>Wmax-Ws, the energy storage unit is stably connected to the grid with a power of [(W1×β-W2)-(Wmax-Ws)] / T; If W1×β-W2≤Wmax-Ws, all power generated by the photovoltaic power generation unit other than that for the car wash unit will be transmitted to the energy storage unit, and the power of the energy storage unit will not be connected to the grid.

[0009] As a further solution of the present invention, in Step 3, for continuous loss periods, the energy storage unit is used to supply power, or the energy storage unit and the photovoltaic power generation unit are used together to supply power, until the storage capacity of the energy storage unit is less than or equal to Wmin, and then the grid is used to supply power until the next continuous period begins or the storage capacity of the energy storage unit reaches a preset value Wm, where Wm is a value between Wmin and Wmax.

[0010] As a further solution of the present invention, when entering a continuous time period, the size relationship between W11, W22 and the preset difference Wy is first determined. When W11, W22 are not greater than the preset difference Wy, the power supply strategy of the previous continuous time period is maintained. Conversely, if W11, W22 are greater than the preset difference Wy, the power supply strategy is adjusted within the corresponding continuous time period.

[0011] Beneficial effects of the present invention: The present invention uses an LSTM neural network to predict the number of car wash users, divides time periods into time periods to calculate the proportion of busyness, and combines it with photovoltaic power generation power prediction to distinguish between continuous surplus and continuous loss periods. Then, the power supply strategy is dynamically adjusted based on the time period type, real-time storage capacity, and charge-discharge conversion efficiency. Specifically, during surplus periods: photovoltaic direct supply to the car wash unit is prioritized, and the remaining power is intelligently allocated to energy storage or to the grid to avoid overcharging of energy storage. During loss periods: the "energy storage power supply → energy storage + photovoltaic combined power supply → grid power supply" mode is activated in a hierarchical manner, and the lower limit of safe storage capacity and the recharge threshold are set to prevent overcharging and over-discharging of energy storage units.

[0012] This method divides the entire day into k time periods and significantly improves passenger flow forecast accuracy by cleaning historical data (generating predicted percentage values). Based on a statistical model of single-vehicle power consumption, it accurately matches time period power demand with the photovoltaic output curve. This effectively reduces the error rate in matching power supply and demand during car wash service periods.

[0013] The direct supply ratio of photovoltaic power in this invention reaches 70%-90%, and carbon emissions are reduced by more than 50%; the energy storage unit cooperates with the power grid to reduce peak loads and fill valleys, creating additional revenue through controllable power access strategies, and improving both economic and environmental benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The present invention will be further described below with reference to the accompanying drawings.

[0015] Figure 1 This is a schematic diagram of the framework structure of a photovoltaic-powered intelligent self-service car washing system of the present invention. DETAILED DESCRIPTION

[0016] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0017] Example 1 A photovoltaic powered intelligent self-service car washing system, such as Figure 1 Shown, including: Photovoltaic power generation unit, used to convert sunlight into electrical energy, which is then connected to the internet or transmitted to an energy storage unit for storage or directly used to power the car wash unit; Specifically, two or more of the actions can be performed simultaneously, such as powering the car wash unit and storing part of the power in the energy storage unit at the same time.

[0018] An energy storage unit, used to store the electricity input by the photovoltaic power generation unit; It is also used to power the car wash unit; A sensing unit, used to detect the real-time power generation of the photovoltaic power generation unit and the real-time storage capacity of the energy storage unit; The car washing unit is powered by the energy storage unit or the grid to clean the vehicle shell. It can be equipped with high-pressure water circulation and hot air drying equipment for vehicle cleaning; Intelligent control unit, used to adjust the power supply strategy.

[0019] Example 2 The method for adjusting the power supply strategy by the intelligent control unit comprises the following steps: Step 1, predict the number of car washers; Then, the number of car washers in each period is predicted based on the predicted value of the number of car washers in a day; Specifically: First, the number of car washes is predicted through the LSTM neural network; The LSTM neural network is a common method for predicting passenger flow, so the present invention does not make any specific limitations on it. Then, the working hours of the car wash shop are evenly divided into k time periods. The length of a time period can be 0.5 hours or 1 hour, etc. The time periods are marked as ti, where i ranges from 1 to k. When marking, they are marked in chronological order. Get the ratio of the number of car washes in each time period to the total number of car washes on that day, and thus obtain the busyness ratio fi corresponding to time period ti; (Note that when counting the number of car washes here, the number of people who started washing the car can be counted as the number of people who completed the car wash.) Obtain all busyness percentage values ​​corresponding to the same time period in the past, and after cleaning these busyness percentage values, calculate the average of the remaining busyness percentage values, and use this average as the representative value of the busyness percentage of the corresponding time period in the past; Calculate the representative value of the busyness ratio corresponding to each time period in the past period in turn.

[0020] Specifically, the Z-score or IQR statistical method can be used to clean the above busyness ratio data; Then, the calculated busyness ratio values ​​of each time period are normalized so that the sum of the busyness ratio values ​​of each time period is 1, and the normalized busyness ratio values ​​are used as the final predicted ratio values ​​of each time period.

[0021] Step 2, calculate the predicted electricity consumption of bicycle washing; Specifically, the power consumption of each vehicle wash is recorded to obtain a set of power consumption data. After cleaning the power consumption data using Z-score or IQR statistical methods, the data with obvious excessive or insufficient values ​​are excluded, and the average of the remaining data is calculated as the predicted power consumption for each vehicle wash. Step 3, predict the power generation of the photovoltaic power generation unit; Obtain the relationship between the power generation of the photovoltaic power generation unit and time in the future; Likewise, the method for predicting photovoltaic power generation is a mature and commonly used method in this field, and the present invention does not make any specific limitation thereto.

[0022] Calculating the predicted power generation of the photovoltaic power generation unit in each time period based on the predicted power generation of the photovoltaic power generation unit in each time period; The predicted power consumption in each time period is obtained based on the predicted number of car washers in each time period and the predicted power consumption of single car washing; When the corresponding predicted power generation is greater than the predicted power consumption, the corresponding time period is recorded as a surplus period; When the corresponding predicted electricity consumption is greater than the predicted power generation, the corresponding time period is recorded as a loss period; When the corresponding predicted power consumption is equal to the predicted power generation, the corresponding time period is recorded as the balance period; Record consecutive periods of profits as consecutive periods of profits; Record consecutive losing periods as consecutive losing periods; For a balance period, it is included in the previous continuous profit period or continuous loss period that is continuous with it in time series; Set a safe storage capacity lower limit Wmin for the energy storage unit, and record the full load storage capacity of the energy storage unit as Wmax; When entering a continuous period (continuous surplus period or continuous loss period), obtain the actual storage capacity Ws of the energy storage unit at this time; For consecutive profit periods, first calculate the profit difference W11=W1-W2; For consecutive losing periods, first calculate the loss difference W22=W2-W1; Determine the relationship between W11, W22 and the preset difference Wy. If W11, W22 are not greater than the preset difference Wy, maintain the power supply strategy of the previous continuous period. Conversely, if W11, W22 are greater than the preset difference Wy, adjust the power supply strategy within the corresponding continuous period. Where W1 is the power generation in a continuous period, and W2 is the power consumption in a continuous period; The specific methods for adjusting the power supply strategy are: During the continuous surplus period, if the real-time power generation of the photovoltaic power generation unit can drive the car wash unit (the power generation of the photovoltaic power generation unit is large enough), the car wash unit will be powered by the photovoltaic power generation unit. At the same time, if W11×β>Wmax-Ws, the power generated by the photovoltaic power generation unit other than the power for the car wash unit will be transmitted to the energy storage unit. The energy storage unit will be stably connected to the grid with a power of [(W11×β)-(Wmax-Ws)] / T. If W11×β≤Wmax-Ws, all the power generated by the photovoltaic power generation unit other than that for the car wash unit is transmitted to the energy storage unit, and the power of the energy storage unit is not connected to the grid; Where β is the charging conversion efficiency of the energy storage unit; If the real-time power generation of the photovoltaic power generation unit is unable to drive the car wash unit directly, the car wash unit will be powered by the energy storage unit. At the same time, if W1×β-W2>Wmax-Ws, the energy storage unit will be stably connected to the grid with a power of [(W1×β-W2)-(Wmax-Ws)] / T; If W1×β-W2≤Wmax-Ws, all power generated by the photovoltaic power generation unit other than that for the car wash unit will be transmitted to the energy storage unit, and the power of the energy storage unit will not be connected to the grid.

[0023] For continuous loss periods, the energy storage unit is used to supply power, or the energy storage unit and the photovoltaic power generation unit are used together to supply power (the photovoltaic power generation unit directly supplies power or the power is first transmitted to the energy storage unit and then supplied through the energy storage unit) until the storage capacity of the energy storage unit is less than or equal to Wmin, and then the grid is used to supply power until the next continuous period begins or the storage capacity of the energy storage unit reaches the preset value Wm, where Wm is a value between Wmin and Wmax, such as Wm=(Wmin+Wmax) / 2.

[0024] Example 3 In this embodiment, the power consumption of each car after washing is also monitored. When the actual power consumption g1 of a single car satisfies (g1-predicted power consumption of single car washing) / predicted power consumption of single car washing is greater than a preset ratio value, it is considered that the actual power consumption g1 of the corresponding vehicle washing is abnormal; When abnormal actual power consumption g1 is detected, an alarm message is issued and the staff will check it.

[0025] The above contents are merely examples and explanations of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in similar ways. As long as they do not deviate from the invention or exceed the scope defined by the claims, they should all fall within the scope of protection of the present invention.

Claims

1. A photovoltaic powered intelligent self-service car washing system, characterized in that: include: Photovoltaic power generation units, which convert sunlight into electricity; An energy storage unit, used to store the electricity input by the photovoltaic power generation unit; A sensing unit, used to detect the real-time power generation of the photovoltaic power generation unit and the real-time storage capacity of the energy storage unit; A car washing unit, used for cleaning the vehicle shell; Intelligent control unit for adjusting power supply strategy; The method for adjusting the power supply strategy comprises the following steps: Step 1: Predict the number of car washes. Divide the working hours of a car wash shop into k time periods, and then predict the number of car washes in each time period based on the predicted number of car washes in a day. Step 2, calculate the predicted electricity consumption of bicycle washing; Step 3: Predict the power generation of the photovoltaic power generation unit. Determine the continuous surplus period and continuous loss period based on the predicted power generation and the predicted power consumption in each time period. When entering a continuous period, obtain the actual storage capacity Ws of the energy storage unit at that time. For consecutive profit periods, first calculate the profit difference W11=W1-W2; For consecutive losing periods, first calculate the loss difference W22=W2-W1; Where W1 is the power generation in a continuous period, and W2 is the power consumption in a continuous period; During the continuous surplus period, if the real-time power generation of the photovoltaic power generation unit is sufficient to drive the car wash unit, the car wash unit will be powered by the photovoltaic power generation unit. At the same time, if W11×β>Wmax-Ws, the power generated by the photovoltaic power generation unit other than that for the car wash unit will be transmitted to the energy storage unit. The energy storage unit will be stably connected to the grid with a power of [(W11×β)-(Wmax-Ws)] / T. If W11×β≤Wmax-Ws, all the power generated by the photovoltaic power generation unit other than that for the car wash unit is transmitted to the energy storage unit, and the power of the energy storage unit is not connected to the grid; Where β is the charging conversion efficiency of the energy storage unit; Wmin is the lower limit of the safe storage capacity of the energy storage unit, and Wmax is the full-load storage capacity of the energy storage unit.

2. The photovoltaic-powered intelligent self-service car washing system according to claim 1, characterized in that: The method for predicting the number of car washers in each period based on the predicted value of the number of car washers in a day is: Mark the time period as ti, where i ranges from 1 to k; Get the ratio of the number of car washes in each time period to the total number of car washes on that day, and thus get the busyness ratio fi corresponding to time period ti; Obtain all busyness percentage values ​​corresponding to the same time period in the past, and after cleaning these busyness percentage values, calculate the average of the remaining busyness percentage values, and use this average as the representative value of the busyness percentage of the corresponding time period in the past; Calculate the representative value of the busyness ratio of each time period in the past period in turn; Then, the calculated busyness ratio values ​​of each time period are normalized so that the sum of the busyness ratio values ​​of each time period is 1, and the normalized busyness ratio values ​​are used as the final predicted ratio values ​​of each time period.

3. The photovoltaic-powered intelligent self-service car washing system according to claim 1, characterized in that: The method for calculating the predicted electricity consumption for bicycle washing is: The power consumption of each vehicle is recorded during washing to obtain a set of power consumption data. After the above power consumption data is cleaned, the average value of the remaining data is calculated as the predicted power consumption of the single vehicle washing.

4. The photovoltaic-powered intelligent self-service car washing system according to claim 1, characterized in that: The method for determining consecutive profit periods and consecutive loss periods is: Calculating the predicted power generation of the photovoltaic power generation unit in each time period based on the predicted power generation of the photovoltaic power generation unit in each time period; The predicted power consumption in each time period is obtained based on the predicted number of car washers in each time period and the predicted power consumption of single car washing; When the corresponding predicted power generation is greater than the predicted power consumption, the corresponding time period is recorded as a surplus period; When the corresponding predicted electricity consumption is greater than the predicted power generation, the corresponding time period is recorded as a loss period; When the corresponding predicted power consumption is equal to the predicted power generation, the corresponding time period is recorded as the balance period; Record consecutive periods of profits as consecutive periods of profits; Record consecutive losing periods as consecutive losing periods; For a balance period, it is included in the previous continuous profit period or continuous loss period that is continuous with it in time series.

5. The photovoltaic-powered intelligent self-service car washing system according to claim 1, characterized in that: In Step 3, if the real-time power generation of the photovoltaic power generation unit cannot drive the car wash unit to work directly, the car wash unit is powered by the energy storage unit. At the same time, if W1×β-W2>Wmax-Ws, the energy storage unit is connected to the grid with a power of [(W1×β-W2)-(Wmax-Ws)] / T. If W1×β-W2≤Wmax-Ws, all power generated by the photovoltaic power generation unit other than that for the car wash unit will be transmitted to the energy storage unit, and the power of the energy storage unit will not be connected to the grid.

6. The photovoltaic-powered intelligent self-service car washing system according to claim 1, characterized in that: In Step 3, for consecutive loss periods, the energy storage unit is used for power supply, or the energy storage unit and the photovoltaic power generation unit are used together for power supply until the storage capacity of the energy storage unit is less than or equal to Wmin, and then the grid is used for power supply until the next consecutive period begins or the storage capacity of the energy storage unit reaches the preset value Wm, where Wm is a value between Wmin and Wmax.

7. The photovoltaic-powered intelligent self-service car washing system according to claim 1, characterized in that: When entering a continuous period, the size relationship between W11, W22 and the preset difference Wy is first determined. When W11, W22 are not greater than the preset difference Wy, the power supply strategy of the previous continuous period is maintained. Conversely, if W11, W22 are greater than the preset difference Wy, the power supply strategy is adjusted within the corresponding continuous period.

Images