Gas monitoring system, dynamic scheduling method and equipment for three-dimensional parking building
By using a dynamic scheduling method of gas sensors, track power supplies, and vertical lifting mechanisms in a multi-story parking garage, combined with clustering and neural network models, the high cost of gas leakage monitoring for fuel cell vehicles in multi-story parking garages was solved, achieving efficient and low-cost gas detection and safety monitoring.
Patent Information
- Application Number
- CN202511083454.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-04
- Publication Date
- 2025-09-16
AI Technical Summary
There is an urgent need to monitor gas leakage from fuel cell vehicles in multi-story parking structures. Existing monitoring devices are expensive and difficult to effectively cover all potential danger areas. There is also a lack of efficient gas sensor layout and scheduling methods.
By using multiple gas sensors, track power supplies and vertical lifting mechanisms, combined with clustering algorithms and neural network models, dynamic scheduling of gas sensors is achieved. Partitions are divided according to vehicle parking data, sensor deployment and scheduling are optimized, the number of sensors is reduced and detection accuracy is improved.
While ensuring the accuracy of gas detection, the number of gas sensors is reduced, the investment cost is lowered, and the space utilization and safety of the multi-story parking lot are improved. The sensors can self-update to adapt to scene changes and quickly respond to gas leaks.
Smart Images
Figure CN120652061A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of gas leakage monitoring, and in particular to a gas monitoring system, dynamic scheduling method and equipment for a multi-story parking building. Background Art
[0002] To reduce automobile emissions, China has been supporting and investing in new energy vehicles in recent years, with an increasing number of these vehicles replacing existing fuel-powered vehicles. However, the electricity generation process used by lithium-ion battery vehicles still produces high levels of pollution, while fuel cells offer lower emissions. Consequently, there will be an increasing number of fuel cell vehicles on the road. However, because gas fuel is highly flammable and has a low flash point, monitoring gas leaks in fuel cell vehicles is a crucial safety measure.
[0003] Chinese cities have a huge number of cars. Although more than one million parking lots have been built in the country, there is still a shortage of parking spaces. The emergence of multi-story parking garages has become an excellent solution to this problem, maximizing utilization within the limited space in the city and accommodating more new energy vehicles with a smaller footprint than traditional parking lots.
[0004] However, it is undeniable that multi-story parking garages have a higher risk factor when encountering the risk of fire. The direction of fire spread will follow the vertical direction of the multi-story parking garage, making the speed and intensity of the combustion spread higher. In addition, multi-story parking garages are closed, and the parking and removal of new energy vehicles are controlled by programs inside. There is no human participation, and it cannot rely on manpower for monitoring. Therefore, more monitoring devices are needed to ensure that dangerous locations are covered to avoid accidents. However, more monitoring devices will inevitably lead to a significant increase in investment costs. Previous research objects were single-story flat parking lots, where there is no stacking of new energy vehicles, and personnel can patrol and monitor. Therefore, there is an urgent need for a gas leakage monitoring method for multi-story parking garages to reduce the initial investment in gas sensors and save costs. Summary of the Invention
[0005] The purpose of this application is to provide a gas monitoring system, dynamic scheduling method and equipment for a multi-story parking building, thereby reducing the investment cost of gas sensors.
[0006] To achieve the above objectives, this application provides the following solutions: In a first aspect, the present application provides a gas monitoring system for a multi-story parking structure, the gas monitoring system for the multi-story parking structure comprising: a plurality of gas sensors, a plurality of positioning modules, a plurality of track power supplies, a plurality of vertical lifting mechanisms, and a central control computer disposed within the multi-story parking structure; the multi-story parking structure comprises multiple parking floors, each parking floor being provided with a plurality of track power supplies, and two track power supplies located on two adjacent parking floors being connected via a vertical lifting mechanism; A positioning module is fixedly mounted on a gas sensor, each gas sensor is slidably connected to the track power supply and the vertical lifting mechanism, and each gas sensor and each positioning module is connected to the central control computer respectively; The gas sensor is used to collect real-time data on gas concentrations leaked from new energy vehicles parked at different locations within the multi-story parking structure; the gases include hydrogen, carbon monoxide, carbon dioxide, nitrogen oxides, methane, ethane, and ethylene; The positioning module is used to collect displacement information of the gas sensor; The vertical lifting mechanism is used to realize the inter-layer movement of the gas sensor between different parking floors; The track power supply is used to supply power to each gas sensor; The central control computer is used for: determining the position information of the gas sensor according to the position of the track power supply and the displacement information; Generate a corresponding scheduling plan based on the gas concentration data of leakage from parked new energy vehicles at different locations and the location information; According to the scheduling plan, each gas sensor realizes movement inside the multi-story parking building through the track power supply and vertical lifting mechanism; the movement includes movement within the floor and movement between floors; The scheduling scheme specifically includes: Obtain parking data of new energy vehicles in a multi-story parking structure; the parking data of new energy vehicles includes: parking location of the new energy vehicle, whether it is a fuel cell vehicle, and the number of vehicles parked; Using a clustering algorithm, based on the parking data of new energy vehicles, all parking floors in the multi-story parking structure are divided into multiple zones, a first deployment position and a predicted gas concentration value of each gas sensor in each zone are determined, and each gas sensor is deployed at the corresponding first deployment position; Determine the risk level of each zone based on the predicted gas concentration value in each zone; the risk level is: high risk, medium risk, low risk or no risk; A gas sensor scheduling model is used to determine the corresponding gas sensor scheduling parameter prediction value based on the coordinate range and risk level of each partition, as well as the first deployment position, gas concentration detection value, and power state of each gas sensor in each partition. The scheduling parameter prediction value includes: intra-layer movement direction, inter-layer movement direction, opening and closing state, and movement speed. The gas sensor scheduling model is obtained by training a neural network model using a training set; the training set includes: the coordinate range and risk level of multiple sample partitions, the first deployment position, gas concentration detection value, and power state of each gas sensor in each sample partition, and the scheduling parameter prediction value of each gas sensor in the corresponding sample partition. Based on the predicted value of the scheduling parameter of each gas sensor in each zone, move each gas sensor in each zone from the corresponding first deployment position to the corresponding zone according to the first preset scheduling plan, and determine the second deployment position of each gas sensor; The scope of gas leakage is determined based on the position of the gas sensor that detects gas leakage from the parked new energy vehicle.
[0007] Optionally, the gas monitoring system for a multi-story parking structure further comprises: a plurality of bases; each base is connected to the central control computer; A gas sensor is fixedly mounted on a base, and each gas sensor is slidably connected to a track power supply and a vertical lifting mechanism through a corresponding base; According to the scheduling scheme, each base drives the corresponding gas sensor to slide on the track power supply and the vertical lifting mechanism to achieve the movement of the corresponding gas sensor.
[0008] Optionally, the positioning module includes: a photoelectric encoder and a microcontroller; The photoelectric encoder and the microcontroller are both mounted on the base, and the photoelectric encoder and the microcontroller are used to jointly determine the displacement information of each gas sensor.
[0009] In a second aspect, the present application provides a dynamic scheduling method for a gas monitoring system for a multi-story parking structure. The dynamic scheduling method for a gas monitoring system for a multi-story parking structure is based on the gas monitoring system for a multi-story parking structure, and the dynamic scheduling method for a gas monitoring system for a multi-story parking structure includes: Obtain parking data of new energy vehicles in a multi-story parking structure; the parking data of new energy vehicles includes: parking location of the new energy vehicle, whether it is a fuel cell vehicle, and the number of vehicles parked; Using a clustering algorithm, based on the parking data of new energy vehicles, all parking floors in the multi-story parking structure are divided into multiple zones, a first deployment position and a predicted gas concentration value of each gas sensor in each zone are determined, and each gas sensor is deployed at the corresponding first deployment position; Determine the risk level for each zone based on the predicted gas concentration within each zone; the risk level is high risk, medium risk, low risk, or no risk; A gas sensor scheduling model is used to determine the corresponding gas sensor scheduling parameter prediction value based on the coordinate range and risk level of each partition, as well as the first deployment position, gas concentration detection value, and power state of each gas sensor in each partition. The scheduling parameter prediction value includes: intra-layer movement direction, inter-layer movement direction, opening and closing state, and movement speed. The gas sensor scheduling model is obtained by training a neural network model using a training set; the training set includes: the coordinate range and risk level of multiple sample partitions, the first deployment position, gas concentration detection value, and power state of each gas sensor in each sample partition, and the scheduling parameter prediction value of each gas sensor in the corresponding sample partition. Based on the predicted value of the scheduling parameter of each gas sensor in each zone, move each gas sensor in each zone from the corresponding first deployment position to the corresponding zone according to the first preset scheduling plan, and determine the second deployment position of each gas sensor; The scope of gas leakage is determined based on the position of the gas sensor that detects gas leakage from the parked new energy vehicle.
[0010] Optionally, a clustering algorithm is used to divide all parking floors in the multi-story parking structure into multiple zones based on parking data of new energy vehicles, and the first deployment position of each gas sensor in each zone is determined, specifically including: Using a K-means clustering algorithm, all parking floors in the multi-story parking structure are divided into multiple zones based on the parking location, parking duration, and parking quantity of each fuel cell vehicle. The cluster center corresponding to each partition is used as the first deployment location of the gas sensor in each partition.
[0011] Optionally, the calculation formula for the predicted gas concentration value in each zone is: ; in, is the predicted value of gas concentration; (x, y, z) is the coordinate of the position to be predicted in the partition; n is the number of fuel cell vehicles in the corresponding partition; is a function used to introduce environmental factors; is the diffusion coefficient of any type of gas, For time; ( x i , y i , z i ) is the i The coordinates of a potential gas leak point.
[0012] Optionally, the training process of the gas sensor scheduling model specifically includes: Get the training set; The coordinate ranges and risk levels of multiple sample partitions, the first deployment position, gas concentration detection value, and power status of each gas sensor in each sample partition, and the scheduling parameter prediction value of each gas sensor in the corresponding sample partition are input into the neural network model, and the scheduling parameter prediction value of the gas sensor is output; A loss function is constructed based on the predicted value of the scheduling parameter of the gas sensor and the predicted value of the scheduling parameter of each gas sensor in the sample partition, and the parameters of the neural network model are iteratively optimized according to the loss function until the loss function reaches a minimum value or the iterative optimization round reaches a maximum value. The iterative optimization is stopped to obtain the gas sensor scheduling model.
[0013] Optionally, the first preset scheduling scheme is: dispatching a first set number of gas sensors to a partition with a high risk level, dispatching a second set number of gas sensors to a partition with a medium risk level, dispatching a third set number of gas sensors to a partition with a low risk level, and not setting gas sensors in a partition with a no risk level; wherein, the first set number is greater than the second set number, and the second set number is greater than the third set number.
[0014] Optionally, determining the gas leakage range based on the position of the gas sensor that detects gas leakage from the parked new energy vehicle specifically includes: The gas sensor that detects gas leakage from parked new energy vehicles is used as the central gas sensor; Based on the central gas sensor, two edge gas sensors are determined; the two edge gas sensors are gas sensors located on both sides of the central gas sensor on the same track power supply as the central gas sensor; Controlling each of the edge gas sensors to move in a direction away from the central gas sensor within a preset range, and obtaining a gas concentration detection value of each of the edge gas sensors in real time during the movement; The gas leakage range is determined based on the position where the gas concentration detection value corresponding to each edge gas sensor is the minimum value.
[0015] In a third aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the above-described dynamic scheduling methods for a gas monitoring system for a multi-story parking garage.
[0016] According to the specific embodiments provided in this application, this application has the following technical effects: The present application discloses a gas monitoring system, dynamic scheduling method and equipment for a multi-story parking garage. By using a plurality of gas sensors, a plurality of track power supplies and a plurality of vertical lifting mechanisms in coordination, and adopting intra-floor and inter-floor scheduling schemes of gas sensors, the space utilization rate of the multi-story parking garage is fully improved, the number of gas sensors is reduced while ensuring the accuracy of gas detection, and the investment cost is reduced. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0018] Figure 1 A schematic structural diagram of a gas monitoring system for a multi-story parking structure provided in one embodiment of the present application.
[0019] Figure 2 A flow chart of a dynamic scheduling method for a gas monitoring system in a multi-story parking garage provided in one embodiment of the present application.
[0020] Figure 3 A schematic diagram of the structure of a computer device provided in one embodiment of the present application.
[0021] Reference numerals: Gas sensor-1, track power supply-2, vertical lifting mechanism-3. DETAILED DESCRIPTION
[0022] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.
[0023] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.
[0024] In an exemplary embodiment, Figure 1 As shown, a gas monitoring system for a multi-story parking building is provided, comprising: a plurality of gas sensors 1, a plurality of positioning modules, a plurality of track power supplies 2, a plurality of vertical lifting mechanisms 3 and a central control computer arranged in the multi-story parking building; the multi-story parking building comprises multiple parking floors, each parking floor is provided with a plurality of track power supplies 2, two track power supplies 2 located between two adjacent parking floors are connected by a vertical lifting mechanism 3, and the track power supplies 2 are connected to the gas sensors 1.
[0025] A positioning module is fixed to a gas sensor 1. Each gas sensor 1 is slidably connected to a track power supply 2 and a vertical lift mechanism 3. Each gas sensor 1 and positioning module is connected to a central control computer. The gas sensors 1 are wireless, and communication between the wireless gas sensors 1 and the central control computer is via a local wireless network.
[0026] The gas sensor 1 is used to collect real-time gas concentration data from leaks from new energy vehicles parked at various locations within a parking structure. New energy vehicles include fuel cell vehicles and lithium battery vehicles. The collected leaked gases are hazardous gases, including hydrogen (H2), carbon monoxide (CO), carbon dioxide (CO2), nitrogen oxides (NOx), methane (CH4), ethane (C2H6), and ethylene (C2H4). Other hazardous gases are also possible and are not limited here.
[0027] The positioning module is used to collect displacement information of the gas sensor 1 .
[0028] The vertical lifting mechanism 3 is used to achieve inter-floor movement of the gas sensor 1 between different parking floors. The vertical lifting mechanism 3 is embedded in the column and connected to the through-type track using the track power supply 2. The gas sensor 1 can enter the rack slot and be transported between floors with the mechanism.
[0029] The track power supply 2 is used to power each gas sensor 1. A power supply device is installed at the bottom of each gas sensor 1, allowing it to power any position on the track. The track power supply 2 is embedded in the floor slabs of the multi-story parking structure. A through-type track power supply 2 is positioned perpendicular to the rear of each floor's upper slab, slightly behind the direction in which new energy vehicles are placed. Racks are installed on either side of the track power supply 2, and two gears are connected to the racks at the base of each gas sensor 1. These gears are driven by motors, all of which are controlled by a central control computer.
[0030] The central control computer is used for: The position information of the gas sensor 1 is determined according to the position of the track power supply 2 and the displacement information.
[0031] A corresponding scheduling plan is generated according to the gas concentration data leaked by parked new energy vehicles at different locations and the location information.
[0032] According to the scheduling plan, each gas sensor 1 is moved inside the multi-story parking building through the track power supply 2 and the vertical lifting mechanism 3; the movement includes intra-layer movement and inter-layer movement.
[0033] The scheduling scheme specifically includes the following steps.
[0034] Step S1, obtaining parking data of new energy vehicles in a multi-story parking garage; the parking data of new energy vehicles includes: parking location of the new energy vehicle, whether it is a fuel cell vehicle, and the number of vehicles parked.
[0035] In step S2, a clustering algorithm is used to divide all parking floors in the multi-story parking building into zones based on the parking data of new energy vehicles to obtain multiple zones, and the first deployment position and gas concentration prediction value of each gas sensor in each zone are determined, and each gas sensor is deployed at the corresponding first deployment position.
[0036] Step S3: determining the risk level of each partition based on the predicted gas concentration value in each partition; the risk level is: high risk, medium risk, low risk or no risk.
[0037] Step S4, using a gas sensor scheduling model, based on the coordinate range and risk level of each partition and the first deployment position, gas concentration detection value and power status of each gas sensor in each partition, determines the scheduling parameter prediction value of the corresponding gas sensor; the scheduling parameter prediction value includes: the movement direction within the layer, the movement direction between layers, the opening and closing state and the moving speed; the gas sensor scheduling model is obtained by training the neural network model using a training set; the training set includes: the coordinate range and risk level of multiple sample partitions, the first deployment position, gas concentration detection value and power status of each gas sensor in each sample partition and the scheduling parameter prediction value of each gas sensor in the corresponding sample partition.
[0038] Step S5, based on the predicted value of the scheduling parameter of each gas sensor in each partition, each gas sensor in each partition is moved from the corresponding first deployment position to the corresponding partition according to the first preset scheduling scheme, and the second deployment position of each gas sensor is determined.
[0039] Step S6: determining the gas leakage range according to the position of the gas sensor that detects gas leakage from the parked new energy vehicle.
[0040] As an optional implementation, the gas monitoring system for a multi-story parking structure further includes: a plurality of bases; each base is connected to the central control computer.
[0041] A gas sensor is fixedly arranged on a base, and each gas sensor is slidingly connected to the track power supply 2 and the vertical lifting mechanism 3 through the corresponding base.
[0042] According to the scheduling scheme, each base drives the corresponding gas sensor to slide on the track power supply 2 and the vertical lifting mechanism 3, thereby realizing the movement of the corresponding gas sensor and achieving the intra-layer movement of the gas sensor.
[0043] As an optional implementation, the positioning module includes: a photoelectric encoder and a microcontroller.
[0044] The photoelectric encoder and the microcontroller are both mounted on the base and are used to jointly determine the displacement information of each gas sensor 1. The wireless communication module of the gas sensor 1 can be used to send the displacement information to the central control computer.
[0045] The photoelectric encoder records the displacement increment of the gas sensor 1, and the microcontroller processes the pulse signal of the photoelectric encoder, calculates the accumulated displacement, and adds the unique identification of the gas sensor 1.
[0046] The beneficial effects of this application are: 1. The intra-layer and inter-layer scheduling and layout method of gas sensors adopted in this application fully improves the space utilization rate of the multi-story parking lot, reduces the number of gas sensors while ensuring the accuracy of gas detection, reduces procurement costs, and can save electricity costs when idle.
[0047] 2. In addition to being able to change in real time based on the current situation, risk areas can also be predicted based on time, allowing for pre-deployment of gas sensors and improving scheduling efficiency.
[0048] 3. The layout and dynamic scheduling of gas sensors are combined with multiple algorithms, which can self-update as the scene of the multi-story parking building changes, ensuring that the multi-story parking building is always in a monitored and safe state.
[0049] 4. This application combines the movable characteristics of the gas sensor and uses the gas sensor itself to indicate the location and range of gas leakage, with fast response speed and high accuracy.
[0050] Based on the same inventive concept, an embodiment of the present application also provides a dynamic scheduling method based on the above-mentioned gas monitoring system for a multi-story parking building. The implementation solution to the problem provided by this method is similar to the implementation solution recorded in the above-mentioned system. Therefore, the specific limitations of one or more embodiments of the dynamic scheduling method for a gas monitoring system for a multi-story parking building provided below can be found in the above limitations on the gas monitoring system for a multi-story parking building, and will not be repeated here.
[0051] In an exemplary embodiment, Figure 2 As shown, a dynamic scheduling method for a gas monitoring system of a multi-story parking building is provided, comprising the following steps.
[0052] Step S1, obtaining parking data of new energy vehicles in a multi-story parking garage; the parking data of new energy vehicles includes: parking location of the new energy vehicle, whether it is a fuel cell vehicle, and the number of vehicles parked.
[0053] Specifically, after obtaining the parking data of new energy vehicles in the multi-story parking building, the parking data of new energy vehicles is preprocessed, invalid and abnormal data are removed, and then normalized to eliminate the dimensional effect, thereby obtaining the normalized parking data of new energy vehicles.
[0054] In step S2, a clustering algorithm is used to divide all parking floors in the multi-story parking building into zones based on the parking data of new energy vehicles to obtain multiple zones, and the first deployment position and gas concentration prediction value of each gas sensor in each zone are determined, and each gas sensor is deployed at the corresponding first deployment position.
[0055] As an optional implementation, in step S2, a clustering algorithm is used to divide all parking floors in the multi-story parking building into zones based on the parking data of new energy vehicles to obtain multiple zones, and the first deployment position of each gas sensor in each zone is determined, which specifically includes the following steps.
[0056] In step S21 , a K-means clustering algorithm is used to divide all parking floors in the multi-story parking building into multiple zones based on the parking location, parking duration, and parking quantity of each fuel cell vehicle.
[0057] First, the K value is selected according to the scale of the multi-story parking structure and the expected number of gas sensors to be deployed, and then K initial cluster centers are randomly selected; the cluster center is updated to the mean of all points in each cluster; the above steps are repeated until the cluster center no longer changes significantly, and the final cluster center of each partition is obtained.
[0058] Step S22: The cluster center corresponding to each partition is used as the first deployment position of the gas sensor in each partition.
[0059] As an optional implementation, in step S2, the calculation formula for the predicted value of the gas concentration in each partition is as follows.
[0060] (1) in, is the predicted value of gas concentration; (x, y, z) is the coordinate of the position to be predicted in the partition; n is the number of fuel cell vehicles in the corresponding partition; is a function used to introduce environmental factors; is the diffusion coefficient of any type of gas, For time; ( x i , y i , z i ) is the i The coordinates of a potential gas leak point.
[0061] Step S3: determining the risk level of each partition based on the predicted gas concentration value in each partition; the risk level is: high risk, medium risk, low risk or no risk.
[0062] According to the number and parking location of fuel cell vehicles in each zone, the gas concentration prediction value is calculated to determine the risk level of each zone: the risk level of the zone with a gas concentration prediction value greater than or equal to 4% is determined to be high risk, the risk level of the zone with a gas concentration prediction value greater than or equal to 1% and less than 4% is determined to be medium risk, the risk level of the zone with a gas concentration prediction value greater than or equal to 0% and less than 1% is determined to be low risk, and the risk level of the zone with a gas concentration prediction value of 0% is determined to be a risk-free area.
[0063] Step S4, using a gas sensor scheduling model, based on the coordinate range and risk level of each partition and the first deployment position, gas concentration detection value and power status of each gas sensor in each partition, determines the scheduling parameter prediction value of the corresponding gas sensor; the scheduling parameter prediction value includes: the movement direction within the layer, the movement direction between layers, the opening and closing state and the moving speed; the gas sensor scheduling model is obtained by training the neural network model using a training set; the training set includes: the coordinate range and risk level of multiple sample partitions, the first deployment position, gas concentration detection value and power status of each gas sensor in each sample partition and the scheduling parameter prediction value of each gas sensor in the corresponding sample partition.
[0064] As an optional implementation, in step S4, the training process of the gas sensor scheduling model specifically includes the following steps: Step S41: Obtain a training set.
[0065] In step S42, the coordinate range and risk level of multiple sample partitions, the first deployment position of each gas sensor in each sample partition, the gas concentration detection value and the power status, and the scheduling parameter prediction value of each gas sensor in the corresponding sample partition are input into the neural network model, and the scheduling parameter prediction value of the gas sensor is output.
[0066] Step S43, constructing a loss function based on the predicted value of the scheduling parameter of the gas sensor and the predicted value of the scheduling parameter of each gas sensor in the sample partition, and iteratively optimizing the parameters of the neural network model according to the loss function until the loss function reaches a minimum value or the iterative optimization round reaches a maximum value, stopping the iterative optimization, and obtaining the gas sensor scheduling model.
[0067] Specifically, the state space and action space of the gas sensor are established. The gas sensor state is defined, including: the current gas sensor location coordinates, including layer number and on-track position; the current gas concentration value; the coordinate range of each sample partition; and the gas sensor's power level. The gas sensor's executable actions are defined, including: movement to the left on the same layer, movement to the right on the same layer, movement between layers upward, and movement between layers downward; turning the gas sensor on and off; and the gas sensor's movement speed.
[0068] Before training, a reward function is designed: different positive rewards are given when the gas sensor moves to different risk zones; positive rewards are given when the gas sensor detects a gas leak; negative rewards are given when the gas sensor fails to detect a gas leak in time; negative rewards are given when the gas sensor is low on battery or passively shuts down; negative rewards are given when the gas sensor moves ineffectively in a risk-free zone; and negative rewards are given to encourage energy-saving operations when the gas sensor consumes power while moving or monitoring. The reward function can be expressed as follows: (2) in: The number of gas sensors required for the zones, is the actual number of gas sensors, is the number of times the gas sensor successfully detects a leak, is the number of times the gas sensor failed to detect the leak in time, The number of times the gas sensor has low battery. is the number of times the gas sensor is passively closed, The power consumed by the gas sensor when moving or monitoring. is the weight coefficient of each item, which is used to adjust the importance of different factors.
[0069] Use the Q-learning algorithm to initialize the Q table, where rows represent states, columns represent actions, and the initial value is 0. Set the learning rate , discount factor and exploration rate ε.
[0070] The action is selected according to the ε-greedy strategy. The specific process is as follows.
[0071] An action is chosen randomly with probability ε.
[0072] The action with the largest current Q value is selected with a probability of 1-ε.
[0073] Perform the chosen action and observe the resulting state and reward obtained.
[0074] Update the Q value using the Q-learning update formula as follows.
[0075] (3) in, is the current state of the gas sensor, is the current action of the gas sensor, For the rewards received, is the next state of the gas sensor, This is the next action of the gas sensor.
[0076] Then iterative training is performed, repeating the process of selecting actions, executing actions, and updating Q values until the preset number of training rounds is reached or the Q value converges.
[0077] The gas sensor scheduling model is applied to the actual scheduling of gas sensors, automatically optimizing the sensor movement and monitoring strategies. Optimized scheduling can be performed every time a fuel cell vehicle is parked or taken out of the multi-story parking garage, while no response is made to changes in non-fuel cell vehicles. This achieves intelligence without consuming additional electricity, ensuring high efficiency and environmental protection.
[0078] In step S5, based on the predicted dispatch parameter values for each gas sensor within each zone, each gas sensor within each zone is moved from its corresponding first deployment position to the corresponding zone according to a first preset dispatching scheme, and a second deployment position for each gas sensor is determined. Subsequently, more gas sensors are dispatched to key areas to ensure adequate monitoring, improving safety and efficiency. When there are fewer new energy vehicles, gas sensors on idle floors can be transported between floors, and more gas sensors can be allocated to high-utilization floors to improve gas sensor response speed and detection accuracy. Unused sensors can be disabled to conserve energy. When there are more new energy vehicles, gas sensors on each floor are not moved between floors.
[0079] As an optional implementation, in step S5, the first preset scheduling scheme is: scheduling a first set number of gas sensors to a partition with a high risk level, scheduling a second set number of gas sensors to a partition with a medium risk level, scheduling a third set number of gas sensors to a partition with a low risk level, and no gas sensors are set in a partition with a no risk level; wherein, the first set number is greater than the second set number, and the second set number is greater than the third set number.
[0080] Step S6: determining the gas leakage range according to the position of the gas sensor that detects gas leakage from the parked new energy vehicle.
[0081] As an optional implementation, step S6 specifically includes the following steps.
[0082] In step S61 , the gas sensor that detects gas leakage from the parked new energy vehicle is used as the central gas sensor.
[0083] Step S62: determining two edge gas sensors based on the central gas sensor; the two edge gas sensors are gas sensors located on both sides of the central gas sensor and on the same track power supply as the central gas sensor.
[0084] Step S63 , controlling each of the edge gas sensors to move in a direction away from the central gas sensor within a preset range, and obtaining the gas concentration detection value of each of the edge gas sensors in real time during the movement.
[0085] In step S64, the gas leakage range is determined based on the location where the gas concentration detection value corresponding to each edge gas sensor reaches its minimum. The location where the gas concentration detection value is minimum is the edge of the gas leakage area. While the central gas sensor is positioned, the gas sensors on both sides can move along the edge of the gas leakage area, providing a visual display of the current gas presence area. This allows administrators to visually determine the current danger situation and monitor the progress of subsequent risk elimination actions.
[0086] The moving speed of the gas sensor is set to the following iterative formula.
[0087] (4) in, is the gas sensor speed, It is a positive coefficient, which is related to the adjustable speed range of the specific gas sensor. It is the instantaneous gas concentration detection value of the gas sensor.
[0088] By setting the sensor speed according to this formula, it is possible to respond promptly and at high speed after detecting a gas leak, reduce the speed when approaching the gas leak, and finally move back and forth slightly above the gas leak to locate the gas leak.
[0089] In step S63, when a gas sensor detects a gas leak, the PID control method is used to set the speeds of the two edge gas sensors on both sides of the gas sensor as follows.
[0090] (5) in, is the moving speed of the edge gas sensor at the current moment, is the minimum gas concentration detection value detected by the edge gas sensor, is the gas concentration detection value at the current moment, is the proportional gain, which is used to respond to the current concentration error. is the integral gain, which is used to accumulate past errors and reduce steady-state errors. is the differential gain, which is used to predict future error changes and enhance system stability.
[0091] Furthermore, the dynamic scheduling method for the gas monitoring system of the multi-story parking structure also includes the following steps.
[0092] The system updates and records the current parking situation in the multi-story parking structure (new energy vehicle parking location, entry and exit timestamps, and whether it is a fuel cell vehicle) in real time, generating historical data. After a period of operation, it can build a time series model of new energy vehicle parking patterns based on the random errors between current and historical data, allowing for future predictions. For example, if there are no or few vehicles at night and more vehicles during daytime peak hours, the system can predict new energy vehicle parking data based on historical peak data from similar dates before the daytime peak arrives. Gas sensors can be pre-deployed during off-peak hours, alleviating time pressure on gas sensor scheduling during peak periods. Predictions can be made for the morning, noon, and evening of the day, weekdays and weekends of the week, and different seasons and months.
[0093] In an exemplary embodiment, a computer device is provided, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement a gas monitoring system and a dynamic scheduling method for a multi-story parking structure.
[0094] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 3As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a gas monitoring system and a dynamic scheduling method for a multi-story parking building are realized.
[0095] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.
[0096] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.
[0097] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).
[0098] The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may include, but are not limited to, general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic units, data processing logic units based on quantum computing, and the like.
[0099] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0100] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above examples is only intended to help understand the method and core concept of this application. At the same time, for those skilled in the art, based on the concept of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.
Claims
1. A gas monitoring system for a multi-story parking structure, characterized in that: The gas monitoring system for a multi-story parking structure includes: multiple gas sensors, multiple positioning modules, multiple track power supplies, multiple vertical lifting mechanisms, and a central control computer arranged in the multi-story parking structure; the multi-story parking structure includes multiple parking floors, each parking floor is provided with multiple track power supplies, and two track power supplies located on two adjacent parking floors are connected via a vertical lifting mechanism; A positioning module is fixedly mounted on a gas sensor, each gas sensor is slidably connected to the track power supply and the vertical lifting mechanism, and each gas sensor and each positioning module is connected to the central control computer respectively; The gas sensor is used to collect real-time data on gas concentrations leaked from new energy vehicles parked at different locations within the multi-story parking structure; the gases include hydrogen, carbon monoxide, carbon dioxide, nitrogen oxides, methane, ethane, and ethylene; The positioning module is used to collect displacement information of the gas sensor; The vertical lifting mechanism is used to realize the inter-layer movement of the gas sensor between different parking floors; The track power supply is used to supply power to each gas sensor; The central control computer is used for: determining the position information of the gas sensor according to the position of the track power supply and the displacement information; Generate a corresponding scheduling plan based on the gas concentration data of leakage from parked new energy vehicles at different locations and the location information; According to the scheduling plan, each gas sensor realizes movement inside the multi-story parking building through the track power supply and vertical lifting mechanism; the movement includes movement within the floor and movement between floors; The scheduling scheme specifically includes: Obtain parking data of new energy vehicles in a multi-story parking structure; the parking data of new energy vehicles includes: parking location of the new energy vehicle, whether it is a fuel cell vehicle, and the number of vehicles parked; Using a clustering algorithm, based on the parking data of new energy vehicles, all parking floors in the multi-story parking structure are divided into multiple zones, a first deployment position and a predicted gas concentration value of each gas sensor in each zone are determined, and each gas sensor is deployed at the corresponding first deployment position; Determine the risk level of each zone based on the predicted gas concentration value in each zone; the risk level is: high risk, medium risk, low risk or no risk; A gas sensor scheduling model is used to determine the corresponding gas sensor scheduling parameter prediction value based on the coordinate range and risk level of each partition, as well as the first deployment position, gas concentration detection value, and power state of each gas sensor in each partition. The scheduling parameter prediction value includes: intra-layer movement direction, inter-layer movement direction, opening and closing state, and movement speed. The gas sensor scheduling model is obtained by training a neural network model using a training set; the training set includes: the coordinate range and risk level of multiple sample partitions, the first deployment position, gas concentration detection value, and power state of each gas sensor in each sample partition, and the scheduling parameter prediction value of each gas sensor in the corresponding sample partition. Based on the predicted value of the scheduling parameter of each gas sensor in each zone, move each gas sensor in each zone from the corresponding first deployment position to the corresponding zone according to the first preset scheduling plan, and determine the second deployment position of each gas sensor; The scope of gas leakage is determined based on the position of the gas sensor that detects gas leakage from the parked new energy vehicle.
2. The gas monitoring system for a multi-story parking structure according to claim 1, characterized in that: The gas monitoring system for a three-dimensional parking structure further includes: a plurality of bases; each base is connected to the central control computer; A gas sensor is fixedly mounted on a base, and each gas sensor is slidably connected to a track power supply and a vertical lifting mechanism through a corresponding base; According to the scheduling scheme, each base drives the corresponding gas sensor to slide on the track power supply and the vertical lifting mechanism to achieve the movement of the corresponding gas sensor.
3. The gas monitoring system for a multi-story parking structure according to claim 2, characterized in that: The positioning module includes: a photoelectric encoder and a microcontroller; The photoelectric encoder and the microcontroller are both mounted on the base, and the photoelectric encoder and the microcontroller are used to jointly determine the displacement information of each gas sensor.
4. A dynamic scheduling method for a gas monitoring system in a multi-story parking garage, characterized in that: The dynamic scheduling method for a gas monitoring system for a multi-story parking structure is based on the gas monitoring system for a multi-story parking structure according to any one of claims 1 to 3, and the dynamic scheduling method for a gas monitoring system for a multi-story parking structure includes: Obtain parking data of new energy vehicles in a multi-story parking structure; the parking data of new energy vehicles includes: parking location of the new energy vehicle, whether it is a fuel cell vehicle, and the number of vehicles parked; Using a clustering algorithm, based on the parking data of new energy vehicles, all parking floors in the multi-story parking structure are divided into multiple zones, a first deployment position and a predicted gas concentration value of each gas sensor in each zone are determined, and each gas sensor is deployed at the corresponding first deployment position; Determine the risk level for each zone based on the predicted gas concentration within each zone; the risk level is high risk, medium risk, low risk, or no risk; A gas sensor scheduling model is used to determine the corresponding gas sensor scheduling parameter prediction value based on the coordinate range and risk level of each partition, as well as the first deployment position, gas concentration detection value, and power state of each gas sensor in each partition. The scheduling parameter prediction value includes: intra-layer movement direction, inter-layer movement direction, opening and closing state, and movement speed. The gas sensor scheduling model is obtained by training a neural network model using a training set; the training set includes: the coordinate range and risk level of multiple sample partitions, the first deployment position, gas concentration detection value, and power state of each gas sensor in each sample partition, and the scheduling parameter prediction value of each gas sensor in the corresponding sample partition. Based on the predicted value of the scheduling parameter of each gas sensor in each zone, move each gas sensor in each zone from the corresponding first deployment position to the corresponding zone according to the first preset scheduling plan, and determine the second deployment position of each gas sensor; The scope of gas leakage is determined based on the position of the gas sensor that detects gas leakage from the parked new energy vehicle.
5. The dynamic scheduling method for a gas monitoring system for a multi-story parking structure according to claim 4, characterized in that: A clustering algorithm is used to divide all parking floors in the multi-story parking structure into multiple zones based on the parking data of new energy vehicles. The first deployment position of each gas sensor in each zone is determined, specifically including: Using a K-means clustering algorithm, all parking floors in the multi-story parking structure are divided into multiple zones based on the parking location, parking duration, and parking quantity of each fuel cell vehicle. The cluster center corresponding to each partition is used as the first deployment location of the gas sensor in each partition.
6. The dynamic scheduling method for a gas monitoring system for a multi-story parking structure according to claim 4, characterized in that: The calculation formula for the predicted gas concentration in each zone is: ； in, is the predicted value of gas concentration; (x, y, z) is the coordinate of the position to be predicted in the partition; n is the number of fuel cell vehicles in the corresponding partition; is a function used to introduce environmental factors; is the diffusion coefficient of any type of gas, For time; ( x i , y i , z i ) is the i The coordinates of a potential gas leak point.
7. The dynamic scheduling method for a gas monitoring system for a multi-story parking structure according to claim 4, characterized in that: The training process of the gas sensor scheduling model specifically includes: Get the training set; The coordinate ranges and risk levels of multiple sample partitions, the first deployment position, gas concentration detection value, and power status of each gas sensor in each sample partition, and the scheduling parameter prediction value of each gas sensor in the corresponding sample partition are input into the neural network model, and the scheduling parameter prediction value of the gas sensor is output; A loss function is constructed based on the predicted value of the scheduling parameter of the gas sensor and the predicted value of the scheduling parameter of each gas sensor in the sample partition, and the parameters of the neural network model are iteratively optimized according to the loss function until the loss function reaches a minimum value or the iterative optimization round reaches a maximum value. The iterative optimization is stopped to obtain the gas sensor scheduling model.
8. The dynamic scheduling method for a gas monitoring system for a multi-story parking structure according to claim 4, characterized in that: The first preset scheduling scheme is: dispatching a first set number of gas sensors to a partition with a high risk level, dispatching a second set number of gas sensors to a partition with a medium risk level, dispatching a third set number of gas sensors to a partition with a low risk level, and no gas sensors are set in a partition with a no risk level; wherein, the first set number is greater than the second set number, and the second set number is greater than the third set number.
9. The dynamic scheduling method for a gas monitoring system for a multi-story parking structure according to claim 4, characterized in that: Based on the location of the gas sensor that detects gas leakage from parked new energy vehicles, determine the scope of gas leakage, including: The gas sensor that detects gas leakage from parked new energy vehicles is used as the central gas sensor; Based on the central gas sensor, two edge gas sensors are determined; the two edge gas sensors are gas sensors located on both sides of the central gas sensor on the same track power supply as the central gas sensor; Controlling each of the edge gas sensors to move in a direction away from the central gas sensor within a preset range, and obtaining a gas concentration detection value of each of the edge gas sensors in real time during the movement; The gas leakage range is determined based on the position where the gas concentration detection value corresponding to each edge gas sensor is the minimum value.
10. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the gas monitoring system and dynamic scheduling method for a multi-story parking structure as described in any one of claims 4 to 9.