A smart fog cannon device and its control method

Abstract

This specification provides an intelligent fog cannon device and control method. The device includes a spray generating device, a base, a control device, an interaction device, and a detection device. The spray generating device operates based on control commands and operating parameters sent by the control device. The control device includes a controller and a processor. The processor is used to generate operating parameters based on input data received from the interaction device and to generate control commands through the controller. The interaction device is used to receive and display the operating parameters generated by the processor. The detection device includes a device detection device, which is used to send reminder information to the processor and the interaction device respectively if it detects that a target device is present within a preset range.

Description

Technical Field

[0001] This manual relates to the field of smart IoT, and in particular to a smart fog cannon device and its control method. Background Technology

[0002] A fog cannon (or fog cannon device) is a spraying device that turns water into a mist under high pressure. It can be used to suppress dust, remove dust, cool down, and reduce smog, and can be applied in construction sites, coal mines, steel plants, and other industrial and mining locations. However, existing fog cannons have a low level of intelligence, and their dust suppression efficiency and effect are not ideal in actual use.

[0003] To improve the intelligence of fog cannons, CN207871797U discloses a device for remote intelligent control of fog cannons based on an Internet of Things touch display terminal. This application collects environmental parameters such as wind speed, temperature, dust, and humidity at the user's site and realizes intelligent control of the fog cannon based on the acquired environmental parameters. However, this process does not involve monitoring the working status of the fog cannon or changes in environmental data. Therefore, this control process does not adjust the fog cannon based on its current working status and environmental data, which has an adverse effect on its working efficiency and dust suppression effect.

[0004] Therefore, it is desirable to provide an intelligent fog cannon device and control method that can more accurately control the fog cannon machine, thereby improving dust suppression effect and operational efficiency. Summary of the Invention

[0005] This specification provides one or more embodiments of an intelligent fog cannon device. The intelligent fog cannon device includes: a spray generating device, a base, a control device, an interaction device, and a detection device; the spray generating device is rotatably connected to the base via a rotating shaft, the rotating shaft being controlled by a motor; the control device and the interaction device are installed in the base, and the control device is communicatively connected to the interaction device; the detection device is installed on a positioning rod, the positioning rod being installed on the base; the spray generating device includes at least a water supply device, an atomizer, a fan, and a spray launcher; the motor, the fan, and the atomizer are communicatively connected to the control device, and are used to operate based on control commands and operating parameters sent by the control device; the control device includes a controller and a processor, the processor being used to: generate the operating parameters based on input data received from the interaction device, and generate the control commands through the controller; the interaction device is used to receive and display the operating parameters generated by the processor; the detection device includes a device detection device, the device detection device being used to: if a target device is detected within a preset range, send a reminder message to the processor and the interaction device respectively.

[0006] This specification provides one or more embodiments of a control method for an intelligent fog cannon device. The method is applied to a control device, a spray generating device, an interaction device, and a detection device. The control method is executed by the processor and includes: receiving a reminder message sent by the detection device in response to the detection device detecting that a target device is present within a preset range; receiving input data from the interaction device to generate operating parameters and generating control commands through a controller; sending the control commands and operating parameters to the spray generating device; and sending the operating parameters to the interaction device.

[0007] This specification provides a control system for an intelligent fog cannon device through one or more embodiments, including a processor for executing the control method for the intelligent fog cannon device as described above.

[0008] This specification provides one or more embodiments of a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions in the storage medium, it executes the control method of the intelligent fog cannon device as described above. Attached Figure Description

[0009] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein:

[0010] Figure 1 This is a device diagram of an intelligent fog cannon device according to some embodiments shown in this specification;

[0011] Figure 2 This is an exemplary flowchart illustrating the adjustment of operating parameters of an intelligent fog cannon device according to some embodiments of this specification;

[0012] Figure 3 This is an exemplary flowchart of a method for predicting future environmental changes according to some embodiments of this specification;

[0013] Figure 4 These are exemplary schematic diagrams of effect prediction models shown in some embodiments of this specification;

[0014] Figure 5 These are exemplary schematic diagrams of environmental prediction models shown in some embodiments of this specification;

[0015] Figure 6 This is a schematic diagram of a relationship spectrum based on some embodiments of this specification. Detailed Implementation

[0016] To more clearly illustrate the technical solutions of the embodiments of this specification, the following will briefly introduce the attached drawings required for the description of the embodiments. Obviously, the attached drawings in the following description are only some examples or embodiments of this specification. For those of ordinary skill in the art, without creative efforts, this specification can also be applied to other similar scenarios based on these drawings. Unless obvious from the language context or otherwise stated, the same reference numerals in the figures represent the same structure or operation.

[0017] It should be understood that the "system", "device", "unit" and / or "module" used herein is a way to distinguish different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the said words can be replaced by other expressions.

[0018] As shown in this specification and the claims, unless the context clearly indicates an exception, words such as "a", "an", "one" and / or "the" are not specifically singular and may also include plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the clearly identified steps and elements, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0019] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the previous or subsequent operations do not necessarily need to be executed precisely in order. On the contrary, the steps can be processed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several steps can be removed from these processes.

[0020] The fog cannon is used to perform dust suppression and dust control on the environment, thereby reducing environmental pollution. Precisely controlling the fog cannon to operate can improve the dust suppression efficiency and effect of the fog cannon. CN207871797U controls the fog cannon according to environmental parameters such as wind speed, temperature, dust emission, and humidity at the equipment site, without considering the changes in environmental parameters and the working parameters of the fog cannon device. Since it does not combine the current working conditions of the fog cannon and environmental data to adjust the fog cannon, it is even less conducive to the fog cannon to flexibly adjust the working parameters according to the current situation in real time, which has an adverse impact on its working efficiency and dust suppression effect.

[0021] Some embodiments of this specification are based on existing environmental data such as temperature, humidity, and dust emission conditions, intelligently predict the environmental data, its change rate, and development trend in the next time period, and automatically take targeted measures for environmental protection dust suppression and humidification processing based on the working parameters of the fog cannon device, which can improve the control accuracy of the fog cannon, thereby improving the dust suppression efficiency and effect. At the same time, through the interaction device, the linkage of multiple fog cannon devices can be achieved, which can improve the control efficiency and effect.

[0022] Figure 1 This is a device diagram of an intelligent fog cannon device according to some embodiments of this specification.

[0023] In some embodiments, the intelligent fog cannon device may include a spray generating device 1, a base 2, a control device, an interaction device, a detection device 3, and a positioning rod 4, etc. The control device (not shown) and the interaction device (not shown) are located inside the base.

[0024] In some embodiments, the spray generating device 1 and the base 2 are rotatably connected by a rotating shaft, which is controlled to rotate by a motor; the control device and the interaction device are installed in the base 2 and are communicatively connected; the detection device 3 is installed on the positioning rod 4, which is installed on the base.

[0025] A spray generating device can be a combination of devices used to produce a spray. For example, a spray generating device may include a water supply device, an atomizer, a fan, and a spray launcher.

[0026] In some embodiments, the motor, fan, and atomizer can be communicatively connected to the control device and operate based on control commands and operating parameters sent by the control device. For example, if the control device issues a command to launch a spray at a 45° westward direction with a power of 50 kW forward for 100 m, the motor, fan, and atomizer can operate according to this command and parameters. Each device can adjust its orientation in response to orientation commands via a positioning rod and a rotating shaft.

[0027] A control device can be a device that directs and coordinates the operation of various equipment or system components. For example, a control device can include a controller and a processor.

[0028] The processor can process data and / or information obtained from other devices or system components. Based on this data, information, and / or processing results, the processor can execute program instructions to perform one or more functions described in this specification. For example, the processor can be used to generate operating parameters based on input data from a receiving device. In some embodiments, the processor may include one or more sub-processing devices (e.g., a single-core processing device or a multi-core multi-chip processing device). By way of example only, the processor may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or any combination thereof.

[0029] Operating parameters can be the parameters required for each device to operate. For example, operating parameters may include spray direction, angle, spray power and corresponding spray distance, and the activation conditions of the fog cannon device.

[0030] The controller can generate control instructions for the operation of various devices. For example, the controller can be used to generate control instructions based on operating parameters obtained from the processor.

[0031] Control commands can be instructions that control the operating parameters of a device. For example, control commands can be generated based on parameters such as the spray direction, angle, spray power, and corresponding spray distance of a spray generating device, instructing the corresponding device to operate based on those operating parameters.

[0032] In some embodiments, the processor can send linkage information to the interaction device of other fog cannon devices and receive feedback information; and based on the feedback information, generate multiple operating parameters for multiple fog cannon devices, and send the control commands corresponding to the operating parameters of multiple fog cannon devices to the corresponding fog cannon devices respectively.

[0033] Linkage information can include requests to link with other fog cannon devices. For example, linkage information may include whether information exchange is permitted.

[0034] Feedback information can be information sent from the receiving device to the sending device. In some embodiments, feedback information may include linkage confirmation information, etc. Linkage confirmation information may include content such as agreeing to linkage, opposing linkage, or pending. For example, if fog cannon device B sends feedback information agreeing to linkage to fog cannon device A, then the interaction system between B and A can perform data exchange.

[0035] In some embodiments, the processor can send control commands corresponding to the operating parameters of multiple fog cannon devices to their respective fog cannon devices. For example, the processor can send a control command to fog cannon device A to spray mist at a 45° angle to the west and a power of 50 kW to a distance of 100 m ahead; and send a control command to fog cannon device B to spray mist at a 30° angle to the north and a power of 40 kW to a distance of 80 m ahead, and so on.

[0036] In some embodiments, the interactive device may be used to receive and display working parameters generated by the processor.

[0037] In some embodiments, the main fog cannon device can be determined based on the processor and interaction device of each fog cannon device. In some embodiments, the main fog cannon device can receive the current location and environmental data of each fog cannon device and their respective determined operating parameters, and determine the adjustment parameters of each fog cannon device.

[0038] Environmental data can be environmentally relevant information within a preset range. For example, environmental data may include temperature, wind speed, smog intensity, and dust levels.

[0039] The preset range can be the area where the fog cannon needs to spray. For example, the preset range can include a certain area in places such as construction sites, farms, city streets, and large factory areas where spraying is required.

[0040] In some embodiments, the interaction device of each fog cannon device can determine the master fog cannon device based on preset rules. For example, the preset rules may include the processor of each fog cannon device obtaining the processing effect scores of other fog cannon devices through the interaction device, and determining the fog cannon device with the relatively high score as the master fog cannon device. The processing effect may include the distance between the fog cannon device and the dust, with a higher score for closer distances; the processing effect may also include the power of the fog cannon device itself, with a higher score for higher power, etc.

[0041] In some embodiments, the treatment effect score can be determined based on an effect prediction model. More details about the effect prediction model can be found in [link to relevant documentation]. Figure 4 And its related descriptions.

[0042] In some embodiments, each fog cannon device can transmit its current location and environmental data, along with its determined operating parameters, to the main fog cannon device. For example, each fog cannon device can acquire its current location information and environmental data through a detection device, generate operating parameters through a processor, and transmit the location information, environmental data, and operating parameters to the main fog cannon device for processing via an interaction device to determine adjusted operating parameters. The adjusted operating parameters generated by the main fog cannon device can then be transmitted to each fog cannon device.

[0043] In some embodiments, the main fog cannon device can determine the adjustment parameters of each fog cannon device based on a graph neural network model. More details regarding parameter adjustment can be found in [link to relevant documentation]. Figure 6 And its related descriptions.

[0044] The detection device can be a device that detects data needed during the spray generation process. For example, the detection device can include equipment detection devices, etc.

[0045] The equipment detection device can be used to detect the configuration information of site monitoring devices within a preset range and whether other fog cannon devices are included. For example, the device can use wireless signals such as Bluetooth to detect the location and system type of site monitoring devices within the preset range, whether other fog cannon devices are included, and receive interactive information sent from external sources such as interactive devices. It then generates an alert message to be sent externally via a processor. More details about the alert message can be found in [link to relevant documentation]. Figure 2 And its related descriptions.

[0046] Other fog cannon devices may include devices that send feedback information to the fog cannon device to confirm linkage.

[0047] In some embodiments, other fog cannon devices can interact with this fog cannon device. For example, other fog cannon devices can send acquired environmental data to this fog cannon device, and this fog cannon device can send adjusted parameter information to the other fog cannon devices. For example, this fog cannon device can send other fog cannon devices adjusted parameters such as a 10° deviation of the firing direction to due west, an increase of 5° upwards, an increase of 10 kW in power, and an increase of 20 m in forward distance.

[0048] Site monitoring devices can be used to monitor environmental data of a site. For example, site monitoring devices can be configured with systems such as site monitoring systems, site dust monitoring systems, smart site management systems, and site environmental monitoring systems.

[0049] In some embodiments, the site monitoring device can be used to monitor sites such as construction sites, farms, city streets, and large factory areas. The site monitoring device can transmit environmental data within a preset range of the monitored site to the Internet of Things (IoT).

[0050] In some embodiments, the detection device may also include an environmental detection device, etc.

[0051] Environmental monitoring devices can be used to detect environmental data at the current location of the fog cannon. For example, environmental monitoring devices can detect the temperature, wind speed and direction, fog intensity, and dust levels around the fog cannon.

[0052] In some embodiments, the environmental monitoring device can transmit the acquired environmental data to the processor of the fog cannon device.

[0053] Figure 2 This is an exemplary flowchart illustrating the adjustment of operating parameters of an intelligent fog cannon device according to some embodiments of this specification.

[0054] In some embodiments, process 200 may include the following steps.

[0055] Step 210: The equipment detection device detects that a site monitoring device is located within a preset range and sends a reminder message to the processor.

[0056] More details about the site monitoring device can be found in [link / reference]. Figure 1 And its related descriptions.

[0057] The reminder information may include details such as the type and location of the site monitoring devices within a preset range for the processor and interactive device. For example, the reminder information may include the location of the site monitoring devices and whether one or more of the following are configured: a site monitoring system, a site dust monitoring system, a smart site management system, or a site environmental monitoring system.

[0058] In some embodiments, the device detection device can send alert information about site monitoring devices within a preset range to the processor and interaction device of the fog cannon device. For example, if a site monitoring device equipped with a site monitoring system is installed at a certain location within the preset range, the device detection device can send the location of the site monitoring device and the information about the site monitoring system as alert information to the processor and interaction device.

[0059] Step 220: The processor acquires environmental data detected by the site monitoring device through the Internet of Things system.

[0060] In some embodiments, the processor can acquire environmental data based on the Internet of Things (IoT). For example, the processor can acquire information such as temperature, wind speed, smog intensity, and dust levels within a preset range using data stored in the IoT.

[0061] Step 230: The processor adjusts its operating parameters based on the acquired environmental data.

[0062] In some embodiments, the processor can adjust operating parameters based on acquired environmental data. For example, if the current ambient temperature is high, the spray power and spray distance can be increased to enhance the cooling effect; if there is a level 2 westerly wind (blowing from west to east), the spray direction can be appropriately adjusted to a slightly easterly direction to meet spraying requirements while reducing energy consumption; the temperature threshold can be adjusted so that the temperature received by the processor continuously rises to a preset maximum threshold, at which point the fog cannon device will be activated for cooling; the haze level conditions can be adjusted so that the fog cannon device will be activated when the haze level output by the site monitoring system meets the conditions, etc.

[0063] In some embodiments, the processor can predict an effectiveness score based on multiple candidate adjusted parameters and environmental data of the current location, and determine the adjusted operating parameters based on the effectiveness score. More details regarding the adjusted operating parameters can be found in [link to relevant documentation]. Figure 4 And related content.

[0064] In some embodiments of this specification, the processor can acquire environmental data through site monitoring equipment and adjust its operating parameters based on the environmental data. This method allows for more accurate environmental data and makes the adjustment of operating parameters more consistent with actual conditions.

[0065] Figure 3 This is an exemplary flowchart illustrating a method for predicting future environmental changes according to some embodiments of this specification. Figure 3 As shown, process 300 includes the following steps. In some embodiments, process 300 may be executed by a processor.

[0066] Step 310: The processor obtains weather data from a third-party platform.

[0067] A third-party platform can be a platform that obtains the parameters required by the processor. For example, a third-party platform can include a network platform, an Internet of Things (IoT) platform, etc.

[0068] Weather data can be weather information for a future period of time within a preset range. For example, weather data can include the future temperature range and future wind speed and direction within a preset range.

[0069] In some embodiments, the processor can obtain weather data such as weather forecasts published by third-party platforms. For example, the processor can obtain data such as the temperature being between 15 and 18°C ​​and the wind force being a level 3 southeasterly wind within the range of the weather forecast.

[0070] Step 320: Based on weather data and combined with environmental data, predict environmental change trends.

[0071] Environmental change trends can refer to changes in the environment within a preset range. For example, environmental change trends could include temperature change trends and their rates of change, wind direction and force changes, changes in haze intensity and direction, and future dust development trends. For instance, an environmental change trend could be a subsequent hourly temperature increase of 2°C, a change in wind direction from a level 3 easterly wind to a level 2 southeasterly wind after 1 hour, a decrease in haze intensity from a yellow alert to a blue alert, and a decrease in dust concentration from 6 mg / m³. 3 Increased to 7mg / m 3 wait.

[0072] In some embodiments, the processor can predict environmental change trends based on weather data and combined with environmental data. For example, the processor can predict environmental change trends by comparing weather data and current environmental data. For instance, weather data may include a temperature of 15-18°C and a southeasterly wind of level 3 for the next period; current environmental data may include a temperature of 19°C, a light easterly wind of level 2, a yellow haze warning level, and a dust concentration of 6 mg / m³. 3 The predicted environmental trends could include a temperature drop of 1-4°C and a decrease in wind speed by one level, shifting to a southeasterly wind, etc., within the next one to two hours.

[0073] In some embodiments, the processor can perform a fitting function based on the temporal relationship between environmental and weather data from the current and previous consecutive time points to preliminarily determine future environmental change trends. The independent variable of the fitting function can be time, and the dependent variable can be temperature, wind force, wind direction, haze, dust, etc. The fitting result can be subsequent environmental data or subsequent weather data.

[0074] In some embodiments, the processor can fit the obtained weather and environmental data from multiple consecutive time points, both current and previous, to obtain time-varying curves for temperature, wind force, wind direction, haze, dust, etc. The fitting method can be a combination of linear fitting, nonlinear fitting, or other fitting methods. The fitting results can be preliminary determinations of subsequent environmental and weather data. For example, based on the fitted curves, the fitting results can include preliminary determinations of environmental data one hour later and weather data one hour later. The fitting results can be used as reference data to predict environmental change trends.

[0075] Step 330: Adjust the operating parameters based on the trend of environmental changes.

[0076] In some embodiments, the processor can adjust the operating parameters of the fog cannon device based on predicted environmental change trends. For example, the processor can directly adjust the operating parameters based on environmental change trends. Exemplary environmental change trends may include a 2°C decrease in temperature, a one-level increase in wind speed with no change in direction, no change in fog intensity, and a 1 mg / m³ decrease in dust concentration over the next hour. 3 Then, the operating parameters can be adjusted downwards accordingly, including reducing the spray angle by 10°, reducing the power by 5kW, and reducing the distance by 10m.

[0077] In some embodiments, the processor can adjust operating parameters using an effect prediction model and an environmental prediction model. For example, the processor can obtain subsequent environmental change trends using an environmental prediction model, and adjust operating parameters such as spray direction, angle, spray power, corresponding spray distance, and fog cannon activation conditions based on these trends. The processor can then obtain the effect score of the adjusted fog cannon using the effect prediction model, repeating the adjustment steps until the effect score reaches a threshold, and finally outputting the operating parameters at this point as the final adjusted operating parameters.

[0078] More details on effect prediction models and environmental prediction models can be found in [link to relevant documentation]. Figure 4 , Figure 5 And its related descriptions.

[0079] It should be noted that the above descriptions of processes 200 and 300 are for illustrative purposes only and do not limit the scope of this specification. Those skilled in the art can make various modifications and changes to processes 200 and 300 under the guidance of this specification. However, these modifications and changes remain within the scope of this specification.

[0080] Figure 4 This is an exemplary schematic diagram of an effect prediction model shown in some embodiments of this specification.

[0081] In some embodiments, the processor determines candidate adjusted operating parameters 412 based on the magnitude of the adjustment of the operating parameters of the fog cannon device.

[0082] like Figure 4 As shown, based on the adjusted working parameters 412 of the fog cannon device and the environmental data 411 of the current location of the fog cannon device, the effect prediction model 400 predicts the effect score 420; based on the effect score 420, the target parameters of the fog cannon device are determined, and the working parameters of the fog cannon device are adjusted based on the target parameters.

[0083] Among them, environmental data 411 is detected by environmental monitoring devices.

[0084] The environmental monitoring device is used to detect environmental data 411 at the current location of the fog cannon device, including functions such as temperature detection, humidity detection, and dust level detection. The environmental monitoring device can be used in construction site monitoring systems or installed within the fog cannon device. For more information on environmental monitoring devices, please refer to [link / reference needed]. Figure 1 The corresponding description.

[0085] The multiple candidate adjusted operating parameters 412 of the fog cannon device can be determined based on the magnitude of multiple adjustments to the fog cannon device and the current operating parameters of the fog cannon device. The target parameters of the fog cannon device can be determined based on the effect scores of the multiple candidate adjusted operating parameters 412 of the fog cannon device.

[0086] The adjustment range refers to the adjustment range of the operating parameters of the fog cannon device. This adjustment range includes the adjustment range of spray direction, angle, and spray power. For example, the adjustment range could be increasing the spray power of the fog cannon device by 5%. The adjustment range can be obtained by matching with a vector database. A vector database is a database used to store, index, and query vectors. The vectors in the vector database are obtained by parsing historical data, and the elements in the vectors include environmental data and the adjustment range of the fog cannon device's operating parameters under that environmental data. Matching refers to matching the environmental data of the fog cannon device's current location with the elements in the vectors in the vector database, such as matching temperature, wind force, wind direction, and haze intensity. The matching process can calculate the vector distance with a large number of vectors in the vector database, selecting the vector with the closest distance as the target vector (e.g., the vector distance is less than a vector distance threshold). The adjustment range corresponding to the target vector is the adjustment range obtained through matching.

[0087] The candidate adjusted operating parameters 412 refer to the possible operating parameters of the fog cannon device determined based on the adjustment range of the fog cannon device. For example, if the current spray power of the fog cannon device is 50%, and the adjustment range of the spray power is to increase it by 50%, 60%, and 70%, then the candidate adjusted spray power of the fog cannon device is 75%, 80%, and 85%.

[0088] In some embodiments, multiple possible adjusted operating parameters 412 of the fog cannon device can be determined based on multiple adjustment ranges of the operating parameters of the fog cannon device. For example, if it is necessary to reduce the ambient temperature, the spray power of the fog cannon device can be increased by 5%, 8%, 10%, etc., and then multiple candidate adjusted spray power parameters can be obtained based on the adjustment range of the spray power and the current spray power.

[0089] The candidate adjusted operating parameters 412 of the fog cannon device can be used to determine their corresponding effect scores, which can then be used to determine target parameters for adjusting the operating parameters of the fog cannon device. In some embodiments, the effect prediction model 400 can predict the effect score 420 of the candidate adjusted operating parameters 412 of the fog cannon device based on multiple candidate adjusted operating parameters 412 of the fog cannon device and environmental data 411 of the current location of the fog cannon device. The target parameters of the fog cannon device are determined based on the effect score 420, and the operating parameters of the fog cannon device are adjusted based on the target parameters.

[0090] The effect score 420 refers to the adjustment effect score of the candidate adjusted working parameter 412 of the fog cannon device, which can be derived based on dust reduction effect, cooling effect, haze removal effect, etc. In some embodiments, the dust reduction effect score can be used as the effect score. In some embodiments, the effect scores corresponding to the dust reduction effect, cooling effect, and haze removal effect can be weighted and summed to obtain the effect score 420.

[0091] In some embodiments, the effect prediction model 400 can be used to predict the effect score 420, and the effect prediction model 400 can be a convolutional neural network (CNN) model, etc.

[0092] In some embodiments, the candidate adjusted operating parameters 412 of the fog cannon device and the environmental data 411 of the current location are input into the effect prediction model 400, and the effect score 420 corresponding to the candidate adjusted operating parameters 412 can be output.

[0093] In some embodiments, the effect prediction model 400 can be trained based on a large amount of labeled historical data. In some embodiments, the labels can be effect scores, which can be obtained through image recognition or environmental detection devices acquired after a first preset time. For example, the labels can be effect scores based on the dust level in images acquired after the first preset time or environmental data detected by an environmental detection device after the first preset time. Labels can be manually labeled. In some embodiments, the samples are collected historical data, including the operating parameters of the fog cannon device and environmental data of the location of the fog cannon device.

[0094] The effect prediction model 400 can derive the effect score 420 corresponding to the candidate adjusted working parameters 412 of the fog cannon device and the environmental data 411 of the current location. Based on the effect score 420, a suitable adjustment scheme for the fog cannon device that matches the environment can be selected, which can make the dust suppression effect and operation efficiency of the fog cannon device better.

[0095] The target parameter is the adjusted operating parameter of the fog cannon device. In some embodiments, the target parameter can be determined from the candidate adjusted operating parameters of the fog cannon device.

[0096] In some embodiments, the effect scores 420 can be sorted, and the target parameter can be determined based on the sorting result. For example, the effect scores 420 can be sorted in descending order, and the candidate adjusted working parameter corresponding to the highest effect score can be used as the target parameter based on the sorting result.

[0097] In some embodiments, the effect prediction model 400 can send the determined target parameters to the processor, which then issues instructions to control the fog cannon device to make adjustments. For example, if the effect prediction model 400 determines that the operating parameters of the fog cannon device are a spray direction of southwest, an upward angle of 45°, and a spray distance of 5m, then the operating parameters are sent to the processor, which then issues instructions to control the fog cannon device to adjust the operating parameters to a spray direction of southwest, an upward angle of 45°, and a spray distance of 10m.

[0098] The effect prediction model can derive the effect score corresponding to the candidate adjusted working parameters of the fog cannon device and the environmental data of the current location. This allows for the selection of a more efficient adjustment scheme for the fog cannon device based on the current environmental data and the current working parameters of the fog cannon device.

[0099] Figure 5 This is an exemplary schematic diagram of an environmental prediction model shown according to some embodiments of this specification.

[0100] In some embodiments, environmental change trend 540 can be predicted by environmental prediction model 500.

[0101] In some embodiments, the environmental prediction model 500 can predict future environmental change trends 540 based on previous environmental data, weather data, and site data (e.g., environmental data, weather data, and site data from a time period prior to the current moment). The environmental change trend 540 includes at least one or more of the following: temperature, wind speed and direction, direction of change in haze intensity (e.g., increasing or decreasing, becoming stronger or weaker), future dust development trends, and the rate of change of each parameter.

[0102] In some embodiments, the structure of the environmental prediction model 500 may include an embedding layer 520 and a prediction layer 530.

[0103] In some embodiments, inputting the previous environmental data 511 and weather data 512 into the embedding layer 520 of the environmental prediction model can output the feature vectors (not shown) corresponding to the environmental data and weather data. Inputting the feature vectors corresponding to the environmental data and weather data output by the embedding layer 520, the subsequent environmental data 514 (fitted based on the previous environmental data 511), the subsequent weather data 515 (fitted based on the previous weather data 512), the site data 513, etc. into the prediction layer 530 of the environmental prediction model 500 can output the subsequent environmental change trend 540.

[0104] In some embodiments, the embedding layer 520 can be a CNN model. A fitted graph, derived from environmental data at current and previous consecutive time points, can be input into the embedding layer 520. The embedding layer 520 can output feature vectors for subsequent environmental data 514 and subsequent weather data 515. The independent variable of the fitting function for the fitted graph is time, and the dependent variables are temperature, wind force, wind direction, haze, dust, etc. The fitting results are subsequent environmental data 514 and subsequent weather data 515.

[0105] The environmental prediction model 500 can be trained based on a large amount of labeled historical data. In some embodiments, the labels can be environmental change trends, which can be automatically determined based on historical data or manually labeled.

[0106] In some embodiments, the output of the embedding layer 520 can be the input of the prediction layer 530, and the embedding layer 520 and the prediction layer 530 can be jointly trained. In some embodiments, the sample data for joint training includes previous environmental data 511, weather data 512, and site data 513, labeled as environmental change trends. The previous environmental data 511 and weather data 512 are input into the embedding layer 520 to obtain the feature vectors of the previous environmental data 511 and weather data 512, as well as the feature vectors of the subsequent environmental data 514 and subsequent weather data 515. The feature vectors of the subsequent environmental data 514 and subsequent weather data 515 and the site data 513 are used as training sample data and input into the prediction layer 530 to obtain the environmental change trend output by the prediction layer 530.

[0107] In some embodiments, the adjustment of working parameters can be determined by an effect prediction model.

[0108] The effect prediction model can be reinforced with future training. This future-oriented reinforcement training includes training the model to score the effects of the fog cannon device operating in future times. For example, the reinforced model can score the dust suppression effect of a fog cannon device 24 hours later.

[0109] The reinforcement training of the performance prediction model can be performed by acquiring image recognition data or environmental detection data after a second preset time, and using the image acquired after the second preset time or the data detected by the environmental detection device after the second preset time as the basis for determining the performance score at the second preset time. The second preset time includes moments later than the first preset time. The performance score can be determined by weighting the scores at the first and second preset times to determine the final label. For example, if the scores at the first and second preset times each have a weight of 50%, the performance score would be the sum of the score of the image recognition acquired after the first preset time multiplied by its 50% weight and the score of the image recognition acquired after the second preset time multiplied by its 50% weight.

[0110] The weights are the proportions of the scores for the first and second preset times in the overall effect score. In some embodiments, the proportions of the scores for the first and second preset times in the overall effect score can be determined based on the actual scenario to be used. For example, if the first preset time is the time corresponding to 10 minutes later, and the dust needs to be reduced within 30 minutes, then the time corresponding to 30 minutes later can be the second preset time, and the proportion of the score for the second preset time in the overall effect score can be set higher, such as 90%.

[0111] In some embodiments, if the target task needs to be completed as quickly as possible, the weight of the second preset time can be set higher. For example, if the dust removal task needs to be completed within 30 minutes, the weight of the second preset time can be set to 100%, 90%, 80%, etc. In some embodiments, if there is sufficient time to complete the target task, for example, if the dust removal task needs to be completed within half a day, the weight of the first preset time and the second preset time can be set to 50% each.

[0112] In some embodiments of this specification, the environmental prediction model 500 predicts the subsequent environmental change trend 540. When adjusting the working parameters of the fog cannon device, this environmental change trend 540 is taken into account, which can make the adjustment effect of the fog cannon device better meet the operational requirements in the future and improve the intelligence level of the fog cannon device.

[0113] Figure 6 This is a schematic diagram of a relationship spectrum based on some embodiments of this specification.

[0114] In some embodiments, the main fog cannon device can obtain a trained graph neural network model and a construction layout map of the site from an IoT platform, and construct a relationship graph based on the received data; output the effect score of the corresponding area based on the edge of the relationship graph; if the effect score of one or more areas does not meet the preset conditions, adjust the working parameters of the two fog cannon devices adjacent to the one or more areas, and predict the effect score of the one or more areas based on the adjusted working parameters of the fog cannon devices, until the effect score of all areas meets the preset conditions, and then transmit the corresponding working parameters at this time from the main fog cannon device to the other fog cannon devices.

[0115] In some embodiments, the relational graph may include multiple nodes (such as...) Figure 6 The nodes shown are A, B, C, D, and E, where node A corresponds to the main fog cannon device) and multiple edges (such as...). Figure 6 (As shown by the connecting lines in the diagram).

[0116] A node represents a fog cannon device. In some embodiments, one node represents one fog cannon device.

[0117] Node features can include operating parameters of the fog cannon device, such as spray direction, angle, and spray power. Adjacent nodes can be connected by edges. Adjacent nodes are adjacent fog cannon devices; nodes less than a preset distance threshold are considered adjacent (e.g., ...). Figure 6 In the example, node B is less than a preset distance threshold from nodes A, D, and E, but greater than a preset distance threshold from node C. The adjacent nodes of node B are nodes A, D, and E, excluding node C. The attributes of the edges reflect the relationships between the nodes.

[0118] Edge features include the distance between fog cannon devices and the construction layout of the area between fog cannon devices (whether there is construction, type of construction, etc.).

[0119] In some embodiments, the main fog cannon device can process the relationship graph based on a graph neural network model, and output the effect score of the corresponding region based on the edges of the relationship graph. For example, by processing the relationship graph through a graph neural network, the effect score of the region between node A and node B can be output based on the distance between node A and node B, the construction layout of the region between fog cannon devices, and the working parameters of the fog cannon devices corresponding to node A and node B.

[0120] In some embodiments, if the effect scores of one or more areas do not meet the preset conditions, the operating parameters of two adjacent fog cannon devices are adjusted, and then prediction is performed using a graph neural network until the effect scores of all areas meet the preset conditions. The operating parameters at the point where the preset conditions are met are then transmitted; that is, the operating parameters corresponding to each fog cannon device at this time are transmitted from the main fog cannon device to the other fog cannon devices. The method for determining the main fog cannon device and the specific transmission method can be found in [reference needed]. Figure 1 The corresponding explanation.

[0121] The preset conditions are preset standards, which can be greater than a specific score threshold (e.g., an effect score greater than 80 points). In some embodiments, different types of fog cannon devices can have different preset conditions.

[0122] For example, if Figure 6 If the area between node A and node B does not meet the preset conditions, the operating parameters of the fog cannon devices corresponding to adjacent nodes A and B in that area will be adjusted based on the effect prediction model (see [link to adjustment method] for details). Figure 4 The process continues until the area between node A and node B meets the preset conditions. Based on the target parameters determined by the effect prediction model at this time, the data can be transmitted from node A (main fog cannon device) to node B, node C, node D, and node E (other fog cannon devices).

[0123] The graph neural network model can construct a map based on the site's construction layout map and combine it with the effect prediction model to obtain the effect score of each area. This allows for targeted and precise control and coordination of the operation of fog cannon devices in each area, further improving the dust suppression effect and operational efficiency of the fog cannon devices in each area.

[0124] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

[0125] Furthermore, this specification uses specific terms to describe embodiments thereof. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "an embodiment," "one embodiment," or "an alternative embodiment" in different locations throughout this specification do not necessarily refer to the same embodiment. Moreover, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0126] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this specification are not intended to limit the order of the processes and methods described herein. Although various examples have been discussed in the foregoing disclosure of some embodiments of the invention that are currently considered useful, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the spirit and scope of the embodiments described herein. For example, while the system components described above can be implemented using hardware devices, they can also be implemented solely using software solutions, such as installing the described system on existing servers or mobile devices.

[0127] Similarly, it should be noted that, in order to simplify the description disclosed herein and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of embodiments in this specification may sometimes combine multiple features into a single embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the subject matter of this specification requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of a single embodiment disclosed above.

[0128] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of embodiments are modified in some examples with the terms "approximately," "approximately," or "generally." Unless otherwise stated, "approximately," "approximately," or "generally" indicates that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may be changed depending on the characteristics required by individual embodiments. In some embodiments, numerical parameters should take into account specified significant digits and employ a general method of digit reservation. Although the numerical ranges and parameters used to confirm their breadth of range in some embodiments of this specification are approximate values, in specific embodiments, such values ​​are set as precisely as feasible.

[0129] For each patent, patent application, patent application publication, and other material such as articles, books, specifications, publications, and documents referenced in this specification, the entire contents of which are incorporated herein by reference. This excludes historical application documents that are inconsistent with or conflict with the content of this specification, as well as documents that limit the broadest scope of the claims in this specification (currently or subsequently appended to this specification). It should be noted that in the event of any inconsistency or conflict between the descriptions, definitions, and / or terminology used in the supplementary materials to this specification and the content of this specification, the descriptions, definitions, and / or terminology used in this specification shall prevail.

[0130] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A smart fog cannon device, characterized in that, include: Spray generating device, base, control device, interaction device, and detection device; The spray generating device is rotatably connected to the base via a rotating shaft, which is controlled to rotate by a motor; the control device and the interaction device are installed in the base and are communicatively connected; the detection device is installed on a positioning rod, which is also installed on the base. The spray generating device includes at least a water supply device, an atomizer, a fan, and a spray launcher; the motor, the fan, and the atomizer are communicatively connected to the control device and are used to operate based on control commands and operating parameters sent by the control device. The control device includes a controller and a processor, the processor being configured to: generate the operating parameters based on input data received from the interactive device, and generate the control commands through the controller; The interactive device is used to receive and display the operating parameters generated by the processor; The detection device includes a device detection device, which is used to: if a target device is detected within a preset range, send reminder information to the processor and the interactive device respectively; The target device includes other fog cannon devices, and the processor is further configured to: Send linkage information to the interactive devices of the other fog cannon devices and receive feedback information; Based on the processing effect scores of multiple fog cannon devices, the main fog cannon device is determined. The processing effect scores are generated by an effect prediction model, which is a machine learning model. The main fog cannon device is used for: Based on the feedback information, a relationship graph is constructed using a graph neural network model, and the effect scores of the regions between the fog cannon devices are determined. The graph neural network model is a machine learning model. Based on the effect score, operating parameters for multiple fog cannon devices are generated, and control commands corresponding to the operating parameters of each fog cannon device are sent to the corresponding fog cannon device.

2. The apparatus as claimed in claim 1, characterized in that, The target device includes a site monitoring device, and the equipment detection device and the processor are further used for: The equipment detection device detects that the site monitoring device is located within the preset range and sends the reminder information to the processor; The processor acquires environmental data detected by the site monitoring device through an Internet of Things (IoT) system. The processor adjusts the operating parameters based on the environmental data.

3. The apparatus as described in claim 2, characterized in that, The processor is further used for: The processor obtains weather data from a third-party platform; Based on the weather data and combined with the environmental data, predict the trend of environmental change; Adjust the operating parameters based on the aforementioned environmental change trends.

4. A control method for the intelligent fog cannon device according to any one of claims 1 to 3, characterized in that, The method is applied to a control device, a spray generating device, an interaction device, and a detection device. The control method is executed by the processor and includes: The system receives a reminder message sent by the detection device, the reminder message being generated in response to the detection device detecting that a target device is present within a preset range; The system receives input data from the interactive device, generates operating parameters, and generates control commands through the controller. The control commands and operating parameters are sent to the spray generating device; Sending the operating parameters to the interactive device includes: Send linkage information to the interactive devices of the other fog cannon devices and receive feedback information; Based on the processing effect scores of multiple fog cannon devices, the main fog cannon device is determined. The processing effect scores are generated by an effect prediction model, which is a machine learning model. The main fog cannon device is used for: Based on the feedback information, a relationship graph is constructed using a graph neural network model, and the effect scores of the regions between the fog cannon devices are determined. The graph neural network model is a machine learning model. Based on the effect score, operating parameters for multiple fog cannon devices are generated, and control commands corresponding to the operating parameters of each fog cannon device are sent to the corresponding fog cannon device.

5. The control method as described in claim 4, characterized in that, The receiving of the reminder information sent by the detection device, the reminder information being generated based on the detection device detecting that a target device is present within a preset range, includes: The device receives a reminder message sent by the detection device, which is generated based on the detection device detecting that a site monitoring device is located within the preset range. The environmental data detected by the site monitoring device is obtained through an Internet of Things (IoT) system; The operating parameters are adjusted based on the environmental data.

6. The control method as described in claim 5, characterized in that, The adjustment of the operating parameters based on the environmental data includes: Obtain weather data from third-party platforms; Based on the weather data and combined with the environmental data, predict the trend of environmental change; Adjust the operating parameters based on the aforementioned environmental change trends.

7. A control system for an intelligent fog cannon device, comprising a processor, the processor being configured to execute the control method for the intelligent fog cannon device according to any one of claims 4 to 6.

8. A computer-readable storage medium storing computer instructions, wherein when a computer reads the computer instructions in the storage medium, the computer executes the control method of the intelligent fog cannon device as described in any one of claims 4 to 6.

Images