Energy-saving type mobile dust removal equipment and working method thereof

Abstract

The invention belongs to the technical field of dust removal, and provides energy-saving type movable dust removal equipment and a working method thereof. The equipment comprises a controller, a camera, a laser detector and an adsorption assembly, wherein the adsorption assembly comprises an adsorption head and an adsorption pump; the controller is electrically connected with the camera, the laser detector and the adsorption assembly. Compared with a working mode of mobile dust removal equipment with a fixed adsorption rate in the prior art, the corresponding dynamic target adsorption rate can be determined according to the actual dust characteristics of the to-be-cleaned area, so that the adsorption rate of the mobile dust removal equipment can be dynamically adjusted, and the power consumption of the mobile dust removal equipment is effectively reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of dust removal, and in particular to an energy-saving mobile dust removal device and a working method thereof. Background Art

[0002] Mobile dust removal equipment is a type of equipment used to remove dust, lint and other dusty materials in industrial production environments. These devices can efficiently collect dusty materials to ensure a clean working environment and the health of workers. Mobile dust removal equipment can be moved by people or it can move on its own.

[0003] However, the adsorption power of existing mobile dust removal equipment is mostly fixed and cannot be adaptively adjusted according to the actual situation of the cleaning area, resulting in generally high energy consumption of mobile dust removal equipment. The present invention aims to adjust the adsorption control strategy of mobile dust removal equipment to reduce its energy consumption. Summary of the invention

[0004] In order to solve the technical problems existing in the above-mentioned background technology, the present invention provides an energy-saving mobile dust removal device, a working method, an electronic device, a computer storage medium and a computer program product.

[0005] The present invention provides an energy-saving mobile dust removal device, which includes a controller, a camera, a laser detector, and an adsorption component, wherein the adsorption component includes an adsorption head and an adsorption pump; the controller is electrically connected to the camera, the laser detector, and the adsorption component respectively; wherein,

[0006] The camera is used to capture high-definition image data of the area to be cleaned and transmit the high-definition image data to the controller;

[0007] The laser detector is used to perform laser detection on the area to be cleaned according to the control instruction of the controller and transmit the laser detection data to the controller;

[0008] The controller is used to implement the following steps:

[0009] Receiving the high-definition image data, and analyzing the high-definition image data to determine the dust recognition difficulty of the area to be cleaned;

[0010] If the dust recognition difficulty is higher than the difficulty threshold, the control instruction is sent to the laser detector, and the control instruction is used to trigger the laser detector to perform laser detection on the area to be cleaned, and obtain the dust characteristics of the area to be cleaned according to the laser detection data analysis; if the dust recognition difficulty is not higher than the difficulty threshold, the dust characteristics of the area to be cleaned are predicted according to the high-definition image data;

[0011] generating a target adsorption rate according to the dust characteristics, and sending the target adsorption rate to the adsorption component;

[0012] The adsorption component is used to perform adsorption operation according to the target adsorption rate.

[0013] In some embodiments, the dust recognition difficulty of the area to be cleaned is obtained according to the analysis of the high-definition image data, including:

[0014] Extracting first appearance features of the ground surface of the area to be cleaned and equipment type data from the high-definition image data, and predicting second appearance features of the dust based on the equipment type data;

[0015] The similarity between the second appearance feature and the first appearance feature is calculated, and the dust recognition difficulty is determined according to the similarity, where the dust recognition difficulty is positively correlated with the similarity.

[0016] In some embodiments, the predicting of the second appearance feature of dust according to the device type data includes:

[0017] crawling out a plurality of on-site image data containing the device of the type according to the device type data, and extracting a third appearance feature of dust from each of the on-site image data;

[0018] The third appearance features are fused to obtain the second appearance features.

[0019] In some embodiments, the dust characteristics of the area to be cleaned are obtained according to the analysis of the laser detection data, including:

[0020] The intensity of scattered light corresponding to the emitted laser is calculated according to the laser detection data, and the first dust level of the area to be cleaned is calculated according to the scattered light intensity;

[0021] Calculate the fluorescence spectrum intensity according to the laser detection data, and calculate the first oil film thickness of the area to be cleaned according to the fluorescence spectrum intensity;

[0022] The first dust level and the first oil film thickness constitute the dust characteristics of the area to be cleaned.

[0023] In some embodiments, predicting dust characteristics of the area to be cleaned based on the high-definition image data includes:

[0024] Identify and obtain a regional image of the area to be cleaned from the high-definition image data, and determine and obtain a second dust level of the area to be cleaned according to the second appearance feature and the regional image;

[0025] Extracting the overall appearance features of the area to be cleaned based on the area image, wherein the overall appearance features include color features and texture features, and inputting the second appearance features and the overall appearance features into an oil film thickness prediction model to obtain a second oil film thickness;

[0026] The second dust level and the second oil film thickness are constituted as the dust characteristics of the area to be cleaned.

[0027] In some embodiments, generating a target adsorption rate according to the dust characteristics includes:

[0028] Extracting the oil film area from the regional image and predicting the oil film viscosity based on the equipment type data;

[0029] Using a dust viscosity prediction model to process the oil film area, the oil film viscosity and the dust characteristics to obtain a predicted ground dust viscosity grade;

[0030] The target adsorption rate is determined based on the ground dust viscosity level and a preset control relationship.

[0031] The present invention also provides a working method of an energy-saving mobile dust removal device, the method comprising the following steps:

[0032] Sending a dust removal task to the started mobile dust removal device, wherein the dust removal task includes a target dust removal route;

[0033] The mobile dust removal device moves along the target dust removal route and uses a camera to capture high-definition image data of the area to be cleaned;

[0034] The difficulty of dust recognition in the area to be cleaned is obtained according to the high-definition image data analysis; if the dust recognition difficulty is higher than the difficulty threshold, a control instruction is sent to the laser detector, the control instruction is used to trigger the laser detector to perform laser detection on the area to be cleaned, and the dust characteristics of the area to be cleaned are obtained according to the laser detection data analysis; if the dust recognition difficulty is not higher than the difficulty threshold, the dust characteristics of the area to be cleaned are obtained according to the high-definition image data prediction;

[0035] A target adsorption rate is generated according to the dust characteristics, and the adsorption component is controlled to adjust to the target adsorption rate.

[0036] The present invention also provides an electronic device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor implements the steps of any one of the above methods when executing the computer program.

[0037] The present invention also provides a computer storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of any one of the above methods can be implemented.

[0038] The present invention also provides a computer program product, wherein the computer program product includes computer program codes, and when the computer program codes are executed by a processor of an electronic device, the steps of any one of the above methods are implemented.

[0039] The beneficial effect of the present invention is that compared with the working mode of the mobile dust removal device with a fixed adsorption rate in the prior art, the present invention can determine the corresponding dynamic target adsorption rate according to the actual dust characteristics of the area to be cleaned, so that the adsorption rate of the mobile dust removal device can be dynamically adjusted, effectively reducing the power consumption of the mobile dust removal device. Moreover, by switching the laser or image recognition method to obtain dust characteristics according to the difficulty of dust recognition, the power consumption of the mobile dust removal device can be further reduced and the recognition accuracy of dust characteristics can be ensured. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 It is a structural schematic diagram of an energy-saving mobile dust removal device disclosed in an embodiment of the present invention;

[0042] Figure 2 It is a basic structural diagram of the dust viscosity prediction model disclosed in the embodiment of the present invention;

[0043] Figure 3 It is a flow chart of a working method of an energy-saving mobile dust removal device disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0044] The following is a description of the implementation of the present application by specific specific embodiments. People familiar with the technology can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0045] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0046] like Figure 1 As shown, an embodiment of the present invention discloses an energy-saving mobile dust removal device, which includes a controller, a camera, a laser detector, and an adsorption component, wherein the adsorption component includes an adsorption head and an adsorption pump; the controller is electrically connected to the camera, the laser detector, and the adsorption component respectively; wherein,

[0047] The camera is used to capture high-definition image data of the area to be cleaned and transmit the high-definition image data to the controller;

[0048] The laser detector is used to perform laser detection on the area to be cleaned according to the control instruction of the controller and transmit the laser detection data to the controller;

[0049] The controller is used to implement the following steps:

[0050] Receiving the high-definition image data, and analyzing the high-definition image data to determine the dust recognition difficulty of the area to be cleaned;

[0051] If the dust recognition difficulty is higher than the difficulty threshold, the control instruction is sent to the laser detector, and the control instruction is used to trigger the laser detector to perform laser detection on the area to be cleaned, and obtain the dust characteristics of the area to be cleaned according to the laser detection data analysis; if the dust recognition difficulty is not higher than the difficulty threshold, the dust characteristics of the area to be cleaned are predicted according to the high-definition image data;

[0052] generating a target adsorption rate according to the dust characteristics, and sending the target adsorption rate to the adsorption component;

[0053] The adsorption component is used to perform adsorption operation according to the target adsorption rate.

[0054] The adsorption component of the energy-saving mobile dust removal device of the present invention does not perform adsorption operations according to a fixed adsorption rate, but performs adsorption operations according to a dynamically generated target adsorption rate. Specifically, the mobile dust removal device is turned on to perform dust removal and cleaning operations, wherein the configured camera shoots the area to be cleaned in front, and transmits the captured high-definition image data to the controller. The controller analyzes the dust recognition difficulty of the area to be cleaned based on the high-definition image data. When the dust recognition difficulty is higher than the difficulty threshold, the controller switches to use a laser detector, and analyzes and obtains the dust characteristics of the area to be cleaned based on the laser detection data of the area to be cleaned detected by the laser detector. When the dust recognition difficulty is not higher than the difficulty threshold, the dust characteristics of the area to be cleaned are predicted based on the high-definition image data. Then, based on the obtained dust characteristics, a target adsorption rate is generated, and then the adsorption component performs adsorption operations according to the target adsorption rate. The adsorption pump is responsible for stimulating air flow to generate suction, thereby achieving the adsorption of dust at the adsorption head.

[0055] Compared with the working mode of the mobile dust removal equipment with a fixed adsorption rate in the prior art, the present invention can determine the corresponding dynamic target adsorption rate according to the actual dust characteristics of the area to be cleaned, so as to dynamically adjust the adsorption rate of the mobile dust removal equipment and effectively reduce the power consumption of the mobile dust removal equipment. Moreover, by switching the laser or image recognition method to obtain dust characteristics according to the difficulty of dust recognition, the power consumption of the mobile dust removal equipment can be further reduced and the recognition accuracy of dust characteristics can be ensured.

[0056] It should be noted that the camera and the laser detector are arranged on the general front side of the mobile dust removal device to achieve alignment with the area to be cleaned, but the present invention does not limit their specific layout positions. The adsorption head of the adsorption assembly can be held by the cleaning personnel or controlled by the mobile dust removal device itself, but in either case, it is preferred that the adsorption head can change its relative position relationship with the body of the mobile dust removal device, thereby achieving cleaning of a larger area.

[0057] In some embodiments, the dust recognition difficulty of the area to be cleaned is obtained according to the analysis of the high-definition image data, including:

[0058] Extracting first appearance features of the ground surface of the area to be cleaned and equipment type data from the high-definition image data, and predicting second appearance features of the dust based on the equipment type data;

[0059] The similarity between the second appearance feature and the first appearance feature is calculated, and the dust recognition difficulty is determined according to the similarity, where the dust recognition difficulty is positively correlated with the similarity.

[0060] In this embodiment, the mobile dust removal device of the present invention preferably extracts the dust features of the ground in the area to be cleaned by image recognition, because it has lower energy consumption and better energy saving performance than using a laser detector. However, there is a certain probability of failure when using image recognition to extract the dust features of the ground, so it is necessary to estimate the difficulty of dust recognition in advance, and when the dust recognition difficulty is too high, switch the laser detector in time to detect the dust features of the ground, so as not to affect the cleaning efficiency of the mobile dust removal device.

[0061] In view of the above situation, the present invention is set to extract the first appearance feature of the ground in the area to be cleaned and the equipment type data from the high-definition image data taken by the camera, and then predict the second appearance feature of the dust on the ground according to the equipment type data, and further calculate the similarity between the second appearance feature of the dust and the first appearance feature of the ground. When the similarity between the two is higher, it indicates that the ground dust in the area to be cleaned is closer to the color, texture, etc. of the ground itself, and the recognition difficulty is higher. Correspondingly, the dust recognition difficulty is set to a larger value; and when the similarity between the two is lower, it indicates that the ground dust in the area to be cleaned is more different from the color, texture, etc. of the ground itself, and the recognition difficulty is lower. Correspondingly, the dust recognition difficulty is set to a smaller value.

[0062] Therefore, the present invention realizes an accurate prediction of the difficulty of identifying dust on the ground in the area to be cleaned by analyzing the similarity between the appearance of the ground in the area to be cleaned and the appearance of the dust (prediction value). The similarity is calculated using existing methods, such as Euclidean distance, cosine distance, etc.

[0063] In some embodiments, the predicting of the second appearance feature of dust according to the device type data includes:

[0064] crawling out a plurality of on-site image data containing the device of the type according to the device type data, and extracting a third appearance feature of dust from each of the on-site image data;

[0065] The third appearance features are fused to obtain the second appearance features.

[0066] In this embodiment, the dust in the area to be cleaned includes not only conventional fine sand and dust, but also waste generated by the equipment in the area during operation, such as metal shavings generated by lathes, cotton dust or hemp dust generated by spinning machines, etc. If the second appearance feature of the dust is input manually, it will take a lot of manpower.

[0067] In view of the above situation, the present invention crawls out several on-site image data containing the type of equipment in the network or local database according to the equipment type data, extracts the third appearance feature of dust from these on-site image data, and then integrates the third appearance features corresponding to multiple on-site image data to fuse (for example, calculate the mean of the features) to obtain the second appearance feature. This realizes the automatic acquisition of the second appearance feature of dust, which can especially improve the acquisition efficiency of the second appearance feature when the types of equipment placed in different areas to be cleaned are different.

[0068] In some embodiments, the dust characteristics of the area to be cleaned are obtained according to the analysis of the laser detection data, including:

[0069] The intensity of scattered light corresponding to the emitted laser is calculated according to the laser detection data, and the first dust level of the area to be cleaned is calculated according to the scattered light intensity;

[0070] Calculate the fluorescence spectrum intensity according to the laser detection data, and calculate the first oil film thickness of the area to be cleaned according to the fluorescence spectrum intensity;

[0071] The first dust level and the first oil film thickness constitute the dust characteristics of the area to be cleaned.

[0072] In this embodiment, the present invention mainly determines the adsorption rate of the adsorption component based on the dust level in the area to be cleaned. At the same time, the presence of oil on the ground will increase the viscosity of the combination of oil and dust, resulting in increased adsorption difficulty. Therefore, the present invention analyzes the adsorption rate that should be adopted based on both the dust level and the oil film thickness.

[0073] The dust level and oil film thickness can be obtained through laser detection technology. Specifically, the laser detector emits a laser of a specific wavelength to the area to be cleaned. The laser irradiates the ground, causing the dust particles on the ground to scatter the laser light. The intensity of the scattered light is positively correlated with the number of dust particles. Therefore, the first dust level of the area to be cleaned is calculated based on the intensity of the scattered light.

[0074] At the same time, the thickness of the oil film on the ground can also be detected by laser induced fluorescence technology (LIF). Specifically, the laser detector emits laser to the area to be cleaned. If there is oil on the ground, the laser light will trigger the oil substances in the oil to emit fluorescence. The fluorescence signal is collected and the corresponding fluorescence spectrum data can be obtained after photoelectric conversion. The fluorescence spectrum is directly related to the molecular structure of the substance. The thickness of the oil film can be estimated by the intensity of the fluorescence spectrum, that is, the first oil film thickness mentioned above.

[0075] Correspondingly, the laser detection data includes scattered light intensity and fluorescence spectrum intensity.

[0076] In some embodiments, predicting dust characteristics of the area to be cleaned based on the high-definition image data includes:

[0077] Identify and obtain a regional image of the area to be cleaned from the high-definition image data, and determine and obtain a second dust level of the area to be cleaned according to the second appearance feature and the regional image;

[0078] Extracting the overall appearance features of the area to be cleaned based on the area image, wherein the overall appearance features include color features and texture features, and inputting the second appearance features and the overall appearance features into an oil film thickness prediction model to obtain a second oil film thickness;

[0079] The second dust level and the second oil film thickness are constituted as the dust characteristics of the area to be cleaned.

[0080] In this embodiment, the dust level and oil film thickness can also be obtained through image recognition technology. Specifically, through the second appearance feature of the dust in the area to be cleaned determined above, dust particles can be identified from the area image corresponding to the area to be cleaned, and then the second dust level can be estimated. Since the oil film thickness is difficult to be directly identified through image recognition technology, the present invention identifies the overall appearance features of the area to be cleaned respectively, and then inputs the second appearance features of the dust obtained above together with the overall appearance features into a pre-constructed oil film thickness prediction model, and then predicts the second oil film thickness. Among them, the second appearance features of the dust can be used to determine the color, particle size, etc. of the dust, while the overall appearance features are used to characterize the composite color features after the dust and the oil film are mixed, as well as the texture features (i.e., the degree of concavity) represented by the dust (such as metal chips) exposed above the oil film. The trained oil film thickness prediction model can predict the corresponding second oil film thickness.

[0081] In some embodiments, generating a target adsorption rate according to the dust characteristics includes:

[0082] Extracting the oil film area from the regional image and predicting the oil film viscosity based on the equipment type data;

[0083] Using a dust viscosity prediction model to process the oil film area, the oil film viscosity and the dust characteristics to obtain a predicted ground dust viscosity grade;

[0084] The target adsorption rate is determined based on the ground dust viscosity level and a preset control relationship.

[0085] In this embodiment, the present invention sets the target adsorption rate in relation to the viscosity grade of the mixture of dust and oil film in the area to be cleaned, that is, the higher the viscosity grade of the mixture, the higher the target adsorption rate is set, that is, the adsorption component is controlled to use a stronger suction force to clean the above-mentioned mixture with high viscosity, thereby improving the adsorption efficiency; and when the viscosity grade of the mixture is lower, the target adsorption rate is set lower, that is, the adsorption component is controlled to use a gentler suction force to clean the above-mentioned mixture with low viscosity, thereby reducing the energy consumption of the mobile dust removal equipment.

[0086] The prediction of the viscosity grade of the mixture is specifically as follows: the oil film area is extracted from the regional image of the area to be cleaned obtained above, and then the possible grease type in the area to be cleaned can be predicted based on the equipment type data, so as to determine the corresponding oil film viscosity. For example, if the A device in the area to be cleaned uses SAE20 engine oil, and the B device in another area to be cleaned uses SAE50 engine oil, the viscosity grade of SAE50 engine oil is higher than that of SAE20 engine oil. The dust viscosity prediction model is used to process the oil film area, oil film viscosity and the dust characteristics obtained above (i.e., the first dust magnitude and the first oil film thickness, or the second dust magnitude and the second oil film thickness) to obtain the predicted ground dust viscosity grade. Among them, the higher the oil film viscosity, the higher the corresponding ground dust viscosity grade; and the smaller the oil film area, the more dust, and the thicker the oil film, the higher the ground dust viscosity grade. Therefore, each training data is labeled based on the above correspondence, and then the labeled training data is used to train the dust viscosity prediction model.

[0087] like Figure 2 As shown, the oil film thickness prediction model and the dust viscosity prediction model are preferably constructed based on a generative adversarial network, mainly including a generator and a discriminator. Generator: The task of the generator is to generate data from random noise, and these data imitate the distribution of real data as much as possible. The generator is usually composed of one or more neural network layers, which can be a fully connected layer, a convolutional layer or other types of network layers. The goal of the generator is to generate more and more real data to "fool" the discriminator. During the training process, the generator continuously optimizes the data it generates to reduce the probability of the discriminator's correct classification. Discriminator: The task of the discriminator is to distinguish between the false data generated by the generator and the real data. It is also composed of one or more neural network layers, and its structure usually corresponds to the generator, but the weights are different. The goal of the discriminator is to accurately identify the real data and the generated data to maximize the probability of their correct classification. It should be noted that the present invention does not limit the specific construction and training process and method of the oil film thickness prediction model and the dust viscosity prediction model.

[0088] like Figure 3As shown, the embodiment of the present invention also discloses a working method of an energy-saving mobile dust removal device, the method comprising the following steps:

[0089] Sending a dust removal task to the started mobile dust removal device, wherein the dust removal task includes a target dust removal route;

[0090] The mobile dust removal device moves along the target dust removal route and uses a camera to capture high-definition image data of the area to be cleaned;

[0091] The difficulty of dust recognition in the area to be cleaned is obtained according to the high-definition image data analysis; if the dust recognition difficulty is higher than the difficulty threshold, a control instruction is sent to the laser detector, the control instruction is used to trigger the laser detector to perform laser detection on the area to be cleaned, and the dust characteristics of the area to be cleaned are obtained according to the laser detection data analysis; if the dust recognition difficulty is not higher than the difficulty threshold, the dust characteristics of the area to be cleaned are obtained according to the high-definition image data prediction;

[0092] A target adsorption rate is generated according to the dust characteristics, and the adsorption component is controlled to adjust to the target adsorption rate.

[0093] The method in this embodiment adopts all the technical solutions of the above embodiments, and therefore has at least all the beneficial effects brought by the technical solutions of the above embodiments, which will not be described one by one here.

[0094] An embodiment of the present invention further discloses an electronic device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor implements the steps of any one of the above methods when executing the computer program.

[0095] The embodiment of the present invention further discloses a computer storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of any one of the above methods can be implemented.

[0096] An embodiment of the present invention further discloses a computer program product, wherein the computer program product includes computer program codes, and when the computer program codes are executed by a processor of an electronic device, the steps of any one of the above methods are implemented.

[0097] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0098] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0099] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0100] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention.

Claims

1. An energy-saving mobile dust removal device, characterized in that : The device includes a controller, a camera, a laser detector, and an adsorption component, wherein the adsorption component includes an adsorption head and an adsorption pump; the controller is electrically connected to the camera, the laser detector, and the adsorption component respectively; wherein, The camera is used to capture high-definition image data of the area to be cleaned and transmit the high-definition image data to the controller; The laser detector is used to perform laser detection on the area to be cleaned according to the control instruction of the controller and transmit the laser detection data to the controller; The controller is used to implement the following steps: Receiving the high-definition image data, and analyzing the high-definition image data to determine the dust recognition difficulty of the area to be cleaned; If the dust recognition difficulty is higher than the difficulty threshold, the control instruction is sent to the laser detector, and the control instruction is used to trigger the laser detector to perform laser detection on the area to be cleaned, and obtain the dust characteristics of the area to be cleaned according to the laser detection data analysis; if the dust recognition difficulty is not higher than the difficulty threshold, the dust characteristics of the area to be cleaned are predicted according to the high-definition image data; generating a target adsorption rate according to the dust characteristics, and sending the target adsorption rate to the adsorption component; The adsorption component is used to perform adsorption operation according to the target adsorption rate.

2. The energy-saving mobile dust removal device according to claim 1, characterized in that: The difficulty of dust identification in the area to be cleaned is obtained based on the analysis of the high-definition image data, including: Extracting first appearance features of the ground surface of the area to be cleaned and equipment type data from the high-definition image data, and predicting second appearance features of the dust based on the equipment type data; The similarity between the second appearance feature and the first appearance feature is calculated, and the dust recognition difficulty is determined according to the similarity, where the dust recognition difficulty is positively correlated with the similarity.

3. The energy-saving mobile dust removal device according to claim 2 is characterized in that: The second appearance feature of the dust is predicted based on the device type data, including: crawling out a plurality of on-site image data containing the device of the type according to the device type data, and extracting a third appearance feature of dust from each of the on-site image data; The third appearance features are fused to obtain the second appearance features.

4. The energy-saving mobile dust removal device according to claim 3 is characterized in that: The dust characteristics of the area to be cleaned are obtained based on the analysis of the laser detection data, including: The intensity of scattered light corresponding to the emitted laser is calculated according to the laser detection data, and the first dust level of the area to be cleaned is calculated according to the scattered light intensity; Calculate the fluorescence spectrum intensity according to the laser detection data, and calculate the first oil film thickness of the area to be cleaned according to the fluorescence spectrum intensity; The first dust level and the first oil film thickness constitute the dust characteristics of the area to be cleaned.

5. The energy-saving mobile dust removal device according to claim 4, characterized in that: The dust characteristics of the area to be cleaned are predicted based on the high-definition image data, including: Identify and obtain a regional image of the area to be cleaned from the high-definition image data, and determine and obtain a second dust level of the area to be cleaned according to the second appearance feature and the regional image; Extracting the overall appearance features of the area to be cleaned based on the area image, wherein the overall appearance features include color features and texture features, and inputting the second appearance features and the overall appearance features into an oil film thickness prediction model to obtain a second oil film thickness; The second dust level and the second oil film thickness are constituted as the dust characteristics of the area to be cleaned.

6. The energy-saving mobile dust removal device according to claim 5, characterized in that: Generating a target adsorption rate according to the dust characteristics includes: Extracting the oil film area from the regional image and predicting the oil film viscosity based on the equipment type data; Using a dust viscosity prediction model to process the oil film area, the oil film viscosity and the dust characteristics to obtain a predicted ground dust viscosity grade; The target adsorption rate is determined based on the ground dust viscosity level and a preset control relationship.

7. A working method of the energy-saving mobile dust removal device according to any one of claims 1 to 6, characterized in that: The method comprises the following steps: Sending a dust removal task to the started mobile dust removal device, wherein the dust removal task includes a target dust removal route; The mobile dust removal device moves along the target dust removal route and uses a camera to capture high-definition image data of the area to be cleaned; deriving the dust recognition difficulty of the area to be cleaned according to the high-definition image data analysis; if the dust recognition difficulty is higher than the difficulty threshold, sending a control instruction to the laser detector, the control instruction is used to trigger the laser detector to perform laser detection on the area to be cleaned, and deriving the dust characteristics of the area to be cleaned according to the laser detection data analysis; If the dust recognition difficulty is not higher than the difficulty threshold, predicting the dust characteristics of the area to be cleaned according to the high-definition image data; A target adsorption rate is generated according to the dust characteristics, and the adsorption component is controlled to adjust to the target adsorption rate.

8. An electronic device, comprising: At least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the method according to claim 7 is implemented when the processor executes the computer program.

9. A computer storage medium, wherein the computer readable storage medium stores a computer program, characterized in that: When the computer program is executed by a processor, the method according to claim 7 is implemented.

10. A computer program product, comprising computer program code, characterized in that: When the computer program code is executed by a processor of an electronic device, the method according to claim 7 is implemented.

Images