Remote control method of cargo compartment intelligent cleaning robot

Abstract

The invention relates to the technical field of car tipplers, in particular to a remote control method of an intelligent cleaning robot for a cargo compartment. Comprising the steps of generating various cleaning scenes according to historical cargo compartment parameters, and sequentially generating control models of the cleaning scenes; generating an initial cleaning plan according to the equipment parameters of the cargo compartment to be cleaned, and generating a plurality of feedback time nodes according to the initial cleaning plan; monitoring data of the cargo compartment to be cleaned are obtained according to the preset feedback time node, and whether a correction instruction is generated or not is judged according to the monitoring data; a plurality of cleaning scenes are set according to cargo compartment parameters and parameters for carrying coal, optimal control strategies under various cleaning scenes are set according to historical parameters, in the cleaning process of a to-be-cleaned cargo compartment, the to-be-cleaned cargo compartment is monitored by setting a plurality of feedback time nodes, and an initial cleaning plan is dynamically corrected according to a correction evaluation value, so that the cleaning efficiency of the to-be-cleaned cargo compartment is improved. Therefore, the cleaning quality of the to-be-cleaned carriage is ensured.

Description

Technical Field

[0001] The present application relates to the technical field of car tipping machines, and in particular to a remote control method for an intelligent cargo compartment cleaning robot. Background Art

[0002] The current method of unloading is to use a dumper. After dumping, there will be varying degrees of residue inside the carriage and at the bottom of the carriage, and the carriage needs to be cleaned. Since it was put into operation, the cleaning of the residual coal in the carriage has been done manually by crawling into the carriage and using primitive cleaning tools such as shovels and brooms. The specific work flow is: workers open the door of the carriage → crawl into the carriage → use shovels and brooms to sweep the residual coal out of the carriage → collect the residual coal piled beside the rails behind the sweeper → transport the residual coal away → reseal the carriage. The manual cleaning method has the following disadvantages:

[0003] 1) There are great safety hazards: cleaning personnel need to open the car door and climb into the car to clean. The labor intensity is high and the cleaning time is tight. There are safety hazards such as mechanical injury or falling from height.

[0004] 2) Poor working environment and high labor intensity: Cleaners work in the carriage for a long time, exposed to dust and noise pollution, which can easily lead to pneumoconiosis. Working in the carriage is hot in summer and cold in winter. Traditional cleaning tools are inefficient and labor-intensive.

[0005] 3) Uneconomical: Manual cleaning cannot guarantee the cleaning quality and timeliness, resulting in high delay costs. Manual cleaning requires opening the car door and resealing it, resulting in unnecessary labor and material costs.

[0006] 4) Not environmentally friendly: Workers create a lot of dust when cleaning the train cargo compartments. At the same time, the remaining coal after cleaning is piled up next to the rails, generating secondary dust, which does not meet environmental protection requirements.

[0007] 5) High labor costs: This type of low-end, high-intensity labor force is mostly older people. As the population structure changes, labor costs will become higher and higher. Summary of the invention

[0008] The purpose of this application is: to solve the above-mentioned technical problems, this application provides a remote control method for an intelligent cargo compartment cleaning robot, aiming to improve the cleaning efficiency of the cargo compartment, reduce the operation and maintenance costs of cleaning, and save human resources.

[0009] In some embodiments of the present application, multiple cleaning scenes are set according to the cargo compartment parameters and the coal transport parameters, and the optimal control strategies for various cleaning scenes are set according to the historical parameters to achieve remote control of the cleaning robot, improve cleaning efficiency, and reduce cleaning costs.

[0010] In some embodiments of the present application, during the cleaning process of the cargo compartment to be cleaned, the cargo compartment to be cleaned is monitored by setting multiple feedback time nodes, and the initial cleaning plan is dynamically corrected according to the corrected evaluation value, so as to ensure the cleaning quality of the compartment to be cleaned. At the same time, the corresponding control model is optimized according to all operating parameters of the cargo compartment to be cleaned during the cleaning cycle, so as to achieve precise control of the cleaning robot and improve the cleaning quality.

[0011] In some embodiments of the present application, when the corrected evaluation value is too large, an operation deviation value is generated by collecting feedback data from the cleaning robot, and an early warning of potential risks of the cleaning robot is issued in a timely manner based on the operation deviation value to avoid operational failures of the cleaning robot and reduce the operation and maintenance costs of the cleaning robot.

[0012] In some embodiments of the present application, a remote control method for a cargo compartment intelligent cleaning robot is provided, comprising:

[0013] Generate multiple cleaning scenarios based on historical cargo compartment parameters, and generate control models for each cleaning scenario in turn;

[0014] Generate an initial cleaning plan according to the equipment parameters of the cargo compartment to be cleaned, and generate multiple feedback time nodes according to the initial cleaning plan;

[0015] Acquire monitoring data of the cargo compartment to be cleaned according to the preset feedback time node, and determine whether to generate correction instructions based on the monitoring data;

[0016] Among them, when generating multiple cleaning scenes, including:

[0017] Establish a cleaning scene sequence A, A = (a1, a2...a i …a n ), where a i is the i-th cleaning scene; n is the number of cleaning scenes.

[0018] In some embodiments of the present application, generating a control model for each cleaning scene includes:

[0019] Set a in sequence according to the cleaning scene sequence A i Clear the scene for the target;

[0020] Establish multiple cleaning sub-areas in the target cleaning scene;

[0021] Set the sub-control strategy of the cleaning robot in each cleaning sub-area;

[0022] Generate a control model for the target cleaning scenario based on all sub-control strategies;

[0023] Generate the control model of each cleaning scene in turn, and establish the control model sequence P;

[0024] P=(p1,p2…p i …p n ), where p i is the control model for the i-th cleaning scene.

[0025] In some embodiments of the present application, an initial cleaning plan is generated according to equipment parameters of the cargo compartment to be cleaned, including:

[0026] Determine the cleaning scene of the cargo compartment to be cleaned according to the equipment parameters of the cargo compartment to be cleaned;

[0027] Select the target control model according to the judgment result;

[0028] Establish a sequence of cleaning sub-areas B, B = (b1, b2...b i …b m ), where bi is the i-th cleaning sub-area in the target cleaning scene; m is the number of cleaning sub-areas in the target control model;

[0029] According to the cleaning sub-area sequence B, a time interval sequence T is established, T = (t1, t2...t i …t m ), where t i To clean sub-area b i The corresponding cleaning time;

[0030] Generate sub-control strategies within each time interval and generate an initial cleaning plan;

[0031] Set the end time node of each time interval as the feedback time node.

[0032] In some embodiments of the present application, determining whether to generate a correction instruction based on monitoring data includes:

[0033] Get the monitoring data of the current feedback time node;

[0034] Establish the time interval sequence T1 of the current feedback time node, T1=(t 11 , t 12 …t 1i ……t 1m1 ), where t 1i is the i-th time interval after the cargo compartment to be cleaned starts cleaning; m1 is the number of time intervals between the start time node of the cargo compartment to be cleaned and the current feedback time node, m1≤m; t 1m1 is the time interval corresponding to the current feedback time node;

[0035] Generate the cleaning evaluation value sequence F of the current feedback time node, F = (f1, f2...f i …f m1 ), where f iis the time interval t 1i The cleaning evaluation value within;

[0036] Generate a modified evaluation value d according to the cleaning evaluation value sequence F;

[0037] Whether to generate a correction instruction is determined based on the correction evaluation value d.

[0038] In some embodiments of the present application, judging whether to generate a correction instruction according to the correction evaluation value d includes:

[0039] Preset a first modified evaluation value threshold D1 and a second modified evaluation value threshold D2;

[0040] If d<D1, no correction instruction is generated at the current feedback time node;

[0041] If D1<d<D2, the current feedback time node generates a first-level correction instruction;

[0042] If d>D2, the current feedback time node generates a secondary correction instruction, and generates an operation deviation value g of the current feedback time node, and determines whether to generate an early warning instruction based on the operation deviation value g.

[0043] In some embodiments of the present application, generating a modified evaluation value d according to the cleaning evaluation value sequence F includes:

[0044]

[0045] Wherein, e1 is the preset first weight coefficient; e2 is the preset second weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; ηf is the average value of all data in the cleaning evaluation value series F; f' is the standard cleaning evaluation value; Y(i) is the selection coefficient; if (f i -f')>0,Y(i)=0; if (f i -f')≤0,Y(i)=-1.

[0046] In some embodiments of the present application, generating a cleaning evaluation value sequence F of the current feedback time node includes:

[0047] Set t in sequence according to the time interval sequence T1 1i is the target time interval;

[0048] Obtain image data in the cleaning sub-area corresponding to the target time interval, and generate a cleaning evaluation value f in the target time interval according to the preprocessing result;

[0049]

[0050] Among them, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; θ is the number of residual points in the cleaning sub-area corresponding to the target time interval; ji is the residual evaluation value of the i-th residual point in the cleaning sub-area corresponding to the target time interval;

[0051] The cleaning evaluation value in each time interval is generated sequentially.

[0052] In some embodiments of the present application, when the running deviation value g of the current feedback time node is fed back, it includes:

[0053] Obtain the feedback data of the cleaning robot at the current feedback time node;

[0054] Generate the running deviation value g of the current feedback time node according to the feedback data;

[0055]

[0056] Among them, e5 is the preset fifth weight coefficient; e6 is the preset sixth weight coefficient; Q5 is the preset fifth fixed coefficient; Q6 is the preset sixth weight coefficient; r is the number of monitoring indicators; βi is the influencing factor of the i-th monitoring indicator; ki is the reference value of the i-th monitoring indicator generated based on the feedback data at the current feedback time node.

[0057] In some embodiments of the present application, when determining whether to generate a warning instruction according to the operation deviation value g, it includes:

[0058] Preset a first operation deviation value threshold G1 and a second operation deviation value threshold G2;

[0059] If g≤G1, no warning instruction is generated at the current feedback time node;

[0060] If G1<g≤G2, the current feedback time node generates a first-level warning instruction;

[0061] If g>G2, the current feedback time node generates a secondary warning instruction.

[0062] In some embodiments of the present application, further comprising:

[0063] Obtain the operation data of the cleaning robot according to the end time node of the initial cleaning plan, and generate an update data packet based on all the operation data;

[0064] modifying the target control model according to the update data packet;

[0065] Update the control model sequence P according to the correction result.

[0066] Compared with the prior art, the remote control method of the intelligent cargo compartment cleaning robot in the embodiment of the present application has the following beneficial effects:

[0067] Multiple cleaning scenarios are set according to the cargo compartment parameters and the coal transport parameters, and the optimal control strategy for various cleaning scenarios is set according to the historical parameters to achieve remote control of the cleaning robot, improve cleaning efficiency and reduce cleaning costs.

[0068] During the cleaning process of the cargo compartment to be cleaned, multiple feedback time nodes are set to monitor the cargo compartment to be cleaned, and the initial cleaning plan is dynamically corrected according to the corrected evaluation value, so as to ensure the cleaning quality of the cargo compartment to be cleaned. At the same time, the corresponding control model is optimized according to all operating parameters of the cargo compartment to be cleaned during the cleaning cycle, so as to achieve precise control of the cleaning robot and improve the cleaning quality.

[0069] When the corrected evaluation value is too large, the feedback data of the cleaning robot is collected to generate an operation deviation value. According to the operation deviation value, the potential risks of the cleaning robot are warned in time to avoid operation failures of the cleaning robot and reduce the operation and maintenance cost of the cleaning robot. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 It is a flow chart of a remote control method of a cargo compartment intelligent cleaning robot in a preferred embodiment of the present application. DETAILED DESCRIPTION

[0071] The specific implementation methods of the present application are further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present application but are not intended to limit the scope of the present application.

[0072] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0073] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0074] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0075] like Figure 1 As shown, a remote control method of a cargo compartment intelligent cleaning robot according to a preferred embodiment of the present application includes:

[0076] S101: Generate multiple cleaning scenarios according to historical cargo compartment parameters, and generate control models for each cleaning scenario in turn;

[0077] S102: generating an initial cleaning plan according to equipment parameters of the cargo compartment to be cleaned, and generating multiple feedback time nodes according to the initial cleaning plan;

[0078] S103: Acquire monitoring data of the cargo compartment to be cleaned according to a preset feedback time node, and determine whether to generate a correction instruction according to the monitoring data;

[0079] Among them, when generating multiple cleaning scenes, including:

[0080] Establish a cleaning scene sequence A, A = (a1, a2...a i …a n ), where a i is the i-th cleaning scene; n is the number of cleaning scenes.

[0081] Specifically, the control model for each cleaning scenario is generated, including:

[0082] Set a in sequence according to the cleaning scene sequence A i Clear the scene for the target;

[0083] Establish multiple cleaning sub-areas in the target cleaning scene;

[0084] Set the sub-control strategy of the cleaning robot in each cleaning sub-area;

[0085] Generate a control model for the target cleaning scenario based on all sub-control strategies;

[0086] Generate the control model of each cleaning scene in turn, and establish the control model sequence P;

[0087] P=(p1,p2…p i …p n ), where p iis the control model for the i-th cleaning scene.

[0088] Specifically, multiple evaluation indicators are established, each of which includes multiple value intervals, and multiple cleaning scenes are generated by randomly combining results of different value intervals of each evaluation indicator. The evaluation indicators include but are not limited to multiple parameters such as cargo compartment size, type of coal being transported, and humidity.

[0089] Specifically, the value ranges of the evaluation indicators in any two cleaning scenes are not exactly the same.

[0090] Specifically, based on the historical cleaning parameters of a single cleaning scene, multiple cleaning sub-areas are set in the cargo compartment corresponding to the cleaning scene, and sub-control strategies are set in each cleaning sub-area. The sub-control strategies include parameters such as the cleaning speed of the cleaning robot, the contact pressure with the inner wall of the cargo compartment, the cleaning time, the suction pressure and the adaptation strategy.

[0091] Specifically, its adaptation strategy refers to the intelligent cleaning robot equipped with a hydraulic suspension mechanism, which can automatically adapt to almost all general open car models. During use, the width and height of the sweeper will be automatically adjusted, so that even when the cleaning device faces an uneven carriage (such as dents, leaks, damages, etc. in the carriage), the cleaning brush can always maintain an effective fit with the carriage and be in the middle of the carriage every time.

[0092] It can be understood that in the above embodiment, multiple cleaning scenes are set according to the cargo compartment parameters and the coal transport parameters, and the optimal control strategy for various cleaning scenes is set according to the historical parameters to achieve remote control of the cleaning robot, improve cleaning efficiency and reduce cleaning costs.

[0093] In a preferred embodiment of the present application, an initial cleaning plan is generated according to the equipment parameters of the cargo compartment to be cleaned, including:

[0094] Determine the cleaning scene of the cargo compartment to be cleaned according to the equipment parameters of the cargo compartment to be cleaned;

[0095] Select the target control model according to the judgment result;

[0096] Establish a sequence of cleaning sub-areas B, B = (b1, b2...b i …b m ), where bi is the i-th cleaning sub-area in the target cleaning scene; m is the number of cleaning sub-areas in the target control model;

[0097] According to the cleaning sub-area sequence B, a time interval sequence T is established, T = (t1, t2...t i …t m ), where t i To clean sub-area b i The corresponding cleaning time;

[0098] Generate sub-control strategies within each time interval and generate an initial cleaning plan;

[0099] Set the end time node of each time interval as the feedback time node.

[0100] Specifically, various evaluation index parameters of the cargo compartment to be cleaned are generated according to the equipment parameters of the cargo compartment to be cleaned, so as to determine the cleaning scene to which the cargo compartment to be cleaned belongs, so as to quickly call the corresponding target control model.

[0101] Specifically, the target control model is used to quickly formulate the initial cleaning plan of the cleaning robot, realize remote control of the cleaning robot, improve cleaning efficiency and reduce cleaning costs.

[0102] Specifically, judging whether to generate a correction instruction based on the monitoring data includes:

[0103] Get the monitoring data of the current feedback time node;

[0104] Establish the time interval sequence T1 of the current feedback time node, T1=(t 11 , t 12 …t 1i ……t 1m1 ), where t 1i is the i-th time interval after the cargo compartment to be cleaned starts cleaning; m1 is the number of time intervals between the start time node of the cargo compartment to be cleaned and the current feedback time node, m1≤m; t 1m1 is the time interval corresponding to the current feedback time node;

[0105] Generate the cleaning evaluation value sequence F of the current feedback time node, F = (f1, f2...f i …f m1 ), where f i is the time interval t 1i The cleaning evaluation value within;

[0106] Generate a modified evaluation value d according to the cleaning evaluation value sequence F;

[0107] Whether to generate a correction instruction is determined based on the correction evaluation value d.

[0108] Specifically, the modified evaluation value d is generated according to the cleaning evaluation value sequence F, including:

[0109]

[0110] Wherein, e1 is the preset first weight coefficient; e2 is the preset second weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; ηf is the average value of all data in the cleaning evaluation value series F; f' is the standard cleaning evaluation value; Y(i) is the selection coefficient; if (f i -f')>0,Y(i)=0; if (f i -f')≤0,Y(i)=-1.

[0111] Specifically, by presetting the first fixed coefficient and the second fixed coefficient, all parameters in the model are normalized so that each parameter is within the same value range.

[0112] Specifically, the larger the correction evaluation value is, the worse the overall cleaning quality of the current cleaning robot is, and the initial cleaning plan needs to be corrected in time to ensure the overall cleaning quality.

[0113] Specifically, the cleaning evaluation value sequence F of the current feedback time node is generated, including:

[0114] Set t in sequence according to the time interval sequence T1 1i is the target time interval;

[0115] Obtain image data in the cleaning sub-area corresponding to the target time interval, and generate a cleaning evaluation value f in the target time interval according to the preprocessing result;

[0116]

[0117] Among them, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; θ is the number of residual points in the cleaning sub-area corresponding to the target time interval; ji is the residual evaluation value of the i-th residual point in the cleaning sub-area corresponding to the target time interval;

[0118] The cleaning evaluation value in each time interval is generated sequentially.

[0119] Specifically, all parameters in the model are normalized by presetting the third fixed coefficient and the fourth fixed coefficient, so that each parameter is within the same value range.

[0120] Specifically, the residual point refers to the point of residual impurities in the corresponding cleaning sub-area generated according to the image data analysis results. The reference value of the residual point can be set according to the area of ​​the residual point and the amount of residual impurities. The larger the reference value, the worse the cleaning quality.

[0121] Specifically, the larger the cleaning evaluation value is, the higher the cleaning quality is.

[0122] Specifically, judging whether to generate a correction instruction according to the correction evaluation value d includes:

[0123] Preset a first modified evaluation value threshold D1 and a second modified evaluation value threshold D2;

[0124] If d<D1, no correction instruction is generated at the current feedback time node;

[0125] If D1<d<D2, the current feedback time node generates a first-level correction instruction;

[0126] If d>D2, the current feedback time node generates a secondary correction instruction, and generates an operation deviation value g of the current feedback time node, and determines whether to generate an early warning instruction based on the operation deviation value g.

[0127] Specifically, the first-level correction instruction means that the current initial cleaning plan may cause residues, and the sub-control strategy of the uncleaned sub-area needs to be corrected to improve the subsequent cleaning efficiency and avoid impurity residues.

[0128] Specifically, the secondary correction instruction means that the current cleaning quality cannot meet the requirements, and the sub-control strategy of the uncleaned sub-area needs to be corrected, and the cleaned sub-area that has been cleaned needs to be re-cleaned to ensure the overall cleaning quality.

[0129] It can be understood that in the above embodiment, during the cleaning process of the cargo compartment to be cleaned, a plurality of feedback time nodes are set to monitor the cargo compartment to be cleaned, and the initial cleaning plan is dynamically corrected according to the corrected evaluation value, so as to ensure the cleaning quality of the compartment to be cleaned. At the same time, the corresponding control model is optimized according to all operating parameters of the cargo compartment to be cleaned during the cleaning cycle, so as to realize precise control of the cleaning robot and improve the cleaning quality.

[0130] In a preferred embodiment of the present application, when the running deviation value g of the current feedback time node is fed back, it includes:

[0131] Obtain the feedback data of the cleaning robot at the current feedback time node;

[0132] Generate the running deviation value g of the current feedback time node according to the feedback data;

[0133]

[0134] Among them, e5 is the preset fifth weight coefficient; e6 is the preset sixth weight coefficient; Q5 is the preset fifth fixed coefficient; Q6 is the preset sixth weight coefficient; r is the number of monitoring indicators; βi is the influencing factor of the i-th monitoring indicator; ki is the reference value of the i-th monitoring indicator generated based on the feedback data at the current feedback time node.

[0135] Specifically, all parameters in the model are normalized by presetting the fifth fixed coefficient and the sixth fixed coefficient, so that each parameter in the model is within the same value range.

[0136] Specifically, the monitoring indicators include, but are not limited to, operating temperature fluctuations, contact surface pressure fluctuation parameters, suction pressure fluctuation parameters and other parameters related to operating failures of the cleaning robot.

[0137] Specifically, the larger the operation deviation value is, the greater the possibility that the current cleaning robot will have an operation failure.

[0138] Specifically, when judging whether to generate a warning instruction according to the operation deviation value g, it includes:

[0139] Preset a first operation deviation value threshold G1 and a second operation deviation value threshold G2;

[0140] If g≤G1, no warning instruction is generated at the current feedback time node;

[0141] If G1<g≤G2, the current feedback time node generates a first-level warning instruction;

[0142] If g>G2, the current feedback time node generates a secondary warning instruction.

[0143] Specifically, the first-level warning instruction means that the current cleaning robot has an abnormal operation and needs to be repaired in time after completing the cleaning task to eliminate potential failure risks. The second-level warning instruction means that the current cleaning robot may fail at any time and needs to be shut down for maintenance immediately.

[0144] It can be understood that in the above embodiment, when the corrected evaluation value is too large, the feedback data of the cleaning robot is collected to generate an operation deviation value, and the potential risks of the cleaning robot are warned in time according to the operation deviation value to avoid operational failures of the cleaning robot and reduce the operation and maintenance cost of the cleaning robot.

[0145] In a preferred embodiment of the present application, it also includes:

[0146] Obtain the operation data of the cleaning robot according to the end time node of the initial cleaning plan, and generate an update data packet based on all the operation data;

[0147] modifying the target control model according to the update data packet;

[0148] Update the control model sequence P according to the correction result.

[0149] Specifically, the corresponding control model is optimized according to all operating parameters of the cargo compartment to be cleaned during the cleaning cycle, and each control model is periodically optimized to achieve precise control of the cleaning robot and improve the cleaning quality.

[0150] According to the first concept of the present application, multiple cleaning scenes are set according to the cargo compartment parameters and the coal transport parameters, and the optimal control strategies for various cleaning scenes are set according to the historical parameters to achieve remote control of the cleaning robot, improve cleaning efficiency and reduce cleaning costs.

[0151] According to the second concept of the present application, during the cleaning process of the cargo compartment to be cleaned, multiple feedback time nodes are set to monitor the cargo compartment to be cleaned, and the initial cleaning plan is dynamically corrected according to the corrected evaluation value, so as to ensure the cleaning quality of the compartment to be cleaned. At the same time, the corresponding control model is optimized according to all operating parameters of the cargo compartment to be cleaned during the cleaning cycle, so as to achieve precise control of the cleaning robot and improve the cleaning quality.

[0152] According to the third concept of the present application, when the corrected evaluation value is too large, the feedback data of the cleaning robot is collected to generate an operation deviation value, and the potential risks of the cleaning robot are warned in time according to the operation deviation value to avoid operational failures of the cleaning robot and reduce the operation and maintenance cost of the cleaning robot.

[0153] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and substitutions can be made without departing from the technical principles of the present application. These improvements and substitutions should also be regarded as the scope of protection of the present application.

Claims

1. A remote control method for a cargo compartment intelligent cleaning robot, characterized in that: include: Generate multiple cleaning scenarios based on historical cargo compartment parameters, and generate control models for each cleaning scenario in turn; Generate an initial cleaning plan according to the equipment parameters of the cargo compartment to be cleaned, and generate multiple feedback time nodes according to the initial cleaning plan; Acquire monitoring data of the cargo compartment to be cleaned according to the preset feedback time node, and determine whether to generate correction instructions based on the monitoring data; Among them, when generating multiple cleaning scenes, including: Establish a cleaning scene sequence A, A = (a1, a2...a i …a n ), where a i is the i-th cleaning scene; n is the number of cleaning scenes.

2. The remote control method of the intelligent cargo compartment cleaning robot according to claim 1, characterized in that: Generate control models for each cleaning scenario, including: Set a in sequence according to the cleaning scene sequence A i Clear the scene for the target; Establish multiple cleaning sub-areas in the target cleaning scene; Set the sub-control strategy of the cleaning robot in each cleaning sub-area; Generate a control model for the target cleaning scenario based on all sub-control strategies; Generate the control model of each cleaning scene in turn, and establish the control model sequence P; P=(p1,p2…p i …p n ), where p i is the control model for the i-th cleaning scene.

3. The remote control method of the intelligent cargo compartment cleaning robot according to claim 2, characterized in that: Generate an initial cleaning plan based on the equipment parameters of the cargo compartment to be cleaned, including: Determine the cleaning scene of the cargo compartment to be cleaned according to the equipment parameters of the cargo compartment to be cleaned; Select the target control model according to the judgment result; Establish a sequence of cleaning sub-areas B, B = (b1, b2...b i …b m ), where bi is the i-th cleaning sub-area in the target cleaning scene; m is the number of cleaning sub-areas in the target control model; According to the cleaning sub-area sequence B, a time interval sequence T is established, T = (t1, t2...t i …t m ), where t i To clean sub-area b i The corresponding cleaning time; Generate sub-control strategies within each time interval and generate an initial cleaning plan; Set the end time node of each time interval as the feedback time node.

4. The remote control method of the intelligent cargo compartment cleaning robot according to claim 3, characterized in that: Determine whether to generate correction instructions based on monitoring data, including: Get the monitoring data of the current feedback time node; Establish the time interval sequence T1 of the current feedback time node, T1=(t 11 , t 12 …t 1i ……t 1m1 ), where t 1i is the i-th time interval after the cargo compartment to be cleaned starts cleaning; m1 is the number of time intervals between the start time node of the cargo compartment to be cleaned and the current feedback time node, m1≤m; t 1m1 is the time interval corresponding to the current feedback time node; Generate the cleaning evaluation value sequence F of the current feedback time node, F = (f1, f2...f i …f m1 ), where f i is the time interval t 1i The cleaning evaluation value within; Generate a modified evaluation value d according to the cleaning evaluation value sequence F; Whether to generate a correction instruction is determined based on the correction evaluation value d.

5. The remote control method of the intelligent cargo compartment cleaning robot according to claim 4, characterized in that: Determining whether to generate a correction instruction according to the correction evaluation value d includes: Preset a first modified evaluation value threshold D1 and a second modified evaluation value threshold D2; If d<D1, no correction instruction is generated at the current feedback time node; If D1<d<D2, the current feedback time node generates a first-level correction instruction; If d>D2, the current feedback time node generates a secondary correction instruction, and generates an operation deviation value g of the current feedback time node, and determines whether to generate an early warning instruction based on the operation deviation value g.

6. The remote control method of the intelligent cargo compartment cleaning robot according to claim 5, characterized in that: Generate a modified evaluation value d according to the cleaning evaluation value sequence F, including: Wherein, e1 is the preset first weight coefficient; e2 is the preset second weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; ηf is the average value of all data in the cleaning evaluation value series F; f' is the standard cleaning evaluation value; Y(i) is the selection coefficient; if (f i -f')>0,Y(i)=0; if (f i -f')≤0,Y(i)=-1.

7. The remote control method of the intelligent cargo compartment cleaning robot according to claim 5, characterized in that: Generate the cleaning evaluation value sequence F of the current feedback time node, including: Set t in sequence according to the time interval sequence T1 1i is the target time interval; Obtain image data in the cleaning sub-area corresponding to the target time interval, and generate a cleaning evaluation value f within the target time interval according to the preprocessing result; Among them, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; θ is the number of residual points in the cleaning sub-area corresponding to the target time interval; ji is the residual evaluation value of the i-th residual point in the cleaning sub-area corresponding to the target time interval; The cleaning evaluation value in each time interval is generated sequentially.

8. The remote control method of the intelligent cargo compartment cleaning robot according to claim 6, characterized in that: The running deviation value g of the current feedback time node includes: Obtain the feedback data of the cleaning robot at the current feedback time node; Generate the running deviation value g of the current feedback time node according to the feedback data; Among them, e5 is the preset fifth weight coefficient; e6 is the preset sixth weight coefficient; Q5 is the preset fifth fixed coefficient; Q6 is the preset sixth weight coefficient; r is the number of monitoring indicators; βi is the influencing factor of the i-th monitoring indicator; ki is the reference value of the i-th monitoring indicator generated based on the feedback data at the current feedback time node.

9. The remote control method of the intelligent cargo compartment cleaning robot according to claim 8, characterized in that: When judging whether to generate a warning instruction according to the running deviation value g, it includes: Preset a first operation deviation value threshold G1 and a second operation deviation value threshold G2; If g≤G1, no warning instruction is generated at the current feedback time node; If G1<g≤G2, the current feedback time node generates a first-level warning instruction; If g>G2, the current feedback time node generates a secondary warning instruction.

10. The remote control method of the intelligent cargo compartment cleaning robot according to claim 8, characterized in that: Also includes: Obtain the operation data of the cleaning robot according to the end time node of the initial cleaning plan, and generate an update data packet based on all the operation data; modifying the target control model according to the update data packet; Update the control model sequence P according to the correction result.

Images