Identification model acquisition method and device, state identification method and device and engineering machinery

Abstract

The embodiment of the invention discloses a recognition model acquisition method, a state recognition method and device and engineering machinery, and belongs to the technical field of equipment detection. The identification model acquisition method comprises the following steps: acquiring historical working condition data of the engineering machinery under the condition that the forward and reverse rotation states of a stirring drum of the engineering machinery change within a preset duration period until the forward and reverse rotation states of the stirring drum change again; clustering all historical working condition data to obtain at least two optimal position clusters; determining a loading position and at least one unloading position from the at least two optimal position clusters; and inputting the loading position, all the unloading positions and all the historical working condition data into a preset model, and iterating the preset model to obtain a working state recognition model of the engineering machinery. The unloading position and device can be determined without obtaining the working track of the engineering machinery, then the working condition data of the engineering machinery are obtained, and the working state of the engineering machinery is accurately recognized through the working state recognition model.

Description

Technical Field

[0001] The present application relates to the technical field of equipment detection, and particularly to a method for obtaining an identification model, a method for state identification, a device and a construction machinery. Background Art

[0002] A mixer truck is a construction machinery used to transport materials such as concrete. During the transportation of concrete, the mixing drum of the mixer truck keeps rotating to prevent the transported concrete from solidifying, thereby realizing the long-distance transportation of concrete. Usually, the mixing station is the loading location of the mixer truck, and the construction site is the unloading location of the mixer truck. When the mixer truck shuttles between the mixing station and the construction site, it is necessary to monitor the working state of the mixer truck. Usually, it is necessary to obtain the complete transportation route as the basic information of the mixer truck, and then determine the mixing station location and the construction site location according to the complete transportation route and the forward and reverse states of the mixing drum. According to the mixing station location, the construction site location and the basic information, the working state of the mixer truck is carried out.

[0003] In the actual monitoring process, it takes a lot of time to determine the complete transportation route of the mixer truck at the mixing station location and the construction site location. If the complete transportation route is inaccurate, it will lead to inaccurate determination of the mixing station location and the construction site location and low efficiency. In addition, usually when the mixing drum of the mixer truck is in the reverse state, the location where the mixer truck is located is determined as the construction site location. However, when the mixer truck unloads the surplus materials at the mixing station location, the mixing drum is also in the reverse state, which leads to misjudgment of the mixing station location and the construction site location. The inaccurate determination of the mixing station location and the construction site location results in the inability to accurately detect the working state of the mixer truck. Summary of the Invention

[0004] The purpose of the embodiments of the present application is to provide a method for obtaining an identification model, a method for state identification, a device and a construction machinery, so as to solve the problem that the working state of the mixer truck cannot be accurately detected in the prior art.

[0005] To achieve the above purpose, the first aspect of the present application provides a method for obtaining an identification model, and the method for obtaining an identification model includes:

[0006] When the forward and reverse states of the mixing drum of the construction machinery change within a preset time period, obtain the historical working condition data of the construction machinery until the forward and reverse states of the mixing drum change again;

[0007] Cluster all the historical working condition data to obtain at least two optimal position clusters;

[0008] Determine the loading position and at least one unloading position from at least two optimal position clusters;

[0009] Input the loading position, all unloading positions and all historical working condition data into a preset model, and iterate the preset model to obtain the working state identification model of the construction machinery.

[0010] In the embodiments of the present application, all historical working condition data are clustered to obtain at least two optimal position clusters, including:

[0011] Cluster all target historical working condition data based on a preset clustering algorithm to obtain multiple position cluster categories, where the target historical working condition data are the historical working condition data obtained when the mixing drum of the construction machinery is switched to the reverse state;

[0012] Obtain the silhouette coefficient of each position cluster category respectively;

[0013] Determine at least two optimal position clusters according to the silhouette coefficient and the number of position cluster categories.

[0014] In the embodiments of the present application, input the loading position, all unloading positions and all historical working condition data into a preset model, and iterate the preset model to obtain a working state recognition model of the construction machinery, including:

[0015] Extract features from all historical working condition data to obtain working condition features;

[0016] Based on the historical working trajectory of the construction machinery within a preset time period, label the loading position, all unloading positions and working condition features to obtain a training sample set and a feature sample set;

[0017] Input the training sample set and the feature sample set into the preset model, and iterate the preset model to obtain a working state recognition model of the construction machinery.

[0018] In the embodiments of the present application, input the training sample set and the feature sample set into a preset model, and iterate the preset model to obtain a working state recognition model of the construction machinery, including:

[0019] Construct a preset model based on a preset decision tree;

[0020] Input the training sample set and the feature sample set into the preset model, and iterate the preset model to obtain decision tree logic;

[0021] Obtain a working state recognition model of the construction machinery according to the decision tree logic.

[0022] In the embodiments of the present application, the method for obtaining the recognition model further includes:

[0023] Obtain updated data of the loading position and updated data of each unloading position based on a preset time interval;

[0024] Update the working state recognition model according to the updated data of the loading position and the updated data of each unloading position.

[0025] In an embodiment of the present application, the method for obtaining the recognition model further includes:

[0026] Based on all historical working condition data, determine the working process duration of the construction machinery within a preset duration period, and the time proportion of each working state in the working process;

[0027] Based on the working process duration, all time proportions, and the historical working trajectory of the construction machinery within a preset duration period, construct an abnormal state monitoring model for the construction machinery;

[0028] Monitor the real-time working trajectory and real-time working condition data of the construction machinery based on the abnormal state monitoring model, and generate an abnormal state monitoring result of the construction machinery.

[0029] In an embodiment of the present application, determining the time proportion of each working state of the construction machinery within a preset duration period based on all historical working condition data includes:

[0030] Sort all historical working condition data based on the time sequence to obtain the process working condition data corresponding to each working process of the construction machinery within a preset duration period;

[0031] For each working process, based on the process working condition data, respectively determine the start time and end time corresponding to each working state;

[0032] Based on the start time and end time corresponding to all working states corresponding to all working processes, determine the working process duration of the construction machinery within a preset duration period, and the time proportion of each working state in the working process.

[0033] In an embodiment of the present application, determining the loading position and at least one unloading position from at least two optimal position clusters includes:

[0034] Based on the historical working condition data corresponding to each optimal position cluster, determine the loading position and at least one unloading position from at least two optimal position clusters.

[0035] The second aspect of the present application provides a state recognition method, and the state recognition method includes:

[0036] Obtain the real-time working condition data of the construction machinery;

[0037] Input the real-time working condition data into the working state recognition model to obtain the working state recognition result of the construction machinery output by the working state recognition model, where the working state recognition model is based on the above-mentioned method for obtaining the recognition model.

[0038] The third aspect of the present application provides a control device, including:

[0039] A memory configured to store instructions;

[0040] A processor, configured to call instructions from a memory and capable of implementing the above-mentioned recognition model acquisition method and / or the above-mentioned state recognition method when executing the instructions.

[0041] A fourth aspect of the present application provides a construction machinery, including:

[0042] The above-mentioned control device;

[0043] A mixing drum, configured to mix materials.

[0044] A fifth aspect of the present application provides a machine-readable storage medium, on which instructions are stored, and the instructions are used to cause a machine to execute the above-mentioned recognition model acquisition method and / or the above-mentioned state recognition method.

[0045] The present application provides a recognition model acquisition method, including: when the forward and reverse rotation states of the mixing drum of a construction machinery change within a preset time period, acquiring the historical working condition data of the construction machinery until the forward and reverse rotation states of the mixing drum change again; clustering all the historical working condition data to obtain at least two optimal position clusters; determining a loading position and at least one unloading position from the at least two optimal position clusters; inputting the loading position, all the unloading positions and all the historical working condition data into a preset model, and iterating the preset model to obtain a working state recognition model of the construction machinery. On the basis of not needing to obtain the working trajectory of the construction machinery, the unloading position and device are determined. Only by acquiring the working condition data of the construction machinery, the working state of the construction machinery can be accurately recognized through the working state recognition model. There is no need for manual intervention in the recognition of the working state, nor is it necessary to spend extra time to obtain information such as working rules, improving the working state recognition efficiency. According to the recognized working state, the scheduling mechanism of the construction machinery can be optimized, thereby improving the working efficiency of the construction machinery.

[0046] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation part. Description of the Drawings

[0047] The drawings are used to provide a further understanding of the embodiments of the present application, and constitute a part of the specification. Together with the following specific implementation, they are used to explain the embodiments of the present application, but do not constitute a limitation to the embodiments of the present application. In the drawings:

[0048] Figure 1 Schematically shows a flowchart of a recognition model acquisition method according to an embodiment of the present application;

[0049] Figure 2 Schematically shows an example diagram of a silhouette coefficient according to an embodiment of the present application;

[0050] Figure 3 A schematic diagram showing an example of a decision tree logic according to an embodiment of the present application;

[0051] Figure 4 A schematic flow chart showing a state recognition method according to an embodiment of the present application. Detailed implementation manners

[0052] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. It should be understood that the specific implementation manners described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0053] It should be noted that the acquisition, transmission, storage, use, processing, etc. of data in the technical solutions of the present application all comply with the relevant provisions of national laws and regulations. In the embodiments of the present application, some existing industry solutions such as software, components, models, etc. may be mentioned, and they should be regarded as exemplary. The purpose is only to illustrate the feasibility in the implementation of the technical solutions of the present application, but it does not mean that the applicant has already or necessarily used this solution.

[0054] It should be noted that if there are directional indications involved in the embodiments of the present application, the directional indications are only used to explain the relative positional relationship and movement conditions between components in a specific posture. If this specific posture changes, the directional indications will also change accordingly.

[0055] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between various embodiments can be combined with each other, but it must be based on the ability of those of ordinary skill in the art to implement. When the combination of technical solutions results in contradictions or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the protection scope required by the present application.

[0056] Embodiment 1

[0057] Figure 1 A schematic flow chart showing a method for obtaining an identification model according to an embodiment of the present application. As Figure 1 shown, the embodiments of the present application provide a method for obtaining an identification model, and the method may include the following steps:

[0058] S110, when the forward and reverse states of the mixing drum of the construction machinery change within a preset time period, obtain the historical working condition data of the construction machinery until the forward and reverse states of the mixing drum change again.

[0059] The value of the preset time period is set according to actual needs and is not limited here. For ease of understanding, the preset time period in the embodiments of the present application is 24 hours. Obtain the working condition data of the construction machinery within 24 hours. Specifically, detect whether the forward and reverse states of the mixing drum change within the preset time period. When the forward and reverse states of the mixing drum of the construction machinery change within the preset time period, start to obtain the historical working condition data of the construction machinery until the forward and reverse states of the mixing drum change again, then restart to obtain the historical working condition data of the project, and further slice the working condition data within 24 hours into multiple segments of historical working condition data.

[0060] S120, cluster all the historical working condition data to obtain at least two optimal location clusters.

[0061] The type of the construction machinery is set according to actual needs and is not limited here. For ease of understanding, the construction machinery in the embodiments of the present application is a mixer truck including a mixing drum. In this embodiment, the historical working condition data includes the forward and reverse states of the mixing drum. When the mixing drum is in the reverse state, usually the mixer truck is at the unloading location or the loading location. Cluster all the historical working condition data to obtain at least two optimal location clusters to obtain the location clusters corresponding to the unloading location and the loading location.

[0062] It should be understood that all the historical working condition data can be clustered through a clustering algorithm or a machine learning algorithm, which will not be elaborated here.

[0063] In the embodiments of the present application, clustering all the historical working condition data to obtain at least two optimal location clusters includes:

[0064] Cluster all the target historical working condition data based on a preset clustering algorithm to obtain multiple location clustering categories, where the target historical working condition data is the historical working condition data obtained when the mixing drum of the construction machinery switches to the reverse state;

[0065] Obtain the silhouette coefficient of each location clustering category respectively;

[0066] Determine at least two optimal location clusters according to the silhouette coefficient and the number of location clustering categories.

[0067] In the actual transportation scenarios of materials such as concrete, construction machinery loads materials at one loading position and unloads materials at at least one unloading position. When the construction machinery unloads materials at the unloading position, the mixing drum is in the reverse state to unload the materials, so that the position when the mixing drum is usually in the reverse state is directly determined as the unloading position. However, when the construction machinery is at the loading position, the mixing drum may also be in the reverse state to unload the excess materials. In addition, during the loading and unloading processes of the construction machinery, the mixing drum may rotate forward or stop, resulting in inaccurate determination of the loading position and the unloading position.

[0068] In this embodiment, when the mixing drum of the construction machinery switches to the reverse state, the obtained historical working condition data is determined as the target historical working condition data. Furthermore, the staying position, staying duration, staying times, reverse state duration, and other data of the construction machinery can be determined through the historical working condition data. Based on a preset clustering algorithm, all the target historical working condition data is clustered, that is, the working condition data when the mixing drum rotates in reverse is fed into the clustering algorithm to obtain multiple position clustering categories. It should be understood that the type of the preset clustering algorithm is set according to actual requirements, and it can be a K-means (k-means) clustering algorithm, a hierarchical clustering algorithm, etc., which is not limited herein.

[0069] For ease of understanding, in the embodiments of the present application, the preset clustering algorithm is the K-means clustering algorithm. To make the clustering categories have obvious characteristic distinctions, the working condition data is used as sample points, and the silhouette coefficient of each position clustering category is obtained respectively:

[0070]

[0071] Among them, s(i) is the silhouette coefficient of the sample point belonging to the position clustering category, a(i) is the average distance of the sample point from the position clustering category it belongs to, b(i) is the average distance of the sample point from the nearest position clustering category, and the nearest position clustering category is determined by the central distance between the sample point and other position clustering categories.

[0072] According to the silhouette coefficients of all the position clustering categories, the average silhouette coefficient is calculated, that is, the total silhouette coefficient is obtained:

[0073]

[0074] Among them, s is the total silhouette coefficient, s(i) is the silhouette coefficient of the i-th position clustering category, and n is the total number of position clustering categories.

[0075] Please refer to Figure 2 , Figure 2 which schematically shows an example diagram of a silhouette coefficient according to an embodiment of the present application.

[0076] Determine at least two optimal location clusters according to the silhouette coefficient and the number of location cluster categories. In this embodiment, the elbow method is used to identify the optimal number of clusters. As shown in the figure, the number of location cluster categories is used as the abscissa, and the silhouette coefficient is used as the ordinate to obtain a silhouette coefficient line graph. Determine the point with the fastest change rate of the slope in the line graph. In this embodiment, the fastest change rate of the slope is 3, and the optimal number of location clusters is determined to be 3. Furthermore, it can be determined that the construction machinery shuttles between 1 loading position and 2 unloading positions within a preset time period.

[0077] S130, determine the loading position and at least one unloading position from at least two optimal location clusters.

[0078] Cluster all historical working condition data. The unsupervised algorithm characteristics of the clustering algorithm make it impossible to pre-determine the number of optimal location clusters. Then, in the actual working scenario, the optimal location clusters are at least two, namely one loading position and at least one unloading position. In the case where the construction machinery unloads at multiple unloading positions, the number of optimal location clusters will be greater than or equal to 3. Since the working condition data of the construction machinery at the loading position and the unloading position are different, it is possible to determine the loading position and at least one unloading position from at least two optimal location clusters.

[0079] Mark the loading position and the unloading position, which can provide a sample data set for working state recognition to improve the recognition efficiency. It should be understood that when the loading position and the unloading position are determined, when the construction machinery is at the loading position, the working state of the construction machinery can be recognized as the loading state, and when the construction machinery is at the unloading position, the working state of the construction machinery can be recognized as the unloading state.

[0080] In the embodiment of the present application, determining the loading position and at least one unloading position from at least two optimal location clusters includes:

[0081] Determine the loading position and at least one unloading position from at least two optimal location clusters according to the historical working condition data corresponding to each optimal location cluster.

[0082] Since the working condition data of the construction machinery at the unloading position and the loading position are different, according to the historical working condition data corresponding to each optimal location cluster, determine the residence duration, residence times and forward and reverse state durations of the construction machinery at different positions, and then determine the loading position and at least one unloading position from at least two optimal location clusters.

[0083] Specifically, usually the residence duration of the construction machinery at the loading position is much longer than that at the unloading position. The forward rotation state duration of the construction machinery at the loading position is longer, and the reverse rotation state duration at the unloading position is longer. When the number of unloading positions is greater than or equal to two, the residence times of the construction machinery at the loading position are greater than those at the unloading position.

[0084] The present application provides a method for obtaining an identification model, including: when the forward and reverse states of the mixing drum of a construction machine change within a preset time period, obtaining the historical working condition data of the construction machine until the forward and reverse states of the mixing drum change again; clustering all the historical working condition data to obtain at least two optimal position clusters; determining a loading position and at least one unloading position from the at least two optimal position clusters; inputting the loading position, all the unloading positions, and all the historical working condition data into a preset model, and iterating the preset model to obtain a working state identification model of the construction machine. On the basis of not needing to obtain the working trajectory of the construction machine, the unloading position and device are determined. Only by obtaining the working condition data of the construction machine can the working state of the construction machine be accurately identified through the working state identification model. There is no need for manual intervention in the identification of the working state, nor is it necessary to spend extra time obtaining information such as working rules, improving the working state identification efficiency. According to the identified working state, the scheduling mechanism of the construction machine can be optimized, thereby improving the working efficiency of the construction machine.

[0085] S140, input the loading position, all the unloading positions, and all the historical working condition data into a preset model, and iterate the preset model to obtain a working state identification model of the construction machine.

[0086] Input the loading position, all the unloading positions, and all the historical working condition data into a preset model. By iterating the preset model, the model can identify the characteristics of the working condition data of the construction machine in different working states, and then obtain a working state identification model of the construction machine. Deploy the working state identification model to the control device of the construction machine, so that during the operation of the construction machine, the real-time working condition data can be input into the working state identification model to obtain the working state identification result output by the working state identification model.

[0087] Specifically, when it is necessary to identify the working state of the construction machine on the current day, obtain the historical working condition data of the previous day, that is, obtain the historical working condition data of the previous 24 hours, to obtain a working state identification model. Input the real-time working condition data of the current day into the working state identification model to obtain a working state identification result. On the basis of not needing to obtain the working trajectory of the construction machine, the unloading position and device are determined. Only by obtaining the working condition data of the construction machine can the working state of the construction machine be accurately identified through the working state identification model.

[0088] In an embodiment of the present application, inputting the loading position, all the unloading positions, and all the historical working condition data into a preset model, and iterating the preset model to obtain a working state identification model of the construction machine includes:

[0089] Extract features from all the historical working condition data to obtain working condition features;

[0090] Based on the historical working trajectory of construction machinery within a preset time period, label the loading position, all unloading positions, and working condition characteristics to obtain a training sample set and a feature sample set;

[0091] Input the training sample set and the feature sample set into a preset model, iterate the preset model, and obtain a working state recognition model for construction machinery.

[0092] Extract features from all historical working condition data to obtain working condition characteristics. It should be understood that the data included in the historical working condition data is set according to actual needs and is not limited here. For ease of understanding, in the embodiments of this application, the historical working condition data includes the duration of forward and reverse states, the longitude and latitude of the position of the construction machinery, the driving mileage, and the vehicle speed. When determining the displacement of the construction machinery, it can be calculated through the longitude and latitude of the position of the construction machinery:

[0093]

[0094] Among them, D is the displacement of the construction machinery, R is the radius of the earth, in this embodiment R = 6371 km, Lng1 is the first position longitude of the construction machinery, Lng2 is the second position longitude of the construction machinery, Lat1 is the first position latitude of the construction machinery, and Lat2 is the second position latitude of the construction machinery.

[0095] Extract features from all historical working condition data to obtain working condition characteristics. For ease of understanding, in this embodiment, the extracted working condition characteristics include the average vehicle speed, driving mileage, forward and reverse states, duration of forward and reverse states, starting longitude and latitude, ending longitude and latitude, loading position longitude and latitude, and unloading position longitude and latitude of the construction machinery. The starting longitude and latitude are the longitude and latitude when the forward and reverse states of the mixing drum change, and the ending longitude and latitude are the longitude and latitude when the forward and reverse states of the mixing drum change again. The driving mileage is calculated based on the mileage change difference between two adjacent changes in the forward and reverse states, and the duration of the forward and reverse states is calculated based on the time difference between two adjacent changes in the forward and reverse states.

[0096] Obtain the historical working trajectory of the construction machinery within 24 hours, that is, the movement trajectory of the construction machinery between the unloading position and the loading position. Based on the historical working trajectory of the construction machinery within a preset time period, label the loading position, all unloading positions, and working condition characteristics to obtain a training sample set and a feature sample set. Input the training sample set and the feature sample set into a preset model, iterate the preset model, and obtain a working state recognition model for construction machinery.

[0097] In the embodiments of this application, inputting the training sample set and the feature sample set into a preset model, iterating the preset model, and obtaining a working state recognition model for construction machinery includes:

[0098] Based on a preset decision tree, construct a preset model;

[0099] Input the training sample set and the feature sample set into a preset model, and iterate the preset model to obtain a decision tree logic;

[0100] According to the decision tree logic, obtain a working state recognition model for construction machinery.

[0101] In this embodiment, the working state is recognized through a decision tree algorithm. Specifically, based on a preset decision tree, a preset model is constructed. The decision tree learning algorithm usually recursively selects the optimal feature and divides the training data according to this feature. Input the training sample set and the feature sample set into the preset model, and iterate the preset model to obtain a decision tree logic. The decision tree algorithm is set according to actual needs and is not limited here. For ease of understanding, in the embodiment of this application, the decision tree algorithm uses the C4.5 decision tree algorithm, that is, the preset decision tree in this embodiment is a C4.5 decision tree. Feed the training sample set and the feature sample set into the C4.5 decision tree algorithm to obtain a decision tree logic. The C4.5 decision tree algorithm is a classification algorithm that can be used to classify different working states of construction machinery, and thus recognize the working state of construction machinery.

[0102] In this embodiment, let the training sample set be D and the feature sample set be A. If all the working condition features in D belong to the same working state C k , then return a single-node tree and use C k as the class of the node. Otherwise, calculate the information gain ratio of each working condition feature in A to D, and select the working condition feature A g with the largest information gain ratio. If the information gain ratio of A g is less than or equal to the threshold n, then return a single-node tree and use the class C k with the largest number of instances in D as the class of the node. Otherwise, for each possibility a g of A i , according to A g =a i divide D into several non-empty subsets D i , use the class with the largest number of instances in D i as the label, construct sub-nodes, and form a decision tree from the node and the sub-nodes. Finally, for each node i, use D i as the training set and {A - A g} as the feature sample set, recursively call the above steps to obtain a subtree T i to obtain a decision tree logic.

[0103] Please refer to Figure 3 , Figure 3 which schematically shows an example diagram of a decision tree logic according to an embodiment of this application.

[0104] According to the decision tree logic, obtain the working state recognition model of construction machinery. As shown in the figure, in this embodiment, the mixing plant is the loading position and the construction site is the unloading position. The working state recognition model determines the effective radius of the mixing plant, the effective radius of the construction site, the vehicle speed threshold during transportation, the waiting time threshold, etc., and then outputs the engineering state recognition result through the decision tree logic. In this embodiment, the first distance threshold is x o , and the second distance threshold is x i , with the unit of m. The vehicle speed is s p , the first speed threshold is V0, and the second speed threshold is V i , with the unit of km / h. The reverse state duration is T, and the duration threshold is T0, with the unit of h.

[0105] When the starting position of the construction machinery is less than or equal to the first distance threshold from the center of the loading position, the vehicle speed is less than or equal to the first speed threshold, and the reverse state duration is less than or equal to the duration threshold, the working state recognition model outputs the working state recognition result as the loading state. When the starting position of the construction machinery is less than or equal to the first distance threshold from the center of the loading position, the vehicle speed is less than or equal to the first speed threshold, and the reverse state duration is greater than the duration threshold, the working state recognition model outputs the working state recognition result as the rest state. When the starting position of the construction machinery is less than or equal to the first distance threshold from the center of the loading position and the vehicle speed is greater than the first speed threshold, the working state recognition model outputs the working state recognition result as the outbound state.

[0106] When the starting position of the construction machinery is greater than the first distance threshold from the center of the loading position and the vehicle speed is less than or equal to the second speed threshold, the working state recognition model outputs the working state recognition result as the waiting for unloading state. When the starting position of the construction machinery is greater than the first distance threshold from the center of the loading position, the vehicle speed is greater than the second speed threshold, and the end position of the construction machinery is less than or equal to the first distance threshold from the center of the loading position, the working state recognition model outputs the working state recognition result as the return state. When the starting position of the construction machinery is greater than the first distance threshold from the center of the loading position, the vehicle speed is greater than the second speed threshold, and the end position of the construction machinery is greater than the first distance threshold from the center of the loading position, the working state recognition model outputs the working state recognition result as the going to another construction site state.

[0107] In the embodiments of the present application, the method for obtaining the recognition model further includes:

[0108] Obtain the updated data of the loading position and the updated data of each unloading position based on a preset time interval;

[0109] Update the working state recognition model according to the updated data of the loading position and the updated data of each unloading position.

[0110] Update the parameters of the working state recognition model based on a preset time interval to improve the performance of the working state recognition model. Based on the preset time interval, obtain the working state of the mixing plant and the working state of the construction site, and then obtain the updated data of the loading position and the updated data of each unloading position.

[0111] In this embodiment, the working state recognition model is a decision tree-based model. According to the updated data of the loading position and the updated data of each unloading position, update the threshold parameters such as the speed threshold and the distance threshold in the decision tree, and then update the working state recognition model. Deploy the updated working state recognition model to the control device of the construction machinery to output a more accurate working state recognition result through the updated working state recognition model.

[0112] In the embodiment of the present application, the method for obtaining the recognition model further includes:

[0113] According to all historical working condition data, determine the working process duration of the construction machinery within a preset time period, and the time proportion of each working state in the working process;

[0114] According to the working process duration, all time proportions, and the historical working trajectory of the construction machinery within a preset time period, construct an abnormal state monitoring model for the construction machinery;

[0115] Based on the abnormal state monitoring model, monitor the real-time working trajectory and real-time working condition data of the construction machinery, and generate an abnormal state monitoring result of the construction machinery.

[0116] According to all historical working condition data, form multiple working processes completed by the construction machinery within a preset time period, and then determine the working process duration of the construction machinery to complete an engineering process within a preset time period, and the time proportion of each working state in each engineering process. The time proportion of each working state can be the time proportion of the driving state, the duration proportion of the unloading state, the time proportion of the return state, etc., which will not be elaborated here.

[0117] According to the working process duration, all time proportions, and the historical working trajectory of the construction machinery within a preset time period, model the working trajectory and time proportion of the construction machinery, and construct an abnormal state monitoring model for the construction machinery.

[0118] It should be understood that the abnormal state monitoring model can determine the working state of the construction machinery through the time proportion, and in this embodiment, the working state of the construction machinery is output through the working state recognition model, which will not be elaborated here. In this embodiment, based on the abnormal state monitoring model, monitor the real-time working trajectory and real-time working condition data of the construction machinery, and generate an abnormal state monitoring result of the construction machinery.

[0119] When the real-time working trajectory, the time proportion of each working state, and the forward and reverse installation duration are all normal, the abnormal state monitoring result is normal. When at least one of the real-time working trajectory, the time proportion of each working state, and the forward and reverse installation duration is abnormal, the abnormal state monitoring result is abnormal, and the construction machinery and the user can be monitored through an image acquisition device. By generating the abnormal state monitoring result through the abnormal state monitoring model, situations such as slacking and idling in the engineering process of construction machinery can be quickly detected, thereby improving the working efficiency of construction machinery.

[0120] In the embodiments of the present application, according to all historical working condition data, determining the time proportion of each working state of the construction machinery within a preset duration period includes:

[0121] Sorting all historical working condition data based on the time sequence to obtain the process working condition data corresponding to each working process of the construction machinery within the preset duration period;

[0122] For each working process, respectively determining the start time and end time corresponding to each working state according to the process working condition data;

[0123] Based on the start time and end time corresponding to all working states corresponding to all working processes, determining the working process duration of the construction machinery within the preset duration period, and the time proportion of each working state in the working process.

[0124] Since each time the forward and reverse installation state of the mixing drum changes, a section of switching data is obtained, that is, a section of historical working condition data is obtained, and then all working condition data of the construction machinery within the preset duration period is obtained. Sorting all historical working condition data based on the time sequence, composing multiple working processes completed by the construction machinery within the preset duration period, and obtaining the process working condition data corresponding to each working process of the construction machinery within the preset duration period.

[0125] For each working process, respectively determining the start time and end time corresponding to each working state according to the process working condition data, that is, determining the start time of the loading state, the end time of the loading state, the start time of the driving state, the end time of the driving state, the start time of the unloading state, and the end time of the unloading state, etc., which will not be elaborated here. Based on the start time and end time corresponding to all working states corresponding to all working processes, determining the working process duration of the construction machinery within the preset duration period, and the time proportion of each working state in the working process.

[0126] Embodiment 2

[0127] Figure 4 Schematically shows a flow diagram of a state recognition method according to an embodiment of the present application. As Figure 4As shown in the figure, an embodiment of the present application provides a state recognition method, and this method may include the following steps:

[0128] S210, obtaining real-time working condition data of construction machinery.

[0129] After obtaining the working state recognition model, obtain the real-time working condition data of the construction machinery during the working process in real time, so as to monitor the working state through the real-time working condition data.

[0130] S220, inputting the real-time working condition data into the working state recognition model to obtain the working state recognition result of the construction machinery output by the working state recognition model, where the working state recognition model is obtained according to the above-mentioned recognition model obtaining method.

[0131] Input the real-time working condition data into the working state recognition model to obtain the working state recognition result of the construction machinery output by the working state recognition model. When identifying the working state through the working state recognition model, it is not necessary to obtain the working trajectory of the construction machinery, and only the working condition data of the construction machinery needs to be input. Since it is not necessary to spend a lot of time obtaining the working trajectory, the accuracy of the working state is improved and the recognition efficiency of the working state is also improved.

[0132] An embodiment of the present application also provides a control device, including:

[0133] A memory, configured to store instructions;

[0134] A processor, configured to call instructions from the memory and be able to implement the above-mentioned recognition model obtaining method and / or the above-mentioned state recognition method when executing the instructions.

[0135] The processor contains a kernel, and the kernel is used to retrieve the corresponding program unit from the memory. One or more kernels can be set, and the above-mentioned recognition model obtaining method and / or the above-mentioned state recognition method can be implemented by adjusting the kernel parameters.

[0136] The memory may include non-permanent memory in a computer-readable medium, forms such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM), and the memory includes at least one storage chip.

[0137] An embodiment of the present application also provides a construction machinery, including:

[0138] The above-mentioned control device;

[0139] A mixing drum, configured to mix materials.

[0140] When the construction machinery is in the loading position, the mixing drum rotates forward to load materials into the mixing drum. During the process of the construction machinery transporting materials, the mixing drum keeps rotating to prevent materials such as concrete being transported from solidifying. When the construction machinery is in the unloading position, the mixing drum rotates in reverse to unload the materials to the construction site. The control device optimizes the scheduling mechanism of the construction machinery based on the working state of the deployed construction machinery, so as to improve the working efficiency of the construction machinery according to the identified working state.

[0141] The embodiment of the present application also provides a machine-readable storage medium, on which instructions are stored, and the instructions are used to make the machine execute the above-mentioned recognition model acquisition method and / or the above-mentioned state recognition method.

[0142] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0143] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of processes and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for realizing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0144] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured product including an instruction device, and the instruction device realizes the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0145] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 steps of the functions specified in one block or multiple blocks.

[0146] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0147] The memory may include non-permanent memory in the computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.

[0148] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can store information by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media, such as modulated data signals and carrier waves.

[0149] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, commodity or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, commodity or device comprising the element.

[0150] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A method for obtaining an identification model, characterized in that, The method for obtaining the recognition model includes: When the forward and reverse states of the mixing drum of the construction machinery change within a preset time period, obtain the historical working condition data of the construction machinery until the forward and reverse states of the mixing drum change again; Cluster all the historical working condition data to obtain at least two optimal position clusters; Determine the loading position and at least one unloading position from the at least two optimal position clusters; Input the loading position, all the unloading positions, and all the historical working condition data into a preset model, iterate the preset model, and obtain the working state recognition model of the construction machinery.

2. The method for obtaining an identification model according to claim 1, wherein The step of clustering all the historical working condition data to obtain at least two optimal position clusters includes: Cluster all the target historical working condition data based on a preset clustering algorithm to obtain multiple position clustering categories, where the target historical working condition data is the historical working condition data obtained when the mixing drum of the construction machinery switches to the reverse state; Obtain the silhouette coefficient of each position clustering category respectively; Determine at least two optimal position clusters according to the silhouette coefficient and the number of the position clustering categories.

3. The method for obtaining an identification model according to claim 1, wherein The step of inputting the loading position, all the unloading positions, and all the historical working condition data into a preset model, iterating the preset model, and obtaining the working state recognition model of the construction machinery includes: Extract features from all the historical working condition data to obtain working condition features; Based on the historical working trajectory of the construction machinery within a preset time period, label the loading position, all the unloading positions, and the working condition features to obtain a training sample set and a feature sample set; Input the training sample set and the feature sample set into a preset model, iterate the preset model, and obtain the working state recognition model of the construction machinery.

4. The method for obtaining the recognition model according to claim 3, wherein The step of inputting the training sample set and the feature sample set into a preset model, iterating the preset model, and obtaining the working state recognition model of the construction machinery includes: Construct a preset model based on a preset decision tree; Input the training sample set and the feature sample set into the preset model, iterate the preset model, and obtain decision tree logic; Obtain the working state recognition model of the construction machinery according to the decision tree logic.

5. The method for obtaining an identification model according to claim 1, wherein The method for obtaining the recognition model further includes: Obtain the updated data of the loading position and the updated data of each unloading position based on a preset time interval; Update the working state recognition model according to the updated data of the loading position and the updated data of each unloading position.

6. The method for obtaining the recognition model according to claim 1, characterized in that The method for obtaining the recognition model further includes: Determine the working process duration of the construction machinery within a preset time period and the time proportion of each working state in the working process according to all the historical working condition data; Construct an abnormal state monitoring model of the construction machinery according to the working process duration, all the time proportions, and the historical working trajectory of the construction machinery within a preset time period; Monitor the real-time working trajectory and real-time working condition data of the construction machinery based on the abnormal state monitoring model, and generate an abnormal state monitoring result of the construction machinery.

7. The method for obtaining an identification model according to claim 6, wherein Determining the time proportion of each working state of the construction machinery within a preset duration period according to all the historical working condition data includes: Sorting all the historical working condition data based on the time sequence to obtain the process condition data corresponding to each working process of the construction machinery within a preset duration period; For each working process, determining the start time and end time corresponding to each working state according to the process condition data; Based on the start time and end time corresponding to all the working states corresponding to all the working processes, determining the working process duration of the construction machinery within a preset duration period and the time proportion of each working state in the working process.

8. The method for obtaining an identification model according to claim 1, wherein Determining the loading position and at least one unloading position from the at least two optimal position clusters includes: Determining the loading position and at least one unloading position from the at least two optimal position clusters according to the historical working condition data corresponding to each optimal position cluster.

9. A state recognition method, characterized in that, The state recognition method includes: Obtaining the real-time working condition data of the construction machinery; Inputting the real-time working condition data into the working state recognition model to obtain the working state recognition result of the construction machinery output by the working state recognition model, where the working state recognition model is obtained according to the recognition model obtaining method described in any one of claims 1 to 8.

10. A control device, characterized in that, Including: A memory configured to store instructions; A processor configured to call the instructions from the memory and capable of implementing the recognition model obtaining method described in any one of claims 1 to 8 and / or the state recognition method described in claim 9 when executing the instructions.

11. An engineering machinery, characterized in that, Including: The control device according to claim 10; A mixing drum configured to mix materials.

12. A machine-readable storage medium, characterized in that, Instructions are stored on the machine-readable storage medium, and the instructions are used to cause the machine to execute the recognition model obtaining method described in any one of claims 1 to 8 and / or the state recognition method described in claim 9.

Images