Scene recognition method, device, system and crane

Abstract

The present application provides a scene recognition method, device, system and crane, which are suitable for crane operation scene recognition, including obtaining loading condition characteristics, the loading condition characteristics including single loading characteristics, and the single loading characteristics including the crane operation condition data during a single loading process; clustering the loading condition characteristics to obtain multiple loading characteristics, the loading characteristics including test pressure block loading characteristics, the test pressure block loading characteristics characterizing that the crane loading operation scene matches the test pressure block loading operation scene; determining whether the crane loading operation scene is a test pressure block loading operation scene based on the proportion of the test pressure block loading characteristics in the continuous loading process, and determining whether the continuous loading process is a test pressure block loading operation scene based on the proportion of the test pressure block loading characteristics in the multiple single loading characteristics contained in the continuous loading process, thereby improving the accuracy of crane operation scene recognition and solving the problem of low accuracy of manual identification of test pressure block loading work scenes in the prior art.

Description

Technical Field

[0001] The present application relates to the field of crane technology, and in particular to a scene recognition method, device, system and crane. Background Art

[0002] Cranes are a traditional and widely used type of engineering machinery that can be widely used in various lifting work scenarios, such as test block lifting scenarios, steel bar lifting scenarios, bridge lifting scenarios, etc.

[0003] Among them, the pressure test block lifting scenario refers to the scenario in which a crane performs continuous lifting operations on a large number of pressure test blocks. In the pressure test block lifting scenario, the construction time may be as long as several days, and hundreds or even thousands of pressure test blocks need to be lifted continuously. The chassis and slewing system of the crane are in a high-intensity working state for a long time. Therefore, it is necessary to accurately identify the pressure test block lifting scenario to help R&D personnel better extract the working condition data under the pressure test block lifting scenario, and optimize the crane structure for the pressure test block lifting scenario in a targeted manner, thereby improving the working efficiency of the crane in the pressure test block lifting scenario and reducing the equipment loss of the crane in this scenario.

[0004] However, the current recognition accuracy of the test pressure block hoisting scene is low, and it is necessary to improve the recognition accuracy of the test pressure block hoisting scene. Summary of the Invention

[0005] In view of this, the embodiments of the present application are dedicated to providing a scene recognition method, device and equipment to solve the problem of low accuracy in manually identifying the test pressure block loading working scene in the prior art.

[0006] To solve the above technical problems, the implementation of the embodiments of this specification is as follows:

[0007] In a first aspect, the present invention provides a scene recognition method for identifying a crane hoisting operation scene, the scene recognition method comprising:

[0008] Obtaining a hoisting operating condition characteristic, wherein the hoisting operating condition characteristic includes a single hoisting characteristic, the single hoisting characteristic being obtained based on operating condition data of the crane during a single hoisting process, and the single hoisting characteristic being used to characterize a hoisting parameter of the crane during the single hoisting process;

[0009] Clustering the hoisting condition features to obtain a plurality of hoisting features, wherein the hoisting features include a pressure test block hoisting feature, wherein the pressure test block hoisting feature indicates that a hoisting operation scenario of the crane matches a pressure test block hoisting operation scenario;

[0010] Whether the lifting operation scene of the crane is the lifting operation scene of the test pressure block is determined according to the ratio of the lifting characteristics of the test pressure block in a continuous lifting process, wherein the continuous lifting process includes a plurality of the single lifting processes.

[0011] Furthermore, after clustering the hoisting operating condition features to obtain a plurality of hoisting features, the method further includes:

[0012] The single loading characteristics are classified to obtain the test pressure block loading characteristics.

[0013] Furthermore, the obtaining of the hoisting working condition characteristics includes:

[0014] According to the change of the actual weight of the crane, a single lifting time period is divided;

[0015] During the single lifting time period, the single lifting characteristics are obtained, and the single lifting characteristics include: average lifting weight, maximum lifting weight, lifting weight variance, single lifting time, and current-to-time ratio of the lifting action.

[0016] Furthermore, the hoisting condition characteristics also include: a continuous hoisting characteristic, and the continuous hoisting characteristic is used to characterize the number of hoisting operations of the crane within a preset time period.

[0017] Furthermore, clustering the hoisting condition features to obtain multiple hoisting features includes:

[0018] Using principal component analysis to perform dimensionality reduction processing on the single load feature to obtain a reduced-dimensional load feature;

[0019] Training a clustering model using the dimension-reduced load features;

[0020] The trained clustering model is used to perform cluster analysis on the single loading feature to obtain a plurality of the loading features.

[0021] Furthermore, the determining whether the hoisting operation scenario of the crane is the hoisting operation scenario of the test pressure block according to the proportion of the hoisting characteristics of the test pressure block during the continuous hoisting process includes:

[0022] Performing cluster analysis on each of the single loading features included in the continuous loading process to determine whether the single loading feature is the test pressure block loading feature;

[0023] Counting the proportion of the test pressure block loading characteristics in the multiple single loading characteristics;

[0024] It is determined according to the ratio whether the hoisting operation scene of the crane is the pressure test block hoisting operation scene.

[0025] Furthermore, before determining whether the hoisting operation scenario of the crane is the hoisting operation scenario of the test pressure block according to the ratio of the hoisting characteristics of the test pressure block during the continuous hoisting process, the method further includes:

[0026] Arranging the plurality of single-load features contained in a set time period in chronological order;

[0027] If the time interval between two adjacent single loading features is less than a set value, the time period corresponding to the two adjacent single loading features is determined to be the continuous loading process.

[0028] In a second aspect, the present invention provides a scene recognition device for identifying a crane hoisting operation scene, the scene recognition device comprising:

[0029] An acquisition module is configured to acquire hoisting operating condition characteristics, wherein the hoisting operating condition characteristics include single hoisting characteristics, which are acquired based on operating condition data of the crane during a single hoisting process and are used to characterize hoisting parameters of the crane during a single hoisting process.

[0030] A clustering module is configured to cluster the hoisting condition characteristics to obtain a plurality of hoisting characteristics, wherein the hoisting characteristics include a pressure test block hoisting characteristic, and the pressure test block hoisting characteristic indicates that the hoisting operation scenario of the crane matches the pressure test block hoisting operation scenario;

[0031] A processing module is used to determine whether the lifting operation scene of the crane is the test pressure block lifting operation scene according to the proportion of the test pressure block lifting characteristics in the continuous lifting process, wherein the continuous lifting process includes multiple single lifting processes.

[0032] In a third aspect, the present invention provides a scene recognition system, comprising the scene recognition device.

[0033] In a fourth aspect, the present invention provides a crane comprising the scene recognition system.

[0034] At least one embodiment of this specification can achieve the following beneficial effects:

[0035] The embodiment of this specification obtains single lifting characteristics by segmenting the lifting condition data, and by clustering the single lifting characteristics, it can accurately determine whether the single lifting characteristics are test pressure block lifting characteristics. Furthermore, according to the proportion of test pressure block lifting characteristics in multiple single lifting characteristics contained in the continuous lifting process, it is determined whether the continuous lifting process is a test pressure block lifting operation scenario. This arrangement improves the accuracy of crane work scene recognition compared to the existing technology of complex crane work scenes when using manual recognition, because it is impossible to perform work scene recognition for multiple single lifting processes contained in the lifting work scene separately, and only a rough judgment of the complex crane work scene is made based on experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 The figure shows a flow chart of a scene recognition method provided by an embodiment of this specification;

[0037] Figure 2 The figure shows a specific flow chart of the scene recognition method provided by the embodiment of this specification;

[0038] Figure 3 FIG2 is a schematic diagram of a scene recognition device provided in an embodiment of this specification. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0040] The technical solutions provided by the embodiments of this specification are described in detail below with reference to the accompanying drawings.

[0041] Cranes are a traditional and widely used type of construction machinery. However, the operating data of cranes varies in different working scenarios. This data can indicate the operating conditions of a machine and is of great significance to its maintenance and use. Therefore, accurately identifying the working scenarios of cranes is of great significance. Existing technologies mainly rely on manual identification, which has low accuracy.

[0042] In order to solve the defects of the above-mentioned prior art, this solution provides the following embodiments:

[0043] A scene recognition method provided in the embodiment of the specification is specifically described with reference to the accompanying drawings:

[0044] Figure 1 A schematic flow chart of a scene recognition method provided in an embodiment of this specification.

[0045] like Figure 1 As shown, the process may include the following steps:

[0046] S202: Obtaining hoisting operating condition characteristics, wherein the hoisting operating condition characteristics include single hoisting characteristics, which are obtained based on operating condition data of the crane during a single hoisting process, and are used to characterize hoisting parameters of the crane during a single hoisting process.

[0047] In the embodiments of this specification, the single-load characteristics are obtained based on the operating condition data of the crane during a single load process. The operating condition data of the crane during a single load process may include data such as the crane's data time, actual weight, main arm angle, telescopic arm current, lifting and lowering amplitude current, main hoisting lifting and lowering current, auxiliary hoisting lifting and lowering current, and left and right rotation current. By extracting the fields of these operating condition data and dividing the single-load time period by the change in actual weight, a single-load time period can be divided. Within the single-load time period, a single-load characteristic can be generated to characterize the load parameters such as the average lifting weight, maximum lifting weight, lifting weight variance, single-load time, and the time ratio of each action current.

[0048] Since the lifting work of a crane is usually a continuous lifting process, which includes multiple single lifting processes, the lifting condition characteristics can also be understood as the data obtained by processing the original working condition data corresponding to the crane in the continuous lifting process, and the single lifting characteristics can be understood as the data obtained by processing the original working condition data generated by the crane in a single lifting process.

[0049] S204: Clustering the hoisting condition features to obtain a plurality of hoisting features, wherein the hoisting features include a pressure test block hoisting feature, and the pressure test block hoisting feature indicates that the hoisting operation scenario of the crane matches the pressure test block hoisting operation scenario.

[0050] In the embodiments of this specification, the loading condition characteristics can be understood as each single loading characteristic included in the continuous loading process; clustering can be understood as the clustering algorithm commonly used in the prior art. The multiple loading characteristics here are the clustering results of the loading condition characteristics, specifically the clustering results of each single loading characteristic. Since the continuous loading process includes multiple single loading characteristics, the clustering results (loading characteristics) are multiple. Among the multiple loading characteristics, the loading characteristics that characterize the test pressure block loading operation scene have a specific feature type, and the loading characteristics with this feature type can be determined as the test pressure block loading characteristics. Since the loading condition characteristics are the characteristics that characterize the crane working scene, and the crane's daily working scene includes test pressure block loading, the loading condition characteristics include the test pressure block loading characteristics, that is, the test pressure block loading characteristics are used to indicate that the crane's working scene is the test pressure block loading operation scene.

[0051] S206: Determine whether the lifting operation scenario of the crane is the test pressure block lifting operation scenario based on the proportion of the test pressure block lifting characteristics in a continuous lifting process, wherein the continuous lifting process includes a plurality of the single lifting processes.

[0052] In the embodiments of this specification, since the daily lifting operation of the crane is usually a continuous lifting process, and the continuous lifting process includes multiple single lifting processes, it is judged whether the crane lifting operation scene is a test pressure block lifting operation scene, that is, the proportion of the number of test pressure block loading features in the continuous lifting process including multiple single lifting processes is judged, and whether the current crane operation scene is a test pressure block lifting operation scene is determined based on the proportion of the number.

[0053] It should be understood that the order of some steps in the methods described in one or more embodiments of this specification can be interchanged according to actual needs, or some steps can be omitted or deleted.

[0054] therefore, Figure 1 The method in the embodiment of the present invention obtains single lifting features by segmenting the lifting condition data. By clustering the single lifting features, it is possible to accurately determine whether the single lifting features are test pressure block lifting features. Furthermore, according to the proportion of test pressure block lifting features in multiple single lifting features contained in the continuous lifting process, it is determined whether the continuous lifting process is a test pressure block lifting operation scenario. Compared with the existing technology, when manual identification is used for complex crane working scenes, since it is impossible to perform working scene identification for multiple single lifting processes contained in the lifting working scene respectively, only a rough judgment of the complex crane working scene is made based on experience, thereby improving the accuracy of crane working scene identification.

[0055] based on Figure 1 The present specification also provides some specific implementation plans of the method, which are described below.

[0056] like Figure 2 As shown, optionally, after clustering the hoisting working condition features to obtain a plurality of hoisting features, the method further includes:

[0057] S205: Classify the single loading characteristics to obtain the test pressure block loading characteristics.

[0058] In the embodiments of this specification, the loading condition characteristics are clustered, which is actually to determine the working scene to which the loading condition characteristics belong. After clustering the loading condition characteristics, the single loading characteristics are classified. The role of classification is to further improve the accuracy of determining the working scene to which the single loading condition characteristics belong. The classification of single loading characteristics can be specifically carried out through a classification model. The training samples of the classification model are the test pressure block loading characteristics among the multiple loading characteristics obtained by clustering. Therefore, the above classification algorithm is used to accurately determine whether each single loading condition characteristic is a test pressure block loading characteristic. The classification model can be based on actual needs. The existing classification model in the prior art is not limited here.

[0059] Optionally, obtaining the lifting condition characteristics includes: dividing a single lifting time period according to changes in the actual weight of the crane; obtaining the single lifting characteristics within the single lifting time period, and the single lifting characteristics include: average lifting weight, maximum lifting weight, lifting weight variance, single lifting duration, and current-to-time ratio of the lifting action.

[0060] In the embodiments of this specification, since the daily working condition of the crane is a continuous lifting process, the continuous lifting condition corresponds to a continuous time period. Therefore, the lifting characteristics of the crane directly obtained are the lifting condition characteristics corresponding to the continuous lifting process, that is, multiple single lifting characteristics in the continuous lifting process are mixed together. Therefore, in order to accurately distinguish the working scene to which each single lifting characteristic belongs, it is necessary to divide the mixed single lifting characteristics so that the working scene to which each single lifting characteristic belongs can be determined later. The specific division method is: according to the actual weight change law during each lifting operation of the crane, the time period corresponding to the continuous lifting process is divided into multiple single lifting time periods, and single lifting characteristics including but not limited to average lifting weight, maximum lifting weight, lifting weight variance, single lifting duration, current time ratio of lifting action, etc. are obtained within the single lifting time period.

[0061] Optionally, the hoisting condition feature further includes: a continuous hoisting feature, and the continuous hoisting feature is used to characterize the number of hoisting operations of the crane within a preset time period.

[0062] In the embodiments of this specification, the continuous loading feature is a derived loading feature based on the loading start time and single loading features such as the number of loading times within a set time period generated from the single loading duration. The number of loading times in the embodiments of this specification is a derived loading feature.

[0063] Optionally, clustering the hoisting condition features to obtain multiple hoisting features includes: performing dimensionality reduction processing on the single hoisting features using a principal component analysis method to obtain reduced-dimensionality hoisting features.

[0064] In the embodiments of this specification, the purpose of using the principal component analysis method to reduce the dimension of a single hoisting feature is to simplify the single hoisting feature so as to facilitate subsequent cluster analysis of the single hoisting feature.

[0065] The reduced-dimensional load features are used to train a clustering model.

[0066] In the embodiment of this specification, the load features after dimensionality reduction are used as training samples to train the clustering model.

[0067] The trained clustering model is used to perform cluster analysis on the single loading feature to obtain a plurality of the loading features.

[0068] In the embodiments of this specification, a trained clustering model is used to perform cluster analysis on the characteristics of each single load during a continuous crane load process, generating clustering results. The clustering results include multiple load characteristics, each of which is used to characterize a crane operation scenario and is used to identify the crane operation scenario. The clustering model is preferably a Kmeans clustering generation model.

[0069] Optionally, determining whether the lifting operation scenario of the crane is the test pressure block lifting operation scenario based on the proportion of the test pressure block lifting characteristics in the continuous lifting process includes: performing cluster analysis on each of the single lifting characteristics included in the continuous lifting process to determine whether the single lifting characteristics are the test pressure block lifting characteristics; counting the proportion of the test pressure block lifting characteristics in the multiple single lifting characteristics; and determining whether the lifting operation scenario of the crane is the test pressure block lifting operation scenario based on the proportion.

[0070] In the embodiment of this specification, a cluster analysis is performed on each single lifting feature included in the continuous lifting process to determine whether each single lifting operation scenario is a test pressure block lifting operation scenario. Finally, based on whether the proportion of the test pressure block lifting features in the continuous lifting process is greater than a set value, if it is greater than the set value, it is determined whether the continuous lifting process is a test pressure block lifting operation scenario. The set value is pre-set according to actual conditions.

[0071] Optionally, before determining whether the lifting operation scene of the crane is the test pressure block lifting operation scene based on the ratio of the test pressure block lifting characteristics in the continuous lifting process, the method also includes: arranging the multiple single lifting characteristics contained in the set time period in chronological order; if the time interval between two adjacent single lifting characteristics is less than a set value, determining that the time period corresponding to the two adjacent single lifting characteristics is the continuous lifting process.

[0072] The above scheme provided in the embodiment of this specification is used to determine whether the continuous lifting process is a test pressure block lifting operation scenario. However, in order to identify the lifting operation scenario of the crane, it should be determined first what is a continuous lifting process. The specific steps for determining a continuous lifting process include: arranging the single lifting features contained in a set time period in chronological order. The operation set in this way is: restoring the actual working conditions of the crane, and then judging whether the time interval between any two adjacent single lifting features is less than the set value. The set value can be set according to the actual situation. If it is less than the set value, the time period corresponding to the two adjacent single lifting features is a continuous lifting process. This cycle is repeated until the time interval between the two adjacent single lifting features is greater than the set value, thereby determining a continuous lifting process containing multiple single lifting features.

[0073] like Figure 3 As shown, based on the same idea, the present invention also provides a scene recognition device corresponding to the above scene recognition method, which is used to recognize the hoisting operation scene of the crane, and the scene recognition device includes:

[0074] Acquisition module 410: used to acquire hoisting condition characteristics, wherein the hoisting condition characteristics include single hoisting characteristics, which are obtained based on the working condition data of the crane during a single hoisting process and are used to characterize the hoisting parameters of the crane during a single hoisting process;

[0075] A first processing module 420 is configured to cluster the hoisting condition characteristics to obtain a plurality of hoisting characteristics, wherein the hoisting characteristics include a pressure test block hoisting characteristic, and the pressure test block hoisting characteristic indicates that the hoisting operation scenario of the crane matches the pressure test block hoisting operation scenario;

[0076] The second processing module 430 is configured to determine whether the crane's lifting operation scenario is the test pressure block lifting operation scenario based on a ratio of the test pressure block lifting characteristics during a continuous lifting process, wherein the continuous lifting process includes a plurality of the single lifting processes.

[0077] Furthermore, after clustering the hoisting operating condition features to obtain a plurality of hoisting features, the first processing module 420 is further configured to:

[0078] The single loading characteristics are classified to obtain the test pressure block loading characteristics.

[0079] Furthermore, the obtaining of the hoisting working condition characteristics includes:

[0080] According to the change of the actual weight of the crane, a single lifting time period is divided;

[0081] During the single lifting time period, the single lifting characteristics are obtained, and the single lifting characteristics include: average lifting weight, maximum lifting weight, lifting weight variance, single lifting time, and current-to-time ratio of the lifting action.

[0082] Furthermore, the hoisting condition characteristics also include: a continuous hoisting characteristic, and the continuous hoisting characteristic is used to characterize the number of hoisting operations of the crane within a preset time period.

[0083] Furthermore, the first processing module 420 is specifically configured to:

[0084] Using principal component analysis to perform dimensionality reduction processing on the single load feature to obtain a reduced-dimensional load feature;

[0085] Training a clustering model using the dimension-reduced load features;

[0086] The trained clustering model is used to perform cluster analysis on the single loading feature to obtain a plurality of the loading features.

[0087] Furthermore, the second processing module 430 is specifically configured to:

[0088] Performing cluster analysis on each of the single loading features included in the continuous loading process to determine whether the single loading feature is the test pressure block loading feature;

[0089] Counting the proportion of the test pressure block loading characteristics in the multiple single loading characteristics;

[0090] It is determined according to the ratio whether the hoisting operation scene of the crane is the pressure test block hoisting operation scene.

[0091] Furthermore, before determining whether the hoisting operation scenario of the crane is the hoisting operation scenario of the test pressure block according to the ratio of the hoisting characteristics of the test pressure block during the continuous hoisting process, the device is further used to:

[0092] Arranging the plurality of single-load features contained in a set time period in chronological order;

[0093] If the time interval between two adjacent single loading features is less than a set value, the time period corresponding to the two adjacent single loading features is determined to be the continuous loading process.

[0094] Based on the same idea, the present invention provides a scene recognition system corresponding to the above scene recognition method, including the scene recognition device.

[0095] Based on the same idea, the present invention also provides a crane corresponding to the above-mentioned scene recognition method, including the scene recognition system.

[0096] The basic principles of the present invention have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, and effects mentioned in the present invention are merely illustrative and non-limiting, and should not be construed as necessarily possessed by each embodiment of the present invention. Furthermore, the specific details disclosed above are provided for illustrative purposes and to facilitate understanding, and are not intended to be limiting. These details do not necessarily limit the present invention to being implemented using these specific details.

[0097] The block diagrams of the devices, apparatuses, equipment, and systems involved in the present invention are intended to be illustrative examples only and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems may be connected, arranged, or configured in any manner. Words such as "include," "comprise," "have," and the like are open-ended words, meaning "including but not limited to," and may be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or" and may be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and may be used interchangeably therewith.

[0098] It should also be noted that in the apparatus, device and method of the present invention, each component or each step can be decomposed and / or recombined, and such decomposition and / or recombination should be regarded as equivalent solutions of the present invention.

[0099] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present invention. Therefore, the present invention is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0100] It should be understood that the qualifiers "first", "second", "third", "fourth", "fifth" and "sixth" used in the description of the embodiments of the present invention are only used to more clearly illustrate the technical solutions and cannot be used to limit the scope of protection of the present invention.

[0101] The above description has been provided for the purpose of illustration and description. Furthermore, this description is not intended to limit the embodiments of the present invention to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A scene recognition method, characterized in that: For identifying a crane hoisting operation scene, the scene recognition method includes: Obtaining a hoisting operating condition characteristic, wherein the hoisting operating condition characteristic includes a single hoisting characteristic, the single hoisting characteristic being obtained based on operating condition data of the crane during a single hoisting process, and the single hoisting characteristic being used to characterize a hoisting parameter of the crane during the single hoisting process; Clustering the hoisting condition features to obtain a plurality of hoisting features, wherein the hoisting features include a pressure test block hoisting feature, wherein the pressure test block hoisting feature indicates that a hoisting operation scenario of the crane matches a pressure test block hoisting operation scenario; Whether the lifting operation scene of the crane is the lifting operation scene of the test pressure block is determined according to the ratio of the lifting characteristics of the test pressure block in a continuous lifting process, wherein the continuous lifting process includes a plurality of the single lifting processes.

2. The method according to claim 1, characterized in that After clustering the hoisting operating condition features to obtain a plurality of hoisting features, the method further includes: The single loading characteristics are classified to obtain the test pressure block loading characteristics.

3. The method according to claim 1, characterized in that The obtaining of the hoisting working condition characteristics includes: According to the change of the actual weight of the crane, a single lifting time period is divided; During the single lifting time period, the single lifting characteristics are obtained, and the single lifting characteristics include: average lifting weight, maximum lifting weight, lifting weight variance, single lifting time, and current-to-time ratio of the lifting action.

4. The method according to claim 1, wherein The hoisting operating condition characteristics further include: a continuous hoisting characteristic, and the continuous hoisting characteristic is used to characterize the number of hoisting times of the crane within a preset time period.

5. The method according to claim 1, wherein Clustering the hoisting working condition features to obtain multiple hoisting features includes: Using principal component analysis to perform dimensionality reduction processing on the single load feature to obtain a reduced-dimensional load feature; Training a clustering model using the dimension-reduced load features; The trained clustering model is used to perform cluster analysis on the single loading feature to obtain a plurality of the loading features.

6. The method according to claim 1, characterized in that The determining, based on the proportion of the test pressure block hoisting characteristics during the continuous hoisting process, whether the hoisting operation scenario of the crane is the test pressure block hoisting operation scenario includes: Performing cluster analysis on each of the single loading features included in the continuous loading process to determine whether the single loading feature is the test pressure block loading feature; Counting the proportion of the test pressure block loading characteristics in the multiple single loading characteristics; It is determined according to the ratio whether the hoisting operation scene of the crane is the pressure test block hoisting operation scene.

7. The method according to claim 1, characterized in that Before determining whether the hoisting operation scenario of the crane is the hoisting operation scenario of the test pressure block according to the ratio of the hoisting characteristics of the test pressure block during the continuous hoisting process, the method further includes: Arranging the plurality of single-load features contained in a set time period in chronological order; If the time interval between two adjacent single loading features is less than a set value, the time period corresponding to the two adjacent single loading features is determined to be the continuous loading process.

8. A scene recognition device, characterized in that: Used to identify the crane hoisting operation scene, the scene recognition device includes: An acquisition module is configured to acquire hoisting operating condition characteristics, wherein the hoisting operating condition characteristics include single hoisting characteristics, which are acquired based on operating condition data of the crane during a single hoisting process and are used to characterize hoisting parameters of the crane during a single hoisting process. A clustering module is configured to cluster the hoisting condition characteristics to obtain a plurality of hoisting characteristics, wherein the hoisting characteristics include a pressure test block hoisting characteristic, and the pressure test block hoisting characteristic indicates that the hoisting operation scenario of the crane matches the pressure test block hoisting operation scenario; A processing module is used to determine whether the lifting operation scene of the crane is the test pressure block lifting operation scene according to the proportion of the test pressure block lifting characteristics in the continuous lifting process, wherein the continuous lifting process includes multiple single lifting processes.

9. A scene recognition system, characterized in that: It comprises the scene recognition device as claimed in claim 8.

10. A crane, characterized in that: Comprising the scene recognition system as claimed in claim 9.

Images