Automated method for establishing list of work executed by crane

Abstract

An automated method of establishing a list of work executed by a crane, the method comprising the following steps:-a step (101) of collecting information from a control command unit (C2) of a crane (E) over at least one time period by a collection unit (UC); -a step (103) of processing the collected information to determine the work performed by the crane (E) during at least one time period, the performed work belonging to at least one work category (T1, T2, T3, T4, T5, T6), and determining at least one parameter associated with the at least one performed work and / or with the at least one performed work category (T1, T2, T3, T4, T5, T6).

Description

Technical Field

[0001] The invention relates to the field of construction and civil engineering and in particular presents the monitoring of technical progress on a construction site where cranes, in particular cranes, are located. Background Art

[0002] The progress of some construction sites may differ significantly from the initial forecast. In such cases, manual timing analyses are sometimes performed in an attempt to reorganize the remaining work to catch up. These timing analyses require at least one person to travel to the site over a period of one to several days. Furthermore, it is not possible to perform these manual timing analyses systematically at all construction sites. Therefore, automated tools for monitoring the progress of the work performed offer a clear advantage to construction sites.

[0003] Therefore, the present invention aims to propose a solution to all or part of these problems. Summary of the invention

[0004] To this end, the invention relates to an automated method for creating a list of various categories of work performed by a crane during different time periods, the method comprising the following steps:

[0005] - A step of collecting, by a collecting unit, information from the control command unit of the crane during at least one period of time;

[0006] - a step of processing by the local processing unit and / or the remote processing unit the information collected by the collection unit to determine the work performed by the crane in at least one time period, the performed work belonging to at least one category of performed work and to determine at least one parameter associated with at least one performed work and / or with at least one category of performed work, the processing step comprising implementing by the local processing unit and / or the remote processing unit an artificial intelligence algorithm trained during a learning phase to be executed during a prediction phase of the processing step, the artificial intelligence algorithm using at least one context information to determine the performed work and / or the category of performed work, the context information being one of at least one lifting time, a maximum load, a maximum speed, the location of a load pickup point and a load unloading point, the location of a delivery point and the location of a storage area.

[0007] The invention therefore proposes to exploit the crane on a construction site to recover data, and in particular information from the control command unit of the crane, for example in a continuous manner, which data will be used to establish one or more available parameters to establish the actual activity of the crane and thus determine the progress of the site; the crane is usually the main element on site, being the core of most operations / works, such as but not limited to concrete pouring work, load-bearing structural elements (beams, double walls, etc.), etc. The advantage of the invention therefore lies in the exploitation of data from the control command unit of the crane, that is to say from a unit inherently present on the crane, for monitoring the progress of the work actually performed, before a possible comparison with the planned work, so as to be able to reliably assess delays. The invention therefore does not require the presence and / or integration of additional sensors on the crane. Furthermore, the invention does not require the use of data external to the relevant site. Finally, the invention is simple and inexpensive to implement by exploiting existing materials on the crane to extract the necessary information, and does not require the addition of additional materials (additional sensors or otherwise) on the crane.

[0008] According to one embodiment, the present invention includes one or more of the following features alone or in a technically acceptable combination.

[0009] According to one embodiment, the collected information includes at least one of the following: a load signal indicating the mass of the load lifted by the crane, a position signal of the hook of the crane in space, a speed signal indicating the change of the frequency converter, and a signal indicating the electrical state of the crane (such as an on or activated state when the crane is on, a deactivated or shut down state when the crane is shut down, a standby state when the lifting device is in standby mode, a state indicating that it is starting up, or a state indicating that it is shutting down).

[0010] According to one possibility, the electrical status of the crane is provided by a control command unit of the crane.

[0011] According to one possibility, the distribution of the load signal from the collecting step is compared with at least one distribution or a typical distribution of a model load signal obtained during a learning phase of the artificial intelligence algorithm, said model load signal distribution representing a class of performed work.

[0012] According to this possibility, comparing the distribution of the load signal from the collecting step with at least one model load signal distribution makes it possible to identify the performed work or the category of performed work of the crane.

[0013] According to one embodiment, the load signal from the collecting step is compared to a set of model signals determined by a learning phase of an artificial intelligence algorithm.

[0014] According to one possibility, the creation of these model signals and their implementation are based on distances between the signals obtained by dynamic time deformation, making it possible to create a model signal and subsequently a category of performed work of the crane.

[0015] According to one possibility, the load signal obtained in the collection step is pre-divided into a certain number of time-limited lifting periods, that is to say represented by a lifting start and a lifting end.

[0016] According to one possibility, a division is performed on the load signal, for example by means of a deterministic algorithm, so that different lifting cycles can be extracted.

[0017] The dynamic time deformation used in the learning step thus makes it possible to carry out a comparison step which makes it possible to define different categories of performed work based on the distribution of the load signal, while in the comparison step the identified lifting periods (i.e. delimited and normalized by the start and the end of the lifting) are compared via dynamic time deformation with the centroid of each work category (representing the average period of the category considered).

[0018] According to one embodiment, at least one category of performed work during at least one time period includes at least one of concrete pouring, transfer of a type of load, positioning of a type of load, empty load movement, material truck unloading.

[0019] According to one embodiment, at least one category of performed work during at least one time period will be an indeterminate category, or a period of inactivity.

[0020] According to one embodiment, one type of load comprises at least one of a concrete bucket, a rubble bucket, one or more building materials, one or more formwork elements, one or more concrete reinforcement elements, and a prefabricated element.

[0021] According to one embodiment, the building material comprises at least one of a set of pillars, a wall formwork (ie, formwork), and a floor formwork element.

[0022] According to one embodiment, the prefabricated element comprises at least one of a staircase, a balcony, a double wall.

[0023] According to one embodiment, at least one parameter associated with at least one performed work category includes at least one of the following: the duration of the performed work belonging to the at least one work category, the mass of the load lifted during the performed work belonging to the at least one work category, the movement of the load lifted during the performed work belonging to the at least one work category, the average duration of the performed work during different time periods belonging to the work category, the maximum duration of the performed work during different time periods belonging to the work category, the shortest duration of the performed work during different time periods belonging to the work category, the minimum mass lifted during the performed work during different time periods belonging to the work category, and the maximum mass lifted during the performed work during different time periods belonging to the work category.

[0024] According to one implementation mode, the artificial intelligence algorithm is further trained to classify at least one executed job determined during the processing step according to at least one job category.

[0025] According to one mode of implementation, at least one parameter associated with the work performed is used during the processing step to determine another parameter associated with at least one category of work.

[0026] According to one embodiment, the context information is at least one of a location of a concrete delivery point of a mixer truck, a location of a material or raw material delivery point of a delivery truck, and a location of a storage point of material or raw materials delivered by a delivery truck.

[0027] According to one mode of implementation, the context information is associated with at least one parameter determined during the processing step.

[0028] According to one embodiment, the processing step generates a description of the work performed by the crane, the description taking at least one form from the following: a graph representing at least one performed work as a function of time represented along a time axis according to the category of the performed work, a pie chart type graph representing the relative importance of at least one parameter associated with at least one work category, a summary table of the values ​​of at least one parameter associated with at least one work category, a three-dimensional representation of the start and end points of at least one performed work belonging to at least one work category.

[0029] According to one embodiment, the method further comprises the step of comparing at least one executed work belonging to at least one executed work category with at least one planned work in order to determine a difference between the at least one executed work and the at least one planned work.

[0030] According to one embodiment, the step of processing the collected information is performed locally on the crane.

[0031] According to one implementation mode, the method further comprises a step of transmitting the collected information to a remote processing unit placed on a remote server, the remote processing unit being configured to implement a step of processing the collected data.

[0032] According to one mode of implementation, the method also comprises a step of transmitting a description of at least one work performed during the processing step to a display unit placed locally on the crane, in order to allow local display and monitoring of the work performed.

[0033] According to one mode of implementation, the processing steps are performed locally on a local processing unit of the crane, or on said remote processing unit located on a remote server.

[0034] According to one mode of implementation, the display step is performed locally on a display unit of the crane, or on a remote display unit and for example associated with a remote server.

[0035] According to one aspect, the present invention relates to a lifting system comprising a crane and a remote server, the crane comprising a control command unit of the crane, the crane further comprising a collecting unit, the collecting unit being configured to collect information from the control command unit of the crane within at least one time period, the collecting unit being configured to transmit the collected information to a remote processing unit arranged on the remote server, the remote processing unit being configured to perform processing on the collected information to determine the work performed by the crane during at least one time period, the performed work belonging to at least one work category, and to determine at least one parameter associated with at least one performed work and / or at least one performed work category, the processing comprising implementing by the remote processing unit an artificial intelligence algorithm trained during a learning phase to perform the processing during a prediction phase, the artificial intelligence algorithm using at least one piece of context information to determine the performed work and / or the performed work category, the context information being at least one of the lifting time, the maximum load, the maximum speed, the location of the load pickup point and the location of the load unloading point, the location of the delivery point, and the location of the storage area.

[0036] According to another aspect, the present invention relates to a crane, comprising a control command unit of the crane and a local processing unit arranged on the crane, the crane also comprising a collecting unit, the collecting unit being configured to collect information from the control command unit of the crane during at least one time period, the collecting unit being configured to transmit the collected information to the local processing unit arranged on the crane, the local processing unit being configured to perform processing on the collected information to determine the work performed by the crane during at least one time period, the performed work belonging to at least one work category, and to determine at least one parameter associated with at least one performed work and / or at least one performed work category, the processing comprising implementing, by the unit processing, an artificial intelligence algorithm trained during a learning phase to perform the processing during a prediction phase, the artificial intelligence algorithm using at least one piece of context information to determine the performed work and / or the performed work category, the context information being at least one of a lifting time, a maximum load, a maximum speed, a location of a load pick-up point and a location of a load unloading point, a location of a delivery point, and a location of a storage area.

[0037] According to one embodiment, the local processing unit and / or the remote processing unit is further configured to generate a description of the work performed by the crane.

[0038] For a correct understanding, embodiments and / or implementations of the present invention are described with reference to the accompanying drawings, which respectively represent embodiments or implementations of the device and / or method according to the present invention by way of non-limiting examples. The same reference numerals in the drawings represent similar elements or elements with similar functions. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] [ Figure 1a ] is a first schematic and simplified illustration of a crane on a construction site configured to implement the method according to the present invention.

[0040] [ Figure 1b ]yes Figure 1a A second schematic and detailed view of the crane.

[0041] [ Figure 2 ] is a simplified diagram of the sequence of steps of the method according to the present invention.

[0042] [ Figure 3 ] is an example of a timing diagram generated by the method according to the invention, in which different categories of work performed by a crane are represented as a function of time along a time axis T, each category of performed work being represented by a specific color.

[0043] [ Figure 4] is an example of a representation of the distribution of different categories of work performed by a crane, the distribution being determined based on certain metrics or parameters, such as the duration of work performed, the number of lifts performed, or the duration of movements of the crane.

[0044] [ Figure 5 ] is an example of a three-dimensional representation of the locations in space of the start and end points of the work performed.

[0045] [ Figure 6 ] represents the stage of collecting different load signals corresponding to different cranes present on different construction sites.

[0046] [ Figure 7 ] indicates three load signal levels, representing three categories of performed work.

[0047] [ Figure 8 ] represents the phase in which the differently determined load signal profiles are transmitted to the local processing unit of the crane.

[0048] [ Fig. 9 ] schematically represents the presence of a single crane at a given construction site. Figure 6 The collection phase represented in Figure 8 The transmission phase represented. DETAILED DESCRIPTION

[0049] The present invention relates to a method 100 for automatically determining work performed by a crane E, such as a crane. Figure 1a and 1b The crane E comprises a control command unit C2 configured to communicate with various sensors mounted on the crane E; the different sensors include, for example, a load measuring sensor CCH, that is to say a sensor for measuring the mass of a load C lifted by the hook C1 of the crane E, and sensors for positioning movable parts of the crane E, such as a lifting encoder CL, an orientation encoder CO and even a distribution encoder CD.

[0050] The lifting encoder CL gives an image of the height of the lifting hook of the crane.

[0051] The distribution encoder CD gives an image of the position of the carriage and therefore of the lifting hook of the crane relative to its axis of rotation between its fixed (mature) part and its rotating part.

[0052] The orientation encoder CO gives an image of the angle of the rotating part of the crane relative to the reference angle of its fixed (fixed) part.

[0053] The control command unit C2 is also configured to command the implementation of the crane E, in particular depending on the measurements provided by the sensors, so as to produce work of different categories T1, T2, T3, T4, T5, T6 during different time periods, such as, for example, concrete pouring, transfer or positioning of a type of load, empty movement or other, such as material truck unloading, optionally also taking into account, within the category of performed work, periods of inactivity or periods of indeterminate activity.

[0054] More specifically, one type of load includes a concrete bucket, a rubble bucket, one or more building materials (e.g. a set of pillars), one or more formwork elements (also called formworks), one or more concrete reinforcement elements, prefabricated elements (e.g. stairs, balconies, double walls).

[0055] The crane E also comprises a collection unit UC configured to capture the different signals used by the control command unit C2 to implement and command the crane E to various categories of work.

[0056] The information collected by the collection unit UC therefore includes in particular a load signal representing the mass of the load C lifted by the crane E over time, a position signal of the hook C1 of the crane E in space, a speed signal representing the variation of the frequency converter and a signal representing the electrical state of the crane E. This list is not exhaustive.

[0057] The collected information is provided as input to the local processing unit UT and / or the remote processing unit UTD. The remote processing unit UTD may be placed on a remote server S, the collection unit UC being configured to communicate with the remote server S via a communication unit UCO of the crane E capable of transmitting and receiving information exchanged, for example, via an extended network such as the Internet. The local processing unit UT may be installed locally near the crane E or directly on it, the collection unit UC being configured to communicate with the local processing unit UT via a wired or wireless link.

[0058] The local processing unit UT and / or the remote processing unit UTD are configured to implement an artificial intelligence algorithm that is trained to determine, based on the information collected by the collection unit UC, the category of work performed by the crane E, such as concrete pouring, displacement of a type of load, transfer of a type of load or unloading of a material truck, and to determine different parameters associated with the category of work performed, such as the duration of the work performed, the mass of the load lifted during the work performed, the movement of the load lifted during the category of work performed; the artificial intelligence algorithm is trained to determine also, based on the information collected over different time periods, the travel distance between the load pickup point and the unloading point and the associated displacement speed, or the average duration of the work performed belonging to the category of work, or the maximum duration of the work performed belonging to the category of work, or the shortest duration of the work performed belonging to the type of work, or the minimum mass lifted during the work performed belonging to the category of work, or the maximum mass lifted during the work performed belonging to the type of work.

[0059] The artificial intelligence algorithm is implemented, for example, by an unsupervised temporal analysis grouping algorithm comprised in the local processing unit UT and / or the remote processing unit UTD.

[0060] The training of the artificial intelligence algorithm can be performed from a set of training data collected via the collection unit UC; before learning the artificial intelligence algorithm, it is planned to perform a stage of cleaning, normalization and grouping of the information collected by distribution and trend via dynamic time deformation to improve the learning results.

[0061] The implemented artificial intelligence algorithm is based on, for example, the distribution (ie the shape or "head") of the temporal load signal; this has the advantage of being simple and relatively cheap in terms of computing time.

[0062] According to one implementation example, in order to reduce the proportion of misclassification of performed work, i.e., the proportion of lifting cycles that are not classified in the expected category of performed work, such as concrete pouring detected as pre-positioned, the artificial intelligence algorithm enriches the contextual data related to these intrinsic features. According to an example of the artificial intelligence algorithm considering contextual data, when it is known that a mixer truck delivers concrete to a delivery point known by its location, the artificial intelligence algorithm uses this contextual information to infer that lifting cycles that start or end near this known location correspond to pouring cycles. According to another example of the artificial intelligence algorithm considering contextual data, when it is known that a delivery truck stops at another known delivery point and the delivered equipment or raw materials are stored in a storage area at a known location, the artificial intelligence algorithm uses this contextual information, the known location of the other delivery point, and the known location of the storage area to infer that a lifting cycle whose pickup point corresponds to the known location of the other delivery point and whose unloading point corresponds to the known location of the storage area corresponds to a work of the "truck unloading" type.

[0063] Thus, the artificial intelligence algorithm may take into account different contextual data associated with different characteristics of the lifting cycle, such as lifting time, maximum load, maximum speed, location of the load pickup point, and location of the load unloading point.

[0064] The method 100 thus allows automatically determining the types of activities performed by the crane E, ie the work categories T1 , T2 , T3 , T4 , T5 , T6 , as well as their duration, the movements involved, the loads lifted, etc.

[0065] See also Figure 2 , the method 100 comprises the following steps:

[0066] - Step 101, collecting information from the control command unit C2 of the crane E in at least one time period by the collection unit UC;

[0067] - A step 103 of processing the information collected by the collection unit UC in order to determine the work performed by the crane E during at least one period of time, the performed work belonging to at least one category of performed work T1, T2, T3, T4, T5, T6, and to determine at least one parameter associated with at least one performed work and / or with at least one category of performed work T1, T2, T3, T4, T5, T6.

[0068] Optionally, the method 100 also comprises a step 102 of transmitting the collected information to a remote processing unit UTD located on a remote server S, the remote processing unit UTD being configured to implement a step 103 of processing the collected data. According to another option, the step 103 of processing the collected information is performed locally on a local processing unit UT of the crane E.

[0069] The following table shows, by way of example, information that the method 100 according to the invention enables to be automatically determined from the control command information collected via the collection unit UC.

[0070] [Table 1]

[0071]

[0072] The number of work categories and the "granularity" of those categories is directly related to the number of parameters that are determined during the processing step 103 of collecting information and that are taken into account when determining and classifying the performed work when enough contextual parameters are found to distinguish one classification from another.

[0073] According to one embodiment, the processing step 103 is configured to generate a description of the work performed by the crane E in the form of a graph or a timing diagram representing the work performed in chronological order along a time axis T, for example by means of a color code, e.g. Figure 3 The description may also be in the form of a pie chart, indicating the relative importance of the values ​​of specific parameters (such as work duration) associated with the executed work T1, T2, T3, T4, T5, T6, such as Figure 4 The description may also take the form of a summary table of values ​​of different parameters associated with different performed work, such as, for example, Table 1 above; The description may also take the form of a representation of the start and end positions of the performed work, measured in three dimensions in a reference system defined by three axes X, Y, Z, such as Figure 5 as shown in the example.

[0074] Optionally, the method 100 further comprises a step 104 of comparing the performed work with the planned work program in order to determine the difference between the performed work and the planned work.

[0075] Also optionally, the method 100 further comprises a step of transmitting 105 the description of at least one executed work generated during the processing step 103 to a display unit UI arranged locally on the crane E or remotely arranged, to allow local display and monitoring of the executed work.

[0076] According to one possibility, the display unit UI further comprises a user interface allowing a user to interact with the display unit UI.

[0077] Thus, the processing steps may be performed locally on a local processing unit UT of the crane E or on a remote processing unit UTD located on a remote server S.

[0078] Likewise, the display step for monitoring the work performed can be performed locally on a display unit of the crane E, but also on a display unit located remotely and associated with a remote server S, for example.

[0079] Therefore, according to one aspect, the present invention relates to a lifting system comprising a crane E and a remote server S, the crane E comprising a control command unit C2 of the crane E, the crane E further comprising a collecting unit UC, which is configured to perform a collecting step 101 of information within at least one time period from the control command unit C2 of the crane E, the collecting unit UC being configured to transmit the collected information to a remote processing unit UTD located on the remote server S, the remote processing unit UTD being configured to perform a processing step 103 of the information collected by the collecting unit UC to determine the work performed by the crane E within at least one time period, the performed work belonging to at least one performed work category T1, T2, T3, T4, T5, T6, and to determine at least one parameter associated with at least one performed work and / or with at least one performed work category T1, T2, T3, T4, T5, T6.

[0080] According to another aspect, the present invention also relates to a crane E, which includes a control command unit C2 of the crane E and a local processing unit UT arranged on the crane E. The crane E also includes a collection unit UC, which is configured to perform a collection step 101 of information within at least one time period from the control command unit C2 of the crane E. The collection unit UC is configured to transmit the collected information to the local processor UT and / or the remote processing unit UTD arranged on the crane E. The local processing unit UT and / or the remote processing unit UTD are configured to perform a processing step 103 of the information collected by the collection unit UC to determine the work performed by the crane E within at least one time period, the performed work belongs to at least one performed work category T1, T2, T3, T4, T5, T6, and determine at least one parameter associated with at least one performed work and / or with at least one performed work category T1, T2, T3, T4, T5, T6.

[0081] According to one embodiment, the local processing unit UT and / or the remote processing unit UTD are configured to implement the artificial intelligence algorithm trained during the learning phase to perform processing step 103 during the prediction phase, using at least one context information to determine the performed work and / or the category of performed work and to generate a description of the work performed by the crane E.

[0082] According to one possibility, the learning phase of the artificial intelligence algorithm includes a phase of collecting data from control command units of cranes operating at different construction sites, such as Figure 6 shown.

[0083] According to one possibility, the collection phase can collect data representative of the different load signals corresponding to each crane present on each considered site, which makes it possible to constitute and continuously enrich the remote database BDD with a large number of load signals.

[0084] Likewise, depending on one possibility, the collection phase can collect contextual information, which can also enrich the remote database.

[0085] This enrichment allows the extraction and determination of different load signal distributions, each of which represents a type of performed work.

[0086] Thus, the learning phase of the artificial intelligence algorithm makes it possible to determine at least one distribution of a model load signal representative of a class of performed work.

[0087] For example and Figure 7 As shown, where the abscissa axis represents duration and the ordinate axis is expressed in kilonewtons (kN), a first load signal distribution a represents concrete pouring, a second load signal distribution b represents positioning of a load type, and a third load signal distribution c represents transfer of a load type.

[0088] Once determined, different model load signal distributions or typical distributions a, b, c can be communicated to the local processing unit / remote processing unit of each crane, such as Figure 8 This allows each local processing unit / remote processing unit to have a different model distribution of the load signal so that it can be identified by performing a distribution comparison step via a distance calculation based on dynamic time deformation and then classifying the load signal of the corresponding lifting equipment according to one of the categories of the performed work.

Claims

1. An automated method (100) for establishing a list of work of various categories (T1, T2, T3, T4, T5, T6) to be performed by a crane (E) during different time periods, the method comprising the following steps: - a step (101) of collecting, by means of a collecting unit (UC), information from a control command unit (C2) of said crane (E) during at least one period of time; - A step (103) of processing, by a local processing unit (UT) and / or a remote processing unit (UTD), the information collected by the collecting unit (UC) in order to determine work performed by the crane (E) during at least one time period, the performed work belonging to at least one category of performed work (T1, T2, T3, T4, T5, T6), and to determine at least one parameter associated with at least one performed work and / or with the at least one category of performed work (T1, T2, T3, T4, T5, T6). wherein the processing step (103) comprises implementing, by the local processing unit (UT) and / or the remote processing unit (UTD), an artificial intelligence algorithm trained during the learning phase to perform the processing step (103) during the prediction phase, Wherein, the artificial intelligence algorithm uses at least one contextual information to determine the performed work and / or the category of the performed work, and the contextual information is at least one of lifting time, maximum load, maximum speed, the location of the load pick-up point and the location of the load unloading point, the location of the delivery point and the location of the storage area.

2. The method (100) according to claim 1, wherein: The collected information includes at least one of a load signal representing the mass of the load lifted by the crane, a position signal of the hook (C1) of the crane in space, a speed signal representing the change of the frequency converter, and a signal representing the electrical status of the crane.

3. The method (100) according to claim 2, wherein: The load signal from the collecting step is compared to a set of model signals determined by the learning phase of the artificial intelligence algorithm.

4. The method (100) according to any one of the preceding claims, wherein: The at least one category of work performed during the at least one time period includes at least one of concrete pouring, transfer of a type of load, positioning of a type of load, empty load movement, and material truck unloading.

5. The method (100) according to any one of the preceding claims, wherein: The one type of load includes at least one of a concrete bucket, a rubble bucket, one or more building materials, one or more formwork elements, one or more concrete reinforcement elements, and a precast element.

6. The method (100) according to any one of the preceding claims, wherein: The at least one parameter associated with the at least one performed work category (T1, T2, T3, T4, T5, T6) comprises at least one of the following: duration of the performed work belonging to the at least one work category (T1, T2, T3, T4, T5, T6), mass of the load lifted during the performed work belonging to the at least one work category (T1, T2, T3, T4, T5, T6), movement of the load lifted during the performed work belonging to the at least one work category (T1, T2, T3, T4, T5, T6), load movement belonging to the at least one work category (T1, T2, T3, T4, T5, T6). The average duration of the work performed during different time periods, the maximum duration of the work performed during different time periods belonging to the work category (T1, T2, T3, T4, T5, T6), the minimum duration of the work performed during different time periods belonging to the work category (T1, T2, T3, T4, T5, T6), the minimum mass lifted during the work performed during different time periods belonging to the work category (T1, T2, T3, T4, T5, T6), the maximum mass lifted during the work performed during different time periods belonging to the work category (T1, T2, T3, T4, T5, T6).

7. The method (100) according to any one of the preceding claims, wherein: The processing step (103) generates a description of the work performed by the crane (E), the description taking at least one form from the following: a graph representing the at least one performed work as a function of time represented along a time axis according to the categories of work performed (T1, T2, T3, T4, T5, T6), a pie chart type graph representing the relative importance of the at least one parameter associated with the at least one work category, a summary table of the at least one parameter values ​​associated with the at least one work category (T1, T2, T3, T4, T5, T6), a three-dimensional representation of the start and end points of the at least one performed work belonging to the at least one work category (T1, T2, T3, T4, T5, T6).

8. According to the method (100) described in any of the preceding claims, the method also includes a step (104) of comparing the at least one executed work belonging to the at least one executed work category (T1, T2, T3, T4, T5, T6) with at least one planned work so as to determine the difference between the at least one executed work and the at least one planned work.

9. The method (100) according to any one of the preceding claims, wherein: A processing step (103) of the collected information is performed locally on the crane.

10. The method (100) according to any one of the preceding claims, further comprising the step of transmitting (102) the collected information to a remote processing unit (UTD) located on a remote server (S), the remote processing unit being configured to implement the processing step (103) of the collected information.

11. The method (100) according to the preceding claim, when it is dependent on claim 9, further comprising a transmission step (105) of the description of at least one executed work generated during the processing step (103) to a display unit arranged locally on the crane (E) or remotely, to allow local display and monitoring of the executed work.

12. A lifting system, comprising a crane (E) and a remote server (S), wherein the crane (E) comprises a control command unit (C2) of the crane (E), and the crane (E) further comprises a collecting unit (UC), wherein the collecting unit (UC) is configured to perform a collecting step (101) of information from the control command unit (C2) of the crane (E) within at least one time period, wherein the collecting unit (UC) is configured to transmit the collected information to a local processing unit (UT) and / or a remote processing unit (UTD) located on the remote server (S), wherein the local processing unit (UT) and / or the remote processing unit (UTD) is configured to perform a processing step (103) on the collected information to determine the operations performed by the crane (E) during at least one time period. work, the performed work belonging to at least one work category (T1, T2, T3, T4, T5, T6), and determining at least one parameter associated with at least one performed work and / or at least one performed work category (T1, T2, T3, T4, T5, T6), wherein the processing step (103) includes implementing an artificial intelligence algorithm trained during a learning phase by the local processing unit (UT) and / or the remote processing unit (UTD) to perform the processing step (103) during a prediction phase, and wherein the artificial intelligence algorithm uses at least one context information to determine the performed work and / or the category of the performed work, the context information being at least one of a time lifting capacity, a maximum load, a maximum speed, a location of a pickup point and a location of a unloading point, a location of a delivery point, and a location of a storage area.

13. A crane (E), comprising a control command unit (C2) of the crane and a local processing unit (UT) arranged on the crane (E), the crane (E) further comprising a collecting unit (UC), the collecting unit (UC) being configured to perform a step of collecting (101) information from the control command unit (C2) of the crane (E) in at least one time period, the collecting unit (UC) being configured to transmit the collected information to the local processing unit (UT) arranged on the crane (E), the local processing unit (UT) being configured to perform a processing step (103) on the collected information to determine work performed by the crane (E) during the at least one time period, the performed work belonging to at least one work category (T1, T2, T3, T4, T5, T6), and determining at least one parameter associated with at least one performed work and / or with said at least one performed work category (T1, T2, T3, T4, T5, T6), wherein said processing step (103) comprises implementing by said local processing unit (UT) an artificial intelligence algorithm trained during a learning phase to perform said processing step (103) during a prediction phase, and wherein said artificial intelligence algorithm uses at least one context information to determine said performed work and / or said performed work category, said context information being at least one of a lifting time, a maximum load, a maximum speed, a location of a load pickup point and a location of a load unloading point, a location of a delivery point and a location of a storage area.

Images