Sensor station and method for predicting vehicle faults

Abstract

A sensor station (600) for an automated vehicle (301) operating in an automated storage and retrieval system, the sensor station being in the form of a wall-mounted chassis or a support, into which the vehicle can travel or under which the vehicle can travel. The chassis or support has a connection point (602) for attaching a sensor (604) and / or one or more compartments (606) for inserting a module (608) containing the sensor. The station can be mounted on the track system of the storage system at a location that minimizes interference with the operation of other vehicles in the automated storage and retrieval system. The collected data is used in a method for predicting faults by comparing the data collected by the sensors with reference values and / or historical maintenance data.

Description

Technical Field

[0001] The present invention relates to an automatic storage and retrieval system for storing and retrieving containers, and in particular to a sensor station arranged to collect data from an automatic vehicle simulating its operation in the automatic storage and retrieval system, which data can be used in a method for early detection and / or prediction of potential failures of the vehicle. Background Art

[0002] Figure 1 A prior art automatic storage and retrieval system 1 having a frame structure 100 is disclosed, and Figure 2 , Figure 3 and Figure 4 Three different prior art container handling vehicles 201 , 301 , 401 suitable for operating on such a system 1 are disclosed.

[0003] The frame structure 100 comprises upright members 102 and a storage volume comprising storage columns 105 arranged in rows between the upright members 102. In these storage columns 105, storage containers 106 (also called boxes) are stacked one on top of the other to form stacks 107. The members 102 may typically be made of metal, for example extruded aluminum profiles.

[0004] The frame structure 100 of the automated storage and retrieval system 1 comprises a rail system 108 arranged across the top of the frame structure 100, on which a plurality of container handling vehicles 201, 301, 401 can operate to lift and lower storage containers 106 from and into the storage array 105, and also to transport storage containers 106 above the storage array 105. The rail system 108 comprises: a first set of parallel rails 110 arranged to guide the container handling vehicles 201, 301, 401 to move across the top of the frame structure 100 in a first direction X; and a second set of parallel rails 111 arranged perpendicular to the first set of rails 110 to guide the container handling vehicles 201, 301, 401 to move in a second direction Y perpendicular to the first direction X. The containers 106 stored in the array 105 are accessed by the container handling vehicles 201, 301, 401 through access openings 112 in the rail system 108. The container handling vehicles 201 , 301 , 401 may move laterally (ie, in a plane parallel to the horizontal XY plane) over the storage row 105 .

[0005] Upright members 102 of frame structure 100 may be used to guide storage containers during raising and lowering of containers from row 105. Stack 107 of containers 106 is generally self-supporting.

[0006] Each prior art container handling vehicle 201, 301, 401 includes a body 201a, 301a, 401a and a first set of wheels and a second set of wheels 201b, 201c, 301b, 301c, 401b, 401c that enable the container handling vehicle 201, 301, 401 to move laterally in the X direction and the Y direction, respectively. Figure 2 , Figure 3 and Figure 4 , the two wheels in each set are fully visible. The first set of wheels 201b, 301b, 401b is arranged to engage with two adjacent tracks in the first set of tracks 110, and the second set of wheels 201c, 301c, 401c is arranged to engage with two adjacent tracks in the second set of tracks 111. At least one of these sets of wheels 201b, 201c, 301b, 301c, 401b, 401c can be raised and lowered so that the first set of wheels 201b, 301b, 401b and / or the second set of wheels 201c, 301c, 401c can engage with the corresponding set of tracks 110, 111 at any time.

[0007] Each prior art container handling vehicle 201, 301, 401 also includes a lifting device for vertically transporting storage containers 106 (e.g., lifting storage containers 106 from and lowering storage containers 106 into the storage row 105). The lifting device includes one or more clamping / engaging devices that are suitable for engaging storage containers 106 and can be lowered from the vehicle 201, 301, 401 so that the position of the clamping / engaging device relative to the vehicle 201, 301, 401 can be adjusted in a third direction Z that is orthogonal to the first direction X and the second direction Y. Part of the clamping device of the container handling vehicle 301, 401 is Figure 3 and Figure 4 The container handling device 201 is shown in FIG. 2 and is indicated by reference numerals 304 and 404. The clamping device of the container handling device 201 is located at Figure 2 201a and is therefore not shown.

[0008] Conventionally, and also for purposes of the present application, Z=1 identifies the uppermost level of storage containers available below the rails 110, 111 (i.e., the level immediately below the rail system 108), Z=2 identifies the second level below the rail system 108, Z=3 identifies the third level, and so on. Figure 1 In the exemplary prior art disclosed in , Z=8 identifies the bottommost layer of the storage container. Similarly, X=1...n and Y=1...n identify the position of each storage column 105 in the horizontal plane. Thus, as an example, and using Figure 1 The Cartesian coordinate system X, Y, Z shown can be considered as Figure 1 The storage container 106' in FIG. 1 occupies storage position X=17, Y=1, Z=6. It can be considered that the container handling vehicles 201, 301, 401 are traveling in the Z=0 layer, and each storage column 105 can be identified by its X and Y coordinates. Therefore, it can also be considered that Figure 1 The storage container shown extending above the rail system 108 is arranged in the Z=0 level.

[0009] The storage volume of the frame structure 100 is generally referred to as a grid 104, wherein the possible storage positions within the grid are referred to as storage units. Each storage column can be identified by the position in the X-direction and the Y-direction, and each storage unit can be identified by the container number in the X-direction, the Y-direction and the Z-direction.

[0010] Each of the prior art container handling vehicles 201, 301, 401 includes a storage compartment or space for receiving and loading the storage container 106 when transporting the storage container 106 across the track system 108. The storage space may include a cavity disposed internally within the vehicle body 201a, 401a, such as Figure 2 and Figure 4 As shown, and as described in, for example, WO2015 / 193278A1 and WO2019 / 206487A1, the contents of which are incorporated herein by reference.

[0011] Figure 3 An alternative construction of a container handling vehicle 301 having a cantilever structure is shown. Such a vehicle is described in detail, for example, in NO 317366, the contents of which are also incorporated herein by reference.

[0012] Figure 2 The occupied area of ​​the chamber container handling vehicle 201 shown in the figure can cover an area with dimensions in the X-direction and the Y-direction substantially equal to the lateral extent of the storage column 105, such as described in WO2015 / 193278A1, the contents of which are incorporated herein by reference. The term "lateral" as used herein can mean "horizontal".

[0013] Alternatively, the footprint of the cavity container handling vehicle 401 may be larger than the lateral area defined by the storage row 105, such as Figure 1 and Figure 4 As shown in and disclosed, for example, in WO 2014 / 090684 A1 or WO 2019 / 206487 A1.

[0014] The track system 108 typically includes a track with grooves in which the wheels of the vehicle travel. Alternatively, the track may include an element extending upward, wherein the wheels of the vehicle include flanges to prevent derailment. These grooves and the elements extending upward are collectively referred to as guide rails. Each track may include one guide rail, or each track 110, 111 may include two parallel guide rails. In other track systems 108, each track may include one guide rail in one direction (e.g., the X direction), and each track may include two guide rails in another vertical direction (e.g., the Y direction). Each track 110, 111 may also include two guide rail members fastened together, each guide rail member providing one of a pair of guide rails provided by each track.

[0015] WO 2018 / 146304 A1 (the contents of which are incorporated herein by reference) shows a typical construction of a track system 108 , which includes tracks in the X-direction and the Y-direction and parallel guide rails.

[0016] In the frame structure 100, most of the rows 105 are storage rows 105, i.e. rows 105 in which storage containers 106 are stored in stacks 107. However, some of the rows 105 may have other purposes. Figure 1 In the embodiment of the present invention, the columns 119 and 120 are such special columns used by the container handling vehicles 201, 301, 401 to unload and / or pick up the storage containers 106, so that the storage containers can be transported to the access station (not shown), where the storage containers 106 can be accessed from the outside of the frame structure 100 or transferred out of or into the frame structure 100. In the art, such positions are generally referred to as "ports", and the columns where the ports are located can be referred to as "port columns" 119, 120. Transport to the access station can be in any direction, i.e. horizontal, inclined and / or vertical. For example, the storage container 106 can be placed in a random or special column 105 within the frame structure 100, and then picked up and transported to the port columns 119, 120 by any container handling vehicle for further transport to the access station. The transportation from the port to the access station may need to be moved in various directions by means such as a delivery vehicle, a trolley or other transportation routes. Note that the term "inclined" refers to the transport of storage container 106 with a general transport orientation somewhere between horizontal and vertical.

[0017] exist Figure 1In the embodiment, the first port column 119 can be, for example, a dedicated unloading port column, in which the container handling vehicles 201, 301, 401 can unload the storage container 106 to be transported to the access station or the transfer station, and the second port column 120 can be a dedicated picking port column, in which the container handling vehicles 201, 301, 401 can pick up the storage container 106 that has been transported from the access station or the transfer station.

[0018] The access station can generally be a pick-up station or a staging station that removes product items from or positions product items in the storage container 106. In the pick-up station or staging station, the storage container 106 is generally not removed from the automated storage and retrieval system 1, but is returned again to the frame structure 100 after being accessed. The port can also be used to transfer the storage container to another storage facility (e.g., to another frame structure or to another automated storage and retrieval system), to a transport vehicle (e.g., a train or truck), or to a production facility.

[0019] A conveyor system including conveyors is typically employed to transport storage containers between the port rows 119, 120 and the access station.

[0020] If the port rows 119, 120 and the access station are located at different levels, the conveyor system may include a lifting device with a vertical component for vertically transporting the storage containers 106 between the port rows 119, 120 and the access station.

[0021] The conveyor system may be arranged to transfer storage containers 106 between different frame structures, for example as described in WO 2014 / 075937 A1, the contents of which are incorporated herein by reference.

[0022] When accessing data stored in Figure 1When a storage container 106 in one of the plurality of columns 105 disclosed in the stack 107 is removed, one of the container handling vehicles 201, 301, 401 is instructed to take out the target storage container from the position of the target storage container 106 and transport it to the unloading port column 119. This operation involves moving the container handling vehicle 201, 301, 401 to a position above the storage column 105 where the target storage container 106 is located, taking out the storage container 106 from the storage column 105 using a lifting device (not shown) of the container handling vehicle 201, 301, 401, and transporting the storage container 106 to the unloading port column 119. If the target storage container 106 is located deep in the stack 107, that is, one or more other storage containers 106 are positioned above the target storage container 106, the operation also involves temporarily moving the storage container positioned above before lifting the target storage container 106 from the storage column 105. This step, sometimes referred to in the art as "digging," may be performed using the same container handling vehicle that is subsequently used to transport the target storage container to the unloading port row 119, or may be performed using one or more other cooperating container handling vehicles. Alternatively or in addition, the automated storage and retrieval system 1 may have container handling vehicles 201, 301, 401 that are specifically designed for the task of temporarily removing storage containers 106 from storage rows 105. After the target storage container 106 is removed from the storage row 105, the temporarily removed storage container 106 may be relocated to the original storage row 105. Alternatively, however, the removed storage container 106 may be relocated to other storage rows 105.

[0023] When a storage container 106 is to be stored in one of the columns 105, one of the container handling vehicles 201, 301, 401 is instructed to pick up a storage container 106 from the pick-up port column 120 and transport the storage container to a position above the storage column 105 where the storage container will be stored. After removing any storage container 106 positioned at or above a target position within the stack 107, the container handling vehicle 201, 301, 401 positions the storage container 106 at the desired position. The removed storage container 106 can then be lowered back into the storage column 105 or relocated to another storage column 105.

[0024] In order to monitor and control the automatic storage and retrieval system 1, for example, to monitor and control the position of each storage container 106 within the frame structure 100, the contents of each storage container 106, and the movement of container handling vehicles 201, 301, 401, so that the desired storage container 106 can be transported to the desired location at the desired time without causing the container handling vehicles 201, 301, 401 to collide with each other, the automatic storage and retrieval system 1 includes a control system 500, which is typically computerized and typically includes a database for tracking the storage containers 106.

[0025] Vehicle failure prediction, as follows:

[0026] As can be appreciated, the automated vehicles operating in the automated storage and retrieval system are complex devices susceptible to failure. Faulty vehicles are one of the main causes of system downtime. Historical maintenance data and experimental data for such vehicles indicate that many types of failures are preceded by observable events, such as observable anomalies and deviations in various vehicle parameters, such as the development of overheating, specific noises or vibrations, degradation of vehicle acceleration or the lifting capacity of the vehicle's lifting device, loss of energy consumption efficiency, battery charge capacity, and other observable parameters. Therefore, it is desirable to be able to predict or detect potential failures of the vehicle at an early stage so that corrective measures can be taken before the failure occurs. Summary of the invention

[0027] The invention is set forth and characterized in the independent claim, while the dependent claims describe further characteristics of the invention.

[0028] In one aspect, the invention relates to a sensor station arranged to be connected to the rail system of an automatic storage and retrieval system as described above. The station is arranged to allow an automatic vehicle running on the rails of the system to drive into the station. According to one aspect, the station includes wheel rotation means allowing the wheels of the vehicle to rotate when the vehicle is located in the station, such as treadles (motorized or passive), rollers, continuous belts, etc., which allow the vehicle to operate its drive wheels and perform a guide shifting operation by which the vehicle can raise or lower the wheel set to change direction. According to one aspect, the station is positioned above an empty or partially empty storage column so that the vehicle can perform or simulate the lifting and lowering of containers when located in the station.

[0029] The station is provided with one or more sensors and / or cameras for observing and / or recording various operating parameters of the vehicle. Examples of such sensors include cameras, microphones, infrared heat detectors, accelerometers, vibration sensors, voltmeters and other electronic test equipment, torque sensors, etc. Parameters measured by the sensors may include heat, noise, vibration, vehicle acceleration and deceleration, the lifting capacity of the vehicle lifting mechanism, the energy consumption efficiency of the vehicle, battery charging capacity and other observable parameters.

[0030] Preferably, the station is arranged so that the vehicle can simulate the vehicle performing normal tasks, wherein the sensors collect data from the vehicle as the vehicle performs these simulated tasks. In one aspect, the station is an enclosed structure having attachment points for the sensors or a compartment for receiving a removable module containing the sensors. In one aspect, the station includes one or more supports extending above the level of the track system, the supports including attachment points for the sensors.

[0031] In one aspect, the wheel rotation device includes treadmills, rollers, or continuous belts arranged in the rails of the track system. The wheel rotation device can be locked or otherwise prevented from rotating to allow the wheels of the vehicle to gain traction and traverse the device and move into position in the station, and then unlocked to allow the wheels of the vehicle to rotate on the device while the vehicle remains stationary.

[0032] The sensor installed in the station may be provided with its own power supply, or may be powered by the common power supply of the station, or alternatively by the vehicle battery (in which case the station may include an electrical connector to connect to the vehicle battery).

[0033] In a second aspect, the present invention relates to a method for detecting and / or predicting potential failures of a vehicle using data collected by sensor stations. In one aspect, the method includes establishing default baseline ranges for normal or acceptable values ​​for various vehicle parameters. The values ​​that may be established in conjunction with a failure of the vehicle may be for the vehicle as a whole or more nuanced in nature (i.e., the values ​​relate to individual components of the vehicle). According to one aspect of the invention, the data collected by the sensor stations are compared to default values ​​in order to detect or predict potential failures. According to one aspect, the data is compared to historical maintenance data and / or experimental data in order to derive a prediction of a failure. Examples of such comparisons / conclusions may include:

[0034] • Historical maintenance data or experimental data may indicate that failure of a particular component was preceded by a discrete frequency tone in the audible or inaudible spectrum, e.g. a specific frequency may indicate the degree of wear on a particular motor component,

[0035] • Heat buildup at specific locations on the vehicle may indicate a defect in a specific component, for example, heat measured at a location on the body adjacent to the battery compartment that exceeds a baseline temperature value for that specific location may indicate a problem with the battery,

[0036] • If the vehicle is observed to run slower than the baseline data would suggest for a given power input, this may indicate wheel bearing wear,

[0037] • Specific vibration patterns or intensities may indicate a specific defect or malfunction, such as deformation of a wheel or loosening of bolts securing a specific component within the vehicle.

[0038] The foregoing list is merely exemplary and not exhaustive, as maintenance data and / or experimental data may continually be developed to demonstrate correlations between observable deviations and specific faults.

[0039] In another aspect, the method includes using an artificial intelligence (AI) program, an artificial neural network, or a machine learning algorithm (hereinafter collectively or alternatively referred to as "AI") to detect or predict faults. According to this aspect, data is collected and transmitted to the AI, which generates an output in the form of a fault prediction or vehicle health status.

[0040] In a third aspect, the present invention relates to a method for training an AI to detect or predict failures of a vehicle operating in an automated storage and retrieval system. According to one aspect, the method includes: inputting baseline values, default values ​​for various vehicle parameters; inputting historical maintenance data and / or experimental data for a single vehicle or a batch of vehicles; and inputting sensor data accumulated from a single vehicle. According to this aspect, the AI ​​utilizes the accuracy or inaccuracy of the predictions generated by the AI ​​to improve its prediction accuracy.

[0041] According to one aspect, the present invention includes a sensor station for an automated vehicle operating in an automated storage and retrieval system, the station comprising a housing or one or more supports having connection points for attaching sensors and / or one or more compartments for inserting modules containing sensors, the station being mountable on a rail system at a position that minimizes interference with normal operation of other vehicles in the automated storage and retrieval system, and wherein the sensors are arranged to collect data about vehicle parameters as the vehicle simulates normal operation in a storage and retrieval system.

[0042] According to another aspect, the present invention includes a method for detecting or predicting a failure of an automated vehicle operating in an automated storage and retrieval system, the method comprising the steps of:

[0043] a. Establish a set of normal baseline values ​​for various vehicle parameters for the vehicle,

[0044] b. establishing historical maintenance data and / or experimental data for the vehicle or a batch of vehicles of similar model and design, the historical maintenance data and / or experimental data including correlations between observable vehicle parameters and the occurrence of vehicle failures,

[0045] c. driving the vehicle into a sensor station as described above,

[0046] d. using the sensors of the sensor station to collect data on vehicle parameters while the vehicle simulates its normal operation and missions while in the station,

[0047] e. comparing the data collected by the sensors with baseline values ​​and / or historical maintenance data and / or experimental data,

[0048] f. Based on the comparison, make a prediction of vehicle failure. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The following drawings are attached to facilitate understanding of the present invention. The drawings illustrate embodiments of the present invention which will now be described by way of example only, in which:

[0050] Figure 1 It is a three-dimensional diagram of the framework structure of the automatic storage and retrieval system of the prior art.

[0051] Figure 2 is a perspective view of a prior art container handling vehicle having an internally disposed cavity for carrying a storage container therein.

[0052] Figure 3 is a perspective view of a prior art container handling vehicle having a cantilever arm for carrying a storage container underneath.

[0053] Figure 4 is a bottom perspective view of a prior art container handling vehicle having an internally disposed cavity for carrying a storage container therein.

[0054] Figure 5 is a perspective view of a sensor station in the form of a housing into which a vehicle can drive.

[0055] Fig. 6A and Figure 6B A station comprising four vertical supports and two cross beams is shown.

[0056] Fig. 7A and Figure 7B A station comprising two vertical supports and a crossbeam is shown.

[0057] Fig. 8A and Figure 8BA detailed view of an embodiment of a station and a wheel rotation device is shown.

[0058] Fig. 9 is a flow chart showing the steps for training an artificial intelligence program, an artificial neural network, or a machine learning algorithm. DETAILED DESCRIPTION

[0059] In the following, embodiments of the present invention will be discussed in more detail with reference to the accompanying drawings. It should be understood, however, that the drawings are not intended to limit the present invention to the subject matter depicted in the drawings.

[0060] The frame structure 100 of the automatic storage and retrieval system 1 is combined with the above Figures 1 to 3 The frame structure 100 of the prior art described is constructed in a similar manner. That is, the frame structure 100 includes a plurality of upright members 102 and includes a first upper track system 108 extending in the X-direction and the Y-direction.

[0061] The frame structure 100 further comprises storage compartments in the form of storage rows 105 arranged between the plurality of components 102 , wherein storage containers 106 can be stacked to form stacks 107 within the storage rows 105 .

[0062] The frame structure 100 may be of any size. In particular, it should be understood that the frame structure may be larger than Figure 1 For example, the frame structure 100 may have a horizontal extent of more than 700×700 columns, and a storage depth of more than twelve containers.

[0063] Now refer to Figures 5 to 9 One embodiment of the automated storage and retrieval system according to the present invention is discussed in more detail.

[0064] Figure 5 Container handling vehicle 301 is shown running on rail system 108 of frame 100 and has already traveled into sensor station 600. Figure 5 In the illustrated embodiment, the sensor station 600 is in the form of a wall-mounted enclosure 601. It should be understood that the sensor station of the present invention also allows access to the container handling vehicle 401 or any automated vehicle operating in the system. The vehicle 301 is depicted as carrying the container 106 by its lifting mechanism to illustrate that the vehicle 301 can simulate its normal tasks when located in the station. Figure 5 As seen in FIG. 1 , a vehicle 301 holds a container 106 above an empty or partially empty storage row 105 from which the vehicle can raise or lower the container into the storage row.

[0065] Fig. 6A and Figure 6BA sensor station 600 is shown in the form of four vertical supports 603 connected by cross beams 605, while Fig. 7A and Figure 7B A sensor station is shown comprising two vertical supports 603 and a single cross beam 605. As can be appreciated, a sensor station according to the present invention may have any physical shape that allows a vehicle to drive into the station while providing the station's sensors with a line of sight to the vehicle to collect data.

[0066] According to one aspect, the wall enclosure 601 or vertical supports 603 and / or crossbars 605 include one or more connection points 602 to which one or more sensors 604 can be attached. As used herein, the term "sensor" should be understood as any form of equipment designed to observe, record and / or collect data, such as cameras, microphones, infrared heat detectors, accelerometers, vibration sensors, voltmeters and other electrical test equipment, torque sensors, etc. Alternatively, as Figure 5 As shown, the station may be provided with one or more compartments 606 into which may be inserted removable modules 608 including one or more sensors, computer equipment, etc. The station may include its own power supply 610 for powering the sensors and / or modules, or the station may be provided with an electrical connector 612 for connecting to a battery of a vehicle in order to power the sensors and / or modules.

[0067] like Fig. 8A and Figure 8B As shown, the station includes a wheel rotation device 607 on which the wheels of the vehicle can be rotated to simulate forward, backward or sideways movement, as well as a so-called "track shifting" operation by which the vehicle raises or lowers the wheel set to change direction. The wheel rotation device can be a treadmill, a roller, a continuous belt, etc. In one aspect, the wheel rotation device includes a treadmill that includes a rotating belt 609 that can be selectively locked to prevent rotation and unlocked to allow rotation.

[0068] The sensors 604 are arranged to collect data from the vehicle 301 while the vehicle is within the station simulating normal tasks of the vehicle in an automated storage and retrieval system, such as driving, braking, lifting and lowering containers. Alternatively, the station may include a charging connector 611 that may perform a dual function, i.e., charging the vehicle while allowing the sensors to collect data under charging operations. Accordingly, in one aspect, the station is positioned above an empty or partially empty storage row to allow for simulation of lifting and lowering operations.

[0069] Examples of data collected by the station's sensors include various vehicle parameters such as heat, noise, vibration, vehicle acceleration and deceleration, the lifting capacity of the vehicle's lifting mechanism, the vehicle's energy consumption efficiency, battery charge capacity, and other observable parameters.

[0070] According to another aspect, the present invention provides a method for detecting or predicting vehicle failure, comprising: Fig. 9 Conceptually shown. According to the method, vehicle data is introduced into a computer system that includes an artificial intelligence program, an artificial neural network, or a machine learning algorithm (hereinafter collectively or alternatively referred to as "AI"). Based on the data input, the AI ​​generates an output, which may include the detection or prediction of a vehicle fault. The AI ​​may run on the control system 500, or on a separate dedicated computer system.

[0071] According to the method, the data input to the AI ​​may include baseline, default value ranges established at the time of manufacture for various vehicle parameters. Examples of such baseline values ​​may include, but are not limited to:

[0072] • Normal, acceptable temperature ranges for the vehicle as a whole or for individual components of the vehicle. Such temperature ranges may include temperatures measured at specific locations on the vehicle body (e.g., at a wall near a motor or other component),

[0073] • A sound profile that includes the range of audible or inaudible frequencies generated by the vehicle during normal operation, such as the normal sound frequency range during lifting operations, during vehicle direction changes, during battery recharging, etc.

[0074] • the normal range of vibration values ​​during vehicle operation and while performing various activities,

[0075] • Torque range for lifting and lowering operations,

[0076] • The expected range of acceleration and deceleration values ​​for the vehicle under different loads

[0077] According to the method, the data input to the AI ​​may include historical maintenance data and / or experimental data related to vehicle failures. Such data may include, for example, identification of specific parameters associated with vehicle failures or identification of specific parameters that indicate that a vehicle failure may occur prior to the occurrence of a vehicle failure. Such historical and / or experimental data may include, but is not limited to:

[0078] • The frequency of the sound associated with or preceding the fault,

[0079] • The specific type of vibration or the specific amount of vibration associated with the fault, such as a specific vibration pattern or vibration intensity,

[0080] • The temperature of individual vehicle body components or specific locations on the vehicle body that are associated with or precede the failure,

[0081] • Battery degradation data,

[0082] • Changes in vehicle acceleration and / or deceleration that indicate a malfunction that is associated with or precedes the malfunction.

[0083] According to this method, the data input to the AI ​​may include previous data output from the AI ​​itself, which the AI ​​may utilize to improve the predictive accuracy of future outputs.

[0084] According to another aspect, the present invention provides a method of training an AI, the method comprising the step of inputting the data described above into the AI. According to this aspect, the vehicle being predicted is observed or inspected for a period of time, the results of the observation or inspection are fed back to the AI, and the AI ​​then uses these results to improve its prediction accuracy.

[0085] Examples of this method include:

[0086] • Provides baseline values ​​for various vehicle parameters (as described above)

[0087] • Feeding baseline data into AI

[0088] • Drive the vehicle to the sensor station as described above

[0089] • Collect vehicle data as described above while the vehicle simulates the mission,

[0090] • Feed the collected data into AI,

[0091] • Inputting historical maintenance data and / or experimental data as described above into the AI,

[0092] • Determine if the data collected by the sensor exceeds the baseline value,

[0093] • Compare deviations from baseline values ​​with historical maintenance data and / or experimental data,

[0094] • Based on the comparison, make predictions about potential failures

[0095] The method may include the further steps of observing the vehicle for a period of time and / or inspecting the vehicle after making the prediction; determining whether the fault prediction is accurate (or whether the vehicle parameters further deviate from the baseline value); and inputting the results of the observation and / or inspection into the AI ​​to improve the prediction accuracy of the AI.

[0096] In the foregoing description, various aspects of the conveying vehicle and the automatic storage and retrieval system according to the present invention have been described with reference to illustrative embodiments. For the purpose of explanation, specific numbering, system and configuration are set forth to provide a thorough understanding of the system and its work. However, this description is not intended to be interpreted in a restrictive sense. Various modifications and variations of other embodiments of the illustrative embodiments and systems that are obvious to those skilled in the art of the disclosed subject matter are considered to fall within the scope of the present invention.

[0097] Reference numerals list

[0098] Prior art ( Figures 1 to 4 )

[0099]

Claims

1. A sensor station (600) for an automated vehicle (301) operating in an automated storage and retrieval system, the station comprising a wall housing (601) or comprising a support (603) and a crossbeam (605), the vehicle being able to travel into the wall housing or under the support and the crossbeam, the sensor station having a connection point (602) for attaching one or more sensors (604) and / or one or more compartments (606) for inserting a module (608) containing sensors, the station being arranged at a position on a rail system of the automated storage and retrieval system so that the vehicle can travel directly into the station when operating on the rail system, the station being provided with a wheel rotation device (607) arranged in a guide rail to allow the wheels of the vehicle to rotate while the vehicle remains stationary in the station, and wherein, The sensors are arranged to collect data about vehicle parameters while the vehicle is at the station simulating vehicle operation.

2. The sensor station according to claim 1, wherein: The station is positioned above an empty or partially empty storage row (105) such that the vehicle can lower a storage container into the storage row or raise a storage container from the storage row while located in the station.

3. The sensor station according to claim 1 or 2, wherein: The station comprises a common power source (610) for supplying power to the sensors.

4. The sensor station according to claim 1 or 2, wherein: The station includes an electrical connector (612) connected to a battery of the vehicle for supplying power to the sensor.

5. The sensor station according to one of the preceding claims, wherein The wheel rotating device is a treadmill comprising a continuous belt (609).

6. The sensor station according to one of the preceding claims, wherein The sensors are arranged to collect heat related data.

7. The sensor station according to one of the preceding claims, wherein The sensor is arranged to collect data related to sound frequencies.

8. The sensor station according to one of the preceding claims, wherein The sensor is arranged to collect data related to vibrations.

9. The sensor station according to one of the preceding claims, wherein The sensors are arranged to collect data related to power consumption of the vehicle.

10. The sensor station according to one of the preceding claims, wherein The sensors are arranged to collect data relating to acceleration or deceleration of the vehicle.

11. The sensor station according to one of the preceding claims, wherein The sensor is arranged to collect data related to the torque of a lifting mechanism of the vehicle.

12. The sensor station according to one of the preceding claims, wherein The station comprises a charging connector (611) for charging a battery of the vehicle.

13. A method for detecting or predicting a fault in an automated vehicle operating in an automated storage and retrieval system, the method comprising the steps of: a. Establish a set of normal baseline values ​​for various vehicle parameters for the vehicle, b. establishing historical maintenance data and / or experimental data for the vehicle or a batch of vehicles of similar model and design, the historical maintenance data and / or experimental data including the correlation between observable vehicle parameters and the occurrence of vehicle failures, c. driving the vehicle into a sensor station according to one of the preceding claims, d. using the sensors of the sensor stations to collect data about vehicle parameters while the vehicle simulates a task that the vehicle performs during normal operation in the automated storage and retrieval system, e. comparing the data collected by the sensor with the reference value and / or the historical maintenance data and / or experimental data, f. Based on the comparison, make a prediction of vehicle failure.

14. The method according to claim 11, comprising the steps of: The baseline values, the historical maintenance data and / or experimental data, and the data collected by the sensors are input into an artificial intelligence program, an artificial neural network, or a machine learning algorithm, collectively or alternatively referred to as "AI", and an output is generated from the AI, the output including the prediction of vehicle failure.

15. The method according to claim 11 or 12, wherein: The prediction of a fault is based on a detected vehicle parameter being outside of the reference range, the vehicle parameter also being correlated to historical or experimental values ​​that indicate prior occurrence of the fault.

16. The method according to one of claims 11 to 14, further comprising the steps of: Observe or inspect the vehicle for which predictions have been made, and input the results of the observation or inspection into the AI ​​to improve the prediction accuracy of the AI.

Images