Construction machinery and work site adaptation systems

The construction machine adapts control parameters to ground conditions using sensor data and a library of optimized settings, addressing the inefficiencies of traditional calibration methods and enhancing precision and efficiency.

JP7588042B2Active Publication Date: 2024-11-21HITACHI CONSTRUCTION MACHINERY CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
JP2021116913
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Filing Date
2021-07-15
Publication Date
2024-11-21
Estimated Expiration
2041-07-15

Smart Images

  • Figure 0007588042000001
    Figure 0007588042000001
  • Figure 0007588042000002
    Figure 0007588042000002
  • Figure 0007588042000003
    Figure 0007588042000003
Patent Text Reader

Abstract

To provide a technology that enables highly accurate construction in construction areas with various ground properties.SOLUTION: A construction machine comprises: a vehicle body having a work device and a driving device driving the work device; a plurality of sensors detecting a state of the work device and a state of the driving device; and a controller generating a control signal for driving the driving device. The controller includes: a planning portion deciding a control instruction of the driving device according to a construction instruction input from the outside of the controller and sensor information output from the plurality of sensors; a site-adaptive processing portion selecting a control parameter set value corresponding to a ground property closest to a ground property of a construction area to be constructed among a plurality of control parameter set values optimized for each of a plurality of ground properties; and a control portion forming the control signal based on the control instruction decided by the planning portion, the sensor information, and the control parameter set value selected by the site-adaptive processing portion.SELECTED DRAWING: Figure 2
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present disclosure relates to a construction machine and a work site adaptation system. [Background technology]

[0002] In construction machinery that is compatible with information-based construction (for example, hydraulic excavators), sensors are attached to the hydraulic equipment (pumps, valves, cylinders) and the attachments that perform the work (booms, arms, buckets) to measure the operating status, and the sensor information is used to automatically control the construction machinery and assist the operator in operating it.

[0003] In such construction machinery, the control parameters are calibrated at the time of manufacture and shipping in order to correct differences in control characteristics caused by manufacturing variations. In the calibration process, the construction machinery is operated using several different test patterns and the control parameters are adjusted based on the sensor information obtained.

[0004] However, calibration takes a long time because of the large number of test patterns to be executed and the large number of control parameters to be adjusted. Therefore, considering the balance between the cost of calibration and the functions and performance to be achieved, it is not realistic to perform perfect calibration for all use cases. For example, hydraulic excavators are calibrated on the assumption that the characteristics of the ground to be excavated are average hardness and average viscosity. In other words, it is difficult to provide high-precision control for hard and soft ground even if the control parameters adjusted at the time of shipment are used.

[0005] In response to this, for example, Patent Document 1 discloses a technology in which the objective of the technology is to "provide an excavator that can excavate appropriately taking into account the ground surface to be excavated" and "the output from the attitude detection device M3 is used to control the bucket toe angle α in accordance with the progress of excavation" (see abstract of Patent Document 1). [Prior art documents] [Patent documents]

[0006] [Patent Document 1] JP 2020-128695 A Summary of the Invention [Problem to be solved by the invention]

[0007] However, because conventional technology employs feedback control, it is difficult to increase the speed of blade tip control in a first-order or second-order lag control system such as that used in construction machinery.

[0008] In addition, the optimal correction value for the ground characteristics should be optimized for each individual machine because it varies depending on the manufacturing variability of the construction machine. However, in order to achieve this, it is necessary to perform calibration for each ground characteristic as described above, which increases personnel costs and the time required for calibration.

[0009] Therefore, the present disclosure provides a construction machine capable of performing construction with high precision in construction areas with various ground characteristics. [Means for solving the problem]

[0010] In order to solve the above problems, the construction machine disclosed herein comprises a vehicle body having a work implement and a drive unit for driving the work implement, a plurality of sensors for detecting the state of the work implement and the state of the drive unit, and a controller for generating a control signal for driving the drive unit, wherein the controller comprises a planning unit that determines control instructions for the drive unit according to construction instructions input from outside the controller and sensor information output from the plurality of sensors, a site adaptation processing unit that selects, from a plurality of control parameter setting values ​​optimized for each of a plurality of ground characteristics, the control parameter setting value that corresponds to the ground characteristics that are closest to the ground characteristics of the construction area to be constructed, and a control unit that generates the control signal based on the control instructions determined by the planning unit, the sensor information, and the control parameter setting values ​​selected by the site adaptation processing unit.

[0011] Further features related to the present disclosure will become apparent from the description of the present specification and the accompanying drawings. Also, the aspects of the present disclosure are achieved and realized by the elements and combinations of various elements and the following detailed description and the appended claims. The description of the present specification is merely exemplary and is not intended to limit the scope or application of the present disclosure in any way. Effect of the Invention

[0012] According to the construction machine of the present disclosure, it is possible to perform construction with high accuracy in construction areas with various ground characteristics. Problems, configurations, and effects other than those described above will become apparent from the description of the embodiment below. [Brief description of the drawings]

[0013] [Figure 1] FIG. 1 is a side view of a hydraulic excavator according to a first embodiment. [Diagram 2] FIG. 1 is a functional block diagram of a hydraulic excavator according to a first embodiment. [Diagram 3] FIG. 11 is a diagram showing an example of control parameter settings stored in a control parameter library. [Figure 4]4 is a flowchart showing an example of a construction operation executed by a controller according to the first embodiment. [Diagram 5] FIG. 5 is a functional block diagram of a hydraulic excavator according to a second embodiment. [Figure 6] 10 is a flowchart showing an example of a construction operation executed by a controller according to a second embodiment. [Figure 7] 13 is a flowchart illustrating an example of a control parameter setting update process. [Figure 8] FIG. 11 is a functional block diagram of a field adaptation processing unit according to a modified example of the second embodiment. [Figure 9] FIG. 13 is a diagram illustrating an example of a distribution of estimation accuracy of control parameter settings. [Figure 10] FIG. 13 is a diagram illustrating an example of a distribution of estimation accuracy of control parameter settings. [Figure 11] FIG. 11 is a functional block diagram of a workplace adaptation system according to a third embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] The technology of the present disclosure will be described below with reference to specific embodiments using the drawings. The position, size, shape, range, etc. of each component shown in the drawings may not represent the actual position, size, shape, range, etc. in order to facilitate understanding of the invention. Therefore, the technology of the present disclosure is not necessarily limited to the position, size, shape, range, etc. disclosed in the drawings.

[0015] When there are multiple components having the same or similar functions, they may be described by using the same reference numerals with different subscripts, or when there is no need to distinguish between these multiple components, the subscripts may be omitted.

[0016] In the embodiments, the processing performed by executing a program may be described. Here, a computer executes the program using a processor (e.g., CPU, GPU), and performs processing defined by the program while using storage resources (e.g., memory) and interface devices (e.g., communication ports). Therefore, the subject of the processing performed by executing the program may be the processor.

[0017] The subject of the processing performed by executing the program may be a controller having a processor, a device having a processor, a system having a processor, a computer having a processor, a node having a processor, etc. The subject of the processing performed by executing the program may be a calculation unit, and may include a dedicated circuit that performs specific processing. Here, the dedicated circuit is, for example, an FPGA (Field Programmable Gate Array), an ASIC (Application Specific Integrated Circuit), a CPLD (Complex Programmable Logic Device), etc.

[0018] The program may be installed in the computer from a program source. The program source may be, for example, a program distribution server or a computer-readable storage medium. When the program source is a program distribution server, the program distribution server may include a processor and a storage resource that stores the program to be distributed, and the processor of the program distribution server may distribute the program to be distributed to other computers. In addition, two or more programs in the embodiments may be realized as one program, and one program in the embodiments may be realized as two or more programs.

[0019] In the following embodiment, an example in which the technology of the present disclosure is applied to a hydraulic excavator will be described, but the technology of the present disclosure is not limited to hydraulic excavators and can be widely applied to construction machines such as cranes, wheel loaders, etc. In the following description, the same symbols (numbers) may be used for devices and equipment that are common to each drawing, and descriptions of devices and equipment that have already been described may be omitted.

[0020] [First embodiment] <Example of hydraulic excavator configuration> 1 is a side view of a hydraulic excavator 100 according to an embodiment. The hydraulic excavator 100 includes a running body 102 and a rotating body 103 (vehicle body). The running body 102 runs by driving tracks provided on the left and right sides. A right running motor 115a and a left running motor 115b are installed on the running body 102. The left and right tracks are driven by the driving of these running motors 115a and 115b, causing the hydraulic excavator 100 to run.

[0021] The rotating body 103 is provided rotatably on the running body 102. A rotation motor 114 is provided in the center of the rotating body 103, and the rotating body 103 rotates relative to the running body 102 when the rotation motor 114 is driven.

[0022] The rotating body 103 has a cab 104, a machine room 105, a counterweight 106, and a work machine 107. The cab 104 is provided on the left side of the front part of the rotating body 103. The cab 104 is provided with an operation lever (not shown in FIG. 1) operated by an operator. The operation lever issues commands to drive the work machine 107 and the rotating body 103. The machine room 105 is provided behind the cab 104. Drive devices such as a hydraulic pump, a hydraulic valve, and an engine (not shown in FIG. 1) are installed inside the machine room 105. The counterweight 106 is provided behind the machine room 105, i.e., at the rear end of the rotating body 103.

[0023] The working machine 107 is provided to the right of the cab 104 and in the center of the front of the rotating body 103. The working machine 107 has a boom 108, an arm 109, a bucket 110, a boom cylinder 111, an arm cylinder 112, and a bucket cylinder 113. The base end of the boom 108 is rotatably attached to the front of the rotating body 103 via a boom pin. The base end of the arm 109 is rotatably attached to the tip of the boom 108 via an arm pin. The base end of the bucket 110 is rotatably attached to the tip of the arm 109 via a bucket pin. The boom cylinder 111, the arm cylinder 112, and the bucket cylinder 113 are hydraulic cylinders driven by hydraulic oil. The boom cylinder 111 drives the boom 108. The arm cylinder 112 drives the arm 109. The bucket cylinder 113 drives the bucket 110. Hereinafter, the boom 108, the arm 109, and the bucket 110 may be collectively referred to as a working device 120. Furthermore, the boom cylinder 111, the arm cylinder 112, the bucket cylinder 113, the hydraulic pump, and the hydraulic valve may be collectively referred to as a driving device.

[0024] <Controller functions> 2 is a functional block diagram of the hydraulic excavator 100. The hydraulic excavator 100 includes a controller 1 and a vehicle body 101 controlled by the controller 1. The controller 1 can be realized by using a known computer. Each function of the controller 1 can be realized by a processor (CPU, GPU, etc.) executing a program stored in a memory inside the controller 1.

[0025] The vehicle body 101 includes a working device 120, a posture sensor 121, a driving device 130, and a hydraulic sensor 131. The controller 1 outputs a control signal for controlling the driving of the driving device 130. The driving device 130 drives the working device 120.

[0026] The working device 120 is composed of a boom 108, an arm 109, and a bucket 110. The attitude sensor 121 detects the attitudes, such as the position, direction, and angle, of the boom 108, the arm 109, and the bucket 110. The drive device 130 is composed of actuators, such as a boom cylinder 111, an arm cylinder 112, and a bucket cylinder 113, and hydraulic components, such as a hydraulic pump and a hydraulic valve, that supply working oil to the actuators. The hydraulic sensor 131 detects the state of the hydraulic components. The state of the hydraulic components includes the pressure at the location of the hydraulic components and the flow rate of the hydraulic valve. The hydraulic sensor 131 includes, for example, a pressure sensor installed in the hydraulic valve, a stroke sensor that indirectly monitors the opening state of the valve, a temperature sensor for hydraulic oil, and a control current sensor for the control signal. The detection signal of the attitude sensor 121 and the detection signal of the hydraulic sensor 131 are input to the controller 1 as sensor information.

[0027] The controller 1 has, as functional modules, a planner 11, a controller 12, a control parameter storage 13, a site adaptation processor 14, and a user interface 15.

[0028] The planning unit 11 outputs a control instruction for instructing how to control the driving device 130 next, according to the construction instruction by the operator's lever operation or the construction instruction input from the construction management system, and the sensor information indicating the current state of the working device 120 detected by the posture sensor 121 and the current state of the driving device 130 detected by the hydraulic sensor 131. The construction instruction input from the construction management system is, for example, information on the target surface of the construction by the working device 120, which is obtained from the position (coordinates) of the hydraulic excavator 100. In addition, the planning unit 11 calculates the cutting edge trajectory at the time of construction from the sensor information, compares the calculated cutting edge trajectory at the time of construction with the instruction value of the cutting edge trajectory included in the construction instruction, calculates the error (difference) of the cutting edge trajectory at the time of construction with respect to the construction instruction, and outputs it to the site adaptation processing unit 14 as error information of the cutting edge trajectory. Note that the cutting edge trajectory mainly refers to the trajectory of the cutting edge of the bucket in the hydraulic excavator. However, when the technology disclosed herein is applied to a construction machine corresponding to other information-based construction, the trajectory of the working device to be controlled by the controller in automatic control or control assistance corresponds to the cutting edge trajectory.

[0029] The control unit 12 outputs a control signal for controlling the drive device 130 based on the control instructions output by the planning unit 11 and the sensor information. The relationship between the input (control instructions and sensor information) and the output (control signal) in the control unit 12 can be adjusted by the control parameters stored in the control parameter storage unit 13. The control parameters are adjusted for each individual hydraulic excavator 100 in a calibration process at the time of manufacturing and shipping the hydraulic excavator 100. The control parameters can be changed to correct deviations in control characteristics due to manufacturing variations or aging deterioration of each hydraulic excavator 100, for example. The control parameters correspond to coefficients of a mathematical model showing the relationship between the current that controls the opening of a valve and the opening area, which are used in the opening control of a hydraulic valve, or the values ​​in a table themselves.

[0030] More specific examples of control parameters are shown below. For example, the flow rate Q of a hydraulic valve is used as a control signal. oWhen calculating, the control unit 12 uses values ​​from sensors such as a pressure sensor in the hydraulic valve, a stroke sensor that indirectly monitors the opening state of the hydraulic valve, a temperature sensor for hydraulic oil, and a control current sensor for the control signal. The calculation logic for determining the flow rate Qo is shown, for example, in the following formula 1.

[0031] Q o =C A v (x)·√{ΔP / (2ρ)} … (Equation 1)

[0032] where C is the flow coefficient and A v represents the opening area of ​​the valve, ΔP represents the pressure difference between the primary and secondary sides of the valve, and ρ represents the density of the hydraulic oil. v is a function of the valve stroke x. v (x), C, and ρ are included in the control parameters and are stored in the control parameter storage unit 13. In an actual hydraulic excavator 100, a plurality of hydraulic valves are provided, and the control parameters also include control parameters used for engine control and pump control, and parameters such as gains used for feedback control and feedforward control. Hereinafter, such a plurality of control parameters will be collectively referred to as "control parameter setting." Also, "control parameter setting value" refers to the value of each control parameter included in the control parameter setting.

[0033] The control unit 12 calculates the flow rate Q by using the above formula 1 based on the control instruction from the planning unit 11 and the control parameter settings stored in the control parameter storage unit 13. o Then, the control unit 12 calculates the calculated flow rate Q o and the flow rate detected by the flow rate sensor of the hydraulic valve, a control signal is calculated and feedback control is performed. oand the flow rate detected by the flow sensor, a stroke amount x of the hydraulic valve is determined so as to reduce the difference between the flow rate and the flow rate detected by the flow sensor, and a control signal is calculated so as to realize this stroke amount x. The control signal is represented by, for example, a control current. The attitude of the working device 120 is controlled by outputting the control signal to the driving device 130.

[0034] The site adaptation processing unit 14 includes a parameter management unit 141 and a control parameter library 142. The control parameter library 142 stores control parameter settings 140 suited for each ground characteristic condition. Each control parameter setting 140 includes a plurality of control parameter setting values. The control parameter settings 140 are prepared, for example, by calculating optimal control parameter setting values ​​for various known ground characteristics when the hydraulic excavator 100 is manufactured and storing them in the control parameter library 142.

[0035] The parameter management unit 141 acquires the ground characteristics of the next construction area (next construction area) from an external database, etc., and selects the control parameter setting 140 stored in the control parameter library 142 according to the ground characteristics of the next construction area. Specifically, the control parameter setting 140 related to the ground characteristics closest to the ground characteristics of the next construction area is selected. There is no particular limitation on the method of acquiring the ground characteristics of the construction area, but for example, the parameter management unit 141 can acquire the ground characteristics by referring to a two-dimensional or three-dimensional map information database or a ground map of the work site. Alternatively, test digging may be performed in the construction area, and the ground characteristics may be estimated from the reaction force detected at that time. In this specification, the "construction area" means the area to be cut by the bucket 110.

[0036] The parameter management unit 141 reads out the selected control parameter setting 140 into the control parameter storage unit 13. This allows the control unit 12 to calculate a control signal using the control parameter setting that is optimal for the ground characteristics, making it possible to carry out construction with high accuracy in response to the ground characteristics of various sites. Note that the control parameter setting 140 selected by the parameter management unit 141 may be output directly to the control unit 12 without going through the control parameter storage unit 13.

[0037] The user interface 15 can be realized by, for example, output devices such as a display, a speaker, and a touch panel, and input devices such as an operating lever, a keyboard, and a touch panel.

[0038] FIG. 3 is a diagram showing an example of the control parameter setting 140 stored in the control parameter library 142. As shown in FIG. 3, the control parameter setting 140 is stored in a matrix form, for example, with the hardness of the ground divided into M stages and the viscosity divided into N stages (M and N are natural numbers). The definition of the indicators of the ground characteristics (such as the viscosity and hardness of the ground) can be arbitrarily specified by the designer. If the number of indicators of the ground characteristics increases, the dimension of the matrix stored in the control parameter library 142 increases. In addition, the relationship of the control parameter setting with respect to the ground characteristics such as hardness and viscosity may be modeled by a formula or the like and stored in the control parameter library 142. Furthermore, the control parameter setting 140 may include, as indicators, not only the ground characteristics of the construction area, but also the ground characteristics directly below the vehicle body 101 and the attitude (inclination) of the vehicle body 101 itself.

[0039] <Construction operation> FIG. 4 is a flowchart showing an example of a construction operation executed by the controller 1.

[0040] (Step S101) The parameter management unit 141 acquires ground information for the next construction area from an external database such as a map information database or a ground map. The ground information includes information on the ground characteristics and topography. As described above, the ground characteristics can be acquired from an external database or estimated from the response value of the sensor during trial digging.

[0041] (Step S102) The parameter management unit 141 refers to the control parameter library 142, reads out the control parameter setting 140 related to the ground characteristics that are closest to the ground characteristics of the next construction area, and stores it in the control parameter storage unit 13. As described above, the ground characteristics are values ​​indirectly calculated from sensor information or values ​​acquired from map data, etc., and are therefore assumed to be continuous values. Meanwhile, the control parameter library 142 stores the control parameter settings 140 according to the ground characteristics defined by discrete values. Therefore, in this step, the parameter management unit 141 selects the control parameter setting 140 that is closest to the acquired ground characteristics.

[0042] (Step S103) The planner 11 receives input of construction instructions from outside the controller 1, and acquires sensor information from the attitude sensor 121 and the hydraulic sensor 131. The planner 11 determines control instructions based on the construction instructions and the sensor information, and outputs them to the controller 12. The controller 12 reads out control parameter settings 140 stored in the control parameter memory 13, generates a control signal based on the sensor information and the control instructions determined by the planner 11, and outputs the control signal to the drive device 130 to drive the work device 120. In this way, construction of the construction area is carried out.

[0043] (Step S104) The planning unit 11 acquires sensor information output from the attitude sensor 121 and the hydraulic sensor 131 during construction in step S103, obtains a construction surface obtained by actual construction from the sensor information, and evaluates the difference (construction error) between the construction surface and a target construction surface (target surface). The construction error differs from case to case, depending on the requirements of the construction company and the specifications of the vehicle body. If the construction error is equal to or less than the target value, the construction is judged to be good, and the process proceeds to step S105. If the construction error is greater than the target value, the construction is judged to be poor, and the process proceeds to step S106. For example, if the target value of the construction error is 10 cm, and the construction error is 10 cm or less, the process returns to step S101 after step S105 in order to proceed to construction of the next construction area, and the ground characteristics of the next construction area are acquired.

[0044] (Step S105) The control unit 12 judges whether the construction itself has been completed. If the construction has been completed (Yes), the process ends. If the construction has not been completed (No), the process returns to step S101. Whether the construction has been completed can be determined by whether all the work included in the construction instructions has been completed, or by acquiring an image of the construction site using a sensor such as a camera and determining whether all the construction areas have been worked on.

[0045] (Step S106) If it is determined in step S104 that the construction error of the construction surface is greater than the target value (10 cm), this means that the selected control parameter setting 140 was not optimal for the ground characteristics of the construction area. Therefore, the parameter management unit 141 updates the selection criteria for the control parameter setting. One example of updating the selection criteria is a method of applying an offset to the acquired ground information. Specifically, for example, when the hardness of the acquired ground information corresponds to 3, if the control parameter setting 140 of hardness 3 is selected but the construction error exceeds +10 cm because the ground could not be dug as expected during construction (harder than hardness 3), the judgment criteria are corrected by regarding the ground characteristics for that construction area as corresponding to hardness 4. Then, the control parameter setting of the ground characteristics of hardness 4 is selected from the next construction onwards.

[0046] If the control accuracy does not improve even if the selection criteria are updated in this way, the parameter management unit 141 may output a notification to the user interface 15 indicating that the ground characteristics cannot be handled, and notify the operator, site supervisor, etc. This allows the operator or site supervisor to understand that the construction area cannot be handled even if the parameter management unit 141 is provided with the function of automatically selecting control parameter settings as described above. As a result, measures such as switching the construction of that construction area to manual work can be taken.

[0047] Regarding the timing of each step described above, for example, steps S101 and S102 can be performed before the work starts, and after the work (step S103), steps S104, S106, S101, and S102 can be performed before the next work starts. This allows for efficient control parameter setting.

[0048] <Summary of the First Embodiment> A hydraulic excavator 100 according to the first embodiment includes a vehicle body 101 having a working device 120 and a driving device 130, an attitude sensor 121 for detecting the state of the working device 120 and a hydraulic sensor 131 for detecting the state of the driving device 130, and a controller 1 for generating a control signal for driving the driving device 130. The controller 1 includes a planner 11 for determining a control instruction for the driving device 130 according to a construction instruction input from outside the controller 1 and sensor information, a site adaptation processor 14 for selecting a control parameter setting 140 corresponding to ground characteristics that are closest to the ground characteristics of a construction area to be constructed from a plurality of control parameter settings 140 optimized for each of a plurality of ground characteristics, and a controller 12 for generating a control signal based on the control instruction determined by the planner 11, the sensor information, and the control parameter setting 140 selected by the site adaptation processor 14.

[0049] In this way, by selecting control parameter settings suitable for the ground characteristics and generating a control signal using the control parameter settings, the accuracy of construction can be improved when working at a site including construction areas with various ground characteristics. In addition, since calibration of the control parameters for each ground characteristic is not required, the time and cost required for calibration can be reduced.

[0050] <Modification of the first embodiment> In addition to the function of automatically selecting the control parameter settings in the parameter management unit 141, an operator may be allowed to arbitrarily select the control parameter settings 140 in the control parameter library 142 via a user interface such as a GUI screen displayed on a display. This enables work assistance that is familiar to the individual operator's operational sense, and is expected to have the effect of improving work efficiency.

[0051] [Second embodiment] In the first embodiment described above, the control parameter settings 140 stored in the control parameter library 142 are only those whose optimum control parameter settings are known in advance for the ground characteristics. Therefore, when construction is performed in a construction area whose ground characteristics do not correspond to any of the control parameter settings, the control parameter settings 140 cannot be used.

[0052] Therefore, in the second embodiment, a configuration is proposed in which new control parameter settings are added to the control parameter library 142. In the explanation of the second embodiment, the differences from the first embodiment will be mainly explained, and the contents already explained will be omitted or only briefly explained.

[0053] <Controller functions> Fig. 5 is a functional block diagram of a hydraulic excavator 200 according to the second embodiment. As shown in Fig. 5, the hydraulic excavator 200 of the second embodiment is different from the hydraulic excavator 100 of the first embodiment in that the site adaptation processing unit 14 further includes a trajectory feature amount calculation unit 143 and a control parameter update unit 144.

[0054] The trajectory feature amount calculation unit 143 calculates a feature amount of the error (difference) of the cutting edge trajectory output from the planning unit 11, and outputs the calculated feature amount to the control parameter update unit 144. The method of calculating the feature amount will be described later.

[0055] The control parameter update unit 144 adjusts the control parameter settings so as to reduce the error of the cutting edge trajectory, using the feature value of the cutting edge trajectory error received from the trajectory feature value calculation unit 143, the ground characteristics of the construction area, and the control parameter settings used during construction. The control parameter update unit 144 can adjust the control parameter settings by using, for example, a machine learning model. The control parameter update unit 144 outputs the adjusted control parameter settings to the parameter management unit 141.

[0056] <Construction operation> 6 is a flowchart showing an example of a construction operation executed by the controller 1 according to the second embodiment. In this embodiment, step S107 is executed instead of the above-mentioned step S106. Steps S101 to S105 are the same as those in the first embodiment.

[0057] (Step S107) If it is determined in step S104 that the construction error of the construction surface is greater than the target value, the control parameter update unit 144 adjusts the control parameter setting selected in step S102 so as to reduce the construction error. Then, the parameter management unit 141 adds the adjusted control parameter setting to the control parameter library 142.

[0058] <Adjustment and update of control parameter settings> FIG. 7 is a flowchart showing an example of the control parameter setting update process in step S107.

[0059] (Step S111) The trajectory feature amount calculation unit 143 compares the information on the cutting edge trajectory during actual construction converted from the sensor information in the planning unit 11 with the instruction value (control instruction) of the cutting edge trajectory determined by the planning unit 11, and calculates feature amounts of the error of the cutting edge trajectory, such as an amplitude difference and a control delay. Here, the feature amount may be anything that characterizes the shape of the waveform of the cutting edge trajectory itself, and may be the maximum or minimum value of the waveform, the sum of the areas of the parts that deviate from the error specifications, or a value extracted by FFT or the like from the frequency components of the waveform. In addition, a means for converting the multi-dimensional feature amount extracted above into a low-dimensional feature amount by principal component analysis may be used.

[0060] (Step S112) The control parameter update unit 144 updates the learning rate of the adjustment model of the control parameter setting so as to reduce the error of the cutting edge trajectory based on the feature amount calculated by the trajectory feature amount calculation unit 143, the ground characteristics of the construction area where construction was performed, and the control parameter setting used during construction. As a means for updating, an optimization algorithm such as the steepest descent method, Bayesian optimization, or reinforcement learning can be used. In the iteration for optimization, the change range (learning rate) of the control parameter setting may reflect manufacturing variations or ground characteristics. That is, when the control characteristics of the individual A of the hydraulic excavator 100 are highly sensitive to changes in the control parameter setting compared to the individual B, the learning rate in the parameter adjustment of the individual A may start from a small value. In addition, when the ground is soft, the learning rate may start from a large value compared to when the ground is hard.

[0061] (Step S113) The control parameter update unit 144 inputs the construction error for each position (for each construction area) and the cutting edge speed calculated from the sensor information into an adjustment model, and adjusts the control parameter settings using the adjustment model. That is, the output of the adjustment model is the adjusted (adjusted) control parameter settings. Thereafter, the control parameter update unit 144 inputs the adjusted control parameter settings into the parameter management unit 141.

[0062] (Step S114) The parameter management unit 141 judges whether or not the ground characteristic conditions for the adjusted control parameter settings received from the control parameter update unit 144 are in the control parameter library 142 (whether or not they are known). If the ground characteristic conditions for the adjusted control parameter settings entered in the control parameter library 142 are present (Yes), the process proceeds to step S115. If the ground characteristic conditions for the adjusted control parameter settings are not present (No), the process proceeds to step S116.

[0063] (Step S115) If the adjusted control parameter settings are in the control parameter library 142 (if the ground characteristics are those experienced in the past), the parameter management unit 141 overwrites and updates the control parameter settings.

[0064] (Step S116) If the control parameter library 142 does not contain control parameter settings corresponding to the ground characteristics (if the ground characteristics are not yet encountered), the parameter management unit 141 additionally registers new control parameter settings in the control parameter library 142.

[0065] <Modification of the second embodiment> A hydraulic excavator immediately after manufacture and shipment has only experienced a small number of ground characteristics, and therefore has a small number of ground characteristic conditions stored in the control parameter library 142. Therefore, the initial values ​​of the control parameter settings 140 may be the same under all conditions. Alternatively, the initial values ​​of the control parameter settings 140 may be determined by assuming optimal control parameter settings for hardness and viscosity in a certain mathematical model, and using the mathematical model. This makes it possible to set the initial values ​​of the control parameters for ground characteristics that are not yet experienced to values ​​that are somewhat close to the optimal values, and is expected to reduce the number of times the control parameter settings are updated.

[0066] <Other Modifications of the Second Embodiment> 8 is a functional block diagram of the site adaptive processor 14 according to a modification of the second embodiment. The site adaptive processor 14 of this modification has a parameter complement unit 145 instead of the trajectory feature amount calculator 143 and the control parameter update unit 144.

[0067] The parameter complementing unit 145 estimates control parameter settings under unexperienced ground characteristic conditions using control parameter settings under experienced ground characteristic conditions. Specifically, the parameter complementing unit 145 estimates optimal control parameter settings under unexperienced ground characteristic conditions according to the ground characteristic conditions used to update the control parameter library 142 (i.e., experienced ground characteristic conditions). The estimation algorithm used at this time may be, for example, a mathematical expression model reflecting the tendency and characteristics of the control parameter settings for the above-mentioned ground characteristics, or a Bayesian estimation algorithm that estimates the mathematical expression model from a small number of actual measurement values. The parameter complementing unit 145 outputs the estimated control parameter settings to the parameter managing unit 141. The parameter managing unit 141 updates the control parameter library 142 by adding the estimated control parameter settings to the control parameter library 142.

[0068] Fig. 9 is a diagram showing an example of the distribution of the estimation accuracy of the control parameter settings. Fig. 9 shows the distribution of the estimation accuracy of the control parameter settings when the ground conditions of hardness 1 and viscosity 1 have been measured and the other ground conditions have not been measured. For example, the conditions of hardness 2 and viscosity 1 and the conditions of hardness 1 and viscosity 2 have high estimation accuracy because they are close to the measured conditions. In contrast, the conditions of hardness 1 and viscosity 3, hardness 2 and viscosity 2, and hardness 3 and viscosity 1 have low estimation accuracy because they are far from the measured conditions.

[0069] Fig. 10 is a diagram showing another example of the distribution of the estimation accuracy of the control parameter setting. Fig. 10 shows a case where measurements have been made under a plurality of conditions. It can be seen that the region of the estimation accuracy for conditions close to the measured conditions is larger than that in Fig. 9. In this way, as the measured conditions increase, the number of control parameter settings with high estimation accuracy increases.

[0070] In this way, the parameter management unit 141 can select control parameter settings for ground conditions close to experienced ground characteristics, even if the ground characteristics of the next construction area are completely unexperienced ground conditions, so that construction can be carried out in a more rapid response to the ground characteristics of the next construction area.

[0071] <Summary of the second embodiment> In the hydraulic excavator 200 according to the second embodiment, the site adaptation processor 14 adjusts the control parameter settings in accordance with the construction results and ground characteristics, and updates the control parameter library 142. In this way, the control parameter settings are adjusted to approach optimal values ​​with each construction experience, and construction is performed using the adjusted control parameter settings, thereby making it possible to realize construction with higher accuracy for various ground characteristics.

[0072] [Third embodiment] In the first and second embodiments, it has been described that the control parameter settings 140 are stored in the control parameter library 142 provided in the controller of the hydraulic excavator and are read out during construction operations. In the case of the first and second embodiments, the control parameter settings 140 in the control parameter library 142 accumulated in one hydraulic excavator can be used only by that hydraulic excavator. In contrast, the control parameter settings 140 may be stored in a server device or the like external to the hydraulic excavator, and may be configured to be readable by a plurality of hydraulic excavators. Therefore, in the third embodiment, a work site adaptation system configured by a hydraulic excavator and an external server device that stores the control parameter settings 140 will be described.

[0073] <Example of the Workplace Adaptive System Configuration> 11 is a functional block diagram of a work site adaptation system according to a third embodiment. The work site adaptation system includes a plurality of hydraulic excavators 300a, 300b, ..., 300n (hereinafter sometimes collectively referred to as "hydraulic excavators 300") and a management server 500. The controller 1 of the hydraulic excavator 300 differs from that of the first embodiment in that it further includes a communication interface 16. The communication interface 16 is configured to transmit and receive information to and from the management server 500. Note that the controller 1 of the hydraulic excavator 300 may have a configuration similar to that of the second embodiment.

[0074] The management server 500 includes a control parameter library 501 and a communication interface 502. The control parameter library 501 stores the control parameter settings 140. The management server 500 is a server device (computer device) external to the hydraulic excavator 300, and is installed in a location away from the work site where the hydraulic excavator 300 is located, such as an office of a construction company.

[0075] The communication interface 502 is configured to transmit and receive information to and from the hydraulic excavator 300. In this manner, the controller 1 of each hydraulic excavator 300 and the management server 500 are capable of communicating with each other.

[0076] <Construction operation> The controller 1 of the hydraulic excavator 300 performs construction in accordance with the ground characteristics of the work site in the same manner as in the first or second embodiment. However, in the above-mentioned step S102, the communication interface 16 communicates with the communication interface 502 of the management server 500 to download the control parameter settings 140 stored in the control parameter library 501 and store them in the control parameter library 142. At this time, all the control parameter settings 140 stored in the control parameter library 501 may be downloaded, or only some of the control parameter settings 140 may be downloaded. By downloading all the control parameter settings 140, it becomes unnecessary to communicate with the management server 500 in real time for each construction operation. On the other hand, by downloading only some of the control parameter settings 140, the storage capacity of the storage device (control parameter library 142) in the hydraulic excavator 300 can be reduced. For example, when the ground characteristics of the site are known in advance, only the control parameter settings for the expected ground characteristics may be downloaded.

[0077] There is no particular limitation on the timing of downloading the control parameter settings 140, so long as it is done immediately before construction starts (before step S103). As in the second embodiment, the control parameter settings 140 may be adjusted and uploaded to the control parameter library 501 (updating the control parameter library 501). The upload may be done after the adjustment process of the control parameter settings to accommodate unsupported ground characteristics is completed (after step S113), or may be uploaded as necessary at the end of the day's work if there is an update.

[0078] <Modification of the third embodiment> The communication interface 502 may be further configured to be capable of transmitting and receiving information to and from a management terminal owned by the administrator and a user terminal owned by the operator of the hydraulic excavator 300. The management terminal and the user terminal are computer devices configured to be able to communicate with the hydraulic excavator 300. In this case, the administrator and the operator can access the control parameter library 501 of the management server 500 from the management terminal and the user terminal, and select the control parameter settings 140 to be transmitted to the hydraulic excavator 300 via a GUI screen.

[0079] <Summary of the third embodiment> The work site adaptation system according to the third embodiment includes a plurality of hydraulic excavators 300 and a management server 500, and is configured so that the hydraulic excavators 300 and the management server 500 can communicate with each other. The control parameter library 501 of the management server 500 stores control parameter settings 140. In this manner, by acquiring control parameter settings for each ground characteristic in the plurality of hydraulic excavators 300 and adding and updating adjusted control parameter settings, it is possible to improve the accuracy of automatic control and assist control of the cutting edge for various ground characteristics of work sites, compared to updating the control parameter library 142 in a single hydraulic excavator to improve site adaptability.

[0080] [Variations] The present disclosure is not limited to the above-described embodiments, and includes various modified examples. For example, the above-described embodiments have been described in detail to clearly explain the present disclosure, and it is not necessary to include all of the configurations described. In addition, a part of an embodiment can be replaced with a configuration of another embodiment. In addition, a configuration of another embodiment can be added to a configuration of an embodiment. In addition, a part of the configuration of each embodiment can be added to, deleted from, or replaced with a part of the configuration of another embodiment. [Explanation of symbols]

[0081] 1...controller, 100, 200, 300...hydraulic excavator, 101...vehicle body, 120...working device, 121...attitude sensor, 130...driving device, 131...hydraulic sensor, 11...planning unit, 12...control unit, 13...control parameter storage unit, 14...site adaptation processing unit, 140...control parameter setting, 141...parameter management unit, 142...control parameter library, 143...trajectory feature calculation unit, 144...control parameter update unit, 145...parameter completion unit, 15...user interface, 16...communication interface, 500...management server (external server), 501...control parameter library, 502...communication interface

Claims

1. a vehicle body having a working device and a drive device that drives the working device; A plurality of sensors for detecting a state of the working device and a state of the driving device; A controller that generates a control signal for driving the drive device, The controller: a planning unit that determines a control instruction for the drive device according to a construction instruction input from outside the controller and sensor information output from the plurality of sensors; A site adaptation processing unit that selects, from among a plurality of control parameter setting values ​​optimized for each of a plurality of ground characteristics, a control parameter setting value corresponding to the ground characteristics that are closest to the ground characteristics of a construction area to be constructed; a control unit that generates the control signal based on the control instructions determined by the planning unit, the sensor information, and the control parameter setting values ​​selected by the site adaptation processing unit.

2. the controller further comprises a storage device for temporarily storing the selected control parameter setting value; The on-site adaptation processing unit includes: a library for storing the plurality of control parameter setting values; 2. The construction machine according to claim 1, further comprising a parameter management section which selects the control parameter setting values ​​and stores them in the storage device.

3. The planning unit calculates a construction surface after construction based on the sensor information when the working device is driven, and calculates a construction result by comparing the construction surface with the control instruction.

2. The construction machine according to claim 1, wherein the site adaptation processing unit updates selection criteria for the control parameter setting values ​​in accordance with the construction results.

4. 2. The construction machine according to claim 1, wherein the plurality of control parameter setting values ​​correspond to each combination of conditions of the ground characteristics of the construction area, the ground characteristics of the area directly below the vehicle body, and the attitude of the vehicle body.

5. The planning unit Calculating a trajectory of the work device during construction based on the sensor information when the work device is driven; calculating an error in the trajectory of the work device by comparing a trajectory of the work device during the construction with an instruction value of the trajectory of the work device included in the control instruction; The on-site adaptation processing unit includes: a library for storing the plurality of control parameter setting values; a trajectory characteristic amount calculation unit that receives an error of a trajectory of the working device from the planner and calculates a characteristic amount of the error; 2. The construction machine according to claim 1, further comprising a parameter update unit that adjusts the selected control parameter setting values ​​based on the feature amount and the ground characteristics of the construction area, and adds or updates the control parameter setting values ​​to the library.

6. The controller further comprises a user interface; 2. The construction machine according to claim 1, wherein the site adaptation processing unit outputs the plurality of control parameter setting values ​​to the user interface and accepts a selection of the control parameter setting value by an operator of the construction machine.

7. The construction machine according to claim 1 ; an external server that stores the plurality of control parameter setting values, The controller of the construction machine further includes a communication interface configured to be able to communicate with the external server, A workplace adaptation system, characterized in that the controller obtains the control parameter setting values ​​from the external server via the communication interface.

8. The work site adaptation system according to claim 7 , wherein the controller obtains all of the plurality of control parameter setting values ​​stored in the external server.

Citation Information

Patent Citations

  • Method and system for selecting desired response of electronically controlled subsystem

    JP2002073112A

  • Control parameter changing system for construction machine

    JP2017075500A

  • Shovel and system for the same

    JP2020128695A

  • Work machine

    JP2020159056A

  • Mapping a Dig Site Diagram

    US20180210454A1