Coffee beverage robot arm fault detection method and system

Abstract

The application provides a coffee beverage robot mechanical arm fault detection method and system, relates to the technical field of mechanical arm fault detection, and receives and acquires single mechanical arm detection parameters and mechanical arm cooperative detection parameters from a detection rule library according to a fault detection instruction to perform single mechanical arm special detection and three-mechanical arm cooperative detection. According to the reference mechanical arm track characteristics, the single mechanical arm track characteristics and the cooperative mechanical arm track obtained by detection are subjected to track deviation analysis, and the mechanical arm fault alarm is output. The technical problem that the existing technology detects the mechanical arm fault of the coffee beverage robot based on a fixed period, and the fault detection is separated from the coffee making process, leading to easy fault missed detection and false alarm. The technical effects of reducing the mechanical arm fault false alarm and missed alarm phenomenon, optimizing the coffee beverage robot mechanical arm maintenance efficiency, and guaranteeing the high precision and stability of the coffee automatic making process are achieved.

Description

Technical Field

[0001] This invention relates to the field of robotic arm fault detection technology, and in particular to a method and system for fault detection of a coffee beverage robot robotic arm. Background Technology

[0002] With the popularization of automated coffee-making technology, coffee beverage robots have become an important piece of equipment in the catering service industry. Their core relies on high-precision robotic arms to complete a series of actions such as taking cups, pouring water, and sealing.

[0003] Current robotic arm fault detection methods mostly employ fixed-cycle shutdown testing or single-sensor threshold alarm mechanisms, with the detection process independent of the daily production workflow. These methods have significant drawbacks: fixed-cycle testing cannot cover the entire working path of the robotic arm; specific motion modes of the robotic arm corresponding to low-frequency beverage production (such as lateral movement for adding ingredients) are easily overlooked due to their infrequent calls, leading to missed detection of potential mechanical wear; single-sensor threshold monitoring (such as motor current exceeding limits) can only identify sudden hardware failures and is unable to capture gradual performance degradation (such as slight trajectory deviations or acceleration decay).

[0004] In addition, existing technologies lack monitoring of the spatiotemporal matching degree of three robotic arms working together, and cannot diagnose systemic faults caused by timing misalignment or path interference. These problems result in low fault detection rate, high false alarm rate, and frequent downtime for maintenance, which seriously affects equipment reliability and service efficiency. Summary of the Invention

[0005] This invention provides a method and system for fault detection of the robotic arm of a coffee beverage robot, which addresses the technical problem that existing technologies perform fault detection of the robotic arm of a coffee beverage robot based on a fixed cycle, and that fault detection is disconnected from the coffee making process, leading to the easy occurrence of missed faults and false alarms.

[0006] In view of the above problems, the present invention provides a method and system for fault detection of a robotic arm for coffee beverage robots.

[0007] A first aspect of the present invention provides a method for fault detection of a robotic arm used in coffee beverage manufacturing, the method comprising:

[0008] By performing no-load idle running monitoring on the calibrated coffee and beverage robot, a baseline robotic arm trajectory feature is constructed. A pre-set periodic detection window is established, and when the coffee and beverage robot's runtime meets the periodic detection window, a fault detection command is generated. The coffee and beverage robot receives and, according to the fault detection command, randomly calls single-arm detection parameters and robotic arm collaborative detection parameters from the detection rule base. The single-arm detection parameters are used to control the coffee and beverage robot to perform single-arm specialized detection, outputting single-arm trajectory features. The robotic arm collaborative detection parameters are used to control the coffee and beverage robot to perform three-arm collaborative detection, outputting collaborative robotic arm trajectory features. Based on the baseline robotic arm trajectory features, trajectory deviation analysis is performed on the single-arm trajectory features and collaborative robotic arm trajectories, outputting robotic arm fault alarms.

[0009] In one implementation, by performing no-load idle run monitoring on the calibrated coffee beverage robot to construct baseline robotic arm trajectory features, the following processing is also performed:

[0010] A first multi-dimensional sensor group, a second multi-dimensional sensor group, and a third multi-dimensional sensor group are respectively installed on the first, second, and third robotic arms of the coffee beverage robot. After calibrating the first, second, and third robotic arms, no-load idle running monitoring is performed on the first, second, and third robotic arms to drive them to simulate the standard coffee-making process. During K rounds of no-load idle running, the first, second, and third multi-dimensional sensor groups synchronously collect running data to obtain K first spatiotemporal trajectory sequences, K second spatiotemporal trajectory sequences, and K third spatiotemporal trajectory sequences, where K ≥ 20. Trajectory association features are collected from the K first spatiotemporal trajectory sequences, K second spatiotemporal trajectory sequences, and K third spatiotemporal trajectory sequences to obtain the baseline robotic arm trajectory features.

[0011] In one implementation, trajectory association features are acquired from the K first spatiotemporal trajectory sequences, K second spatiotemporal trajectory sequences, and K third spatiotemporal trajectory sequences to obtain the baseline robotic arm trajectory features, and the following processing is also performed:

[0012] After spatially aligning the K first spatiotemporal trajectory sequences, a first single-arm reference trajectory feature is output by performing trajectory spatiotemporal deviation analysis; similarly, a second single-arm reference trajectory feature is output by performing trajectory spatiotemporal deviation analysis on the K second spatiotemporal trajectory sequences; similarly, a third single-arm reference trajectory feature is output by performing trajectory spatiotemporal deviation analysis on the K third spatiotemporal trajectory sequences; after spatiotemporally mapping and aligning the K first spatiotemporal trajectory sequences, K second spatiotemporal trajectory sequences, and K third spatiotemporal trajectory sequences, the temporal mean of the robotic arm joint motion is extracted, and a reference collaborative spatial feature is output; wherein, the first single-arm reference trajectory feature, the second single-arm reference trajectory feature, the third single-arm reference trajectory feature, and the reference collaborative spatial feature constitute the reference robotic arm trajectory feature.

[0013] In one implementation, after spatially aligning the K first spatiotemporal trajectory sequences, the first single-arm reference trajectory features are output by performing trajectory spatiotemporal deviation analysis, and the following processing is also performed:

[0014] By locating the trajectory deviations of the K first spatiotemporal trajectory sequences, the trajectory deviation boundaries are extracted and used as the first robotic arm motion boundaries; the average values ​​of multiple accelerations at multiple key points of the K first spatiotemporal trajectory sequences are calculated as the first motion features; wherein, the first robotic arm motion boundaries and the first motion features constitute the first single-arm reference trajectory features.

[0015] In one implementation, the coffee beverage robot receives and, based on the fault detection instruction, randomly calls single-arm detection parameters and robotic arm collaborative detection parameters from the detection rule base, and also performs the following processing:

[0016] Historical coffee production records are traced back based on the periodic detection window to obtain multiple production frequency characteristics of various coffee beverages; sample coffee beverages are reverse-selected based on the multiple production frequency characteristics to locate a set of candidate test beverages; the set of candidate test beverages is used as a random call constraint to call the single robotic arm detection parameters and robotic arm collaborative detection parameters corresponding to the random test beverage production control information from the detection rule base, wherein the single robotic arm detection parameters consist of a first robotic arm detection parameter, a second robotic arm detection parameter, and a third robotic arm detection parameter.

[0017] In one implementation, the single-arm detection parameters are used to control the coffee beverage robot to perform single-arm specialized detection, output single-arm trajectory features, and the following processing is also performed:

[0018] During the operation of the first robotic arm driven by the first robotic arm detection parameters, the first multi-dimensional sensor group synchronously collects operating data to obtain a first real-time trajectory sequence; calculates multiple first real-time accelerations at multiple key points of the displacement trajectory based on the first real-time trajectory sequence; similarly, a second real-time trajectory sequence is collected and multiple second real-time accelerations are calculated and output based on the second real-time trajectory sequence; similarly, a third real-time trajectory sequence is collected and multiple third real-time accelerations are calculated and output based on the third real-time trajectory sequence; the first real-time trajectory sequence, the second real-time trajectory sequence, the third real-time trajectory sequence, multiple first real-time accelerations, multiple second real-time accelerations, and multiple third real-time accelerations are structured and stored, and the single robotic arm trajectory features are output.

[0019] In one implementation, the coffee beverage robot is controlled to perform three-arm collaborative detection using the robotic arm collaborative detection parameters, outputting collaborative robotic arm trajectory features, and also performing the following processing:

[0020] The detection parameters of the first, second, and third robotic arms in synchronous execution states are used as the collaborative detection parameters of the robotic arms. During the collaborative driving of the first, second, and third robotic arms using the collaborative detection parameters, the first, second, and third multi-dimensional sensor groups synchronously collect running data to obtain a third, fourth, and fifth real-time trajectory sequence. The robotic arm joint motion timing data are extracted from the third, fourth, and fifth real-time trajectory sequences to output the collaborative robotic arm trajectory features.

[0021] In one implementation, trajectory deviation analysis is performed on the single-manipulator trajectory features and the collaborative manipulator trajectory based on the baseline manipulator trajectory features, and a manipulator fault alarm is output. The following processing is also performed:

[0022] If the Euclidean distance between the plurality of first real-time accelerations and the average of the plurality of accelerations is greater than a preset acceleration deviation scale, and / or the first real-time trajectory sequence does not completely fall within the motion boundary of the first robotic arm, a first robotic arm alarm is output; similarly, based on the second real-time trajectory sequence and the plurality of second real-time accelerations, a fault judgment is made on the second device robotic arm, and a second robotic arm alarm is output; similarly, based on the third real-time trajectory sequence and the plurality of third real-time accelerations, a fault judgment is made on the third device robotic arm, and a third robotic arm alarm is output; based on the spatial deviation between the collaborative robotic arm trajectory characteristics and the benchmark collaborative space characteristics, a fourth robotic arm alarm is quantified and output; by associating the first robotic arm alarm, the second robotic arm alarm, the third robotic arm alarm, and the fourth robotic arm alarm, a robotic arm fault alarm is output.

[0023] A second aspect of the present invention provides a fault detection system for a coffee and beverage robot's robotic arm. The system includes: a trajectory construction unit for constructing baseline robotic arm trajectory features by performing no-load idle running monitoring on a calibrated coffee and beverage robot; an instruction output unit for pre-setting a periodic detection window and generating a fault detection instruction when the coffee and beverage robot's runtime meets the periodic detection window; a parameter calling unit for the coffee and beverage robot to receive and randomly call single-arm detection parameters and robotic arm collaborative detection parameters from a detection rule base according to the fault detection instruction; a single-arm detection unit for controlling the coffee and beverage robot to perform single-arm-specific detection using the single-arm detection parameters and outputting single-arm trajectory features; a collaborative detection unit for controlling the coffee and beverage robot to perform three-arm collaborative detection using the robotic arm collaborative detection parameters and outputting collaborative robotic arm trajectory features; and a fault alarm unit for performing trajectory deviation analysis on the single-arm trajectory features and collaborative robotic arm trajectories based on the baseline robotic arm trajectory features and outputting a robotic arm fault alarm.

[0024] One or more technical solutions provided in this invention have at least the following technical effects or advantages:

[0025] The method provided in this invention constructs a baseline robotic arm trajectory feature by performing no-load idle running monitoring on a calibrated coffee and beverage robot; a pre-set periodic detection window is established, and a fault detection command is generated when the coffee and beverage robot's running time meets the periodic detection window; the coffee and beverage robot receives and, according to the fault detection command, randomly calls single-robotic arm detection parameters and robotic arm collaborative detection parameters from the detection rule base; the single-robotic arm detection parameters are used to control the coffee and beverage robot to perform single-robotic arm-specific detection, outputting single-robotic arm trajectory features; the robotic arm collaborative detection parameters are used to control the coffee and beverage robot to perform three-robotic arm collaborative detection, outputting collaborative robotic arm trajectory features; and trajectory deviation analysis is performed on the single-robotic arm trajectory features and collaborative robotic arm trajectories based on the baseline robotic arm trajectory features, outputting a robotic arm fault alarm. This achieves the technical effect of effectively distinguishing between individual component faults and robotic arm collaborative function abnormalities, shortening fault location time, reducing false alarms and missed alarms for robotic arm faults, optimizing the maintenance efficiency of the coffee and beverage robot's robotic arm, and ensuring the high precision and stability of the automated coffee making process. Attached Figure Description

[0026] Figure 1 A schematic diagram of the fault detection method for the robotic arm of a coffee beverage robot provided by the present invention is shown.

[0027] Figure 2 A schematic diagram of the fault detection system for the robotic arm of a coffee beverage robot provided by the present invention is shown.

[0028] Figure labeling: 1. Trajectory construction unit; 2. Command output unit; 3. Parameter calling unit; 4. Single-arm detection unit; 5. Collaborative detection unit; 6. Fault alarm unit. Detailed Implementation

[0029] This invention provides a method and system for fault detection of the robotic arm of a coffee beverage robot, which addresses the technical problem that existing technologies perform fault detection of the robotic arm of a coffee beverage robot based on a fixed cycle, and that fault detection is disconnected from the coffee making process, leading to the easy occurrence of missed faults and false alarms.

[0030] The technical solutions of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. It should be understood that the present invention is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention. It should also be noted that, for ease of description, only the parts related to the present invention are shown in the accompanying drawings, not all of them.

[0031] Example 1: A flowchart of the fault detection method for the robotic arm of a coffee beverage robot provided in this embodiment of the invention, see [link / reference]. Figure 1 The method includes:

[0032] S100: By performing no-load empty run monitoring on the calibrated coffee and beverage robot, a baseline robotic arm trajectory feature is constructed;

[0033] In one implementation, by performing no-load idle running monitoring on the calibrated coffee beverage robot, a baseline robotic arm trajectory feature is constructed. The method step S100 provided by this invention includes:

[0034] S110: Install a first multi-dimensional sensor group, a second multi-dimensional sensor group, and a third multi-dimensional sensor group on the first, second, and third robotic arms of the coffee beverage robot, respectively.

[0035] S120: After calibrating the first, second, and third robotic arms, perform no-load idle running monitoring on the first, second, and third robotic arms to drive them to simulate the standard coffee-making process.

[0036] S130: During the K rounds of no-load empty running of the first equipment robotic arm, the second equipment robotic arm and the third equipment robotic arm, the first multi-dimensional sensor group, the second multi-dimensional sensor group and the third multi-dimensional sensor group synchronously collect running data to obtain K first spatiotemporal trajectory sequences, K second spatiotemporal trajectory sequences and K third spatiotemporal trajectory sequences, where K≥20;

[0037] S140: Trajectory association features are collected from the K first spatiotemporal trajectory sequences, K second spatiotemporal trajectory sequences, and K third spatiotemporal trajectory sequences to obtain the baseline robotic arm trajectory features.

[0038] Specifically, in this embodiment, the coffee beverage robot includes three robotic arms. Through the coordinated operation of the three robotic arms, the programmed automatic production of coffee beverage orders can be realized.

[0039] In this embodiment, the functional design of the first, second, and third robotic arms is not limited. For example, the first robotic arm is responsible for cup management, performing the action of grabbing empty cups and transferring them to the raw material addition area (such as the syrup / ice cube dispensing position), and accurately placing the cups at the primary handover position; the second robotic arm then takes over the raw material processing, completing the auxiliary material addition operation (such as jam injection or ice quantity calibration) at the primary handover position, and then transferring the cups to the secondary handover position; the third robotic arm dominates the liquid operation, taking over the cups from the secondary handover position to perform coffee pouring, milk foam blending, and cup lid pressing and sealing, forming a functional segmented handover chain of cup picking → processing → liquid pouring.

[0040] The entire process ensures collaborative safety and efficiency through layered spatiotemporal constraints: the second robotic arm must start gripping within 0.4 seconds after the first robotic arm releases the cup to prevent it from tipping over, and the third robotic arm must take over within 0.3 seconds after the second robotic arm releases it to maintain the beverage temperature; spatially, the primary and secondary junctions maintain a distance of ≥25cm to avoid cross-contamination of raw materials, and when the three arms work together, the end effector forms a dynamic mutually exclusive zone within a 40cm diameter spherical space (only one arm is allowed to enter), effectively avoiding the risk of collision.

[0041] In this embodiment, a first multi-dimensional sensor group, a second multi-dimensional sensor group, and a third multi-dimensional sensor group are respectively installed on the first, second, and third robotic arms of the coffee beverage robot. It should be understood that the sensors in the multi-dimensional sensor groups are not of a single type, but rather are sensing devices integrating composite functions such as angle detection, displacement tracking, and acceleration measurement, ensuring that the motion details of each joint and end effector of the robotic arm can be captured from all angles.

[0042] After initial calibration (such as joint zero-point correction and sensor zeroing) of the first, second, and third robotic arms, they are driven to perform a no-load run according to the standardized coffee-making process. For example, the first robotic arm precisely picks up the cup from the cup holder and moves it along an optimized path to the ingredient addition area (such as the ice dispensing area), placing the cup stably at the primary handover position. The second robotic arm then takes over the cup within 0.4 seconds, completes the ingredient addition operation (such as quantitative ice addition or syrup injection), and moves it to the secondary handover position. The third robotic arm takes over from this position within 0.3 seconds, performs liquid operations such as high-pressure injection of coffee liquid and layered blending of milk foam, and finally moves it to the cup lid to complete the adaptive pressure seal, forming a closed-loop action chain of cup picking-processing-liquid injection-sealing. This process completely replicates the real operation process but eliminates the need for actual material handling.

[0043] By continuously executing the above-mentioned empty run process at least 20 times (K≥20), motion data of the three robotic arms are synchronously collected during each run using the first multi-dimensional sensor group, the second multi-dimensional sensor group, and the third multi-dimensional sensor group.

[0044] Each run generates three sets of data: the spatiotemporal trajectory sequence of the first robotic arm (recording its path, velocity, and acceleration changes), the spatiotemporal trajectory sequence of the second robotic arm (recording its path, velocity, and acceleration changes), and the spatiotemporal trajectory sequence of the third robotic arm (recording its path, velocity, and acceleration changes). The requirement of a minimum of 20 runs is to accumulate sufficient data, eliminate random errors, and ensure statistical significance.

[0045] Trajectory association features are collected from the K first spatiotemporal trajectory sequences, K second spatiotemporal trajectory sequences, and K third spatiotemporal trajectory sequences. Specifically, two types of features are extracted through algorithms: first single-arm reference trajectory features, second single-arm reference trajectory features, third single-arm reference trajectory features, and reference collaborative space features. Finally, these features are integrated into reference robotic arm trajectory features, which serve as a reference standard for subsequent fault detection.

[0046] The method for analyzing and determining the trajectory characteristics of the reference robotic arm will be described in detail in the following description.

[0047] This embodiment uses the benchmark data accumulated through high-frequency idle running monitoring to construct the benchmark robotic arm trajectory features, thereby achieving the technical effect of providing a reliable reference for subsequent diagnosis of whether the robotic arm handles a fault state.

[0048] S200: A pre-defined periodic detection window is established. When the operating time of the coffee and beverage robot meets the periodic detection window, a fault detection command is generated.

[0049] Specifically, the preset periodic detection window is to set regular self-check trigger conditions for the coffee and beverage robot, ensuring that the equipment performs health checks regularly during long-term operation.

[0050] This window is usually set based on the device's cumulative working time or number of production runs, for example, automatically activating the detection process after every 200 cups produced or after 8 hours of continuous operation.

[0051] This periodic design balances equipment availability with maintenance needs, avoiding service interruptions during peak usage periods. When the actual runtime or workload of the coffee and beverage robot reaches the periodic detection window, a fault detection command is generated, triggering the subsequent robotic arm fault diagnosis process.

[0052] S300: The coffee beverage robot receives and, according to the fault detection instruction, randomly calls single robotic arm detection parameters and robotic arm collaborative detection parameters from the detection rule base;

[0053] In one implementation, the coffee beverage robot receives and, according to the fault detection instruction, randomly calls single-arm detection parameters and robotic arm collaborative detection parameters from the detection rule base. Step S300 of the method provided by this invention includes:

[0054] S310: Based on the periodic detection window, historical coffee production records are traced back to obtain multiple production frequency characteristics of various coffee beverages;

[0055] S320: Based on the multiple production frequency characteristics, reverse screening of sample coffee beverages is performed to locate the candidate test beverage set;

[0056] S330: Using the set of candidate test beverages as a random call constraint, the single robotic arm detection parameters and robotic arm collaborative detection parameters corresponding to the random test beverage production control information are called from the detection rule base, wherein the single robotic arm detection parameters consist of a first robotic arm detection parameter, a second robotic arm detection parameter, and a third robotic arm detection parameter.

[0057] Specifically, this embodiment systematically backtracks all production records within a periodic detection window to analyze the production frequency of different beverages. For example, statistics show that 70% of the production tasks in the past 8 hours were Americano, 25% were latte, and 5% were mocha. By extracting these frequency characteristics, the impact of high-frequency beverage action patterns on the specific load of the robotic arm is identified (e.g., the multiple water-pouring actions of Americano may accelerate the wear of the vertical downward movement mechanism of the second robotic arm), providing data for subsequent screening of detection parameters.

[0058] Based on historical frequency data, test samples were selected by reverse screening, prioritizing the production processes of low-frequency beverages as the test targets. For example, if mocha coffee accounts for only 5% of the production volume, its corresponding robotic arm movements (such as the lateral movement during the chocolate sauce addition stage) are used less frequently in daily operation, and the related transmission components may accumulate potential problems due to the lack of regular activity.

[0059] By including the production process of low-frequency beverages in the candidate test beverage set, the detection is ensured to cover the entire range of motion of the robotic arm, avoiding the omission of edge scenes by conventional detection that only verifies high-frequency paths.

[0060] Randomly selected test beverages are chosen from the candidate test set, and the corresponding production control parameters for each beverage are extracted from the detection rule base. Specifically, the detection rule base stores production process control information for different coffee beverages (such as the water pouring height for Americano and the milk frothing speed for latte). Each beverage corresponds to a specific set of single robotic arm detection parameters (e.g., the movement path parameters of the first robotic arm, the pressure control parameters of the second robotic arm, and the sealing control pressure parameters of the third robotic arm) and robotic arm collaborative detection parameters.

[0061] Based on the beverage type (such as mocha or cold brew) in the candidate set, the control parameters of one of the beverages are randomly selected and converted into detection action instructions for the robotic arm. For example, if mocha coffee is selected, the single robotic arm detection parameters preset during its preparation are invoked. These single robotic arm detection parameters consist of a first robotic arm detection parameter, a second robotic arm detection parameter, and a third robotic arm detection parameter.

[0062] The first robotic arm detection parameter corresponds to the speed curve of its lateral movement to the raw material addition area (such as the chocolate sauce area), the second robotic arm detection parameter defines the auxiliary material addition action (such as the sauce injection pressure threshold), and the third robotic arm detection parameter is associated with the injection height and sealing pressure value during the liquid operation stage. When these parameters are called to drive the three robotic arms to run in coordination, if the robotic arms are fault-free, their motion trajectory will strictly conform to the baseline robotic arm trajectory characteristics.

[0063] This random call mechanism based on actual beverage preparation parameters ensures that the detection actions cover all working conditions of the robotic arm, rather than just testing fixed paths.

[0064] This embodiment achieves the technical effect of avoiding detection blind spots, increasing the probability of fault mode detection, and enhancing the robustness of fault detection by randomly calling diverse detection parameters to cover the full range of robotic arm movements.

[0065] S400: The single robotic arm detection parameters are used to control the coffee beverage robot to perform single robotic arm-specific detection and output the single robotic arm trajectory features.

[0066] In one implementation, the single-arm detection parameters are used to control the coffee beverage robot to perform single-arm specialized detection, and the single-arm trajectory features are output. Step S400 of the method provided by this invention includes:

[0067] S410: During the process of driving the first device robotic arm to operate with the first robotic arm detection parameters, the first real-time trajectory sequence is obtained by synchronously collecting operation data through the first multi-dimensional sensor group.

[0068] S420: Calculate the first real-time acceleration of the first real-time trajectory sequence at the multiple displacement trajectory key points;

[0069] S430: Similarly, acquire the second real-time trajectory sequence, and calculate and output multiple second real-time accelerations based on the second real-time trajectory sequence;

[0070] S440: By analogy, the third real-time trajectory sequence is acquired, and multiple third real-time accelerations are calculated and output based on the third real-time trajectory sequence;

[0071] S450: Structures and stores the first real-time trajectory sequence, the second real-time trajectory sequence, the third real-time trajectory sequence, multiple first real-time accelerations, multiple second real-time accelerations, and multiple third real-time accelerations, and outputs the trajectory features of the single robotic arm.

[0072] This embodiment obtains real-time motion data and extracts key features by individually driving each robotic arm to perform a specific detection action, providing input for subsequent fault determination. During detection, only the target robotic arm (such as the first robotic arm) is activated, while the other two robotic arms remain stationary, ensuring that the individual performance evaluation is not affected by collaborative interference.

[0073] Specifically, during the process of driving the first robotic arm to operate independently using the first robotic arm detection parameters (such as the lateral movement speed curve), the motion data of the first robotic arm is continuously collected by the first multi-dimensional sensor group installed.

[0074] For example, when the detection parameters require the first robotic arm to perform a cup-picking and transferring action, the sensor records the complete path coordinates, joint angle changes, and acceleration fluctuations from the cup holder to the ice removal area, forming the first real-time trajectory sequence containing timestamps. The first real-time trajectory sequence fully reflects the actual motion state of the robotic arm under the detection parameters.

[0075] Using the same method for calculating multiple accelerations of the K first spatiotemporal trajectory sequences at multiple displacement trajectory key points in the detailed explanation of step S1412, the multiple first real-time accelerations of the first real-time trajectory sequence at the multiple displacement trajectory key points are calculated.

[0076] Similarly, a second real-time trajectory sequence is acquired, and multiple second real-time accelerations are calculated and output based on the second real-time trajectory sequence. Similarly, a third real-time trajectory sequence is acquired, and multiple third real-time accelerations are calculated and output based on the third real-time trajectory sequence.

[0077] The first real-time trajectory sequence, the second real-time trajectory sequence, the third real-time trajectory sequence, multiple first real-time accelerations, multiple second real-time accelerations, and multiple third real-time accelerations are stored in a structured manner, and the trajectory features of the single robotic arm are output.

[0078] This embodiment achieves the technical effect of providing input for subsequent fault determination by individually driving each robotic arm to perform a specific detection action, acquiring its real-time motion data, and extracting key features.

[0079] S500: The coffee beverage robot is controlled to perform three-arm collaborative detection using the aforementioned robotic arm collaborative detection parameters, and the collaborative robotic arm trajectory features are output.

[0080] In one implementation, the collaborative detection parameters of the robotic arms are used to control the coffee beverage robot to perform three-arm collaborative detection, and the collaborative robotic arm trajectory features are output. The method step S500 provided by the present invention includes:

[0081] S510: The first robotic arm detection parameters, the second robotic arm detection parameters, and the third robotic arm detection parameters in the synchronous execution state are used as the robotic arm collaborative detection parameters;

[0082] S520: During the operation of the first, second, and third equipment robotic arms, which are driven by the collaborative detection parameters of the robotic arms, the first, second, and third multi-dimensional sensor groups synchronously collect the operation data to obtain the third, fourth, and fifth real-time trajectory sequences.

[0083] S530: Extract the timing data of the joint motion of the robotic arm from the third, fourth, and fifth real-time trajectory sequences, and output the trajectory features of the collaborative robotic arm.

[0084] Specifically, in this embodiment, the independent detection parameters of the first, second, and third robotic arms are combined into a collaborative operation command as the collaborative detection parameters of the robotic arms. For example, in the mocha making process, the speed curve (0.4 m / s) of the first robotic arm moving to the raw material area needs to be triggered synchronously with the jam injection pressure threshold (5 N) of the second robotic arm and the milk foam fusion height parameter (10 cm) of the third robotic arm according to a preset timing sequence to ensure seamless connection of the "cup-processing-liquid injection" action chain.

[0085] During the collaborative operation of the first, second, and third equipment robotic arms using collaborative detection parameters, the first, second, and third multi-dimensional sensor groups synchronously collect operational data to obtain the third, fourth, and fifth real-time trajectory sequences.

[0086] The third, fourth, and fifth real-time trajectory sequences are used to extract the time-series data of the robotic arm joint motion, and the collaborative robotic arm trajectory features are output. These collaborative robotic arm trajectory features have a mapping relationship with the baseline collaborative space features. Specifically:

[0087] The trajectory features of the collaborative robotic arm are composed of spatiotemporal interaction data when the three robotic arms cooperate, including timing synchronization parameters, spatial overlap spacing, path distance between the three robotic arms, and measured timing of joint linkage.

[0088] This embodiment achieves the technical effect of effectively supplementing the detection of single robotic arms through collaborative detection, and providing effective detection data for subsequent comprehensive fault identification of single-robotic arms to three-robotic arms.

[0089] S600: Based on the baseline robotic arm trajectory characteristics, perform trajectory deviation analysis on the single robotic arm trajectory characteristics and the collaborative robotic arm trajectory, and output a robotic arm fault alarm.

[0090] In one implementation, trajectory deviation analysis is performed on the single-manipulator trajectory features and the collaborative manipulator trajectory based on the reference manipulator trajectory features, and a manipulator fault alarm is output. Step S600 of the method provided by this invention includes:

[0091] S610: If the Euclidean distance between the plurality of first real-time accelerations and the average of the plurality of accelerations is greater than a preset acceleration deviation scale, and / or the first real-time trajectory sequence does not completely fall within the first robotic arm motion boundary, output a first robotic arm alarm.

[0092] S620: Similarly, based on the second real-time trajectory sequence and multiple second real-time accelerations, the second device robotic arm is fault-determined, and a second robotic arm alarm is output.

[0093] S630: Similarly, based on the third real-time trajectory sequence and multiple third real-time accelerations, the third device robotic arm is fault-determined, and a third robotic arm alarm is output.

[0094] S640: Based on the spatial deviation between the collaborative robotic arm trajectory characteristics and the baseline collaborative spatial characteristics, output a fourth robotic arm alarm in a quantitative manner.

[0095] S650: Associate the first robotic arm alarm, the second robotic arm alarm, the third robotic arm alarm and the fourth robotic arm alarm, and output the robotic arm fault alarm.

[0096] Specifically, if the Euclidean distance between the plurality of first real-time accelerations and the average of the plurality of accelerations is greater than a preset acceleration deviation scale, and / or the first real-time trajectory sequence does not completely fall within the motion boundary of the first robotic arm, it indicates that the first robotic arm has experienced gear wear or joint loosening, and an alarm for the first robotic arm is output.

[0097] Similarly, based on the second real-time trajectory sequence and multiple second real-time accelerations, the second device robotic arm is fault-determined and a second robotic arm alarm is output. Similarly, based on the third real-time trajectory sequence and multiple third real-time accelerations, the third device robotic arm is fault-determined and a third robotic arm alarm is output.

[0098] By comparing the trajectory characteristics of the collaborative robotic arm (such as the handover time difference and end-effector spacing) with the baseline collaborative spatial characteristics (such as the time difference threshold of 0.3 seconds and the spacing threshold of 5 mm), a spatial deviation index is calculated. For example, if the handover time difference of the cup reaches 0.35 seconds (exceeding the 0.3-second threshold) or the end-effector spacing expands to 6 mm (exceeding the 5 mm threshold), a collaborative fault alarm (third robotic arm alarm) is generated, indicating a program timing misalignment or a decrease in positioning accuracy.

[0099] The system performs correlation analysis on alarms from both individual robotic arms and collaborative systems. For example, if the first robotic arm alarms alone and a collaborative alarm exists simultaneously, it may indicate that its path deviation has caused a collaborative anomaly. If only a collaborative alarm is triggered while the individual robotic arm detects normally, it may be due to communication delay or incorrect collaborative parameter configuration. The final output fault alarm will be labeled with the specific fault type (such as "first robotic arm gear wear" or "collaborative timing exceeded"), providing precise guidance for maintenance.

[0100] This embodiment constructs the single-arm motion boundary and collaborative spatiotemporal rules through no-load modeling, combines random parameter calls to cover the entire working condition path, and uses trajectory deviation analysis and dynamic threshold comparison to accurately identify mechanical wear, motor abnormalities and timing misalignments. The hierarchical alarm mechanism distinguishes between individual unit and system collaborative faults, improves detection sensitivity and positioning accuracy, reduces false alarms and missed alarms, and ensures the reliable operation of the equipment.

[0101] This embodiment achieves the technical effect of effectively distinguishing between individual component failures and abnormalities in the collaborative function of the robotic arm, shortening the fault location time, reducing false alarms and missed alarms of robotic arm faults, optimizing the maintenance efficiency of the coffee beverage robot robotic arm, and ensuring the high precision and stability of the automated coffee making process.

[0102] In one implementation, trajectory association features are acquired from the K first spatiotemporal trajectory sequences, K second spatiotemporal trajectory sequences, and K third spatiotemporal trajectory sequences to obtain the baseline robotic arm trajectory features. Step S140 of the method provided by this invention includes:

[0103] S141: After spatially aligning the K first spatiotemporal trajectory sequences, output the first single-arm reference trajectory features by performing trajectory spatiotemporal deviation analysis;

[0104] S142: By analogy, the second single-arm reference trajectory features are output by performing trajectory spatiotemporal deviation analysis on the K second spatiotemporal trajectory sequences.

[0105] S143: By analogy, the characteristics of the third single-arm reference trajectory are output by performing trajectory spatiotemporal deviation analysis on the K third spatiotemporal trajectory sequences.

[0106] S144: After aligning the K first spatiotemporal trajectory sequences, K second spatiotemporal trajectory sequences, and K third spatiotemporal trajectory sequences through spatiotemporal mapping, extract the mean temporal values ​​of the robotic arm joint motion and output the benchmark collaborative spatial features;

[0107] The first single-arm reference trajectory feature, the second single-arm reference trajectory feature, the third single-arm reference trajectory feature, and the reference collaborative space feature constitute the reference robotic arm trajectory feature.

[0108] In one implementation, after spatially aligning the K first spatiotemporal trajectory sequences, a first single-arm reference trajectory feature is output by performing trajectory spatiotemporal deviation analysis. Step S141 of the method provided by this invention includes:

[0109] S1411: By locating the trajectory deviation of the K first spatiotemporal trajectory sequences, the trajectory deviation boundary is extracted and used as the motion boundary of the first robotic arm;

[0110] S1412: The average acceleration values ​​of the K first spatiotemporal trajectory sequences at multiple key points of multiple displacement trajectories are used as the first motion feature;

[0111] The first robotic arm motion boundary and the first motion feature constitute the first single-arm reference trajectory feature.

[0112] Specifically, the spatial position of the K first spatiotemporal trajectory sequences recorded by the first device's robotic arm during K empty run tests is calibrated to ensure that all data are analyzed in the same coordinate system.

[0113] For example, when the robotic arm of the first device performs a cup-picking action, it should theoretically start from a fixed position on the cup holder (set as the coordinate origin). However, due to mechanical assembly errors or sensor drift, the actual starting point may be distributed within a small area around the origin. By using mathematical transformation, the starting points of all trajectories are aligned to the theoretical origin, eliminating the interference of the device's own errors on the comparability of the data.

[0114] After alignment, the fluctuations of these trajectories in terms of movement path, velocity curve, and acceleration change are analyzed, and the allowable deviation range under normal conditions is statistically determined as the first single-arm reference trajectory feature.

[0115] The specific implementation method for trajectory spatiotemporal deviation analysis is as follows:

[0116] By analyzing K spatiotemporal trajectory sequences from K empty runs, the maximum permissible deviation of the first robotic arm at each position point during its movement is determined. For example, when the robotic arm navigates around a corner of a coffee machine, the actual path may exhibit a slight curvature rather than an ideal straight line due to joint flexibility or control delay. The lateral and longitudinal positions of each trajectory point in 20 tests are statistically analyzed, and the mean plus or minus three standard deviations are used as boundaries (e.g., lateral -1.5mm to +1.8mm, longitudinal ±2mm), forming a spatial envelope channel as the motion boundary of the first robotic arm. This first robotic arm motion boundary represents the motion corridor that the robotic arm should strictly follow under fault-free conditions. If the real-time trajectory exceeds this range, it indicates a possible loose mechanical structure or abnormal program parameters.

[0117] The multiple displacement trajectory key points are obtained based on equal time division, and instantaneous acceleration between nodes is calculated based on the multiple displacement trajectory key points in the K first spatiotemporal trajectory sequences to obtain multiple sets of instantaneous accelerations. By averaging the multiple sets of instantaneous accelerations, multiple acceleration averages corresponding to the multiple displacement trajectory key points are obtained, which serve as the first motion feature. The first robotic arm motion boundary and the first motion feature constitute the first single-arm reference trajectory feature.

[0118] The same processing method is applied to the second robotic arm. By performing trajectory spatiotemporal deviation analysis on the K second spatiotemporal trajectory sequences, the second single-arm reference trajectory features are output. The same processing method is applied to the third robotic arm. By performing trajectory spatiotemporal deviation analysis on the K third spatiotemporal trajectory sequences, the third single-arm reference trajectory features are output.

[0119] The motion data of the first, second, and third robotic arms are correlated in time and space to establish spatiotemporal coordination rule parameters for the three robotic arms to cooperate, which serve as the baseline collaborative space features.

[0120] For example, the baseline collaborative spatial features include: timing synchronization thresholds, such as the second robotic arm must grab the cup within 0.3 seconds after the first robotic arm releases it; spatial overlap rules, such as the distance between end effectors must be <5mm during handover; path interference constraints, such as the minimum safe distance of the motion envelope of the three robotic arms (e.g., ≥50mm); joint linkage timing, such as the phase synchronization requirement between the wrist rotation of the second robotic arm and the elbow extension of the first robotic arm.

[0121] For example, when the first robotic arm places the cup on the transfer platform, the second robotic arm needs to reach the grasping position within 0.25 seconds, and the spatial distance between the end effectors of the two robotic arms must not exceed 3 millimeters. By statistically analyzing the time difference of their movements (e.g., mean 0.18 seconds, standard deviation 0.03 seconds) and spatial overlap (e.g., 95% of the trajectory point spacing is within 1 millimeter) in 20 tests, the spatiotemporal tolerance range for collaborative operation is defined. Simultaneously, the joint linkage timing is analyzed; for example, the wrist rotation of the second robotic arm must be strictly synchronized with the elbow retraction of the first robotic arm, and a time phase difference exceeding 0.1 seconds is considered abnormal.

[0122] The first single-arm reference trajectory feature, the second single-arm reference trajectory feature, the third single-arm reference trajectory feature, and the reference collaborative space feature constitute the reference robotic arm trajectory feature.

[0123] This embodiment achieves the technical effect of providing an effective reference benchmark for the hierarchical detection of robot arm faults in subsequent steps S200-S600 by separating the features of a single robot arm from the features of collaboration.

[0124] Example 2, based on the same inventive concept as the coffee beverage robot arm fault detection method in the foregoing examples, such as... Figure 2 As shown, the present invention provides a fault detection system for a coffee beverage robot arm, wherein the system includes:

[0125] Trajectory construction unit 1 is used to construct the baseline robotic arm trajectory features by performing no-load empty run monitoring on the calibrated coffee and beverage robot.

[0126] The instruction output unit 2 is used to preset a periodic detection window and generate a fault detection instruction when the coffee beverage robot's operating time limit meets the periodic detection window.

[0127] The parameter calling unit 3 is used for the coffee beverage robot to receive and randomly call single robotic arm detection parameters and robotic arm collaborative detection parameters from the detection rule base according to the fault detection instruction.

[0128] Single-arm detection unit 4 is used to control the coffee beverage robot to perform single-arm specialized detection using the single-arm detection parameters and output single-arm trajectory features.

[0129] The collaborative detection unit 5 is used to control the coffee beverage robot to perform three-arm collaborative detection using the collaborative detection parameters of the robotic arms, and output the collaborative robotic arm trajectory features.

[0130] The fault alarm unit 6 is used to perform trajectory deviation analysis on the single robot arm trajectory characteristics and the collaborative robot arm trajectory based on the reference robot arm trajectory characteristics, and output a robot arm fault alarm.

[0131] In one implementation, the trajectory construction unit 1 is further configured to:

[0132] The first, second, and third robotic arms of the coffee beverage robot are respectively equipped with a first multi-dimensional sensor group, a second multi-dimensional sensor group, and a third multi-dimensional sensor group. After calibrating the first, second, and third robotic arms, no-load idle running monitoring is performed on the first, second, and third robotic arms to drive them to simulate the standard coffee-making process. During the first, second, and third robotic arms performing K rounds of no-load idle running, the first, second, and third multi-dimensional sensor groups synchronously collect running data to obtain K first spatiotemporal trajectory sequences, K second spatiotemporal trajectory sequences, and K third spatiotemporal trajectory sequences, where K ≥ 20. Trajectory association feature acquisition is performed on the K first spatiotemporal trajectory sequences, K second spatiotemporal trajectory sequences, and K third spatiotemporal trajectory sequences to obtain the baseline robotic arm trajectory features. In one implementation, the trajectory construction unit 1 is further used for:

[0133] After spatially aligning the K first spatiotemporal trajectory sequences, a first single-arm reference trajectory feature is output by performing trajectory spatiotemporal deviation analysis; similarly, a second single-arm reference trajectory feature is output by performing trajectory spatiotemporal deviation analysis on the K second spatiotemporal trajectory sequences; similarly, a third single-arm reference trajectory feature is output by performing trajectory spatiotemporal deviation analysis on the K third spatiotemporal trajectory sequences; after spatiotemporally mapping and aligning the K first spatiotemporal trajectory sequences, K second spatiotemporal trajectory sequences, and K third spatiotemporal trajectory sequences, the temporal mean of the robotic arm joint motion is extracted, and a reference collaborative spatial feature is output; wherein, the first single-arm reference trajectory feature, the second single-arm reference trajectory feature, the third single-arm reference trajectory feature, and the reference collaborative spatial feature constitute the reference robotic arm trajectory feature.

[0134] In one implementation, the trajectory construction unit 1 is further configured to:

[0135] By locating the trajectory deviations of the K first spatiotemporal trajectory sequences, the trajectory deviation boundaries are extracted and used as the first robotic arm motion boundaries; the average values ​​of multiple accelerations at multiple key points of the K first spatiotemporal trajectory sequences are calculated as the first motion features; wherein, the first robotic arm motion boundaries and the first motion features constitute the first single-arm reference trajectory features.

[0136] In one implementation, the parameter calling unit 3 is further used for:

[0137] Historical coffee production records are traced back based on the periodic detection window to obtain multiple production frequency characteristics of various coffee beverages; sample coffee beverages are reverse-selected based on the multiple production frequency characteristics to locate a set of candidate test beverages; the set of candidate test beverages is used as a random call constraint to call the single robotic arm detection parameters and robotic arm collaborative detection parameters corresponding to the random test beverage production control information from the detection rule base, wherein the single robotic arm detection parameters consist of a first robotic arm detection parameter, a second robotic arm detection parameter, and a third robotic arm detection parameter.

[0138] In one implementation, the single-arm detection unit 4 is further used for:

[0139] During the operation of the first robotic arm driven by the first robotic arm detection parameters, the first multi-dimensional sensor group synchronously collects operating data to obtain a first real-time trajectory sequence; calculates multiple first real-time accelerations at multiple key points of the displacement trajectory based on the first real-time trajectory sequence; similarly, a second real-time trajectory sequence is collected and multiple second real-time accelerations are calculated and output based on the second real-time trajectory sequence; similarly, a third real-time trajectory sequence is collected and multiple third real-time accelerations are calculated and output based on the third real-time trajectory sequence; the first real-time trajectory sequence, the second real-time trajectory sequence, the third real-time trajectory sequence, multiple first real-time accelerations, multiple second real-time accelerations, and multiple third real-time accelerations are structured and stored, and the single robotic arm trajectory features are output.

[0140] In one implementation, the collaborative detection unit 5 is further configured to:

[0141] The detection parameters of the first, second, and third robotic arms in synchronous execution states are used as the collaborative detection parameters of the robotic arms. During the collaborative driving of the first, second, and third robotic arms using the collaborative detection parameters, the first, second, and third multi-dimensional sensor groups synchronously collect running data to obtain a third, fourth, and fifth real-time trajectory sequence. The robotic arm joint motion timing data are extracted from the third, fourth, and fifth real-time trajectory sequences to output the collaborative robotic arm trajectory features.

[0142] In one implementation, the fault alarm unit 6 is further configured to:

[0143] If the Euclidean distance between the plurality of first real-time accelerations and the average of the plurality of accelerations is greater than a preset acceleration deviation scale, and / or the first real-time trajectory sequence does not completely fall within the motion boundary of the first robotic arm, a first robotic arm alarm is output; similarly, based on the second real-time trajectory sequence and the plurality of second real-time accelerations, a fault judgment is made on the second device robotic arm, and a second robotic arm alarm is output; similarly, based on the third real-time trajectory sequence and the plurality of third real-time accelerations, a fault judgment is made on the third device robotic arm, and a third robotic arm alarm is output; based on the spatial deviation between the collaborative robotic arm trajectory characteristics and the benchmark collaborative space characteristics, a fourth robotic arm alarm is quantified and output; by associating the first robotic arm alarm, the second robotic arm alarm, the third robotic arm alarm, and the fourth robotic arm alarm, a robotic arm fault alarm is output.

[0144] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for fault detection of a robotic arm used in coffee beverage manufacturing, characterized in that, include: By performing no-load empty run monitoring on the calibrated coffee and beverage robot, a baseline robotic arm trajectory feature was constructed. A pre-defined periodic detection window is established, and a fault detection command is generated when the operating time of the coffee and beverage robot meets the periodic detection window. The coffee beverage robot receives and, according to the fault detection instruction, randomly calls single-arm detection parameters and robotic arm collaborative detection parameters from the detection rule base; The single-arm detection parameters are used to control the coffee beverage robot to perform single-arm specialized detection and output the single-arm trajectory features; The coffee beverage robot is controlled to perform three-arm collaborative detection using the aforementioned robotic arm collaborative detection parameters, and the collaborative robotic arm trajectory features are output. Based on the baseline robotic arm trajectory characteristics, trajectory deviation analysis is performed on the single robotic arm trajectory characteristics and the collaborative robotic arm trajectory, and a robotic arm fault alarm is output. Among these methods, a baseline robotic arm trajectory feature was constructed by performing no-load idle running monitoring on the calibrated coffee beverage robot, including: The first, second, and third robotic arms of the coffee beverage robot are respectively equipped with a first multi-dimensional sensor group, a second multi-dimensional sensor group, and a third multi-dimensional sensor group; After calibrating the first, second, and third robotic arms, no-load idle running monitoring is performed on the first, second, and third robotic arms to drive them to simulate the standard coffee-making process. During the K rounds of no-load empty running of the first, second, and third equipment robotic arms, the first, second, and third multi-dimensional sensor groups synchronously collect running data to obtain K first spatiotemporal trajectory sequences, K second spatiotemporal trajectory sequences, and K third spatiotemporal trajectory sequences, where K ≥ 20; Trajectory association features are collected from the K first spatiotemporal trajectory sequences, K second spatiotemporal trajectory sequences, and K third spatiotemporal trajectory sequences to obtain the baseline robotic arm trajectory features; Trajectory association features are collected from the K first spatiotemporal trajectory sequences, K second spatiotemporal trajectory sequences, and K third spatiotemporal trajectory sequences to obtain the baseline robotic arm trajectory features, including: After spatially aligning the K first spatiotemporal trajectory sequences, the first single-arm reference trajectory features are output by performing trajectory spatiotemporal deviation analysis. By performing trajectory spatiotemporal deviation analysis on the K second spatiotemporal trajectory sequences, the characteristics of the second single-arm reference trajectory are output. By performing trajectory spatiotemporal deviation analysis on the K third spatiotemporal trajectory sequences, the characteristics of the third single-arm reference trajectory are output. After aligning the K first spatiotemporal trajectory sequences, K second spatiotemporal trajectory sequences, and K third spatiotemporal trajectory sequences through spatiotemporal mapping, the mean temporal values ​​of the robotic arm joint motion are extracted, and the baseline collaborative spatial features are output. The first single-arm reference trajectory feature, the second single-arm reference trajectory feature, the third single-arm reference trajectory feature, and the reference collaborative space feature constitute the reference robotic arm trajectory feature. After spatially aligning the K first spatiotemporal trajectory sequences, the first single-arm reference trajectory features are output through trajectory spatiotemporal deviation analysis, including: By locating the trajectory deviations of the K first spatiotemporal trajectory sequences, the trajectory deviation boundaries are extracted and used as the motion boundaries of the first robotic arm. The average acceleration values ​​of the K first spatiotemporal trajectory sequences at multiple key points of multiple displacement trajectories are used as the first motion feature; Wherein, the first robotic arm motion boundary and the first motion feature constitute the first single-arm reference trajectory feature; The coffee beverage robot receives and, according to the fault detection instruction, randomly calls single-arm detection parameters and robotic arm collaborative detection parameters from the detection rule base, including: Based on the periodic detection window, historical coffee production records are traced back to obtain multiple production frequency characteristics for various coffee beverages; Based on the multiple production frequency characteristics, the sample coffee beverages are screened in reverse to locate the set of candidate test beverages; Using the set of candidate test beverages as a random call constraint, the single robotic arm detection parameters and robotic arm collaborative detection parameters corresponding to the random test beverage production control information are called from the detection rule base. The single robotic arm detection parameters consist of a first robotic arm detection parameter, a second robotic arm detection parameter, and a third robotic arm detection parameter.

2. The method for fault detection of the robotic arm of a coffee beverage robot as described in claim 1, characterized in that, The single-arm detection parameters are used to control the coffee beverage robot to perform single-arm specialized detection, and the single-arm trajectory features are output, including: During the process of driving the first device robotic arm to operate on a single arm using the first robotic arm detection parameters, the first real-time trajectory sequence is obtained by synchronously collecting operating data through the first multi-dimensional sensor group. Calculate the first real-time acceleration of the first real-time trajectory sequence at multiple key points of the multiple displacement trajectories; Acquire a second real-time trajectory sequence, and calculate and output multiple second real-time accelerations based on the second real-time trajectory sequence; Acquire a third real-time trajectory sequence, and calculate and output multiple third real-time accelerations based on the third real-time trajectory sequence; The first real-time trajectory sequence, the second real-time trajectory sequence, the third real-time trajectory sequence, multiple first real-time accelerations, multiple second real-time accelerations, and multiple third real-time accelerations are stored in a structured manner, and the trajectory features of the single robotic arm are output.

3. The method for fault detection of the robotic arm of a coffee beverage robot as described in claim 2, characterized in that, The coffee beverage robot is controlled by the aforementioned robotic arm collaborative detection parameters to perform three-arm collaborative detection, and the collaborative robotic arm trajectory features are output, including: The first robotic arm detection parameters, the second robotic arm detection parameters, and the third robotic arm detection parameters in the synchronous execution state are used as the robotic arm collaborative detection parameters. During the operation of the first, second, and third equipment robotic arms, which are driven by the collaborative detection parameters of the robotic arms, the first, second, and third multi-dimensional sensor groups synchronously collect the operation data to obtain the third, fourth, and fifth real-time trajectory sequences. The timing data of the joint motion of the robotic arm is extracted from the third, fourth, and fifth real-time trajectory sequences, and the trajectory features of the collaborative robotic arm are output.

4. The method for fault detection of the robotic arm of a coffee beverage robot as described in claim 3, characterized in that, Based on the baseline robotic arm trajectory characteristics, trajectory deviation analysis is performed on the single robotic arm trajectory characteristics and the collaborative robotic arm trajectory, and a robotic arm fault alarm is output, including: If the Euclidean distance between the plurality of first real-time accelerations and the average of the plurality of accelerations is greater than a preset acceleration deviation scale, and / or the first real-time trajectory sequence does not completely fall within the first robotic arm motion boundary, a first robotic arm alarm will be output. Based on the second real-time trajectory sequence and multiple second real-time accelerations, the second device robotic arm is fault-determined, and a second robotic arm alarm is output. Based on the third real-time trajectory sequence and multiple third real-time accelerations, the third device robotic arm is fault-determined and an alarm for the third robotic arm is output. Based on the spatial deviation between the collaborative robotic arm trajectory characteristics and the baseline collaborative spatial characteristics, a fourth robotic arm alarm is quantitatively output. Associate the first robotic arm alarm, the second robotic arm alarm, the third robotic arm alarm, and the fourth robotic arm alarm, and output the robotic arm fault alarm.

5. A fault detection system for a coffee beverage robot arm, characterized in that, The steps for implementing the method according to any one of claims 1 to 4 include: The trajectory construction unit is used to construct the trajectory features of a baseline robotic arm by performing no-load idle run monitoring on the calibrated coffee and beverage robot. The construction of the baseline robotic arm trajectory features by performing no-load idle run monitoring on the calibrated coffee and beverage robot includes: The first, second, and third robotic arms of the coffee beverage robot are respectively equipped with a first multi-dimensional sensor group, a second multi-dimensional sensor group, and a third multi-dimensional sensor group; After calibrating the first, second, and third robotic arms, no-load idle running monitoring is performed on the first, second, and third robotic arms to drive them to simulate the standard coffee-making process. During the K rounds of no-load empty running of the first, second, and third equipment robotic arms, the first, second, and third multi-dimensional sensor groups synchronously collect running data to obtain K first spatiotemporal trajectory sequences, K second spatiotemporal trajectory sequences, and K third spatiotemporal trajectory sequences, where K ≥ 20; Trajectory association features are collected from the K first spatiotemporal trajectory sequences, K second spatiotemporal trajectory sequences, and K third spatiotemporal trajectory sequences to obtain the baseline robotic arm trajectory features; Trajectory association features are collected from the K first spatiotemporal trajectory sequences, K second spatiotemporal trajectory sequences, and K third spatiotemporal trajectory sequences to obtain the baseline robotic arm trajectory features, including: After spatially aligning the K first spatiotemporal trajectory sequences, the first single-arm reference trajectory features are output by performing trajectory spatiotemporal deviation analysis. By performing trajectory spatiotemporal deviation analysis on the K second spatiotemporal trajectory sequences, the characteristics of the second single-arm reference trajectory are output. By performing trajectory spatiotemporal deviation analysis on the K third spatiotemporal trajectory sequences, the characteristics of the third single-arm reference trajectory are output. After aligning the K first spatiotemporal trajectory sequences, K second spatiotemporal trajectory sequences, and K third spatiotemporal trajectory sequences through spatiotemporal mapping, the mean temporal values ​​of the robotic arm joint motion are extracted, and the baseline collaborative spatial features are output. The first single-arm reference trajectory feature, the second single-arm reference trajectory feature, the third single-arm reference trajectory feature, and the reference collaborative space feature constitute the reference robotic arm trajectory feature. After spatially aligning the K first spatiotemporal trajectory sequences, the first single-arm reference trajectory features are output through trajectory spatiotemporal deviation analysis, including: By locating the trajectory deviations of the K first spatiotemporal trajectory sequences, the trajectory deviation boundaries are extracted and used as the motion boundaries of the first robotic arm. The average acceleration values ​​of the K first spatiotemporal trajectory sequences at multiple key points of multiple displacement trajectories are used as the first motion feature; Wherein, the first robotic arm motion boundary and the first motion feature constitute the first single-arm reference trajectory feature; The instruction output unit is used to preset a periodic detection window and generate a fault detection instruction when the coffee beverage robot's operating time limit meets the periodic detection window. The parameter calling unit is used by the coffee beverage robot to receive and, according to the fault detection instruction, randomly call single-arm detection parameters and robotic arm collaborative detection parameters from the detection rule base, including: Based on the periodic detection window, historical coffee production records are traced back to obtain multiple production frequency characteristics for various coffee beverages; Based on the multiple production frequency characteristics, the sample coffee beverages are screened in reverse to locate the set of candidate test beverages; Using the set of candidate test beverages as a random call constraint, the single robotic arm detection parameters and robotic arm collaborative detection parameters corresponding to the random test beverage production control information are called from the detection rule base. The single robotic arm detection parameters consist of a first robotic arm detection parameter, a second robotic arm detection parameter, and a third robotic arm detection parameter. A single-arm detection unit is used to control the coffee beverage robot to perform single-arm specialized detection using the single-arm detection parameters and output the single-arm trajectory features. The collaborative detection unit is used to control the coffee beverage robot to perform three-arm collaborative detection using the robotic arm collaborative detection parameters, and output the collaborative robotic arm trajectory features. The fault alarm unit is used to perform trajectory deviation analysis on the single robot arm trajectory characteristics and the collaborative robot arm trajectory based on the reference robot arm trajectory characteristics, and output robot arm fault alarm.

Images