Method, device, medium, equipment and product for detecting handling equipment

Abstract

The application discloses a kind of handling equipment detection method, device, medium, equipment and product, it is related to electronic technical field, for accurately detecting the exception of handling equipment.The method comprises: obtaining multiple groups of log information of handling equipment;Log information includes speed data and torque data;According to speed data, multiple groups of log information are clustered, and multiple groups of log information after clustering are obtained;Based on the torque data in multiple groups of log information after clustering, determine whether handling equipment is abnormal handling equipment.

Description

Technical Field

[0001] This application relates to the field of electronic technology, and in particular to a method, apparatus, medium, equipment and product for detecting handling equipment. Background Technology

[0002] In current industrial applications, material handling equipment (such as multi-axis industrial robots) is widely used. Due to prolonged high-speed operation, material handling equipment faces problems such as equipment wear, abnormal joint movement, and fluctuations in speed and torque. These problems often manifest as minor motion abnormalities and vibration fluctuations in the early stages, making them difficult to detect in advance through traditional routine maintenance methods.

[0003] However, as abnormal fluctuations accumulate, the safety hazards in the production process will increase. How to accurately detect abnormalities in handling equipment is a technical problem that urgently needs to be solved. Summary of the Invention

[0004] This application provides a method, apparatus, medium, equipment, and product for detecting abnormalities in handling equipment.

[0005] To achieve the above objectives, this application adopts the following technical solution:

[0006] Firstly, a method for detecting handling equipment is provided. The method includes: acquiring multiple sets of log information of the handling equipment; the log information includes speed data and torque data; clustering the multiple sets of log information according to the speed data to obtain multiple sets of clustered log information; and determining whether the handling equipment is an abnormal handling equipment based on the torque data in the multiple sets of clustered log information.

[0007] Optionally, based on the torque data in the clustered log information, determine whether the handling equipment is an abnormal handling equipment, including: correcting the torque data in the clustered log information to obtain target torque data; comparing the target torque data with the torque data to generate a reconstruction loss for each torque data; and determining whether the handling equipment is an abnormal handling equipment based on the dispersion of the reconstruction loss of different torque data after clustering.

[0008] Optionally, based on the degree of dispersion of the reconstruction loss of different torque data after clustering, it is determined whether the handling equipment is an abnormal handling equipment, including: if the degree of dispersion of the reconstruction loss of different torque data after clustering is greater than or equal to a preset degree of dispersion, the handling equipment is determined to be an abnormal handling equipment; if the degree of dispersion of the reconstruction loss of different torque data after clustering is less than the preset degree of dispersion, the handling equipment is determined to be a non-abnormal handling equipment.

[0009] Optionally, the method further includes: for each reconstruction loss, if the reconstruction loss is greater than or equal to a reconstruction loss threshold, determining that the dispersion of the reconstruction loss of different torque data after clustering is greater than or equal to a preset dispersion.

[0010] Optionally, the reconstruction loss threshold satisfies the following relationship: Threshold1=μ+kσ; where Threshold1 represents the reconstruction loss threshold; μ represents the mean of multiple reconstruction losses; k represents the preset scaling factor; and σ represents the standard deviation of multiple reconstruction losses.

[0011] Optionally, the torque data in the clustered log information is corrected to obtain the target torque data, including: correcting the torque data in the clustered log information based on multiple correction models to obtain multiple corrected torque data; and performing weighted summation on the multiple corrected torque data to obtain the target torque data.

[0012] Optionally, multiple sets of log information from the handling equipment can be obtained, including: obtaining multiple sets of initial log information from the handling equipment; interpolating the multiple sets of initial log information to obtain multiple sets of log information; and ensuring that the data lengths of the multiple sets of log information are the same.

[0013] Optionally, multiple sets of log information for the handling equipment can be obtained, including: multiple sets of log information for each axis component of the handling equipment; each axis component is configured with a different servo motor.

[0014] Based on the technical solution provided in this application, multiple sets of log information are clustered according to speed data to obtain clustered sets of log information. Based on the torque data in these clustered sets of log information, it is determined whether the handling equipment is abnormal. This eliminates the need for manual annotation; different operating states of the equipment can be identified through clustering, and the accuracy of determining whether the handling equipment is abnormal can be significantly improved by using torque data from similar operating states to identify abnormalities in the handling equipment.

[0015] Secondly, a handling equipment detection device is provided, comprising: an acquisition unit and a processing unit; the acquisition unit is used to acquire multiple sets of log information of the handling equipment; the log information includes speed data and torque data; the processing unit is used to cluster the multiple sets of log information according to the speed data to obtain multiple sets of clustered log information; the processing unit is also used to determine whether the handling equipment is an abnormal handling equipment based on the torque data in the multiple sets of clustered log information.

[0016] Optionally, the processing unit is specifically used to: correct the torque data in multiple sets of clustered log information to obtain target torque data; compare the target torque data with the torque data to generate a reconstruction loss for each torque data; and determine whether the handling equipment is an abnormal handling equipment based on the dispersion of the reconstruction loss of different torque data after clustering.

[0017] Optionally, the processing unit is further configured to: determine the handling equipment as abnormal handling equipment when the degree of dispersion of the reconstruction loss of different torque data after clustering is greater than or equal to a preset degree of dispersion; and determine the handling equipment as non-abnormal handling equipment when the degree of dispersion of the reconstruction loss of different torque data after clustering is less than a preset degree of dispersion.

[0018] Optionally, the processing unit is also configured to: for each reconstruction loss, if the reconstruction loss is greater than or equal to the reconstruction loss threshold, determine that the degree of dispersion of the reconstruction loss of different torque data after clustering is greater than or equal to a preset degree of dispersion.

[0019] Optionally, the reconstruction loss threshold satisfies the following relationship: Threshold1=μ+kσ; where Threshold1 represents the reconstruction loss threshold; μ represents the mean of multiple reconstruction losses; k represents the preset scaling factor; and σ represents the standard deviation of multiple reconstruction losses.

[0020] Optionally, the processing unit is further configured to: correct the torque data in multiple sets of clustered log information based on multiple correction models to obtain multiple corrected torque data; and perform weighted summation on the multiple corrected torque data to obtain the target torque data.

[0021] Optionally, the acquisition unit is specifically used for: acquiring multiple sets of initial log information from the handling equipment; performing interpolation processing on the multiple sets of initial log information to obtain multiple sets of log information; and ensuring that the data lengths of the multiple sets of log information are the same.

[0022] Optionally, the acquisition unit is also used to: acquire multiple sets of log information for each axis component of the handling equipment; and configure different servo motors for each axis component.

[0023] Thirdly, a handling equipment detection device is provided, which can realize the functions performed by the handling equipment detection device in the above aspects or possible designs. The functions can be implemented by hardware. For example, in one possible design, the handling equipment detection device may include a processor and a communication interface. The processor can be used to support the handling equipment detection device in realizing the functions involved in the first aspect or any possible design of the first aspect.

[0024] In another possible design, the handling equipment detection device may further include a memory for storing necessary computer execution instructions and data. When the handling equipment detection device is running, the processor executes the computer execution instructions stored in the memory to cause the handling equipment detection device to perform the first aspect or any of the possible handling equipment detection methods described above.

[0025] Fourthly, a computer-readable storage medium is provided, which may be a readable non-volatile storage medium storing computer instructions or programs that, when executed on a computer, enable the computer to perform the first aspect or any of the possible handling device detection methods described above.

[0026] Fifthly, a computer program product containing instructions is provided, which, when run on a computer, enables the computer to execute the handling equipment detection method of the first aspect or any possible design of the above aspects.

[0027] A sixth aspect provides an electronic device comprising one or more processors and one or more memories. The one or more memories are coupled to the one or more processors, and the one or more memories are used to store computer program code, including computer instructions, which, when executed by the one or more processors, cause the electronic device to perform a handling device detection method as described in the first aspect or any possible design of the first aspect.

[0028] In a seventh aspect, a chip system is provided, comprising a processor and a communication interface, which can be used to implement the functions performed by the handling equipment detection device in the first aspect or any possible design of the first aspect. In one possible design, the chip system further includes a memory for storing program instructions and / or data. The chip system may be composed of chips or may include chips and other discrete devices, without limitation. Attached Figure Description

[0029] Figure 1 This is a schematic diagram of the structure of a handling equipment detection system provided in an embodiment of this application;

[0030] Figure 2 This is a schematic diagram of the structure of a handling equipment detection device provided in an embodiment of this application;

[0031] Figure 3 A schematic flowchart illustrating a method for detecting handling equipment provided in an embodiment of this application;

[0032] Figure 4This is a schematic diagram of initial log information provided in an embodiment of this application;

[0033] Figure 5 A schematic diagram of torque data before interpolation processing is provided in an embodiment of this application;

[0034] Figure 6 A schematic diagram of velocity data before interpolation processing is provided in an embodiment of this application;

[0035] Figure 7 A schematic diagram of torque data after interpolation processing is provided in an embodiment of this application;

[0036] Figure 8 A schematic diagram of speed data after interpolation processing is provided in an embodiment of this application;

[0037] Figure 9 A clustering diagram provided for an embodiment of this application;

[0038] Figure 10 A flowchart illustrating another method for detecting handling equipment provided in this application embodiment;

[0039] Figure 11 A schematic diagram of the corrected first torque data output by a CAE model provided in an embodiment of this application;

[0040] Figure 12 A schematic diagram of the corrected second torque data output by the Densenet model provided in an embodiment of this application;

[0041] Figure 13 A schematic diagram of the corrected third torque data output by a DropoutAE model provided in an embodiment of this application;

[0042] Figure 14 A schematic diagram of target torque data provided in an embodiment of this application;

[0043] Figure 15 A schematic diagram of reconstruction loss provided for an embodiment of this application;

[0044] Figure 16 This is a schematic diagram of another handling equipment detection device provided in an embodiment of this application. Detailed Implementation

[0045] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0046] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0047] It should also be understood that the term "comprising" indicates the presence of the described feature, whole, step, operation, element and / or component, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements and / or components.

[0048] In current industrial applications, material handling equipment (such as multi-axis industrial robots) is widely used. Due to prolonged high-speed operation, material handling equipment faces problems such as equipment wear, abnormal joint movement, and fluctuations in speed and torque. These problems often manifest as minor motion abnormalities and vibration fluctuations in the early stages, making them difficult to detect in advance through traditional routine maintenance methods.

[0049] However, as abnormal fluctuations accumulate, the safety hazards in the production process will increase. These accumulated abnormal fluctuations may evolve into sudden malfunctions during production, leading to complete line shutdowns, decreased production efficiency, and even safety accidents. Furthermore, traditional methods of health management for material handling equipment rely on regular manual inspections and post-malfunction repairs, which cannot obtain real-time status data of the equipment or respond promptly to dynamic changes in its condition.

[0050] In some embodiments, a sliding window algorithm can be used for data segmentation, and an encoder-decoder architecture can be employed to extract data features. Adding a Dropout layer effectively prevents overfitting, and the reconstruction error distribution is introduced to determine the operating status of the handling equipment. This technology provides an innovative solution for real-time fault detection, improving the accuracy and timeliness of fault identification in handling equipment in complex industrial environments.

[0051] However, this method has significant limitations, especially when processing operational data from multi-axis material handling equipment. Although reconstruction error and sliding window algorithms are introduced, this method mainly focuses on the characteristics of a single axis and fails to effectively integrate speed and torque data from multiple axes. This results in a one-sided understanding of the overall health of the equipment and cannot fully reflect the failure modes of the material handling equipment under different operating conditions.

[0052] In other embodiments, short-time Fourier transform can be used to process time-domain motion data to generate a time-frequency graph, and then the HOG feature extraction algorithm can be used to obtain the feature information of the vibration data. By combining it with fault-labeled data, a LightGBM fault detection model is constructed, and a genetic algorithm is used to optimize the model parameters. This technique utilizes modern machine learning algorithms to improve the efficiency of fault detection, especially in vibration data analysis.

[0053] However, it relies on vibration data, neglecting the comprehensive analysis of other important operating parameters such as speed and torque. While vibration data is important, it cannot fully reflect the overall operating status of the robot, especially in complex fault scenarios. Furthermore, the high computational complexity of genetic algorithms leads to response delays in real-time monitoring, and when processing non-stationary signals, the limitations of short-time Fourier transform prevent it from providing reliable feature extraction in the presence of strong noise or sudden faults, thus affecting the accuracy and timeliness of fault detection.

[0054] Therefore, how to accurately detect abnormalities in handling equipment is a technical problem that urgently needs to be solved.

[0055] In view of this, embodiments of this application provide a method for detecting a handling device, including: obtaining the position coordinates of multiple chips to be welded in a substrate; welding the chips to be welded based on the position coordinates and multiple split laser beams obtained by splitting a laser beam; the number of multiple split laser beams is the same as the number of multiple chips to be welded, and each split laser beam is focused on the chip to be welded corresponding to a different position coordinate.

[0056] The methods provided in the embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0057] It should be noted that the network system described in the embodiments of this application is for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and does not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of network systems and the emergence of other network systems, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0058] Figure 1 The diagram shown is a structural schematic of a handling equipment detection system 10 provided in an embodiment of this application. Figure 1 As shown, the handling equipment detection system 10 may include a handling equipment detection device 11 and a handling equipment 12.

[0059] The handling equipment detection device 11 and the handling equipment 12 are connected. For example, the handling equipment detection device 11 and the handling equipment 12 can be connected via a wired connection. Alternatively, the handling equipment detection device 11 and the handling equipment 12 can be connected wirelessly.

[0060] The conveying device 12 involved in the embodiments of this application can be used to convey objects to be processed. For example, the conveying device 12 can be a robot, and the object to be processed can be a substrate.

[0061] In this application, the handling equipment detection device 11 can be an electronic device with processing capabilities, such as a computer or server. It is used to detect the handling equipment 12 to determine whether any abnormalities have occurred. For example, the handling equipment detection device 11 can be a computer, server, etc. The server can be a single server or a server cluster consisting of multiple servers. In some embodiments, the server cluster can also be a distributed cluster. This application does not limit the specific technology, quantity, or form of the handling equipment detection device 11.

[0062] In practical implementation, Figure 1 Each device in the process can be adopted Figure 2 The shown composition structure, or including Figure 2 The components shown. Figure 2 This is a schematic diagram of the structure of a handling equipment detection device 200 provided in an embodiment of this application. The handling equipment detection device 200 can be a network device, or it can be a chip or system-on-a-chip within a network device. Figure 2 As shown, the handling equipment detection device 200 includes a processor 201, a communication interface 202, and a communication line 203.

[0063] Furthermore, the handling equipment detection device 200 may also include a memory 204. The processor 201, memory 204, and communication interface 202 can be connected via a communication line 203.

[0064] The processor 201 can be a CPU, a general-purpose processor, a network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a programmable logic device (PLD), or any combination thereof. The processor 201 can also be other devices with processing capabilities, such as circuits, devices, or software modules, without limitation.

[0065] Communication interface 202 is used to communicate with other devices or other communication networks. Communication interface 202 can be a module, circuit, communication interface, or any device capable of enabling communication.

[0066] Communication line 203 is used to transmit information between the various components included in the handling equipment detection device 200.

[0067] Memory 204 is used to store instructions. These instructions can be computer programs.

[0068] The memory 204 can be a read-only memory (ROM) or other type of static storage device that can store static information and / or instructions; it can also be a random access memory (RAM) or other type of dynamic storage device that can store information and / or instructions; it can also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, etc., without limitation.

[0069] It should be noted that the memory 204 can exist independently of the processor 201 or can be integrated with the processor 201. The memory 204 can be used to store instructions, program code, or some data, etc. The memory 204 can be located inside or outside the handling equipment detection device 200, without limitation. The processor 201 is used to execute the instructions stored in the memory 204 to implement the handling equipment detection method provided in the following embodiments of this application.

[0070] In one example, processor 201 may include one or more CPUs, for example, Figure 2 CPU0 and CPU1 in the CPU.

[0071] As an optional implementation, the handling equipment detection device 200 includes multiple processors, for example, besides Figure 2 In addition to processor 201, it may also include processor 205.

[0072] It should be pointed out that, Figure 2 The composition shown does not constitute a basis for the interpretation of this invention. Figure 1 The limitations of each device in the process, except Figure 2 In addition to the components shown, Figure 1 The various devices in the can include ratio Figure 2 More or fewer components, or combinations of certain components, or different arrangements of components.

[0073] In this embodiment of the application, the chip system may be composed of chips or may include chips and other discrete devices.

[0074] Furthermore, the actions, terms, etc., involved in the various embodiments of this application can be referenced interchangeably without limitation. The message names or parameter names in the messages exchanged between the various devices in the embodiments of this application are merely examples, and other names may be used in specific implementations without limitation.

[0075] To facilitate a clear description of the technical solutions in the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish identical or similar items with essentially the same function and effect. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and the terms "first" and "second" are not necessarily different.

[0076] It should be noted that, in this application, the terms "exemplary" or "for example" are used to indicate that something is being described as an example, illustration, or illustration. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or design solutions. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0077] In this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0078] The following is combined with Figure 1 The present invention describes a handling equipment detection system and a handling equipment detection method provided in the embodiments of this application.

[0079] Figure 3 This is a flowchart illustrating a method for detecting handling equipment provided in an embodiment of this application, as shown below. Figure 3 As shown, the method includes the following steps S301-S303:

[0080] S301. Obtain multiple sets of log information from the handling equipment.

[0081] Among them, the handling equipment can be Figure 1 The handling equipment 12 in the system. Log information includes speed data and torque data.

[0082] Multiple sets of log information can be log information for preset historical time periods. For example, the preset historical time period can be the 24 hours before the current time. A single set of log information can be the log information from the start time to the end time corresponding to the execution of a task by the handling equipment.

[0083] As one possible implementation, the handling equipment detection device can acquire multiple sets of initial log information from the handling equipment and perform interpolation processing on these multiple sets of initial log information to obtain multiple sets of log information.

[0084] In one example, Figure 4 This diagram illustrates initial log information. Figure 4 As shown, the initial log information may include speed data and torque data.

[0085] It should be noted that when the handling equipment is a multi-axis robot, the amount of data collected varies depending on the robot's different tasks and load conditions. Through interpolation, the multiple sets of log information obtained after interpolation correspond to data of the same length.

[0086] In one example, the handling equipment detection device can use the sample size with the most collected data as the baseline, and use a linear interpolation formula to supplement the missing data samples to the baseline, ensuring that the amount of data in each log message is consistent in quantity.

[0087] For example, the linear interpolation formula can be the following formula:

[0088]

[0089] Here, x′ represents the new index value, indicating the position of each point in the new dataset. The interpolator interpld maps the original data y to the new index x′.

[0090] y′=interpld(x,y,kind=′linear′)(x′)

[0091] Where y′ is the normalized waveform data after interpolation, and x is the index of the original data.

[0092] As another possible implementation, the handling equipment detection device can acquire multiple sets of initial log information of the handling equipment, and use the initial log information extraction algorithm to process the data to obtain processed initial log information. Furthermore, the multiple sets of processed initial log information are interpolated to obtain multiple sets of log information.

[0093] In one example, Figure 5 This diagram illustrates torque data before interpolation. Figure 6 A schematic diagram of velocity data before interpolation is shown. For example... Figure 5 and Figure 6 As shown, the torque data and speed data before interpolation have different data lengths.

[0094] In one example, Figure 7 A schematic diagram of the torque data after interpolation is shown. Figure 8 A schematic diagram of velocity data after interpolation is shown. For example... Figure 7 and Figure 8 As shown, the torque and speed data after interpolation have the same data length.

[0095] In some embodiments, the process of using an initial log information extraction algorithm to process data and obtain processed initial log information may include the following S1-S3:

[0096] S1. The handling equipment detection device performs median filtering on the collected initial log information to eliminate noise and smooth the signal.

[0097] For example, a handling equipment detection device can use the following formula (Formula 2) to perform median filtering on the collected initial log information to eliminate noise and smooth the signal. Formula 2 can be:

[0098] vel smo [i] = median(vel) data [ik],…,vel data Formula 2 for [i+k]

[0099] Among them, vel smo [i] represents the i-th group of initial log information after processing, where i is any positive integer. data This represents the initial log information. `k` represents the window size. For example, it can be set to 25. `median` represents the median filter function.

[0100] S2. The handling equipment detection device identifies active units by detecting changes in speed signals, defines a flag variable cal_label to identify the start and end positions of the activity, and iterates through the smoothed signals to determine the boundaries of the active units based on the increasing or decreasing trend of the signals within the window according to specific conditions.

[0101] S3. After the start and end indices of the active unit are identified, the handling equipment detection device extracts the speed and torque data of the unit from the initial log information.

[0102] The above steps can effectively remove noise and abnormal data, providing a reliable data foundation for subsequent feature extraction and fault prediction.

[0103] In practical applications, multiple sets of log information for handling equipment can be multiple sets of log information for each axis component of the handling equipment.

[0104] Each axis component is equipped with a different servo motor.

[0105] The various axis components of the handling equipment may include the upper arm axis (RR axis), the lower arm axis (RL axis), the rotation axis (TH axis), the travel axis (X axis), and the lifting axis (Z axis).

[0106] In this way, by comprehensively analyzing the speed and torque data of multiple axes, the deviation caused by a single data source is effectively reduced, providing more comprehensive information for assessing the overall health status of the handling equipment.

[0107] S302. Cluster multiple sets of log information based on speed data to obtain multiple sets of clustered log information.

[0108] As one possible implementation, the handling equipment detection device can use a preset clustering algorithm to cluster speed data to obtain clustered speed data, and then cluster multiple sets of log information corresponding to the clustered speed data to obtain multiple sets of clustered log information.

[0109] As another possible implementation, the handling equipment detection device can generate corresponding speed waveforms based on speed data. Furthermore, a preset clustering algorithm is used to cluster the speed waveforms. Then, the multiple sets of log information corresponding to the clustered speed waveforms are clustered again to obtain multiple sets of clustered log information.

[0110] The preset clustering algorithm can be set as needed. For example, it can be the K-means clustering algorithm.

[0111] In one example, when the various axis components of the conveying equipment include the RR axis, RL axis, TH axis, X axis, and Z axis, the conveying equipment detection device can classify the speed data into different categories based on the characteristics and similarity of the speed waveform. For example, the RR axis can be classified into category 1, the RL axis into category 1, the TH axis into category 2, the X axis into category 2, and the Z axis into category 2.

[0112] In one example, a clustering diagram illustrating the use of a pre-defined clustering algorithm to cluster velocity waveforms can be shown as follows: Figure 9 As shown. For example, Figure 9 The horizontal axis can represent the maximum velocity value in each velocity waveform, and the vertical axis can represent the cluster type in each velocity waveform.

[0113] This reduces reliance on fault data, and refined data processing is performed on speed and torque data, enabling multi-axis data to better adapt to model input without losing key information, thereby improving data quality and consistency, and making anomaly prediction more accurate and stable.

[0114] S303. Based on the torque data in multiple sets of log information after clustering, determine whether the handling equipment is an abnormal handling equipment.

[0115] As one possible implementation, the handling equipment detection device can determine the vibration amplitude of each clustered torque data set, and if the vibration amplitude of any torque data set exceeds a vibration amplitude threshold, the handling equipment is identified as abnormal. If the vibration amplitude of any torque data set is less than or equal to the vibration amplitude threshold, the handling equipment is identified as normal.

[0116] As another possible implementation, the handling equipment detection device can correct the torque data in multiple sets of clustered log information to obtain target torque data; compare the target torque data with the torque data to generate a reconstruction loss for each torque data; and determine whether the handling equipment is abnormal based on the dispersion of the reconstruction loss of different torque data after clustering.

[0117] It should be noted that the specific details of this step can be found in the following sections, and will not be repeated here.

[0118] In some embodiments, the handling equipment detection device can establish a mapping relationship between the speed data and torque data in each group of log information after acquiring the speed data and torque data in each group of log information, and index the torque data corresponding to each type of speed data based on the mapping relationship and the clustered speed data.

[0119] In practical applications, the material handling equipment detection device can output the specific abnormal component of the material handling equipment based on the degree of dispersion of the reconstruction loss of torque data of different shafts.

[0120] For example, if the dispersion of the reconstructed torque data of the RL axis is abnormal, the display panel of the handling equipment detection device may display "RL axis abnormality of the handling equipment".

[0121] Based on the technical solution provided in this application, multiple sets of log information are clustered according to speed data to obtain clustered sets of log information. Based on the torque data in these clustered sets of log information, it is determined whether the handling equipment is abnormal. This eliminates the need for manual annotation; different operating states of the equipment can be identified through clustering, and the accuracy of determining whether the handling equipment is abnormal can be significantly improved by using torque data from similar operating states to identify abnormalities in the handling equipment.

[0122] One possible implementation, Figure 10 This is a flowchart illustrating another method for detecting handling equipment provided in an embodiment of this application, as shown below. Figure 10 As shown, in order to determine whether the handling equipment is abnormal handling equipment, S303 in this application may also include the following S401-S403.

[0123] S401. Correct the torque data in the clustered log information to obtain the target torque data.

[0124] As one possible implementation, the handling equipment detection device can use any correction model to correct the torque data in multiple sets of clustered log information to obtain the target torque data.

[0125] As another possible implementation, the handling equipment detection device can use multiple correction models to correct the torque data in multiple sets of clustered log information, obtain multiple corrected torque data, and perform weighted summation on the multiple corrected torque data to obtain the target torque data.

[0126] The modified model can be configured as needed. For example, it can include CAE models, DenseNet models, and DropoutAE models.

[0127] In one example, the handling equipment detection device can input torque data from multiple clustered log information sets into a CAE model, and the CAE model outputs corrected first torque data; the handling equipment detection device can input torque data from multiple clustered log information sets into a DenseNet model, and the DenseNet model outputs corrected second torque data; the handling equipment detection device can input torque data from multiple clustered log information sets into a DropoutAE model, and the DropoutAE model outputs corrected third torque data. Furthermore, the handling equipment detection device can substitute the first torque data, the second torque data, and the third torque data into a weighted summation formula to obtain the target torque data.

[0128] For example, the weighted summation formula can be expressed as Formula 3 below:

[0129] Ofusion =α·O CaE +β·O DenseNet +γ·O Dropout Formula 3

[0130] Among them, O fusion This represents the target torque data. α, β, and γ represent the weighted weights of the CAE model, DenseNet model, and DropoutAE model, respectively, with α + β + γ = 1. CAE This indicates the first torque data. DenseNet This indicates the second torque data. (O) Dropout This indicates the third torque data.

[0131] In one example, the corrected first torque data output by the CAE model can be as follows: Figure 11 As shown. The corrected second torque data output by the DenseNet model can be seen as follows. Figure 12 As shown. The corrected third torque data output by the DropoutAE model can be seen as follows. Figure 13 As shown.

[0132] In one example, the target torque data is obtained by weighted summation of multiple corrected torque data points, as shown below. Figure 14 As shown.

[0133] As another possible implementation, the handling equipment detection device can normalize the torque data in multiple clustered log information to obtain normalized torque data, and then use multiple correction models to correct the normalized torque data to obtain multiple corrected torque data. Finally, the multiple corrected torque data are weighted and summed to obtain the target torque data.

[0134] In one example, the torque data in multiple sets of log information is trq = [trq1, trq2, ..., trq] N In the case of […], the normalized torque data can be...

[0135] Among them, trq norm(i) This represents the i-th normalized torque data. trq(i) represents the i-th torque data. min This represents the minimum torque value among multiple sets of log data. trq max This indicates the largest torque data among multiple sets of log information.

[0136] S402. Compare the target torque data with the torque data to generate a reconstruction loss for each torque data point.

[0137] As one possible implementation, the handling equipment detection device can substitute the target torque data and torque data into the reconstruction loss function to obtain the reconstruction loss for each torque data.

[0138] In one example, the reconstruction loss function can be the following formula:

[0139]

[0140] Where Loss represents the reconstruction loss (also known as reconstruction error) of the torque data. n represents the total number of torque data samples.

[0141] Understandably, fusing three different types of models not only improves the accuracy of anomaly detection but also ensures the efficiency of model training.

[0142] S403. Based on the degree of dispersion of the reconstruction loss of different torque data after clustering, determine whether the handling equipment is an abnormal handling equipment.

[0143] As one possible implementation, the handling equipment detection device can determine that the handling equipment is abnormal if the dispersion of the reconstruction loss of different torque data after clustering is greater than or equal to a preset dispersion; and determine that the handling equipment is non-abnormal if the dispersion of the reconstruction loss of different torque data after clustering is less than the preset dispersion.

[0144] It should be noted that, for each reconstruction loss, if the reconstruction loss is greater than or equal to the reconstruction loss threshold, the degree of dispersion of the reconstruction loss of different torque data after clustering is determined to be greater than or equal to the preset degree of dispersion.

[0145] The reconstruction loss threshold can be set as needed. For example, the reconstruction loss threshold satisfies the following formula five:

[0146] Threshold = μ + kσ (Formula 5)

[0147] Where Threshold represents the reconstruction loss threshold; μ represents the mean of multiple reconstruction losses. k represents a preset scaling factor, such as 2 or 3. σ represents the standard deviation of multiple reconstruction losses.

[0148]

[0149] In one example, Figure 15 A schematic diagram of reconstruction loss is shown, such as Figure 15 As shown, the horizontal axis of the reconstruction loss diagram can be time, and the vertical axis can be the specific value of the reconstruction loss.

[0150] In some embodiments, to determine the severity of equipment malfunctions in the handling equipment, the handling equipment detection device can be configured with multiple reconstruction loss thresholds.

[0151] Among them, multiple reconstruction loss thresholds may include a first reconstruction loss threshold and a second reconstruction loss threshold.

[0152] The handling equipment detection device can determine a minor anomaly when the reconstruction loss of any torque data exceeds a first reconstruction loss threshold, and a severe anomaly when the reconstruction loss of any torque data exceeds a second reconstruction loss threshold.

[0153] In one example, the first reconstruction loss threshold can satisfy some of the following formulas:

[0154] Threshold1=μ+2σ Formula Six

[0155] In one example, the second reconstruction loss threshold can satisfy some of the following Formula 7:

[0156] Threshold2=μ+3σ Formula 7

[0157] This application embodiment can divide the handling equipment detection device into functional modules or functional units according to the above method example. For example, each function can be divided into a separate functional module or functional unit, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or in software functional modules or functional units. The module or unit division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0158] When dividing each function into modules according to its corresponding function. Figure 16 A schematic diagram of a handling equipment detection device 800 is shown. This handling equipment detection device can be a handling equipment detection device itself, or it can be a chip, processor, etc., applied in a handling equipment detection device. The handling equipment detection device 800 can be used to perform the functions of the handling equipment detection devices involved in the above embodiments. Figure 16 The handling equipment detection device 800 shown may include: an acquisition unit 801 and a processing unit 802; the acquisition unit 801 is used to acquire multiple sets of log information of the handling equipment; the log information includes speed data and torque data; the processing unit 802 is used to cluster the multiple sets of log information according to the speed data to obtain multiple sets of clustered log information; the processing unit 802 is also used to determine whether the handling equipment is abnormal handling equipment based on the torque data in the clustered multiple sets of log information.

[0159] Optionally, the processing unit 802 is specifically used to: correct the torque data in multiple sets of clustered log information to obtain target torque data; compare the target torque data with the torque data to generate a reconstruction loss for each torque data; and determine whether the handling equipment is an abnormal handling equipment based on the degree of dispersion of the reconstruction loss of different torque data after clustering.

[0160] Optionally, the processing unit 802 is further configured to: determine the handling equipment as abnormal handling equipment when the degree of dispersion of the reconstruction loss of different torque data after clustering is greater than or equal to a preset degree of dispersion; and determine the handling equipment as non-abnormal handling equipment when the degree of dispersion of the reconstruction loss of different torque data after clustering is less than a preset degree of dispersion.

[0161] Optionally, the processing unit 802 is further configured to: for each reconstruction loss, if the reconstruction loss is greater than or equal to the reconstruction loss threshold, determine that the degree of dispersion of the reconstruction loss of different torque data after clustering is greater than or equal to a preset degree of dispersion.

[0162] Optionally, the reconstruction loss threshold satisfies the following relationship: Threshold1=μ+kσ; where Threshold1 represents the reconstruction loss threshold; μ represents the mean of multiple reconstruction losses; k represents the preset scaling factor; and σ represents the standard deviation of multiple reconstruction losses.

[0163] Optionally, the processing unit 802 is further configured to: correct the torque data in multiple sets of clustered log information based on multiple correction models to obtain multiple corrected torque data; and perform weighted summation on the multiple corrected torque data to obtain the target torque data.

[0164] Optionally, the acquisition unit 801 is specifically used for: acquiring multiple sets of initial log information from the handling equipment; performing interpolation processing on the multiple sets of initial log information to obtain multiple sets of log information; and ensuring that the data lengths of the multiple sets of log information are the same.

[0165] Optionally, the acquisition unit 801 is further used to: acquire multiple sets of log information for each axis component of the handling equipment; and configure different servo motors for each axis component.

[0166] This application also provides a computer-readable storage medium. All or part of the processes in the above method embodiments can be implemented by a computer program instructing related hardware. This program can be stored in the computer-readable storage medium, and when executed, it can include the processes of the above method embodiments. The computer-readable storage medium can be an internal storage unit of the handling equipment detection device (including a data transmitter and / or a data receiver) of any of the foregoing embodiments, such as the hard disk or memory of the handling equipment detection device. The computer-readable storage medium can also be an external storage device of the terminal device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the terminal device. Further, the computer-readable storage medium can include both the internal storage unit of the handling equipment detection device and an external storage device. The computer-readable storage medium is used to store the computer program and other programs and data required by the handling equipment detection device. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0167] It should be noted that the terms "first" and "second," etc., in the specification, claims, and drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0168] It should be understood that in this application, "at least one (item)" means one or more, "more than one" means two or more, "at least two (items)" means two or three or more, and "and / or" is used to describe the relationship between related objects, indicating that there can be three relationships. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the related objects before and after are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0169] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0170] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another apparatus, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0171] The units described as separate components may or may not be physically separate. A component shown as a unit can be one or more physical units; that is, it can be located in one place or distributed in multiple different locations. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0172] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0173] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, essentially, or the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0174] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for detecting handling equipment, characterized in that, The method includes: Acquire multiple sets of log information from the handling equipment; the log information includes speed data and torque data. Based on the speed data, the multiple sets of log information are clustered to obtain multiple sets of clustered log information. Based on the torque data in the multiple sets of log information after clustering, it is determined whether the handling equipment is an abnormal handling equipment.

2. The method according to claim 1, characterized in that, The step of determining whether the handling equipment is an abnormal handling equipment based on the torque data in the multiple sets of log information after clustering includes: The torque data in the clustered log information is corrected to obtain the target torque data; The target torque data is compared with the torque data to generate a reconstruction loss for each torque data. Based on the degree of dispersion of the reconstruction loss of different torque data after clustering, it is determined whether the handling equipment is an abnormal handling equipment.

3. The method according to claim 2, characterized in that, The determination of whether the handling equipment is an abnormal handling equipment is based on the degree of dispersion of the reconstruction loss of different torque data after clustering, including: If the degree of dispersion of the reconstruction loss of the different torque data after clustering is greater than or equal to the preset degree of dispersion, the handling equipment is determined to be the abnormal handling equipment. If the degree of dispersion of the reconstruction loss of different torque data after clustering is less than the preset degree of dispersion, the handling equipment is determined to be a non-abnormal handling equipment.

4. The method according to claim 3, characterized in that, The method further includes: For each reconstruction loss, if the reconstruction loss is greater than or equal to the reconstruction loss threshold, the degree of dispersion of the reconstruction loss of the different torque data after clustering is determined to be greater than or equal to the preset degree of dispersion.

5. The method according to claim 4, characterized in that, The reconstruction loss threshold satisfies the following relationship: Threshold1=μ+kσ; Where Threshold1 represents the reconstruction loss threshold; μ represents the mean of the multiple reconstruction losses; k represents the preset scaling factor; and σ represents the standard deviation of the multiple reconstruction losses.

6. The method according to claim 2, characterized in that, The step of correcting the torque data in the clustered log information to obtain the target torque data includes: Based on multiple correction models, the torque data in the clustered log information is corrected to obtain multiple corrected torque data. The target torque data is obtained by performing a weighted summation on the multiple corrected torque data.

7. The method according to any one of claims 1-6, characterized in that, The acquisition of multiple sets of log information from the handling equipment includes: Obtain multiple sets of initial log information from the transport equipment; Multiple sets of initial log information are interpolated to obtain the multiple sets of log information; the data lengths of the multiple sets of log information are the same.

8. The method according to any one of claims 1-6, characterized in that, The acquisition of multiple sets of log information from the handling equipment includes: Obtain multiple sets of log information for each axis component of the conveying equipment; each axis component is configured with a different servo motor.

9. A detection device for handling equipment, characterized in that, The device includes: an acquisition unit and a processing unit; The acquisition unit is used to acquire multiple sets of log information from the handling equipment; the log information includes speed data and torque data. The processing unit is used to cluster the multiple sets of log information based on the speed data to obtain multiple sets of clustered log information. The processing unit is also used to determine whether the handling equipment is an abnormal handling equipment based on the torque data in the multiple sets of log information after clustering.

10. A computer-readable storage medium, characterized in that, The readable storage medium stores instructions that, when executed, implement the method as described in any one of claims 1-8.

11. An electronic device, characterized in that, include: The electronic device includes a processor, memory, and a communication interface; wherein the communication interface is used for communication between the electronic device and other devices or networks. The memory is used to store one or more programs, the one or more programs including computer-executable instructions, which, when the electronic device is running, are executed by the processor to execute the computer-executable instructions stored in the memory to cause the electronic device to perform the method of any one of claims 1-8.

Images