Control system and method for programming robot

By extracting real-time energy consumption and reference energy consumption data of programming robots, and using deep learning algorithms to identify energy consumption abnormal patterns, the problem of lack of in-depth analysis of energy consumption management in the existing technology is solved, and timely identification and early warning of energy consumption abnormalities is achieved. Improve management efficiency and stability.

CN118578413BActive Publication Date: 2024-11-19HANGZHOU XUEQUYIXUE EDUCATION TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410827712.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-06-25
Publication Date
2024-11-19
Estimated Expiration
2044-06-25

AI Technical Summary

Technical Problem

The existing energy consumption management of programming robots mainly stays at the monitoring level, lacking in-depth analysis and abnormal identification capabilities, which makes energy consumption abnormalities difficult to detect and deal with in a timely manner, affecting efficiency and cost.

Method used

By obtaining real-time energy consumption data and reference energy consumption data, using the energy consumption mode capture network and the energy consumption state matching network for processing, extracting the timing mode feature vector, identifying energy consumption state abnormalities and generating early warning prompts.

Benefits of technology

It realizes identification and early warning of abnormal energy consumption patterns of programming robots, improves the depth and accuracy of energy consumption management, and reduces the risks of equipment damage and cost increase.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118578413B_ABST
    Figure CN118578413B_ABST
Patent Text Reader

Abstract

The present disclosure relates to a control system and method for a programming robot. The method includes: obtaining real-time energy consumption data of the programming robot when running a first motion trajectory; extracting a set of reference energy consumption data simulating the first motion trajectory from a background database; using an energy consumption pattern capture network to process the set of reference energy consumption data and the real-time energy consumption data to obtain a set of reference energy consumption timing pattern feature vectors and a real-time energy consumption timing pattern feature vector; using an energy consumption state matching network to process the set of real-time energy consumption timing pattern feature vectors and the reference energy consumption timing pattern feature vector to determine whether the energy consumption state of the programming robot is abnormal; and, in response to the energy consumption state of the programming robot being abnormal, generating an early warning prompt. In this way, the recognition and early warning of abnormal energy consumption patterns of the programming robot can be realized in combination with a deep learning algorithm.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the technical field of programming robots, and in particular, to a control system and method for programming robots. Background Art

[0002] With the development of automation and intelligent technology, programmable robots have been widely used in many fields such as industrial production, logistics and transportation, and service industries. These robots complete specific tasks by executing preset programs, and their efficiency and stability have a direct impact on the quality of production and services. However, the energy consumption management of robots in the process of performing tasks is a key issue, which is not only related to the rational use of energy, but also directly affects the operating cost and maintenance cycle of robots.

[0003] At present, the energy consumption management of most programmed robots is still at the basic monitoring level, lacking the ability to deeply analyze energy consumption data and identify anomalies. As a result, during the operation of the robot, some energy consumption anomalies caused by program errors, mechanical failures or changes in the external environment are difficult to be discovered and handled in a timely manner, which may lead to problems such as reduced efficiency, increased costs and even equipment damage. Therefore, a solution is expected. Summary of the invention

[0004] This summary is provided to introduce concepts in a brief form that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0005] In a first aspect, the present disclosure provides a control method for a programming robot, the method comprising:

[0006] Obtaining real-time energy consumption data of the programmed robot when running the first motion trajectory;

[0007] Extracting a set of reference energy consumption data under the simulated first motion trajectory from a background database;

[0008] Using an energy consumption pattern capture network to process the set of reference energy consumption data and the real-time energy consumption data to obtain a set of reference energy consumption time series pattern feature vectors and a real-time energy consumption time series pattern feature vector;

[0009] Using an energy consumption state matching network to process the set of the real-time energy consumption time series pattern feature vector and the reference energy consumption time series pattern feature vector to determine whether the energy consumption state of the programmed robot is abnormal; and

[0010] In response to an abnormality in the energy consumption state of the programmed robot, an early warning prompt is generated.

[0011] Optionally, an energy consumption pattern capture network is used to process the set of reference energy consumption data and the real-time energy consumption data to obtain a set of reference energy consumption timing pattern feature vectors and a real-time energy consumption timing pattern feature vector, including: passing each reference energy consumption data in the set of reference energy consumption data through an energy consumption timing pattern feature extractor based on a one-dimensional extended convolution layer to obtain the set of reference energy consumption timing pattern feature vectors; and passing the real-time energy consumption data through the energy consumption timing pattern feature extractor based on a one-dimensional extended convolution layer to obtain the real-time energy consumption timing pattern feature vector.

[0012] Optionally, each reference energy consumption data in the set of reference energy consumption data is passed through an energy consumption timing pattern feature extractor based on a one-dimensional extended convolutional layer to obtain a set of reference energy consumption timing pattern feature vectors, including: arranging each reference energy consumption data in the set of reference energy consumption data into reference energy consumption timing input vectors according to the time dimension to obtain a set of reference energy consumption timing input vectors; and, each reference energy consumption timing input vector in the set of reference energy consumption timing input vectors is passed through the energy consumption timing pattern feature extractor based on a one-dimensional extended convolutional layer to obtain a set of reference energy consumption timing pattern feature vectors.

[0013] Optionally, each reference energy consumption timing input vector in the set of reference energy consumption timing input vectors is respectively passed through the energy consumption timing pattern feature extractor based on the one-dimensional extended convolution layer to obtain the set of reference energy consumption timing pattern feature vectors, including: processing the reference energy consumption timing input vectors with the following one-dimensional extended convolution formula to obtain the reference energy consumption timing pattern feature vectors; wherein the one-dimensional extended convolution formula is:

[0014]

[0015]

[0016]

[0017] Among them, the one-dimensional expanded convolution kernel The size is 1× , is the length of the original convolution kernel, is the expansion rate, Indicates that the reference energy consumption timing input vector The length of the first feature value at the position is time window, is a bias term, and , is a nonlinear activation function, It is local convolutional coding feature vector, is the dimension of the reference energy consumption time series input vector, is the reference energy consumption timing pattern feature vector, Indicates cascade.

[0018] Optionally, an energy consumption state matching network is used to process the real-time energy consumption timing pattern feature vector and the set of reference energy consumption timing pattern feature vectors to determine whether there is an abnormality in the energy consumption state of the programming robot, including: optimizing each reference energy consumption timing pattern feature vector in the set of the real-time energy consumption timing pattern feature vector and the reference energy consumption timing pattern feature vector to obtain a set of real-time energy consumption timing pattern feature vector and reference energy consumption timing pattern feature vector; calculating the global matching coefficient of each reference energy consumption timing pattern feature vector in the set of the real-time energy consumption timing pattern feature vector and the reference energy consumption timing pattern feature vector to obtain a set of global matching coefficients; calculating the global mean of the set of global matching coefficients as a second-order matching coefficient; and, based on a comparison between the second-order matching coefficient and a predetermined threshold, determining whether there is an abnormality in the energy consumption state of the programming robot.

[0019] Optionally, calculating the global matching coefficient of each reference energy consumption timing pattern feature vector in the set of the real-time energy consumption timing pattern feature vector and the reference energy consumption timing pattern feature vector to obtain a set of global matching coefficients includes: processing the set of the real-time energy consumption timing pattern feature vector and the reference energy consumption timing pattern feature vector using the following global matching formula to obtain the set of global matching coefficients; wherein the global matching formula is:

[0020]

[0021] in, Indicates The global matching coefficient, For the The reference energy consumption timing pattern feature vector, is the real-time energy consumption timing pattern feature vector, Indicates transpose.

[0022] In a second aspect, the present disclosure provides a control system for a programming robot, the system comprising:

[0023] A real-time energy consumption data acquisition module, used to acquire real-time energy consumption data of the programmed robot when running the first motion trajectory;

[0024] A reference energy consumption data acquisition module, used to extract a set of reference energy consumption data under the simulated first motion trajectory from a background database;

[0025] A data processing module, used to process the set of reference energy consumption data and the real-time energy consumption data using an energy consumption pattern capture network to obtain a set of reference energy consumption time series pattern feature vectors and a real-time energy consumption time series pattern feature vector;

[0026] a vector processing module, configured to process the set of the real-time energy consumption timing pattern feature vector and the reference energy consumption timing pattern feature vector using an energy consumption state matching network to determine whether the energy consumption state of the programmed robot is abnormal; and

[0027] The early warning prompt generating module is used to generate an early warning prompt in response to an abnormality in the energy consumption state of the programmed robot.

[0028] Optionally, the data processing module includes: a reference energy consumption timing pattern feature extraction unit, which is used to pass each reference energy consumption data in the set of reference energy consumption data through an energy consumption timing pattern feature extractor based on a one-dimensional extended convolution layer to obtain a set of reference energy consumption timing pattern feature vectors; and a real-time energy consumption timing pattern feature extraction unit, which is used to pass the real-time energy consumption data through the energy consumption timing pattern feature extractor based on the one-dimensional extended convolution layer to obtain the real-time energy consumption timing pattern feature vector.

[0029] The above technical solution is adopted to obtain the real-time energy consumption data of the programming robot when running the first motion trajectory; extract the set of reference energy consumption data under the simulated first motion trajectory from the background database; use the energy consumption pattern capture network to process the set of reference energy consumption data and the real-time energy consumption data to obtain the set of reference energy consumption timing pattern feature vectors and the real-time energy consumption timing pattern feature vector; use the energy consumption state matching network to process the set of real-time energy consumption timing pattern feature vectors and the reference energy consumption timing pattern feature vector to determine whether the energy consumption state of the programming robot is abnormal; and, in response to the abnormality of the energy consumption state of the programming robot, generate an early warning prompt. In this way, the recognition and early warning of the abnormal energy consumption pattern of the programming robot can be realized in combination with the deep learning algorithm.

[0030] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale. In the drawings:

[0032] Figure 1The figure is a flow chart of a control method for a programming robot according to an exemplary embodiment.

[0033] Figure 2 It is a block diagram of a control system for a programming robot according to an exemplary embodiment.

[0034] Figure 3 It is a block diagram of an electronic device according to an exemplary embodiment.

[0035] Figure 4 It is an application scenario diagram of a control method for a programming robot according to an exemplary embodiment. DETAILED DESCRIPTION

[0036] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0037] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0038] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0039] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0040] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0041] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0042] In order to solve the above problems, the present disclosure provides a control system and method for a programming robot, which obtains the real-time energy consumption data of the programming robot when running a first motion trajectory; extracts a set of reference energy consumption data under the simulated first motion trajectory from a background database; uses an energy consumption pattern capture network to process the set of reference energy consumption data and the real-time energy consumption data to obtain a set of reference energy consumption timing pattern feature vectors and a real-time energy consumption timing pattern feature vector; uses an energy consumption state matching network to process the real-time energy consumption timing pattern feature vector and the set of reference energy consumption timing pattern feature vector to determine whether the energy consumption state of the programming robot is abnormal; and, in response to the abnormality of the energy consumption state of the programming robot, generates an early warning prompt. In this way, the recognition and early warning of abnormal energy consumption patterns of the programming robot can be realized in combination with a deep learning algorithm.

[0043] The specific embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0044] Figure 1 is a flow chart of a control method for a programming robot according to an exemplary embodiment. Figure 1 As shown, the method includes:

[0045] Step 101, obtaining real-time energy consumption data of the programmed robot when running a first motion trajectory;

[0046] Step 102: extracting a set of reference energy consumption data under the simulated first motion trajectory from a background database;

[0047] Step 103: using an energy consumption pattern capture network to process the set of reference energy consumption data and the real-time energy consumption data to obtain a set of reference energy consumption time series pattern feature vectors and a real-time energy consumption time series pattern feature vector;

[0048] Step 104: using an energy consumption state matching network to process the set of the real-time energy consumption time series pattern feature vector and the reference energy consumption time series pattern feature vector to determine whether the energy consumption state of the programmed robot is abnormal; and

[0049] Step 105: In response to an abnormality in the energy consumption state of the programmed robot, generate an early warning prompt.

[0050] In response to the above technical problems, the technical concept of this application is to transform the problem of abnormal energy consumption status identification into the problem of matching and differential quantification between real-time energy consumption data and reference data. Specifically, the real-time energy consumption time series pattern characteristics of the programmed robot and the reference energy consumption time series pattern characteristics in the background database (simulation data) are mined in combination with a deep learning algorithm, and the two are compared and matched in a high-dimensional feature space, so as to quantify the degree of difference between the real-time energy consumption time series pattern characteristics and the reference energy consumption time series pattern characteristics, and based on this, the abnormal energy consumption pattern of the programmed robot can be identified and warned.

[0051] Based on this, in the technical solution of the present application, first, the real-time energy consumption data of the programmed robot when running the first motion trajectory is obtained; and a set of reference energy consumption data under the simulated first motion trajectory is extracted from the background database. Among them, the first motion trajectory can be regarded as the initial motion path of the programmed robot when performing a specific task. By recording the energy consumption data under this path, it can be used as an important data source for energy consumption analysis to determine whether the energy consumption under this path is normal. Specifically, the definition of the first motion trajectory can be determined according to specific scenarios and task requirements. In industrial production, the first motion trajectory can refer to the initial movement path of the programmed robot when completing a certain production task, such as the path from the starting point to the first workstation on the assembly line; in logistics transportation, the first motion trajectory can be the movement path of the programmed robot from the cargo storage area to the loading area in the warehouse for the first time. The purpose of extracting the set of reference energy consumption data under the simulated first motion trajectory from the background database is to capture the expected energy consumption operation mode as benchmark information for comparison and analysis with the actual real-time energy consumption data.

[0052] Then, each reference energy consumption data in the set of reference energy consumption data is respectively passed through an energy consumption time series pattern feature extractor based on a one-dimensional extended convolution layer to obtain a set of reference energy consumption time series pattern feature vectors. Among them, one-dimensional extended convolution is a convolution operation in a convolutional neural network, which is usually used to process one-dimensional data. In a one-dimensional convolution, the convolution kernel slides along one direction of the input data (usually the time axis or sequence axis) to extract implicit correlation features in the one-dimensional data. One-dimensional extended convolution is an extension of the traditional one-dimensional convolution, which defines an expansion rate to adjust the receptive field of the one-dimensional convolution, and can better capture the dependencies and complex patterns in the one-dimensional data. In this way, the energy consumption time series pattern feature extractor is constructed through a one-dimensional extended convolution layer to capture the local time series implicit patterns of each reference energy consumption time series input vector arranged by the reference energy consumption data, including the periodicity and trend characteristics of energy consumption changes. At the same time, the real-time energy consumption data is passed through the energy consumption time series pattern feature extractor based on the one-dimensional extended convolution layer to obtain a real-time energy consumption time series pattern feature vector. That is, a one-dimensional expanded convolution layer is also used to capture the local time series implicit pattern of the energy consumption change state of the real-time energy consumption time series input vector formed by arranging the real-time energy consumption data.

[0053] In one embodiment of the present disclosure, an energy consumption pattern capture network is used to process the set of reference energy consumption data and the real-time energy consumption data to obtain a set of reference energy consumption timing pattern feature vectors and a real-time energy consumption timing pattern feature vector, including: passing each reference energy consumption data in the set of reference energy consumption data through an energy consumption timing pattern feature extractor based on a one-dimensional extended convolution layer to obtain the set of reference energy consumption timing pattern feature vectors; and passing the real-time energy consumption data through the energy consumption timing pattern feature extractor based on a one-dimensional extended convolution layer to obtain the real-time energy consumption timing pattern feature vector.

[0054] Furthermore, each reference energy consumption data in the set of reference energy consumption data is passed through an energy consumption timing pattern feature extractor based on a one-dimensional extended convolutional layer to obtain a set of reference energy consumption timing pattern feature vectors, including: arranging each reference energy consumption data in the set of reference energy consumption data into reference energy consumption timing input vectors according to the time dimension to obtain a set of reference energy consumption timing input vectors; and, each reference energy consumption timing input vector in the set of reference energy consumption timing input vectors is passed through the energy consumption timing pattern feature extractor based on a one-dimensional extended convolutional layer to obtain a set of reference energy consumption timing pattern feature vectors.

[0055] Furthermore, each reference energy consumption timing input vector in the set of reference energy consumption timing input vectors is respectively passed through the energy consumption timing pattern feature extractor based on the one-dimensional extended convolution layer to obtain the set of reference energy consumption timing pattern feature vectors, including: processing the reference energy consumption timing input vectors with the following one-dimensional extended convolution formula to obtain the reference energy consumption timing pattern feature vectors; wherein the one-dimensional extended convolution formula is:

[0056]

[0057]

[0058]

[0059] Among them, the one-dimensional expanded convolution kernel The size is 1× , is the length of the original convolution kernel, is the expansion rate, Indicates that the reference energy consumption timing input vector The length of the first feature value at the position is time window, is a bias term, and , is a nonlinear activation function, It is local convolutional coding feature vector, is the dimension of the reference energy consumption time series input vector, is the reference energy consumption timing pattern feature vector, Indicates cascade.

[0060] Next, the global matching coefficients of the real-time energy consumption timing pattern feature vectors and the reference energy consumption timing pattern feature vectors in the set are calculated to obtain a set of global matching coefficients. That is, the similarity and matching degree between the real-time energy consumption data and each reference energy consumption data are quantified by calculating the global matching coefficients between the real-time energy consumption timing pattern feature vectors and each reference energy consumption timing pattern feature vector, thereby measuring the difference between the real-time energy consumption timing pattern and the reference energy consumption timing pattern representing the expected energy consumption operating state.

[0061] In the application scenario of the present application, considering that the various reference energy consumption data may contain noise information, it may be biased if the set of global matching coefficients is directly used as the basis for abnormal identification. That is to say, if the set of global matching coefficients is used as the basis for whether the energy consumption state of the programming robot is abnormal, it may often be affected by specific data points, causing the abnormal assessment of the energy consumption state to deviate from the actual situation, thereby increasing the false alarm rate of the early warning prompt. Therefore, in the technical solution of the present application, the global mean of the set of global matching coefficients is first calculated as the second-order matching coefficient; further, based on the comparison between the second-order matching coefficient and the predetermined threshold, it is determined whether the energy consumption state of the programming robot is abnormal; and in response to the abnormality of the energy consumption state of the programming robot, an early warning prompt is generated. In this way, by calculating the global mean of the set of global matching coefficients as the second-order matching coefficient, the influence of contingency can be reduced, so that the abnormal identification of the energy consumption mode is not affected by local fluctuations or abnormal data points, and the stability and reliability of the early warning are increased.

[0062] In one embodiment of the present disclosure, an energy consumption state matching network is used to process the real-time energy consumption timing pattern feature vector and the set of reference energy consumption timing pattern feature vectors to determine whether there is an abnormality in the energy consumption state of the programming robot, including: optimizing each reference energy consumption timing pattern feature vector in the set of the real-time energy consumption timing pattern feature vector and the reference energy consumption timing pattern feature vector to obtain a set of real-time energy consumption timing pattern feature vectors and reference energy consumption timing pattern feature vectors; calculating the global matching coefficient of each reference energy consumption timing pattern feature vector in the set of the real-time energy consumption timing pattern feature vector and the reference energy consumption timing pattern feature vector to obtain a set of global matching coefficients; calculating the global mean of the set of global matching coefficients as a second-order matching coefficient; and, based on a comparison between the second-order matching coefficient and a predetermined threshold, determining whether there is an abnormality in the energy consumption state of the programming robot.

[0063] Further, calculating the global matching coefficient of each reference energy consumption timing pattern feature vector in the set of the real-time energy consumption timing pattern feature vector and the reference energy consumption timing pattern feature vector to obtain a set of global matching coefficients includes: processing the set of the real-time energy consumption timing pattern feature vector and the reference energy consumption timing pattern feature vector using the following global matching formula to obtain the set of global matching coefficients; wherein the global matching formula is:

[0064]

[0065] in, Indicates The global matching coefficient, For the The reference energy consumption timing pattern feature vector, is the real-time energy consumption timing pattern feature vector, Indicates transpose.

[0066] In particular, in the technical solution of the present application, the set of reference energy consumption timing pattern feature vectors and the real-time energy consumption timing pattern feature vectors represent the extended timing correlation characteristics of reference energy consumption data and real-time energy consumption data, respectively. Thus, the global matching coefficient between the real-time energy consumption timing pattern feature vector and each reference energy consumption timing pattern feature vector in the set of reference energy consumption timing pattern feature vectors has a complex timing feature association representation dimension based on the interaction between the local sample domain and the global sample domain. That is, there is a problem of insufficient timing feature expression aggregation between the real-time energy consumption timing pattern feature vector and each reference energy consumption timing pattern feature vector in the set of reference energy consumption timing pattern feature vectors, thereby affecting the calculation accuracy of the global matching coefficient between the real-time energy consumption timing pattern feature vector and each reference energy consumption timing pattern feature vector in the set of reference energy consumption timing pattern feature vectors.

[0067] In a preferred example, the global matching coefficients of each reference energy consumption timing pattern feature vector in the set of the real-time energy consumption timing pattern feature vector and the reference energy consumption timing pattern feature vector are calculated to obtain a set of global matching coefficients, specifically including: cascading the set of reference energy consumption timing pattern feature vectors into a reference energy consumption timing pattern joint semantic feature vector; matching the reference energy consumption timing pattern joint semantic feature vector with the length of the reference energy consumption timing pattern joint semantic feature vector and the square of the length of the reference energy consumption timing pattern joint semantic feature vector respectively. The root point multiplication is performed to obtain the reference energy consumption timing pattern joint semantic full-width vector and the reference energy consumption timing pattern joint semantic half-width vector; the reference energy consumption timing pattern joint semantic full-width vector is subtracted from the first norm of the reference energy consumption timing pattern joint semantic feature vector, and the square root of the absolute value of each position of the point subtraction result vector is calculated to obtain the reference energy consumption timing pattern joint semantic full-width semantic change vector; the reference energy consumption timing pattern joint semantic half-width vector is subtracted from the second norm of the reference energy consumption timing pattern joint semantic feature vector, and the square root of the absolute value of each position of the point subtraction result vector is calculated The square root of the absolute value of the position is used to obtain the reference energy consumption timing pattern combined with the semantic half-width semantic change vector; the logarithm of each eigenvalue with base 2 of the reference energy consumption timing pattern combined with the semantic full-width semantic change vector and the reference energy consumption timing pattern combined with the semantic half-width semantic change vector are calculated respectively to obtain the reference energy consumption timing pattern combined with the semantic full-width semantic change information vector and the reference energy consumption timing pattern combined with the semantic half-width semantic change information vector; the reference energy consumption timing pattern combined with the semantic full-width semantic change information vector and the reference energy consumption timing pattern combined with the semantic half-width semantic change information vector are calculated with the balance hyperparameter as the weight The weighted sum of the timing pattern joint semantic half-width semantic change information vectors is used to obtain an optimized reference energy consumption timing pattern joint semantic feature vector; the optimized reference energy consumption timing pattern joint semantic feature vector is split into a set of optimized reference energy consumption timing pattern feature vectors according to the cascade of the set of reference energy consumption timing pattern feature vectors; the global matching coefficients between each optimized reference energy consumption timing pattern feature vector in the set of optimized reference energy consumption timing pattern feature vectors and the real-time energy consumption timing pattern feature vector are calculated respectively to obtain a set of global matching coefficients.

[0068] Further, respectively calculating the global matching coefficients between each optimized reference energy consumption timing pattern feature vector in the set of the optimized reference energy consumption timing pattern feature vector and the real-time energy consumption timing pattern feature vector to obtain a set of global matching coefficients, including: processing the real-time energy consumption timing pattern feature vector and the set of the optimized reference energy consumption timing pattern feature vector using the following global matching formula to obtain the set of global matching coefficients; wherein the global matching formula is:

[0069]

[0070] in, Indicates The global matching coefficient, For the The optimized reference energy consumption timing pattern feature vector, is the real-time energy consumption timing pattern feature vector, Indicates transpose.

[0071] Based on this, the present application takes the set of reference energy consumption timing pattern feature vectors as a feature set, wherein the change semantics in units of the feature values ​​of the set of reference energy consumption timing pattern feature vectors are expressed. In order to dynamically aggregate the semantic set composed of different change semantics of the set of reference energy consumption timing pattern feature vectors without ignoring individual semantic change information, the individual features of the set of reference energy consumption timing pattern feature vectors and the collective expression of the aggregation scale of the set of reference energy consumption timing pattern feature vectors are used as feature full amplitude and half amplitude, and the low-rank negative correlation of different dimensions of the overall semantics of the feature set of the set of reference energy consumption timing pattern feature vectors is used as phase and scaled to dynamically adjust the change relationship of the semantic content of the set of reference energy consumption timing pattern feature vectors, thereby improving the overall semantic information expression aggregation of the feature set of the set of reference energy consumption timing pattern feature vectors, thereby improving the calculation accuracy of the global matching coefficient of the real-time energy consumption timing pattern feature vector and each reference energy consumption timing pattern feature vector in the set of reference energy consumption timing pattern feature vectors.

[0072] In summary, the above scheme is adopted to transform the problem of abnormal energy consumption status recognition into the problem of matching and differential quantification between real-time energy consumption data and reference data. Specifically, the real-time energy consumption time series pattern characteristics of the programming robot and the reference energy consumption time series pattern characteristics in the background database (simulation data) are mined in combination with the deep learning algorithm, and the two are compared and matched in the high-dimensional feature space, so as to quantify the degree of difference between the real-time energy consumption time series pattern characteristics and the reference energy consumption time series pattern characteristics, and based on this, the abnormal energy consumption pattern of the programming robot can be recognized and warned.

[0073] Figure 2 FIG. 1 is a block diagram of a control system for a programming robot according to an exemplary embodiment. Figure 2 As shown, the control system 200 includes:

[0074] A real-time energy consumption data acquisition module 201 is used to acquire real-time energy consumption data of the programmed robot when running the first motion trajectory;

[0075] A reference energy consumption data acquisition module 202 is used to extract a set of reference energy consumption data under a simulated first motion trajectory from a background database;

[0076] The data processing module 203 is used to process the set of reference energy consumption data and the real-time energy consumption data using the energy consumption pattern capture network to obtain a set of reference energy consumption time series pattern feature vectors and a real-time energy consumption time series pattern feature vector;

[0077] A vector processing module 204 is used to process the set of the real-time energy consumption timing pattern feature vector and the reference energy consumption timing pattern feature vector using an energy consumption state matching network to determine whether there is an abnormality in the energy consumption state of the programmed robot; and

[0078] The early warning prompt generating module 205 is used to generate an early warning prompt in response to an abnormality in the energy consumption state of the programmed robot.

[0079] In one embodiment of the present disclosure, the data processing module includes: a reference energy consumption timing pattern feature extraction unit, which is used to pass each reference energy consumption data in the set of reference energy consumption data through an energy consumption timing pattern feature extractor based on a one-dimensional extended convolution layer to obtain a set of reference energy consumption timing pattern feature vectors; and a real-time energy consumption timing pattern feature extraction unit, which is used to pass the real-time energy consumption data through the energy consumption timing pattern feature extractor based on the one-dimensional extended convolution layer to obtain the real-time energy consumption timing pattern feature vector.

[0080] Reference below Figure 3 , which shows a schematic diagram of the structure of an electronic device 600 suitable for implementing the embodiment of the present disclosure. The terminal device in the embodiment of the present disclosure may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0081] like Figure 3As shown, the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0082] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 600 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0083] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0084] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0085] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0086] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0087] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0088] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0089] The modules involved in the embodiments described in the present disclosure may be implemented by software or hardware. The name of a module does not limit the module itself in some cases. For example, a test parameter acquisition module may also be described as a "module for acquiring device test parameters corresponding to a target device".

[0090] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0091] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0092] Figure 4 FIG. 1 is an application scenario diagram of a control method for a programming robot according to an exemplary embodiment. Figure 4 As shown, in this application scenario, first, the real-time energy consumption data of the programmed robot when running the first motion trajectory is obtained (for example, Figure 4 ); extracting a set of reference energy consumption data under the simulated first motion trajectory from the background database (for example, Figure 4 Then, the acquired real-time energy consumption data and reference energy consumption data are input into a server (for example, Figure 4 In S) shown in , the server is capable of processing the real-time energy consumption data and the reference energy consumption data based on the control algorithm of the programming robot to determine whether there is an abnormality in the energy consumption status of the programming robot; and, in response to the presence of an abnormality in the energy consumption status of the programming robot, generating an early warning prompt.

[0093] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0094] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0095] Although the subject matter has been described in language specific to structural features and / or method logic actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims. Regarding the device in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

Claims

1. A control method for a programming robot, characterized in that: include: Obtaining real-time energy consumption data of the programmed robot when running the first motion trajectory; Extracting a set of reference energy consumption data under the simulated first motion trajectory from a background database; Using an energy consumption pattern capture network to process the set of reference energy consumption data and the real-time energy consumption data to obtain a set of reference energy consumption time series pattern feature vectors and a real-time energy consumption time series pattern feature vector; Using an energy consumption state matching network to process the set of the real-time energy consumption time series pattern feature vector and the reference energy consumption time series pattern feature vector to determine whether the energy consumption state of the programmed robot is abnormal; as well as In response to an abnormality in the energy consumption state of the programmed robot, generating an early warning prompt; The energy consumption pattern capture network is used to process the reference energy consumption data set and the real-time energy consumption data to obtain a reference energy consumption time series pattern feature vector set and a real-time energy consumption time series pattern feature vector, including: Passing each reference energy consumption data in the set of reference energy consumption data through an energy consumption time series pattern feature extractor based on a one-dimensional extended convolutional layer to obtain a set of reference energy consumption time series pattern feature vectors; and Passing the real-time energy consumption data through the energy consumption time series pattern feature extractor based on the one-dimensional extended convolution layer to obtain the real-time energy consumption time series pattern feature vector; The process of using an energy consumption state matching network to process the set of the real-time energy consumption time series pattern feature vector and the reference energy consumption time series pattern feature vector to determine whether the energy consumption state of the programmed robot is abnormal includes: Calculating the global matching coefficient of each reference energy consumption timing pattern feature vector in the set of the real-time energy consumption timing pattern feature vector and the reference energy consumption timing pattern feature vector to obtain a set of global matching coefficients; Calculating a global mean of the set of global matching coefficients as a second-order matching coefficient; and Based on the comparison between the second-order matching coefficient and a predetermined threshold, it is determined whether there is an abnormality in the energy consumption state of the programmed robot.

2. The control method of a programming robot according to claim 1, characterized in that: Each reference energy consumption data in the set of reference energy consumption data is respectively passed through an energy consumption time series pattern feature extractor based on a one-dimensional extended convolutional layer to obtain a set of reference energy consumption time series pattern feature vectors, including: Arranging each reference energy consumption data in the set of reference energy consumption data into a reference energy consumption time series input vector according to a time dimension to obtain a set of reference energy consumption time series input vectors; and Each reference energy consumption timing input vector in the set of reference energy consumption timing input vectors is respectively passed through the energy consumption timing pattern feature extractor based on the one-dimensional extended convolution layer to obtain the set of reference energy consumption timing pattern feature vectors.

3. The control method of a programming robot according to claim 2, characterized in that: The reference energy consumption time series input vectors in the set of reference energy consumption time series input vectors are respectively passed through the energy consumption time series pattern feature extractor based on the one-dimensional extended convolution layer to obtain the set of reference energy consumption time series pattern feature vectors, including: The reference energy consumption time series input vector is processed using the following one-dimensional extended convolution formula to obtain the reference energy consumption time series pattern feature vector; wherein the one-dimensional extended convolution formula is: Among them, the one-dimensional expanded convolution kernel The size is 1× , is the length of the original convolution kernel, is the expansion rate, Indicates that the reference energy consumption timing input vector The length of the first eigenvalue at each position is time window, is the bias term, and , is a nonlinear activation function, It is local convolutional coding feature vector, is the dimension of the reference energy consumption time series input vector, is the reference energy consumption timing pattern feature vector, Indicates cascade.

4. The control method of a programming robot according to claim 3, characterized in that: Calculating the global matching coefficient of each reference energy consumption timing pattern feature vector in the set of the real-time energy consumption timing pattern feature vector and the reference energy consumption timing pattern feature vector to obtain a set of global matching coefficients, including: The set of the real-time energy consumption timing pattern feature vector and the set of the reference energy consumption timing pattern feature vector are processed by the following global matching formula to obtain the set of the global matching coefficients; wherein the global matching formula is: in, Indicates The global matching coefficient, For the The reference energy consumption timing pattern feature vector, is the real-time energy consumption timing pattern feature vector, Indicates transpose.

5. A control system for a programmed robot, characterized in that: include: A real-time energy consumption data acquisition module, used to acquire real-time energy consumption data of the programmed robot when running the first motion trajectory; A reference energy consumption data acquisition module, used to extract a set of reference energy consumption data under the simulated first motion trajectory from a background database; A data processing module, used to process the set of reference energy consumption data and the real-time energy consumption data using an energy consumption pattern capture network to obtain a set of reference energy consumption time series pattern feature vectors and a real-time energy consumption time series pattern feature vector; A vector processing module, used for processing the set of the real-time energy consumption timing pattern feature vector and the reference energy consumption timing pattern feature vector using an energy consumption state matching network to determine whether the energy consumption state of the programmed robot is abnormal; as well as An early warning prompt generating module, used for generating an early warning prompt in response to an abnormality in the energy consumption state of the programmed robot; Wherein, the data processing module includes: A reference energy consumption time series pattern feature extraction unit, configured to obtain a set of reference energy consumption time series pattern feature vectors by respectively passing each reference energy consumption data in the set of reference energy consumption data through an energy consumption time series pattern feature extractor based on a one-dimensional extended convolution layer; and A real-time energy consumption time series pattern feature extraction unit, used for passing the real-time energy consumption data through the energy consumption time series pattern feature extractor based on the one-dimensional extended convolution layer to obtain the real-time energy consumption time series pattern feature vector; The process of using an energy consumption state matching network to process the set of the real-time energy consumption time series pattern feature vector and the reference energy consumption time series pattern feature vector to determine whether the energy consumption state of the programmed robot is abnormal includes: Calculating the global matching coefficient of each reference energy consumption timing pattern feature vector in the set of the real-time energy consumption timing pattern feature vector and the reference energy consumption timing pattern feature vector to obtain a set of global matching coefficients; Calculating a global mean of the set of global matching coefficients as a second-order matching coefficient; and Based on the comparison between the second-order matching coefficient and a predetermined threshold, it is determined whether there is an abnormality in the energy consumption state of the programmed robot.