A robot fault detection method and device

Abstract

The present invention discloses a robot fault detection method and device, wherein the detection method comprises the following steps: Step 1: installing a variety of sensors and self-healing materials with self-healing function on key components of the robot; Step 2: a variety of sensors transmit the collected data to the central control system for real-time processing and analysis; Step 3: the central control system integrates the data of each sensor to monitor the operating status and health status of each component of the robot in real time. If a fault is detected, the central control system automatically triggers the repair mechanism of the self-healing material; Step 4: during the self-healing material repair process, the system optimizes the repair strategy in real time and adjusts the parameters and methods of the repair process according to the actual situation; Step 5: the system records the data of each fault detection and repair. The present invention selects a suitable repair strategy for repair according to the priority and type of the fault, reduces the downtime due to fault inversion, and thus improves the production efficiency and reliability of the robot.

Description

Technical Field

[0001] The present invention relates to the field of robot technology, and in particular to a robot fault detection method and device. Background Art

[0002] With the rapid development of robotics technology, robots are widely used in various industries, such as manufacturing, logistics, and medical treatment. However, the complexity of robots and the diversity of their working environments make their fault detection and repair an important and complex issue. Traditional robot fault detection methods usually require manual intervention and rely on the experience and knowledge of experts. They are not only inefficient but also susceptible to human errors. At the same time, fault repair usually requires downtime, which seriously affects the production efficiency and reliability of robots. Summary of the invention

[0003] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions: a robot fault detection method, mainly comprising the following steps:

[0005] Step 1: Install a variety of sensors and self-healing materials with self-healing functions on the key components of the robot;

[0006] Step 2: Various sensors transmit the collected data to the central control system for real-time processing and analysis;

[0007] Step 3: The central control system integrates the data from various sensors to monitor the operating status and health status of each component of the robot in real time. If a fault is detected, the central control system automatically triggers the repair mechanism of the self-healing material. The repair mechanism is based on the priority P of the fault. i , decide on an appropriate restoration strategy;

[0008] Step 4: During the self-healing material repair process, the system optimizes the repair strategy in real time and adjusts the parameters and methods of the repair process according to the actual situation to ensure the best repair effect and robot performance recovery;

[0009] Step 5: The system records the data of each fault detection and repair.

[0010] As a preferred solution of the robot fault detection method described in the present invention, the automatic material has an integrated nanosensor inside for periodically or in real time detecting the physical state and health state of the material. If any damage or abnormality is detected in the material, the nanosensor will immediately feedback the damage location and degree to the central control system.

[0011] As a preferred solution of the robot fault detection method described in the present invention, the multiple sensors include stress sensors, temperature sensors and vibration sensors, the stress sensors are used to monitor stress changes of components, the temperature sensors are used to monitor temperature changes of components, and the vibration sensors are used to monitor vibration conditions of components.

[0012] As a preferred solution of the robot fault detection method of the present invention, the specific steps of the self-healing material repair are as follows:

[0013] S11: Self-healing materials are embedded in key robot components. Nano-sensors are embedded in these materials to monitor the status of the materials in real time. The collected status data is transmitted to the central control system via wireless or wired means for real-time monitoring;

[0014] S12: When the sensor detects an abnormal signal, it immediately records the abnormal data and reports it to the central control system, which determines the type, location and severity of the damage through algorithm analysis;

[0015] S13: The central control system generates the corresponding priority P according to the damage assessment results. i and self-healing instructions;

[0016] S14: Select an appropriate repair strategy from a preset self-healing strategy library according to the damage type and location, and then send the self-healing instruction and strategy to the control module of the self-healing material to start the self-healing process;

[0017] S15: During the self-healing process, the microcapsules in the self-healing material rupture, releasing the repair agent and initiating chemical reactions for repair. The nanosensors continue to monitor the material status in real time and feed back the material status change data to the central control system. The system monitors and adjusts the process based on the feedback data.

[0018] S16: If an abnormality is detected during the self-healing process, the system automatically adjusts the repair parameters to optimize the self-healing effect.

[0019] As a preferred solution of the robot fault detection method of the present invention, the self-healing material includes a polymer material containing microcapsules or microtube networks, which can release repair agents when damaged.

[0020] As a preferred solution of the robot fault detection method of the present invention, the algorithm analysis includes:

[0021] Data preprocessing: Cleaning and denoising sensor data using filtering algorithms;

[0022] Feature extraction: Identify the characteristics of abnormal signals through feature extraction algorithms;

[0023] Damage Assessment Algorithm: Use machine learning algorithms to classify and evaluate feature data to determine the type, location, and severity of damage.

[0024] As a preferred solution of the robot fault detection method of the present invention, the fault priority classification formula is:

[0025]

[0026] in:

[0027] i = 1, 2, ..., n, represents the number of the component;

[0028] P i represents the priority of component i, the priority of the fault P i The range of is [0, 1], where:

[0029] P i =0 means that the failure of component i has a minor impact, is not urgent and is easy to repair;

[0030] P i =1 means that the failure of component i has a great impact, is very urgent and difficult to repair;

[0031] I i represents the fault index of component i;

[0032] e is the base of natural logarithms;

[0033] α is a parameter used to adjust the impact of fault indicators on priority;

[0034] ω j is the weight of component j, which is used to weight the failure index of the component;

[0035] is a function that converts the fault indicator I i Mapping to the interval (0,1) means that the higher the fault index, the lower the priority, and vice versa. The parameter α controls the slope of the curve and affects the sensitivity of the fault index to the priority;

[0036] For the normalization part, the weighted fault indicators of all components are normalized to ensure the relative importance of each component under the overall weight.

[0037] As a preferred solution of the robot fault detection method of the present invention, the repair speed of the self-healing material is:

[0038]

[0039] in:

[0040] R represents the repair speed of the self-healing material;

[0041] P i Indicates the priority of component i;

[0042] I i represents the fault index of component i;

[0043] f(i i ) is a function that represents the fault index I i Impact on repair speed;

[0044] g(t) is a time function that represents the effect of the repair process over time.

[0045] A detection device using the above robot fault detection method comprises:

[0046] A variety of sensors to monitor the status of key components of the robot in real time;

[0047] self-healing materials, embedded in key robotic components and containing nanosensors;

[0048] The central control system is used to receive and process the data collected by the sensors and monitor the operating status and health of each component of the robot in real time;

[0049] A data transmission module is used to transmit the data collected by the sensor to the central control system wirelessly or wiredly;

[0050] A control module, used to receive self-healing instructions and repair strategies generated by the central control system and execute the self-healing process;

[0051] The feedback and recording module is used to record the data of each fault detection and repair and generate a repair report.

[0052] As a preferred solution of the detection device of the robot fault detection method of the present invention, the central control system includes:

[0053] A data processing unit, used for filtering and denoising the data collected by the sensor;

[0054] A feature extraction unit, used to identify the features of abnormal signals through a feature extraction algorithm;

[0055] A damage assessment unit is used to classify and evaluate the feature data using machine learning algorithms to determine the type, location, and severity of the damage.

[0056] Beneficial effects of the present invention:

[0057] 1. The robot fault detection method provided by the present invention introduces a self-healing material with a self-healing function. When a fault is detected, it can automatically trigger the repair mechanism and select a suitable repair strategy for repair according to the priority and type of the fault, thereby reducing the downtime caused by the fault, thereby improving the production efficiency and reliability of the robot.

[0058] 2. In the robot fault detection method provided by the present invention, through algorithm analysis and priority division, the system can intelligently evaluate the severity and urgency of the fault, so as to formulate a more reasonable repair strategy. This intelligent decision-making capability enables the system to deal with complex faults more calmly and reduce misjudgments and missed judgments.

[0059] 3. In the robot fault detection method provided by the present invention, since it can automatically detect and repair faults, the need for manual intervention is reduced and maintenance costs are reduced. At the same time, since it can optimize the repair strategy in real time, unnecessary material waste and repair time are reduced, further reducing maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0061] Figure 1 The present invention is a flowchart of a robot fault detection method.

[0062] Figure 2 The present invention is a flowchart of a self-healing material repair process in a robot fault detection method. DETAILED DESCRIPTION

[0063] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0064] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0065] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0066] Secondly, the present invention is described in detail with reference to the schematic diagram. When describing the embodiments of the present invention in detail, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0067] Example 1

[0068] Reference Figure 1-2 , which is the first embodiment of the present invention, provides a robot fault detection method, which mainly includes the following steps:

[0069] Step 1: Install a variety of sensors and self-healing materials with self-healing functions on the key components of the robot (such as joints, motors, control systems, etc.);

[0070] Among them, the various sensors include stress sensors, temperature sensors, vibration sensors, etc. The stress sensor is used to monitor the stress change of the component, the temperature sensor is used to monitor the temperature change of the component, and the vibration sensor is used to monitor the vibration of the component;

[0071] The automatic material has an integrated nano sensor inside, which is used to detect the physical state and health state of the material regularly or in real time. If any damage or abnormality is detected in the material, the nano sensor will immediately feedback the damage location and degree to the central control system;

[0072] Step 2: Various sensors transmit the collected data to the central control system for real-time processing and analysis;

[0073] Step 3: The central control system integrates the data from various sensors to monitor the operating status and health status of each component of the robot in real time. If a fault is detected, the central control system automatically triggers the repair mechanism of the self-healing material. The repair mechanism is based on the priority P of the fault. i , decide on an appropriate repair strategy;

[0074] Step 4: During the self-healing material repair process, the system optimizes the repair strategy in real time and adjusts the parameters and methods of the repair process according to the actual situation to ensure the best repair effect and robot performance recovery;

[0075] Step 5: The system records the data of each fault detection and repair.

[0076] Specifically, the specific steps of the self-healing material repair are as follows:

[0077] S11: Self-healing materials are embedded in key robot components. Nano-sensors are embedded in these materials to monitor the state of the materials in real time, including parameters such as stress, cracks, and temperature changes. The collected state data is transmitted to the central control system via wireless or wired means for real-time monitoring;

[0078] Among them, self-healing materials include polymer materials containing microcapsules or microtube networks that can release repair agents when damaged;

[0079] S12: When the sensor detects an abnormal signal (such as stress exceeding the limit, crack generation, etc.), the abnormal data is immediately recorded and reported to the central control system, which determines the type, location and severity of the damage through algorithm analysis;

[0080] S13: The central control system generates the corresponding priority P according to the damage assessment results. i and self-healing instructions;

[0081] S14: According to the damage type and location, an appropriate repair strategy is selected from a preset self-healing strategy library, and then the self-healing instruction and strategy are sent to the control module of the self-healing material to start the self-healing process, wherein the strategy library includes different repair steps and parameter settings. In addition, according to the characteristics of the self-healing material, the control module may need to be heated or pressurized to promote the self-healing process;

[0082] S15: During the self-healing process, the microcapsules in the self-healing material rupture, releasing the repair agent and initiating chemical reactions for repair. The nanosensors continue to monitor the material status in real time and feed back the material status change data to the central control system. The system monitors and adjusts the process based on the feedback data.

[0083] S16: If an abnormality is detected during the self-healing process (such as excessive temperature or insufficient repair agent), the system automatically adjusts the repair parameters to optimize the self-healing effect.

[0084] The above steps combine nanosensors, data analysis, self-healing process monitoring and feedback, etc., which can ensure that the robot can quickly and effectively repair itself when a failure occurs, and continuously optimize the self-healing process, reducing downtime due to failure inversion, thereby improving the robot's production efficiency and reliability. At the same time, since the repair strategy can be optimized in real time, unnecessary material waste and repair time are reduced, further reducing maintenance costs.

[0085] Furthermore, the algorithm analysis includes:

[0086] Data preprocessing: Use filtering algorithms (such as Fourier transform, wavelet transform) to clean and denoise sensor data;

[0087] Feature extraction: Identify the characteristics of abnormal signals through feature extraction algorithms;

[0088] Damage assessment algorithm: Use machine learning algorithms (such as support vector machines, random forests) to classify and evaluate feature data to determine the type, location, and severity of damage.

[0089] Through advanced algorithm analysis, including data preprocessing, feature extraction and damage assessment algorithms, the central control system can filter and denoise the data collected by sensors, identify the characteristics of abnormal signals through feature extraction algorithms, and use machine learning algorithms to classify and evaluate feature data to determine the type, location and severity of damage, thereby improving the level of intelligent fault detection.

[0090] Specifically, the fault priority classification formula is:

[0091]

[0092] in:

[0093] i = 1, 2, ..., n, represents the number of the component;

[0094] P i represents the priority of component i, the priority of the fault P i The range of is [0, 1], where:

[0095] P i =0 means that the failure of component i has a minor impact, is not urgent and is easy to repair;

[0096] P i =1 means that the failure of component i has a great impact, is very urgent and difficult to repair;

[0097] I i represents the fault index of component i;

[0098] e is the base of natural logarithms;

[0099] α is a parameter used to adjust the impact of fault indicators on priority;

[0100] ω j is the weight of component j, which is used to weight the failure index of the component;

[0101] is a function that converts the fault indicator I i Mapping to the interval (0,1) means that the higher the fault index, the lower the priority, and vice versa. The parameter α controls the slope of the curve and affects the sensitivity of the fault index to the priority;

[0102] For the normalization part, the weighted fault indicators of all components are normalized to ensure the relative importance of each component under the overall weight.

[0103] Through the priority classification formula, fault priorities can be flexibly classified according to the fault indicators, weights and fault impact of the components. Components with higher priorities will be repaired first, thus ensuring the reliability and stability of key components of the robot.

[0104] As a preferred solution of the robot fault detection method of the present invention, the repair speed of the self-healing material is:

[0105]

[0106] in:

[0107] R represents the repair speed of the self-healing material;

[0108] P i Indicates the priority of component i;

[0109] I i represents the fault index of component i;

[0110] f(i i ) is a function that represents the fault index I i Impact on repair speed, for example: the repair speed can be dynamically adjusted according to different fault types and severity. For example, when the fault index is high (serious fault), the repair speed increases accordingly, making the repair process more targeted and effective

[0111] g(t) is a time function that represents the effect of the repair process changing over time, that is, the repair speed can be adjusted dynamically over time. For example, the repair speed may be faster in the early stage of repair in order to quickly control the fault, and then the repair speed may be gradually slowed down to ensure the quality of the repair. This dynamic adjustment mechanism can optimize the repair process and ensure the repair effect.

[0112] Therefore, by intelligently adjusting the repair speed, it is possible to reduce resource waste and unnecessary maintenance operations during the repair process, thereby reducing overall maintenance costs. Efficient repair speed reduces robot downtime, improves production efficiency, and indirectly saves costs.

[0113] A detection device using the above robot fault detection method comprises:

[0114] A variety of sensors to monitor the status of key components of the robot in real time;

[0115] self-healing materials, embedded in key robotic components and containing nanosensors;

[0116] The central control system is used to receive and process the data collected by the sensors and monitor the operating status and health of each component of the robot in real time;

[0117] The central control system comprises:

[0118] A data processing unit, used for filtering and denoising the data collected by the sensor;

[0119] A feature extraction unit, used to identify the features of abnormal signals through a feature extraction algorithm;

[0120] A damage assessment unit that uses machine learning algorithms to classify and assess feature data to determine the type, location, and severity of damage;

[0121] A data transmission module is used to transmit the data collected by the sensor to the central control system wirelessly or wiredly;

[0122] A control module, used to receive self-healing instructions and repair strategies generated by the central control system and execute the self-healing process;

[0123] The control module includes:

[0124] A self-healing process control unit, used to control the repair process of the self-healing material, including steps such as microcapsule rupture, repair agent release, heating or pressurization;

[0125] Real-time monitoring and adjustment unit, used to monitor the material status during the self-healing process and make adaptive adjustments based on feedback data;

[0126] The feedback and recording module is used to record the data of each fault detection and repair and generate a repair report.

[0127] Specifically, the central control system includes:

[0128] A data processing unit, used for filtering and denoising the data collected by the sensor;

[0129] A feature extraction unit, used to identify the features of abnormal signals through a feature extraction algorithm;

[0130] A damage assessment unit is used to classify and evaluate the feature data using machine learning algorithms to determine the type, location, and severity of the damage.

[0131] In summary, by installing a variety of sensors on the key components of the robot, the operating status and health of the robot can be monitored in real time. Once an abnormality or fault is found, an early warning can be issued immediately, thereby achieving timely response and processing of the fault. This method introduces self-healing materials with self-healing functions. When a fault is detected, the repair mechanism can be automatically triggered, and the appropriate repair strategy can be selected according to the priority and type of the fault for repair, which reduces downtime and maintenance costs and improves the reliability of the robot. During the repair process of the self-healing material, the system can optimize the repair strategy in real time, adjust the parameters and methods of the repair process according to the actual situation, and ensure the best repair effect and robot performance recovery. This real-time optimization capability makes the repair process more efficient and accurate. Through algorithm analysis and priority division, the system can intelligently evaluate the severity and urgency of the fault, so as to formulate a more reasonable repair strategy. This intelligent decision-making ability enables the system to respond more calmly when facing complex faults, reducing misjudgments and missed judgments. In addition, since the fault can be discovered and repaired in time, the downtime caused by the fault is reduced, thereby improving the production efficiency of the robot. At the same time, due to the efficiency and accuracy of the repair process, secondary failures and downtime caused by improper maintenance are also reduced. Since faults can be automatically detected and repaired, the need for manual intervention is reduced, which reduces maintenance costs. At the same time, since the repair strategy can be optimized in real time, unnecessary material waste and repair time are reduced, further reducing maintenance costs.

[0132] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A robot fault detection method, characterized in that: The following steps are involved: Step 1: Install a variety of sensors and self-healing materials with self-healing functions on the key components of the robot; Step 2: Various sensors transmit the collected data to the central control system for real-time processing and analysis; Step 3: The central control system integrates the data from various sensors to monitor the operating status and health status of each component of the robot in real time. If a fault is detected, the central control system automatically triggers the repair mechanism of the self-healing material. The repair mechanism is based on the priority P of the fault. i , decide on an appropriate restoration strategy; The specific steps of the self-healing material repair are as follows: S11: Self-healing materials are embedded in key robot components. Nano-sensors are embedded in these materials to monitor the status of the materials in real time. The collected status data is transmitted to the central control system via wireless or wired means for real-time monitoring; S12: When the sensor detects an abnormal signal, it immediately records the abnormal data and reports it to the central control system, which determines the type, location and severity of the damage through algorithm analysis; S13: The central control system generates the corresponding priority P according to the damage assessment results. i and self-healing instructions; S14: Select an appropriate repair strategy from a preset self-healing strategy library according to the damage type and location, and then send the self-healing instruction and strategy to the control module of the self-healing material to start the self-healing process; S15: During the self-healing process, the microcapsules in the self-healing material rupture, releasing the repair agent and initiating chemical reactions for repair. The nanosensors continue to monitor the material status in real time and feed back the material status change data to the central control system. The system monitors and adjusts the process based on the feedback data. S16: If an abnormality is detected during the self-healing process, the system automatically adjusts the repair parameters to optimize the self-healing effect; Step 4: During the self-healing material repair process, the system optimizes the repair strategy in real time and adjusts the parameters and methods of the repair process according to the actual situation to ensure the best repair effect and robot performance recovery; Step 5: The system records the data of each fault detection and repair.

2. The robot fault detection method according to claim 1, characterized in that: The self-healing material has integrated nanosensors for periodically or in real time detecting the physical state and health status of the material. If any damage or abnormality is detected in the material, the nanosensor will immediately feedback the location and extent of the damage to the central control system.

3. The robot fault detection method according to claim 1, characterized in that: The various sensors include stress sensors, temperature sensors and vibration sensors. The stress sensors are used to monitor stress changes of components, the temperature sensors are used to monitor temperature changes of components, and the vibration sensors are used to monitor vibration conditions of components.

4. The robot fault detection method according to claim 1, characterized in that: The self-healing materials include polymer materials containing microcapsules or microtube networks that can release repair agents when damaged.

5. The robot fault detection method according to claim 1, characterized in that: The algorithm analysis includes: Data preprocessing: Cleaning and denoising sensor data using filtering algorithms; Feature extraction: Identify the characteristics of abnormal signals through feature extraction algorithms; Damage Assessment Algorithm: Use machine learning algorithms to classify and evaluate feature data to determine the type, location, and severity of damage.

6. The robot fault detection method according to claim 1, characterized in that: The fault priority classification formula is: in: i = 1, 2, ..., n, represents the number of the component; P i represents the priority of component i, the priority of the fault P i The range of is [0, 1], where: P i =0 means that the failure of component i has a minor impact, is not urgent and is easy to repair; P i =1 means that the failure of component i has a great impact, is very urgent and difficult to repair; I i represents the fault index of component i; e is the base of natural logarithms; α is a parameter used to adjust the impact of fault indicators on priority; ω j is the weight of component j, which is used to weight the failure index of the component; is a function that converts the fault indicator I i Mapping to the interval (0,1) means that the higher the fault index, the lower the priority, and vice versa. The parameter α controls the slope of the curve and affects the sensitivity of the fault index to the priority; For the normalization part, the weighted fault indicators of all components are normalized to ensure the relative importance of each component under the overall weight.

7. The robot fault detection method according to claim 1, characterized in that: The repair speed of the self-healing material is: in: R represents the repair speed of the self-healing material; P i Indicates the priority of component i; I i represents the fault index of component i; f(i i ) is a function that represents the fault index I i Impact on repair speed; g(t) is a time function that represents the effect of the repair process over time.

8. The detection device of the robot fault detection method according to any one of claims 1 to 7, characterized in that: include: A variety of sensors to monitor the status of key components of the robot in real time; self-healing materials, embedded in key robotic components and containing nanosensors; The central control system is used to receive and process the data collected by the sensors and monitor the operating status and health of each component of the robot in real time; A data transmission module is used to transmit the data collected by the sensor to the central control system wirelessly or wiredly; A control module, used to receive self-healing instructions and repair strategies generated by the central control system and execute the self-healing process; The feedback and recording module is used to record the data of each fault detection and repair and generate a repair report.

9. The detection device of the robot fault detection method according to claim 8, characterized in that: The central control system comprises: A data processing unit, used for filtering and denoising the data collected by the sensor; A feature extraction unit, used to identify the features of abnormal signals through a feature extraction algorithm; A damage assessment unit is used to classify and evaluate the feature data using machine learning algorithms to determine the type, location, and severity of the damage.

Images