Construction method and device of door body damage detection model and electronic equipment

Abstract

The invention provides a door body damage detection model construction method and device and electronic equipment, and belongs to the field of artificial intelligence, and the method comprises the steps: constructing a damage behavior simulation model based on physical benchmarking data and a damage coefficient of a door body core component at each discrete time point; training the initial network model by using the training data set to obtain the door body damage detection model; training data in the training data set comprises a door opening angle and a damage coefficient of the damage behavior simulation model at a discrete time point, and a label of the training data is door opening force at the discrete time point. According to the method, a simulation model is benchmarked by designing a model test, meanwhile, a 3D parameterized damage behavior simulation model considering damage is established, finally, the discrete damage behavior simulation model is subjected to order reduction through deep learning, a network model capable of rapidly and accurately monitoring the door body damage in real time is obtained, and the industry blank is filled up.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence, and particularly to a method, device and electronic device for constructing a door body damage detection model. Background Art

[0002] During long-term use, the door body system of appliances such as dishwashers will have damage to core components, which affects the performance and safety of the equipment. Therefore, it is a current industry requirement to monitor the damage state of the door body system in real time and accurately to improve the reliability and service life of the equipment.

[0003] Under the traditional door body system health management mode, there are generally two ways to obtain the health state of the door body system: 1) Collect the usage feedback of customers. During the customer's use, if they find that the door body system is abnormal, they will contact the customer service for feedback. The after-sales team will investigate the abnormal situation to find the cause of the failure of the door body system, and relevant failure data can be collected through long-term accumulation. 2) Establish a corresponding laboratory to conduct a quick closing acceleration fatigue durability life test on the door body system. By using this method, the evolution of the health state of the door body system can be understood, but due to the difference in the action time sequence of the door body system in the actual use process, the damage evolution result is inaccurate.

[0004] It can be seen that there is currently no technology for real-time monitoring of the damage of the door body system in the industry, and it is urgent to fill this industry gap. Summary of the Invention

[0005] The present invention provides a method, device and electronic device for constructing a door body damage detection model, which is used to fill the technical gap of accurately, real-time and quickly detecting the damage evolution process of the door body system of household appliances, and proposes a door body damage detection model based on a deep learning network algorithm and considering the damage evolution behavior, which can effectively solve this problem.

[0006] The present invention provides a method for constructing a door body damage detection model, including the following steps: Based on the physical calibration data and the damage coefficients of each door body core component at each discrete time point in a preset time sequence, construct a damage behavior simulation model for each of the discrete time points; the physical calibration data is obtained by performing physical opening and closing experiments on the core components of a real physical door body; Use a training data set to train an initial network model to obtain the door body damage detection model; any training data in the training data set includes the opening angle of a damage behavior simulation model at its corresponding discrete time point and the damage coefficients of each door body core component, and the label of the training data is the opening force at the discrete time point.

[0007] A method for constructing a door body damage detection model provided by the present invention, which constructs a damage behavior simulation model for each discrete time point based on physical calibration data and damage coefficients of each core component of the door body at each discrete time point in a preset time sequence, includes: Using the physical calibration data to calibrate each non-damage simulation model one by one to obtain a normal behavior simulation model for each core component of the door body; Combining the normal behavior simulation models to form a door body system simulation model; According to the damage coefficients of each core component of the door body at each discrete time point in the preset time sequence, updating the door body system simulation model to obtain the damage behavior simulation models under different damage states at each discrete time point.

[0008] A method for constructing a door body damage detection model provided by the present invention, wherein the physical calibration data includes force time sequence curve samples obtained from physical opening and closing experiments with angle control for each core component of the door body; The step of using the physical calibration data to calibrate each non-damage simulation model one by one to obtain a normal behavior simulation model for each core component of the door body includes: For the non-damage simulation model of any core component of the door body, adjusting the model parameters of the non-damage simulation model according to the curve difference between the virtual force time sequence curve output by the non-damage simulation model and the force time sequence curve sample until the curve difference is within a preset range, and obtaining the adjusted non-damage simulation model as the normal behavior simulation model.

[0009] A method for constructing a door body damage detection model provided by the present invention, wherein the core components of the door body include an outer door subsystem and all key subsystems, and the key subsystems include one or more of a hinge subsystem, a pull rope spring subsystem, a lock buckle subsystem, and a sealing subsystem; the hinge subsystem is composed of a skeleton subsystem and an outer door subsystem; Correspondingly, the non-damage simulation models include an outer door subsystem simulation model, a hinge subsystem simulation model, a pull rope spring subsystem simulation model, a lock buckle subsystem simulation model, and a sealing subsystem simulation model.

[0010] A method for constructing a door body damage detection model provided by the present invention, wherein the step of combining the normal behavior simulation models to form a door body system simulation model includes: Integrate the normal behavior simulation models of the outer door subsystem, hinge subsystem, cable spring subsystem, lock subsystem, and sealing subsystem corresponding to the outer door subsystem simulation model, hinge subsystem simulation model, cable spring subsystem simulation model, lock subsystem simulation model, and sealing subsystem simulation model to obtain the door body system simulation model.

[0011] According to a method for constructing a door body damage detection model provided by the present invention, updating the door body system simulation model according to the damage coefficients of each door body core component at each discrete time point in the preset time sequence, and obtaining the damage behavior simulation models in different damage states at each discrete time point, including: Based on the current opening and closing times of any door body core component at any discrete time point and the fatigue opening and closing times limit value of the any door body core component, determine the damage coefficient of the any door body core component at the any discrete time point; Based on the damage coefficient, determine the scaling coefficient of the target parameter related to door body damage of the any door body core component; At the any discrete time point, update the door body system simulation model according to the scaling coefficients of the target parameters related to door body damage of all door body core components, and obtain the damage behavior simulation model at the any discrete time point; Traverse all the discrete time points to obtain all the damage behavior simulation models.

[0012] According to a method for constructing a door body damage detection model provided by the present invention, the target parameters of the hinge subsystem include the deformation parameters at the connection point of the hinge and the cable, the target parameters of the cable spring subsystem include the cable stiffness and the telescopic spring stiffness, the target parameters of the lock subsystem include the locking spring stiffness, and the target parameters of the sealing subsystem include the sealing strip stiffness.

[0013] According to a method for constructing a door body damage detection model provided by the present invention, using any training data in the training dataset to train the initial network model to obtain the door body damage detection model, including: According to the preset time sequence, sequentially input the training data corresponding to each discrete time point into the initial network model to obtain an opening force prediction sequence output by the initial network model; According to the network error between the opening force prediction sequence and the opening force label sequence, gradually update the model parameters of the initial network model until the model converges to obtain the door body damage detection model; The opening force label sequence is composed of the opening forces at all discrete time points in the preset time sequence.

[0014] A method for constructing a door body damage detection model provided by the present invention, wherein the initial network model is obtained based on a long short-term memory network model as the basic model architecture.

[0015] The present invention also provides a device for constructing a door body damage detection model, mainly including: A damage behavior simulation model construction unit, configured to construct a damage behavior simulation model for each of the discrete time points based on physical calibration data and damage coefficients of each core component of the door body at each discrete time point in a preset time sequence; the physical calibration data is obtained by performing physical opening and closing experiments on each core component of a real physical door body; An initial network model training control unit, configured to train the initial network model using a training data set to obtain the door body damage detection model; any training data in the training data set includes the opening angle of a damage behavior simulation model at its corresponding discrete time point and the damage coefficients of each core component, and the label of the training data is the opening force at the discrete time point.

[0016] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the method for constructing a door body damage detection model as described in any one of the above is implemented.

[0017] The present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method for constructing a door body damage detection model as described in any one of the above is implemented.

[0018] The present invention also provides a computer program product, including a computer program. When the computer program is executed by a processor, the method for constructing a door body damage detection model as described in any one of the above is implemented.

[0019] The method, device, and electronic device for constructing a door body damage detection model provided by the present invention fill the industry gap by designing model experiments to calibrate the simulation model, establishing a 3D parametric damage behavior simulation model considering damage, and finally reducing the order of the discrete damage behavior simulation model through deep learning to obtain a network model that can quickly and accurately monitor the door body damage in real time. Description of the Drawings

[0020] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0021] Figure 1 It is a schematic flow chart of the method for constructing the door body damage detection model provided by the present invention.

[0022] Figure 2 It is a schematic diagram of the method for determining the damage coefficient of the hinge subsystem provided by the present invention.

[0023] Figure 3 It is a schematic diagram of the sealing strip stiffness curve provided by the present invention.

[0024] Figure 4 It is a schematic flow chart of the training process of the door body damage detection model provided by the present invention.

[0025] Figure 5 It is a schematic structural diagram of the device for constructing the door body damage detection model provided by the present invention.

[0026] Figure 6 It is one of the schematic diagrams of the performance of the door body damage detection model provided by the present invention in the training data set.

[0027] Figure 7 It is another schematic diagram of the performance of the door body damage detection model provided by the present invention in the training data set.

[0028] Figure 8 It is yet another schematic diagram of the performance of the door body damage detection model provided by the present invention in the training data set.

[0029] Figure 9 It is still another schematic diagram of the performance of the door body damage detection model provided by the present invention in the training data set.

[0030] Figure 10 It is the fifth schematic diagram of the performance of the door body damage detection model provided by the present invention in the training data set.

[0031] Figure 11 It is one of the schematic diagrams of the performance of the door body damage detection model provided by the present invention in the test data set.

[0032] Figure 12 It is another schematic diagram of the performance of the door body damage detection model provided by the present invention in the test data set.

[0033] Figure 13 It is yet another schematic diagram of the performance of the door body damage detection model provided by the present invention in the test data set.

[0034] Figure 14 It is still another schematic diagram of the performance of the door body damage detection model provided by the present invention in the test data set.

[0035] Figure 15 It is the fifth schematic diagram of the performance of the door body damage detection model provided by the present invention in the test data set.

[0036] Figure 16 It is one of the schematic diagrams showing the evolution of the loss function value during the training process of the door body damage detection model provided by the present invention.

[0037] Figure 17 It is the second schematic diagram showing the evolution of the loss function value during the training process of the door body damage detection model provided by the present invention.

[0038] Figure 18 It is the schematic structural diagram of the electronic device provided by the present invention. Detailed implementation manners

[0039] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below with reference to the accompanying drawings in the present invention. Obviously, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without making creative efforts based on the embodiments in the present invention belong to the scope of protection of the present invention.

[0040] It should be noted that in the description of the present invention, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the phrase "including one..." does not exclude the existence of additional identical elements in the process, method, article or device including the said element. The orientation or positional relationship indicated by the terms "upper", "lower", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus cannot be construed as a limitation of the present invention. Unless otherwise clearly defined and limited, the terms "mounted", "connected" and "coupled" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the internal communication of two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0041] The terms "first", "second", etc. in the present invention are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present invention can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more.

[0042] For the scenario of health state management of electrical appliances, especially household electrical appliances, it is a very broad category. Taking a dishwasher as an example, during the actual use by users, the scenarios that require health state management are as follows: 1) Monitoring the health state of the dishwasher's washing system: During the washing process, whether there are abnormalities in water pressure, water temperature, booster pump, breather, drainage system, etc. The monitoring, prediction, and fault diagnosis of the overall health state of the washing system are generally related to the relevant control system; 2) Monitoring the health state of the dishwasher's structural system: Whether there are damages in various systems of the dishwasher, including the door system, inner tank system, chassis system, etc., analyzing the damage value, remaining life, and judging whether the life limit has been reached, etc.

[0043] During the user's use process, for the door system of electrical appliances, such as the core components of the door system including the drawstring spring subsystem, seal strip subsystem, lock subsystem, hinge subsystem, etc., after being used for a certain number of years, there is a probability of failure. For example, the following failure situations may occur: 1) Drawstring spring subsystem: The telescopic spring becomes loose or breaks, and the drawstring wears or breaks; 2) Seal strip subsystem: The sealing performance of the seal strip gradually decreases, and the resilience decreases; 3) Lock subsystem: The insertion position of the lock pin wears, and the locking spring becomes loose or breaks; 4) Hinge subsystem: The hinge structure is deformed or broken, etc.

[0044] During the design process of the door system, in order to quickly obtain the process of damage evolution of the door system throughout its life cycle, a corresponding laboratory will be established to conduct the quick-closing accelerated fatigue durability life test of the door system. At the same time, combined with the fault data obtained from the fault analysis of the feedback during the customer's use process, however, due to the complexity and individuality of the action timing of each door system, the damage evolution is also fast and slow, so these existing methods often cannot achieve systematic and real-time analysis of the damage of the door system. How to solve this need is an urgent problem in the industry.

[0045] Today, with the rapid development of digitalization, the integration of digital twin technology with reinforcement learning algorithms and deep learning algorithms may become a new health management mode for door systems. To address this technical need in the current industry, the present invention proposes a method, apparatus, and electronic device for constructing a door damage detection model. The main implementation principles include the following steps: First, design a model experiment to obtain physical benchmark data as the benchmark standard for the non-destructive simulation model. Second, construct a normal behavior simulation model through benchmarking with the physical benchmark data. Third, based on the corrected normal behavior simulation model, apply the fatigue damage theory, propose reasonable mechanical assumptions, and establish a damage behavior simulation model considering damage evolution, and output a training data set for deep learning. Then, train based on the deep learning network algorithm and output the corresponding AI reduced-order model of the damage behavior simulation model as a high-fidelity digital twin model considering damage evolution behavior, that is, the door damage detection model. Subsequently, based on the reinforcement learning algorithm, the door damage detection model can be learned to obtain the corresponding door damage recognition agent, which can be used for real-time monitoring of the damage state of the door system.

[0046] It should be noted that the object of the door damage detection model to be constructed in the present invention can be any door system, not limited to the door systems of various electrical appliances. For example, it can be a dishwasher door system, a refrigerator door system, a washing machine door system, or other systems containing the door structure. For the convenience of description, the dishwasher door system will be used as an example hereinafter, which is not regarded as a specific limitation of the protection scope of the present invention.

[0047] The following will combine Figures 1-18 to describe the method, apparatus, and electronic device for constructing the door damage detection model provided by the present invention.

[0048] Figure 1 is a schematic flow chart of the method for constructing the door damage detection model provided by the present invention. As Figure 1 shown, it includes but is not limited to the following steps: Step 101, construct a damage behavior simulation model for each discrete time point based on the physical benchmark data and the damage coefficients of each core component of the door at each discrete time point in a preset time sequence.

[0049] Among them, the physical benchmark data is obtained by conducting physical opening and closing experiments on each core component of the real physical door. The specific acquisition method can be: Select a representative dishwasher door system to ensure that its core components (such as the pull cord spring subsystem, the sealing subsystem, the locking subsystem, etc.) are in an initial undamaged state. In the physical opening and closing experiment, adopt the angle control method, that is, keep the angle increment consistent each time the door is opened (for example, increase by 1° each time), and record the opening force data of the door system at different opening and closing angles. Specifically, high-precision force sensors and angle sensors can be used to collect the opening force data and the opening angle at each discrete time point of the preset time sequence (i.e., discrete sampling time points), constituting the opening force time sequence data and the opening angle time sequence data. The obtained opening force time sequence data and opening angle time sequence data can be represented by the opening force time sequence curve and the opening angle time sequence curve respectively. These data will be used as physical benchmark data for subsequent benchmarking of the undamaged simulation model.

[0050] The damage coefficient is mainly used to quantify the damage degree of each core component of the door at different usage stages, and generally can be determined by the ratio between the current opening and closing times of each core component of the door and the fatigue opening and closing times limit value.

[0051] For example, for the pull cord spring subsystem, the damage coefficient D at any discrete time point can be defined as: , where is the current opening and closing times at this any discrete time point, and

[0052] is the fatigue opening and closing times limit value of the pull cord spring subsystem. First, according to the initial parameters of each core component of the door, construct the initialization simulation model of each core component of the door system in the door system. This initialization simulation model can be called an undamaged simulation model.

[0053] Then, use the physical benchmark data to benchmark each undamaged simulation model respectively, and the normal behavior simulation models of each core component of the door can be obtained. Using the normal behavior simulation models of all core components of the door, the door system simulation model can be constructed.

[0054] Finally, at each discrete time point of the preset time sequence, according to the loss coefficient of each core component of the door at this discrete time point, update the parameters of the corresponding components in the door system simulation model. For example, at a certain discrete time point, adjust the stiffness of the pull cord spring according to the damage coefficient D of the pull cord spring subsystem. In this way, at each discrete time point, a damage behavior simulation model considering the damage evolution behavior can be obtained.

[0055] Assume that 50 discrete sampling points are set over the entire preset time sequence, then 50 damage behavior simulation models under different damage states can be obtained.

[0056] Step 102: Use the training data set to train the initial network model to obtain the door body damage detection model.

[0057] Among them, any training data in the training data set includes the opening angle of a damage behavior simulation model at its corresponding discrete time point and the damage coefficients of each core component of the door body, and the label of the training data is the opening force at the discrete time point.

[0058] Specifically, the preparation of the training data set can be carried out first. Each training data in this training data set is closely related to the damage behavior simulation models obtained at each discrete sampling point. First, through experiments, the opening force data of the door body system at different opening and closing angles within the preset time sequence are tested first, that is, the opening angle and opening force at each discrete sampling point can be obtained. At the same time, according to the opening and closing times of each core component of the door body system at each discrete sampling point, the damage coefficients of each core component of the door body are counted.

[0059] Furthermore, the opening angle obtained at each discrete time point and the damage coefficients of each core component of the door body are combined into a training data, and the opening force obtained at this discrete time point is used as the label of this training data, then a set of training samples corresponding to each discrete time point can be obtained. Assume that there are 5 core components of the door body, and the damage coefficients at any discrete time point are D1, D2, D3, D4, and D5 respectively. Then the input of the training sample at this discrete time point = (opening angle, D1, D2, D3, D4, D5), and its corresponding label = (opening force).

[0060] Select a suitable neural network model as the first initial network model. For example, after selecting the long short-term memory network LSTM, use the training data set to train it. The specific training steps can be: (1) Input a training data in the training data set into the first initial network model.

[0061] (2) Calculate the predicted value of the opening force output by the first initial network model, and calculate the network error (such as the mean square error) between the predicted value of the opening force and the label corresponding to this training data.

[0062] (3) Use the backpropagation algorithm to update the parameters of the first initial network model to optimize the model performance, with the goal of reducing the network error between the output of the first initial network model and the label.

[0063] (4) Repeat the above process until the model converges to obtain a trained door body damage detection model.

[0064] The method for constructing the door body damage detection model provided by the present invention calibrates the simulation model through the design of model tests. At the same time, a 3D parametric damage behavior simulation model considering damage is established. Finally, the discrete damage behavior simulation model is reduced in order through deep learning to obtain a network model that can quickly and accurately monitor the door body damage in real time, filling the industry gap.

[0065] Based on the content of the above embodiments, as an alternative embodiment, the core components of the door body include the outer door subsystem and all key subsystems, and the key subsystems include one or more of the hinge subsystem, the cable spring subsystem, the lock subsystem, and the sealing subsystem; the hinge subsystem is composed of the skeleton subsystem and the outer door subsystem; Correspondingly, the non-destructive simulation model includes an outer door subsystem simulation model, a hinge subsystem simulation model, a cable spring subsystem simulation model, a lock subsystem simulation model, and a sealing subsystem simulation model.

[0066] Taking the door body system of a dishwasher as an example, its key subsystems mainly include a hinge subsystem, a cable spring subsystem, a lock subsystem, and a sealing subsystem. Overall, the above key subsystems are composed of 6 core components: springs (the spring of the cable spring subsystem is called a telescopic spring for distinction, and the spring of the lock subsystem is called a locking spring), ropes, pulleys, hinge walls, door bodies, door lock buckles, and sealing strips.

[0067] Correspondingly, the simulation model of the entire door body system of the dishwasher is formed by fusing the simulation models of 5 subsystems related to the core components of the door body, namely the outer door subsystem simulation model, the hinge subsystem simulation model, the cable spring subsystem simulation model, the lock subsystem simulation model, and the sealing subsystem simulation model.

[0068] Traditional calibration methods require obtaining the key mechanical parameters of each core component of the door body through standard mechanical test experiments. For standard mechanical test experiments, it is generally necessary to make standard specimens of each core component of the door body, and it may be necessary to complete the acquisition of key mechanical parameters through multiple test experiments. Many universities or research institutes cannot complete all the test experiments. Generally, the test cycle is relatively long and the test cost is relatively high.

[0069] In view of this, the present invention calibrates the simulation model of the door body system of the dishwasher by designing key model tests, directly at the system level.

[0070] First, the method for constructing the calibration model of each real core component of the door body will be introduced below.

[0071] The hinge subsystem mainly includes a skeleton and an outer door. To be consistent with the subsequent non-destructive simulation model to be constructed, the state of its benchmark model test is designed as follows: remove the latch, sealing strip, and rope, and retain the door hinge.

[0072] The pull rope spring subsystem mainly includes a skeleton, an outer door, a pull rope, a spring, etc. To be consistent with the subsequent non-destructive simulation model to be constructed, the state of its benchmark model test is designed as follows: remove the latch and sealing strip, and retain the rope, outer door, hinge, etc.

[0073] The latch subsystem mainly includes a skeleton, an outer door, and a latch. To be consistent with the subsequent non-destructive simulation model to be constructed, the state of its benchmark model test is designed as follows: remove the sealing strip, rope, etc., and retain the latch, outer door, hinge, etc.

[0074] The sealing subsystem mainly includes a skeleton, an outer door, and a sealing strip, etc. To be consistent with the subsequent non-destructive simulation model to be constructed, the state of its benchmark model test is designed as follows: remove the latch and rope, and retain the outer door, hinge, and sealing strip, etc.

[0075] Taking the door system of the above dishwasher as an example for illustration, using the physical benchmark data and the damage coefficients of each door core component at each discrete time point in the preset time sequence, a damage behavior simulation model for each of the discrete time points is constructed, specifically including but not limited to: Using the physical benchmark data to benchmark each non-destructive simulation model one by one to obtain a normal behavior simulation model for each door core component; Collect the normal behavior simulation models to form a door system simulation model; According to the damage coefficients of each door core component at each discrete time point in the preset time sequence, update the door system simulation model to obtain the damage behavior simulation models under different damage states at each discrete time point.

[0076] The non-destructive simulation model is established based on the theoretical and empirical data of each door core component and is used to simulate the behavior of the door core component in a non-damaged state. The general construction process includes: 1) Construct non-destructive simulation models according to the physical characteristics and mechanical behaviors of each door core component. These non-destructive simulation models mainly include: hinge subsystem, pull rope spring subsystem, latch subsystem, sealing subsystem, etc.

[0077] 2) Initialize the model parameters related to each door core component in these non-destructive simulation models, such as the stiffness, strength, friction coefficient, etc. of each component.

[0078] Furthermore, the above non-destructive simulation models are calibrated using physical calibration data to adjust the model parameters of each non-destructive simulation model, so that the simulation output of the non-destructive simulation model is consistent with the real test data, and the normal behavior simulation models of each core component of the door body are obtained.

[0079] As an alternative embodiment, to simplify and standardize the calibration process, when calibrating the above non-destructive simulation models using physical calibration data, the following settings can be made for the corresponding calibration process: (1) During the calibration test of the non-destructive simulation model of each core component of the door body, since the door body undergoes the same timing actions, from the locked state of the door body to opening to a preset angle and then returning to the original locked state, relevant data is collected, including recording the magnitude of each opening force and the corresponding opening angle at discrete time points.

[0080] (2) The angle control is adopted during the test process, that is, for each opening and closing process of each test, the time used to open the door by 1° is the same. Through the above tests, the force-time curve and angle-time curve of the real physical prototype can be obtained as the physical calibration data for subsequent simulation calibration.

[0081] (3) A force sensor is used to collect the magnitude of the opening force, and an angle sensor is used to collect the magnitude of the opening angle. The entire opening process can be automatically controlled by a robotic arm.

[0082] Furthermore, the normal behavior simulation models of each core component of the door body are combined to form a complete door body system simulation model. Specifically, the normal behavior simulation models of core components of the door body such as the pull rope spring subsystem, seal strip subsystem, lock subsystem, hinge subsystem, etc. are integrated together to form a complete door body system simulation model. System-level verification can also be carried out on the integrated door body system simulation model to ensure that the interaction and overall behavior between each core component of the door body conform to the actual physical system.

[0083] The damage coefficient is used to quantify the damage degree of each core component of the door body at different usage stages. First, according to the fatigue characteristics of the core components of the door body, the damage coefficient D of each core component of the door body can be defined i , and the value range of each damage coefficient is [0, 1], where 0 indicates no damage and 1 indicates complete failure.

[0084] Then, according to the current opening and closing times and the fatigue opening and closing times limit value of each core component of the door body, the damage coefficient at each discrete time point is calculated.

[0085] Further, according to the determined damage coefficients of each core component of the door body at each discrete time point, relevant model parameters in the door body system simulation model can be updated. For example, if the damage coefficient of the drawstring spring subsystem is calculated to be D2 at a certain discrete time point, the stiffness of the drawstring spring in the drawstring spring subsystem of the door body system simulation model can be updated according to the damage coefficient D2.

[0086] In this way, by continuously running within a preset time sequence and obtaining the updated door body system simulation model, a damage behavior simulation model at each discrete time point is obtained.

[0087] The method for constructing the door body damage detection model provided by the present invention obtains the normal behavior simulation model of each component by using physical calibration data to calibrate the non-destructive simulation models of each core component of the door body. Subsequently, these normal behavior simulation models are combined to form a complete door body system simulation model. Finally, according to the damage coefficients at each discrete time point, the door body system simulation model is updated to obtain a damage behavior simulation model under different damage states. This process solves the technical problem that the simulation software cannot directly establish damage evolution, provides a solid foundation for the subsequent construction of the door body damage detection model, and ensures the accuracy and reliability of the model.

[0088] As an optional embodiment, the physical calibration data includes force time sequence curve samples obtained by respectively performing physical opening and closing experiments on each of the core components of the door body under angle control.

[0089] The following details the process of using the physical calibration data to calibrate each non-destructive simulation model one by one to obtain the normal behavior simulation model of each core component of the door body, which specifically includes: For the non-destructive simulation model of any core component of the door body, according to the curve difference between the virtual force time sequence curve output by the non-destructive simulation model and the force time sequence curve sample, the model parameters of the non-destructive simulation model are adjusted until the curve difference is within a preset range, and the adjusted non-destructive simulation model is obtained as the normal behavior simulation model.

[0090] The physical calibration data is obtained by performing physical opening and closing experiments on each core component of the real physical door body. Taking the dishwasher door body system as an example, its actual acquisition process can be realized through the following steps: First, select a representative dishwasher door body system to ensure that all its important components (such as drawstring springs, sealing strips, lock catches, etc.) are in an initial non-damaged state.

[0091] In the experiment, an angle control method is adopted, that is, the angle increment of each door opening is kept consistent (for example, increasing by 1° each time), and the door opening force data at different opening and closing angles of the door body is recorded.

[0092] Meanwhile, high-precision force sensors and angle sensors are used to collect the time-series data of the door-opening force and the door-opening angle respectively, forming a sample of the force time-series curve. These physical benchmark data will be used as the basis for subsequent simulation model benchmarking.

[0093] The lossless simulation model is pre-constructed using simulation software (such as MotionView) based on the physical characteristics and mechanical behaviors of the core components of each door body. For the dishwasher door body system, it mainly includes the hinge subsystem simulation model, the cable spring subsystem simulation model, the lock subsystem simulation model, and the seal subsystem simulation model, etc. The hinge subsystem simulation model is mainly composed of the skeleton subsystem simulation model and the outer door subsystem simulation model.

[0094] The skeleton subsystem simulation model, which is mainly composed of components such as the inner liner, the inner liner hinge, and the door hinge, uses MotionView and MotionSolve as the front and back processors respectively. Unit selection is carried out according to the force characteristics of each component. All components of the inner liner, the inner liner hinge, and the door hinge are simulated using rigid body elements; all components of the inner liner are fixedly connected, the inner liner and the inner liner hinge are fixedly connected, the inner liner hinge and the ground are fixedly connected, and a revolute joint is set between the door hinge and the inner liner hinge.

[0095] The outer door subsystem simulation model, which is mainly composed of the inner door, the outer door, and other components, uses MotionView and MotionSolve as the front and back processors respectively. Unit selection is carried out according to the force characteristics of each component. The inner door, the outer door, and other components are all simulated using rigid body elements. The inner door, the outer door, and other components are fixedly connected, and the inner door is fixedly connected to the door hinge.

[0096] The cable spring subsystem simulation model, which is mainly composed of a cable, a fixed pulley, a spring group, and other components, selects units according to the force characteristics of each component. The fixed pulley is simulated using a rigid body element, the cable is simulated using a nonlinear finite element element, and the spring is simulated using a spring element. One end of the cable is connected to the door hinge, the other end of the cable is connected to the spring, the spring is fixedly connected to the ground, and contact is defined between the cable and the fixed pulley.

[0097] The lock subsystem simulation model, which is mainly composed of a door lock and an inner liner lock and other components, and the inner liner lock is composed of a lock box, a tension spring, and 2 locking teeth. MotionView and MotionSolve are used as the front and back processors respectively. Unit selection is carried out according to the force characteristics of each component. Both the door lock and the inner liner lock are simulated using rigid body elements. The door lock is fixedly connected to the inner door, the inner liner lock is fixedly connected to the inner liner, the 2 locking teeth are respectively connected to both ends of the tension spring, each locking tooth rotates around a defined revolute joint, and contact is defined between the locking teeth, the lock box, and the door lock.

[0098] The seal subsystem simulation model can be composed of multiple Forces (e.g., 34). Using the macroscopic modeling method, the entire sealing strip is divided into 34 equal parts. The mechanical behavior of each sealing strip is described by a macroscopic constitutive model. According to past test experience, a two-segment linear line mathematical expression is used to describe the macroscopic constitutive model of the sealing strip. MotionView and MotionSolve are used as the pre- and post-processors respectively. Unit selection is carried out according to the force characteristics of each component. The acting force of the sealing strip is a pair of action and reaction forces. 34 Forces are used, and each Force acts on the inner liner and the inner door respectively.

[0099] Furthermore, using the physical benchmarking data of each door core component, the non-destructive simulation models of each door core component are benchmarked one by one to obtain the normal behavior simulation model of each said door core component. Taking the non-destructive simulation model of any one door core component as an example, the following steps can be used to achieve this: First, run the non-destructive simulation model to generate a virtual force time series curve. This virtual force time series curve describes the change in the predicted opening force of the non-destructive simulation model at different opening and closing angles.

[0100] Specifically, the Transient solver in MotionSolve can be used for solving. The outer door subsystem and the skeleton subsystem are connected by hinges. Set the rotating pair and the position of the outer door opening, and at the same time set the rotational motion of the door body. The analysis total time is 20s.

[0101] During the simulation process of running the non-destructive simulation model, the door body experiences the same time series actions. From the door body locked state, it opens to a preset angle and then returns to the original locked state. The simulation uses angle control, that is, for each opening and closing process of the non-destructive simulation model, the time used to open 1° is the same. Through the above simulation, the virtual force time series curve and the virtual angle time series curve of the virtual non-destructive simulation model can be obtained as the simulation output data. Since the angle control method is used, the angles are the same at the preset time series, so only the virtual force time series curve needs to be concerned about in the subsequent analysis.

[0102] Then, compare the virtual force time series curve generated by the non-destructive simulation model with the force time series curve sample obtained from the physical opening and closing experiment of this door core component, and calculate the curve difference between the two.

[0103] Optionally, the curve difference can be quantified by the mean square error (MSE) or other statistical indicators, which will not be elaborated here.

[0104] Furthermore, the model parameters of the non-destructive simulation model can be adjusted according to the calculated curve difference. Multiple operations can be iteratively carried out until the curve difference is within the preset range.

[0105] For example, if the mean square error between the virtual force time series curve and the force time series curve sample (i.e., the test curve) is less than a certain threshold (such as 0.01 N²), it is considered that the adjustment of the model parameters is completed. At this time, the virtual force time series curve output by the non-destructive simulation model is basically consistent with the force time series curve sample of the real physical prototype, that is, the model calibration is completed.

[0106] The adjusted non-destructive simulation model is the normal behavior simulation model, which can accurately simulate the behavior of the core components of the door body in a non-damaged state.

[0107] By using the above method to calibrate the non-destructive simulation models of each core component of the door body respectively, the normal behavior simulation models corresponding to each core component of the door body can be obtained.

[0108] Finally, by fusing the normal behavior simulation models of all the core components of the door body obtained by calibration, the complete simulation model of the door body system can be obtained in the present invention.

[0109] Taking the above dishwasher door body system as an example, by calibrating the simulation models of the outer door subsystem, the hinge subsystem, the pull cord spring subsystem, the lock subsystem and the seal subsystem, the normal behavior simulation models of the corresponding outer door subsystem, hinge subsystem, pull cord spring subsystem, lock subsystem and seal subsystem can be obtained. Finally, by fusing all these normal behavior simulation models in the simulation software, the simulation model of the door body system corresponding to the dishwasher door body system can be obtained.

[0110] The method for constructing the door body damage detection model provided by the present invention calibrates the non-destructive simulation models of each core component of the door body by using physical calibration data, adjusts the model parameters to make the simulation output consistent with the experimental data, and finally obtains the normal behavior simulation model that can accurately reflect the real behavior of the door body. This process lays a solid foundation for the subsequent construction of the door body damage detection model and effectively improves the reliability of the model.

[0111] Based on the content of the above embodiments, as an optional embodiment, the updating of the door body system simulation model according to the damage coefficient of each core component of the door body at each discrete time point in the preset time sequence to obtain the damage behavior simulation model in different damage states at each discrete time point includes: Based on the current opening and closing times of any core component of the door body at any discrete time point and the fatigue opening and closing times limit value of the any core component of the door body, determining the damage coefficient of the any core component of the door body at the any discrete time point; Determine the scaling factor of the target parameter related to the door body damage for any door body core component based on the damage coefficient; At any discrete time point, update the door body system simulation model according to the scaling factors of the target parameters related to the door body damage of all door body core components, and obtain the damage behavior simulation model at any discrete time point; Traverse all the discrete time points to obtain all the damage behavior simulation models.

[0112] Through the description of the above embodiments, a normal behavior simulation model of the door body system is established, which is idealized as intact throughout the time series. However, to build a high-fidelity digital twin model, it is necessary to consider the damage evolution process of the real physical prototype. And how to consider the change of the structural health state of the door body system is a technical difficulty in the industry.

[0113] Through the fatigue damage mechanics theory, the present invention proposes reasonable basic assumptions and establishes the theoretical relationship between the number of door openings and the structural damage evolution. The following continues to elaborate in detail on how to update the door body system simulation model according to the damage coefficients of each door body core component at each discrete time point in the preset time series to obtain the damage behavior simulation models under different damage states.

[0114] During the entire life cycle of the door body system, the action time series it experiences is to open the door and then close the door, repeating this until its service life. In view of this, the present invention proposes several reasonable mechanical basic assumptions: 1) Assume that for two consecutive door openings and closings, if the opening angles are the same, then the damage to each door body core component caused by these two door openings and closings is the same. The present invention adopts a special experimental design to make the opening angle of each door opening and closing the same, so the damage of each door opening and closing is the same. Assume that the fatigue life of a certain door body core component is N times, then the damage of each door opening and closing is 1 / N, which is represented by the D value.

[0115] 2) Assume that the damage of each door body core component of the door body system can be linearly accumulated. When the damage of a certain door body core component accumulates to a certain extent (such as reaching a certain limit value), then this door body core component reaches its service life. This limit value can be assumed to be 1 according to Miner's fatigue damage mechanics.

[0116] 3) For subsequent model reduction sampling, it is necessary to collect curves with significantly different relationships between the opening force and the opening angle. Assume that after every m door openings and closings, the relationship between the opening force and the opening angle changes significantly, and within m times, assume that the change in the relationship between the opening force and the opening angle is not obvious and can be regarded as the same. Among them, m can be data such as 100 or 200.

[0117] Through the above assumptions, the relationship between the number of door openings and the evolution of structural damage can be established. The fatigue life of each core component of the door body can be obtained through simulation methods or experimental methods, thus perfectly solving the technical problem that damage evolution cannot be directly realized by simulation software at the level of the dishwasher door body system.

[0118] In the process of constructing the damage behavior simulation model, the object is the complete door body system simulation model, and the Transient solver can be used for solution. The outer door subsystem and the skeleton are connected by hinges, and a revolute pair is set. The position of the outer door opening is set, and the rotational motion of the door body is set. The total analysis time is 20s, etc. During the simulation process of the damage behavior simulation model in each damage state, the door body system experiences the same timing actions, from the door body locked state, opening to the preset angle, and then returning to the original locked state. The simulation also adopts angle control synchronously, that is, during each opening and closing simulation process of the door, the time used to open the door by 1° is the same. Through the above simulation, the force-time sequence curve of the virtual simulation prototype in each damage state can be obtained (since the angle-time sequence curve is actually the same at this time due to the angle control method, it can be not considered), which is used as the output data of the damage behavior simulation model.

[0119] The steps to obtain the damage behavior simulation model in different damage states at each of the discrete time points can generally be divided into: Step 1, for each core component of the door body, at each discrete time point, calculate the damage coefficient according to its current number of opening and closing times and the fatigue opening and closing times limit value. According to experimental data or theoretical analysis, determine the fatigue opening and closing times limit value N lim of each core component of the door body, indicating that the core component of the door body may experience fatigue failure when reaching this number of times. Record the actual number of opening and closing times N cuee of each core component of the door body during use, then the damage coefficient can be calculated according to the formula: D i = N cuee / N lim ; where D i represents the damage coefficient of the i-th core component of the door body, and the value range is [0, 1], 0 indicates no damage, and 1 indicates complete failure.

[0120] Step 2, according to the damage coefficient of each core component of the door body, determine the scaling coefficient of the target parameters related to door body damage, including: determining the key parameters related to the damage of each core component of the door body, such as the stiffness of the pull rope spring, the stiffness of the lock catch spring, the resilience of the sealing strip, etc. According to the damage coefficient D i of each core component of the door body at each discrete sampling point, the scaling coefficient of the target parameters can be calculated.

[0121] For example, for the drawstring spring subsystem, the scaling factor of its drawstring stiffness can be expressed as: S i = 1 - D i , which means that as the damage coefficient increases, the target parameter (such as the drawstring stiffness) will decrease accordingly.

[0122] Step 3, at each discrete time point, update the door system simulation model according to the scaling factors of the target parameters of all door core components to obtain the damage behavior simulation model at this discrete time point. The specific steps include: for each door core component, update the corresponding target parameter in the door system simulation model according to the scaling factor S i of its target parameter. For example, for the drawstring spring subsystem, update its initial drawstring stiffness K0 to K updated : K updated = K0 * S i . Finally, the updated target parameters can be used to run the door system simulation model to obtain the damage behavior simulation model at this discrete time point and output the opening force time series data.

[0123] Step 4, traverse all preset discrete time points and repeat the above steps to obtain the damage behavior simulation model at each discrete time point. For example, starting from the first discrete time point, gradually traverse all discrete time points, and at each discrete time point, update the door system simulation model according to the current damage coefficient and the scaling factor of the target parameter and run the simulation. Collect the results of the damage behavior simulation models obtained at each discrete time point to form a complete set of damage behavior simulation models.

[0124] In the present invention, by determining the damage coefficient based on the current opening and closing times and the fatigue opening and closing times limit value of each door core component, and updating the target parameters in the door system simulation model according to the damage coefficient, the damage behavior simulation models in different damage states are obtained. This process provides detailed damage state data for the subsequent construction of the door damage detection model, ensuring that the model can accurately reflect the dynamic damage behavior of the door system at different usage stages.

[0125] Based on the content of the above embodiments, as an alternative embodiment, the target parameters of the hinge subsystem include the deformation parameters at the connection point between the hinge and the drawstring, the target parameters of the drawstring spring subsystem include the drawstring stiffness and the telescopic spring stiffness, the target parameters of the lock subsystem include the locking spring stiffness, and the target parameters of the sealing subsystem include the sealing strip stiffness.

[0126] Next, taking the dishwasher door system as an example, the damage conditions of its 4 subsystems will be described using the corresponding damage coefficients. The damage coefficients of the entire door system simulation model include: 1) Regarding the hinge damage coefficient D1 corresponding to the hinge subsystem: Based on the force analysis of the hinge, the damage is described by the deformation at the connection point between the hinge and the pulling rope. Since the hinge is a rigid body in the model and does not deform, the damage is characterized by the position change of the connection point, that is, the deformation parameter at the connection point between the hinge and the pulling rope.

[0127] Figure 2 It is a schematic diagram of the method for determining the damage coefficient of the hinge subsystem provided by the present invention. As Figure 2 shown, the vertical line represents the original position of the connection point between the hinge and the pulling rope, and the inclined line represents the state position after deformation of the connection point between the hinge and the pulling rope. Then the deformation parameter of the connection point can be expressed as: R*θ. Then the damage coefficient D1 = θ1 / θ0, 0 ≤ θ1 ≤ θ0, 0 ≤ D1 ≤ 1. R represents the radial distance from the hinge center to the pulling rope connection point, which is used to convert the angular change θ into an actual displacement.

[0128] 2) Regarding the pulling rope damage coefficient D2 corresponding to the pulling rope spring subsystem: Considering that the pulling rope in the pulling rope spring subsystem is composed of a steel wire rope wrapped with nylon, and its force is mainly borne by the steel wire rope, which is in a pure tensile state. Therefore, in the present invention, the change in the stiffness of the pulling rope is used to characterize a target parameter for judging the damage of the pulling rope spring subsystem.

[0129] Specifically, define the initial stiffness of the pulling rope as K0, and its stiffness after multiple switches at any discrete time point is K1. Then the damage coefficient D2 of this target parameter of the pulling rope spring subsystem at this discrete time point can be defined as D2 = (K0 - K1) / K0. Where 0 ≤ K1 ≤ K0, 0 ≤ D2 ≤ 1.

[0130] 3) Regarding the pulling rope damage coefficient D3 corresponding to the pulling rope spring subsystem: At the same time, the present invention also considers that the change in the stiffness of the telescopic spring in the pulling rope spring subsystem is also an important target parameter reflecting the damage degree of this subsystem. Its corresponding damage formula can be expressed as: D3 = (K2 - K3) / K2, where 0 ≤ K3 ≤ K2, and 0 ≤ D3 ≤ 1. Where the initial stiffness of the telescopic spring is K2, and its stiffness after multiple switches at any discrete time point is K3.

[0131] 4) Regarding the sealing strip damage coefficient D4 corresponding to the sealing subsystem: The sealing strip only generates a certain resilience when the door body is opened instantaneously. After the door body is separated from the skeleton subsystem, the resilience of the sealing strip disappears. Therefore, for the determination of the damage coefficient of the sealing subsystem, it is related to a specific damage behavior simulation model, and its most direct target parameter is the change in the stiffness of the sealing strip.

[0132] Figure 3 The following is a schematic diagram of the stiffness curve of the sealing strip provided by the present invention, wherein the horizontal axis represents the compression deformation of the sealing strip when subjected to an external force, usually expressed in length units (such as millimeters or inches), and the vertical axis represents the force applied to the sealing strip, usually expressed in force units (such as Newtons or pounds). Figure 3 As shown in the figure, the sealing strip stiffness curve describes the force response of the sealing strip under different compression deformations, reflecting the stiffness characteristics of the sealing strip. The slope of the stiffness curve (i.e. the ratio of force to compression deformation) reflects the stiffness of the sealing strip. The larger the slope of the stiffness curve, the harder the sealing strip; the smaller the slope of the stiffness curve, the softer the sealing strip.

[0133] Therefore, when performing the scaling coefficient of the target parameter related to the door body damage of the sealing subsystem at any discrete time point, the present invention quantifies the damage degree of the sealing strip and determines the corresponding damage coefficient D4, where D4=0 indicates that the sealing strip is not damaged, and D4=1 indicates that the sealing strip is completely ineffective.

[0134] Furthermore, the scaling factor of the sealing strip stiffness curve can be calculated according to the damage coefficient D4: S4=1-D4. For example, if D4=0.2, the scaling factor of the sealing strip stiffness curve=0.8.

[0135] Then, at each discrete time point, the sealing strip stiffness curve can be updated according to the scaling factor S4: K5 = K4 × S 4, where K4 is the initial stiffness curve slope of the sealing strip, and K5 is the updated stiffness curve slope.

[0136] By running the door system simulation model using the updated stiffness curve, a damage behavior simulation model at that discrete time point can be obtained.

[0137] 5) Regarding the spring damage coefficient D5 corresponding to the lock subsystem: At the initial moment of opening the door, the door opening force is mainly composed of the locking force generated by the lock, which is mainly the tension caused by the deformation of the locking spring. The damage of the entire lock subsystem can be understood as being mainly caused by the locking spring. Furthermore, the change in the locking spring stiffness in the door system simulation model can be defined to associate it with the corresponding damage coefficient.

[0138] Specifically, the initial stiffness of the locking spring can be defined as K6, the stiffness after multiple switches can be defined as K7, and the damage coefficient D5=(K6-K7) / K6, where 0≤K7≤K6, and 0≤D5≤1.

[0139] Based on the above description, the construction of a 3D parametric damage behavior simulation model considering damage evolution can be completed. A total of 5 target parameters D1 - D5 associated with each core component of the door body are set. At each discrete time point, according to the number of door openings, the corresponding damage coefficients D1 - D5 are calculated. Then, according to the above definitions of the damage coefficients, the simulation model of the door body system is automatically updated to obtain corresponding damage behavior simulation models one by one.

[0140] The method for constructing the door body damage detection model provided by the present invention determines the damage coefficient based on the current number of openings and closings of each core component of the door body and the fatigue opening and closing limit value, and updates the target parameters in the simulation model of the door body system according to the damage coefficient, so as to obtain the damage behavior simulation model under different damage states. This process provides detailed damage state data for the subsequent construction of the door body damage detection model, ensuring that the model can accurately reflect the dynamic behavior of the door body system at different usage stages.

[0141] Based on the content of the above embodiments, as an alternative embodiment, training the initial network model with any training data in the training dataset to obtain the door body damage detection model includes: According to the preset time sequence, sequentially input the training data corresponding to each discrete time point into the initial network model to obtain an opening force prediction sequence output by the initial network model; According to the network error between the opening force prediction sequence and the opening force label sequence, gradually update the model parameters of the initial network model until the model converges to obtain the door body damage detection model; The opening force label sequence is composed of the opening forces at all discrete time points in the preset time sequence.

[0142] When directly performing door body damage detection calculations based on all the damage behavior simulation models obtained by the methods mentioned in the above embodiments, there are limitations such as low calculation efficiency, limited generalization ability, and complex data processing. In particular, these door body damage detection models are usually based on physical equations and complex mechanical calculations. Each time the simulation model is run, a large amount of computing resources and time are required, and the amount of generated data is usually very large. Especially when considering multiple discrete time points and multiple damage states, processing and analyzing these data require complex algorithms and a large amount of computing resources, and they cannot become digital twin models applicable to actual situations.

[0143] The present invention creatively adopts a deep learning network structure algorithm to train the data generated by the 3D parametric damage behavior simulation model, and outputs a reduced - order damage behavior simulation model considering damage behavior as the digital twin model of the door body system considering damage evolution.

[0144] As an alternative embodiment, the present invention selects the Long Short-Term Memory (LSTM) network as the basic architecture of the initial network model because the LSTM can effectively process time series data and capture the time dependencies in the input data. However, in actual application, other network models can also be considered as the basic model architecture for training to obtain the door body damage detection model. For example, the Recurrent Neural Network (RNN), Gated Recurrent Unit (GRU), Transformer network model can be used, or in scenarios with higher detection accuracy requirements, a hybrid model composed of multiple network models can be used as the basic model architecture.

[0145] Figure 4 is a schematic diagram of the training process of the door body damage detection model provided by the present invention. The following will be combined with Figure 4 As shown, taking the use of LSTM as the basic model architecture as an example, it will be described in detail how to implement the training of the door body damage detection model. It mainly includes but is not limited to the following steps: Step 1: Based on the method provided in the foregoing embodiment, obtain the damage behavior simulation model corresponding to each discrete time point, so as to generate a training data set by using these damage behavior simulation models. Each data sample in the training data set includes input data and label data. Among them, the input data is the opening angle data at a discrete time point and the damage coefficients of each core component of the door body, and the corresponding label data is the corresponding opening force data.

[0146] Specifically, taking the door body system of a general dishwasher as an example, its entire life cycle will probably run about 50,000 times. Every 1000 times (select different sampling frequencies according to the actual situation), take the door body system simulation model once. According to the assumptions and methods provided in the above embodiment, the damage value coefficients of each subsystem (core component of the door body) of each door body system simulation model can be obtained. According to the damage coefficients, a damage behavior simulation model corresponding to a door body system simulation model can be obtained. In this way, 50 door body system simulation models can be obtained. Input all the door body system simulation models into MotionSolve for solution to obtain the opening force time series data set of the dishwasher. Based on these opening force time series data sets, a training data set for the improved LSTM deep learning neural network algorithm can be constructed.

[0147] Step 2: Select an LSTM network as the basic architecture of the initial network model. Its input layer can receive the opening angle and the damage coefficients of each core component of the door body. The LSTM layer processes the time series data and extracts the time-dependent features, and its output layer outputs the predicted opening force.

[0148] Step 3: Input the training data corresponding to each discrete time point into the initial network model in sequence according to the preset time sequence, including recording the input data and label data of each discrete time point from the training dataset, and input the input data (opening angle and damage coefficient) among them into the initial network model.

[0149] Run the initial network model to obtain the predicted opening force sequence output by it, that is, use the initial network model to infer the input data and generate the predicted opening force sequence (collect the prediction results of each discrete time point to form a complete predicted opening force sequence).

[0150] Step 4: Calculate the network error according to the difference between the predicted sequence and the label sequence. Obtain the true opening force data of each discrete time point from the training dataset to form the opening force label sequence. Use the mean square error (MSE) or other statistical metrics to calculate the network error between the predicted sequence and the label sequence, for example: ; where N is the total number of discrete time points, and respectively represent the opening force error at the i-th discrete time point.

[0151] Step 5: According to the calculated network error, the parameters of the initial network model can be gradually updated until the model converges. The specific steps include: 1) Use the backpropagation algorithm to calculate the gradient of the error with respect to the model parameters.

[0152] 2) Use an optimization algorithm (such as Adam) to update the model parameters according to the gradient.

[0153] 3) Repeat the above process until the network error no longer decreases significantly and the model converges.

[0154] Step 6: After the above training process, the parameters of the initial network model are gradually optimized, and finally a high-precision door body damage detection model is obtained. This door body damage detection model can accurately predict the corresponding opening force according to the input opening angle and damage coefficient, so as to realize the real-time detection of the door body damage state.

[0155] The method for constructing the door body damage detection model provided by the present invention trains the initial network model using the training dataset, gradually optimizes the model parameters, and finally obtains a high-precision door body damage detection model, which can significantly improve the calculation efficiency, enhance the generalization ability, simplify the data processing, and meet the requirements of real-time monitoring and complex working conditions adaptation, and is a key step to realize efficient and accurate door body damage detection.

[0156] Figure 5It is a schematic structural diagram of a device for constructing a door body damage detection model provided by the present invention, as Figure 5 shown, mainly including but not limited to: A damage behavior simulation model construction unit 51, configured to construct a damage behavior simulation model for each of the discrete time points based on physical calibration data and damage coefficients of each core component of the door body at each discrete time point in a preset time sequence.

[0157] Among them, the physical calibration data is obtained by performing physical opening and closing experiments on each core component of a real physical door body; An initial network model training control unit 52, configured to train an initial network model using a training data set to obtain the door body damage detection model.

[0158] Among them, any training data in the training data set includes the opening angle of a damage behavior simulation model at its corresponding discrete time point and the damage coefficients of each core component, and the label of the training data is the opening force at the discrete time point.

[0159] It should be noted that when the device for constructing the door body damage detection model provided by the present invention is specifically operated, it can implement the method for constructing the door body damage detection model provided in any of the above embodiments, which will not be elaborated here one by one.

[0160] The device for constructing the door body damage detection model provided by the present invention calibrates the simulation model through a designed model experiment, and at the same time establishes a 3D parametric damage behavior simulation model considering damage. Finally, the discrete damage behavior simulation model is reduced in order through deep learning to obtain a network model that can quickly and accurately monitor the door body damage in real time, filling a gap in the industry.

[0161] In order to fully illustrate the advantages of the method for constructing the door body damage detection model provided by the present invention in actual detection, the following will be described in detail in combination with relevant test data.

[0162] Figure 6 It is one of the schematic diagrams of the performance of the door body damage detection model provided by the present invention in the training data set, Figure 7 It is the second schematic diagram of the performance of the door body damage detection model provided by the present invention in the training data set, Figure 8 It is the third schematic diagram of the performance of the door body damage detection model provided by the present invention in the training data set, Figure 9 It is the fourth schematic diagram of the performance of the door body damage detection model provided by the present invention in the training data set, Figure 10It is the fifth schematic diagram of the performance of the door damage detection model provided by the present invention in the training dataset. Among them, the abscissa represents the time step, and each unit corresponds to 0.025 seconds. For example, 400 on the abscissa represents 10 seconds; the ordinate represents the numerical values of the predicted value and the actual value. For example, in the case of representing the opening force, angle or other relevant parameters, the unit is Newton (N). One of the two force time series curves represents the predicted value, and the other represents the actual value (the dotted line represents the predicted value, and the solid line represents the actual value).

[0163] Among them, during Figures 6-10 the training process of the initial network model shown, the total number of door openings (the data scale in the training dataset) is 20,900, 27,100, 34,800, 4,200, and 9,700 respectively. Mainly through the comparison relationship between the predicted value and the actual value, the abscissa also represents the time step, and the ordinate represents the opening force. The force time series curve fully demonstrates the convergence of the door damage detection model during the training process, and can effectively prove that the door damage detection model obtained through a finite number of trainings has a high prediction accuracy.

[0164] Figure 11 It is one of the schematic diagrams of the performance of the door damage detection model provided by the present invention in the test dataset, Figure 12 It is one of the schematic diagrams of the performance of the door damage detection model provided by the present invention in the test dataset, Figure 13 It is one of the schematic diagrams of the performance of the door damage detection model provided by the present invention in the test dataset, Figure 14 It is one of the schematic diagrams of the performance of the door damage detection model provided by the present invention in the test dataset, Figure 15 It is one of the schematic diagrams of the performance of the door damage detection model provided by the present invention in the test dataset. Among them, the abscissa of the coordinate system where the force time series curve is located represents the time step, and the ordinate represents the numerical value of the opening force.

[0165] Among them, during Figures 11-15 the training process of the initial network model shown, the total number of door openings (the data scale in the test dataset) is 10,400, 11,400, 12,200, 12,900, and 13,600 respectively. Mainly through the comparison relationship between the predicted value and the actual value, the convergence of the door damage detection model during the test process is demonstrated, which can help evaluate the generalization ability and prediction accuracy of the model on unseen data. Through the verification of the test dataset, it can be determined that the door damage detection model obtained by the present invention has good generalization and has a high prediction accuracy.

[0166] Figure 16 It is one of the schematic diagrams of the evolution of the loss function value during the training process of the door damage detection model provided by the present invention, Figure 17This is the second schematic diagram showing the evolution of the loss function value during the training process of the door body damage detection model provided by the present invention. Among them, the abscissa represents the number of iterations, and the ordinate represents the loss function value. The curve is mainly used to show the change of the loss function value as the number of training iterations increases. If the loss function value drops rapidly and tends to be stable, it indicates that the model converges quickly. The fact that the loss function value finally tends to a small value indicates that the training effect of the model is good.

[0167] Reference Figures 16-17 As shown, the loss function value Loss error of the door body damage detection model reaches 2.53 at the 171st step, and the convergence accuracy is very high. Thus, a deep learning network model with a very high fitting accuracy is obtained, which is used as the digital twin model of the damage behavior of the dishwasher door body system.

[0168] The above experiments fully prove the construction method of the door body damage detection model provided by the present invention, and a LSTM deep learning network model with a very high fitting accuracy is obtained, which has the ability to effectively utilize temporal features and solve the problem of long-term temporal prediction.

[0169] Figure 18 This is the structural schematic diagram of the electronic device provided by the present invention. As Figure 18 shown, the electronic device may include: a processor 1810, a communication interface 1820, a memory 1830, and a communication bus 1840. Among them, the processor 1810, the communication interface 1820, and the memory 1830 complete communication with each other through the communication bus 1840. The processor 1810 can call the logical instructions in the memory 1830 to execute the construction method of the door body damage detection model, and the method includes: constructing a damage behavior simulation model for each of the discrete time points based on the physical calibration data and the damage coefficients of each core component of the door body at each discrete time point in a preset time sequence; the physical calibration data is obtained by performing physical opening and closing experiments on each core component of the real physical door body; training an initial network model using a training data set to obtain the door body damage detection model; any training data in the training data set includes the opening angle of a damage behavior simulation model at its corresponding discrete time point and the damage coefficients of each core component of the door body, and the label of the training data is the opening force at the discrete time point.

[0170] In addition, when the logical instructions in the above-mentioned memory 1830 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs.

[0171] On the other hand, the present invention also provides a computer program product. The computer program product includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the method for constructing a door body damage detection model provided in the above-mentioned various embodiments. The method includes: constructing a damage behavior simulation model for each of the discrete time points based on physical calibration data and the damage coefficients of each core component of the door body at each discrete time point in a preset time sequence; the physical calibration data is obtained by performing physical opening and closing experiments on each core component of a real physical door body; training an initial network model using a training data set to obtain the door body damage detection model; any training data in the training data set includes the opening angle of a damage behavior simulation model at its corresponding discrete time point and the damage coefficients of each core component of the door body, and the label of the training data is the opening force at the discrete time point.

[0172] In yet another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is configured to execute the method for constructing a door body damage detection model provided in the above-mentioned various embodiments. The method includes: constructing a damage behavior simulation model for each of the discrete time points based on physical calibration data and the damage coefficients of each core component of the door body at each discrete time point in a preset time sequence; the physical calibration data is obtained by performing physical opening and closing experiments on each core component of a real physical door body; training an initial network model using a training data set to obtain the door body damage detection model; any training data in the training data set includes the opening angle of a damage behavior simulation model at its corresponding discrete time point and the damage coefficients of each core component of the door body, and the label of the training data is the opening force at the discrete time point.

[0173] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0174] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0175] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or equivalently replace some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for constructing a door body damage detection model, characterized in that Including: Construct a damage behavior simulation model for each discrete time point based on physical calibration data and the damage coefficients of each core component of the door body at each discrete time point in a preset time sequence; the physical calibration data is obtained from physical opening and closing experiments on each core component of the real physical door body. Train an initial network model using a training data set to obtain the door body damage detection model; any training data in the training data set includes the opening angle of a damage behavior simulation model at its corresponding discrete time point and the damage coefficients of each core component of the door body, and the label of the training data is the opening force at the discrete time point.

2. The method for constructing a door body damage detection model according to claim 1, characterized in that The constructing a damage behavior simulation model for each discrete time point based on physical calibration data and the damage coefficients of each core component of the door body at each discrete time point in a preset time sequence includes: Use the physical calibration data to calibrate each non-damaged simulation model one by one to obtain a normal behavior simulation model for each core component of the door body. Aggregate the normal behavior simulation models to form a door body system simulation model. Update the door body system simulation model according to the damage coefficients of each core component of the door body at each discrete time point in the preset time sequence to obtain the damage behavior simulation models in different damage states at each discrete time point.

3. The method for constructing a door body damage detection model according to claim 2, wherein, The physical calibration data includes force time sequence curve samples obtained from physical opening and closing experiments with angle control for each core component of the door body respectively. The using the physical calibration data to calibrate each non-damaged simulation model one by one to obtain a normal behavior simulation model for each core component of the door body includes: For the non-damaged simulation model of any core component of the door body, adjust the model parameters of the non-damaged simulation model according to the curve difference between the virtual force time sequence curve output by the non-damaged simulation model and the force time sequence curve sample until the curve difference is within a preset range, and obtain the adjusted non-damaged simulation model as the normal behavior simulation model.

4. The method for constructing a door body damage detection model according to any one of claims 2-3, characterized in that, The core components of the door body include an outer door subsystem and all key subsystems, and the key subsystems include one or more of a hinge subsystem, a cable spring subsystem, a lock subsystem, and a sealing subsystem; the hinge subsystem is composed of a skeleton subsystem and an outer door subsystem. Correspondingly, the non-damaged simulation models include an outer door subsystem simulation model, a hinge subsystem simulation model, a cable spring subsystem simulation model, a lock subsystem simulation model, and a sealing subsystem simulation model.

5. The method for constructing a door body damage detection model according to claim 4, wherein The aggregating the normal behavior simulation models to form a door body system simulation model includes: Fuse the normal behavior simulation models of the outer door subsystem, the hinge subsystem, the cable spring subsystem, the lock subsystem, and the sealing subsystem corresponding to the outer door subsystem simulation model, the hinge subsystem simulation model, the cable spring subsystem simulation model, the lock subsystem simulation model, and the sealing subsystem simulation model to obtain the door body system simulation model.

6. The method for constructing a door body damage detection model according to claim 5, wherein, Updating the door system simulation model according to the damage coefficients of each door core component at each discrete time point in the preset time sequence, and obtaining the damage behavior simulation models in different damage states at each discrete time point, including: Determining the damage coefficient of any door core component at any discrete time point based on the current opening and closing times of the any door core component at the any discrete time point and the fatigue opening and closing times limit value of the any door core component; Determining the scaling coefficient of the target parameter related to the door damage of the any door core component based on the damage coefficient; At the any discrete time point, updating the door system simulation model according to the scaling coefficients of the target parameters related to the door damage of all door core components, and obtaining the damage behavior simulation model at the any discrete time point; Traversing all the discrete time points to obtain all the damage behavior simulation models.

7. The method for constructing a door body damage detection model according to claim 6, characterized in that The target parameters of the hinge subsystem include the deformation parameters at the connection point of the hinge and the pulling rope, the target parameters of the pulling rope spring subsystem include the pulling rope stiffness and the telescopic spring stiffness, the target parameters of the lock subsystem include the locking spring stiffness, and the target parameters of the sealing subsystem include the sealing strip stiffness.

8. The method for constructing a door body damage detection model according to claim 1, wherein Training the initial network model with any training data in the training dataset to obtain the door damage detection model, including: Sequentially inputting the training data corresponding to each discrete time point into the initial network model according to the preset time sequence, and obtaining the opening force prediction sequence output by the initial network model; Gradually updating the model parameters of the initial network model until the model converges according to the network error between the opening force prediction sequence and the opening force label sequence, and obtaining the door damage detection model; The opening force label sequence is composed of the opening forces at all discrete time points in the preset time sequence.

9. The method for constructing a door body damage detection model according to claim 1, wherein The initial network model is obtained based on the long short-term memory network model as the basic model architecture.

10. An apparatus for constructing a door body damage detection model, characterized in that, Including: A damage behavior simulation model construction unit, configured to construct a damage behavior simulation model for each discrete time point based on physical calibration data and the damage coefficients of each door core component at each discrete time point in the preset time sequence; the physical calibration data is obtained by performing physical opening and closing experiments on each door core component of a real physical door; An initial network model training control unit, configured to train the initial network model with the training dataset to obtain the door damage detection model; any training data in the training dataset includes the opening angle of a damage behavior simulation model at its corresponding discrete time point and the damage coefficients of each core component, and the label of the training data is the opening force at the discrete time point.

11. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, the construction method of the door damage detection model according to any one of claims 1 to 9 is implemented.

12. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the construction method of the door damage detection model according to any one of claims 1 to 9 is implemented.

13. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method for constructing the door body damage detection model according to any one of claims 1 to 9.

Images