Safe battery swapping system applying new energy automobile battery swapping station

Abstract

The invention belongs to the technical field of battery swap monitoring, and provides a safe battery swap system applying a new energy automobile battery swap station, which comprises the steps that a safety sensing module constructs a stress concentration sequence and identifies a stress distribution concentration cluster by collecting a stress concentration coefficient of a battery swap working surface contact point; the grading module collects electric heating characteristic parameters of the stress distribution set cluster, adopts radial basis function fitting to form an early warning curved surface, and divides a power conversion risk grade by calculating a cross-border ratio; the capability matching module constructs a protection vector, compares the protection vector with a target feature vector, and judges whether the protection feature is matched with the risk level; if yes, the shrinkage analysis module constructs a border-crossing shrinkage model based on historical data, inputs a real-time protection vector to obtain a border-crossing ratio shrinkage degree, and draws a shrinkage track on the early warning curved surface. According to the invention, risk grading early warning and protection capability dynamic matching in the battery replacement process are realized, and the battery replacement safety is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of battery swapping monitoring, and specifically relates to a safe battery swapping system applied to a new energy vehicle battery swapping station. Background Art

[0002] With the rapid development of the new energy vehicle industry, battery swapping has become an important technological solution to addressing electric vehicle range anxiety due to its efficient and convenient energy replenishment advantages. However, the battery swap process involves high-risk operations such as battery plugging and unplugging, high-voltage electrical connections, and mechanical transmission, and faces multiple safety challenges.

[0003] The existing battery swap station protection system fails to differentiate between active and passive protection mechanisms, employing a unified strategy that results in excessive resource consumption in low-risk areas and insufficient protection in high-risk areas. Active and passive protection operate independently, lacking dynamic matching and evaluation. Under extreme operating conditions, passive protection cannot provide a sufficient safety window, easily leading to the spread of disasters. Existing technologies lack a three-dimensional risk trajectory display, making it difficult to identify key causes during accident review, resulting in a lack of targeted corrective measures. Summary of the Invention

[0004] In order to make up for the deficiencies of the prior art, at least one technical problem raised in the background technology is solved.

[0005] The technical solution adopted by the present invention to solve the technical problem is: a safe battery swap system using a new energy vehicle battery swap station, including the following modules:

[0006] Safety perception module: collects stress concentration coefficients at contact points and constructs stress concentration sequences. It establishes a dynamic baseline for the stress concentration sequences and performs synchronous identification analysis to obtain stress distribution concentration clusters.

[0007] Level classification module: This module collects the electrothermal characteristic parameters of the stress distribution cluster and performs function fitting to form a warning surface. It then constructs a three-dimensional input vector for fitting analysis to determine whether the three-dimensional input vector breaks through the warning surface boundary. If so, it calculates the boundary crossing ratio of the warning surface and classifies the battery replacement risk level.

[0008] Capability matching module: Based on the determined battery swap risk level, it extracts the protection features of the battery swap interface and performs capability matching analysis to determine whether the protection features of the battery swap interface match the risk level;

[0009] Contraction analysis module: If there is a match, an out-of-bounds contraction model is constructed, the current active and passive protection vectors are input into the out-of-bounds contraction model, the contraction degree of the out-of-bounds ratio is obtained, and the out-of-bounds contraction trajectory is drawn.

[0010] Furthermore, the method of establishing a dynamic baseline for the stress concentration sequence and performing synchronous identification analysis is as follows:

[0011] Obtain the stress concentration coefficient of each contact point on the battery swapping contact surface at the current moment and multiple historical moments, and construct a stress concentration sequence;

[0012] A graph convolutional autoencoder is used to perform unsupervised learning on the stress concentration sequence of each contact point, and a dynamic baseline model with time dependency and spatial correlation is constructed:

[0013] The dynamic baseline model is trained to reconstruct the stress concentration sequence, and the reconstruction error of the real-time sequence is used as the anomaly score;

[0014] Based on the sliding time window and the anomaly scores of spatially adjacent contact points, the stress distribution clusters are identified.

[0015] Furthermore, the stress concentration factor is obtained as follows:

[0016] The contact pressure factors of different contact points on the battery exchange contact surface are obtained for numerical analysis to obtain the stress concentration coefficient of the contact point.

[0017] Furthermore, the method of performing function fitting to form the warning surface is:

[0018] Obtain the stress concentration coefficient within the stress distribution cluster of the battery swap contact surface, as well as the contact resistance of multiple contact points within the stress distribution cluster, and perform evidence consistency verification;

[0019] Obtain the stress concentration coefficient, contact resistance, and temperature gradient between adjacent contact points of the stress concentration cluster on the historical battery swap contact surface after evidence consistency verification, and construct a three-dimensional input vector;

[0020] The three-dimensional input vector is fitted with a function to obtain a warning surface including stress concentration factor, resistance and temperature gradient.

[0021] Furthermore, the method for calculating the cross-boundary ratio of the warning surface is:

[0022] The three-dimensional input vector acquired in real time is input into the fitting function. If the output of the fitting function exceeds the surface boundary, the Euclidean distance to the surface boundary is calculated based on the output of the fitting function to obtain the out-of-bounds margin.

[0023] Calculate the Euclidean distance from the center point of the surface to the output of the fitting function to obtain the out-of-bounds distance;

[0024] The out-of-bounds margin is ratioed to the out-of-bounds length to obtain the out-of-bounds ratio.

[0025] Furthermore, the method of performing capability matching analysis is:

[0026] The protection of the battery swap interface is divided into active protection and passive protection. The active redundancy coefficient and active response coefficient under active protection are obtained and combined to obtain the active protection vector.

[0027] Obtain the thermal resistance coefficient and thermal redundancy coefficient in passive protection, combine the thermal resistance coefficient and thermal redundancy coefficient to construct a passive protection vector;

[0028] Perform feature overlimit calculation on active protection vectors and passive protection vectors to obtain safety matching values;

[0029] A comparison is performed based on the safety matching value to determine whether the protection features of the battery swap interface match the risk level.

[0030] Furthermore, the active response coefficient and the active redundancy coefficient are obtained as follows:

[0031] Obtain the content of fire extinguishing agent for active protection of the battery swapping operation surface, and obtain the average usage of fire extinguishing agent at the current risk level from historical data;

[0032] The active redundancy coefficient is obtained by comparing the average amount of fire extinguishing agent used at the current risk level with the content of fire extinguishing agent in active protection.

[0033] The number of successful warnings and the total number of warnings under the current risk level are obtained from historical data, and the ratio is processed to obtain the active response coefficient.

[0034] Furthermore, the method of performing feature overlimit calculation is:

[0035] Obtain the target feature vector, and calculate the Chebyshev distance between the target feature vector and the active protection vector as the feature excess value between the target feature vector and the active protection vector;

[0036] The Chebyshev distance between the target feature vector and the passive protection vector is calculated as the feature excess value between the target feature vector and the passive protection vector.

[0037] Furthermore, the method for obtaining the shrinkage degree of the cross-boundary ratio is:

[0038] Obtain multiple active and passive protection vectors of different risk levels from historical data and establish a protection feature matrix;

[0039] Based on the protection feature matrix and the corresponding out-of-bounds ratio, an out-of-bounds shrinkage model is constructed and trained;

[0040] The real-time active protection vector and passive protection vector are input into the out-of-bounds contraction model, and the out-of-bounds contraction model outputs the predicted out-of-bounds ratio under the current active protection vector and passive protection vector;

[0041] The deviation is calculated based on the predicted out-of-bounds ratio to obtain the contraction degree of the out-of-bounds ratio. Based on the contraction degree of the out-of-bounds ratio, the contraction trajectory of the out-of-bounds ratio is drawn on the warning surface.

[0042] Furthermore, the deviation calculation is performed as follows:

[0043] The predicted out-of-bounds ratio output by the out-of-bounds shrinkage model is obtained, and the deviation ratio is calculated with the out-of-bounds ratio of the current battery swapping operation surface to obtain the shrinkage degree of the out-of-bounds ratio.

[0044] The beneficial effects of the present invention are as follows:

[0045] 1. Collect the stress concentration coefficient of the battery exchange operation surface to build a dynamic baseline model, realize the spatiotemporal correlation analysis of the stress anomaly of the contact interface, identify the stress distribution cluster in advance, and warn of risk precursors such as sudden increase in contact resistance and material fatigue. For safety monitoring, use radial basis function to fit the warning surface, quantify the risk level through the out-of-bounds ratio, realize nonlinear coupling relationship modeling of high-risk scenarios such as thermal runaway, and improve the accuracy of risk prediction.

[0046] 2. Split the protection system into active protection and passive protection. By constructing active protection vectors and passive protection vectors, differentiated protection capability assessments for different risk levels can be achieved. By calculating characteristic over-limit values ​​and determining safety matching values, the compatibility of protection measures with risk levels can be verified in real time, reducing resource waste (such as reducing fire extinguishing agent consumption at low risks) or insufficient capabilities (such as triggering redundant protection activation at high risks), thereby achieving optimal configuration of protection resources.

[0047] 3. Construct an out-of-bounds contraction model based on historical data to quantify the inhibitory effect of the protection vector on the out-of-bounds ratio. Support the predicted contraction degree of the out-of-bounds ratio and the actual out-of-bounds ratio, provide data support for the dynamic adjustment of the warning threshold and the optimization of the local protection strategy, draw the contraction trajectory of the risk point on the warning surface, and intuitively display the evolution path of the risk indicators (stress, resistance, temperature) to the safe area under the protection intervention, assisting operation and maintenance personnel to quickly locate weak links and improve decision-making efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The present invention will be further described below with reference to the accompanying drawings.

[0049] Figure 1 This is a module diagram of a safe battery swapping system using a new energy vehicle battery swapping station according to an embodiment of the present invention;

[0050] Figure 2 This is a flow chart for determining whether the protection features of the battery swap interface according to an embodiment of the present invention match the risk level;

[0051] Figure 3This is a flow chart of a safe battery replacement method using a new energy vehicle battery replacement station according to an embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to make the technical means, creative features, objectives and effects achieved by the present invention easier to understand, the present invention is further described below in conjunction with specific implementation methods.

[0053] Example 1

[0054] See also Figure 1 As shown, a safe battery swapping system using a new energy vehicle battery swapping station according to an embodiment of the present invention includes the following modules:

[0055] Safety perception module: In the battery swapping operation surface, the stress concentration coefficient of the contact point is collected and a stress concentration sequence is constructed. A dynamic baseline is established for the stress concentration sequence and synchronous identification analysis is performed to obtain stress distribution concentration clusters.

[0056] Among them, the method of collecting the stress concentration factor of the battery replacement operation surface is:

[0057] It should be explained that the battery swap operation area refers to the core operation area for battery replacement of new energy vehicles, including the vehicle compartment during battery swap (the closed or semi-enclosed space where the vehicle is parked and the battery is loaded and unloaded) and the battery transportation and installation facility area (such as the area where the battery swap robot arm, battery transport track, loading and unloading interface and other equipment are located);

[0058] The battery swapping operation area is where high-risk operations such as battery plugging and unplugging, electrical connections, and mechanical transmission are concentrated. Intelligent monitoring and early warning systems (such as six-dimensional force sensors and infrared thermal imaging) are required to monitor mechanical stress (plugging and unplugging force, torque) and temperature anomalies (precursors of thermal runaway) in real time. At the same time, full-scene spraying facilities (such as follow-up nozzles and targeted spray pipelines) are equipped to suppress early fires. This is the core control area for safety protection in battery swapping stations and is directly related to the safety of vehicles, batteries, and operators during the battery swapping process.

[0059] Preferably, a six-dimensional force sensor is integrated into the end effector of the battery-swapping robot arm on the battery-swapping operation surface to synchronously measure the z-axis force of the contact point of the battery-swapping contact surface in the new energy battery-swapping process, that is, F z (t);

[0060] By formula: Obtain the contact pressure factor P of the contact point, where A is the electrode contact area;

[0061] By formula: Get the stress concentration factor K of contact point i on the battery swap contact surface t (i)

[0062] in, is the contact pressure of the i-th contact point on the battery swapping contact surface at time t, Represents the average contact pressure factor of the contact interface at all contact points at time t;

[0063] It needs to be explained that the physical meaning of calculating the stress concentration factor is to measure stress unevenness: K t Reflects the degree of stress concentration in the contact interface or local area of ​​the component. t =1, indicating that the stress is evenly distributed; K t >1 indicates that there is local stress concentration, and the larger the value, the more significant the stress concentration; for example, during the plugging and unplugging of the battery-swapping robot arm, if K t >1.8, indicating that the local stress at the contact interface is far above the average level;

[0064] Assessing structural risks: Stress concentration factor is a key indicator for judging structural safety and reliability. High Kt value will accelerate material fatigue, induce micro crack propagation (such as metal fatigue at the contact interface of the battery), and even lead to plastic deformation or fracture. By monitoring Kt t , can provide early warning of abnormalities in the contact interface, avoiding chain reactions such as sudden increase in contact resistance and thermal runaway caused by stress concentration;

[0065] Obtain the stress concentration coefficient of each contact point on the battery swapping contact surface at the current moment and multiple historical moments, and construct a stress concentration sequence;

[0066] Establish a dynamic baseline for the stress concentration sequence and perform simultaneous identification analysis to identify the stress distribution concentration clusters on the battery swap contact surface;

[0067] Among them, the method of establishing a dynamic baseline for the stress concentration sequence and performing synchronous identification analysis is:

[0068] Preferably, a graph convolutional autoencoder (GCAE) is used to perform unsupervised learning on the stress concentration sequence of each contact point, and a dynamic baseline model that includes temporal dependency and spatial correlation (graph convolution aggregated neighborhood features) is constructed:

[0069] The dynamic baseline model is trained under normal working conditions to reconstruct the stress concentration sequence, and the reconstruction error of the real-time stress concentration sequence is used as the anomaly score;

[0070] Identify stress distribution clusters based on the anomaly scores of spatially adjacent contact points within a sliding time window;

[0071] It needs to be explained that each contact point of the battery swap contact surface is modeled as a graph structure, with the contact points as nodes and the spatial adjacent relationships as edges, to construct a spatiotemporal graph data containing the node stress concentration sequence; then a graph convolutional autoencoder (GCAE) is designed, and the spatial correlation features of adjacent nodes are aggregated through the graph convolution layer (GCN), combined with the long short-term memory network (LSTM) or time convolution layer in the time dimension to capture the time dependency of the sequence, and the model is trained unsupervised under normal working conditions. The stress concentration sequence is reconstructed through the autoencoder and the reconstruction error is minimized to establish a dynamic baseline; during real-time monitoring, the stress concentration sequence of the current contact point is input into the trained model, and the reconstruction error between the real-time sequence and the baseline is calculated as the anomaly score. Based on the sliding spatiotemporal window, when the anomaly scores of ≥3 adjacent nodes in 3 consecutive windows exceed 3 times the standard deviation of the baseline, it is identified as a stress distribution concentration cluster, thereby realizing the spatiotemporal correlation analysis of the contact point stress anomaly and the construction of a dynamic baseline;

[0072] For example, when the anomaly scores of ≥3 spatially adjacent contact points in three consecutive sliding spatiotemporal windows all exceed 3 times the standard deviation of the baseline, the three spatially adjacent contact points are identified as a stress distribution concentrated cluster.

[0073] Level classification module: This module collects the electrothermal characteristic parameters of the stress distribution cluster on the battery swapping contact surface, performs function fitting to form a warning surface, constructs a three-dimensional input vector for fitting analysis, and determines whether the three-dimensional input vector exceeds the warning surface boundary. If so, it calculates the boundary crossing ratio of the warning surface and classifies the battery swapping risk level.

[0074] The method for collecting the electrothermal characteristic parameters of the stress distribution cluster on the battery exchange contact surface is as follows:

[0075] Obtain the stress concentration coefficient within the stress distribution cluster of the battery swap contact surface, as well as the contact resistance of multiple contact points within the stress distribution cluster, and perform evidence consistency verification to eliminate invalid data;

[0076] For example, when K t When the value is greater than 2.0 but the contact resistance is less than 50 micro-ohms, the physical law that stress concentration is accompanied by resistance increase is violated, and it is determined to be a sensor data conflict. In this case, a cross-calibration of the six-dimensional force sensor and the contact resistance measurement value is performed;

[0077] After obtaining the evidence consistency check, the stress concentration coefficient, contact resistance and temperature gradient between adjacent contact points of the historical battery exchange contact surface stress concentration cluster are used as electrothermal characteristic parameters, and the stress concentration coefficient K is obtained by function fitting. t , contact resistance Rc, temperature gradient Warning surface;

[0078] It can be understood that by collecting historical battery replacement data to construct a three-dimensional data set including stress concentration factor, contact resistance, and temperature gradient, after denoising and normalizing abnormal samples (such as the working conditions before thermal runaway), the radial basis function (RBF) is used to fit the coupling relationship between parameters. With the critical runaway temperature and the upper safety limit threshold of resistance during historical faults as constraints, an early warning surface with stress, resistance, and temperature gradient as coordinate axes is constructed in three-dimensional space. The surface parameters are optimized through cross-validation, and finally the real-time input parameters are compared with the surface boundary to trigger a graded early warning.

[0079] Among them, when the radial basis function is fitted by using the radial basis function (RBF), the stress concentration factor, contact resistance, and temperature gradient in the historical data are first used as three-dimensional input vectors. , taking the temperature corresponding to the critical state of thermal runaway and the fault label corresponding to the resistance threshold as the output constraint, select the Gaussian kernel RBF basis function ,in is the center generated by the cluster, j is the number of the cluster center, and the weight coefficient w of the basis function is solved by minimizing the weighted mean square error containing the historical fault threshold constraint as the loss function (such as weighted mean square error). j , construct the fitting function ,The fitting function is expressed as a surface formed by nonlinear ,combination of basis functions in three dimensional space, and the boundary of ,the surface is dynamically constrained by the fault threshold;

[0080] The three-dimensional input vector acquired in real time is input into the fitting function, and the output of the fitting function is compared with the surface boundary;

[0081] If the result output by the fitting function exceeds the surface boundary, it is considered that there is a battery swap safety risk on the new energy battery swap contact surface;

[0082] Based on the output of the fitting function, the Euclidean distance closest to the surface boundary is calculated to obtain the out-of-bounds margin;

[0083] Calculate the Euclidean distance from the center point of the surface to the output of the fitting function to obtain the out-of-bounds distance;

[0084] The out-of-bounds margin is processed with the out-of-bounds length to obtain the out-of-bounds ratio;

[0085] It can be understood that the physical significance of constructing the early warning surface is as follows: the early warning surface fits the risk parameter coupling relationship in the historical data through the radial basis function (RBF), and its boundary is dynamically constrained by fault thresholds such as the critical temperature of thermal runaway and the upper limit of resistance safety (for example, the critical temperature of thermal runaway of ternary lithium batteries is about 200°C, and the upper limit of contact resistance safety is 50μΩ). The interior of the early warning surface is the safe area, and the outside of the boundary is the risk area. Breaking the boundary means that the parameter combination triggers the coordinated anomaly of "stress-resistance-temperature", which may lead to the possibility of thermal runaway accidents.

[0086] RBF fitting constructs a nonlinear mapping through the Gaussian kernel function, so that the surface can accurately capture the complex relationship of multi-parameter coupling, and the reliability of the boundary can be guaranteed after cross-validation optimization.

[0087] Out-of-bounds margin (Euclidean distance from a point to the surface boundary): reflects the absolute degree of deviation between the current risk state and the safety boundary. The smaller the distance, the closer it is to the critical value of danger.

[0088] Out-of-bounds distance (Euclidean distance from a point to the center of the surface): measures the overall deviation of the current risk status in three-dimensional space, reducing misjudgments caused by single-dimensional anomalies (for example, when only the temperature gradient is abnormal but the stress and resistance are normal, the out-of-bounds distance is small);

[0089] Breach ratio: By eliminating dimensional differences through dimensionless transformation, the risk position in three-dimensional space is converted into a relative risk indicator between 0 and 1, facilitating cross-scenario comparison and grading (e.g., a breach ratio > 0.6 is considered Level III high risk);

[0090] Based on the numerical value of the out-of-bounds ratio, the battery swapping risk of the battery swapping contact surface is divided into multiple levels, and different levels of battery swapping warning signals are sent to the system.

[0091] The technical solution of this embodiment is: in the battery swapping operation surface, the stress concentration coefficient of the contact point is collected and a stress concentration sequence is constructed, a dynamic baseline is established for the stress concentration sequence, and synchronous identification analysis is performed to obtain a stress distribution concentration cluster; the electrothermal characteristic parameters of the stress distribution concentration cluster of the battery swapping contact surface are collected, and function fitting is performed to form a warning surface, a three-dimensional input vector is constructed for fitting analysis, and it is judged whether the three-dimensional input vector breaks through the warning surface boundary. If it breaks through the warning surface boundary, the out-of-bounds ratio of the warning surface is calculated and the battery swapping risk level is divided; the radial basis function is used to fit the warning surface, and the risk level is quantified by the out-of-bounds ratio to realize nonlinear coupling relationship modeling of high-risk scenarios such as thermal runaway, thereby improving the accuracy of risk prediction.

[0092] Example 2

[0093] like Figure 1 As shown, a safe battery replacement method using a new energy vehicle battery replacement station includes the following steps:

[0094] Capability matching module: Based on the determined battery swap risk level, it extracts the protection features of the battery swap interface and performs capability matching analysis to determine whether the protection features of the battery swap interface match the risk level;

[0095] Among them, the method of extracting the protection features of the battery swap interface is:

[0096] The protection of the battery swap interface is divided into active protection and passive protection;

[0097] It should be explained that active protection includes: the intelligent monitoring and early warning described in Example 1, as well as the full-scene spray system and active fire extinguishing agent intervention of the battery swap interface;

[0098] Passive protection includes: outer insulation materials, new insulation and fireproof structures;

[0099] Protection is divided into active and passive protection, and the action mechanism and response logic of the safety protection of the battery swap interface are classified: Active protection uses real-time monitoring of stress, resistance, and temperature sensors to obtain risk levels and perform corresponding dynamic interventions (such as spray response and pressurization systems) to proactively block the risk evolution chain (such as cooling and extinguishing fires in the early stages of thermal runaway), focusing on pre-emptive prevention and in-process control;

[0100] Passive protection passively slows the spread of disasters through material properties and structural design. For example, low-thermal-conductivity insulation layers and full-coverage spray pipes between battery racks are used to isolate the spread of thermal runaway in single cells. Passive protection focuses on post-event suppression and disaster scale control. Active and passive protection form a complementary system of "actively suppressing risk occurrence while passively limiting risk expansion." This system meets the need for real-time response to high-dynamic risks (such as local overheating caused by a sudden increase in contact resistance) during battery swapping, ensures basic safety under extreme operating conditions (such as spray system failure), and establishes the key logical division of the three-level protection architecture of "prevention-control-disaster reduction."

[0101] Obtain the content of fire extinguishing agent for active protection of the battery swapping operation surface, and obtain the average usage of fire extinguishing agent at the current risk level from historical data;

[0102] The active redundancy coefficient is obtained by comparing the average amount of fire extinguishing agent used at the current risk level with the content of fire extinguishing agent in active protection.

[0103] Obtain the number of successful warnings and the total number of warnings at the current risk level from historical data, perform ratio processing, and obtain the active response coefficient;

[0104] The active redundancy coefficient and the active response coefficient are combined as active protection features to construct the active protection vector XA;

[0105] Obtain the thermal resistance coefficient and thermal redundancy coefficient in passive protection, use the thermal resistance coefficient and thermal redundancy coefficient as passive protection features and combine them to construct the passive protection vector XB;

[0106] It will be understood by those skilled in the art that the thermal resistance coefficient is calculated by measuring the physical parameters of the thermal insulation layer at the battery exchange interface, that is, the thickness of the thermal insulation layer is divided by the thermal conductivity of the material, where the thermal conductivity is obtained by testing the thermal conductivity of the material and the thickness is measured by a measuring instrument;

[0107] The thermal redundancy coefficient is the ratio of the actual thermal resistance of the battery swap interface to the critical thermal resistance at the target risk level. The critical thermal resistance is set according to the risk level, and the redundancy is quantified by comparing the actual thermal resistance with the preset critical value.

[0108] For example, XA=[x1,x2],XB=[x3,x4];

[0109] Among them, x1-x4 are active response coefficient, active response coefficient, thermal resistance coefficient, and thermal redundancy coefficient respectively;

[0110] Obtain the preset target feature vectors YA and YB, where YA = [y1, y2] and YB = [y3, y4], where the elements in the target feature vector correspond one-to-one to the active protection vector and the passive protection vector;

[0111] By formula: Get the characteristic over-limit value D of the target characteristic vector and the active protection vector XA A ;

[0112] By formula: Get the characteristic over-limit value D of the target characteristic vector and the passive protection vector XB B ;

[0113] The characteristic exceeds the limit value D A and D B Perform summation to obtain a safe matching value;

[0114] It can be understood that the purpose of calculating the safety matching value is to systematically evaluate the adaptability of the protection capability of the battery swap interface to the risk level by quantifying the degree of deviation between the active protection vector and the passive protection vector and the preset characteristic vector of the target risk level. Active protection and passive protection form a synergistic complementarity of "suppressing the occurrence of risks and limiting the expansion of risks", providing a basis for the dynamic adjustment of protection strategies (such as resource optimization and maintenance work order generation), and verifying the safety redundancy bottom line under extreme working conditions.

[0115] like Figure 2 As shown, if the safety matching value meets the preset safety matching range value, it is determined whether the protection characteristics of the battery swap interface can match the risk level, otherwise it does not match.

[0116] Contraction Analysis Module: If a match occurs, the historical active and passive protection vectors are obtained and a protection feature matrix is ​​established. A cross-border contraction model is constructed based on the cross-border ratio. The current active and passive protection vectors are input into the cross-border contraction model to obtain the contraction degree of the cross-border ratio and draw the cross-border contraction trajectory.

[0117] It should be explained that the method of drawing the out-of-bounds shrinkage trajectory on the warning surface based on the shrinkage degree of the out-of-bounds ratio is as follows: extracting historical and real-time three-dimensional risk data points (corresponding to the stress concentration factor, contact resistance, and temperature gradient at different times), and calculating the out-of-bounds ratio and shrinkage degree of each point after protective intervention;

[0118] The degree of contraction of the cross-border ratio is mapped to the distance the risk point moves toward the surface safety area (inside) in three-dimensional space (for example, for every 10% contraction of the cross-border ratio, the corresponding coordinates of each dimension are adjusted 5% toward the safety threshold). Arrows are used to connect historical points and current points in the same risk area to form a contraction trajectory.

[0119] By color-coding the degree of contraction (e.g., red indicates no contraction of high risk, green indicates significant contraction of low risk), key nodes (e.g., critical threshold points for thermal runaway, starting points for protective intervention) are marked on the surface. Ultimately, the path of risk points contracting from outside the boundary of the warning surface to the safe area under the action of active and passive protection is dynamically displayed, presenting the inhibitory effect and evolution trend of protective measures on three-dimensional risk indicators.

[0120] It can be understood that the function of calculating the shrinkage degree of the cross-boundary ratio is:

[0121] Function 1: Quantify the protection effect: By comparing the predicted and real-time cross-border ratios, evaluate the extent to which active and passive protection measures suppress risk indicators and measure the degree to which risks converge to safe areas;

[0122] Function 2: Provide data support for dynamically adjusting the warning surface boundary, optimizing sensor layout or protection resource allocation, and realizing adaptive adjustment of protection strategies;

[0123] Function 3: Draw a contraction trajectory on the warning surface to intuitively present the migration path of risk points, and assist operation and maintenance personnel to quickly locate key risk areas and weak links in protection.

[0124] The technical solution of this embodiment is: based on the determined battery swap risk level, the protection features of the battery swap interface are extracted, and a capability matching analysis is performed to determine whether the protection features of the battery swap interface match the risk level; if matched, the historical active and passive protection vectors are obtained and a protection feature matrix is ​​established, and an out-of-bounds shrinkage model is constructed in combination with the out-of-bounds ratio. The current active and passive protection vectors are input into the out-of-bounds shrinkage model to obtain the shrinkage degree of the out-of-bounds ratio and draw the out-of-bounds shrinkage trajectory; the risk point shrinkage trajectory is drawn on the warning surface to intuitively display the evolution path of risk indicators (stress, resistance, temperature) to the safe area under protection intervention, assisting operation and maintenance personnel to quickly locate weak links and improve decision-making efficiency.

[0125] Example 3

[0126] like Figure 3 As shown, a safe battery replacement method using a new energy vehicle battery replacement station includes the following steps:

[0127] S1. In the battery swapping operation surface, the stress concentration coefficient of the contact point is collected and a stress concentration sequence is constructed. A dynamic baseline is established for the stress concentration sequence and synchronous identification analysis is performed to obtain a stress distribution concentration cluster.

[0128] Among them, the method of collecting the stress concentration factor of the battery replacement operation surface is:

[0129] Preferably, a six-dimensional force sensor is integrated into the end effector of the battery-swapping robot arm on the battery-swapping operation surface to synchronously measure the z-axis force of the contact point of the battery-swapping contact surface in the new energy battery-swapping process, that is, F z (t);

[0130] By formula: Obtain the contact pressure factor P of the contact point, where A is the electrode contact area;

[0131] By formula: Get the stress concentration factor K of contact point i on the battery swap contact surface t (i)

[0132] in, is the contact pressure of the i-th contact point on the battery swapping contact surface at time t, Represents the average contact pressure factor of the contact interface at all contact points at time t;

[0133] Obtain the stress concentration coefficient of each contact point on the battery swapping contact surface at the current moment and multiple historical moments, and construct a stress concentration sequence;

[0134] Establish a dynamic baseline for the stress concentration sequence and perform simultaneous identification analysis to identify the stress distribution concentration clusters on the battery swap contact surface;

[0135] Among them, the method of establishing a dynamic baseline for the stress concentration sequence and performing synchronous identification analysis is:

[0136] Preferably, a graph convolutional autoencoder (GCAE) is used to perform unsupervised learning on the stress concentration sequence of each contact point, and a dynamic baseline model that includes temporal dependency and spatial correlation (graph convolution aggregated neighborhood features) is constructed:

[0137] The dynamic baseline model is trained under normal working conditions to reconstruct the stress concentration sequence, and the reconstruction error of the real-time stress concentration sequence is used as the anomaly score;

[0138] Based on the sliding time window and the anomaly scores of spatially adjacent contact points, the stress distribution clusters are identified.

[0139] S2. Collect the electrothermal characteristic parameters of the stress distribution cluster on the battery swapping contact surface, perform function fitting to form a warning surface, construct a three-dimensional input vector for fitting analysis, and determine whether the three-dimensional input vector breaks through the warning surface boundary. If so, calculate the boundary crossing ratio of the warning surface and classify the battery swapping risk level;

[0140] The method for collecting the electrothermal characteristic parameters of the stress distribution cluster on the battery exchange contact surface is as follows:

[0141] Obtain the stress concentration coefficient within the stress distribution cluster of the battery swap contact surface, as well as the contact resistance of multiple contact points within the stress distribution cluster, and perform evidence consistency verification to eliminate invalid data;

[0142] After obtaining the evidence consistency check, the stress concentration coefficient, contact resistance and temperature gradient between adjacent contact points of the historical battery exchange contact surface stress concentration cluster are used as electrothermal characteristic parameters, and the stress concentration coefficient K is obtained by function fitting. t , contact resistance Rc, temperature gradient Warning surface;

[0143] The three-dimensional input vector acquired in real time is input into the fitting function, and the output of the fitting function is compared with the surface boundary;

[0144] If the result output by the fitting function exceeds the surface boundary, it is considered that there is a battery swap safety risk on the new energy battery swap contact surface;

[0145] Based on the output of the fitting function, the Euclidean distance closest to the surface boundary is calculated to obtain the out-of-bounds margin;

[0146] Calculate the Euclidean distance from the center point of the surface to the output of the fitting function to obtain the out-of-bounds distance;

[0147] The out-of-bounds margin is ratioed to the out-of-bounds length to obtain the out-of-bounds ratio.

[0148] S3. Based on the determined battery swap risk level, extract the protection features of the battery swap interface and perform capability matching analysis to determine whether the protection features of the battery swap interface match the risk level;

[0149] Among them, the method of extracting the protection features of the battery swap interface is:

[0150] The protection of the battery swap interface is divided into active protection and passive protection;

[0151] Obtain the content of fire extinguishing agent for active protection of the battery swapping operation surface, and obtain the average usage of fire extinguishing agent at the current risk level from historical data;

[0152] The active redundancy coefficient is obtained by comparing the average amount of fire extinguishing agent used at the current risk level with the content of fire extinguishing agent in active protection.

[0153] Obtain the number of successful warnings and the total number of warnings at the current risk level from historical data, perform ratio processing, and obtain the active response coefficient;

[0154] The active redundancy coefficient and the active response coefficient are combined as active protection features to construct the active protection vector XA;

[0155] Obtain the thermal resistance coefficient and thermal redundancy coefficient in passive protection, use the thermal resistance coefficient and thermal redundancy coefficient as passive protection features and combine them to construct the passive protection vector XB;

[0156] The thermal redundancy coefficient is the ratio of the actual thermal resistance of the battery swap interface to the critical thermal resistance at the target risk level. The critical thermal resistance is set according to the risk level, and the redundancy is quantified by comparing the actual thermal resistance with the preset critical value.

[0157] Among them, x1-x4 are active response coefficient, active response coefficient, thermal resistance coefficient, and thermal redundancy coefficient respectively;

[0158] Obtain the preset target feature vectors YA and YB, where YA = [y1, y2] and YB = [y3, y4], where the elements in the target feature vector correspond one-to-one to the active protection vector and the passive protection vector;

[0159] By formula: Get the characteristic over-limit value D of the target characteristic vector and the active protection vector XA A ;

[0160] By formula: Get the characteristic over-limit value D of the target characteristic vector and the passive protection vector XB B ;

[0161] The characteristic exceeds the limit value D A and D BPerform summation to obtain a safe matching value;

[0162] If the safety matching value meets the preset safety matching range value, it is determined whether the protection characteristics of the battery swap interface match the risk level, otherwise it does not match.

[0163] S4. If there is a match, obtain the historical active and passive protection vectors and establish a protection feature matrix. Combine the cross-border ratio to build a cross-border contraction model. Input the current active and passive protection vectors into the cross-border contraction model to obtain the contraction degree of the cross-border ratio and draw the cross-border contraction trajectory.

[0164] Among them, the method of establishing the protection feature matrix is:

[0165] Obtain multiple active and passive protection vectors of different risk levels from historical data and establish a protection feature matrix;

[0166] Based on the protection feature matrix and the corresponding out-of-bounds ratio, an out-of-bounds shrinkage model is constructed and trained;

[0167] The real-time active protection vector and passive protection vector are input into the out-of-bounds contraction model, and the out-of-bounds contraction model outputs the predicted out-of-bounds ratio under the current active protection vector and passive protection vector;

[0168] Obtain the predicted out-of-bounds ratio output by the out-of-bounds shrinkage model, calculate the deviation ratio between it and the out-of-bounds ratio of the current battery swapping operation surface, and obtain the shrinkage degree of the out-of-bounds ratio;

[0169] Based on the shrinkage degree of the out-of-bounds ratio, the out-of-bounds shrinkage trajectory is drawn on the warning surface.

[0170] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the foregoing embodiments. The foregoing embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A safe battery swap system using a new energy vehicle battery swap station, characterized by: Includes the following modules: Safety perception module: collects stress concentration coefficients at contact points and constructs stress concentration sequences. It establishes a dynamic baseline for the stress concentration sequences and performs synchronous identification analysis to obtain stress distribution concentration clusters. Level classification module: This module collects the electrothermal characteristic parameters of the stress distribution cluster and performs function fitting to form a warning surface. It then constructs a three-dimensional input vector for fitting analysis to determine whether the three-dimensional input vector breaks through the warning surface boundary. If so, it calculates the boundary crossing ratio of the warning surface and classifies the battery replacement risk level. Capability matching module: Based on the determined battery swap risk level, it extracts the protection features of the battery swap interface and performs capability matching analysis to determine whether the protection features of the battery swap interface match the risk level; Contraction analysis module: If there is a match, an out-of-bounds contraction model is constructed, the current active and passive protection vectors are input into the out-of-bounds contraction model, the contraction degree of the out-of-bounds ratio is obtained, and the out-of-bounds contraction trajectory is drawn.

2. A safe battery swap system using a new energy vehicle battery swap station according to claim 1, characterized in that: The method of establishing a dynamic baseline for the stress concentration sequence and performing synchronous identification analysis is as follows: Obtain the stress concentration coefficient of each contact point on the battery swapping contact surface at the current moment and multiple historical moments, and construct a stress concentration sequence; A graph convolutional autoencoder is used to perform unsupervised learning on the stress concentration sequence of each contact point, and a dynamic baseline model with time dependency and spatial correlation is constructed: The dynamic baseline model is trained to reconstruct the stress concentration sequence, and the reconstruction error of the real-time sequence is used as the anomaly score; Based on the sliding time window and the anomaly scores of spatially adjacent contact points, the stress distribution clusters are identified.

3. The safe battery swap system using a new energy vehicle battery swap station according to claim 2 is characterized by: The stress concentration factor is obtained as follows: The contact pressure factors of different contact points on the battery exchange contact surface are obtained for numerical analysis to obtain the stress concentration coefficient of the contact point.

4. The safe battery swapping system using a new energy vehicle battery swapping station according to claim 1 is characterized in that: The method of performing function fitting to form the early warning surface is: Obtain the stress concentration coefficient within the stress distribution cluster of the battery swap contact surface, as well as the contact resistance of multiple contact points within the stress distribution cluster, and perform evidence consistency verification; Obtain the stress concentration coefficient, contact resistance, and temperature gradient between adjacent contact points of the stress concentration cluster on the historical battery swap contact surface after evidence consistency verification, and construct a three-dimensional input vector; The three-dimensional input vector is fitted with a function to obtain a warning surface including stress concentration factor, resistance and temperature gradient.

5. The safe battery swap system using a new energy vehicle battery swap station according to claim 1 is characterized by: The method for calculating the out-of-bounds ratio of the warning surface is: The three-dimensional input vector acquired in real time is input into the fitting function. If the output of the fitting function exceeds the surface boundary, the Euclidean distance to the surface boundary is calculated based on the output of the fitting function to obtain the out-of-bounds margin. Calculate the Euclidean distance from the center point of the surface to the output of the fitting function to obtain the out-of-bounds distance; The out-of-bounds margin is ratioed to the out-of-bounds length to obtain the out-of-bounds ratio.

6. The safe battery swap system using a new energy vehicle battery swap station according to claim 1 is characterized by: The method for performing capability matching analysis is as follows: The protection of the battery swap interface is divided into active protection and passive protection. The active redundancy coefficient and active response coefficient under active protection are obtained and combined to obtain the active protection vector. Obtain the thermal resistance coefficient and thermal redundancy coefficient in passive protection, combine the thermal resistance coefficient and thermal redundancy coefficient to construct a passive protection vector; Perform feature overlimit calculation on active protection vectors and passive protection vectors to obtain safety matching values; A comparison is performed based on the safety matching value to determine whether the protection features of the battery swap interface match the risk level.

7. A safe battery swap system using a new energy vehicle battery swap station according to claim 6, characterized in that: The active response coefficient and active redundancy coefficient are obtained as follows: Obtain the content of fire extinguishing agent for active protection of the battery swapping operation surface, and obtain the average usage of fire extinguishing agent at the current risk level from historical data; The active redundancy coefficient is obtained by comparing the average amount of fire extinguishing agent used at the current risk level with the content of fire extinguishing agent in active protection. The number of successful warnings and the total number of warnings under the current risk level are obtained from historical data, and the ratio is processed to obtain the active response coefficient.

8. The safe battery swap system using a new energy vehicle battery swap station according to claim 6 is characterized by: The method for calculating the characteristic overrun is as follows: Obtain the target feature vector, and calculate the Chebyshev distance between the target feature vector and the active protection vector as the feature excess value between the target feature vector and the active protection vector; The Chebyshev distance between the target feature vector and the passive protection vector is calculated as the feature excess value between the target feature vector and the passive protection vector.

9. The safe battery swap system using a new energy vehicle battery swap station according to claim 1 is characterized by: The method for obtaining the degree of contraction of the cross-boundary ratio is: Obtain multiple active and passive protection vectors of different risk levels from historical data and establish a protection feature matrix; Based on the protection feature matrix and the corresponding out-of-bounds ratio, an out-of-bounds shrinkage model is constructed and trained; The real-time active protection vector and passive protection vector are input into the out-of-bounds contraction model, and the out-of-bounds contraction model outputs the predicted out-of-bounds ratio under the current active protection vector and passive protection vector; The deviation is calculated based on the predicted out-of-bounds ratio to obtain the contraction degree of the out-of-bounds ratio. Based on the contraction degree of the out-of-bounds ratio, the contraction trajectory of the out-of-bounds ratio is drawn on the warning surface.

10. A safe battery swap system using a new energy vehicle battery swap station according to claim 9, characterized in that: The deviation calculation is performed as follows: The predicted out-of-bounds ratio output by the out-of-bounds shrinkage model is obtained, and the deviation ratio is calculated with the out-of-bounds ratio of the current battery swapping operation surface to obtain the shrinkage degree of the out-of-bounds ratio.

Images