Method and device for changing load configuration of crane under interference of dangerous sources

Abstract

The present invention relates to the technical field of mechanical equipment safety assessment, and provides a method and device for variable load configuration of a crane under interference from a dangerous source, the method comprising: obtaining the total failure degree of the crane based on a failure network structure model assessment; collecting the longest crack of the crane; predicting the stress and deformation of the first dangerous point based on a proxy model according to the load spectrum of the crane; calculating the actual remaining service life of the crane according to the stress of the first dangerous point, the crack length of the longest crack and the total failure degree; constructing a stress-deformation optimization model according to the actual remaining service life, stress, deformation and load capacity; inputting the preset remaining service life of the crane into the stress-deformation optimization model to obtain the optimal stress and optimal deformation of the first dangerous point; substituting the optimal stress and optimal deformation into the proxy model, and inversely solving to obtain the optimized load of the crane. The present invention can accurately calculate the actual remaining service life of the crane and dynamically adjust the load of the crane to meet user requirements.

Description

Technical Field

[0001] The present invention relates to the technical field of mechanical equipment safety assessment, and in particular to a crane load change configuration method under the interference of a dangerous source and a crane load change configuration device under the interference of a dangerous source. Background Art

[0002] In recent years, with the expansion of production scale and the improvement of intelligence level, lifting machinery is in a period of rapid market development. And as the modernization process is getting faster and faster, the requirements for lifting machinery are getting higher and higher. Lifting machinery is developing towards large-scale, automated and professional trends. As important engineering machinery used in various fields such as construction sites, ports and shipping, energy and mining, its safe service is of vital importance. The metal structure of the crane is the skeleton and load-bearing structure of the crane, and all mechanical and electrical equipment are distributed on it. However, during the long-term use of the crane, it will be affected by environmental factors (hazard sources), and the degradation of its load-bearing capacity is inevitable.

[0003] In response to this phenomenon, the actual working load can be reduced in a timely manner to improve the safety and service life of the crane during its service. At present, in terms of crane deloading, special inspection personnel give qualitative results of deloading after visually inspecting the failure characteristics (such as wear, cracks, and deformation). As for the amount of deloading and the subsequent service life of the crane after deloading, they are all given artificially based on their own experience, resulting in too large differences in the results and low reliability. Therefore, starting from adapting to market / user needs, it is very important to reasonably and timely deload to extend the service life of the crane. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a method and device for variable load configuration of a crane under interference from dangerous sources, which can more accurately calculate the actual remaining service life of the crane and dynamically adjust the load of the crane to meet the service life required by the user while ensuring the safety of the crane in service.

[0005] The technical solution adopted by the present invention is as follows:

[0006] A method for variable load configuration of a crane under interference from a dangerous source, the method comprising the following steps: S1, using a risk assessment method based on a failure network structure model to evaluate the failure probability of a dangerous event occurring in a crane due to a dangerous source, and obtaining the total failure degree of the crane; S2, collecting the longest crack on a metal structural member of the crane according to an image of the crane, wherein the longest crack occurs at a first dangerous point with the highest degree of danger among dangerous points of the metal structural member of the crane; S3, predicting the stress and deformation of the first dangerous point based on a proxy model according to the load spectrum of the crane; S4, calculating the actual remaining service life of the crane according to the stress of the first dangerous point, the crack length of the longest crack and the total failure degree; S5, establishing an objective function according to the actual remaining service life of the crane, with stress and deformation as design variables and bearing capacity as a constraint condition, and constructing a stress-deformation optimization model; S6, inputting the preset remaining service life of the crane into the stress-deformation optimization model, and obtaining the optimal stress and optimal deformation of the first dangerous point; S7, substituting the optimal stress and optimal deformation into the proxy model, and inversely solving to obtain the optimized load of the crane.

[0007] In addition, the crane load configuration method under the interference of dangerous sources proposed by the present invention may also have the following additional technical features:

[0008] According to one embodiment of the present invention, step S1 specifically includes the following steps: determining the hazardous source of the crane under the influence of the environment and the metal structure information of the crane, taking the hazardous source as the top event, the metal structural parts of the crane and the failure parts of the metal structural parts as the intermediate events, the failure characteristics of the failure parts as the secondary intermediate events, and the hazardous factors corresponding to the hazardous events as the basic events, and establishing a failure network structure model of the crane, wherein each of the failure parts corresponds to a hazardous point; an expert group evaluates the hazardous factors in the failure network structure model and uses a reverse logic generator to determine the weight of the degree of influence of each layer of events in the failure grid on the upper layer of events; and evaluating the failure level of the crane under the influence of the hazardous source according to the expected value of the top-level evaluation unit group corresponding to the top event of the failure network structure model, and obtaining the failure probability of the hazardous source causing the crane to have a hazardous event, and then obtaining the total failure degree of the crane.

[0009] According to one embodiment of the present invention, the proxy model is a support vector machine proxy model, and before step S3, the following steps are further included:

[0010] Collecting a sample load spectrum of the crane and sample dangerous point parameters of each dangerous point of a metal structure of the crane, wherein the sample dangerous point parameters include stress parameters and deformation parameters;

[0011] The support vector machine proxy model is trained according to the sample load spectrum and the sample dangerous point parameters, and the support vector machine proxy model is used to predict the stress and deformation of the dangerous points of the metal structure of the crane according to the load spectrum of the crane.

[0012] According to one embodiment of the present invention, in step S4, the formula for calculating the actual remaining service life of the crane is:

[0013]

[0014] In the formula, a 0 is the initial crack size of the longest crack (mm), a c is the critical crack size of the longest crack (mm), f is the geometric correction factor, Δ σ is the stress at the first dangerous point; C , m is the material parameter; N is the actual remaining useful life of the crane; δ is the total failure degree of the crane.

[0015] According to one embodiment of the present invention, the stress-deformation optimization model is:

[0016]

[0017] In the formula, x 1 represents the stress at the first dangerous point, x 2 represents the deformation of the first dangerous point, L 0 is the preset remaining useful life of the crane, L N is the actual remaining service life of the crane, min[·] is the fitness function based on the minimum value, T ( x 1, x 2) The stress and deformation of the first dangerous point are x 1 and x 2 is the calculated value of the load-bearing capacity index of the crane, μ is the allowable value of the load-bearing capacity index of the metal structure of the crane, X 1down represents the minimum stress threshold of the first danger point, X 1now represents the current maximum stress threshold of the crane, X 2down represents the minimum deformation threshold of the first dangerous point, X 2nowIndicates the current maximum deformation threshold of the crane.

[0018] In addition, to achieve the above-mentioned purpose, the present invention also proposes a crane load-changing configuration device under interference from dangerous sources.

[0019] A load-changing configuration device for a crane under interference from a dangerous source, the system comprising: a failure degree assessment module, the failure degree assessment module being used to assess the failure probability of a dangerous event occurring in a crane due to a dangerous source by adopting a risk assessment method based on a failure network structure model, and obtaining a total failure degree of the crane; a first acquisition module, the first acquisition module being used to acquire the longest crack on a metal structural part of the crane according to an image of the crane, wherein the longest crack occurs at a first dangerous point with the highest degree of danger among dangerous points of the metal structural part of the crane; a prediction module, the prediction module being used to predict the stress and deformation of the first dangerous point based on a proxy model according to the load spectrum of the crane; and a service life calculation module. Block, the service life calculation module is used to calculate the actual remaining service life of the crane according to the stress of the first dangerous point, the crack length of the longest crack and the total failure rate; the modeling module is used to establish an objective function according to the actual remaining service life of the crane, with stress and deformation as design variables and bearing capacity as constraint conditions, to construct a stress-deformation optimization model; the optimization module is used to input the preset remaining service life of the crane into the stress-deformation optimization model to obtain the optimal stress and optimal deformation of the first dangerous point; the inverse solution module is used to substitute the optimal stress and optimal deformation into the proxy model to obtain the optimized load of the crane by inverse solution.

[0020] In addition, the crane load change configuration device under the interference of dangerous sources proposed by the present invention may also have the following additional technical features:

[0021] According to one embodiment of the present invention, the failure degree assessment module is specifically used to: determine the hazardous sources of the crane under the influence of the environment and the metal structure information of the crane, take the hazardous sources as top events, the metal structural parts of the crane and the failure parts of the metal structural parts as intermediate events, the failure characteristics of the failure parts as sub-intermediate events, and the hazardous factors corresponding to the hazardous events as basic events, and establish a failure network structure model of the crane, wherein each of the failure parts corresponds to a hazardous point; an expert group evaluates the hazardous factors in the failure network structure model and uses a reverse logic generator to determine the weight of the degree of influence of each layer of events in the failure grid on the upper layer of events; evaluates the failure level of the crane under the influence of the hazardous sources according to the expected value of the top-level evaluation unit group corresponding to the top event of the failure network structure model, and obtains the failure probability of the hazardous source causing the crane to have a hazardous event, thereby obtaining the total failure degree of the crane.

[0022] According to one embodiment of the present invention, the proxy model is a support vector machine proxy model, and the device also includes: a second acquisition module, the second acquisition module is used to collect the sample load spectrum of the crane and the sample dangerous point parameters of each dangerous point of the metal structure of the crane, the sample dangerous point parameters include stress parameters and deformation parameters; a proxy model training module, the proxy model training module is used to train the support vector machine proxy model according to the sample load spectrum and the sample dangerous point parameters, and the support vector machine proxy model is used to predict the stress and deformation of the dangerous points of the metal structure of the crane according to the load spectrum of the crane.

[0023] According to one embodiment of the present invention, the formula for calculating the actual remaining service life of the crane by the service life calculation module is:

[0024]

[0025] In the formula, a 0 is the initial crack size of the longest crack (mm), a c is the critical crack size of the longest crack (mm), f is the geometric correction factor, Δ σ is the stress at the first dangerous point; C , m is the material parameter; N is the actual remaining useful life of the crane; δ is the total failure degree of the crane.

[0026] According to one embodiment of the present invention, the stress-deformation optimization model is:

[0027]

[0028] In the formula, x 1 represents the stress at the first dangerous point, x 2 represents the deformation of the first dangerous point, L 0 is the preset remaining useful life of the crane, L N is the actual remaining service life of the crane, min[·] is the fitness function based on the minimum value, T ( x 1, x 2) The stress and deformation of the first dangerous point are x 1 and x 2 is the calculated value of the load-bearing capacity index of the crane, μ is the allowable value of the load-bearing capacity index of the metal structure of the crane, X 1down represents the minimum stress threshold of the first danger point, X 1now represents the current maximum stress threshold of the crane, X 2down represents the minimum deformation threshold of the first dangerous point, X 2now Indicates the current maximum deformation threshold of the crane.

[0029] Beneficial effects of the present invention:

[0030] The method for variable load configuration of a crane under interference from hazardous sources in an embodiment of the present invention adopts a risk assessment method based on a failure network structure model to obtain the total failure degree of the crane, and calculates the actual remaining service life of the crane according to the stress of the first hazardous point, the crack length of the longest crack and the total failure degree. This method can more accurately calculate the actual remaining service life of the crane; the preset remaining service life of the crane is input into a stress-deformation optimization model to obtain the optimal stress and optimal deformation of the first hazardous point, and the optimized load of the crane is obtained by inverse solution. This method can dynamically adjust the load of the crane to meet the service life required by the user while ensuring the safety of the crane in service. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a flow chart of a method for changing load configuration of a crane under interference from a dangerous source according to an embodiment of the present invention;

[0032] Figure 2 A failure network structure diagram of a specific embodiment of the present invention;

[0033] Figure 3 It is a block diagram of a crane load changing configuration device under interference from a dangerous source according to an embodiment of the present invention. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] like Figure 1 As shown, the crane load change configuration method under the interference of dangerous sources in the embodiment of the present invention includes the following steps:

[0036] S1, a risk assessment method based on the failure network structure model is used to evaluate the failure probability of the crane causing a dangerous event due to the hazard source, and the total failure degree of the crane is obtained.

[0037] Specifically, step S1 may include the following steps:

[0038] S11, determine the hazard sources of the crane under the influence of the environment and the metal structure information of the crane, take the hazard sources as top events, the metal structural parts of the crane and the failure parts of the metal structural parts as intermediate events, the failure characteristics of the failure parts as sub-intermediate events, and the hazard factors corresponding to the hazard events as basic events, and establish a failure network structure model of the crane, in which each failure part corresponds to a dangerous point.

[0039] like Figure 2 As shown in the figure, a failure network is constructed by taking a level 4 wind as an example. At this time, the dangerous source of strong wind is the top event of the failure network. Under the influence of strong wind, the wind loads borne by the end beam A1, the main beam A2, the end beam A3, the end beam A4, the connecting beam A5, the connecting beam A6 and their respective failure parts (B1-1~B6-n) are different. The strong wind, the beam structure and the failure part are connected by an "AND gate". Subsequently, the failure part will produce failure characteristics (C1~C9), which will further increase the probability of failure of the dangerous source. The two events are connected by an "OR gate". When technicians use cranes to perform tasks, such as cargo handling, equipment hoisting and installation, maintenance and repair of public facilities, etc., a series of dangerous events may occur (the corresponding dangerous factors of dangerous events are D1~D5). The failure characteristics and dangerous events are connected by an "OR gate" to form a complete failure network structure.

[0040] S12, the expert group evaluates the risk factors in the failure network structure model and uses a reverse logic generator to determine the weight of the impact of each layer of events in the failure grid on the events in the previous layer.

[0041] Specifically, the weight range can be divided into five levels, namely: slightly important, secondarily important, generally important, relatively important, and extremely important, and the five-level comment sets are evenly mapped to the interval [0,1]. According to the golden section method, the expected value, entropy value, and super entropy value of the five importance levels are calculated respectively in combination with the following formula:

[0042]

[0043] In the formula, Ex is the expected value of five important levels, En are the entropy values ​​at five important levels, He There are five important levels of super entropy, a max is the maximum value of the five important level intervals, a min It is the minimum value of the five important level intervals.

[0044] The reverse logic generator is used to convert the expert group's comments on each event into digital features, and the expected value is normalized among the events of the same level as the weight value of each layer of events. The calculation formula of the reverse logic generator is shown as follows:

[0045]

[0046] In the formula, x ij For the j Experts on i The evaluation value of a unit group, n is the number of evaluation experts, for n Experts on i The average evaluation value of the unit group, For the current layer i The variance of the cell group, Ex i For the current layer i The expectation of a group of units, En i For the current layer i The entropy of a group of cells, He i For the current layer i The super entropy of a group of cells.

[0047] The downward method is used to gradually deduce from the basic events of the failure network structure model. During this period, the causal and logical relationships between different events need to be analyzed. Experts evaluate the failure level of the basic events of the failure network structure model and divide them into five levels. The failure probability is described in natural language, namely: low failure rate, low, general, high, and high, and these five concept levels are mapped to the interval [0,1]. Combined with the golden section method, the digital features of the corresponding failure level comments are calculated, and each probability level is mapped in the interval and the digital feature column.

[0048] After evaluating the failure probability level of each basic event, the corresponding subgroups are formed using the logical model, and the uncertainty of multiple subgroups and the fuzziness of concepts are combined to regenerate a parent group with a broader concept. In the failure network model, the upper events connected by logic gates can be regarded as the parent group of the lower connected events, that is, the basic event subgroups are synthesized upward into basic unit groups according to the logic gates of the failure tree, the basic unit groups are synthesized upward into intermediate unit groups, and the intermediate unit clouds are synthesized upward into evaluation unit groups; when synthesizing unit groups upward, the corresponding level of weights should be introduced.

[0049] In the failure network, the digital characteristic calculation formula of the intermediate event synthesis unit group connected by the "OR gate" is:

[0050]

[0051] In the failure network, the digital feature calculation formula of the intermediate event synthesis unit group connected by the "AND gate" is:

[0052]

[0053] In the formula, Ex To synthesize the expectations of the basic unit group, intermediate unit group or evaluation unit group, En is the entropy of the synthetic basic unit group, intermediate unit group or evaluation unit group, He is the super entropy of the synthetic basic unit group, intermediate unit group or evaluation unit group, ω i For the current layer i The basic event subgroup, i The basic unit group or i The weight of the intermediate unit group when synthesizing to the upper layer; Ex i For the current layer i The basic event subgroup, i The basic unit group or i The expectation of a group of intermediate units, En i For the current layer i The basic event subgroup, iThe basic unit group or i The entropy of the intermediate unit group, He i For the current layer i The basic event subgroup, i The basic simple group or i The super entropy of a group of intermediate units.

[0054] S13, the expected value of the top evaluation unit group corresponding to the top event of the failure network structure model Ex The failure level of the crane under the influence of hazardous sources is evaluated to obtain the failure probability of the crane causing a hazardous event due to the hazardous source, and then the total failure degree of the crane is obtained.

[0055] When only a single hazard source under the influence of the environment is considered, the failure probability of the crane causing a dangerous event due to the hazard source is the total failure degree of the crane. When there are multiple hazard sources under the influence of the environment, such as earthquakes, lightning, strong winds, altitude, etc., the failure probability corresponding to each hazard source can be multiplied to obtain the total failure degree of the crane.

[0056] S2, collecting the longest crack on the metal structure of the crane according to the image of the crane, wherein the longest crack occurs at the first dangerous point with the highest degree of danger among the dangerous points of the metal structure of the crane.

[0057] In one embodiment of the present invention, the image acquisition and recognition method may adopt a texture-based recognition method, by using a high-definition camera to collect cracks at dangerous points of the metal structure of the crane, observing the changes in crack length in real time, obtaining the longest crack on the metal structure, and defining the dangerous point where the longest crack is located as the first dangerous point.

[0058] It should be noted that the use of image acquisition and recognition methods can measure crack length more accurately. Compared with special inspectors' visual inspection or manual measurement of crack length, the image acquisition and recognition method has higher precision and accuracy.

[0059] S3, predict the stress and deformation of the first danger point based on the agent model according to the load spectrum of the crane.

[0060] In one embodiment of the present invention, the load spectrum of the crane can be determined according to the rated lifting capacity of the crane. The rated lifting capacity of the crane refers to the maximum weight that the crane can safely lift after determining the lifting height and the operating span. Under the restriction of the rated lifting capacity, the actual load in use must not exceed the rated load. Therefore, according to the rated lifting capacity of the crane, the actual load range of the crane during actual operation, that is, the load spectrum, can be determined. The load spectrum refers to any load within the actual load range and its corresponding number of times.

[0061] In one embodiment of the present invention, the proxy model is a support vector machine proxy model, and before step S3, the following steps are also included:

[0062] Sa, collects sample load spectra of the crane and sample dangerous point parameters of each dangerous point of the metal structure of the crane, the sample dangerous point parameters include stress parameters and deformation parameters.

[0063] Sb, trains the support vector machine proxy model based on the sample load spectrum and sample dangerous point parameters. The support vector machine proxy model is used to predict the stress and deformation of the dangerous points of the metal structure of the crane based on the load spectrum of the crane. The specific steps of training the support vector machine proxy model are as follows:

[0064] Data preprocessing involves data cleaning, feature selection, and data standardization of the sample load spectra and sample dangerous point parameters of each dangerous point of the metal structure. Data cleaning aims to eliminate or correct errors, anomalies, or duplicates in the data. Feature selection is to select the most useful features for model training from the original features. Data standardization is to scale the data according to certain rules to eliminate the dimensional differences between different features.

[0065] Select the kernel function. The kernel function has a crucial impact on the performance of the model. Different kernel functions have different computational complexities. In order to find the most suitable kernel function, a cross-validation method is used. By choosing between different kernel functions and evaluating the performance of each kernel function on the validation set, the best kernel function can be selected. Since the number of sample load spectrum data features is large compared to the sample size, a linear kernel can be considered as the kernel function of the surrogate model.

[0066] Determine the hyperparameters. Hyperparameter selection is crucial to the performance of the model. Hyperparameters are parameters that need to be determined before model training. They are not learned through the model's training data. For support vector machines, common hyperparameters include the regularization parameter C and kernel function parameters (such as the gamma parameter in the RBF (Radial Basis Function) kernel). The selection of these hyperparameters will directly affect the generalization ability and prediction performance of the model. Therefore, a random search method can be used. Random search is to randomly select a set of hyperparameters within a specified hyperparameter range for training and evaluation. Through multiple random selections and evaluations, a hyperparameter combination with good performance can be found. Compared with grid search, it has relatively low computational cost, is easy to implement, and has certain advantages in dealing with non-convex, non-smooth or highly complex optimization problems.

[0067] Training model,After data preprocessing and hyperparameter determination, start training the support vector machine proxy model.,During the model training process, the data set is divided into 70% training set and 30% test set.,The training set is used to train the model, and the test set is used to evaluate the,performance of the model.

[0068] S4, the actual remaining service life of the crane is calculated based on the stress at the first danger point, the crack length of the longest crack and the total failure rate.

[0069] Specifically, the formula for calculating the actual remaining useful life of a crane is:

[0070]

[0071] In the formula, a 0 is the initial crack size of the longest crack (mm), a c is the critical crack size of the longest crack (mm), f is the geometric correction factor, Δ σ is the stress at the first danger point; C , m is the material parameter; N is the actual remaining useful life of the crane; δ is the total failure rate of the crane.

[0072] It should be noted that the calculation formula for the actual remaining service life of the crane can more accurately calculate the actual remaining service life of the crane by taking into account the total failure rate of the crane caused by hazardous sources, avoid inaccurate calculation of the remaining service life, and cause accidents due to unreasonable crane load configuration schemes under the interference of hazardous sources, thereby ensuring the safe service of the crane.

[0073] S5, establish the objective function according to the actual remaining service life of the crane, use stress and deformation as design variables, and load-bearing capacity as constraint conditions to build a stress-deformation optimization model.

[0074] In one embodiment of the present invention, the stress-deformation optimization model is:

[0075]

[0076] In the formula, x 1 represents the stress at the first danger point, x 2 indicates the deformation of the first danger point, L N is the actual remaining useful life of the crane, L0 is the preset remaining service life of the crane, which can be calculated based on the preset service life of the crane, or can be set based on the preset service life of the crane so that the actual service life of the crane is not less than the preset service life, where the preset service life comes from the factory information of the crane, min[·] is the fitness function based on the minimum value, T ( x 1, x 2) The stress and deformation of the first dangerous point are x 1 and x 2 is the calculated value of the crane's load-bearing capacity index, which may include the strength, rigidity, stability, etc. of the metal structure. μ is the allowable value of the load-bearing capacity index of the metal structure of the crane, X 1down represents the minimum stress threshold of the first danger point, X 1now Indicates the current maximum stress threshold of the crane, X 2down represents the minimum deformation threshold of the first danger point, X 2now Indicates the current maximum deformation threshold of the crane.

[0077] S6, inputting the preset remaining service life of the crane into the stress-deformation optimization model to obtain the optimal stress and optimal deformation of the first dangerous point.

[0078] In one embodiment of the present invention, a genetic algorithm may be used to solve the stress-deformation optimization model, which specifically includes the following steps:

[0079] Initialize the population: Randomly generate a set of initial solutions, each of which represents a design scheme or parameter combination.

[0080] Target evaluation: Evaluate the solutions in the population and calculate their actual remaining useful life.

[0081] Selection operation: select the individuals that are most suitable for survival and reproduction. The selection operation is based on the fitness of the individuals. Individuals with high fitness have a high probability of being selected, while individuals with low fitness may be eliminated.

[0082] Crossover and mutation: Perform a crossover operation on the selected individuals to generate new combinations of solutions and make random changes to the genetic material of the individuals.

[0083] Iteration and optimization: Repeat the above evaluation, selection, crossover, mutation and update steps until the stopping criterion is met. The stopping criterion can be reaching a preset number of iterations, finding a solution that meets all objectives (optimal stress and optimal deformation of the first critical point), or population convergence.

[0084] S7, substitute the optimal stress and optimal deformation into the proxy model, and inversely solve to obtain the optimized load of the crane.

[0085] Specifically, the optimal stress and optimal deformation can be used as independent variables to substitute into the support vector machine proxy model trained in step Sb, and the output result obtained by reverse mapping and inverse solution of the support vector machine proxy model is the optimized load of the crane, that is, the low-configuration load spectrum. The operator can reduce the load based on the original load spectrum according to the low-configuration load spectrum to extend the service life of the crane.

[0086] In one embodiment of the present invention, if the operator has adopted a low-configuration load spectrum during the operation of the crane according to steps S1 to S7, and wants to change the load configuration of the crane again, the load spectrum of the crane in step S3 can be replaced with the low-configuration load spectrum being used, and the new low-configuration load spectrum can be recalculated.

[0087] According to the method for variable load configuration of a crane under interference from hazardous sources in an embodiment of the present invention, the total failure degree of the crane is calculated by a risk assessment method based on a failure network structure model, and the actual remaining service life of the crane is calculated according to the stress of the first hazardous point, the crack length of the longest crack and the total failure degree. This method can more accurately calculate the actual remaining service life of the crane; the preset remaining service life of the crane is input into a stress-deformation optimization model to obtain the optimal stress and optimal deformation of the first hazardous point, and the optimized load of the crane is obtained by inverse solution. This method can dynamically adjust the load of the crane to meet the service life required by the user while ensuring the safety of the crane in service.

[0088] In addition, to achieve the above-mentioned purpose, the present invention also proposes a crane load-changing configuration device under interference from dangerous sources.

[0089] like Figure 3As shown, the variable load configuration device for controlling the degradation of the load-bearing capacity of a crane according to an embodiment of the present invention comprises a failure degree assessment module 10, a first acquisition module 20, a prediction module 30, a service life calculation module 40, a modeling module 50, an optimization module 60 and an inverse solution module 70, wherein the failure degree assessment module 10 is used to assess the failure probability of a dangerous event of the crane caused by a dangerous source by adopting a risk assessment method based on a failure network structure model, and obtain the total failure degree of the crane; the first acquisition module 20 is used to acquire the longest crack on the metal structure of the crane according to the image of the crane, wherein the longest crack occurs at the first dangerous point with the highest degree of danger among the dangerous points of the metal structure of the crane; the prediction module 30 It is used to predict the stress and deformation of the first dangerous point based on the proxy model according to the load spectrum of the crane; the service life calculation module 40 is used to calculate the actual remaining service life of the crane according to the stress of the first dangerous point, the crack length of the longest crack and the total failure rate; the modeling module 50 is used to establish an objective function according to the actual remaining service life of the crane, with stress and deformation as design variables and bearing capacity as constraint conditions, and construct a stress-deformation optimization model; the optimization module 60 is used to input the preset remaining service life of the crane into the stress-deformation optimization model to obtain the optimal stress and optimal deformation of the first dangerous point; the inverse solution module 70 is used to substitute the optimal stress and optimal deformation into the proxy model, and inversely solve to obtain the optimized load of the crane.

[0090] In one embodiment of the present invention, the failure degree assessment module 10 is specifically used to: determine the hazard source of the crane under the influence of the environment and the metal structure information of the crane, take the hazard source as the top event, the metal structure of the crane and the failure part of the metal structure as the intermediate event, the failure characteristics of the failure part as the secondary intermediate event, and the hazard factor corresponding to the hazard event as the basic event, and establish a failure network structure model of the crane, wherein each failure part corresponds to a hazard point; the expert group evaluates the hazard factors in the failure network structure model and uses a reverse logic generator to determine the weight of the degree of influence of each layer event of the failure grid on the upper layer event; the failure level of the crane under the influence of the hazard source is evaluated according to the expected value of the top-level evaluation unit group corresponding to the top event of the failure network structure model, and the failure probability of the crane causing a hazard event due to the hazard source is obtained, and then the total failure degree of the crane is obtained.

[0091] When only considering a single hazard source of the crane under the influence of the environment, the failure probability of the crane causing a dangerous event due to the hazard source is the total failure degree of the crane. When the crane has multiple hazard sources under the influence of the environment, such as earthquakes, lightning, strong winds, altitude, etc., the failure probability corresponding to each hazard source can be multiplied to obtain the total failure degree of the crane.

[0092] like Figure 2As shown in the figure, a failure network is constructed by taking a level 4 wind as an example. At this time, the dangerous source of strong wind is the top event of the failure network. Under the influence of strong wind, the wind loads borne by the end beam A1, the main beam A2, the end beam A3, the end beam A4, the connecting beam A5, the connecting beam A6 and their respective failure parts (B1-1~B6-n) are different. The strong wind, the beam structure and the failure part are connected by an "AND gate". Subsequently, the failure part will produce failure characteristics (C1~C9), which will further increase the probability of failure of the dangerous source. The two events are connected by an "OR gate". When technicians use cranes to perform tasks, such as cargo handling, equipment hoisting and installation, maintenance and repair of public facilities, etc., a series of dangerous events may occur (the corresponding dangerous factors of dangerous events are D1~D5). The failure characteristics and dangerous events are connected by an "OR gate" to form a complete failure network structure.

[0093] The expert group evaluates the risk factors in the failure network structure model and uses the reverse logic generator to determine the weight of the impact of each layer of the failure grid event on the upper layer event. Specifically, the weight range can be divided into five levels, namely: slightly important, secondary important, general important, more important, and extremely important, and the five-level comment sets are evenly mapped to the interval [0,1]. According to the golden section method, the expected value, entropy value, and super entropy value of the five important levels are calculated respectively in combination with the following formula:

[0094]

[0095] In the formula, Ex is the expected value of five important levels, En are the entropy values ​​at five important levels, He There are five important levels of super entropy, a max is the maximum value of the five important level intervals, a min It is the minimum value of the five important level intervals.

[0096] The reverse logic generator is used to convert the expert group's comments on each event into digital features, and the expected value is normalized among the events of the same level as the weight value of each layer of events. The calculation formula of the reverse logic generator is shown as follows:

[0097]

[0098] In the formula, x ij For the j Experts on i The evaluation value of a unit group, n is the number of evaluation experts, for n Experts on iThe average evaluation value of the unit group, For the current layer i The variance of the cell group, Ex i For the current layer i The expectation of a group of units, En i For the current layer i The entropy of a group of cells, He i For the current layer i The super entropy of a group of cells.

[0099] The downward method is used to gradually deduce from the basic events of the failure network structure model. During this period, the causal and logical relationships between different events need to be analyzed. Experts evaluate the failure level of the basic events of the failure network structure model and divide them into five levels. The failure probability is described in natural language, namely: low failure rate, low, general, high, and high, and these five concept levels are mapped to the interval [0,1]. Combined with the golden section method, the digital features of the corresponding failure level comments are calculated, and each probability level is mapped in the interval and the digital feature column.

[0100] After evaluating the failure probability level of each basic event, the corresponding subgroups are formed using the logical model, and the uncertainty of multiple subgroups and the fuzziness of concepts are combined to regenerate a parent group with a broader concept. In the failure network model, the upper events connected by logic gates can be regarded as the parent group of the lower connected events, that is, the basic event subgroups are synthesized upward into basic unit groups according to the logic gates of the failure tree, the basic unit groups are synthesized upward into intermediate unit groups, and the intermediate unit clouds are synthesized upward into evaluation unit groups; when synthesizing unit groups upward, the corresponding level of weights should be introduced.

[0101] In the failure network, the digital characteristic calculation formula of the intermediate event synthesis unit group connected by the "OR gate" is:

[0102]

[0103] In the failure network, the digital feature calculation formula of the intermediate event synthesis unit group connected by the "AND gate" is:

[0104]

[0105] In the formula, Ex To synthesize the expectations of the basic unit group, intermediate unit group or evaluation unit group, En is the entropy of the synthetic basic unit group, intermediate unit group or evaluation unit group, He is the super entropy of the synthetic basic unit group, intermediate unit group or evaluation unit group, ω i For the current layeri The basic event subgroup, i The basic unit group or i The weight of the intermediate unit group when synthesizing to the upper layer; Ex i For the current layer i The basic event subgroup, i The basic unit group or i The expectation of the intermediate unit group, En i For the current layer i The basic event subgroup, i The basic unit group or i The entropy of the intermediate unit group, He i For the current layer i The basic event subgroup, i The basic simple group or i The super entropy of a group of intermediate units.

[0106] In one embodiment of the present invention, the first acquisition module 20 can use a texture-based recognition method to perform image acquisition to obtain the longest crack on the metal structure. By using a high-definition camera to collect cracks at dangerous points of the metal structure of the crane, the changes in crack length are observed in real time to obtain the longest crack on the metal structure, and the dangerous point where the longest crack is located is defined as the first dangerous point.

[0107] It should be noted that the use of image acquisition and recognition methods can measure crack length more accurately. Compared with special inspectors' visual inspection or manual measurement of crack length, the image acquisition and recognition method has higher precision and accuracy.

[0108] In one embodiment of the present invention, the prediction module 30 can determine the load spectrum of the crane according to the rated lifting capacity of the crane. The rated lifting capacity of the crane refers to the maximum weight that the crane can safely lift after determining the lifting height and the operating span. Under the restriction of the rated lifting capacity, the actual load in use must not exceed the rated load. Therefore, according to the rated lifting capacity of the crane, the actual load range of the crane during actual operation, that is, the load spectrum, can be determined. The load spectrum refers to any load within the actual load range and its corresponding number of times.

[0109] In one embodiment of the present invention, the proxy model used by the prediction module 30 is a support vector machine proxy model, and the variable load configuration device also includes: a second acquisition module and a proxy model training module, wherein the second acquisition module is used to collect sample load spectra of the crane and sample dangerous point parameters of each dangerous point of the metal structure of the crane, and the sample dangerous point parameters include stress parameters and deformation parameters; the proxy model training module is used to train the support vector machine proxy model according to the sample load spectrum and the sample dangerous point parameters, and the support vector machine proxy model is used to predict the stress and deformation of the dangerous points of the metal structure of the crane according to the load spectrum of the crane. The specific steps of training the support vector machine proxy model are as follows:

[0110] Data preprocessing involves data cleaning, feature selection, and data standardization of the sample load spectra and sample dangerous point parameters of each dangerous point of the metal structure. Data cleaning aims to eliminate or correct errors, anomalies, or duplicates in the data. Feature selection is to select the most useful features for model training from the original features. Data standardization is to scale the data according to certain rules to eliminate the dimensional differences between different features.

[0111] Select the kernel function. The kernel function has a crucial impact on the performance of the model. Different kernel functions have different computational complexities. In order to find the most suitable kernel function, a cross-validation method is used. By choosing between different kernel functions and evaluating the performance of each kernel function on the validation set, the best kernel function can be selected. Since the number of sample load spectrum data features is large compared to the sample size, a linear kernel can be considered as the kernel function of the surrogate model.

[0112] Determine the hyperparameters. Hyperparameter selection is crucial to the performance of the model. Hyperparameters are parameters that need to be determined before model training. They are not learned through the model's training data. For support vector machines, common hyperparameters include the regularization parameter C and kernel function parameters (such as the gamma parameter in the RBF (Radial Basis Function) kernel). The selection of these hyperparameters will directly affect the generalization ability and prediction performance of the model. Therefore, a random search method can be used. Random search is to randomly select a set of hyperparameters within a specified hyperparameter range for training and evaluation. Through multiple random selections and evaluations, a hyperparameter combination with good performance can be found. Compared with grid search, it has relatively low computational cost, is easy to implement, and has certain advantages in dealing with non-convex, non-smooth or highly complex optimization problems.

[0113] Training model,After data preprocessing and hyperparameter determination, start training the support vector machine proxy model.,During the model training process, the data set is divided into 70% training set and 30% test set.,The training set is used to train the model, and the test set is used to evaluate the,performance of the model.

[0114] In one embodiment of the present invention, the formula for calculating the actual remaining service life of the crane by the service life calculation module 40 is:

[0115]

[0116] In the formula, a 0 is the initial crack size of the longest crack (mm), a c is the critical crack size of the longest crack (mm), f is the geometric correction factor, Δ σ is the stress at the first danger point; C , m is the material parameter; N is the actual remaining useful life of the crane; δ is the total failure rate of the crane.

[0117] It should be noted that the calculation formula for the actual remaining service life of the crane can more accurately calculate the actual remaining service life of the crane by taking into account the total failure rate of the crane caused by hazardous sources, avoid inaccurate calculation of the remaining service life, and cause accidents due to unreasonable crane load configuration schemes under the interference of hazardous sources, thereby ensuring the safe service of the crane.

[0118] In one embodiment of the present invention, the stress-deformation optimization model constructed by the modeling module 50 is:

[0119]

[0120] In the formula, x 1 represents the stress at the first danger point, x 2 indicates the deformation of the first danger point, L N is the actual remaining useful life of the crane, L 0 is the preset remaining service life of the crane, which can be calculated based on the preset service life of the crane, or can be set based on the preset service life of the crane so that the actual service life of the crane is not less than the preset service life, where the preset service life comes from the factory information of the crane, min[·] is the fitness function based on the minimum value, T ( x 1, x 2) The stress and deformation of the first dangerous point are x 1 and x2 is the calculated value of the crane's load-bearing capacity index, which may include the strength, rigidity, stability, etc. of the metal structure. μ is the allowable value of the load-bearing capacity index of the metal structure of the crane, X 1down represents the minimum stress threshold of the first danger point, X 1now Indicates the current maximum stress threshold of the crane, X 2down represents the minimum deformation threshold of the first danger point, X 2now Indicates the current maximum deformation threshold of the crane.

[0121] In one embodiment of the present invention, the optimization module 60 may use a genetic algorithm to solve the stress-deformation optimization model, which specifically includes the following steps:

[0122] Initialize the population: Randomly generate a set of initial solutions, each of which represents a design scheme or parameter combination.

[0123] Target evaluation: Evaluate the solutions in the population and calculate their actual remaining useful life.

[0124] Selection operation: select the individuals that are most suitable for survival and reproduction. The selection operation is based on the fitness of the individuals. Individuals with high fitness have a high probability of being selected, while individuals with low fitness may be eliminated.

[0125] Crossover and mutation: Perform a crossover operation on the selected individuals to generate new combinations of solutions and make random changes to the genetic material of the individuals.

[0126] Iteration and optimization: Repeat the above evaluation, selection, crossover, mutation and update steps until the stopping criterion is met. The stopping criterion can be reaching a preset number of iterations, finding a solution that meets all objectives (optimal stress and optimal deformation of the first critical point), or population convergence.

[0127] In one embodiment of the present invention, the inverse solution module 70 can substitute the optimal stress and optimal deformation as independent variables into the support vector machine proxy model trained in step Sb, and obtain the output result through reverse mapping of the support vector machine proxy model, which is the optimized load of the crane, that is, the low-configuration load spectrum. The operator can reduce the load based on the original load spectrum according to the low-configuration load spectrum to extend the service life of the crane.

[0128] According to the variable load configuration device of the crane under the interference of dangerous sources in the embodiment of the present invention, by adopting the total failure degree of the crane in the risk assessment method based on the failure network structure model, the actual remaining service life of the crane is calculated according to the stress of the first dangerous point, the crack length of the longest crack and the total failure degree, so that the actual remaining service life of the crane can be calculated more accurately; the preset remaining service life of the crane is input into the stress-deformation optimization model to obtain the optimal stress and optimal deformation of the first dangerous point, and the optimized load of the crane is obtained by inverse solution, so that the load of the crane can be dynamically adjusted to meet the service life required by the user under the condition of ensuring the safety of the crane in service.

[0129] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. "Multiple" means two or more, unless otherwise clearly and specifically defined.

[0130] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0131] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0132] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0133] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0134] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0135] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0136] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A method for variable load configuration of a crane under interference from a dangerous source, characterized in that: The method comprises the following steps: S1, using a risk assessment method based on a failure network structure model to assess the failure probability of a dangerous event occurring in a crane due to a dangerous source, and obtaining a total failure degree of the crane; S2, collecting the longest crack on the metal structure of the crane according to the image of the crane, wherein the longest crack occurs at a first dangerous point with the highest degree of danger among dangerous points of the metal structure of the crane; S3, predicting the stress and deformation of the first dangerous point based on the agent model according to the load spectrum of the crane; S4, calculating the actual remaining service life of the crane according to the stress of the first dangerous point, the crack length of the longest crack and the total failure rate; S5, establishing an objective function according to the actual remaining service life of the crane, with stress and deformation as design variables and bearing capacity as a constraint condition, and constructing a stress-deformation optimization model; S6, inputting the preset remaining service life of the crane into the stress-deformation optimization model to obtain the optimal stress and optimal deformation of the first dangerous point; S7, substituting the optimal stress and optimal deformation into the proxy model, and performing inverse analysis to obtain the optimized load of the crane.

2. The crane load configuration method under the interference of dangerous sources according to claim 1 is characterized in that: Step S1 specifically includes the following steps: Determine the danger source of the crane under the influence of the environment and the metal structure information of the crane, take the danger source as the top event, the metal structure of the crane and the failure location of the metal structure as the intermediate event, the failure characteristics of the failure location as the secondary intermediate event, the danger factor corresponding to the danger event as the basic event, and establish the failure network structure model of the crane, wherein each failure location corresponds to a danger point; An expert group evaluates the risk factors in the failure network structure model and uses a reverse logic generator to determine the weight of the impact of each layer event of the failure grid on the previous layer event; The failure level of the crane under the influence of the hazard source is evaluated according to the expected value of the top-level evaluation unit group corresponding to the top event of the failure network structure model, so as to obtain the failure probability of the crane causing a dangerous event due to the hazard source, and further obtain the total failure degree of the crane.

3. The crane load configuration method under the interference of dangerous sources according to claim 1 is characterized in that: The proxy model is a support vector machine proxy model, and before step S3, the following steps are also included: Collecting a sample load spectrum of the crane and sample dangerous point parameters of each dangerous point of a metal structure of the crane, wherein the sample dangerous point parameters include stress parameters and deformation parameters; The support vector machine proxy model is trained according to the sample load spectrum and the sample dangerous point parameters, and the support vector machine proxy model is used to predict the stress and deformation of the dangerous points of the metal structure of the crane according to the load spectrum of the crane.

4. The method for variable load configuration of a crane under interference from a dangerous source according to claim 1, characterized in that: In step S4, the formula for calculating the actual remaining service life of the crane is: ； In the formula, a 0 is the initial crack size of the longest crack, a c is the critical crack size of the longest crack, f is the geometric correction factor, Δ σ is the stress at the first dangerous point; C , m is the material parameter; N is the actual remaining useful life of the crane; δ is the total failure degree of the crane.

5. The method for variable load configuration of a crane under interference from a dangerous source according to claim 1, characterized in that: The stress-deformation optimization model is: ； In the formula, x 1 represents the stress at the first dangerous point, x 2 represents the deformation of the first dangerous point, L 0 is the preset remaining useful life of the crane, L N is the actual remaining service life of the crane, min[·] is the fitness function based on the minimum value, T ( x 1, x 2) The stress and deformation of the first dangerous point are x 1 and x 2 is the calculated value of the load-bearing capacity index of the crane, μ is the allowable value of the load-bearing capacity index of the metal structure of the crane, X 1down represents the minimum stress threshold of the first danger point, X 1now represents the current maximum stress threshold of the crane, X 2down represents the minimum deformation threshold of the first dangerous point, X 2now Indicates the current maximum deformation threshold of the crane.

6. A crane load-changing configuration device under interference from dangerous sources, characterized in that: The device comprises: A failure degree assessment module, wherein the failure degree assessment module is used to assess the failure probability of a dangerous event occurring in a crane due to a dangerous source by using a risk assessment method based on a failure network structure model, and obtain a total failure degree of the crane; a first acquisition module, the first acquisition module being used to acquire the longest crack on the metal structure of the crane according to the image of the crane, wherein the longest crack occurs at a first dangerous point with the highest degree of danger among dangerous points of the metal structure of the crane; A prediction module, the prediction module is used to predict the stress and deformation of the first dangerous point based on the agent model according to the load spectrum of the crane; A service life calculation module, the service life calculation module is used to calculate the actual remaining service life of the crane according to the stress of the first dangerous point, the crack length of the longest crack and the total failure rate; A modeling module, the modeling module is used to establish an objective function according to the actual remaining service life of the crane, with stress and deformation as design variables and bearing capacity as a constraint condition, to construct a stress-deformation optimization model; An optimization module, wherein the optimization module is used to input the preset remaining service life of the crane into the stress-deformation optimization model to obtain the optimal stress and optimal deformation of the first dangerous point; An inverse solution module is used to substitute the optimal stress and optimal deformation into the proxy model to obtain the optimized load of the crane through inverse solution.

7. The crane load-changing configuration device under interference from dangerous sources according to claim 6 is characterized in that: The failure degree assessment module is specifically used for: Determine the danger source of the crane under the influence of the environment and the metal structure information of the crane, take the danger source as the top event, the metal structure of the crane and the failure location of the metal structure as the intermediate event, the failure characteristics of the failure location as the secondary intermediate event, the danger factor corresponding to the danger event as the basic event, and establish the failure network structure model of the crane, wherein each failure location corresponds to a danger point; An expert group evaluates the risk factors in the failure network structure model and uses a reverse logic generator to determine the weight of the impact of each layer event of the failure grid on the previous layer event; The failure level of the crane under the influence of the hazard source is evaluated according to the expected value of the top-level evaluation unit group corresponding to the top event of the failure network structure model, so as to obtain the failure probability of the crane causing a dangerous event due to the hazard source, and further obtain the total failure degree of the crane.

8. The crane load-changing configuration device under the interference of dangerous sources according to claim 6 is characterized in that: The proxy model is a support vector machine proxy model, and the device further includes: A second acquisition module, the second acquisition module is used to collect sample load spectra of the crane and sample dangerous point parameters of each dangerous point of the metal structure of the crane, the sample dangerous point parameters including stress parameters and deformation parameters; The proxy model training module is used to train the support vector machine proxy model according to the sample load spectrum and the sample dangerous point parameters, and the support vector machine proxy model is used to predict the stress and deformation of the dangerous points of the metal structure of the crane according to the load spectrum of the crane.

9. The crane load-changing configuration device under interference from dangerous sources according to claim 6 is characterized in that: The formula used by the service life calculation module to calculate the actual remaining service life of the crane is: ； In the formula, a 0 is the initial crack size of the longest crack, a c is the critical crack size of the longest crack, f is the geometric correction factor, Δ σ is the stress at the first dangerous point; C , m is the material parameter; N is the actual remaining useful life of the crane; δ is the total failure degree of the crane.

10. The crane load-changing configuration device under the interference of dangerous sources according to claim 6, characterized in that: The stress-deformation optimization model is: ； In the formula, x 1 represents the stress at the first dangerous point, x 2 represents the deformation of the first dangerous point, L 0 is the preset remaining useful life of the crane, L N is the actual remaining service life of the crane, min[·] is the fitness function based on the minimum value, T ( x 1, x 2) The stress and deformation of the first dangerous point are x 1 and x 2 is the calculated value of the load-bearing capacity index of the crane, μ is the allowable value of the load-bearing capacity index of the metal structure of the crane, X 1down represents the minimum stress threshold of the first danger point, X 1now represents the current maximum stress threshold of the crane, X 2down represents the minimum deformation threshold of the first dangerous point, X 2now Indicates the current maximum deformation threshold of the crane.

Images