CN115563549A - Welding defect cause diagnosis method and system and electronic equipment - Google Patents
Welding defect cause diagnosis method and system and electronic equipment Download PDFInfo
- Publication number
- CN115563549A CN115563549A CN202211323505.2A CN202211323505A CN115563549A CN 115563549 A CN115563549 A CN 115563549A CN 202211323505 A CN202211323505 A CN 202211323505A CN 115563549 A CN115563549 A CN 115563549A
- Authority
- CN
- China
- Prior art keywords
- diagnosis
- fuzzy
- rule
- neural network
- cause
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/048—Fuzzy inferencing
Abstract
The invention relates to a welding defect cause diagnosis method, a system and electronic equipment, wherein the method carries out defect diagnosis by establishing a fuzzy diagnosis rule and a cause diagnosis neural network database and combining the two databases, the method carries out previous item expansion based on a traditional fuzzy rule and adds a threshold value, a sample rule selected from the fuzzy diagnosis rule is used for carrying out fuzzy reasoning, if the sample rule with actual credibility larger than a preset threshold value exists, a target diagnosis result can be obtained according to the sample rule, and if the sample rule does not exist, the cause diagnosis neural network is used for carrying out supplementary processing so as to obtain an ideal target diagnosis result. Compared with the traditional fuzzy neural network, the fuzzy neural network fuzzy inference method combines two theories of a fuzzy rule and a neural network, has the advantages that fuzzy inference can process uncertain knowledge, also has the advantages of self learning, high efficiency and high precision of the neural network, greatly improves the reliability of the inference process, and is more suitable for welding the scene with multiple influence factors.
Description
Technical Field
The invention relates to the technical field of welding defect diagnosis, in particular to a method and a system for diagnosing welding defect cause and electronic equipment.
Background
Analysis of causes of welding defects is difficult in the welding field, and due to the fact that the types and the forms of the defects are various and the causes of the defects are complex, diagnosis of the causes of the defects depends on manual experience too much, and therefore efficiency and reliability are extremely low. To solve this problem, a welding expert system having an intelligent diagnosis function is gradually applied.
For the research of welding defect cause detection, a welding defect analysis system based on big data is proposed in the Chinese patent (CN 109447403A), but the diagnosis of the final welding defect cause is directly influenced by the quality of the selected data set, and a knowledge base does not have corresponding self-learning capability and lacks generality. Chinese patent "a welding defect diagnosis method based on sparse matrix" (CN 105223275A) proposes a welding defect diagnosis method based on sparse matrix, but the database sources obtained by the method are self-made standard samples with single prefabricated defects, and are not suitable for the detection of multi-defect non-standard weldments.
It can be known from the above research that deductive reasoning is mostly performed based on production rules in the prior art, that is, deduction is performed based on existing samples and existing data sets, so that complex nonlinear relations among defect characteristics, process parameters and welding defect causes cannot be well reflected, the diagnosis accuracy is low, the method is not suitable for diagnosing and identifying the nonlinear and multi-classification problems of the welding defects, and uncertain knowledge cannot be well processed.
Disclosure of Invention
In view of the above, it is necessary to provide a method, a system and an electronic device for diagnosing the cause of the welding defect, so as to solve the problem that the existing welding defect cause diagnosis technology is too dependent on the existing samples, and cannot well deal with the non-linearity, multi-classification and uncertain knowledge of the welding defect diagnosis.
In order to achieve the technical purpose, the invention adopts the following technical scheme:
in a first aspect, the present invention provides a method for diagnosing cause of welding defect, including:
determining evaluation factors and defect causes, and establishing a plurality of fuzzy diagnosis rules for representing fuzzy relations between the evaluation factors and the defect causes based on fuzzy rules of expansion antecedents;
establishing a cause diagnosis neural network model, wherein input parameters of the cause diagnosis neural network model comprise welding defect types and the evaluation factors, and output parameters of the cause diagnosis neural network model comprise diagnosis results;
acquiring actual welding defect types and evaluation factor data corresponding to the defects to be diagnosed;
based on the evaluation factor data, selecting a matched fuzzy diagnosis rule from the fuzzy diagnosis rules as a sample rule, and carrying out fuzzy reasoning on the sample rule to obtain the actual credibility of each sample rule;
and judging whether the sample rule with the actual reliability larger than a preset threshold exists, if so, obtaining a target diagnosis result according to the defect cause of the sample rule with the actual reliability larger than the preset threshold, and if not, diagnosing a neural network model according to the cause to obtain the target diagnosis result.
Further, the determining of the evaluation factor and the defect cause, and establishing a plurality of fuzzy diagnosis rules for characterizing the fuzzy relation between the evaluation factor and the defect cause based on the fuzzy rule of the expansion antecedent, include:
establishing a welding characteristic information base, and obtaining the evaluation factors and the defect causes according to the welding characteristic information base;
establishing a plurality of fuzzy diagnosis rules based on the fuzzy rules of the expansion antecedents according to the evaluation factors;
wherein each fuzzy diagnosis rule comprises a front term, a back term, a theoretical reliability and the preset threshold, the front term comprises a plurality of the evaluation factors, and the back term comprises the defect cause.
Further, the selecting, based on the evaluation factor data, a matched fuzzy diagnosis rule from the plurality of fuzzy diagnosis rules as a sample rule, and performing fuzzy inference on the sample rule to obtain the actual reliability of each sample rule includes:
selecting a matched fuzzy diagnosis rule from a plurality of diagnosis rules as the sample rule based on the evaluation factor data;
obtaining a weight coefficient of each evaluation factor for the actual welding defect type based on an analytic hierarchy process according to the actual welding defect type;
obtaining the membership degree of each evaluation factor in the sample rule according to the evaluation factor data;
and calculating the actual reliability of each sample rule according to the weight coefficient and the membership degree.
Further, obtaining a weight coefficient of each evaluation factor for the actual welding defect type based on an analytic hierarchy process according to the actual welding defect type includes:
establishing a pair comparison matrix of the evaluation factors according to the actual welding defect type;
carrying out consistency check on the paired comparison matrixes, and adjusting the paired comparison matrixes according to a check result;
obtaining a feature vector of the adjusted paired comparison matrix according to the adjusted paired comparison matrix;
and normalizing the characteristic vector to obtain a weight coefficient of each evaluation factor for the actual welding defect type.
Further, the determining whether the sample rule with the actual reliability greater than a preset threshold exists or not, if yes, obtaining a target diagnosis result according to a defect cause of the sample rule with the actual reliability greater than the preset threshold, and if not, obtaining a target diagnosis result according to the cause diagnosis neural network model, including:
sequencing the sample rules according to the numerical value of the actual credibility to obtain a sample rule sequence;
and judging whether the actual credibility of the sample rule is larger than the corresponding preset threshold value, if so, selecting a set number of defect causes of the sample rule with the highest actual credibility according to the sample rule sequence to obtain the target diagnosis result, otherwise, inputting the evaluation factor data and the actual welding defect type into the cause diagnosis neural network model to obtain the target diagnosis result.
Further, the establishing of the cause diagnosis neural network model includes:
establishing an initial BP neural network model, wherein input parameters of the initial BP neural network model comprise a plurality of evaluation factors, and output parameters of the initial BP neural network model comprise the diagnosis result;
acquiring initial parameters of the initial BP neural network model, and optimizing through a PSO-BP algorithm to obtain optimized parameters;
and optimizing the initial BP neural network model according to the optimization parameters to obtain the cause diagnosis neural network model.
Further, the obtaining of the initial parameter of the initial BP neural network model and the optimization by the PSO-BP algorithm to obtain the optimized parameter includes:
acquiring initial parameters of the initial BP neural network model, wherein the initial parameters comprise weight values, threshold values and loss functions of neurons;
establishing a solution space and a particle population according to the weight and the threshold of the neuron, and initializing the position of the particle population in the solution space;
establishing a fitness function according to the loss function;
optimizing the position of the particle population in the solution space according to the fitness function;
and obtaining the position of the optimized particle population in the solution space to obtain the optimization parameter.
In a second aspect, the present invention also provides a welding defect cause diagnosis system, including:
the rule establishing module is used for determining evaluation factors and defect causes and establishing a plurality of fuzzy diagnosis rules for representing fuzzy relations between the evaluation factors and the defect causes on the basis of fuzzy rules of expansion antecedents;
the network establishing module is used for establishing a cause diagnosis neural network model, wherein input parameters of the cause diagnosis neural network model comprise welding defect types and the evaluation factors, and output parameters of the cause diagnosis neural network model comprise diagnosis results;
the data acquisition module is used for acquiring the actual welding defect type and evaluation factor data corresponding to the defect to be diagnosed;
the fuzzy reasoning module is used for selecting a matched fuzzy diagnosis rule from the plurality of fuzzy diagnosis rules as a sample rule based on the evaluation factor data, and carrying out fuzzy reasoning on the sample rule to obtain the actual credibility of each sample rule;
and the result diagnosis module is used for judging whether the sample rule with the actual reliability larger than a preset threshold exists, if so, obtaining a target diagnosis result according to the defect cause of the sample rule with the actual reliability larger than the preset threshold, and if not, obtaining the target diagnosis result according to the neural network model.
In a third aspect, the present invention also provides an electronic device comprising a memory and a processor, wherein,
a memory for storing a program;
and the processor is coupled with the memory and used for executing the program stored in the memory so as to realize the steps in the welding defect cause diagnosis method in any implementation mode.
The invention provides a welding defect cause diagnosis method, a system and electronic equipment, wherein the method diagnoses the welding defect by establishing a fuzzy diagnosis rule and a cause diagnosis neural network database and combining the two databases, concretely, the method is firstly based on the traditional fuzzy rule to carry out the previous item expansion and add a threshold value, and carries out fuzzy reasoning by using a sample rule selected from the fuzzy diagnosis rule, if the sample rule with actual credibility larger than the preset threshold value exists, a target diagnosis result can be obtained according to the sample rule, if the sample rule does not exist, the existing fuzzy diagnosis rule can not process the existing fact, and at the moment, the cause diagnosis neural network is utilized to carry out supplementary processing, so that an ideal target diagnosis result can be obtained. Compared with the prior art, the method combines the fuzzy rule theory and the neural network theory, so that the diagnosis process has the advantages of fuzzy reasoning capable of processing uncertain knowledge, and also has the advantages of neural network self-learning, high efficiency and high precision, the reliability of the reasoning process is greatly improved, and compared with the traditional fuzzy neural network model, the method is more suitable for welding the scene with multiple influence factors.
Drawings
FIG. 1 is a flowchart of a method of diagnosing a cause of a weld defect according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a welding characteristic information base established in an embodiment of a method for diagnosing a cause of a welding defect according to the present invention;
FIG. 3 is a flowchart of a method of step S104 in FIG. 1;
FIG. 4 is a flowchart of a method of step S302 in FIG. 3;
FIG. 5 is a schematic structural diagram of an embodiment of a weld defect cause diagnosis system provided in the present invention;
fig. 6 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate preferred embodiments of the invention and together with the description, serve to explain the principles of the invention and not to limit the scope of the invention.
In the description of the present application, "a plurality" means two or more unless specifically limited otherwise.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the invention. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
According to the welding defect cause diagnosis method, system and electronic equipment, on one hand, the capability of processing uncertain knowledge is improved by using a fuzzy theory; on the other hand, the fact that fuzzy reasoning cannot be processed is subjected to supplementary reasoning by using a connection mechanism of the neural network, so that the neural network has the advantages of two theories, is beneficial to diagnosing the welding defect cause under the condition of lacking rules or low matching degree, and has important engineering practice significance for promoting the automation of the welding process.
The invention provides a method and a system for diagnosing welding defect cause and an electronic device, which are respectively explained below.
Referring to fig. 1, a method for diagnosing causes of weld defects is disclosed in an embodiment of the present invention, which includes:
s101, determining evaluation factors and defect causes, and establishing a plurality of fuzzy diagnosis rules for representing fuzzy relations between the evaluation factors and the defect causes based on fuzzy rules of expansion antecedents;
s102, establishing a cause diagnosis neural network model, wherein input parameters of the cause diagnosis neural network model comprise welding defect types and the evaluation factors, and output parameters of the cause diagnosis neural network model comprise diagnosis results;
s103, acquiring actual welding defect types and evaluation factor data corresponding to the defects to be diagnosed;
s104, based on the evaluation factor data, selecting a matched fuzzy diagnosis rule from the fuzzy diagnosis rules as a sample rule, and carrying out fuzzy reasoning on the sample rule to obtain the actual credibility of each sample rule;
s105, judging whether the sample rule with the actual credibility larger than a preset threshold exists, if so, obtaining a target diagnosis result according to the defect cause of the sample rule with the actual credibility larger than the preset threshold, and if not, diagnosing a neural network model according to the cause to obtain a target diagnosis result.
The invention provides a welding defect cause diagnosis method, a system and electronic equipment, wherein the method diagnoses the welding defect by establishing a fuzzy diagnosis rule and a cause diagnosis neural network database and combining the two databases, concretely, the method is firstly based on the traditional fuzzy rule to carry out the previous item expansion and add a threshold value, and carries out fuzzy reasoning by using a sample rule selected from the fuzzy diagnosis rule, if the sample rule with actual credibility larger than the preset threshold value exists, a target diagnosis result can be obtained according to the sample rule, if the sample rule does not exist, the existing fuzzy diagnosis rule can not process the existing fact, and at the moment, the cause diagnosis neural network is utilized to carry out supplementary processing, so that an ideal target diagnosis result can be obtained. Compared with the prior art, the method combines two theories of fuzzy rules and the neural network, so that the diagnosis process has the advantages that fuzzy reasoning can process uncertain knowledge, and the neural network self-learning, high efficiency and high precision, the reliability of the reasoning process is greatly improved, and the method is more suitable for welding the scene with multiple influence factors compared with the traditional fuzzy neural network model.
It should be noted that the evaluation factors in this embodiment include any influencing factors that can cause the welding defect, the defect cause refers to a specific quantitative condition of the influencing factors that form the defect to be diagnosed, which indicates the specific cause of the defect, and the diagnosis result includes the defect cause and a diagnosis conclusion that can be derived according to the defect cause, such as the cause that the defect may occur, the possibility of each cause, a process optimization scheme, and the like.
Specifically, as a preferred embodiment, the step S101 in this embodiment of determining an evaluation factor and a defect cause, and establishing a plurality of fuzzy diagnosis rules for characterizing a fuzzy relationship between the evaluation factor and the defect cause based on the fuzzy rule of the pre-expansion item specifically includes:
establishing a welding characteristic information base, and obtaining the evaluation factors and the defect causes according to the welding characteristic information base;
according to the evaluation factors, establishing a plurality of fuzzy diagnosis rules based on a fuzzy rule of an expansion foreitem, wherein each fuzzy diagnosis rule comprises a foreitem, a postitem, theoretical credibility and the preset threshold, the foreitem comprises a plurality of evaluation factors, and the postitem comprises the defect cause.
Compared with the traditional fuzzy rule model, the welding cause obtained by the method better meets the diagnosis requirement of actual welding.
Fig. 2 shows a welding characteristic information base established in this embodiment, which may be directly obtained from the prior art, and then, according to actual needs, a test or other mode is selected to determine required evaluation factors from the welding characteristic information base.
In this embodiment, the determined evaluation factors include: welding method C 0 Defect relative center distance C 1 Two defects closest distance C 2 Defect length-width ratio C 3 Thickness C of board 4 Welding current C 5 Welding voltage C 6 Welding speed C 7 Wire feeding speed C 8 Gas flow rate C 9 Ten factors.
After the evaluation factors are determined, the fuzzy diagnosis rule can be established, in the embodiment, the fuzzy diagnosis rule is designed by adopting the C-F model based on the fuzzy rule, and is further expanded, specifically, the previous item is expanded, and the membership degree of each condition is increased. The fuzzy diagnostic rule in this embodiment is designed as follows:
IF E 1 (α 1 ,η 1 )AND E 2 (α 2 ,η 2 )…AND E n (α n ,η n )THEN H(CF(H),λ)
wherein E is 1 、E 2 、…、E n All correspond to various known facts, namely the actual conditions of various evaluation factors; alpha is alpha 1 、α 2 、…、α n In the present embodiment, the weight coefficient, i.e., the influence degree of each fact on the defect cause, is ensured
η 1 ,η 2 ,…,η n Representing the degree of membership of the fact, CF (H) representing the theoretical confidence of the whole rule, and λ being a preset threshold for this rule. In the above parameters, the weight coefficient and the membership degree are correspondingly calculated in the subsequent steps according to the actual situation.
The following table is a part of the fuzzy diagnostic rules established in this example:
partial rules for diagnosing cause of defect
Reasoning is carried out through the fuzzy diagnosis rule, and compared with a traditional fuzzy rule model, the fuzzy diagnosis rule model is more suitable for a scene with multiple influence factors, the judgment accuracy is improved, a reasonable analysis scheme can be provided, an artificial expert is effectively replaced, a large amount of time and labor cost are saved, an operator is helped to timely and effectively reduce the influence caused by welding defects, and the automation degree of welding production is improved. Meanwhile, as a preferred embodiment, in step S102 in this embodiment, a cause diagnosis neural network model is established, input parameters of the cause diagnosis neural network model include a welding defect type and the evaluation factor, and output parameters of the cause diagnosis neural network model include a diagnosis result, which specifically includes:
establishing an initial BP neural network model, wherein input parameters of the initial BP neural network model comprise a plurality of evaluation factors, and output parameters of the initial BP neural network model comprise diagnosis results;
acquiring initial parameters of the initial BP neural network model, and optimizing through a PSO-BP algorithm to obtain optimized parameters;
and optimizing the initial BP neural network model according to the optimization parameters to obtain the cause diagnosis neural network model.
Specifically, in a preferred embodiment, the obtaining of the initial parameter of the initial BP neural network model in the above process and the optimization by the PSO-BP algorithm to obtain the optimized parameter specifically include:
acquiring initial parameters of the initial BP neural network model, wherein the initial parameters comprise weight values, threshold values and loss functions of neurons;
establishing a solution space and a particle population according to the weight and the threshold of the neuron, and initializing the position of the particle population in the solution space;
establishing a fitness function according to the loss function;
optimizing the position of the particle population in the solution space according to the fitness function;
and obtaining the position of the optimized particle population in the solution space to obtain the optimization parameter.
In order to more conveniently understand the above process, the present invention further provides a more specific embodiment, in which:
(1) Collecting welding experiment data, and establishing a single-hidden-layer BP neural network welding defect analysis model as an initial BP neural network model according to the process experiment data, wherein input parameters of the initial BP neural network model comprise a plurality of evaluation factors, and output parameters of the initial BP neural network model comprise diagnosis results;
(2) In order to further improve the convergence efficiency and accuracy of the model, an initial value and parameter updating improvement is performed on the initial BP neural network model by using an initial parameter of the initial BP neural network through an improved PSO-BP algorithm, and the specific flow comprises the following steps:
(1) setting specific parameters of a particle swarm algorithm by using initial parameters of an initial BP neural network, setting weights and thresholds of all neurons in an initial BP neural network structure as position variables of particles, and establishing a solution space and a particle population according to the weights and the thresholds of the neurons; setting a loss function of the initial BP neural network as a fitness function of the particles, and initializing a population of the particles, namely initializing the positions of the population of the particles in the solution space;
(2) for each example, a fitness f of the particle may be calculated i And a minimum fitness f to the particle min Making a comparison if f i ＜f min Then the updated fitness is taken as the minimum fitness f of the particle min The corresponding position is the optimum position P i ；
(3) The particle swarm searches the whole state space by updating the speed and the position of the particle swarm, and updates the particle swarm by tracking an individual extreme value (the optimal solution of the optimal fitness found by the particle itself) and a global extreme value (the optimal solution of the optimal fitness found by the whole swarm at present) until the optimal solution is found;
the evolution formula of the speed and the position of the particles in the process is as follows:
in the formula, omega is nonlinear dynamic change inertia weight; c. C 1 And c 2 Is a learning factor; r is a radical of hydrogen 1 And r 2 To take on a value of [0,1]A random number in between; p is a radical of formula in (k) Representing an extreme value of the individual positions of the particles; p is a radical of gn (k) Representing a particle global position extremum; x is the number of in (k) Is the position of particle i at time k; x is the number of in (k + 1) is the position of particle i at time k + 1; v. of in (k) Is the velocity of particle i at time k; v. of in (k + 1) is the velocity of particle i at time k + 1;
wherein the nonlinear dynamically changing inertia weight ω is represented as:
wherein, ω is min Is the minimum inertial weight; omega max Is the maximum inertial weight,/ 1 (t) is a non-linear function, l 2 (t) is a linear function, f i As a fitness of the current particle, f min Is the minimum fitness of the particle. l. the 1 (t)、l 2 (t) is determined by the following formula:
where t is the current iteration number of the model, t max The maximum number of iterations of the model;
(4) calculating the minimum fitness f of the whole particle swarm g ＝min{f 1 ，f 2 ，…，f M Judging whether the current iteration times reach the set maximum iteration times, if so, stopping the iteration, otherwise, turning to the step (2) to continue updating;
(5) outputting the neural network parameter P determined by the whole particle swarm g ＝(p g1 ,p g2 ,...,p gD ) As an initial value for the neural network structure. And combining the particle swarm optimization algorithm with the gradient descent algorithm, and further iteratively updating the neural network parameters by using the dynamic weight factors. And outputting the initial parameters of the neural network determined by the improved PSO-BP algorithm, and replacing the corresponding parameters of the initial BP neural network to optimize the initial BP neural network model to obtain the cause diagnosis neural network model.
The following table shows specific values of some other parameters required in the above process of the present embodiment:
adaptive PSO-BP algorithm parameter setting based on dynamic weight
In the neural network structure of the embodiment, the original gradient descent algorithm is reserved by the updating mode of the network parameters, the dynamic weight factor is introduced, the PSO algorithm and the BP algorithm are combined, the advantages of different algorithms are played at different stages of iteration, and the training speed and the iteration efficiency are improved. The fact that fuzzy rule reasoning cannot be determined is subjected to supplementary diagnosis by using the PSO-BP neural network model obtained through training, the reason for forming the welding defects is determined, the model is corrected according to the evaluation result, for example, the output result is used as a new fuzzy diagnosis rule, so that the whole method has the characteristic of self-learning, the problem that the prior art excessively depends on the existing sample is effectively solved, and the training efficiency and the diagnosis precision of the model are effectively improved; the rule reasoning and the model reasoning are combined to form a rule-model cooperative reasoning mechanism, compared with the traditional neural network or a fuzzy neural network, the self-learning capability of the rule-model cooperative reasoning mechanism is improved, the rule-model cooperative reasoning mechanism is more suitable for welding the scene with multiple influence factors, and the reliability of a reasoning mode is improved.
After the fuzzy diagnosis rule and the cause diagnosis neural network model are established, actual diagnosis can be started, and firstly, step S103 needs to be performed to obtain an actual welding defect type and evaluation factor data corresponding to the defect to be diagnosed, wherein the evaluation factor data is an actual numerical value corresponding to the evaluation factor of the defect to be diagnosed.
Further, as shown in fig. 3, as a preferred embodiment, in step S104 in this embodiment, based on the evaluation factor data, a matched fuzzy diagnosis rule is selected from the plurality of fuzzy diagnosis rules as a sample rule, and fuzzy inference is performed on the sample rule to obtain the actual reliability of each sample rule, which specifically includes:
s301, based on the evaluation factor data, selecting a matched fuzzy diagnosis rule from the plurality of diagnosis rules as the sample rule;
s302, obtaining a weight coefficient of each evaluation factor for the actual welding defect type based on an analytic hierarchy process according to the actual welding defect type;
s303, obtaining the membership degree of each evaluation factor in the sample rule according to the evaluation factor data;
s304, calculating to obtain the actual credibility of each sample rule according to the weight coefficient and the membership degree.
The above process is the main step of the fuzzy inference in this embodiment, and it can be understood that, because the fuzzy inference is the prior art that can be understood by those skilled in the relevant field, actually, other fuzzy inference methods may also be adopted to obtain the confidence level.
As a preferred embodiment, in this embodiment, an apparently unreasonable rule is removed from a plurality of fuzzy diagnosis rules, a proper rule is selected as a sample rule, and then step S302 is performed, specifically, referring to fig. 4, step S302 in this embodiment, obtaining a weight coefficient of each evaluation factor for the actual welding defect type based on an analytic hierarchy process according to the actual welding defect type, specifically includes:
s401, establishing a pair comparison matrix of the evaluation factors according to the actual welding defect type;
s402, carrying out consistency check on the paired comparison matrixes, and adjusting the paired comparison matrixes according to a check result;
s403, obtaining a feature vector of the adjusted paired comparison matrix according to the adjusted paired comparison matrix;
s404, normalizing the characteristic vectors to obtain a weight coefficient of each evaluation factor for the actual welding defect type.
The present invention further provides a more specific embodiment to explain the above processes S401 to S404:
according to the actual welding type, determining the relative importance of each evaluation factor by a field expert, comparing every two evaluation factors, and adopting the relative comparison scale of 1-5 shown in the following table during comparison:
relative comparative scale
Using the relative comparison metrics, a pairwise comparison matrix a is obtained as follows:
the calculation of each element in matrix a is calculated as follows:
wherein i, j, k =0,1,2, 3.
According to the obtained paired comparison matrix A, obtaining the maximum characteristic root lambda max The corresponding feature vector is taken as the weight vector ω, i.e. a ω = λ max . And carrying out normalization processing on the weight vector to obtain a final weight coefficient.
Because different evaluation factors have different influences on different types of defect characteristics, the above process needs to be flexibly set according to the actual welding defect type, in this embodiment, the "welding through" defect is taken as an example, and the importance of different evaluation factors on the welding defect cause is compared, so as to obtain a pairwise comparison matrix a as follows:
after the comparison matrix is obtained, consistency check needs to be performed on the comparison matrix to verify the rationality, and the comparison process can be performed by calculating a consistency index CR:
the weight distribution of the established paired comparison matrix to the relevant parameters is reasonable, the reliability is high, and the weight coefficient can be calculated. In this embodiment, the final weight coefficient vector β of "welding through" obtained according to the matrix is:
β＝(0.25,0.05,0.05,0.06,0.09,0.13,0.13,0.09,0.09,0.06)
as described aboveThe process is only the weight coefficient of one actual welding defect type, and actually different welding defect types need to be purposefully and independently established into a pair comparison matrix and calculated into the weight coefficient. In this example, there are ten influencing factors C i Corresponding to four different types of defects S i The resulting defect weight coefficient table is shown in the following table.
Defect weight coefficient table
After determining the weighting coefficients, step S303 and step S304 may be performed, in which the membership degree of each fact is determined by using a membership degree function according to the evaluation factor data, and a specific process thereof is the prior art and will not be described herein. Then, step S304 is performed, in this embodiment, the actual reliability λ of each fuzzy diagnosis rule g Can be calculated from the following formula:
for convenience of understanding, the present invention also provides a specific embodiment for explaining the above calculation process of the actual reliability. The evaluation factor data obtained in this embodiment is: welding method M 'pulse arc welding' with relative central distance of defect l 1 3mm, the closest distance l between two defects 2 "1.2mm", defect aspect ratio δ "1.1", plate thickness b "6mm", welding current I "142A", welding voltage U "19.8V", welding speed V h 0.36m/min, wire feed speed V s 9.0m/min, gas flow V q "25L". The actual welding defect type is 'air holes', and the weighting coefficient S of each evaluation factor for the defects such as 'air holes' can be known through the process 3 0.25,0.05, 0.06,0.08,0.06, 0.13, and the actual confidence levels λ of the three fuzzy diagnostic rules (i.e., rule 1, rule 2, rule 3 in the above table) can be obtained g1 、λ g2 、λ g3 ：
λ g1 ＝0.95×(0.25×1+0.05×1+0.05×1+0.06×1+0.08×1+0.06×0.9+0.06×0.9+0.13×1+0.13×1+0.13×1)＝0.9386
λ g2 ＝0.95×(0.25×1+0.05×1+0.05×1+0.06×1+0.08×1+0.06×0.9+0.06×0.9+0.13×1+0.13×1+0.13×0)＝0.8151
λ g3 ＝0.90×(0.25×1+0.05×1+0.05×1+0.06×1+0.08×1+0.06×0.9+0.06×0.9+0.13×0.5+0.13×1+0.13×0.5)＝0.7722
After calculating the actual reliability, step S105 may be performed to determine whether the sample rule with the actual reliability greater than the preset threshold exists, if so, obtain a target diagnosis result according to a defect cause of the sample rule with the actual reliability greater than the preset threshold, and if not, obtain a target diagnosis result according to the neural network model, which is used as a preferred embodiment, where the step in this embodiment specifically includes:
sequencing the sample rules according to the numerical value of the actual credibility to obtain a sample rule sequence;
and judging whether the actual credibility of the sample rule is larger than the corresponding preset threshold value, if so, selecting a set number of defect causes of the sample rule with the highest actual credibility according to the sample rule sequence to obtain the target diagnosis result, otherwise, inputting the evaluation factor data and the actual welding defect type into the cause diagnosis neural network model to obtain the target diagnosis result.
In this embodiment, the three actual reliability levels are compared with the preset threshold λ for each rule, so that the comprehensive reliability λ of rule 1 can be obtained g1 =0.9386 is greater than the threshold λ =0.88, λ of the remaining two rules g Less than λ, so only rule 1 is activated and used, and finally it can be derived from rule 1 that the cause of the band diagnostic defect may be an excessive gas flow and its confidence level is 0.9386.
It is understood that, in the present embodiment, each will beThe actual credibility is compared with the self preset threshold of the corresponding rule, and in practice, the same preset threshold can be uniformly set for comparison. When λ exists g And when the rule is larger than or equal to lambda, the diagnostic result of the defect cause corresponding to the rule is credible, and after all the rules are retrieved, if the actual credibility of a plurality of fuzzy diagnostic rules is larger than a preset threshold value, a set number (for example, three) of fuzzy diagnostic rules can be selected from the rules and are all used as the final diagnostic result.
And when the comprehensive credibility lambdag of all the rules is smaller than the threshold lambdag, the existing fuzzy diagnosis rules are not credible, and then a neural network model can be further selected for reasoning. Normalizing the input features, then introducing the normalized input features into a model, reasoning by using a cause diagnosis neural network model obtained by training, outputting a reasonable welding defect cause by the network model in a specific form (such as the probability of each defect cause), and then evaluating the output result of the model by a user to finally obtain a defect cause diagnosis scheme or a model correction report.
In order to verify the application effect of the method in actual production, 5 test samples are randomly selected in the production of the enterprise tank body, and the test samples are shown in the following table.
Test specimen
In the test, the system gives reasoning results for samples 2 to 5 according to fuzzy rules, as shown in the following table, wherein the real value of the defect cause is actually acquired evaluation factor data in the preceding text, and the rule reasoning credibility is the actual credibility in the preceding text:
true value of defect cause and rule reasoning result
Whereas for sample 1 there is a regular synthetic confidence λ g Under the condition of being lower than the preset threshold lambda, the cause diagnosis neural network model is adopted to carry out auxiliary reasoning, and the real values of the defect causes and the network output results are shown in the following table:
real value of defect cause and model output result
Taking the diagnosis of the aluminum alloy welding gas hole defect (sample 1) in an enterprise as an example for testing, it can be seen that, through the auxiliary diagnosis of the self-adaptive PSO-BP neural network model based on the dynamic weight, it is inferred that 99.51% of the input gas hole defect is caused by the overlarge welding speed, 0.38% of the input gas hole defect is caused by the overlarge gas flow, and 0.11% of the input gas hole defect is caused by the overlarge gas flow.
In order to better implement the method for diagnosing the cause of the welding defect in the embodiment of the present invention, on the basis of the method for diagnosing the cause of the welding defect, correspondingly, please refer to fig. 5, fig. 5 is a schematic structural diagram of an embodiment of a system for diagnosing the cause of the welding defect according to the present invention, and a system 500 for diagnosing the cause of the welding defect according to the embodiment of the present invention includes:
a rule establishing module 510, configured to determine an evaluation factor and a defect cause, and establish a plurality of fuzzy diagnosis rules for characterizing a fuzzy relationship between the evaluation factor and the defect cause based on a fuzzy rule of a pre-expansion item;
a network establishing module 520 for establishing a cause diagnosis neural network model, wherein input parameters of the cause diagnosis neural network model comprise welding defect types and the evaluation factors, and output parameters of the cause diagnosis neural network model comprise diagnosis results;
a data obtaining module 530, configured to obtain an actual welding defect type and evaluation factor data corresponding to the defect to be diagnosed;
the fuzzy inference module 540 is configured to select a matched fuzzy diagnosis rule from the plurality of fuzzy diagnosis rules as a sample rule based on the evaluation factor data, and perform fuzzy inference on the sample rule to obtain an actual reliability of each sample rule;
and a result diagnosis module 550, configured to determine whether the sample rule with the actual reliability greater than a preset threshold exists, if yes, obtain a target diagnosis result according to a defect cause of the sample rule with the actual reliability greater than the preset threshold, and if not, obtain a target diagnosis result according to the neural network model.
Here, it should be noted that: the corresponding system 500 provided in the foregoing embodiments may implement the technical solutions described in the foregoing method embodiments, and the specific implementation principle of each module or unit may refer to the corresponding content in the foregoing method embodiments, and is not described here again.
In addition, the present invention also provides an embodiment of a weld defect cause diagnosis system, the system comprising:
a database module: the functions of data retrieval and query are carried out on materials, processes and defect identification characteristics required by welding, and the storage cost of data and the time cost of data query are saved. Meanwhile, the system administrator is given authority to increase, decrease and maintain data in the system;
a defect identification module: the user can upload the X-ray negative in the system, and the system identifies the X-ray negative by adopting the convolutional neural network with super-resolution reconstruction so as to acquire relevant characteristics of the welding defect, such as defect type, area, length-width ratio and the like;
a defect cause diagnosis module: the cause diagnosis is carried out on the welding defects by combining the data in the database and the defect identification characteristics, and the system determines the welding defect cause with the highest confidence coefficient by using the welding defect cause diagnosis method;
a process optimization module: the system designed by the method comprises two optimization modes, wherein the first mode is from the diagnosis level of the defect cause, and after the defect cause is obtained, a process optimization scheme is given according to the defect cause to obtain a defect-free welding seam; the second mode is that the multi-target particle swarm optimization (MOPSO) is utilized to carry out multi-target optimization on the welding seam performance from the welding seam performance, and the welding seam performance index meeting the industrial requirement is obtained through the regulation and control of technological parameters;
the user authority management module: for the security of the database, the user authority is divided into a system administrator, a system operator and a common user. A system administrator can use a user authority management module to endow all users in the system with related authorities; the system operator can increase, decrease and maintain the database; ordinary users can only search and consult the database, and cannot perform other operations on the database.
Further, please refer to fig. 6, where fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. Based on the above method for diagnosing the cause of the welding defect, the present invention also provides a device 600 for diagnosing the cause of the welding defect, i.e. the electronic device, wherein the device 600 for diagnosing the cause of the welding defect can be a mobile terminal, a desktop computer, a notebook computer, a palm computer, a server, and other computing devices. The welding defect cause diagnosis apparatus 600 includes a processor 610, a memory 620, and a display 630. Fig. 6 shows only some of the components of the weld defect cause diagnostic apparatus, but it should be understood that not all of the shown components are required and that more or fewer components may be implemented instead.
The memory 620 may be an internal storage unit of the welding defect cause diagnosis apparatus 600 in some embodiments, such as a hard disk or a memory of the welding defect cause diagnosis apparatus 600. The memory 620 may also be an external storage device of the welding-defect-cause diagnosing apparatus 600 in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the welding-defect-cause diagnosing apparatus 600. Further, the memory 620 may also include both an internal storage unit and an external storage device of the welding defect cause diagnosis apparatus 600. The memory 620 is used for storing application software installed in the welding defect cause diagnosis apparatus 600 and various types of data, such as program codes for installing the welding defect cause diagnosis apparatus 600. The memory 620 may also be used to temporarily store data that has been output or is to be output. In one embodiment, the memory 620 stores a welding defect cause diagnosis program 640, and the welding defect cause diagnosis program 640 can be executed by the processor 610, so as to implement the welding defect cause diagnosis method according to the embodiments of the present application.
The processor 610 may be a Central Processing Unit (CPU), microprocessor or other data Processing chip in some embodiments, and is used for executing program codes stored in the memory 620 or Processing data, such as performing a welding defect cause diagnosis method.
The display 630 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch panel, or the like in some embodiments. The display 630 is used to display information at the welding defect cause diagnosis apparatus 600 and to display a visual user interface. The components 610-630 of the weld defect cause diagnostic apparatus 600 communicate with each other via a system bus.
In one embodiment, the steps in the weld defect cause diagnostic method described above are implemented when the processor 610 executes the weld defect cause diagnostic program 640 in the memory 620.
The invention provides a welding defect cause diagnosis method, a system and electronic equipment, wherein the method diagnoses the welding defect by establishing a fuzzy diagnosis rule and a cause diagnosis neural network database and combining the two databases, concretely, the method is firstly based on the traditional fuzzy rule to carry out the previous item expansion and add a threshold value, and carries out fuzzy reasoning by using a sample rule selected from the fuzzy diagnosis rule, if the sample rule with actual credibility larger than the preset threshold value exists, a target diagnosis result can be obtained according to the sample rule, if the sample rule does not exist, the existing fuzzy diagnosis rule can not process the existing fact, and at the moment, the cause diagnosis neural network is utilized to carry out supplementary processing, so that an ideal target diagnosis result can be obtained. Compared with the prior art, the method combines two theories of fuzzy rules and the neural network, so that the diagnosis process has the advantages that fuzzy reasoning can process uncertain knowledge, and the neural network self-learning, high efficiency and high precision, the reliability of the reasoning process is greatly improved, and the method is more suitable for welding the scene with multiple influence factors compared with the traditional fuzzy neural network model.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention.
Claims (9)
1. A method for diagnosing cause of weld defect, comprising:
determining evaluation factors and defect causes, and establishing a plurality of fuzzy diagnosis rules for representing fuzzy relations between the evaluation factors and the defect causes on the basis of fuzzy rules of expansion antecedents;
establishing a cause diagnosis neural network model, wherein input parameters of the cause diagnosis neural network model comprise welding defect types and the evaluation factors, and output parameters of the cause diagnosis neural network model comprise diagnosis results;
acquiring actual welding defect types and evaluation factor data corresponding to defects to be diagnosed;
based on the evaluation factor data, selecting a matched fuzzy diagnosis rule from the fuzzy diagnosis rules as a sample rule, and carrying out fuzzy reasoning on the sample rule to obtain the actual credibility of each sample rule;
judging whether the sample rule with the actual reliability larger than a preset threshold exists, if so, obtaining a target diagnosis result according to the defect cause of the sample rule with the actual reliability larger than the preset threshold, and if not, diagnosing a neural network model according to the cause to obtain the target diagnosis result.
2. The welding defect cause diagnosis method according to claim 1, wherein the determining of the evaluation factor and the defect cause, and the establishing of the plurality of fuzzy diagnosis rules for characterizing the fuzzy relationship between the evaluation factor and the defect cause based on the fuzzy rules of the pre-expansion term, comprise:
establishing a welding characteristic information base, and obtaining the evaluation factors and the defect causes according to the welding characteristic information base;
establishing a plurality of fuzzy diagnosis rules based on the fuzzy rules of the expansion antecedents according to the evaluation factors;
wherein each fuzzy diagnosis rule comprises a front term, a back term, a theoretical reliability and the preset threshold, the front term comprises a plurality of the evaluation factors, and the back term comprises the defect cause.
3. The welding defect cause diagnosis method according to claim 2, wherein the selecting a matched fuzzy diagnosis rule from the plurality of fuzzy diagnosis rules as a sample rule based on the evaluation factor data, and performing fuzzy inference on the sample rule to obtain an actual reliability of each sample rule comprises:
selecting a matched fuzzy diagnosis rule from a plurality of diagnosis rules as the sample rule based on the evaluation factor data;
obtaining a weight coefficient of each evaluation factor for the actual welding defect type based on an analytic hierarchy process according to the actual welding defect type;
obtaining the membership degree of each evaluation factor in the sample rule according to the evaluation factor data;
and calculating the actual reliability of each sample rule according to the weight coefficient and the membership degree.
4. The welding defect cause diagnosis method according to claim 3, wherein the obtaining of the weight coefficient of each evaluation factor for the actual welding defect type based on an analytic hierarchy process according to the actual welding defect type comprises:
establishing a pair comparison matrix of the evaluation factors according to the actual welding defect type;
carrying out consistency check on the paired comparison matrixes, and adjusting the paired comparison matrixes according to a check result;
obtaining the feature vector of the adjusted paired comparison matrix according to the adjusted paired comparison matrix;
and normalizing the characteristic vectors to obtain a weight coefficient of each evaluation factor for the actual welding defect type.
5. The welding defect cause diagnosis method according to claim 3, wherein the determining whether the sample rule with the actual reliability being greater than a preset threshold exists is performed, if yes, a target diagnosis result is obtained according to the defect cause of the sample rule with the actual reliability being greater than the preset threshold, and if not, a target diagnosis result is obtained according to the cause diagnosis neural network model, and the method includes:
sequencing the sample rules according to the numerical value of the actual credibility to obtain a sample rule sequence;
and judging whether the actual credibility of the sample rule is larger than the corresponding preset threshold value, if so, selecting a set number of defect causes of the sample rule with the highest actual credibility according to the sample rule sequence to obtain the target diagnosis result, otherwise, inputting the evaluation factor data and the actual welding defect type into the cause diagnosis neural network model to obtain the target diagnosis result.
6. The weld defect cause diagnosis method according to claim 1, wherein the establishing a cause diagnosis neural network model includes:
establishing an initial BP neural network model, wherein input parameters of the initial BP neural network model comprise a plurality of evaluation factors, and output parameters of the initial BP neural network model comprise the diagnosis result;
acquiring initial parameters of the initial BP neural network model, and optimizing through a PSO-BP algorithm to obtain optimized parameters;
and optimizing the initial BP neural network model according to the optimization parameters to obtain the cause diagnosis neural network model.
7. The method for diagnosing cause of weld defect of claim 6, wherein the obtaining initial parameters of the initial BP neural network model and optimizing through PSO-BP algorithm to obtain optimized parameters comprises:
acquiring initial parameters of the initial BP neural network model, wherein the initial parameters comprise weight values, threshold values and loss functions of neurons;
establishing a solution space and a particle population according to the weight and the threshold of the neuron, and initializing the position of the particle population in the solution space;
establishing a fitness function according to the loss function;
optimizing the position of the particle population in the solution space according to the fitness function;
and obtaining the position of the optimized particle population in the solution space to obtain the optimization parameter.
8. A system for diagnosing causes of weld defects, comprising:
the rule establishing module is used for determining evaluation factors and defect causes and establishing a plurality of fuzzy diagnosis rules for representing fuzzy relations between the evaluation factors and the defect causes on the basis of fuzzy rules of expansion antecedents;
the network establishing module is used for establishing a cause diagnosis neural network model, wherein input parameters of the cause diagnosis neural network model comprise welding defect types and the evaluation factors, and output parameters of the cause diagnosis neural network model comprise diagnosis results;
the data acquisition module is used for acquiring the actual welding defect type and evaluation factor data corresponding to the defect to be diagnosed;
the fuzzy reasoning module is used for selecting a matched fuzzy diagnosis rule from the plurality of fuzzy diagnosis rules as a sample rule based on the evaluation factor data, and carrying out fuzzy reasoning on the sample rule to obtain the actual credibility of each sample rule;
and the result diagnosis module is used for judging whether the sample rule with the actual reliability higher than a preset threshold exists, if so, obtaining a target diagnosis result according to the defect cause of the sample rule with the actual reliability higher than the preset threshold, and if not, obtaining the target diagnosis result according to the neural network model.
9. An electronic device comprising a memory and a processor, wherein,
the memory is used for storing programs;
the processor, coupled to the memory, is configured to execute the program stored in the memory to implement the steps of the method for diagnosing cause of weld defect as set forth in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211323505.2A CN115563549B (en) | 2022-10-27 | 2022-10-27 | Welding defect cause diagnosis method and system and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211323505.2A CN115563549B (en) | 2022-10-27 | 2022-10-27 | Welding defect cause diagnosis method and system and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115563549A true CN115563549A (en) | 2023-01-03 |
| CN115563549B CN115563549B (en) | 2023-10-20 |
Family
ID=84769177
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211323505.2A Active CN115563549B (en) | 2022-10-27 | 2022-10-27 | Welding defect cause diagnosis method and system and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115563549B (en) |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5544256A (en) * | 1993-10-22 | 1996-08-06 | International Business Machines Corporation | Automated defect classification system |
| US5591355A (en) * | 1994-02-25 | 1997-01-07 | Miyachi Technos Corporation | Method for controlling resistance welding using fuzzy reasoning |
| KR20040088896A (en) * | 2003-04-14 | 2004-10-20 | 기아자동차주식회사 | Arc welding network system |
| WO2005071582A2 (en) * | 2004-01-27 | 2005-08-04 | British Telecommunications Public Limited Company | Detection of abnormal behaviour in dynamic systems |
| US20090037772A1 (en) * | 2007-08-03 | 2009-02-05 | Wegerich Stephan W | Fuzzy classification approach to fault pattern matching |
| CN102436524A (en) * | 2011-10-19 | 2012-05-02 | 清华大学 | Fuzzy reasoning method for soft fault diagnosis for analog circuit |
| CN103091112A (en) * | 2013-01-31 | 2013-05-08 | 林惠堂 | Method and device of car emission fault detection and diagnosis based on fuzzy reasoning and self-learning |
| CN105787563A (en) * | 2014-12-18 | 2016-07-20 | 中国科学院沈阳自动化研究所 | Self-learning mechanism-base fast matching fuzzy reasoning method |
| CN106909727A (en) * | 2017-02-20 | 2017-06-30 | 武汉理工大学 | Laser welding temperature field Finite Element Method based on BP neural network and Genetic Algorithms |
| CN106919982A (en) * | 2017-03-20 | 2017-07-04 | 中国科学院沈阳自动化研究所 | A kind of method for diagnosing faults towards semiconductor manufacturing equipment |
| CN106961249A (en) * | 2017-03-17 | 2017-07-18 | 广西大学 | A kind of diagnosing failure of photovoltaic array and method for early warning |
| CN108205727A (en) * | 2016-12-20 | 2018-06-26 | 中国科学院沈阳自动化研究所 | A kind of digitlization plant process decision-making technique based on decision tree and expert system |
| CN109491816A (en) * | 2018-10-19 | 2019-03-19 | 中国船舶重工集团公司第七六研究所 | Knowledge based engineering method for diagnosing faults |
| CN112068542A (en) * | 2020-06-30 | 2020-12-11 | 武汉乐庭软件技术有限公司 | Automatic driving behavior planning method based on fuzzy control |
| CN112101597A (en) * | 2020-10-14 | 2020-12-18 | 辽宁电能发展股份有限公司 | Electric vehicle leasing operation platform vehicle fault pre-judging system, method and device |
| CN113139514A (en) * | 2021-05-14 | 2021-07-20 | 安徽三禾一信息科技有限公司 | Hydraulic system fault diagnosis method based on fuzzy neural network |
| CN114184367A (en) * | 2021-11-29 | 2022-03-15 | 北京唐智科技发展有限公司 | Fault diagnosis method, device and equipment for rotary mechanical equipment and readable storage medium |
| CN114361536A (en) * | 2022-03-18 | 2022-04-15 | 北汽福田汽车股份有限公司 | Fault processing method and device for fuel cell system |
-
2022
- 2022-10-27 CN CN202211323505.2A patent/CN115563549B/en active Active
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5544256A (en) * | 1993-10-22 | 1996-08-06 | International Business Machines Corporation | Automated defect classification system |
| US5591355A (en) * | 1994-02-25 | 1997-01-07 | Miyachi Technos Corporation | Method for controlling resistance welding using fuzzy reasoning |
| KR20040088896A (en) * | 2003-04-14 | 2004-10-20 | 기아자동차주식회사 | Arc welding network system |
| WO2005071582A2 (en) * | 2004-01-27 | 2005-08-04 | British Telecommunications Public Limited Company | Detection of abnormal behaviour in dynamic systems |
| US20090037772A1 (en) * | 2007-08-03 | 2009-02-05 | Wegerich Stephan W | Fuzzy classification approach to fault pattern matching |
| CN102436524A (en) * | 2011-10-19 | 2012-05-02 | 清华大学 | Fuzzy reasoning method for soft fault diagnosis for analog circuit |
| CN103091112A (en) * | 2013-01-31 | 2013-05-08 | 林惠堂 | Method and device of car emission fault detection and diagnosis based on fuzzy reasoning and self-learning |
| CN105787563A (en) * | 2014-12-18 | 2016-07-20 | 中国科学院沈阳自动化研究所 | Self-learning mechanism-base fast matching fuzzy reasoning method |
| CN108205727A (en) * | 2016-12-20 | 2018-06-26 | 中国科学院沈阳自动化研究所 | A kind of digitlization plant process decision-making technique based on decision tree and expert system |
| CN106909727A (en) * | 2017-02-20 | 2017-06-30 | 武汉理工大学 | Laser welding temperature field Finite Element Method based on BP neural network and Genetic Algorithms |
| CN106961249A (en) * | 2017-03-17 | 2017-07-18 | 广西大学 | A kind of diagnosing failure of photovoltaic array and method for early warning |
| CN106919982A (en) * | 2017-03-20 | 2017-07-04 | 中国科学院沈阳自动化研究所 | A kind of method for diagnosing faults towards semiconductor manufacturing equipment |
| CN109491816A (en) * | 2018-10-19 | 2019-03-19 | 中国船舶重工集团公司第七六研究所 | Knowledge based engineering method for diagnosing faults |
| CN112068542A (en) * | 2020-06-30 | 2020-12-11 | 武汉乐庭软件技术有限公司 | Automatic driving behavior planning method based on fuzzy control |
| CN112101597A (en) * | 2020-10-14 | 2020-12-18 | 辽宁电能发展股份有限公司 | Electric vehicle leasing operation platform vehicle fault pre-judging system, method and device |
| CN113139514A (en) * | 2021-05-14 | 2021-07-20 | 安徽三禾一信息科技有限公司 | Hydraulic system fault diagnosis method based on fuzzy neural network |
| CN114184367A (en) * | 2021-11-29 | 2022-03-15 | 北京唐智科技发展有限公司 | Fault diagnosis method, device and equipment for rotary mechanical equipment and readable storage medium |
| CN114361536A (en) * | 2022-03-18 | 2022-04-15 | 北汽福田汽车股份有限公司 | Fault processing method and device for fuel cell system |
Non-Patent Citations (4)
| Title |
|---|
| ESSA ALGHANNAM 等: "A Novel Method of Using Vision System and Fuzzy Logic for Quality Estimation of Resistance Spot Welding", 《SYMMETRY》, pages 1 - 20 * |
| 吕现彪: "模糊关联规则挖掘算法的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》, no. 02, pages 138 - 2485 * |
| 梁硼 等: "X射线焊缝图像缺陷自动提取与识别技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》, no. 04, pages 138 - 932 * |
| 高昶霖 等: "基于动态权重的自适应 PSO-BP 神经网络焊接缺陷成因诊断", 《焊接学报》, vol. 43, no. 1, pages 98 - 106 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115563549B (en) | 2023-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021004324A1 (en) | Resource data processing method and apparatus, and computer device and storage medium | |
| CN111898867B (en) | Airplane final assembly production line productivity prediction method based on deep neural network | |
| CN112906764B (en) | Communication safety equipment intelligent diagnosis method and system based on improved BP neural network | |
| CN110987436B (en) | Bearing fault diagnosis method based on excitation mechanism | |
| CN111507365A (en) | Confidence rule automatic generation method based on fuzzy clustering | |
| CN113822388A (en) | Parameter setting method, device, electronic device and storage medium | |
| CN115049019A (en) | Method and device for evaluating arsenic adsorption performance of metal organic framework and related equipment | |
| CN111651220A (en) | Spark parameter automatic optimization method and system based on deep reinforcement learning | |
| CN111666981B (en) | System data anomaly detection method based on genetic fuzzy clustering | |
| CN113033898A (en) | Electrical load prediction method and system based on K-means clustering and BI-LSTM neural network | |
| CN115563549A (en) | Welding defect cause diagnosis method and system and electronic equipment | |
| CN117113086A (en) | Energy storage unit load prediction method, system, electronic equipment and medium | |
| CN113821975B (en) | Method and system for predicting performance decay of fuel cell | |
| CN115017988A (en) | Competitive clustering method for state anomaly diagnosis | |
| CN114780619A (en) | Abnormity early warning method for automatic engineering audit data | |
| CN114926075A (en) | Mechanical part production scheduling method based on man-hour prediction | |
| CN113947332A (en) | Method and system for evaluating comprehensive guarantee capability of underground engineering | |
| WO2021017284A1 (en) | Cortex-learning-based anomaly detection method and apparatus, terminal device, and storage medium | |
| CN112699229A (en) | Self-adaptive question-pushing method based on deep learning model | |
| CN111709585A (en) | Air conditioner load prediction method and device and storage medium | |
| CN116595883B (en) | Real-time online system state correction method for numerical reactor | |
| CN110942149B (en) | Feature variable selection method based on information change rate and condition mutual information | |
| CN117521897A (en) | Method, device, medium and equipment for predicting load distribution of energy station | |
| CN117131325A (en) | Data processing method, device, storage medium and program product | |
| CN115481575A (en) | Failure mode and influence analysis method based on data driving |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |