A method and system for NC machine tool control fault diagnosis based on the Internet of Things

Abstract

The present invention relates to the field of digital control technology, and specifically to a method and system for diagnosing control faults of numerically controlled machine tools based on the Internet of Things. The system comprises a data acquisition module for the normal operating status of various components of the numerically controlled machine tool, a data range interval construction module for the normal operating status of various components of the numerically controlled machine tool, an abnormal operating status data determination module, an image feature data acquisition module, and a control fault diagnosis result output module for the numerically controlled machine tool. The numerically controlled machine tool components that need to be diagnosed are determined by collecting abnormal operating data in the operating status of the numerically controlled machine tool, and the image feature data of the components with abnormal operating status data are matched with the fault image feature data of the corresponding numerically controlled machine tool components through the Pelican algorithm, and the matching results are analyzed and outputted. The speed of the matching process is improved, the efficiency of the convergence process is improved, and the accuracy of the fault diagnosis results is ensured at the same time.

Description

Technical Field

[0001] The present invention relates to the field of digital control technology, and in particular to a method and system for diagnosing control faults of numerically controlled machine tools based on the Internet of Things. Background Art

[0002] CNC machine tools are complex mechatronic equipment that require different components to work together during operation. Even a slight error in one component can cause the CNC machine tool to malfunction.

[0003] The Chinese patent application with publication number CN101697072A introduces a CNC machine tool fault diagnosis system and method, which uses a variety of sensors to collect vibration signals generated during the operation of the CNC machine tool, processes the collected vibration signals, and finally uses a computer to calculate and analyze the processed vibration signals to diagnose the faults of the CNC machine tool. Diagnosing the faults of the CNC machine tool only through the collected vibration signals is prone to calculation errors that lead to deviations in the fault diagnosis results.

[0004] In the existing technology of CNC machine tool control fault diagnosis, the operating status information of the CNC machine tool is often obtained through sensors, and the operating status of the CNC machine tool is judged based on the obtained operating status information. Due to the complex operating mechanism of CNC machine tools, the fault diagnosis process is based on single data and the accuracy of the diagnosis result cannot be guaranteed. Summary of the invention

[0005] 1. Technical issues to be resolved

[0006] In order to address the deficiencies in the background technology, the present invention proposes a CNC machine tool control fault diagnosis method and system based on the Internet of Things. By collecting abnormal operation data in the operation state of the CNC machine tool, the CNC machine tool components that need to be diagnosed are determined, and then the image feature data of the components with abnormal operation state data are matched with the fault image feature data of the corresponding CNC machine tool components. The matching results are analyzed and the CNC machine tool control fault diagnosis results are output.

[0007] (II) Technical solution

[0008] A method for diagnosing control faults of CNC machine tools based on the Internet of Things, the method comprising the following steps:

[0009] S1, setting a CNC machine tool component set and a normal operating status data collection time point set, collecting data on each component in the CNC machine tool component set according to the normal operating status data collection time point set, and obtaining a normal operating status data matrix of each component of the CNC machine tool;

[0010] S2, setting a range interval set of normal operating status data of each component of the CNC machine tool according to the normal operating status data of each component in the normal operating status matrix of each component of the CNC machine tool;

[0011] S3, collecting the operating status data of each component of the CNC machine tool to be tested, and obtaining an operating status data set of each component of the CNC machine tool to be tested;

[0012] S4, comparing the normal operating status data range interval set of each component of the CNC machine tool with the operating status data set of each component of the CNC machine tool to be detected, and selecting abnormal operating status data in the operating status data set of each component of the CNC machine tool to be detected;

[0013] S5, collecting image feature data of the component with abnormal operation status in the CNC machine tool to be detected as the first image feature data, and collecting image feature data of each component of the CNC machine tool in a fault state at the same time, to obtain a first fault image feature data set;

[0014] S6. Match the first image feature data with the fault image feature data in the fault image feature data type set corresponding to the CNC machine tool component in the first fault image feature data set one by one through a data analysis algorithm, analyze the matching results and output the CNC machine tool control fault diagnosis result.

[0015] By setting the range of normal operating status data of each component of the CNC machine tool through a large amount of collected normal operating status data, the accuracy of the set range of normal operating status data is ensured; by analyzing the relationship between the numerical value of the operating status data of each component of the CNC machine tool to be detected and the range of normal operating status data of the corresponding component, the abnormal operating status data is selected to ensure the reliability of the obtained abnormal operating status data; the first image feature data is matched with the fault image feature data of the corresponding CNC machine tool component through a data analysis algorithm, and the CNC machine tool fault diagnosis is performed based on the matching result, so that the fault diagnosis process is more accurate and the efficiency and effect of the fault diagnosis are ensured at the same time;

[0016] Preferably, the CNC machine tool component set and the normal operating status data collection time point set are set, and data is collected from each component in the CNC machine tool component set according to the normal operating status data collection time point set to obtain the normal operating status data matrix of each component of the CNC machine tool. The operation steps are as follows:

[0017] S11, set CNC machine tool component set A = {a 1 ,a 2 ,…,a i ,…,a k}, where a i represents the i-th CNC machine tool component, k represents the total number of CNC machine tool components;

[0018] Set the operation cycle of the CNC machine tool, divide the operation cycle of the CNC machine tool evenly, and obtain the normal operation state data collection time point set B = {b 1,b 2 ,…,b i ,…,b l}, where b i represents the i-th time point of normal operation status data collection, and l represents the total number of time points of normal operation status data collection;

[0019] S12, for the CNC machine tool component set A = {a 1 ,a 2 ,…,a i ,…,a k The data collection time point set B of each component in the normal operation state is {b 1 ,b 2 ,…,b i ,…,b l} to collect data at each normal operating status data collection time point, and obtain the normal operating status data matrix of each component of the CNC machine tool as follows:

[0020]

[0021] Among them, d ij It represents the normal operating status data of the i-th CNC machine tool component at the j-th normal operating status data collection time point.

[0022] By evenly dividing the operating cycle of the CNC machine tool to obtain multiple collection time points, data is collected from various components of the CNC machine tool to ensure the comprehensiveness of the acquired data and provide a data basis for subsequent operations.

[0023] Preferably, the operation steps of setting the normal operating status data range interval set of each component of the CNC machine tool according to the normal operating status data of each component in the normal operating status data set of each component of the CNC machine tool are as follows:

[0024] S21, compare the normal operation status data of each component in the operation status data matrix of each component of the CNC machine tool, select the maximum and minimum values ​​of the normal operation status data of each component, and set the range interval set of the normal operation status data of each component of the CNC machine tool. in, and They respectively represent the minimum and maximum values ​​of the normal operating status data of the i-th CNC machine tool component.

[0025] The data range of the normal operating status of each component of the CNC machine tool is set by collecting a large amount of normal operating status data, thereby ensuring the accuracy of the set normal operating status data range.

[0026] Preferably, the operation steps of collecting the operating status data of each component of the CNC machine tool to be detected and obtaining the operating status data set of each component of the CNC machine tool to be detected are as follows:

[0027] S31, collect the running status data of each component of the CNC machine tool to be tested in real time, and obtain the running status data set X'={x 1 ',x 2 ',…,x i ',…,x k '}, where x i ' represents the operating status data of the i-th CNC machine tool component to be detected.

[0028] By collecting the operating status data of each component of the CNC machine tool to be inspected in real time, the timeliness of the acquired data is guaranteed, providing a data basis for subsequent operations.

[0029] Preferably, the operation steps of comparing the normal operating state data range interval set of each component of the CNC machine tool with the operating state data set of each component of the CNC machine tool to be detected, and selecting abnormal operating state data in the operating state data set of each component of the CNC machine tool to be detected are as follows:

[0030] S41, sequentially determine the operating status data set X'={x 1 ',x 2 ',…,x i ',…,x k The operating status data x of the i-th CNC machine tool component to be detected in '} i 'Whether the value of is within the normal operating status data range of each component of the CNC machine tool The normal operating status data range interval of the i-th CNC machine tool component If the running status data x i The value of ' is within the normal operating state data range of CNC machine tool components If , the running status data is normal running status data; otherwise, the running status data is abnormal running status data; i=1,2,…,i,…,k.

[0031] By analyzing the relationship between the numerical value of the operating status data of each component of the CNC machine tool to be tested and the range of the normal operating status data of the corresponding component, the abnormal operating status data is selected to ensure the reliability of the obtained abnormal operating status data.

[0032] Preferably, the image feature data of the component with abnormal operation status in the CNC machine tool to be detected is collected as the first image feature data, and the image feature data of each component of the CNC machine tool under the fault state is collected at the same time. The operation steps for obtaining the first fault image feature data set are as follows:

[0033] S51, collecting image feature data of abnormal operation status data components in the CNC machine tool to be detected through an image acquisition device;

[0034] S52, collecting historical image feature data of various components of the CNC machine tool under fault conditions in the past, to obtain a first fault image feature data set A'={a' 1 ,a' 2 ,…,a' i ,…,a' k};

[0035] Among them, a' i The fault image feature data type set A”={a” 1 ,a” 2 ,…,a” i ,…,a” p}, a” i represents the i-th type of fault image feature data of the CNC machine tool component, and p represents the total number of types of fault image feature data of the CNC machine tool component.

[0036] The image feature data of the abnormal operating status data components in the CNC machine tool to be detected are collected, and the historical image feature data of the various components of the CNC machine tool under the fault state in the past are collected to establish the first fault image feature data set, which ensures the accuracy of the subsequent matching results.

[0037] Preferably, the first image feature data is matched one by one with the fault image feature data in the fault image feature data type set corresponding to the CNC machine tool component in the first fault image feature data set by a data analysis algorithm, and the operation steps of analyzing the matching result and outputting the CNC machine tool control fault diagnosis result are as follows:

[0038] S61, using a data analysis algorithm to compare the first image feature data with the first fault image feature data set A'={a' 1 ,a' 2 ,…,a' i ,…,a' k}, and the specific operation steps are as follows:

[0039] S611, initialize the pelican population, set the population size to p, and the pelican population is represented by M = {m 1 ,m 2 ,…,m i ,…,m p},m i represents the i-th pelican in the pelican population, and sets the maximum number of iterations to t max ;

[0040] Among them, each pelican individual corresponds to a fault image feature data in a fault image feature data type set corresponding to a CNC machine tool component in a first fault image feature data set; the pelican population initialization formula is as follows:

[0041] y i,j =I lj +rand×(I uj -I lj )

[0042] Among them, y i,j is the position of the ith pelican in the jth dimension search space, rand represents a random number between (0,1), I uj and I lj Respectively represent the upper and lower boundaries of the j-th dimension search space;

[0043] S612. Calculate the current objective function value of each pelican; the objective function formula is as follows:

[0044] F = x

[0045] Wherein, F represents the objective function value of the pelican individual, and x represents the similarity between the fault image feature data in the fault image feature data type set corresponding to the CNC machine tool component in the first fault image feature data set and the first image feature data;

[0046] S613, exploration phase, mathematical modeling of the pelican's behavior of determining the location of prey and approaching the prey, the formula is as follows:

[0047]

[0048] in, represents the updated position of the i-th pelican after it approaches the prey in the j-dimensional search space during the survey phase, I represents a random number with a value of 1 or 2, and p j represents the randomly generated prey position in the j-th dimension search space, rand represents a random number between (0,1), and F p and F i denote the objective function values ​​of the prey and the i-th pelican respectively;

[0049] S614, Development phase, mathematical modeling of the process of pelicans hunting on the water surface, the formula is as follows:

[0050]

[0051] in, represents the updated position of the ith pelican after hunting in the jth dimensional search space during the development phase, R represents a random number with a value of 0 or 2, rand represents a random number between (0,1), and t represents the current iteration number;

[0052] S615, calculating the objective function value of each pelican in the updated pelican population, and taking the pelican with the highest objective function value as the current global optimal solution;

[0053] S616: Determine whether the maximum number of iterations has been reached. If not, return to S613; if reached, calculate the objective function value F of the final global optimal solution. max , when F max Greater than the set objective function threshold F 阈值 , then the fault image feature data corresponding to the global optimal solution matches the first image feature data successfully; otherwise, the fault image feature data do not match successfully;

[0054] S62. If the fault image feature data are not matched successfully, the CNC machine tool control fault diagnosis result is output as no fault in the CNC machine tool; otherwise, the CNC machine tool control fault diagnosis result is output as a fault in the CNC machine tool component corresponding to the fault image feature data that is matched successfully.

[0055] By simulating the behavior of a pelican approaching its prey and hunting, a mathematical model is constructed to achieve the process of matching the first image feature data with the fault image feature data of the corresponding CNC machine tool component, thereby improving the speed and accuracy of the matching process and the efficiency of the convergence process.

[0056] The present invention also discloses a CNC machine tool control fault diagnosis system based on the Internet of Things, comprising a normal operating state data acquisition module for each component of the CNC machine tool, a normal operating state data range interval construction module for each component of the CNC machine tool, an abnormal operating state data determination module, an image feature data acquisition module, and a CNC machine tool control fault diagnosis result output module;

[0057] The normal operating status data acquisition module of each component of the CNC machine tool acquires data of each component in the CNC machine tool component set through a set normal operating status data acquisition time point set to obtain a normal operating status data matrix of each component of the CNC machine tool;

[0058] The normal operating status data range interval construction module of each component of the numerical control machine tool sets the normal operating status data range interval set of each component of the numerical control machine tool by comparing the numerical value of the normal operating status data of each component in the normal operating status data matrix of each component of the numerical control machine tool;

[0059] The abnormal operation status data determination module obtains all abnormal operation status data by determining whether the value of each operation status data in the operation status data set of each component of the CNC machine tool to be detected is within the corresponding normal operation status data range interval;

[0060] The image feature data acquisition module acquires image feature data of components with abnormal operation status data in the CNC machine tool to be detected through an image acquisition device to obtain first image feature data and collects historical image feature data of various components of the CNC machine tool under previous fault conditions to establish a first fault image feature data set;

[0061] The CNC machine tool control fault diagnosis result output module performs one-to-one matching of the first image feature data with the image feature data in the fault image feature data type set corresponding to the CNC machine tool component in the fault image feature data set of each component of the CNC machine tool, analyzes the matching results and outputs the CNC machine tool control fault diagnosis result.

[0062] (III) Beneficial effects

[0063] 1. The present invention provides a normal operating state data acquisition module for each component of a CNC machine tool, a normal operating state data range interval construction module for each component of a CNC machine tool, an abnormal operating state data determination module, an image feature data acquisition module, and a CNC machine tool control fault diagnosis result output module; the normal operating state data range interval of each component of the CNC machine tool is set by a large amount of normal operating state data collected, thereby ensuring the accuracy of the set normal operating state data range interval; by analyzing the relationship between the numerical value of the operating state data of each component of the CNC machine tool to be detected and the normal operating state data range interval of the corresponding component, the abnormal operating state data is selected, thereby ensuring the reliability of the obtained abnormal operating state data; the first image feature data is matched with the fault image feature data of the corresponding CNC machine tool component through a data analysis algorithm, and the CNC machine tool fault diagnosis is performed based on the matching result, thereby making the fault diagnosis process more accurate and ensuring the efficiency and effect of the fault diagnosis;

[0064] 2. The process of matching the first image feature data with various types of fault image feature data in the fault image feature data type set corresponding to the CNC machine tool components in the first fault image feature data set is realized by the Pelican algorithm. By simulating the behavior of the pelican approaching prey and hunting, a mathematical model is constructed to improve the speed and accuracy of the matching process, while improving the efficiency of the convergence process. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the technical solutions of the embodiments of the invention, the drawings required for describing the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For ordinary technicians in this field, they can also obtain drawings based on these drawings without paying creative work.

[0066] Figure 1 A flowchart of a method for diagnosing control faults of CNC machine tools based on the Internet of Things provided by the present invention;

[0067] Figure 2 A module schematic diagram of a CNC machine tool control fault diagnosis system based on the Internet of Things provided by the present invention. DETAILED DESCRIPTION

[0068] 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.

[0069] In the description of the present invention, it is necessary to understand that the terms "opening", "upper", "lower", "top", "middle", "inside" and the like indicating orientation or positional relationship are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the components or elements referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the invention.

[0070] The embodiments of the CNC machine tool control fault diagnosis method and system based on the Internet of Things are as follows:

[0071] See also Figure 1 — Figure 2 , a CNC machine tool control fault diagnosis method based on the Internet of Things, the method comprises the following steps:

[0072] S1, setting a CNC machine tool component set and a normal operating status data collection time point set, collecting data on each component in the CNC machine tool component set according to the normal operating status data collection time point set, and obtaining a normal operating status data matrix of each component of the CNC machine tool;

[0073] S11, set CNC machine tool component set A = {a 1 ,a 2 ,|,a i ,…,a k}, where a i represents the i-th CNC machine tool component, k represents the total number of CNC machine tool components;

[0074] Set the operation cycle of the CNC machine tool, divide the operation cycle of the CNC machine tool evenly, and obtain the normal operation state data collection time point set B = {b 1 ,b 2 ,…,b i ,…,b l}, where b i represents the i-th time point of normal operation status data collection, and l represents the total number of time points of normal operation status data collection;

[0075] S12, for the CNC machine tool component set A = {a 1 ,a 2 ,…,a i ,…,a k The data collection time point set B of each component in the normal operation state is {b 1 ,b 2 ,…,b i ,…,b l} to collect data at each normal operating status data collection time point, and obtain the normal operating status data matrix of each component of the CNC machine tool as follows:

[0076]

[0077] Among them, d ij It represents the normal operating status data of the i-th CNC machine tool component at the j-th normal operating status data collection time point.

[0078] S2, setting a range interval set of normal operating status data of each component of the CNC machine tool according to the normal operating status data of each component in the normal operating status matrix of each component of the CNC machine tool;

[0079] S21, compare the normal operation status data of each component in the operation status data matrix of each component of the CNC machine tool, select the maximum and minimum values ​​of the normal operation status data of each component, and set the range interval set of the normal operation status data of each component of the CNC machine tool. in, and They respectively represent the minimum and maximum values ​​of the normal operating status data of the i-th CNC machine tool component.

[0080] S3, collecting the operating status data of each component of the CNC machine tool to be tested, and obtaining an operating status data set of each component of the CNC machine tool to be tested;

[0081] S31, collect the running status data of each component of the CNC machine tool to be tested in real time, and obtain the running status data set X'={x 1 ',x 2 ',…,x i ',…,x k '}, where x i ' represents the operating status data of the i-th CNC machine tool component to be detected.

[0082] S4, comparing the normal operating status data range interval set of each component of the CNC machine tool with the operating status data set of each component of the CNC machine tool to be detected, and selecting abnormal operating status data in the operating status data set of each component of the CNC machine tool to be detected;

[0083] S41, sequentially determine the operating status data set X'={x 1 ',x 2 ',…,x i ',…,x k The operating status data x of the i-th CNC machine tool component to be detected in '} i 'Whether the value of is within the normal operating status data range of each component of the CNC machine tool The normal operating status data range interval of the i-th CNC machine tool component If the running status data x i The value of ' is within the normal operating state data range of CNC machine tool components If , the running status data is normal running status data; otherwise, the running status data is abnormal running status data; i=1,2,…,i,…,k.

[0084] S5, collecting image feature data of the component with abnormal operation status in the CNC machine tool to be detected as the first image feature data, and collecting image feature data of each component of the CNC machine tool in a fault state at the same time, to obtain a first fault image feature data set;

[0085] S51, collecting image feature data of abnormal operation status data components in the CNC machine tool to be detected through an image acquisition device;

[0086] S52, collecting historical image feature data of various components of the CNC machine tool under fault conditions in the past, to obtain a first fault image feature data set A'={a' 1 ,a' 2 ,…,a' i ,…,a' k};

[0087] Among them, a' i The fault image feature data type set A”={a” 1 ,a” 2 ,…,a” i ,…,a” p}, a” i represents the i-th type of fault image feature data of the CNC machine tool component, and p represents the total number of types of fault image feature data of the CNC machine tool component.

[0088] S6, using a data analysis algorithm, one-to-one match the first image feature data with the fault image feature data in the fault image feature data type set corresponding to the CNC machine tool component in the first fault image feature data set, analyze the matching results and output the CNC machine tool control fault diagnosis result;

[0089] S61, using a data analysis algorithm to compare the first image feature data with the first fault image feature data set A'={a' 1 ,a' 2 ,…,a' i ,…,a' k}, and the specific operation steps are as follows:

[0090] S611, initialize the pelican population, set the population size to p, and the pelican population is represented by M = {m 1 ,m 2 ,…,m i ,…,m p},m i represents the i-th pelican in the pelican population, and sets the maximum number of iterations to t max ;

[0091] Among them, each pelican individual corresponds to a fault image feature data in a fault image feature data type set corresponding to a CNC machine tool component in a first fault image feature data set; the pelican population initialization formula is as follows:

[0092] y i,j =I lj +rand×(I uj -I lj )

[0093] Among them, y i,j is the position of the ith pelican in the jth dimension search space, rand represents a random number between (0,1), I uj and I lj Respectively represent the upper and lower boundaries of the j-th dimension search space;

[0094] S612. Calculate the current objective function value of each pelican; the objective function formula is as follows:

[0095] F = x

[0096] Wherein, F represents the objective function value of the pelican individual, and x represents the similarity between the fault image feature data in the fault image feature data type set corresponding to the CNC machine tool component in the first fault image feature data set and the first image feature data;

[0097] S613, exploration phase, mathematical modeling of the pelican's behavior of determining the location of prey and approaching the prey, the formula is as follows:

[0098]

[0099] in, represents the updated position of the i-th pelican after it approaches the prey in the j-dimensional search space during the survey phase, I represents a random number with a value of 1 or 2, and p j represents the randomly generated prey position in the j-th dimension search space, rand represents a random number between (0,1), and F p and F i denote the objective function values ​​of the prey and the i-th pelican respectively;

[0100] S614, Development phase, mathematical modeling of the process of pelicans hunting on the water surface, the formula is as follows:

[0101]

[0102] in, represents the updated position of the ith pelican after hunting in the jth dimensional search space during the development phase, R represents a random number with a value of 0 or 2, rand represents a random number between (0,1), and t represents the current iteration number;

[0103] S615, calculating the objective function value of each pelican in the updated pelican population, and taking the pelican with the highest objective function value as the current global optimal solution;

[0104] S616: Determine whether the maximum number of iterations has been reached. If not, return to S613; if reached, calculate the objective function value F of the final global optimal solution. max , when F max Greater than the set objective function threshold F 阈值 , then the fault image feature data corresponding to the global optimal solution matches the first image feature data successfully; otherwise, the fault image feature data do not match successfully;

[0105] S62. If the fault image feature data are not matched successfully, the CNC machine tool control fault diagnosis result is output as no fault in the CNC machine tool; otherwise, the CNC machine tool control fault diagnosis result is output as a fault in the CNC machine tool component corresponding to the fault image feature data that is matched successfully.

[0106] The present invention also discloses a CNC machine tool control fault diagnosis system based on the Internet of Things, comprising a normal operating state data acquisition module for each component of the CNC machine tool, a normal operating state data range interval construction module for each component of the CNC machine tool, an abnormal operating state data determination module, an image feature data acquisition module, and a CNC machine tool control fault diagnosis result output module;

[0107] The normal operating status data acquisition module of each component of the CNC machine tool acquires data of each component in the CNC machine tool component set through a set normal operating status data acquisition time point set to obtain a normal operating status data matrix of each component of the CNC machine tool;

[0108] The normal operating status data range interval construction module of each component of the numerical control machine tool sets the normal operating status data range interval set of each component of the numerical control machine tool by comparing the numerical value of the normal operating status data of each component in the normal operating status data matrix of each component of the numerical control machine tool;

[0109] The abnormal operation status data determination module obtains all abnormal operation status data by determining whether the value of each operation status data in the operation status data set of each component of the CNC machine tool to be detected is within the corresponding normal operation status data range interval;

[0110] The image feature data acquisition module acquires image feature data of components with abnormal operation status data in the CNC machine tool to be detected through an image acquisition device to obtain first image feature data and collects historical image feature data of various components of the CNC machine tool under previous fault conditions to establish a first fault image feature data set;

[0111] The CNC machine tool control fault diagnosis result output module performs one-to-one matching of the first image feature data with the image feature data in the fault image feature data type set corresponding to the CNC machine tool component in the fault image feature data set of each component of the CNC machine tool, analyzes the matching results and outputs the CNC machine tool control fault diagnosis result.

[0112] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", 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 invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0113] The preferred embodiments of the invention disclosed above are only used to help explain the invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the invention, so that those skilled in the art can understand and use the invention well.

Claims

1. A method for diagnosing control faults of CNC machine tools based on the Internet of Things, characterized in that: The steps include: S1, setting a CNC machine tool component set and a normal operating status data collection time point set, collecting data on each component in the CNC machine tool component set according to the normal operating status data collection time point set, and obtaining a normal operating status data matrix of each component of the CNC machine tool; S2, setting a data range interval set of the normal operating status of each component of the CNC machine tool according to the normal operating status data of each component in the normal operating status matrix of each component of the CNC machine tool; S3, collecting the operating status data of each component of the CNC machine tool to be tested, and obtaining an operating status data set of each component of the CNC machine tool to be tested; S4, comparing the normal operating status data range interval set of each component of the CNC machine tool with the operating status data set of each component of the CNC machine tool to be detected, and selecting abnormal operating status data in the operating status data set of each component of the CNC machine tool to be detected; S5, collecting image feature data of the component with abnormal operation status in the CNC machine tool to be detected as the first image feature data, and collecting image feature data of each component of the CNC machine tool in a fault state at the same time, to obtain a first fault image feature data set; S6, using a data analysis algorithm, one-to-one match the first image feature data with the fault image feature data in the fault image feature data type set corresponding to the CNC machine tool component in the first fault image feature data set, analyze the matching results and output the CNC machine tool control fault diagnosis result; The S6 comprises the following steps: S61, using a data analysis algorithm to compare the first image feature data with a first fault image feature data set A'={a'1, a'2, ..., a' i ,…,a' k } one by one matching various types of fault image feature data in the fault image feature data type set corresponding to the CNC machine tool parts; S62, if the fault image feature data are not matched successfully, the CNC machine tool control fault diagnosis result is output as no fault in the CNC machine tool; otherwise, the CNC machine tool control fault diagnosis result is output as a fault in the CNC machine tool component corresponding to the fault image feature data that is matched successfully; The matching of the first image feature data with the fault image feature data of the corresponding CNC machine tool component comprises the following steps: S611, initialize the pelican population, set the population size to p, and the pelican population is represented by M = {m1, m2, ..., m i ,…,m p },m i represents the i-th pelican in the pelican population, and sets the maximum number of iterations to t max ; Among them, each pelican individual corresponds to a fault image feature data in a fault image feature data type set corresponding to a CNC machine tool component in a first fault image feature data set; the pelican population initialization formula is as follows: y i,j =I lj +rand×(I uj -I lj ) Among them, y i,j is the position of the ith pelican in the jth dimension search space, rand represents a random number between (0,1), I uj and I lj Respectively represent the upper and lower boundaries of the j-th dimension search space; S612. Calculate the current objective function value of each pelican; the objective function formula is as follows: F = x Wherein, F represents the objective function value of the pelican individual, and x represents the similarity between the fault image feature data in the fault image feature data type set corresponding to the CNC machine tool component in the first fault image feature data set and the first image feature data; S613, exploration phase, mathematical modeling of the pelican's behavior of determining the location of prey and approaching the prey, the formula is as follows: in, represents the updated position of the i-th pelican after it approaches the prey in the j-dimensional search space during the survey phase, I represents a random number with a value of 1 or 2, and p j represents the randomly generated prey position in the j-th dimension search space, rand represents a random number between (0,1), and F p and F i denote the objective function values ​​of the prey and the i-th pelican respectively; S614, Development phase, mathematical modeling of the process of pelicans hunting on the water surface, the formula is as follows: in, represents the updated position of the ith pelican after hunting in the jth dimensional search space during the development phase, R represents a random number with a value of 0 or 2, rand represents a random number between (0,1), and t represents the current iteration number; S615, calculating the objective function value of each pelican in the updated pelican population, and taking the pelican with the highest objective function value as the current global optimal solution; S616: Determine whether the maximum number of iterations has been reached. If not, return to S613; if reached, calculate the objective function value F of the final global optimal solution. max , when F max Greater than the set objective function threshold F 阈值 , then the fault image feature data corresponding to the global optimal solution matches the first image feature data successfully; otherwise, the fault image feature data do not match successfully.

2. The method for diagnosing faults of CNC machine tools based on the Internet of Things according to claim 1 is characterized in that: The S1 comprises the following steps: S11, set the CNC machine tool component set A = {a1, a2, ..., a i ,…,a k }, where a i represents the i-th CNC machine tool component, k represents the total number of CNC machine tool components; Set the operation cycle of the CNC machine tool, divide the operation cycle of the CNC machine tool evenly, and obtain the normal operation state data collection time point set B = {b1, b2, ..., b i ,…,b l }, where b i represents the i-th time point of normal operation status data collection, and l represents the total number of time points of normal operation status data collection; S12, for the CNC machine tool component set A = {a1, a2, ..., a i ,…,a k The data collection time point set B = {b1, b2, ..., b i ,…,b l } to collect data at each normal operating status data collection time point, and obtain the normal operating status data matrix of each component of the CNC machine tool as follows: Among them, d ij It represents the normal operating status data of the i-th CNC machine tool component at the j-th normal operating status data collection time point.

3. The method for diagnosing faults of CNC machine tools based on the Internet of Things according to claim 2 is characterized in that: The S2 comprises the following steps: S21, compare the normal operation status data of each component in the operation status data matrix of each component of the CNC machine tool, select the maximum and minimum values ​​of the normal operation status data of each component, and set the range interval set of the normal operation status data of each component of the CNC machine tool. in, and They respectively represent the minimum and maximum values ​​of the normal operating status data of the i-th CNC machine tool component.

4. The method for diagnosing faults of CNC machine tools based on the Internet of Things according to claim 3 is characterized in that: The S3 comprises the following steps: S31, collect the running status data of each component of the CNC machine tool to be tested in real time, and obtain the running status data set X'={x1',x2',...,x i ',…,x k '}, where x i ' represents the operating status data of the i-th CNC machine tool component to be detected.

5. The method for diagnosing faults of CNC machine tools based on the Internet of Things according to claim 4 is characterized in that: The S4 comprises the following steps: S41, determine the running status data set X'={x1', x2', ..., x i ',…,x k The operating status data x of the i-th CNC machine tool component to be detected in '} i 'Whether the value of is within the normal operating status data range of each component of the CNC machine tool The normal operating status data range interval of the i-th CNC machine tool component If the running status data x i The value of ' is within the normal operating state data range of CNC machine tool components If , the running status data is normal running status data; otherwise, the running status data is abnormal running status data; i=1,2,…,i,…,k.

6. The method for diagnosing faults of CNC machine tools based on the Internet of Things according to claim 5 is characterized in that: The S5 comprises the following steps: S51, collecting image feature data of abnormal operation status data components in the CNC machine tool to be detected through an image acquisition device; S52, collecting historical image feature data of various components of the CNC machine tool under fault conditions in the past, obtaining a first fault image feature data set A'={a'1, a'2, ..., a' i ,…,a' k }; Among them, a' i The fault image feature data type set A”={a”1, a”2,…, a” i ,…,a” p }, a” i represents the i-th type of fault image feature data of the CNC machine tool component, and p represents the total number of types of fault image feature data of the CNC machine tool component.

7. A system for implementing the method for diagnosing control faults of CNC machine tools based on the Internet of Things as described in any one of claims 1 to 6, comprising a data collection module for the normal operating status of each component of the CNC machine tool, a module for constructing the data range interval of the normal operating status of each component of the CNC machine tool, an abnormal operating status data determination module, an image feature data collection module, and a CNC machine tool control fault diagnosis result output module.

Images