Construction method and evaluation method of mechanical equipment state evaluation model, equipment and medium

Abstract

The invention provides a construction and evaluation method and device of a mechanical equipment state evaluation model and a medium, and belongs to the technical field of mechanical equipment state evaluation, and the construction and evaluation method comprises the steps: dividing parts which are related in function, have a connection relation and have the same contact type in mechanical equipment into the same module; the static characteristic measurement indexes of the mechanical equipment are detected according to the hierarchical sequence of part-module-mechanical equipment, and detection data are obtained; based on a weighted quantitative evaluation method and / or a fuzzy comprehensive evaluation method, constructing a mathematical model for describing the relationship between each static characteristic measurement index and the mechanical equipment state; and fitting and optimizing the weight of each static characteristic measurement index in the mathematical model based on detection data to obtain a final mechanical equipment state evaluation model for evaluating the state of the mechanical equipment according to the measurement value of the static characteristic measurement index. According to the invention, the technical problem of limited effectiveness of mechanical equipment state evaluation in the prior art is effectively solved.

Description

Technical Field

[0001] The present invention relates to the technical field of mechanical equipment status assessment, and in particular to a method, equipment and medium for constructing a mechanical equipment status assessment model and conducting an assessment. Background Art

[0002] In modern manufacturing, the performance and reliability of mechanical equipment play a crucial role in production efficiency and product quality. Mechanical equipment is a complex integrated system of mechanical, electrical, magnetic, hydraulic, and pneumatic components. Failures can occur in numerous components, each of which influences the others. Correlations between part-level and component-level condition analysis results make mechanical equipment condition assessment difficult.

[0003] In the field of mechanical equipment condition assessment, researchers have explored various methods to improve the accuracy and comprehensiveness of assessments. International research is relatively mature, with many scholars employing machine learning and data mining methods to analyze historical data to assess the condition of mechanical equipment. For example, algorithms such as neural networks and support vector machines are used to model equipment operating data and identify its failure modes and health status. Furthermore, the application of Six Sigma methodologies in the manufacturing industry has provided theoretical support for equipment condition assessment, emphasizing data-based decision-making and process optimization, which helps improve the accuracy and reliability of assessments. Domestic research has focused more on combining maintenance data with operational performance data, employing methods such as the Analytic Hierarchy Process (AHP), grey relational models, and principal component analysis to construct comprehensive performance assessment models. Furthermore, domestic scholars have explored the functional and structural relationships between components to enhance the comprehensiveness of assessments. Regarding the selection of condition assessment indicators, international researchers generally prioritize indicator importance analysis, using weight assignment and sensitivity analysis to identify the indicators with the greatest impact on equipment condition assessment. However, while some domestic research has begun to focus on the selection of condition indicators, a systematic indicator system has yet to be established, limiting the effectiveness of assessment methods.

[0004] The construction of a mechanical equipment condition assessment method and related indicator system requires considering the combined influence of historical maintenance data, static characteristic measurement data, and other data. It also requires considering the structural and functional relationships between the mechanical equipment as a whole and its components, and between components. Given the large number of parts and relatively complex structures of mechanical equipment, a mechanical equipment condition assessment method based on static characteristic measurement indicators is needed to address these issues. Summary of the Invention

[0005] In view of this, it is necessary to provide a construction and evaluation method, equipment and medium for a mechanical equipment status evaluation model to solve the technical problem that the existing technology has limited effectiveness in evaluating the status of mechanical equipment.

[0006] In order to achieve the above technical effects, in a first aspect, the present invention provides a method for constructing a mechanical equipment condition assessment model, comprising: Classify parts of mechanical equipment that are functionally related, have connection relationships, and have the same contact type into the same module; Testing static characteristic measurement indicators of the mechanical equipment in a hierarchical order of "parts-modules-mechanical equipment" to obtain test data, wherein the test data includes: measured values ​​of the static characteristic measurement indicators and corresponding states of the mechanical equipment, and the static characteristic measurement indicators include: indicators for evaluating characteristics of the entire machine or module under static conditions; Constructing a mathematical model based on a weighted quantitative evaluation method and / or a fuzzy comprehensive evaluation method to describe the relationship between various static characteristic measurement indicators and the state of the mechanical equipment; The weights of various static characteristic measurement indicators in the mathematical model are optimized based on the detection data fitting, so as to obtain a final mechanical equipment state evaluation model for evaluating the mechanical equipment state according to the measured values ​​of the static characteristic measurement indicators.

[0007] In some embodiments of the present invention, dividing the parts of the mechanical equipment that are functionally related, have a connection relationship, and have the same contact type into the same module includes: Formulate evaluation value assignment standards for the module division criteria and set weight coefficients, wherein the module division criteria include: function relevance criteria, contact type criteria, and connection relationship criteria; Calculate the comprehensive correlation between any two common parts in the mechanical equipment after removing the fasteners. The calculation formula of the comprehensive correlation includes:

[0008] in, Indicates parts 、 The comprehensive correlation of Indicates the strength of functional association, represents the contact association strength, Represents the connection correlation, represents a corresponding weight coefficient of the functional relevance criterion in the comprehensive relevance, wherein the functional relevance criterion represents dividing functionally related parts into the same module; Indicates the corresponding weight coefficient of the contact type criterion in the comprehensive correlation degree. The contact type criterion indicates that the parts in the same module have the same contact type. Indicates the corresponding weight coefficient of the connection type criterion in the comprehensive association degree. The connection type criterion indicates that the parts within the same module have a connection relationship and meet the constraints: ; Establish a correlation matrix; According to the degree of association, the two individuals with the closest distance are merged in turn based on the hierarchical cluster analysis method to obtain a hierarchical structure diagram; Determine the module size and number according to the number of parts and complexity of the mechanical equipment, and divide the hierarchical structure diagram into several modules; After completing the module division of common parts, fasteners are added to the modules to achieve complete module division.

[0009] In some embodiments of the present invention, the detecting of the static characteristic measurement indicators of the mechanical equipment in the hierarchical order of "parts-modules-mechanical equipment" to obtain the detection data includes: Detect various indicators of the mechanical equipment in the hierarchical order of "parts-modules-mechanical equipment" to construct a set of condition assessment indicators; Performing importance analysis based on the state evaluation indicator set to screen and obtain the static characteristic measurement indicator; The measured values ​​of static characteristic measurement indicators are obtained by sorting.

[0010] In some embodiments of the present invention, the formula for constructing the state assessment indicator set includes: The calculation formula for the construction index set of the mechanical equipment condition assessment model is as follows:

[0011]

[0012] in, Indicates the number of indicators, Indicates the number of detections, represents the number of samples, Indicates the The first indicator The measured value, Indicates the first of multiple tests The mean of the indicators, Indicates the The first sample The standard deviation of the indicator, is the state evaluation indicator set.

[0013] In some embodiments of the present invention, performing importance analysis based on the state assessment indicator set to screen and obtain the static characteristic measurement indicator includes: The importance of the state assessment indicator set is analyzed based on the random forest model, wherein the calculation formula of the importance of the state assessment indicator includes: feature Importance in a single tree:

[0014] in, For a single tree, is the number of non-leaf nodes, For nodes The reduction in squared loss after the split, For and node associated features; Calculate features After calculating the importance of a single tree, the importance values ​​of all trees are accumulated and averaged, and then normalized to calculate the feature The global importance value of:

[0015] in, is the number of trees, , Indicates the a tree; The state indicators whose global importance values ​​are greater than a preset threshold are retained as the static characteristic measurement indicators.

[0016] In some embodiments of the present invention, building an initial model based on a weighted quantitative evaluation method in combination with the detection data includes: Constructing quality loss function As the initial model, the calculation formula is:

[0017] in, is the actual value of a single status indicator of a single part of the mechanical equipment, is the standard value of a single status indicator of a single part, is the proportionality constant; The larger the value, the worse the condition of the part.

[0018] In some embodiments of the present invention, an initial model is constructed based on the fuzzy comprehensive evaluation method in combination with the detection data, including: For Mechanical equipment parts with multiple measurement indicators, establish an evaluation coefficient matrix based on the importance of each indicator for status evaluation , the calculation formula is:

[0019] Where, is the importance of the indicator, ; The absolute value of the deviation of each measurement indicator Divide by the tolerance band to get the evaluation matrix , the calculation formula is:

[0020] Where, = , is the deviation value of each indicator; is the tolerance band of the indicator; Establish the excellent, good, medium and poor probability matrix for each indicator , the calculation formula is:

[0021]

[0022]

[0023]

[0024]

[0025] Where, For the The probability that the point is optimal; For the The probability that a point is good; For the The probability of the point being in the middle; For the The probability of the pip being the difference; ; Establish an excellent, good, fair, and poor rating system matrix The measurement index is a point for excellent, b point for good, c point for medium, and d point for poor, that is, ; Create a matrix , determine the score of each indicator as:

[0026] Where, , Assign a score to each indicator; Combined with the impact of each indicator on the status of mechanical equipment , establish a scoring matrix for mechanical equipment parts , the calculation formula is:

[0027] As a basis for measuring the status of mechanical equipment parts.

[0028] In a second aspect, the present invention further provides a method for evaluating the condition of a mechanical device, comprising: Constructing a mechanical equipment condition assessment model based on the method for constructing a mechanical equipment condition assessment model described in any one of the above methods; The measured value of the static characteristic measurement index is input into the mechanical equipment state evaluation model, and the evaluation result of the mechanical equipment state is determined according to the output value of the mechanical equipment state evaluation model.

[0029] In a third aspect, the present invention further provides a device comprising: Memory, used to store programs; A processor is coupled to the memory and is used to execute the program stored in the memory to implement the method for constructing a mechanical equipment condition assessment model or the steps in the mechanical equipment condition assessment method described in any one of the above method items.

[0030] In a fourth aspect, the present invention further provides a medium, comprising: Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the method for constructing a mechanical equipment condition assessment model or the steps in the mechanical equipment condition assessment method described in any one of the above method items.

[0031] The beneficial effects of the present invention are: the present invention provides a method for constructing a mechanical equipment status assessment model, firstly, the parts of the mechanical equipment are divided into separate modules, while eliminating the dimensionality curse, the coupling relationship is retained, and the distortion of the indicator weights of the subsequent assessment model is avoided; then, the equipment detection of the three levels of "parts-modules-mechanical equipment" is carried out, and the detection data is obtained, and the mathematical model and parameter fitting are established in combination with the status assessment method to obtain the final status assessment model, while incorporating the static characteristic measurement indicators into the evaluation system, it also effectively avoids the problem of confusion in the granularity of the measurement object, thereby realizing accurate status assessment of the mechanical equipment, effectively reducing the assessment error, improving the equipment maintenance efficiency, reducing the failure rate, and ultimately optimizing resource allocation and reducing operation and maintenance costs, solving the technical problem that the existing technology has limited effectiveness in evaluating the status of mechanical equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0033] Figure 1 A flow chart of an embodiment of a method for constructing a mechanical equipment condition assessment model provided by the present invention; Figure 2 for Figure 1A flow chart of an embodiment of step S101; Figure 3 A hierarchical structure diagram of the mechanical equipment provided by the present invention; Figure 4 for Figure 1 A flow chart of an embodiment of step S102; Figure 5 for Figure 4 A flow chart of an embodiment of step S402; Figure 6 Typical parts diagram of a mechanical device provided by the present invention; Figure 7 A schematic flow chart of an embodiment of a method for evaluating the condition of mechanical equipment provided by the present invention; Figure 8 This is the overall framework diagram of the mechanical equipment status assessment method provided by the present invention; Figure 9 This is a structural diagram of an embodiment of the device provided by the present invention. DETAILED DESCRIPTION

[0034] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0035] In the description of the embodiments of the present invention, unless otherwise specified, "plurality" means two or more. "And / or" describes the association relationship between associated objects, indicating that three relationships can exist. For example, "A and / or B" can mean: A exists alone, A and B exist simultaneously, or B exists alone.

[0036] The terms "first," "second," and so on, used in the embodiments of the present invention are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, technical features designated as "first" or "second" may explicitly or implicitly include at least one such feature.

[0037] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute a separate or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0038] The present invention provides a method, device and medium for constructing and evaluating a mechanical equipment condition assessment model, which are described below respectively.

[0039] Prior to this, it should be noted that the present invention can be implemented as an automated information processing system that integrates data collection, correlation calculation, indicator weight analysis, and condition assessment, completing a quantitative assessment of the static characteristics of mechanical equipment without human intervention. This invention can be applied to scenarios such as final factory inspection and preventive maintenance.

[0040] like Figure 1 As shown, in a first aspect, the present invention provides a method for constructing a mechanical equipment condition assessment model, comprising: S101. Parts of mechanical equipment that are functionally related, have a connection relationship, and have the same contact type are divided into the same module.

[0041] It should be noted that when formulating the module division criteria, the differences between different modules should be as obvious as possible, and the differences between the internal parts of the same module should be as small as possible.

[0042] In some embodiments of the present invention, the module division criteria include functional relevance criteria and structural relevance criteria. The functional relevance criteria can ensure that the functions of the components divided into the same module are related, the tightness within the module will be improved, and the degree of interaction between modules will be reduced, so as to achieve the purpose of low coupling and high cohesion; the structural relevance criteria refers to the spatial position and geometric relationship between components, mainly including the connection type and contact type between components. It should be ensured that the connection relationship between components divided into the same module is as strong as possible and the contact type is the same.

[0043] like Figure 2 , step S101 specifically includes: S201. Formulate evaluation value assignment standards for module division criteria and set weight coefficients.

[0044] Preferably, the module division criteria include: functional relevance criteria, contact type criteria and connection relationship criteria.

[0045] S202. Calculate the comprehensive correlation between any two common parts in the mechanical equipment after removing the fasteners.

[0046] The calculation formula of comprehensive correlation includes: (1) In formula (1), Indicates parts 、 The comprehensive correlation of Indicates the strength of functional association, represents the contact association strength, Represents the connection correlation, represents a corresponding weight coefficient of the functional relevance criterion in the comprehensive relevance, wherein the functional relevance criterion represents dividing functionally related parts into the same module; Indicates the corresponding weight coefficient of the contact type criterion in the comprehensive correlation degree. The contact type criterion indicates that the parts in the same module have the same contact type. Indicates the corresponding weight coefficient of the connection type criterion in the comprehensive association degree. The connection type criterion indicates that the parts within the same module have a connection relationship and meet the constraints: .

[0047] It should be noted that the method of setting the weight is mainly based on experience and subjective judgment. When there are many criteria, the difficulty of weight allocation is greater. In this embodiment, the function type has the greatest impact on the difficulty of disassembly, so The largest, followed by the connection type, and the contact type has the smallest impact.

[0048] S203, establish a correlation matrix: By parts 、 The comprehensive correlation degree obtained after weighted average Build a correlation matrix : (2) In formula (2), , , , the correlation matrix It is a symmetric matrix with a diagonal value of 1, indicating that the part has the greatest correlation with itself.

[0049] S204. Based on the degree of association, the two individuals with the closest distance are merged in sequence based on the hierarchical cluster analysis method to obtain a hierarchical structure diagram.

[0050] It should be noted that the end point of hierarchical clustering merging is to form a module division result that meets the requirements of "high functional cohesion, strong structural association, and reasonable module size and number".

[0051] S205. Determine the module size and number of modules according to the number of parts and complexity of the mechanical equipment, and divide the hierarchical structure diagram into several modules.

[0052] S206. After completing the module division of common parts, fasteners are added to the modules to achieve complete module division.

[0053] When the number of mechanical equipment parts is large, the mechanical equipment can be divided into several large modules. If some large modules still include many parts, secondary division is performed until the requirements are met. Figure 3 This is a hierarchical diagram of mechanical equipment. The indivisible modules and parts at the bottom layer are combined into the modules or assemblies at the upper layer, and these are combined in sequence to form mechanical equipment. The position of each component can be found based on this diagram.

[0054] S102 , testing static characteristic measurement indicators of the mechanical equipment in the hierarchical order of “parts-modules-mechanical equipment” to obtain test data.

[0055] Preferably, the test data includes: the measured values ​​of static characteristic measurement indicators and the corresponding mechanical equipment status; static characteristic measurement indicators include indicators used to evaluate the characteristics of the entire machine or module under static conditions, key dimensions, surface quality, assembly fit, etc.; key dimensions include linear dimensions, geometric shapes, angles, etc.; surface quality includes roughness, hardness, etc.; assembly fit includes clearance, centering, assembly structure dimensions, etc.

[0056] like Figure 4 In some embodiments of the present invention, step S102 specifically includes: S401. Detect various indicators of mechanical equipment in the hierarchical order of "parts-modules-complete machine" and construct a set of status assessment indicators.

[0057] Assume that the sample set collected for the status detection of mechanical equipment parts is In this sample set, each row represents a component, and each column represents an indicator process parameter in each detection process. Due to the different importance of different indicators, some indicators will be measured multiple times in different detection processes during the detection process. Therefore, it is necessary to evaluate the status of mechanical equipment components based on the stability of the mechanical equipment detection indicators. For the multiple detection data of a single indicator of each sample in the sample set, the standard deviation of the multiple detection data of the single indicator is calculated, and the calculated standard deviation is combined into a new data set, that is, the fused feature data set is obtained. .

[0058] Specifically, the calculation formula for the construction index set of the mechanical equipment condition assessment model is as follows: (3) (4) In formulas (2)-(3), Indicates the number of indicators, Indicates the number of detections, represents the number of samples, Indicates the The first indicator The measured value, Indicates the first of multiple tests The mean of the indicators, Indicates the The first sample The standard deviation of the indicator, is the state evaluation indicator set.

[0059] S402: Perform importance analysis based on the state evaluation indicator set to screen and obtain static characteristic measurement indicators.

[0060] Preferably, the present invention adopts the random forest method to perform importance analysis. Specifically, by comparing and screening the importance values ​​of the status indicators of the random forest model, a suitable threshold is formulated. Indicator importance values ​​less than the threshold are considered to be poor status indicators and are deleted, while indicators importance values ​​greater than the threshold are considered to be good status indicators and are retained.

[0061] like Figure 5 In some embodiments of the present invention, step S402 includes: S501. Perform importance analysis on the status assessment indicator set based on the random forest model.

[0062] Among them, the calculation formula of the importance of the status evaluation index includes: feature Importance in a single tree: (5) In formula (4), For a single tree, is the number of non-leaf nodes, For nodes The reduction in squared loss after the split, For and node associated features; Calculate features After calculating the importance of a single tree, the importance values ​​of all trees are accumulated and averaged, and then normalized to calculate the feature The global importance value of: (6) In formula (5), is the number of trees, , Indicates the A tree.

[0063] S502: retain the state indicators whose global importance values ​​are greater than a preset threshold as static characteristic measurement indicators.

[0064] S403: Arrange and obtain the detection data of the static characteristic measurement index.

[0065] S103. Construct a mathematical model for describing the relationship between various static characteristic measurement indicators and the state of the mechanical equipment based on a weighted quantitative evaluation method and / or a fuzzy comprehensive evaluation method.

[0066] It should be noted that the core of the weighted quantitative assessment method is to quantify the component condition through a quality loss function. The loss value is calculated directly based on the square of the deviation between the actual value and the standard value. The larger the deviation, the worse the condition. Its characteristics are precise quantification and clear dependence on numerical deviation. It is suitable for scenarios where the indicator boundaries are clear and can be accurately measured.

[0067] The fuzzy comprehensive evaluation method introduces fuzzy functions based on weighted quantitative assessment methods. By establishing a probability matrix for excellent, good, fair, and poor, quantitative deviations are converted into fuzzy probabilities. This is then combined with a scoring system and an indicator importance matrix to calculate a comprehensive score. Its characteristic is its ability to handle fuzziness and uncertainty, making it suitable for scenarios where indicator boundaries are fuzzy or where a hierarchical evaluation is required.

[0068] These two methods can be used either or both depending on the specific scenario. When the evaluation metric boundaries are clear, the data accuracy is high, and precise quantification of state differences is required, the weighted quantitative evaluation method can be used alone. When the evaluation metric boundaries are fuzzy, or when the results need to be converted into hierarchical conclusions to aid decision-making, the fuzzy comprehensive evaluation method can be used. When both precision and fuzziness are required, the two methods can be used in combination.

[0069] In some embodiments of the present invention, an initial model is constructed based on a weighted quantitative evaluation method in combination with detection data, including: Constructing quality loss function As the initial model, the calculation formula is: (7) In formula (7), is the actual value of a single status indicator of a single part of the mechanical equipment, is the standard value of a single status indicator of a single part, is the proportionality constant; The larger the value, the worse the condition of the part.

[0070] The main working principle of weighted quantitative condition assessment is: first determine the condition assessment result of the part size, then obtain the condition assessment result of each surface of the part after weighting it, and then obtain the final condition assessment result of the part after weighting.

[0071] In a specific embodiment, the steps of using the weighted quantitative method to perform status assessment are as follows: Step 1: Conduct quality evaluation of part size, shape error, and position error According to the actual processing size of the part and the quality loss function, the actual quality score of the part processing size is calculated; according to the actual shape error and position error of the part, the quality score of the part shape accuracy and position accuracy is calculated using the same method.

[0072] Step 2: Calculate the quality score of the machined surface of the component The processing of a surface may be composed of multiple size, shape errors, and position errors. Once the size, shape, and position accuracy quality scores of the surface are calculated, the surface quality score of the component can be obtained based on the importance of its impact on performance.

[0073]

[0074] The weighted coefficients of component size importance are shown in Table 1.

[0075] Table 1 Weighted coefficients of component size importance

[0076] in, .

[0077] Step 3: Calculate the part surface quality score A component is composed of multiple surfaces. After the quality scores of each surface are obtained, the surface quality score of the entire component is obtained by multiplying the corresponding surface importance weighting coefficient according to the degree of influence of these surfaces on the performance of the part.

[0078]

[0079] The weighted coefficients of part surface importance are shown in Table 2.

[0080] Table 2 Weighted coefficients of part surface importance

[0081] in, .

[0082] like Figure 6 The figure shows a typical parts diagram of a mechanical equipment, and its data is obtained to perform quantitative status assessment. , the measured value is 100.2mm; , the measured value is 59.95mm; , the measured value is 45mm; , the measured value is 20.02mm; , the measured value is 25.01mm; the end face parallelism is 0.05mm, the measured value is 0.025mm.

[0083] The relevant measurement data and importance are shown in Table 3.

[0084] Table 3 Related measurement data and importance

[0085] According to the formula and Figure 5 , calculate the quality score of the part size and shape tolerance. According to the formula and the importance weighting coefficients given in Table 1 and Table 2, calculate the surface quality score of the part and list it in Table 4.

[0086] Table 4 Part surface quality scores

[0087] Importance weighting coefficients in Table 4 , , Calculate the part condition score. Part condition score = (98.3 × 1 + 90 × 5 + 91.7 × 3) / (1 + 5 + 3) = 91.49. The condition assessment result is excellent.

[0088] In some embodiments of the present invention, an initial model is constructed based on the fuzzy comprehensive evaluation method and combined with the detection data, including: For mechanical equipment parts measurement indicators, and establish an evaluation coefficient matrix based on the importance of each indicator for status evaluation. , the calculation formula is: (8) In formula (8), is the importance of the indicator, ; The absolute value of the deviation of each measurement indicator Divide by the tolerance band to get the evaluation matrix , the calculation formula is: (9) In formula (9), = , is the deviation value of each indicator; is the tolerance band of this indicator.

[0089] It should be noted that The smaller the value, the better the status. The measurement indicator status is divided into excellent, good, medium and poor. When it is 0, the probability that the measurement index is excellent is 1, and the probability that the measurement index is good is 0; when When it is 0.5, the probability that the measurement index is good is 1, and the probability that the measurement index is excellent is 0; when When is 1, the probability that the measurement index is medium is 1, and the probability that the measurement index is good is 0; when When it is 1.5, the probability that the measurement index is poor is 1, and the probability that the measurement index is good is 0; when When it is greater than 1.5, the probability that the measurement indicator is poor is 1.

[0090] Establish the excellent, good, medium and poor probability matrix for each indicator , the calculation formula is: (10) (11) (12) (13) (14) In formula (10), For the The probability that the point is optimal; For the The probability that a point is good; For the The probability of the point being in the middle; For the The probability of the pip being the difference; .

[0091] Establish an excellent, good, fair, and poor rating system matrix The measurement index is a point for excellent, b point for good, c point for fair, and d point for poor, that is: (11) For example, the measurement index is 100 points for excellent, 70 points for good, 40 points for fair, and 0 points for poor. .

[0092] Create a matrix , determine the score of each indicator as: (12) In formula (12), , Assign a score to each indicator; Combined with the impact of each indicator on the status of mechanical equipment , establish a scoring matrix for mechanical equipment parts , the calculation formula is: (13) Will As a basis for measuring the status of mechanical equipment parts.

[0093] S104 , optimizing the weights of various static characteristic measurement indicators in the mathematical model based on the detection data fitting, to obtain a final mechanical equipment state evaluation model for evaluating the mechanical equipment state according to the measured values ​​of the static characteristic measurement indicators.

[0094] like Figure 7 In a second aspect, the present invention further provides a method for evaluating the condition of a mechanical device, comprising: S701: Construct a mechanical equipment condition assessment model based on the method for constructing a mechanical equipment condition assessment model according to any one of the above methods; S702 : Input the measured values ​​of the static characteristic measurement indicators into a mechanical equipment state evaluation model, and determine an evaluation result of the mechanical equipment state according to an output value of the mechanical equipment state evaluation model.

[0095] To better understand the specific embodiments of the present invention, Figure 8 A complete process for condition assessment of mechanical equipment in a more specific embodiment is provided.

[0096] like Figure 9 In a third aspect, the present invention further provides a device 90, comprising: Memory 910, used for storing programs; The processor 920 is coupled to the memory 910 and is used to execute the program stored in the memory 910 to implement the method for constructing a mechanical equipment condition assessment model or the steps in the mechanical equipment condition assessment method described in any one of the above method items.

[0097] In a fourth aspect, the present invention further provides a medium, comprising: Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the method for constructing a mechanical equipment condition assessment model or the steps in the mechanical equipment condition assessment method described in any one of the above method items.

[0098] The above is a detailed introduction to the construction and evaluation method, equipment and medium of a mechanical equipment status assessment model provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for technical personnel in this field, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for constructing a mechanical equipment condition assessment model, characterized in that: include: Classify parts of mechanical equipment that are functionally related, have connection relationships, and have the same contact type into the same module; Testing static characteristic measurement indicators of the mechanical equipment in the hierarchical order of "parts-modules-mechanical equipment" to obtain test data, wherein the test data includes: measured values ​​of the static characteristic measurement indicators and corresponding states of the mechanical equipment; the static characteristic measurement indicators include: indicators used to evaluate the characteristics of the entire machine or module under static conditions; Constructing a mathematical model based on a weighted quantitative evaluation method and / or a fuzzy comprehensive evaluation method to describe the relationship between various static characteristic measurement indicators and the state of the mechanical equipment; The weights of various static characteristic measurement indicators in the mathematical model are optimized based on the detection data fitting, so as to obtain a final mechanical equipment state evaluation model for evaluating the mechanical equipment state according to the measured values ​​of the static characteristic measurement indicators.

2. The method for constructing a mechanical equipment condition assessment model according to claim 1, characterized in that: The method of dividing the parts of the mechanical equipment that are functionally related, have a connection relationship, and have the same contact type into the same module includes: Formulate evaluation value assignment standards for the module division criteria and set weight coefficients, wherein the module division criteria include: function relevance criteria, contact type criteria, and connection relationship criteria; Calculate the comprehensive correlation between any two common parts in the mechanical equipment after removing the fasteners. The calculation formula of the comprehensive correlation includes: in, Indicates parts 、 The comprehensive correlation of Indicates the strength of functional association, represents the contact association strength, Represents the connection correlation, represents a corresponding weight coefficient of the functional relevance criterion in the comprehensive relevance, wherein the functional relevance criterion represents dividing functionally related parts into the same module; Indicates the corresponding weight coefficient of the contact type criterion in the comprehensive correlation degree. The contact type criterion indicates that the parts in the same module have the same contact type. Indicates the corresponding weight coefficient of the connection type criterion in the comprehensive association degree. The connection type criterion indicates that the parts within the same module have a connection relationship and meet the constraints: ; Establish a correlation matrix; According to the degree of association, the two individuals with the closest distance are merged in turn based on the hierarchical cluster analysis method to obtain a hierarchical structure diagram; Determine the module size and number according to the number of parts and complexity of the mechanical equipment, and divide the hierarchical structure diagram into several modules; After completing the module division of common parts, fasteners are added to the modules to achieve complete module division.

3. The method for constructing a mechanical equipment condition assessment model according to claim 1, wherein: The static characteristic measurement indicators of the mechanical equipment are tested in the hierarchical order of "parts-modules-mechanical equipment" to obtain test data, including: Detect various indicators of the mechanical equipment in the hierarchical order of "parts-modules-mechanical equipment" to construct a set of condition assessment indicators; Performing importance analysis based on the state evaluation indicator set to screen and obtain the static characteristic measurement indicator; The measured values ​​of static characteristic measurement indicators are obtained by sorting.

4. The method for constructing a mechanical equipment condition assessment model according to claim 3, wherein: The construction formula of the state evaluation index set includes: The calculation formula for the construction index set of the mechanical equipment condition assessment model is as follows: in, Indicates the number of indicators, Indicates the number of detections, represents the number of samples, Indicates the The first indicator The measured value, Indicates the first of multiple tests The mean of the indicators, Indicates the The first sample The standard deviation of the indicator, is the state evaluation indicator set.

5. The method for constructing a mechanical equipment condition assessment model according to claim 4, characterized in that: The importance analysis is performed based on the state evaluation indicator set to screen and obtain the static characteristic measurement indicator, including: The importance of the state assessment indicator set is analyzed based on the random forest model, wherein the calculation formula of the importance of the state assessment indicator includes: feature Importance in a single tree: in, For a single tree, is the number of non-leaf nodes, For nodes The reduction in squared loss after the split, For and node associated features; Calculate features After calculating the importance of a single tree, the importance values ​​of all trees are accumulated and averaged, and then normalized to calculate the feature The global importance value of: in, is the number of trees, , Indicates the a tree; The state indicators whose global importance values ​​are greater than a preset threshold are retained as the static characteristic measurement indicators.

6. The method for constructing a mechanical equipment condition assessment model according to claim 1, characterized in that: Based on the weighted quantitative evaluation method, an initial model is constructed in combination with the test data, including: Constructing quality loss function As the initial model, the calculation formula is: in, is the actual value of a single status indicator of a single part of the mechanical equipment, is the standard value of a single status indicator of a single part, is the proportionality constant; The larger the value, the worse the condition of the part.

7. The method for constructing a mechanical equipment condition assessment model according to claim 1, characterized in that: Based on the fuzzy comprehensive evaluation method, an initial model is constructed in combination with the detection data, including: For Mechanical equipment parts with multiple measurement indicators, establish an evaluation coefficient matrix based on the importance of each indicator for status evaluation , the calculation formula is: Where, is the importance of the indicator, ; The absolute value of the deviation of each measurement indicator Divide by the tolerance band to get the evaluation matrix , the calculation formula is: Where, = , is the deviation value of each indicator; is the tolerance band of the indicator; Establish the excellent, good, medium and poor probability matrix for each indicator , the calculation formula is: Where, For the The probability that the point is optimal; For the The probability that a point is good; For the The probability of the point being in the middle; For the The probability of the pip being the difference; ; Establish an excellent, good, fair, and poor rating system matrix The measurement index is a point for excellent, b point for good, c point for medium, and d point for poor, that is, ; Create a matrix , determine the score of each indicator as: Where, , Assign a score to each indicator; Combined with the impact of each indicator on the status of mechanical equipment , establish a scoring matrix for mechanical equipment parts , the calculation formula is: As a basis for measuring the status of mechanical equipment parts.

8. A method for evaluating the condition of mechanical equipment, characterized in that: include: Constructing a mechanical equipment condition assessment model based on the method for constructing a mechanical equipment condition assessment model according to any one of claims 1 to 7; The measured value of the static characteristic measurement index is input into the mechanical equipment state evaluation model, and the evaluation result of the mechanical equipment state is determined according to the output value of the mechanical equipment state evaluation model.

9. A device, characterized in that include: Memory, used to store programs; A processor, coupled to the memory, is used to execute the program stored in the memory to implement the method for constructing a mechanical equipment condition assessment model as described in any one of claims 1 to 7 or the steps in the mechanical equipment condition assessment method as described in any one of claim 8.

10. A medium, characterized in that include: Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the method for constructing a mechanical equipment condition assessment model as described in any one of claims 1 to 7 or the steps in the mechanical equipment condition assessment method as described in any one of claim 8.

Images