Equipment fault diagnosis data analysis method and system based on information screening

Abstract

The invention discloses an equipment fault diagnosis data analysis method and system based on information screening, and belongs to the technical field of data analysis. The system comprises a data acquisition module, a diagnostic analysis module, a fault processing module and a data storage module. The data acquisition module is used for acquiring a standard comparison table of the equipment and acquiring environment records and parameter records of all parts under the equipment through a sensor; the diagnostic analysis module identifies the abnormal part through the standard comparison table and the parameter record, matches other parts with an influence relationship for the abnormal part according to the environment record and the parameter record, and establishes an influence relationship chain; the fault processing module analyzes the relationship among the components in the influence relationship chain, establishes a relational expression, and predicts the operation parameters of each component according to the relational expression, so as to mark the components and generate a fault diagnosis report; and the data storage module stores the fault diagnosis report to an intelligent terminal of a manager, and updates the environment record and the parameter record in real time.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a method and system for analyzing equipment fault diagnosis data based on information screening. Background Art

[0002] As technology develops, the complexity of industrial equipment continues to increase, and the combination of various mechanical components makes it essential to monitor the operating status of equipment. However, these devices may experience various failures during operation, resulting in reduced production efficiency, property losses, and even threats to safety. Therefore, it is particularly important to accurately and promptly identify and diagnose equipment failures.

[0003] In the field of equipment fault diagnosis, the accuracy and reliability of data collection are crucial. However, during the data collection process, interference from adjacent units and the influence of the external environment often lead to data distortion, making the acquired data unable to truly reflect the actual operating status of the unit. This distortion not only reduces the accuracy of fault diagnosis, but also may lead to the risk of misjudgment and missed judgment. Therefore, it is increasingly important to use advanced data analysis technology to improve the safety and reliability of equipment operation, eliminate these interferences from the root, and improve the reliability and accuracy of data. Therefore, at this stage, an efficient and intelligent equipment fault diagnosis data analysis technology solution is needed to solve the above problems. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for analyzing equipment fault diagnosis data based on information screening to solve the problems raised in the above-mentioned background technology.

[0005] In order to solve the above technical problems, the present invention provides an equipment fault diagnosis data analysis method based on information screening, comprising the following steps:

[0006] S100, collecting the standard comparison table of the equipment, collecting the environmental records and parameter records of each component under the equipment in real time through sensors.

[0007] S200, identifying abnormal components through standard comparison tables and parameter records, matching other components with impact relationships for the abnormal components according to environment records and parameter records, and establishing an impact relationship chain.

[0008] S300, analyzing the relationship between the components in the impact relationship chain and establishing a relationship expression, predicting the operating parameters of each component according to the relationship expression, thereby marking the components and generating a fault diagnosis report.

[0009] S400: Store the fault diagnosis report in the manager's smart terminal, and update the environment record and parameter record in real time.

[0010] In S100, the standard comparison table includes the maximum allowable vibration value of each component under the device. The sensor includes a temperature and humidity sensor and a vibration sensor. The temperature and humidity sensor is used to collect the temperature and humidity of the surrounding environment of the device, and the vibration sensor is used to collect the vibration value of each component under the device. The environmental record includes the temperature and humidity at different times, and the parameter record includes the vibration value of the component at different times.

[0011] The standard comparison table is an important reference document developed to ensure the safe and reliable operation of the equipment. It lists in detail the maximum allowable vibration values ​​of each component under the equipment. The table includes the names of different components, the corresponding maximum vibration values, the applicable measurement frequency range, and related remarks.

[0012] This data helps the monitoring system evaluate the operating status of the equipment and identify potential vibration problems in a timely manner, thereby avoiding equipment failure and extending its service life. By following this standard comparison table, maintenance managers can develop effective preventive maintenance plans and ensure that the equipment is always in optimal working condition.

[0013] Temperature and humidity sensors are used to collect temperature and humidity data around the equipment in order to monitor and control the working environment in real time and ensure that the equipment operates in the best condition. At the same time, vibration sensors are specifically used to detect the vibration values ​​of various parts of the equipment. By accurately monitoring the vibration, potential mechanical failures can be identified in a timely manner.

[0014] The combination of these sensors not only improves the operational safety and stability of the equipment, but also provides important data support for subsequent maintenance decisions and promotes the intelligent management of industrial equipment.

[0015] In S200, the specific steps are as follows:

[0016] S201, obtain the standard comparison table and the parameter records of each component, and analyze the vibration value VIB at the latest time in each parameter record now , and the maximum allowable vibration value VIB of each component max , the vibration value VIB now Greater than VIB max The component corresponding to the parameter record is regarded as an abnormal component.

[0017] S202: When there is an abnormal component in the device, obtain the temperature TEM at the current time in the environmental record. now and humidity now ; Set the temperature threshold TEM thr and humidity threshold HUM thr , analyze the temperature and humidity in the past time in the environmental records and calculate the TEM now and HUM nowThe difference between the two values ​​is smaller than TEM. thr and HUM thr The time period is taken as the sampling time period.

[0018] The main function of this process is to monitor and analyze the temperature and humidity of the environment surrounding the equipment in real time, so as to ensure that when there are abnormal components in the equipment, the impact of the environment on the performance of the equipment can be identified and evaluated in time.

[0019] First, record the temperature and humidity data of the current time and set the corresponding temperature and humidity thresholds. Then, by analyzing the historical environmental records, calculate the difference between the temperature and humidity in the past time period and the current value, and filter out those time periods where the difference is less than the set threshold at the same time.

[0020] This method not only helps to determine the operating status of equipment under various environmental conditions, but also provides data support for subsequent fault analysis and maintenance decisions, thereby improving the reliability and safety of equipment.

[0021] S203, set the sampling time length e, divide the time length of each sampling time period by e to get the number of sampling points, and evenly set the sampling points in the sampling time period according to the number of sampling points. ab The associated components are associated with each other in turn, so as to establish the associated components. The vibration values ​​of the associated components at the corresponding time of each sampling point in all sampling time periods are obtained and the difference is calculated. The standard deviation of the difference at all sampling points is calculated as the difference coefficient of the associated components.

[0022] S204, set the coefficient threshold U, mark the associated components with a difference coefficient less than U, and establish an influence relationship between the two components in the marked associated components. Analyze whether each abnormal component has an influence relationship with other components. After all abnormal components are analyzed, continue to associate the components that have an influence relationship with the abnormal components with other components again, analyze and establish the influence relationship, and connect the components with the influence relationship to establish an influence relationship chain.

[0023] The purpose of this process is to analyze and establish the influence relationship between equipment components to identify potential sources of failure and related factors.

[0024] By marking the associated components whose difference coefficient is less than the preset threshold, it is possible to effectively identify which components may have mutual influence, and then establish the corresponding influence relationship. After completing the analysis of all abnormal components, further pairwise correlation analysis is performed on other components that have influence relationships with these abnormal components, thereby forming a more complex influence relationship chain.

[0025] This process not only helps reveal the fault propagation path within the equipment, but also provides clear guidance for maintenance personnel to formulate more effective repair and maintenance strategies, thereby improving the overall operational reliability and safety of the equipment.

[0026] In S300, the specific steps are as follows:

[0027] S301. Establish a training set for each pair of associated components. Use the vibration values ​​of the two components in the associated components at the same sampling point as independent variables and dependent variables respectively. The independent variables and dependent variables are packaged into samples. Each sampling point corresponds to a sample. These samples are put into the training set of the corresponding associated components.

[0028] S302, establish a linear regression model, substitute the independent variables of the samples in the training set as input values ​​into the linear regression model expression, calculate the difference between the output result of each sample and the dependent variable, sum the differences of all samples in the training set as the gap coefficient, and minimize the gap coefficient by adjusting the intercept L and the regression coefficient α in the expression, and obtain the relationship expression corresponding to each training set respectively:

[0029] P=L+αW

[0030] In the formula, P is the dependent variable and W is the independent variable.

[0031] S303, obtain the vibration values ​​of all abnormal components, substitute them into the corresponding relationship expressions respectively, and use the calculation results as the corresponding component CAP of the relationship expression cd Expected vibration value Then put the component CAP cd Substitute the expected vibration value into other components that have an impact on CAP ef In the corresponding relationship expression of ef Expected vibration value Similarly, calculate the expected vibration value of each component separately.

[0032] The main purpose of this process is to predict and diagnose the vibration behavior of equipment components through a systematic approach to identify potential failures and provide a basis for maintenance decisions.

[0033] By obtaining the vibration values ​​of all abnormal components and substituting these values ​​into the corresponding relationship expressions, the expected vibration value of each component is calculated. These expected vibration values ​​are then used to calculate the expected vibration values ​​of other components that have an impact relationship with them, thus forming a coherent vibration prediction chain.

[0034] S304, obtain the vibration values ​​of all components with influencing relationships, substitute them into all corresponding relational expressions respectively, and use the calculation results as the predicted vibration values ​​of the components corresponding to each relational expression. Analyze the predicted vibration value and all predicted vibration values ​​of each component, calculate the average value of the predicted vibration value and all predicted vibration values ​​as the theoretical vibration value, and the standard deviation of the predicted vibration value and all predicted vibration values ​​as the abnormal index. Set the index threshold S, mark the components whose theoretical vibration value is greater than the maximum allowable vibration value and whose abnormal index is less than S, and generate a fault diagnosis report based on the current vibration values ​​of all abnormal components, as well as the current vibration values ​​and theoretical vibration values ​​of all marked components.

[0035] By substituting the vibration values ​​of all components with influencing relationships into the formula for processing and calculation, the predicted vibration value of each component is obtained. Each component has as many predicted vibration values ​​as the number of pairs of related components it exists in. By calculating the theoretical vibration value and abnormal index, the health status of the component can be further evaluated.

[0036] Set appropriate index thresholds to mark components whose theoretical vibration values ​​exceed the maximum allowable vibration value and whose abnormal index is lower than the index threshold. The final results of this series of analyses and calculations will be summarized as a fault diagnosis report to help maintenance personnel promptly discover potential equipment failures and develop corresponding maintenance strategies, thereby improving the safety and reliability of equipment.

[0037] In S400, the fault diagnosis report is stored in the manager's smart terminal. The manager can analyze the fault diagnosis report to determine whether to conduct an on-site inspection or ignore it. The environmental records and parameter records are updated in real time according to the changes in temperature and humidity in the environment and the vibration values ​​of each component.

[0038] The equipment fault diagnosis data analysis system based on information screening includes a data acquisition module, a diagnosis analysis module, a fault processing module and a data storage module.

[0039] The data acquisition module is used to collect the standard comparison table of the equipment, and collect environmental records and parameter records of each component under the equipment through sensors.

[0040] The diagnostic analysis module identifies abnormal components through standard comparison tables and parameter records, matches abnormal components with other components that have an impact relationship based on environmental records and parameter records, and establishes an impact relationship chain.

[0041] The fault handling module analyzes the relationship between components in the impact relationship chain and establishes a relationship expression, predicts the operating parameters of each component based on the relationship expression, and thus marks the components and generates a fault diagnosis report.

[0042] The data storage module stores the fault diagnosis report to the manager's intelligent terminal and updates the environmental record and parameter record.

[0043] The data acquisition module includes a parameter record acquisition unit, an environmental data acquisition unit and a comparison table acquisition unit.

[0044] The parameter record collection unit is used to collect parameter records of various components under the equipment, and the parameter records include vibration values ​​of the components at different times.

[0045] The environmental data acquisition unit is used to collect the environmental records of the equipment. The environmental records refer to the temperature and humidity of the surrounding environment of the equipment, specifically including the temperature and humidity at different times.

[0046] The comparison table collection unit is used to collect standard comparison tables, specifically including the maximum allowable vibration values ​​of various components under the equipment.

[0047] The diagnosis and analysis module includes an information screening unit and a chain building unit.

[0048] The information screening unit is used to screen out the sampling time period.

[0049] First analyze the vibration value VIB at the latest time in each parameter record now , and the maximum allowable vibration value VIB of each component in the standard comparison table max , the vibration value VIB now Greater than VIB max The component corresponding to the parameter record is regarded as an abnormal component. When there is an abnormal component in the device, the temperature TEM at the current time in the environmental record is obtained. now and humidity now .

[0050] Then set the temperature threshold TEM thr and humidity threshold HUM thr , analyze the temperature and humidity in the past time in the environmental records and calculate the TEM now and HUM now The difference between the two values ​​is smaller than TEM. thr and HUM thr The time period is taken as the sampling time period.

[0051] Chain building units are used to establish chains of influence relationships.

[0052] First, set the sampling duration e, divide the duration of each sampling period by e to get the number of sampling points, and evenly set the sampling points in the sampling period according to the number of sampling points. Associate the abnormal component L with other components in turn to establish associated components.

[0053] Secondly, obtain the vibration value of the associated component at the corresponding time of each sampling point in all sampling time periods and calculate the difference, and calculate the standard deviation of the difference at all sampling points as the difference coefficient of the associated component. Set the coefficient threshold U, mark the associated components with a difference coefficient less than U, and establish an influence relationship between the two components in the marked associated components.

[0054] Finally, analyze whether each abnormal component has an impact relationship with other components. After all abnormal components are analyzed, continue to associate the components that have an impact relationship with the abnormal components with other components again, analyze and establish the impact relationship, and connect the components with the impact relationship to establish an impact relationship chain.

[0055] The fault processing module includes a relationship analysis unit and a fault prediction unit.

[0056] The relational analysis unit is used to establish relational expressions.

[0057] First, a training set is established for each pair of associated components. The vibration values ​​of the two components in the associated components at the same sampling point are used as independent variables and dependent variables respectively. The independent variables and dependent variables are packaged into samples. Each sampling point corresponds to a sample, and these samples are placed in the training set of the corresponding associated components.

[0058] Then establish a linear regression model, substitute the independent variables of the samples in the training set as input values ​​into the linear regression model expression, calculate the difference between the output result of each sample and the dependent variable, sum the differences of all samples in the training set as the gap coefficient, and minimize the gap coefficient by adjusting the intercept L and the regression coefficient α in the expression, so as to obtain the relationship expression corresponding to each training set: P = L + αW, where P is the dependent variable and W is the independent variable.

[0059] The fault prediction unit is used to mark components and generate fault diagnosis reports.

[0060] First, obtain the vibration values ​​of all abnormal components, substitute them into the corresponding relationship expressions, and use the calculation results as the corresponding component CAP of the relationship expression cd Expected vibration value

[0061] Then put the component CAP cd Substitute the expected vibration value into other components that have an impact on CAP ef In the corresponding relationship expression of ef Expected vibration value

[0062] Similarly, calculate the expected vibration value of each component separately.

[0063] Secondly, the vibration values ​​of all components with influencing relationships are obtained, and are substituted into all corresponding relationship expressions respectively, and the calculation results are used as the predicted vibration values ​​of the components corresponding to each relationship expression.

[0064] The expected vibration value and all predicted vibration values ​​of each component are analyzed, and the average values ​​of the expected vibration value and all predicted vibration values ​​are calculated as the theoretical vibration value, and the standard deviations of the expected vibration value and all predicted vibration values ​​are calculated as the abnormality index.

[0065] Finally, the index threshold S is set to mark the components whose theoretical vibration values ​​are greater than the maximum allowable vibration value and whose abnormal index is less than S, and a fault diagnosis report is generated based on the current vibration values ​​of all abnormal components, as well as the current vibration values ​​and theoretical vibration values ​​of all marked components.

[0066] The data storage module stores the fault diagnosis report to the manager's smart terminal. The manager processes the fault diagnosis report by analyzing it and updates the environmental records and parameter records in real time according to the changes in temperature and humidity in the environment and the vibration values ​​of each component.

[0067] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0068] Real-time data collection and processing: Through real-time data collection by sensors, the operating status of the equipment and environmental changes can be obtained in a timely manner, improving the timeliness of fault identification.

[0069] Intelligent anomaly identification: Utilize standard comparison tables and parameter records to automatically identify abnormal components, reduce manual intervention, and improve the accuracy and efficiency of fault detection.

[0070] Impact relationship analysis: By establishing an impact relationship chain, the mutual impact between components can be analyzed more comprehensively, helping managers better understand the cause of the failure and its scope of impact.

[0071] Data-based prediction model: Using a linear regression model to predict vibration values ​​can provide more scientific fault warnings and reduce the risks of equipment failure.

[0072] Intelligent storage and updating of fault reports: Fault diagnosis reports are stored in real time on smart terminals, allowing managers to obtain information and make decisions at any time, thereby improving management efficiency.

[0073] Comprehensive consideration of environmental factors: Consider changes in ambient temperature and humidity during fault diagnosis to make the diagnostic results more accurate and reliable.

[0074] In summary, this technical solution significantly improves the efficiency and accuracy of equipment fault diagnosis through intelligent and data-driven methods. Compared with traditional technologies, it has the advantages of rapid anomaly screening and intelligent impact relationship analysis, and can improve the efficiency of fault detection and analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0076] Figure 1 It is a flow chart of the equipment fault diagnosis data analysis method based on information screening of the present invention;

[0077] Figure 2 It is a structural schematic diagram of the equipment fault diagnosis data analysis system based on information screening of the present invention. DETAILED DESCRIPTION

[0078] 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.

[0079] See also Figure 1 The present invention provides a method for analyzing equipment fault diagnosis data based on information screening, comprising the following steps:

[0080] S100, collecting the standard comparison table of the equipment, collecting the environmental records and parameter records of each component under the equipment in real time through sensors.

[0081] S200, identifying abnormal components through standard comparison tables and parameter records, matching other components with impact relationships for the abnormal components according to environment records and parameter records, and establishing an impact relationship chain.

[0082] S300, analyzing the relationship between the components in the impact relationship chain and establishing a relationship expression, predicting the operating parameters of each component according to the relationship expression, thereby marking the components and generating a fault diagnosis report.

[0083] S400: Store the fault diagnosis report in the manager's smart terminal, and update the environment record and parameter record in real time.

[0084] In S100, the standard comparison table includes the maximum allowable vibration value of each component under the device. The sensor includes a temperature and humidity sensor and a vibration sensor. The temperature and humidity sensor is used to collect the temperature and humidity of the surrounding environment of the device, and the vibration sensor is used to collect the vibration value of each component under the device. The environmental record includes the temperature and humidity at different times, and the parameter record includes the vibration value of the component at different times.

[0085] The standard comparison table is an important reference document developed to ensure the safe and reliable operation of the equipment. It lists in detail the maximum allowable vibration values ​​of each component under the equipment. The table includes the names of different components, the corresponding maximum vibration values, the applicable measurement frequency range, and related remarks.

[0086] This data helps the monitoring system evaluate the operating status of the equipment and identify potential vibration problems in a timely manner, thereby avoiding equipment failure and extending its service life. By following this standard comparison table, maintenance managers can develop effective preventive maintenance plans and ensure that the equipment is always in optimal working condition.

[0087] Temperature and humidity sensors are used to collect temperature and humidity data around the equipment in order to monitor and control the working environment in real time and ensure that the equipment operates in the best condition. At the same time, vibration sensors are specifically used to detect the vibration values ​​of various parts of the equipment. By accurately monitoring the vibration, potential mechanical failures can be identified in a timely manner.

[0088] The combination of these sensors not only improves the operational safety and stability of the equipment, but also provides important data support for subsequent maintenance decisions and promotes the intelligent management of industrial equipment.

[0089] In S200, the specific steps are as follows:

[0090] S201, obtain the standard comparison table and the parameter records of each component, and analyze the vibration value VIB at the latest time in each parameter record now , and the maximum allowable vibration value VIB of each component max , the vibration value VIB now Greater than VIB max The component corresponding to the parameter record is regarded as an abnormal component.

[0091] S202: When there is an abnormal component in the device, obtain the temperature TEM at the current time in the environmental record. now and humidity now ; Set the temperature threshold TEM thr and humidity threshold HUM thr , analyze the temperature and humidity in the past time in the environmental records and calculate the TEM now and HUM nowThe difference between the two values ​​is smaller than TEM. thr and HUM thr The time period is taken as the sampling time period.

[0092] The main purpose of this process is to monitor and analyze the temperature and humidity of the environment surrounding the equipment in real time, so as to ensure that when there are abnormal components in the equipment, the impact of the environment on the performance of the equipment can be identified and evaluated in time.

[0093] First, record the temperature and humidity data of the current time and set the corresponding temperature and humidity thresholds. Then, by analyzing the historical environmental records, calculate the difference between the temperature and humidity in the past time period and the current value, and filter out those time periods where the difference is less than the set threshold at the same time.

[0094] This method not only helps to determine the operating status of equipment under various environmental conditions, but also provides data support for subsequent fault analysis and maintenance decisions, thereby improving the reliability and safety of equipment.

[0095] S203, set the sampling time length e, divide the time length of each sampling time period by e to get the number of sampling points, and evenly set the sampling points in the sampling time period according to the number of sampling points. ab The associated components are associated with each other in turn, so as to establish the associated components. The vibration values ​​of the associated components at the corresponding time of each sampling point in all sampling time periods are obtained and the difference is calculated. The standard deviation of the difference at all sampling points is calculated as the difference coefficient of the associated components.

[0096] S204, set the coefficient threshold U, mark the associated components with a difference coefficient less than U, and establish an influence relationship between the two components in the marked associated components. Analyze whether each abnormal component has an influence relationship with other components. After all abnormal components are analyzed, continue to associate the components that have an influence relationship with the abnormal components with other components again, analyze and establish the influence relationship, and connect the components with the influence relationship to establish an influence relationship chain.

[0097] The purpose of this process is to analyze and establish the influence relationship between equipment components to identify potential sources of failure and related factors.

[0098] By marking the associated components whose difference coefficient is less than the preset threshold, it is possible to effectively identify which components may have mutual influence, and then establish the corresponding influence relationship. After completing the analysis of all abnormal components, further pairwise correlation analysis is performed on other components that have influence relationships with these abnormal components, thereby forming a more complex influence relationship chain.

[0099] This process not only helps reveal the fault propagation path within the equipment, but also provides clear guidance for maintenance personnel to formulate more effective repair and maintenance strategies, thereby improving the overall operational reliability and safety of the equipment.

[0100] In S300, the specific steps are as follows:

[0101] S301. Establish a training set for each pair of associated components. Use the vibration values ​​of the two components in the associated components at the same sampling point as independent variables and dependent variables respectively. The independent variables and dependent variables are packaged into samples. Each sampling point corresponds to a sample. These samples are put into the training set of the corresponding associated components.

[0102] S302, establish a linear regression model, substitute the independent variables of the samples in the training set as input values ​​into the linear regression model expression, calculate the difference between the output result of each sample and the dependent variable, sum the differences of all samples in the training set as the gap coefficient, and minimize the gap coefficient by adjusting the intercept L and the regression coefficient α in the expression, and obtain the relationship expression corresponding to each training set respectively:

[0103] P=L+αW

[0104] In the formula, P is the dependent variable and W is the independent variable.

[0105] S303, obtain the vibration values ​​of all abnormal components, substitute them into the corresponding relationship expressions respectively, and use the calculation results as the corresponding component CAP of the relationship expression cd Expected vibration value Then put the component CAP cd Substitute the expected vibration value into other components that have an impact on CAP ef In the corresponding relationship expression of ef Expected vibration value Similarly, calculate the expected vibration value of each component separately.

[0106] The main purpose of this process is to predict and diagnose the vibration behavior of equipment components through a systematic approach to identify potential failures and provide a basis for maintenance decisions.

[0107] By obtaining the vibration values ​​of all abnormal components and substituting these values ​​into the corresponding relationship expressions, the expected vibration value of each component is calculated. These expected vibration values ​​are then used to calculate the expected vibration values ​​of other components that have an impact relationship with them, thus forming a coherent vibration prediction chain.

[0108] S304, obtain the vibration values ​​of all components with influencing relationships, substitute them into all corresponding relational expressions respectively, and use the calculation results as the predicted vibration values ​​of the components corresponding to each relational expression. Analyze the predicted vibration value and all predicted vibration values ​​of each component, calculate the average value of the predicted vibration value and all predicted vibration values ​​as the theoretical vibration value, and the standard deviation of the predicted vibration value and all predicted vibration values ​​as the abnormal index. Set the index threshold S, mark the components whose theoretical vibration value is greater than the maximum allowable vibration value and whose abnormal index is less than S, and generate a fault diagnosis report based on the current vibration values ​​of all abnormal components, as well as the current vibration values ​​and theoretical vibration values ​​of all marked components.

[0109] By substituting the vibration values ​​of all components with influencing relationships into the formula for processing and calculation, the predicted vibration value of each component is obtained. Each component has as many predicted vibration values ​​as the number of pairs of related components it exists in. By calculating the theoretical vibration value and abnormal index, the health status of the component can be further evaluated.

[0110] Set appropriate index thresholds to mark components whose theoretical vibration values ​​exceed the maximum allowable vibration value and whose abnormal index is lower than the index threshold. The final results of this series of analyses and calculations will be summarized as a fault diagnosis report to help maintenance personnel promptly discover potential equipment failures and develop corresponding maintenance strategies, thereby improving the safety and reliability of equipment.

[0111] In S400, the fault diagnosis report is stored in the manager's smart terminal. The manager can analyze the fault diagnosis report to determine whether to conduct an on-site inspection or ignore it. The environmental records and parameter records are updated in real time according to the changes in temperature and humidity in the environment and the vibration values ​​of each component.

[0112] See also Figure 2 The present invention provides an equipment fault diagnosis data analysis system based on information screening, including a data acquisition module, a diagnosis and analysis module, a fault processing module and a data storage module.

[0113] The data acquisition module is used to collect the standard comparison table of the equipment, and collect environmental records and parameter records of each component under the equipment through sensors.

[0114] The diagnostic analysis module identifies abnormal components through standard comparison tables and parameter records, matches abnormal components with other components that have an impact relationship based on environmental records and parameter records, and establishes an impact relationship chain.

[0115] The fault handling module analyzes the relationship between components in the impact relationship chain and establishes a relationship expression, predicts the operating parameters of each component based on the relationship expression, and thus marks the components and generates a fault diagnosis report.

[0116] The data storage module stores the fault diagnosis report to the manager's intelligent terminal and updates the environmental record and parameter record.

[0117] The data acquisition module includes a parameter record acquisition unit, an environmental data acquisition unit and a comparison table acquisition unit.

[0118] The parameter record collection unit is used to collect parameter records of various components under the equipment, and the parameter records include vibration values ​​of the components at different times.

[0119] The environmental data acquisition unit is used to collect the environmental records of the equipment. The environmental records refer to the temperature and humidity of the surrounding environment of the equipment, specifically including the temperature and humidity at different times.

[0120] The comparison table collection unit is used to collect standard comparison tables, specifically including the maximum allowable vibration values ​​of various components under the equipment.

[0121] The diagnosis and analysis module includes an information screening unit and a chain building unit.

[0122] The information screening unit is used to screen out the sampling time period.

[0123] First analyze the vibration value VIB at the latest time in each parameter record now , and the maximum allowable vibration value VIB of each component in the standard comparison table max , the vibration value VIB now Greater than VIB max The component corresponding to the parameter record is regarded as an abnormal component. When there is an abnormal component in the device, the temperature TEM at the current time in the environmental record is obtained. now and humidity now .

[0124] Then set the temperature threshold TEM thr and humidity threshold HUM thr , analyze the temperature and humidity in the past time in the environmental records and calculate the TEM now and HUM now The difference between the two values ​​is smaller than TEM. thr and HUM thr The time period is taken as the sampling time period.

[0125] Chain building units are used to establish chains of influence relationships.

[0126] First, set the sampling duration e, divide the duration of each sampling period by e to get the number of sampling points, and evenly set the sampling points in the sampling period according to the number of sampling points. ab Associate components with other components one by one in turn to establish associated components.

[0127] Secondly, obtain the vibration value of the associated component at the corresponding time of each sampling point in all sampling time periods and calculate the difference, and calculate the standard deviation of the difference at all sampling points as the difference coefficient of the associated component. Set the coefficient threshold U, mark the associated components with a difference coefficient less than U, and establish an influence relationship between the two components in the marked associated components.

[0128] Finally, analyze whether each abnormal component has an impact relationship with other components. After all abnormal components are analyzed, continue to associate the components that have an impact relationship with the abnormal components with other components again, analyze and establish the impact relationship, and connect the components with the impact relationship to establish an impact relationship chain.

[0129] The fault processing module includes a relationship analysis unit and a fault prediction unit.

[0130] The relational analysis unit is used to establish relational expressions.

[0131] First, a training set is established for each pair of associated components. The vibration values ​​of the two components in the associated components at the same sampling point are used as independent variables and dependent variables respectively. The independent variables and dependent variables are packaged into samples. Each sampling point corresponds to a sample, and these samples are placed in the training set of the corresponding associated components.

[0132] Then establish a linear regression model, substitute the independent variables of the samples in the training set as input values ​​into the linear regression model expression, calculate the difference between the output result of each sample and the dependent variable, sum the differences of all samples in the training set as the gap coefficient, and minimize the gap coefficient by adjusting the intercept L and the regression coefficient α in the expression, so as to obtain the relationship expression corresponding to each training set: P = L + αW, where P is the dependent variable and W is the independent variable.

[0133] The fault prediction unit is used to mark components and generate fault diagnosis reports.

[0134] First, obtain the vibration values ​​of all abnormal components, substitute them into the corresponding relationship expressions, and use the calculation results as the corresponding component CAP of the relationship expression cd Expected vibration value

[0135] Then put the component CAP cd Substitute the expected vibration value into other components that have an impact on CAP ef In the corresponding relationship expression of ef Expected vibration value

[0136] Similarly, calculate the expected vibration value of each component separately.

[0137] Secondly, the vibration values ​​of all components with influencing relationships are obtained, and are substituted into all corresponding relationship expressions respectively, and the calculation results are used as the predicted vibration values ​​of the components corresponding to each relationship expression.

[0138] The expected vibration value and all predicted vibration values ​​of each component are analyzed, and the average values ​​of the expected vibration value and all predicted vibration values ​​are calculated as the theoretical vibration value, and the standard deviations of the expected vibration value and all predicted vibration values ​​are calculated as the abnormality index.

[0139] Finally, the index threshold S is set to mark the components whose theoretical vibration values ​​are greater than the maximum allowable vibration value and whose abnormal index is less than S, and a fault diagnosis report is generated based on the current vibration values ​​of all abnormal components, as well as the current vibration values ​​and theoretical vibration values ​​of all marked components.

[0140] The data storage module stores the fault diagnosis report to the manager's smart terminal. The manager processes the fault diagnosis report by analyzing it and updates the environmental records and parameter records in real time according to the changes in temperature and humidity in the environment and the vibration values ​​of each component.

[0141] Embodiment 1:

[0142] Assume that there are two samples A1 and A2 in the training set G, their independent variables are 2 and 3, and their dependent variables are 8 and 10, respectively. The initial relationship expression is P = L + αW;

[0143] Substitute the A1 independent variable and dependent variable into the formula, and adjust the intercept L and regression coefficient α to obtain a further relationship expression:

[0144] P=2+3×W

[0145] Substitute the A2 independent variable into the above formula and we get:

[0146] 2+3×3=11

[0147] Then the gap coefficient is 1. By adjusting the intercept L and regression coefficient α in the expression to minimize the gap coefficient to 0, the final relationship expression is obtained:

[0148] P=4+2×W

[0149] Then the relational expression corresponding to the training set G is P=4+2×W.

[0150] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0151] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for analyzing equipment fault diagnosis data based on information screening, characterized in that: The method comprises the following steps: S100, collect the standard comparison table of the equipment, and collect the environmental records and parameter records of each component of the equipment in real time through sensors; S200, identifying abnormal components through standard comparison tables and parameter records, matching other components with impact relationships for the abnormal components according to environment records and parameter records, and establishing an impact relationship chain; S300, analyzing the relationship between the components in the impact relationship chain and establishing a relationship expression, predicting the operating parameters of each component according to the relationship expression, thereby marking the components and generating a fault diagnosis report; S400: Store the fault diagnosis report in the manager's smart terminal, and update the environment record and parameter record in real time.

2. The equipment fault diagnosis data analysis method based on information screening according to claim 1 is characterized in that: In S100, the standard comparison table includes the maximum allowable vibration value of each component under the equipment; the sensor includes a temperature and humidity sensor and a vibration sensor, the temperature and humidity sensor is used to collect the temperature and humidity of the environment around the equipment, and the vibration sensor is used to collect the vibration value of each component under the equipment; the environmental record includes the temperature and humidity at different times, and the parameter record includes the vibration value of the component at different times.

3. The equipment fault diagnosis data analysis method based on information screening according to claim 2 is characterized in that: In S200, the specific steps are as follows: S201, obtain the standard comparison table and the parameter records of each component, and analyze the vibration value VIB at the latest time in each parameter record now , and the maximum allowable vibration value VIB of each component max , the vibration value VIB now Greater than VIB max The component corresponding to the parameter record is regarded as an abnormal component; S202: When there is an abnormal component in the device, obtain the temperature TEM at the current time in the environmental record. now and humidity now ; Set the temperature threshold TEM thr and humidity threshold HUM thr , analyze the temperature and humidity in the past time in the environmental records and calculate the TEM now and HUM now The difference between the two values ​​is smaller than TEM. thr and HUM thr The time period is taken as the sampling time period; S203, set the sampling time length e, divide the time length of each sampling time period by e to obtain the number of sampling points, and evenly set the sampling points in the sampling time period according to the number of sampling points; ab Associate with other components one by one in turn to establish associated components; obtain the vibration value of the associated component at the corresponding time of each sampling point in all sampling time periods and calculate the difference, and calculate the standard deviation of the difference at all sampling points as the difference coefficient of the associated component; S204, setting a coefficient threshold U, marking associated components whose difference coefficients are less than U, and establishing an influence relationship between two components in the marked associated components; analyzing whether each abnormal component has an influence relationship with other components, and after all abnormal components are analyzed, continuing to associate components that have an influence relationship with the abnormal components with other components again, analyzing and establishing an influence relationship, and connecting the components with an influence relationship to establish an influence relationship chain.

4. The equipment fault diagnosis data analysis method based on information screening according to claim 3 is characterized in that: In S300, the specific steps are as follows: S301, establishing a training set for each pair of associated components, taking the vibration values ​​of the two components in the associated components at the same sampling point as the independent variable and the dependent variable respectively, packaging the independent variable and the dependent variable into samples, each sampling point corresponding to a sample, and putting these samples into the training set of the corresponding associated components; S302, establish a linear regression model, substitute the independent variables of the samples in the training set as input values ​​into the linear regression model expression, calculate the difference between the output result of each sample and the dependent variable, sum the differences of all samples in the training set as the gap coefficient, and minimize the gap coefficient by adjusting the intercept L and the regression coefficient α in the expression, and obtain the relationship expression corresponding to each training set respectively: P=L+αW In the formula, P is the dependent variable and W is the independent variable; S303, obtain the vibration values ​​of all abnormal components, substitute them into the corresponding relationship expressions respectively, and use the calculation results as the corresponding component CAP of the relationship expression cd Expected vibration value Then put the component CAP cd Substitute the expected vibration value into other components that have an impact on CAP ef In the corresponding relationship expression of ef Expected vibration value And so on, calculate the expected vibration value of each component separately; S304, obtain the vibration values ​​of all components with influencing relationships, substitute them into all corresponding relationship expressions respectively, and use the calculation results as the predicted vibration values ​​of the components corresponding to each relationship expression; analyze the expected vibration value and all predicted vibration values ​​of each component, calculate the average value of the expected vibration value and all predicted vibration values ​​as the theoretical vibration value, and the standard deviation of the expected vibration value and all predicted vibration values ​​as the abnormality index; set the index threshold S, mark the components whose theoretical vibration values ​​are greater than the maximum allowable vibration value and whose abnormality index is less than S, and generate a fault diagnosis report according to the current vibration values ​​of all abnormal components, as well as the current vibration values ​​and theoretical vibration values ​​of all marked components.

5. The equipment fault diagnosis data analysis method based on information screening according to claim 4 is characterized in that: In S400, the fault diagnosis report is stored in the manager's smart terminal. The manager can analyze the fault diagnosis report to determine whether to conduct an on-site inspection or ignore it. The environmental records and parameter records are updated in real time according to the changes in temperature and humidity in the environment and the vibration values ​​of each component.

6. Equipment fault diagnosis data analysis system based on information screening, characterized by: The system includes a data acquisition module, a diagnosis and analysis module, a fault processing module and a data storage module; The data acquisition module is used to collect the standard comparison table of the equipment, collect environmental records and parameter records of each component under the equipment through sensors; The diagnostic analysis module identifies abnormal components through standard comparison tables and parameter records, matches other components with impact relationships for abnormal components based on environmental records and parameter records, and establishes an impact relationship chain; The fault processing module analyzes the relationship between the components in the impact relationship chain and establishes a relationship expression, predicts the operating parameters of each component based on the relationship expression, and thus marks the components and generates a fault diagnosis report; The data storage module stores the fault diagnosis report to the manager's intelligent terminal and updates the environmental record and parameter record.

7. The equipment fault diagnosis data analysis system based on information screening according to claim 6 is characterized in that: The data acquisition module includes a parameter record acquisition unit, an environmental data acquisition unit and a comparison table acquisition unit; The parameter record collection unit is used to collect parameter records of various components under the equipment, and the parameter records include vibration values ​​of the components at different times; The environmental data acquisition unit is used to collect environmental records of the equipment. Environmental records refer to the temperature and humidity of the surrounding environment of the equipment, including the temperature and humidity at different times; The comparison table collection unit is used to collect standard comparison tables, specifically including the maximum allowable vibration values ​​of various components under the equipment.

8. The equipment fault diagnosis data analysis system based on information screening according to claim 7 is characterized in that: The diagnostic analysis module includes an information screening unit and a chain building unit; The information screening unit is used to screen out the sampling time period; First analyze the vibration value VIB at the latest time in each parameter record now , and the maximum allowable vibration value VIB of each component in the standard comparison table max , the vibration value VIB now Greater than VIB max The component corresponding to the parameter record is regarded as an abnormal component; when there is an abnormal component in the device, the temperature TEM at the current time in the environmental record is obtained. now and humidity now ; Then set the temperature threshold TEM thr and humidity threshold HUM thr , analyze the temperature and humidity in the past time in the environmental records and calculate the TEM now and HUM now The difference between the two values ​​is smaller than TEM. thr and HUM thr The time period is taken as the sampling time period; Chain building units are used to establish chains of influence relationships; First, set the sampling duration e, divide the duration of each sampling period by e to get the number of sampling points, and evenly set the sampling points in the sampling period according to the number of sampling points; ab Associate with other components one by one in turn to establish associated components; Secondly, obtain the vibration value of the associated component at the corresponding time of each sampling point in all sampling time periods and calculate the difference, and calculate the standard deviation of the difference at all sampling points as the difference coefficient of the associated component; set the coefficient threshold U, mark the associated components with a difference coefficient less than U, and establish an influence relationship between the two components in the marked associated components; Finally, analyze whether each abnormal component has an impact relationship with other components. After all abnormal components are analyzed, continue to associate the components that have an impact relationship with the abnormal components with other components again, analyze and establish the impact relationship, and connect the components with the impact relationship to establish an impact relationship chain.

9. The equipment fault diagnosis data analysis system based on information screening according to claim 8 is characterized in that: The fault processing module includes a relationship analysis unit and a fault prediction unit; The relational analysis unit is used to establish relational expressions; First, a training set is established for each pair of associated components. The vibration values ​​of the two components in the associated components at the same sampling point are used as independent variables and dependent variables respectively. The independent variables and dependent variables are packaged into samples. Each sampling point corresponds to a sample, and these samples are put into the training set of the corresponding associated components. Then, a linear regression model is established, and the independent variables of the samples in the training set are substituted into the linear regression model expression as input values. The difference between the output result of each sample and the dependent variable is calculated, and the difference of all samples in the training set is summed as the gap coefficient. The gap coefficient is minimized by adjusting the intercept L and the regression coefficient α in the expression, thereby obtaining the relationship expression corresponding to each training set: P = L + αW, where P is the dependent variable and W is the independent variable; The fault prediction unit is used to mark components and generate fault diagnosis reports; First, obtain the vibration values ​​of all abnormal components, substitute them into the corresponding relationship expressions, and use the calculation results as the corresponding component CAP of the relationship expression cd Expected vibration value Then put the component CAP cd Substitute the expected vibration value into other components that have an impact on CAP ef In the corresponding relationship expression of ef Expected vibration value And so on, calculate the expected vibration value of each component separately; Secondly, the vibration values ​​of all the components with influencing relationships are obtained, and they are substituted into all the corresponding relationship expressions respectively, and the calculation results are used as the predicted vibration values ​​of the components corresponding to each relationship expression; Analyze the expected vibration value and all predicted vibration values ​​of each component, calculate the average of the expected vibration value and all predicted vibration values ​​as the theoretical vibration value, and calculate the standard deviation of the expected vibration value and all predicted vibration values ​​as the abnormality index; Finally, the index threshold S is set to mark the components whose theoretical vibration values ​​are greater than the maximum allowable vibration value and whose abnormal index is less than S, and a fault diagnosis report is generated based on the current vibration values ​​of all abnormal components, as well as the current vibration values ​​and theoretical vibration values ​​of all marked components.

10. The equipment fault diagnosis data analysis system based on information screening according to claim 9 is characterized in that: The data storage module stores the fault diagnosis report to the manager's smart terminal. The manager processes the fault diagnosis report by analyzing it and updates the environmental records and parameter records in real time according to the changes in temperature and humidity in the environment and the vibration values ​​of each component.

Images