Fault tree diagnosis and grading response method and system for stacker
By constructing a fault tree model and a hierarchical response strategy, the problem of high root cause localization error rate in stacker crane fault diagnosis was solved, and dynamic fault analysis and cost optimization were realized.
Patent Information
- Application Number
- CN202511093694.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-06
- Publication Date
- 2025-11-21
AI Technical Summary
Existing fault diagnosis of stacker cranes relies on a single sensor or human experience, making it difficult to analyze the propagation path of the fault, resulting in a high root cause location error rate and increasing maintenance time and cost.
The fault tree diagnosis and hierarchical response method is adopted. By acquiring historical fault information of the stacker crane, a fault tree model and case library are constructed. Real-time operation data is collected, feature parameters are extracted, and fault location and risk assessment are carried out by combining Boolean logic and expert experience. Hierarchical response strategies are output, and the diagnostic logic is optimized by machine learning.
It enables dynamic analysis of stacker crane faults, reduces fault location error rate, and optimizes maintenance time and cost.
Smart Images
Figure CN120996779A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of stacker fault detection, in particular to a stacker fault tree diagnosis and hierarchical response method and system. BACKGROUND
[0002] With the rapid development of the warehousing logistics industry towards automation and intelligence, as the core equipment of automated stereoscopic warehouse, the stacker, as the most important handling, lifting and stacking equipment in the automated stereoscopic warehouse, has an important influence on the working efficiency of the stereoscopic warehouse. At present, the fault diagnosis of the stacker relies on a single sensor or manual experience.
[0003] However, the existing fault diagnosis of the stacker relies on a single sensor or manual experience, which is difficult to analyze the propagation path of the fault, and the same processing method is adopted for the high and low fault risks, resulting in high error rate of root cause positioning, increasing maintenance time and cost. SUMMARY
[0004] The present application aims to provide a stacker fault tree diagnosis and hierarchical response method and system, which aims to solve the technical problems that the existing fault diagnosis of the stacker relies on a single sensor or manual experience, which is difficult to analyze the propagation path of the fault, and the same processing method is adopted for the high and low fault risks, resulting in high error rate of root cause positioning, increasing maintenance time and cost.
[0005] To achieve the above-mentioned purpose, a stacker fault tree diagnosis and hierarchical response method is adopted, which comprises the following steps:
[0006] Obtain the historical fault information of the stacker, analyze the fault information, and construct the stacker fault tree model and the fault case library;
[0007] Collect real-time operation data of the stacker, extract fault characteristic parameters, and store the parameters in the database;
[0008] Diagnose the fault of the stacker according to the real-time monitoring data and the fault tree model, and locate and determine the fault cause;
[0009] Establish a fault risk level, output a hierarchical response strategy according to the fault risk level, and provide a diagnosis decision;
[0010] Collect the fault diagnosis and processing results each time, and update the fault case library data.
[0011] In the step of obtaining the historical fault information of the stacker, analyzing the fault information, and constructing the stacker fault tree model and the fault case library:
[0012] Collect historical failure data from the stacker maintenance records, sensor logs and operator feedback information, and clean the failure data to remove duplicates, errors and missing values in the failure data;
[0013] Classify the cleaned data by fault type, and extract the fault occurrence time, frequency and associated component features;
[0014] Describe the causal relationship between failures through Boolean logic, combine historical data and expert experience, and assign a probability to each event to form a probabilistic fault tree;
[0015] Store historical failure data, diagnosis results and treatment measures in the database to form a reusable failure case library.
[0016] In the step of classifying the cleaned data by fault type and extracting the fault occurrence time, frequency and associated component features:
[0017] The fault type includes mechanical failure, electrical failure and control failure.
[0018] In the step of collecting real-time operation data of the stacker, extracting fault feature parameters, and storing the parameters in the database:
[0019] Install vibration sensors, temperature sensors, current sensors and displacement sensors at various parts of the stacker to collect real-time operation data;
[0020] Preprocess the collected operation data;
[0021] Extract fault feature parameters using time domain analysis, frequency domain analysis and time-frequency analysis;
[0022] Store the extracted feature parameters in the real-time database and back up to the historical database regularly.
[0023] In the step of installing vibration sensors, temperature sensors, current sensors and displacement sensors at various parts of the stacker to collect real-time operation data:
[0024] The parts include motors, forks, tracks and control cabinets.
[0025] In the step of diagnosing the stacker failure according to the real-time monitoring data and the fault tree model, and locating and determining the failure cause:
[0026] In the fault tree model, top-down traversal is performed, and the real-time monitored fault feature parameters are matched with the feature threshold of the bottom event in the model to screen the possible triggered bottom event;
[0027] Combine the fault tree model to calculate the occurrence probability of the current fault path and evaluate the fault severity;
[0028] Consider the possibility of multiple failures occurring simultaneously, and analyze the impact of compound failures on the system, excluding interference factors;
[0029] According to the probability calculation result, the specific components and subsystems where the fault occurs are located, and the root cause is inferred in combination with the fault case library.
[0030] Among them, in the step of establishing the fault risk level, outputting the grading response strategy according to the fault risk level, and providing diagnostic decision:
[0031] Establish the fault risk level, define different response measures according to the fault risk level, and the risk level includes high risk, medium risk and low risk;
[0032] In combination with the fault tree reasoning result, the specific maintenance steps and the required tool list are provided.
[0033] Among them, in the step of establishing the fault risk level, defining different response measures according to the fault risk level, and the risk level includes high risk, medium risk and low risk:
[0034] High risk needs to be stopped immediately and alarmed, and the maintenance personnel are notified, medium risk needs to limit the running speed, start the standby system, and low risk needs to record the fault log and plan maintenance.
[0035] Among them, in the step of collecting the fault diagnosis and processing result of each time, updating the fault case library data:
[0036] Store each fault diagnosis and processing result in the database to form a reusable fault case library;
[0037] Periodically update the fault tree model with new data, and optimize the diagnostic logic using machine learning algorithms;
[0038] According to user feedback, improve the system interface.
[0039] The present application also provides a fault tree diagnosis and grading response system for a stacker, comprising a data management module, a fault tree modeling module, a data acquisition module, a fault diagnosis positioning module, a grading response decision module and an optimization module; wherein:
[0040] The data management module is used to obtain the historical fault information of the stacker, and analyze the fault information, the fault case library;
[0041] The fault tree modeling module is used to construct a fault tree model of the stacker;
[0042] The data acquisition module is used to collect real-time operation data of the stacker, extract fault characteristic parameters, and store the parameters in the database;
[0043] The fault diagnosis positioning module is used for diagnosing the fault of the stacker according to the real-time monitoring data and the fault tree model, and positioning and determining the fault cause.
[0044] The hierarchical response decision module is used for establishing a fault risk level, outputting a hierarchical response strategy according to the fault risk level, and providing a diagnosis decision.
[0045] The optimization module is used for collecting the fault diagnosis and processing result each time, and updating the fault case library data.
[0046] The stacker fault tree diagnosis and hierarchical response method and system of the present application adopts the data management module, the fault tree modeling module, the data acquisition module, the fault diagnosis positioning module, the hierarchical response decision module and the optimization module to perform the following steps: obtaining stacker historical fault information, analyzing the fault information, constructing a stacker fault tree model and a fault case library; collecting real-time operation data of the stacker, extracting fault characteristic parameters, and storing the parameters in a database; diagnosing the fault of the stacker according to the real-time monitoring data and the fault tree model, and positioning and determining the fault cause; establishing a fault risk level, outputting a hierarchical response strategy according to the fault risk level, and providing a diagnosis decision; collecting the fault diagnosis and processing result each time, and updating the fault case library data. In this way, dynamic analysis of the stacker is realized, the fault positioning error rate is reduced, the fault handling mode can be dynamically adjusted according to the real-time operation state, and the maintenance time and cost are greatly reduced. BRIEF DESCRIPTION OF DRAWINGS
[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.
[0048] Figure 1 is the step flow chart of the stacker fault tree diagnosis and hierarchical response method of the present application.
[0049] Figure 2 is the step flow chart of S100 of the present application.
[0050] Figure 3 is the step flow chart of S200 of the present application.
[0051] Figure 4 is the step flow chart of S300 of the present application.
[0052] Figure 5 is the step flow chart of S400 of the present application.
[0053] Figure 6 is a step flow chart of S500 of the present application.
[0054] Figure 7 is a structure principle diagram of the fault tree diagnosis and hierarchical response system of the stacker of the present application.
[0055] 601 - data management module, 602 - fault tree modeling module, 603 - data acquisition module, 604 - fault diagnosis positioning module, 605 - hierarchical response decision module, 606 - optimization module. DETAILED DESCRIPTION
[0056] The exemplary embodiments will be described in detail herein with reference to the attached drawings. In the following description, the same numbers are used to designate the same elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not meant to represent all embodiments consistent with the present application.
[0057] The terminology used in the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application. As used in the description of the application and the appended claims, the singular forms “a,” “an,” and “the” are intended to include plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the term “and / or” as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
[0058] It will be understood that, although the terms first, second, third, etc. can be used herein to describe various information, these terms are not intended to denote a temporal or chronological order. These terms are used only to distinguish one type of information from another. For example, a first information can be termed a second information, and similarly, a second information can be termed a first information, without departing from the scope of the present application. Depending on the context, the word “if’ as used herein can be interpreted as meaning “when” or “in response to determining” or “in response to a determination”.
[0059] Referring to Figures 1-5 The present application provides a fault tree diagnosis and hierarchical response method of a stacker, comprising the following steps:
[0060] S100: Acquire historical fault information of the stacker, analyze the fault information, and construct a fault tree model and a fault case library of the stacker.
[0061] In the present embodiment, historical fault information of the stacker is acquired, the fault information is analyzed, a fault tree model and a fault case library of the stacker are constructed, and the specific process is as follows:
[0062] S101: Collect historical fault data from the stacker maintenance records, sensor logs and operator feedback information, and clean the fault data to remove duplicates, errors and missing values in the fault data;
[0063] S102: Classify the cleaned data by fault type, and extract fault occurrence time, frequency and associated component features;
[0064] S103: Describe the causal relationship between faults through Boolean logic, combine historical data and expert experience, and assign occurrence probability to each event to form a probabilistic fault tree;
[0065] S104: Store historical fault data, diagnosis results and treatment measures in the database to form a reusable fault case library.
[0066] In the above process, historical fault data is collected from stacker maintenance records, sensor logs and operator feedback information, and the fault data is cleaned to remove duplicates, errors and missing values to ensure data integrity. Then, the cleaned data is classified by fault type, and fault occurrence time, frequency and associated component features are extracted, where the fault type includes mechanical failure, electrical failure and control failure. Then, the causal relationship between faults is described through Boolean logic (AND / OR gate), combined with historical data and expert experience, and occurrence probability is assigned to each event to form a probabilistic fault tree. By storing historical fault data, diagnosis results and treatment measures in the database, a reusable fault case library is formed to support subsequent model training and verification.
[0067] S200: Collect real-time operation data of the stacker, extract fault feature parameters, and store the parameters in the database.
[0068] In this embodiment, real-time operation data of the stacker is collected, fault feature parameters are extracted, and the parameters are stored in the database. The specific process is as follows:
[0069] S201: Install vibration sensors, temperature sensors, current sensors and displacement sensors at various parts of the stacker to collect real-time operation data;
[0070] S202: Preprocess the collected operation data;
[0071] S203: Extract fault feature parameters using time domain analysis, frequency domain analysis and time-frequency analysis;
[0072] S204: Store the extracted feature parameters in the real-time database and back up to the historical database periodically.
[0073] In the above process, vibration sensors, temperature sensors, current sensors and displacement sensors are installed at various parts of the stacker, including the motor, forks, rails and control cabinet, to collect real-time operation data, which are then preprocessed, and then time domain analysis (mean, variance, peak), frequency domain analysis (FFT transform to extract characteristic frequency) and time-frequency analysis (wavelet transform) are used to extract fault characteristic parameters (vibration spectrum, temperature abnormal value), which are then stored in a real-time database and backed up to a historical database periodically to support long-term trend analysis.
[0074] S300: Stack failure diagnosis according to real-time monitoring data and fault tree model, and fault location and fault cause determination.
[0075] In this embodiment, the stacker failure is diagnosed according to real-time monitoring data and fault tree model, and fault location and fault cause determination are performed, and the specific process is as follows:
[0076] S301: In the fault tree model, top-down traversal is performed, the real-time monitored fault characteristic parameters are matched with the characteristic threshold of the bottom event in the model, and the possible triggered bottom event is screened;
[0077] S302: Combined with the fault tree model, the occurrence probability of the current fault path is calculated, and the fault severity is evaluated;
[0078] S303: Considering the possibility of multiple faults occurring simultaneously, and analyzing the influence of composite faults on the system, the interference factors are excluded;
[0079] S304: According to the probability calculation result, the specific components and subsystems where the fault occurs are located, and the root cause is inferred combined with the fault case library.
[0080] In the above process, in the fault tree model, top-down traversal is performed, the real-time monitored fault characteristic parameters are matched with the characteristic threshold of the bottom event in the model, and the possible triggered bottom event is screened, and combined with the fault tree model, the occurrence probability of the current fault path is calculated, and the fault severity is evaluated, then considering the possibility of multiple faults occurring simultaneously, and analyzing the influence of composite faults on the system, the interference factors are excluded, and then according to the probability calculation result, the specific components and subsystems where the fault occurs are located, and the root cause (design defect, wear and tear, operation error) is inferred combined with the fault case library.
[0081] S400: Establishing a fault risk level, outputting a hierarchical response strategy according to the fault risk level, and providing a diagnostic decision.
[0082] In this embodiment, a fault risk level is established, a hierarchical response strategy is output according to the fault risk level, and a diagnostic decision is provided, and the specific process is as follows:
[0083] S401: Establishing a fault risk level, and defining different response measures according to the fault risk level, the risk level including high risk, medium risk and low risk;
[0084] S402: Providing specific maintenance steps and required tool lists in combination with the fault tree reasoning result.
[0085] In the above process, a fault risk level is established, and different response measures are defined according to the fault risk level, the risk level including high risk, medium risk and low risk, wherein high risk needs to be immediately stopped and alarmed to notify maintenance personnel, medium risk needs to limit the running speed and start the standby system, and low risk needs to record the fault log and plan maintenance, and specific maintenance steps and required tool lists are provided in combination with the fault tree reasoning result.
[0086] S500: Collecting each fault diagnosis and processing result, and updating the fault case library data.
[0087] In the embodiment, each fault diagnosis and processing result is collected, and the fault case library data is updated, and the specific process is as follows:
[0088] S501: Storing each fault diagnosis and processing result into a database to form a reusable fault case library;
[0089] S502: Regularly updating the fault tree model with new data, and optimizing the diagnosis logic by using a machine learning algorithm;
[0090] S503: Improving the system interface according to user feedback.
[0091] In the above process, each fault diagnosis and processing result is stored into a database, including (fault cause, maintenance measure, replacement component and processing time), to form a reusable fault case library, the fault tree model is regularly updated with new data, the diagnosis logic is optimized by using a machine learning algorithm, and the system interface is improved according to user feedback.
[0092] Please refer to Figure 6 The application also provides a fault tree diagnosis and hierarchical response system of a stacker, including a data management module 601, a fault tree modeling module 602, a data acquisition module 603, a fault diagnosis positioning module 604, a hierarchical response decision module 605 and an optimization module 606; wherein:
[0093] The data management module 601 is used for acquiring stacker historical fault information, and analyzing the fault information, a fault case library;
[0094] The fault tree modeling module 602 is used for constructing a stacker fault tree model;
[0095] The data collection module 603 is configured to collect real-time operation data of the stacker, extract fault characteristic parameters, and store the parameters in a database.
[0096] The fault diagnosis and positioning module 604 is configured to diagnose faults of the stacker according to real-time monitoring data and a fault tree model, and perform fault positioning and determine fault causes.
[0097] The hierarchical response decision module 605 is configured to establish a fault risk level, output a hierarchical response strategy according to the fault risk level, and provide a diagnosis decision.
[0098] The optimization module 606 is configured to collect fault diagnosis and processing results each time, and update fault case library data.
[0099] In the embodiment, the data management module 601 acquires historical fault information of the stacker, and analyzes the fault information and a fault case library. The fault tree modeling module 602 constructs a fault tree model of the stacker. The data collection module 603 collects real-time operation data of the stacker, extracts fault characteristic parameters, and stores the parameters in a database. The fault diagnosis and positioning module 604 diagnoses faults of the stacker according to real-time monitoring data and the fault tree model, and performs fault positioning and determines fault causes. The hierarchical response decision module 605 establishes a fault risk level, outputs a hierarchical response strategy according to the fault risk level, and provides a diagnosis decision. The optimization module 606 collects fault diagnosis and processing results each time, and updates fault case library data.
[0100] Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. It is intended that the application embrace any and all variations of the present application that fall within the scope of the general inventive concept as defined in the claims and that the application include all modifications and alterations from such descriptions as fall in the scope of the claims.
[0101] It is to be understood that the application is not limited to the precise construction described and as shown in the attached drawings, and that various modifications and changes can be effected thereon without departing from the scope of the application.
Claims
1. A fault tree diagnosis and hierarchical response method for a stacker crane, characterized in that, Includes the following steps: Obtain historical fault information of the stacker crane, analyze the fault information, and build a fault tree model and fault case library for the stacker crane; Real-time data collection of stacker crane operation, extraction of fault characteristic parameters, and storage of parameters in database; Based on real-time monitoring data and fault tree models, the stacker crane is diagnosed for faults, and the fault location and cause are determined. Establish fault risk levels, output graded response strategies based on fault risk levels, and provide diagnostic decisions; Collect the results of each fault diagnosis and handling, and update the fault case database.
2. The fault tree diagnosis and hierarchical response method for a stacker crane as described in claim 1, characterized in that, In the steps of acquiring historical fault information of the stacker crane, analyzing the fault information, and constructing a fault tree model and fault case library for the stacker crane: Historical fault data is collected from stacker crane maintenance records, sensor logs, and operator feedback information. The fault data is then cleaned to remove duplicate, erroneous, and missing values. The cleaned data is classified according to fault type, and the fault occurrence time, frequency, and characteristics of associated components are extracted. By describing the causal relationships between faults using Boolean logic and combining historical data and expert experience, a probability of occurrence is assigned to each event, forming a probabilistic fault tree. Historical fault data, diagnostic results, and handling measures are stored in a database to form a reusable fault case library.
3. The fault tree diagnosis and hierarchical response method for stacker cranes as described in claim 2, characterized in that, In the steps of classifying the cleaned data according to fault type and extracting fault occurrence time, frequency, and characteristics of associated components: Fault types include mechanical faults, electrical faults, and control faults.
4. The fault tree diagnosis and hierarchical response method for a stacker crane as described in claim 1, characterized in that, In the steps of collecting real-time operational data from the stacker crane, extracting fault characteristic parameters, and storing the parameters in the database: Vibration sensors, temperature sensors, current sensors, and displacement sensors are installed on various parts of the stacker crane to collect operational data in real time. Preprocess the collected operational data; Fault characteristic parameters are extracted using time-domain analysis, frequency-domain analysis, and time-frequency analysis. The extracted feature parameters are stored in a real-time database and backed up to a historical database periodically.
5. The fault tree diagnosis and hierarchical response method for a stacker crane as described in claim 4, characterized in that, The steps involved in installing vibration sensors, temperature sensors, current sensors, and displacement sensors at various parts of the stacker crane to collect operational data in real time are as follows: The components include the motor, forks, rails, and control cabinet.
6. The fault tree diagnosis and hierarchical response method for a stacker crane as described in claim 1, characterized in that, In the steps of diagnosing stacker crane faults based on real-time monitoring data and fault tree models, and locating and determining the cause of the fault: In the fault tree model, the fault feature parameters monitored in real time are traversed from top to bottom, and the feature thresholds of the bottom events in the model are matched to filter the bottom events that may be triggered. By combining the fault tree model, the probability of occurrence of the current fault path is calculated, and the severity of the fault is assessed. Consider the possibility of multiple faults occurring simultaneously, analyze the impact of compound faults on the system, and eliminate interference factors; Based on the probability calculation results, the specific component and subsystem where the failure occurred are located, and the root cause is inferred by combining the failure case library.
7. The fault tree diagnosis and hierarchical response method for a stacker crane as described in claim 1, characterized in that, In the steps of establishing fault risk levels, outputting graded response strategies based on fault risk levels, and providing diagnostic decisions: Establish a fault risk level and define different response measures based on the fault risk level. The risk levels include high risk, medium risk and low risk. Based on the fault tree reasoning results, provide specific repair steps and a list of required tools.
8. The fault tree diagnosis and hierarchical response method for a stacker crane as described in claim 7, characterized in that, In the steps of establishing a failure risk level and defining different response measures based on the failure risk level, with risk levels including high risk, medium risk, and low risk: High-risk situations require immediate shutdown and alarm activation, and notification of maintenance personnel; medium-risk situations require limiting operating speed and activating backup systems; low-risk situations require logging faults and planning maintenance.
9. The fault tree diagnosis and hierarchical response method for a stacker crane as described in claim 1, characterized in that, In the steps of collecting the results of each fault diagnosis and handling and updating the fault case database: Each fault diagnosis and handling result is stored in the database to form a reusable fault case library. The fault tree model is updated regularly using new data, and the diagnostic logic is optimized using machine learning algorithms. Improve the system interface based on user feedback.
10. A fault tree diagnosis and hierarchical response system for a stacker crane, applied to the fault tree diagnosis and hierarchical response method for a stacker crane as described in claim 1, characterized in that, It includes a data management module, a fault tree modeling module, a data acquisition module, a fault diagnosis and location module, a graded response decision-making module, and an optimization module; among which: The data management module is used to acquire historical fault information of the stacker crane and analyze the fault information and fault case library; The fault tree modeling module is used to construct a fault tree model for the stacker crane. The data acquisition module is used to collect real-time operating data of the stacker crane, extract fault characteristic parameters, and store the parameters in the database. The fault diagnosis and location module is used to diagnose stacker crane faults based on real-time monitoring data and fault tree models, and to locate and determine the cause of the fault. The graded response decision module is used to establish fault risk levels, output graded response strategies based on fault risk levels, and provide diagnostic decisions. The optimization module is used to collect the results of each fault diagnosis and handling, and update the fault case database.