Online fault diagnosis and state estimation method for crane

Abstract

The invention relates to the technical field of special equipment, in particular to a crane online fault diagnosis and state estimation method which comprises the following steps: S1, data acquisition and storage: acquiring working process parameters of a crane through a sensor; s2, data processing: processing the stored working process parameters; s3, real-time fault state estimation and fault diagnosis of the crane: predicting the running state of the crane in real time, and judging whether a fault exists or not and the type of the fault; s4, optimizing parameters of the fault state estimation and fault diagnosis model: optimizing the parameters of the fault state estimation and fault diagnosis model; and S5, man-machine interaction: presenting a fault diagnosis and state estimation result through a man-machine interaction system, reversely writing manual inspection information, providing fault information and suggestions, and stopping the crane. According to the invention, the operation state of the crane can be monitored in real time, potential faults can be predicted, fault types can be diagnosed in time, preventive measures can be taken in advance, the equipment fault rate can be reduced, accidents can be avoided, and the safety and reliability of equipment operation can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of special equipment, and in particular to a method for online fault diagnosis and state prediction of a crane. Background Art

[0002] With the widespread application of intelligent mechanical equipment, cranes, as special equipment, are also one of the important industrial equipment. Their operating stability and safety are crucial to production efficiency and personal safety. However, in daily use, cranes are prone to various failures due to long-term high-load operation, complex working environment and component wear. Traditional fault diagnosis and status prediction methods usually rely on regular inspections and manual analysis, which is not only inefficient, but also difficult to accurately capture early signs of failures. They are often handled only when a failure occurs, resulting in long downtime and high maintenance costs.

[0003] Most existing fault diagnosis systems lack real-time performance and accuracy, especially in the monitoring of high-load equipment such as cranes. Existing technologies usually rely on simple sensor data and empirical judgment, making it difficult to achieve a comprehensive and dynamic assessment of the equipment status. In addition, many traditional systems fail to effectively integrate machine learning and intelligent optimization technologies, and therefore are unable to improve the accuracy of fault prediction and diagnosis through continuous learning and self-optimization. In addition, most of the human-computer interaction systems in existing technologies are single-function and cannot provide effective real-time fault feedback and decision-making support for operators and maintenance personnel, and cannot maximize the work efficiency and safety of cranes.

[0004] In order to solve the above problems, the present invention provides a method for online fault diagnosis and state prediction of a crane, aiming to improve the operational safety, work efficiency and reliability of the crane, and provide an intelligent and automated solution for equipment maintenance and management. Summary of the invention

[0005] The invention provides a crane online fault diagnosis and state prediction method.

[0006] The crane online fault diagnosis and state prediction method includes the following steps:

[0007] S1, data collection and storage: collect the working process parameters of the crane through sensors, including displacement, load, temperature, voltage, current, and speed, and transmit the collected real-time working process parameters to the engineer station terminal and store them in real time in EXCEL or ACCESS database through data interaction technology;

[0008] S2, data processing: using improved recursive smoothing filtering method to process the stored working process parameters;

[0009] S3, real-time crane fault status prediction and fault diagnosis: Based on the processed working process parameters, the crane's operating status is predicted in real time to determine whether there is a fault and its type;

[0010] S4, fault state prediction and fault diagnosis model parameter optimization: an improved particle swarm algorithm (PSO) is used to optimize the parameters of the fault state prediction and fault diagnosis model;

[0011] S5, human-computer interaction: The human-computer interaction system presents the fault diagnosis and status prediction results, reversely writes the manual inspection information, provides fault information and suggestions, and stops the crane.

[0012] Optionally, the improved recursive smoothing filtering method is expressed as:

[0013]

[0014] Where k is an imaginary number, X t is the signal value output by data processing, and α is the rate of change.

[0015] Optionally, the real-time crane fault state prediction and fault diagnosis in S3 includes:

[0016] S31, fault state prediction: by inputting the processed working process parameters, using the fault state prediction and fault diagnosis model, the future operation state of the crane is predicted;

[0017] S32, fault diagnosis: performing fault diagnosis by performing an inverse operation on the fault state estimation.

[0018] Optionally, the fault state prediction in S31 includes:

[0019] S311, predicting fault status: inputting the processed working process parameters, predicting through the fault status prediction and fault diagnosis model, and calculating the input value F of each transition, expressed as:

[0020] F (k) =I T *(α⊙W⊙M (k-1) );

[0021] Where k represents the current iteration number, I is the input matrix, and M is the place mark distribution vector;

[0022]

[0023] Among them, λ is the threshold set of transition rules;

[0024] S312, calculation of new place mark value: Calculate a new place mark distribution vector M, expressed as:

[0025]

[0026] Among them, O is the output matrix, U is the credibility vector of the transition rule;

[0027] S313, reasoning calculation end judgment: when M (k-1) =M (k) When , the inference calculation ends. If the distribution vector of the library event flag has a value, it means that a failure event has occurred in the library.

[0028] Optionally, the fault diagnosis in S32 includes:

[0029] S321, fault diagnosis process: Fault diagnosis is the inverse operation of fault prediction, which can be expressed as:

[0030]

[0031] S322, deriving fault events using the fault data that has occurred: deriving the model structure of the fault event occurrence through the fault association matrix A' that has occurred, expressed as:

[0032]

[0033] Optionally, the improved particle swarm algorithm (PSO) is expressed as:

[0034]

[0035] x ij (t+1)=x ij (t)+v ij (t+1);

[0036] Where i and j represent the number of i-th (i∈n) particles and j-th (j∈D) dimension, t is the number of iterations, and x ij represents each particle, v ij Indicates the update speed of each particle, Indicates iteration to the current individual optimal solution, ω (t) is the inertia factor, Iterates to the current global optimal solution. c1 and c2 are acceleration factors. r1 and r2 are random numbers in the interval [0,1].

[0037] Optionally, the human-computer interaction in S5 includes:

[0038] S51, Human-computer interaction system design: Use object-oriented language development technology to design a human-computer interaction system for real-time fault state prediction and fault diagnosis of cranes;

[0039] S52, system function realization: realizing the real-time fault state prediction of the crane and the calling of the fault diagnosis calculation program through the human-computer interaction system;

[0040] S53, data feedback and processing: the actual inspection result values ​​of the crane operators, commanders and maintenance personnel are reversely written into the input data set of the crane real-time fault state prediction and fault diagnosis calculation program;

[0041] S54, result display: the real-time fault state prediction of the crane and the fault diagnosis reasoning calculation results are displayed to the crane operator and the commander through a graphical interface;

[0042] S55, control instruction: according to the real-time fault state prediction and fault diagnosis reasoning calculation results, a stop instruction is issued to the crane control system.

[0043] Beneficial effects of the present invention:

[0044] The present invention effectively improves the prediction and diagnosis accuracy of fault conditions through precise real-time data collection and processing combined with an improved recursive smoothing filtering method. Through the established fault diagnosis and prediction model, the system can monitor the operating status of the crane in real time, predict potential faults and diagnose the fault type in a timely manner, so as to take preventive measures in advance, reduce equipment failure rates, avoid accidents, and improve the safety and reliability of equipment operation.

[0045] The present invention uses an improved particle swarm optimization algorithm to optimize the parameters of the fault diagnosis and prediction model, thereby further improving the calculation efficiency and diagnostic accuracy of the model. Through the human-computer interaction system, crane operators, commanders and maintenance personnel can obtain fault diagnosis and status prediction results in real time, provide timely feedback and adjust operations, thereby optimizing equipment management and maintenance, reducing downtime caused by faults, and improving the operating efficiency and service life of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0047] Figure 1 A schematic diagram of a fault diagnosis and state prediction method flow chart of an embodiment of the present invention;

[0048] Figure 2 A schematic diagram of the data collection and storage process according to an embodiment of the present invention;

[0049] Figure 3 A schematic diagram of a fault state prediction and fault diagnosis system model according to an embodiment of the present invention;

[0050] Figure 4 A schematic diagram of a fault state prediction calculation process according to an embodiment of the present invention;

[0051] Figure 5 A schematic diagram of a calculation flow of fault diagnosis according to an embodiment of the present invention;

[0052] Figure 6 A schematic diagram of the calculation flow of the improved particle swarm optimization algorithm according to an embodiment of the present invention;

[0053] Figure 7 A schematic diagram of a human-computer interaction system according to an embodiment of the present invention;

[0054] Figure 8 Schematic diagram of the hardware structure of the real-time fault status prediction and diagnosis system for a crane according to an embodiment of the present invention. DETAILED DESCRIPTION

[0055] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0056] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0057] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0058] like Figure 1-Figure 8 As shown, the crane online fault diagnosis and state prediction method includes the following steps:

[0059] 1. Data collection and storage:

[0060] By analyzing the process parameters generated by the entire process and cycle of crane operation, and selecting the corresponding sensor transmission device based on the data type, the real-time process parameter data is converted into electrical signals and transmitted to the input and output (I / O) acquisition module. The I / O data acquisition module converts the electrical signals into digital signals and transmits the real-time process parameter data to the programmable controller (PLC) through the data communication module for the data acquisition system program to call. The PLC transmits the real-time process parameter data of the crane to the engineer station terminal through the data bus technology and stores the data in real time in databases such as EXCEL or ACCESS through data interaction technology. The flow chart is as follows Figure 2 shown.

[0061] 2. Data processing:

[0062] Based on the physical characteristics of the object data, the improved recursive smoothing filter method is selected to process the collected real-time data of the crane process parameters to ensure the reliability and stability of the data and avoid data anomalies causing errors in subsequent fault state prediction and fault diagnosis system decision-making. In view of the shortcomings of the conventional recursive smoothing filter method, the change rate α is introduced as the evaluation factor of the current signal, and the tolerance range of α is given by expert experience and experimental data based on the objective laws of the measured physical quantity. If α is within the tolerance range, the current sampling value X is retained. n+1 ; If α exceeds the tolerance range, then according to the previous sampling value X n The rate of change α' is calculated to obtain the calculated sampling value X' n+1 , the calculation expression is as follows:

[0063]

[0064] Data processing output signal value X t The calculation formula is:

[0065] k is an imaginary number, which refers to the continuous filtering calculation process.

[0066] 3. Real-time crane fault status prediction and fault diagnosis:

[0067] The fuzzy Petri net algorithm is used to establish a real-time fault state prediction and fault diagnosis system for cranes. Firstly, the fault state prediction and fault diagnosis system model is established according to the physical link mechanism and fault mode of the target object, such as Figure 3 In the model, “◎” indicates the initial input place; “○” indicates the intermediate place; Represents the top-level place, which is the final output place of the system. The model parameters are FPN = (P, T, I, O, α, f, λ, ω, U, M), where P is a finite non-empty place set, T is a finite non-empty transition set, I is an input matrix, O is an output matrix, α is a fault event confidence vector, f is a place fuzzy fault probability set, λ is a transition rule threshold set, ω is a place fault event weight vector, U is a transition rule credibility vector, and M is a place mark distribution vector. α, f, λ, ω, and U are all set by fuzzy rules, hoisting machinery maintenance instructions, inspection data, and other expert experience and experimental data.

[0068] Based on process-oriented programming language, the fuzzy Petri net graphical structure model is transformed into a mathematical calculation formula.

[0069] 3.1. Fault status prediction:

[0070] The input value F of each transition is calculated as shown in the following formula, where k represents the current number of iterations, expressed as:

[0071] F (k) =I T *(α⊙W⊙M (k-1) );

[0072] From the above structure, we can see that F is an n-dimensional column vector, and the transition excitation judgment is as follows:

[0073]

[0074] The new place mark value M is calculated as follows:

[0075]

[0076] When M (k-1) =M (k) When , the inference calculation ends. If the place event flag vector has a value, it means that the place fault event occurs.

[0077] The fault status prediction calculation process is as follows: Figure 4 shown.

[0078] 3.2 Fault diagnosis:

[0079] Fault diagnosis is the inverse operation of fault prediction. The fault diagnosis reasoning matrix is:

[0080]

[0081] The fault association matrix A' is used to describe the fuzzy Petri net topology that causes a certain fault, which can be expressed as:

[0082]

[0083] The calculation process of fault diagnosis is as follows: Figure 5 shown.

[0084] 4. Fault state prediction and fault diagnosis model parameter optimization:

[0085] In order to ensure the accuracy of the real-time fault state prediction and fault diagnosis system of the crane, the actual inspection results of the crane operators, commanders and maintenance personnel are used as evaluation factors of the calculation results of the fault state prediction and fault diagnosis system. When the evaluation results exceed the allowable range, the improved particle swarm algorithm (PSO) is used to optimize the model structure parameters of the fault state prediction and fault diagnosis system to ensure the prediction and diagnosis accuracy of the system.

[0086] In order to improve the optimization efficiency of the traditional particle swarm algorithm, the inertia factor is introduced to solve the problem that the traditional particle swarm algorithm is prone to fall into the local optimality in the later stage, and the chord function is introduced to improve the acceleration factor to solve the problem of inconsistent rates before and after the traditional particle swarm algorithm operation. The calculation formula of the improved particle swarm algorithm (PSO) is as follows:

[0087]

[0088] x ij (t+1)=x ij (t)+v ij (t+1);

[0089] Where i and j represent the number of the i-th (i∈n) particle and the j-th (j∈D) dimension respectively; t is the number of iterations; x ij represents each particle; v ij Indicates the update speed of each particle; Iterates to the current individual optimal solution; ω(t) is the inertia factor. Iterates to the current global optimal solution; c1 and c2 are acceleration factors, constants; r1 and r2 represent random numbers in the interval [0,1].

[0090] The calculation process of the improved particle swarm optimization algorithm is as follows: Figure 6 shown.

[0091] 5. Human-computer interaction:

[0092] The object-oriented language development technology is used to design a human-computer interaction system for real-time crane fault state prediction and fault diagnosis. The system is used to call the crane real-time fault state prediction and fault diagnosis calculation program. The actual inspection result values ​​of the crane operator, commander and maintenance personnel are reversely written into the input data set of the crane real-time fault state prediction and fault diagnosis calculation program. The real-time fault state prediction and fault diagnosis reasoning calculation results of the crane are graphically displayed to the crane operator and commander; and the crane is controlled to stop in time to avoid accidents according to the real-time fault state prediction and fault diagnosis reasoning calculation results of the crane. Figure 7 shown.

[0093] 6. Hardware structure of crane real-time fault status prediction and diagnosis system:

[0094] The hardware structure of the crane real-time fault status prediction and diagnosis system is as follows: Figure 8 shown.

[0095] Engineer station terminal: used to develop data collection and storage programs for real-time operation process parameters of cranes, to develop real-time fault state prediction and diagnosis system programs for cranes, to develop real-time fault state prediction and fault diagnosis model parameter optimization system programs for cranes, to develop a human-computer interaction system and implement the calling and operation of the data collection and storage system, the calling and operation of the real-time fault state prediction and diagnosis system for cranes, the calling and operation of the real-time fault state prediction and fault diagnosis model parameter optimization system for cranes, the reverse writing of actual inspection result values ​​of crane operators / commanders and maintenance personnel into the input data set of the crane real-time fault state prediction and fault diagnosis calculation program, the graphical display of the real-time fault state prediction and fault diagnosis reasoning operation results of the crane to the crane operators and commanders, and the issuance of crane control instructions to the PLC based on the real-time fault state prediction and fault diagnosis reasoning operation results of the crane.

[0096] Programmable Logic Controller (PLC): Runs the data collection program for the real-time operation process parameters of the crane, exchanges data with the engineer station terminal through the communication bus, and controls the crane to stop in time based on the real-time fault status prediction of the crane and the fault diagnosis reasoning calculation results.

[0097] I / O data communication module: converts the electrical signal detected by the sensor into a digital signal and transmits the data to the PLC in real time through the communication bus.

[0098] Sensor group: A sensor transmission device configured according to the physical properties of the object being measured. It converts the state value of the object being measured into an electrical signal and uploads it to the I / O data communication module.

[0099] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0100] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A crane online fault diagnosis and state prediction method, characterized in that: The following steps are involved: S1, data collection and storage: collect the working process parameters of the crane through sensors, including displacement, load, temperature, voltage, current, and speed, and transmit the collected real-time working process parameters to the engineer station terminal and store them in real time in EXCEL or ACCESS database through data interaction technology; S2, data processing: using improved recursive smoothing filtering method to process the stored working process parameters; S3, real-time crane fault status prediction and fault diagnosis: Based on the processed working process parameters, the crane's operating status is predicted in real time to determine whether there is a fault and its type; S4, fault state prediction and fault diagnosis model parameter optimization: the improved particle swarm algorithm is used to optimize the parameters of the fault state prediction and fault diagnosis model; S5, human-computer interaction: The human-computer interaction system presents the fault diagnosis and status prediction results, reversely writes the manual inspection information, provides fault information and suggestions, and stops the crane.

2. The crane online fault diagnosis and state prediction method according to claim 1 is characterized in that: The improved recursive smoothing filtering method is expressed as: Where k is an imaginary number, X t is the signal value output by data processing, and α is the rate of change.

3. The crane online fault diagnosis and state prediction method according to claim 2 is characterized in that: The real-time crane fault state prediction and fault diagnosis in S3 include: S31, fault state prediction: by inputting the processed working process parameters, using the fault state prediction and fault diagnosis model, the future operation state of the crane is predicted; S32, fault diagnosis: perform fault diagnosis by performing an inverse operation on the fault state estimation to locate the fault point.

4. The crane online fault diagnosis and state prediction method according to claim 3 is characterized in that: The fault state prediction in S31 includes: S311, predicting fault status: inputting the processed working process parameters, predicting through the fault status prediction and fault diagnosis model, and calculating the input value F of each transition, expressed as: F (k) =I T *(α⊙W⊙M (k-1) ); Where k represents the current iteration number, I is the input matrix, and M is the place mark distribution vector; Among them, λ is the threshold set of transition rules; S312, calculation of new place mark value: Calculate a new place mark distribution vector M, expressed as: Among them, O is the output matrix, U is the credibility vector of the transition rule; S313, reasoning calculation end judgment: when M (k-1) =M (k) When , the inference calculation ends. If the distribution vector of the library event flag has a value, it means that a failure event has occurred in the library.

5. The crane online fault diagnosis and state prediction method according to claim 4 is characterized in that: The fault diagnosis in S32 includes: S321, fault diagnosis process: Fault diagnosis is the inverse operation of fault prediction, which can be expressed as: S322, deriving fault events using the fault data that has occurred: deriving the model structure of the fault event occurrence through the fault association matrix A' that has occurred, expressed as:

6. The crane online fault diagnosis and state prediction method according to claim 5 is characterized in that: The improved particle swarm algorithm is expressed as: x ij (t+1)=x ij (t)+v ij (t+1); Where i and j represent the number of i-th (i∈n) particles and j-th (j∈D) dimension, t is the number of iterations, and x ij represents each particle, v ij Indicates the update speed of each particle, Indicates iteration to the current individual optimal solution, ω (t) is the inertia factor, Iterates to the current global optimal solution. c1 and c2 are acceleration factors. r1 and r2 are random numbers in the interval [0,1].

7. The crane online fault diagnosis and state prediction method according to claim 6 is characterized in that: The human-computer interaction in S5 includes: S51, Human-computer interaction system design: Use object-oriented language development technology to design a human-computer interaction system for real-time fault state prediction and fault diagnosis of cranes; S52, system function realization: realizing the real-time fault state prediction of the crane and the calling of the fault diagnosis calculation program through the human-computer interaction system; S53, data feedback and processing: the actual inspection result values ​​of the crane operators, commanders and maintenance personnel are reversely written into the input data set of the crane real-time fault state prediction and fault diagnosis calculation program; S54, result display: the real-time fault state prediction of the crane and the fault diagnosis reasoning calculation results are displayed to the crane operator and the commander through a graphical interface; S55, control instruction: according to the real-time fault state prediction and fault diagnosis reasoning calculation results, a stop instruction is issued to the crane control system.

Images