Equipment predictive maintenance telemetering system based on industrial automation

Abstract

The invention belongs to the technical field of equipment maintenance, and discloses an equipment predictive maintenance telemetering system based on industrial automation. The method comprises the following steps: collecting equipment operation data of industrial automation equipment; preprocessing the equipment operation data to obtain preprocessed data; modeling the preprocessed data to obtain an equipment comprehensive prediction model; on the basis of the equipment comprehensive prediction model, predicting the future operation state of the equipment to obtain a health degree evaluation result of the equipment; the corresponding maintenance strategy and maintenance time are determined based on the health degree evaluation result of the equipment, and the equipment is maintained according to the corresponding maintenance strategy and maintenance time, so that the operation cost of an enterprise can be reduced, the utilization rate of the equipment can be improved, and the market competitiveness of the enterprise can be enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment maintenance, and more particularly to an equipment predictive maintenance telemetry system based on industrial automation. Background Art

[0002] The patent with application publication number CN110705133A discloses a predictive maintenance method and predictive maintenance equipment, including: receiving first data sent by a data transmission device; classifying the first data, wherein the types of the first data include normal data, abnormal data and fault data; using a variance algorithm and the first data to establish a prediction model, which can provide data support for equipment maintenance, realize predictive maintenance of equipment in a practical sense, reduce maintenance costs, reduce downtime, and avoid production losses and material waste caused by equipment failure.

[0003] However, there are still many problems in the existing industrial automation equipment maintenance technology, which seriously restricts the improvement of production efficiency and equipment reliability. The traditional regular maintenance method often cannot accurately reflect the actual condition of the equipment, resulting in a waste of maintenance resources or insufficient maintenance; and the simple fault detection system often cannot detect potential problems in time, resulting in sudden equipment failure, causing production line shutdown and huge economic losses; the existing predictive maintenance system usually only focuses on a single type of data, such as only analyzing vibration or temperature, which makes it difficult to fully grasp the health status of the equipment; in terms of data processing, many systems lack effective noise processing capabilities, affecting data quality and the reliability of analysis results; in addition, the current equipment status modeling methods are often oversimplified and difficult to accurately capture the nonlinear dynamic characteristics in complex industrial environments; in terms of health assessment, most systems only consider short-term status and ignore long-term trends, resulting in a lack of foresight in maintenance decisions; the formulation of maintenance strategies is often lacking in flexibility and systematicity, making it difficult to make the best decision based on the actual condition of the equipment and the specific needs of the enterprise; these problems are particularly prominent in actual production.

[0004] In view of this, the present invention proposes an equipment predictive maintenance telemetry system based on industrial automation to solve the above problems. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solutions: an equipment predictive maintenance telemetry system based on industrial automation, comprising: a data acquisition module for collecting equipment operation data of industrial automation equipment; A data processing module is used to pre-process the equipment operation data to obtain pre-processed data; A modeling module is used to model the preprocessed data using an improved Markov chain to obtain a comprehensive prediction model for the equipment; The comprehensive evaluation module predicts the future operation status of the equipment based on the equipment comprehensive prediction model and obtains the health evaluation result of the equipment; The strategy maintenance module determines the corresponding maintenance strategy and maintenance time based on the health assessment result of the equipment, and performs maintenance on the equipment according to the corresponding maintenance strategy and maintenance time; each module is connected by wired and / or wireless means.

[0006] Furthermore, the equipment operation data includes vibration data, temperature data, current data and power data.

[0007] Furthermore, the method of preprocessing the equipment operation data includes: The equipment operation data is cleaned according to the data type. The data cleaning method is as follows: remove duplicate data and outliers; process noise data; obtain preliminary processed operation data; normalize or standardize the preliminary processed operation data to obtain preprocessed data.

[0008] Furthermore, the method of processing noise data includes: The equipment operation data is modeled as k source signals according to the data type. and noise A linear mixture of ;in, is the time index, is the mixing matrix; To observe the signal; The observed signal Perform preliminary processing, which is to subtract its mean to make it have zero mean and obtain the preliminary observation signal ; Calculate each time Initial observation signal The covariance matrix of At every time , using the current estimate of the covariance matrix Perform eigenvalue decomposition to obtain the eigenvector matrix and its diagonal matrix ; Based on the eigenvector matrix and its diagonal matrix Constructing the transformation matrix ;in, for The transpose of , the initial observation signal Left multiply by the transformation matrix , get the middle signal ; The middle signal Perform reverse transformation to obtain the standard original signal ; For the standard original signal Post-processing is performed to obtain preliminary processing operation data.

[0009] Furthermore, the covariance matrix is ​​calculated by: Defining the adaptive forgetting factor ( ); initialize a covariance matrix as a diagonal matrix or a unit matrix; and a gain vector as a 0 vector; for the initial observation signal , recursively calculate the gain vector and update the covariance matrix; the formula for calculating the gain vector is: ;in, Indicates at time The estimated value of the covariance matrix when , Indicates at time The calculated gain vector is a column vector; for The transpose of is a positive constant; The formula for updating the covariance matrix is: ;in, is the regularization coefficient, is the unit matrix; For in time The estimated value of the covariance matrix when ; Adaptive forgetting factor ;in, for The kurtosis of is the kurtosis constant of a normal distribution; for The skewness of and is the weight coefficient of the corresponding item, is the index parameter; for The approximate entropy of is a positive adjustment coefficient.

[0010] Furthermore, the mid-segment signal Ways to reverse the transformation include: The middle signal In an overcomplete dictionary The above transformation is expressed as ;in, is a sparse coefficient vector; Add a transformation mixing matrix based on the transformation representation ,Right now ; Define the optimization objective function FH= ;in, is the square of the L2 norm within it, for The L1 norm of for The mixed norm of Calculate the L2 norm for each row of , and then calculate the L1 norm of the L2 norm of all rows; is the time-varying regularization coefficient; is a fixed regularization coefficient; ;in, is a basic L1 regularization coefficient, and are two positive exponential adjustment coefficients; for The dimension of for The L2 norm of ; By minimizing the function value of the objective function, Normalize each column of to obtain the transformed mixing matrix The specific value of , in this case, QR decomposition or maximum likelihood estimation method is used to decompose , get the inverse matrix W; use the inverse matrix W to correct the mid-segment signal Perform linear transformation to obtain the standard original signal .

[0011] Furthermore, the method of modeling the preprocessed data includes: Preset a high-dimensional phase space; divide the high-dimensional phase space into grids to obtain a hierarchical lattice model; map the preprocessed data into the hierarchical lattice model to obtain a trajectory sequence, where each time step corresponds to a state point in the hierarchical lattice model; Traverse each state point in the trajectory sequence, and determine the number of the grid to which it belongs according to the coordinates of the state point; maintain a dictionary structure to store the number of visits to each grid, and for each grid to which the state point belongs, add 1 to the value of the corresponding dictionary. After traversing the entire trajectory sequence, the value in the dictionary is the number of visits to each grid; based on the number of visits, calculate its visit probability, that is, the number of visits divided by the length of the trajectory sequence; regard each grid as a discrete state of the Markov chain, and for each grid, count the average residence time of the trajectory sequence in the grid, and regard the average residence time as the duration distribution of the discrete state; Define the state transition count matrix , where the elements Recorded from The grid is transferred to The number of grids, for the grids, traverse the trajectory sequence, and accumulate , and calculate the value of The state transition probability of a grid ;in, is the smoothing parameter; It is from The sum of all transfer times starting from the grid; Indicates the size of the state space; Based on the average residence time, define the self-loop probability ;in, For the trajectory sequence The average residence time of a grid; based on its own cycle probability and state transition probability A state transfer matrix of the Markov chain is constructed. For each row of the state transfer matrix, the value of the state transfer probability is normalized so that the row sum is 1; the Markov chain with the state transfer matrix is ​​the equipment comprehensive prediction model.

[0012] Furthermore, the method of dividing the high-dimensional phase space into grids includes: Define the number of levels and scales; that is, specify a scale parameter for each level; the scale parameter is the embedding dimension or delay; Starting from level 0, use a uniform grid to construct the initial grid. level( ), based on A hierarchical grid structure, where new grids are constructed by merging adjacent grids; this is done layer by layer until a defined number of levels is reached; during this process, the grids are numbered at the same time; The merging methods include: In the The entropy and the probability of being visited of each grid are counted, and the entropy and the probability of being visited are weighted and summed to obtain the statistical characteristics of the corresponding grid; based on the statistical characteristics, the similarity score between any two grids is calculated; the similarity scores between all grids are constructed into a similarity matrix S; based on the similarity matrix S, the grids are clustered using a hierarchical clustering algorithm to generate a hierarchical clustering tree; for each The Silhouette coefficient of each grid is calculated; on the hierarchical clustering tree, starting from the root node, the cutting height is moved downward layer by layer, and for each cutting height, the average Silhouette coefficient SC of all grids is calculated to obtain a mapping curve between the cutting height and SC; the inflection point in the mapping curve is identified, and the cutting height corresponding to the inflection point is the optimal cutting height; according to the optimal cutting height, the grids belonging to the same category on the hierarchical clustering tree are merged, and the merged grids inherit the statistical characteristics of the grids before the merger.

[0013] Furthermore, the method for obtaining the health evaluation result of the device includes: According to the current operation data of the equipment, its current state is determined in the hierarchical grid model, and the grid is used as the initial state of the equipment comprehensive prediction model; Using the state transfer matrix, perform n3-step prediction, where n3 is an integer greater than 1; starting from the initial state, after n3 time steps, the short-term prediction distribution is achieved; As n3 tends to infinity, the Markov chain converges to a stable state distribution, recorded as steady-state distribution; predefine a set of one or more health states , The state in is the state of normal operation of the equipment; the elements in the short-term prediction distribution Indicates that after n3 steps, it is in the The probability of a state, based on which the short-term health is calculated ; Elements in a Steady-State Distribution Indicates that the long-term The probability of a state is calculated to obtain the long-term health ;in, For the The average dwell time of a state, and are two positive function adjustment parameters; the health assessment results include short-term health and long-term health.

[0014] Furthermore, the maintenance strategy and maintenance time are determined in the following ways: Define a maintenance strategy set, which contains all optional maintenance strategies; define a time window T, which is a discrete time series consisting of possible maintenance times; form a decision space D1 by taking the Cartesian product of the maintenance strategy set and the time window T; define a decision function ; ;in, and is the strategy weight coefficient; is a normal number, It is also a normal number; For maintenance time, is the basic exponential constant; Yes and maintenance strategy Related weight factors, different Corresponding to different value; The decision space D1 is regarded as a discrete space, and each decision in the decision space D1 is a mass point; the function value of each mass point on the decision function is calculated and recorded as the mass of the mass point; Defining the Gravity Field , gravity field The elements in are any two particles and The attraction between ;in is the gravitational constant, There are two particles and The Euclidean distance between For mass point Quality, For mass point Quality, is a characteristic positive real-valued function; ;in, is the underlying positive constant; and are two positive weight parameters; and Particle and The corresponding maintenance time, For measuring point and The similarity function of the corresponding decision; In the gravity field For each particle, calculate the resultant force of all other particles on it, and select the particle with the largest resultant force. , and its corresponding decision is the optimal maintenance strategy and maintenance time.

[0015] The technical effects and advantages of the equipment predictive maintenance telemetry system based on industrial automation of the present invention are as follows: The present invention realizes comprehensive and real-time monitoring of the operating status of industrial automation equipment, greatly improving the accuracy and timeliness of fault prediction. By intelligently analyzing short-term and long-term health indicators, the system can accurately identify potential problems and effectively prevent sudden equipment failures, which not only significantly reduces unplanned downtime, but also optimizes maintenance plans and avoids problems of excessive maintenance and insufficient maintenance; its dynamically adjusted maintenance strategy ensures the optimal allocation of maintenance resources, which not only extends the service life of equipment but also reduces the overall maintenance cost; the system's adaptive ability makes it suitable for various complex industrial environments, and can continuously optimize the prediction model according to the actual condition of the equipment; it greatly improves the stability and reliability of the production line, and significantly improves production efficiency and product quality; in addition, the system's prediction function provides a reliable basis for production planning and resource allocation, which helps to optimize the overall operation strategy; in the long run, it can not only reduce operating costs, but also improve equipment utilization and enhance market competitiveness; at the same time, by reducing unnecessary repairs and replacements, it also helps to reduce resource consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic diagram of the equipment predictive maintenance telemetry system based on industrial automation of the present invention; Figure 2 It is a schematic diagram of the equipment predictive maintenance telemetry method based on industrial automation of the present invention. DETAILED DESCRIPTION

[0017] 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.

[0018] Example 1 See also Figure 1 As shown, the equipment predictive maintenance telemetry system based on industrial automation described in this embodiment includes: a data acquisition module, which is used to collect equipment operation data of industrial automation equipment; A data processing module is used to pre-process the equipment operation data to obtain pre-processed data; A modeling module is used to model the preprocessed data using an improved Markov chain to obtain a comprehensive prediction model for the equipment; The comprehensive evaluation module predicts the future operation status of the equipment based on the equipment comprehensive prediction model and obtains the health evaluation result of the equipment; The strategy maintenance module determines the corresponding maintenance strategy and maintenance time based on the health assessment results of the equipment, and implements maintenance on the equipment according to the corresponding maintenance strategy and maintenance time; each module is connected through wired and / or wireless means to achieve data transmission between modules.

[0019] Equipment operation data includes vibration data, temperature data, current data and power data; the data are collected in time series. Specifically, acceleration sensors are installed on key components of the equipment (such as bearings, gear boxes, etc.); the acceleration sensors convert mechanical vibrations into analog voltage or current signals, and use data acquisition cards or field bus modules to sample and digitize the analog voltage or current signals to obtain vibration data; temperature data is obtained by installing temperature sensors (such as thermocouples, thermal resistors, etc.); a clamp current sensor or leakage current sensor is used to measure the operating current of the equipment to obtain current data, and a power meter or power sensor is used to measure the active power, reactive power, etc. of the equipment; the power meter or power sensor outputs an analog voltage or current signal, and the analog signal is sampled and digitized. The sampling frequency is appropriately set according to the power fluctuation situation to obtain power data.

[0020] The collected analog and digital data need to be collected, converted and stored in real time through the data acquisition module to construct equipment operation data and lay the foundation for subsequent data processing and analysis.

[0021] Methods for preprocessing equipment operation data include: The equipment operation data are cleaned according to the data type (vibration data, temperature data, current data and power data). The data cleaning method is as follows: remove duplicate data and outliers, such as data points that are obviously beyond the reasonable range, check and repair data inconsistencies, such as inconsistent units, format errors, etc.; and process noise data; obtain preliminary processed operation data; normalize or standardize the preliminary processed operation data so that variables of different dimensions are in the same numerical range to obtain preprocessed data.

[0022] Ways to deal with noisy data include: The equipment operation data is modeled as k source signals according to the data type. and noise A linear mixture of ;in, is the time index, is the mixing matrix; mixing matrix Each row of represents an observation signal channel; each column corresponds to a source signal, and the elements represent the contribution weight of the source signal to the observation signal; It is the observation signal, that is, the data signal composed of different data types.

[0023] The observed signal Perform preliminary processing, which is to subtract its mean to make it have zero mean and obtain the preliminary observation signal ; Remove the DC component of the signal to make subsequent processing easier; Calculate each time Initial observation signal The covariance matrix of ( ), which controls the weights of new and old data; initialize a covariance matrix as a diagonal matrix or a unit matrix; and a gain vector as a 0 vector; for the initial observation signal , recursively calculate the gain vector and update the covariance matrix; the formula for calculating the gain vector is: ;in, Indicates at time The estimated value of the covariance matrix when , Indicates at time The calculated gain vector is a column vector; it is used according to To update the estimate of the covariance matrix; for The transpose of A small positive constant used to improve numerical stability and avoid the denominator being 0.

[0024] The formula for updating the covariance matrix is: ;in, is the regularization coefficient, is the unit matrix, which is used to ensure that the estimated covariance matrix has an appropriate condition number and improve the robustness of the estimate; For in time The estimated value of the covariance matrix when ; Adaptive forgetting factor ;in, for The kurtosis of is the kurtosis constant of a normal distribution, approximately equal to 3; for The skewness of and is the weight coefficient of the corresponding item, controlling the degree of influence, is an exponential parameter that controls the sensitivity of the adaptive forgetting factor range; for The approximate entropy of reflects the uncertainty and randomness of the data; It is a positive adjustment coefficient used to control the influence of skewness.

[0025] At every time , using the current estimate of the covariance matrix Perform eigenvalue decomposition to obtain the eigenvector matrix and its diagonal matrix ; Based on the eigenvector matrix and its diagonal matrix Constructing the transformation matrix ;in, for The transpose of , the initial observation signal Left multiply by the transformation matrix , get the middle signal ; The middle signal Perform inverse transformation to obtain the standard original signal.

[0026] Specifically, the middle signal In an overcomplete dictionary The above transformation is expressed as ;in, is a sparse coefficient vector, most of the elements are 0; an overcomplete dictionary It is a pre-designed basis matrix (such as wavelet basis, Fourier basis, etc.) or a dictionary obtained by data-driven learning.

[0027] Add a transformation mixing matrix based on the transformation representation ,Right now ; Define the optimization objective function FH= ;in, is the square of the L2 norm within it, for The L1 norm of for The mixed norm of Calculate the L2 norm for each row (corresponding to each source signal), and then calculate the L1 norm for the L2 norm of all rows; is the time-varying regularization coefficient, which is adaptively adjusted to obtain optimal sparsity; is a fixed regularization coefficient used to enhance the robustness of the estimation.

[0028] ;in, is a basic L1 regularization coefficient, and are two positive exponential adjustment coefficients, Controls the decay rate. Control Relative to The range of changes; for The dimension of for The L2 norm of ; By minimizing the function value of the objective function, Normalize each column of to obtain the transformed mixing matrix The specific value of , in this case, QR decomposition or maximum likelihood estimation method is used to decompose , get the inverse matrix W; use the inverse matrix W to correct the mid-segment signal Perform linear transformation to obtain the standard original signal .

[0029] Standard original signal Post-processing is performed to obtain data after processing the noise data, and then the preliminary processing operation data is obtained; the post-processing methods include sorting and scaling; specifically, using the known prior knowledge of the source signal, For example, sorting based on time domain features (such as statistical moments, peak values, etc.), sorting based on frequency domain features (such as dominant frequency, bandwidth, etc.), or sorting based on time-frequency features (such as wavelet packets, etc.); according to the known statistical characteristics of the source signal, The individual components of are scaled, for example, variance-based scaling, peak-based scaling, or energy-based scaling.

[0030] Ways to model preprocessed data include: A high-dimensional phase space is preset; the high-dimensional phase space is divided into grids to obtain a hierarchical lattice model; specifically, the number of levels and the scale are defined; that is, a scale parameter is specified for each level to control the granularity of the grid at the level; the scale parameter is the embedding dimension or the time delay.

[0031] Starting from the finest granularity level (level 0), the initial grid is constructed using a uniform grid. level( ), based on A hierarchical grid structure builds new grids (coarse-grained) by merging adjacent grids; it builds up layer by layer until the defined number of levels is reached; the grids are numbered during this process.

[0032] The merger methods include: In the Hierarchical, count the entropy and the probability of being visited of each grid, and perform weighted summation of the entropy and the probability of being visited to obtain the statistical characteristics of the corresponding grid; based on the statistical characteristics, calculate the similarity score (Euclidean distance, cosine similarity or KL divergence) between any two grids; construct the similarity scores between all grids into a similarity matrix S; based on the similarity matrix S, use a hierarchical clustering algorithm (such as AGNES or DIANA) to cluster the grids to generate a hierarchical clustering tree (dendrogram).

[0033] For each For each hierarchical grid, calculate its Silhouette coefficient (Silhouette coefficient is an indicator used to evaluate clustering effect. It combines the compactness and separation of clustering. The value range of this coefficient is between -1 and 1. The larger the value, the better the clustering effect). On the hierarchical clustering tree, start from the root node and move down the cutting height layer by layer. For each cutting height, calculate the average Silhouette coefficient SC of all grids to obtain a mapping curve between the cutting height and SC. Identify the inflection point in the mapping curve, and the cutting height corresponding to the inflection point is the optimal cutting height. According to the optimal cutting height, merge the grids belonging to the same category on the hierarchical clustering tree, and the merged grid inherits the statistical characteristics of the grid before the merger. For example, the probability of a coarse-grained grid being visited can be the weighted average of the probability of a fine-grained grid.

[0034] The preprocessed data is mapped into the hierarchical lattice model to obtain a trajectory sequence, where each time step corresponds to a state point (phase space vector) in the hierarchical lattice model; each state point in the trajectory sequence is traversed, and the number of the grid to which it belongs is determined based on the coordinates of the state point (the grid can be quickly located using an efficient hash-based search method); a dictionary (hash table) structure is maintained to store the number of times each grid is visited. For each grid to which a state point belongs, the value of the corresponding dictionary is increased by 1. After traversing the entire trajectory sequence, the value in the dictionary is the number of times each grid is visited; based on the number of visits, the probability of being visited is calculated, that is, the number of visits divided by the length of the trajectory sequence (the number of state points). If a new trajectory sequence arrives, there is no need to re-count all grids. Instead, the new trajectory needs to be traversed, the number of visits to the corresponding grid needs to be updated, and then the visit probability of each grid is recalculated. This is suitable for streaming data.

[0035] Each grid is regarded as a discrete state of the Markov chain. For each grid (discrete state), the average residence time of the trajectory sequence in the grid is counted, and the average residence time is regarded as the duration distribution of the discrete state.

[0036] Define the state transition count matrix , where the elements Recorded from The grid is transferred to The number of grids, for the grids, traverse the trajectory sequence, and accumulate , and calculate the value of The state transition probability of a grid ;in, is the smoothing parameter, when When it is equal to 0, it is equivalent to the maximum likelihood estimation; It is from The sum of all transfer times starting from the grid; Represents the size of the state space, that is, the total number of discrete states.

[0037] Due to the existence of residence time, each state has a certain probability of self-looping. Based on the average residence time, the self-loop probability is defined ;in, For the trajectory sequence The average dwell time of a grid.

[0038] Based on the probability of self-circulation and state transition probability Construct the state transfer matrix of the Markov chain. For each row of the state transfer matrix, normalize the value of the state transfer probability so that the row sum is 1. This ensures the randomness of the state transfer matrix. The Markov chain with the state transfer matrix is ​​the comprehensive prediction model of the equipment. The state transfer matrix describes the evolution law of the system state in the phase space and is the basis for subsequent state prediction and health assessment.

[0039] The methods for obtaining the health assessment results of the device include: According to the current operation data of the equipment, its current state (grid) is determined in the hierarchical grid model, and the grid is used as the initial state of the equipment comprehensive prediction model.

[0040] Using the state transfer matrix, perform n3-step prediction, where n3 is an integer greater than 1; get the short-term prediction distribution (expressed as a vector or matrix) from the initial state after n3 time steps, which reflects the uncertainty in the short term; As n3 tends to infinity, the Markov chain will converge to a stable state distribution, denoted as the steady-state distribution (represented by a vector or matrix). The steady-state distribution is the only steady-state distribution of the Markov chain and can be obtained through matrix calculation; the steady-state distribution reflects the average state distribution after long-term operation.

[0041] Predefine a set of one or more health states , The state in is the state of normal operation of the equipment; the elements in the short-term prediction distribution Indicates that after n3 steps, it is in the The probability of a state, based on which the short-term health is calculated ; Elements in a Steady-State Distribution Indicates that the long-term The probability of a state is calculated to obtain the long-term health ;in, For the The average dwell time of a state, and are two positive function adjustment parameters used to control the shape of the function; for those states that belong to the health state set H but have a long average residence time, their contribution to long-term health is appropriately reduced; because if a state stays in a health state for a long time, it may also mean that there is a potential abnormality; it should be noted that and The same state can be indexed at the same time; this is to distinguish between elements in the short-term prediction distribution and the steady-state distribution; the health assessment results include short-term health and long-term health.

[0042] Maintenance strategies and maintenance times are determined by: Define a maintenance strategy set, which contains all optional maintenance strategies, such as replacing parts, cleaning, adjustment, etc. Define a time window T, which is a discrete time series consisting of possible maintenance times; The Cartesian product of the maintenance strategy set and the time window T constitutes the decision space D1; Define the decision function ; ;in, and is the strategy weight coefficient, which is used to balance short-term health and long-term health; is a positive constant used to control the decay rate. It is also a positive constant used to adjust the impact of long-term health; For maintenance time, is the basic exponential constant, such as ; Yes and maintenance strategy Related weight factors, different Corresponding to different value; for example, you can set To replace parts ; For cleaning , For adjustment ; In this way, the replacement component strategy corresponds to The largest value indicates that its impact on long-term health is the highest.

[0043] The decision space D1 is regarded as a discrete space, and each decision (maintenance strategy and maintenance time) in the decision space D1 is a particle. The function value of each particle on the decision function is calculated and recorded as the mass of the particle.

[0044] Defining the Gravity Field , gravity field The elements in are any two particles and The attraction between ;in is the gravitational constant, There are two particles and The Euclidean distance between For mass point The quality of (the function value on the decision function), For mass point Quality, It is a characteristic positive real-valued function, which dynamically adjusts the influence of distance on gravity according to the characteristics of different pairs of particles.

[0045] ;in, is the underlying positive constant, such as ; and are two positive weight parameters used to control the influence of time difference and strategy difference; and Particle and The corresponding maintenance time, For measuring point and The similarity function of the corresponding decision (a weighted function that integrates the type of decision, the quality of the particle corresponding to the decision, and the cost of implementing the decision).

[0046] In the gravity field For each particle, calculate the resultant force of all other particles on it, and select the particle with the largest resultant force. The corresponding decision is the optimal maintenance strategy and maintenance time; according to the obtained optimal maintenance strategy and maintenance time, corresponding maintenance is carried out on the equipment.

[0047] Comprehensively consider the short-term and long-term health status of the equipment, find the optimal maintenance strategy and maintenance time in the decision space, and thus achieve efficient predictive maintenance of the equipment.

[0048] This embodiment realizes comprehensive and real-time monitoring of the operating status of industrial automation equipment, greatly improving the accuracy and timeliness of fault prediction. By intelligently analyzing short-term and long-term health indicators, the system can accurately identify potential problems and effectively prevent sudden equipment failures, which not only significantly reduces unplanned downtime, but also optimizes maintenance plans and avoids problems of over-maintenance and under-maintenance. Its dynamically adjusted maintenance strategy ensures the optimal allocation of maintenance resources, which not only extends the service life of equipment but also reduces the overall maintenance cost. The system's adaptive ability makes it suitable for various complex industrial environments and can continuously optimize the prediction model according to the actual condition of the equipment. It greatly improves the stability and reliability of the production line and significantly improves production efficiency and product quality. In addition, the system's prediction function provides a reliable basis for production planning and resource allocation, which helps to optimize the overall operation strategy. In the long run, it can not only reduce operating costs, but also improve equipment utilization and enhance market competitiveness. At the same time, by reducing unnecessary repairs and replacements, it also helps to reduce resource consumption.

[0049] Example 2 See also Figure 2 As shown, the part not described in detail in this embodiment is described in Example 1, which provides a predictive maintenance telemetry method for equipment based on industrial automation, including: S1. Collect equipment operation data of industrial automation equipment; S2. Preprocessing the equipment operation data to obtain preprocessed data; S3, using improved Markov chain to model the preprocessed data and obtain the equipment comprehensive prediction model; S4. Based on the equipment comprehensive prediction model, the future operation status of the equipment is predicted to obtain the health assessment result of the equipment; S5. Determine the corresponding maintenance strategy and maintenance time based on the health assessment result of the equipment, and implement maintenance on the industrial automation equipment according to the corresponding maintenance strategy and maintenance time.

[0050] Example 3 This embodiment discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the operation mode of the equipment predictive maintenance telemetry method based on industrial automation provided above is implemented.

[0051] Since the electronic device introduced in this embodiment is an electronic device used to implement the equipment predictive maintenance telemetry method based on industrial automation in the embodiment of this application, based on the equipment predictive maintenance telemetry method based on industrial automation introduced in the embodiment of this application, the technical personnel of this field can understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of this application is not described in detail here. As long as the technical personnel of this field implement the electronic device used in the equipment predictive maintenance telemetry method based on industrial automation in the embodiment of this application, it belongs to the scope of protection of this application.

[0052] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0053] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technical users in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. Equipment predictive maintenance telemetry system based on industrial automation, characterized by: include: Data acquisition module, used to collect equipment operation data of industrial automation equipment; A data processing module is used to pre-process the equipment operation data to obtain pre-processed data; A modeling module is used to model the preprocessed data using an improved Markov chain to obtain a comprehensive prediction model for the equipment; The comprehensive evaluation module predicts the future operation status of the equipment based on the equipment comprehensive prediction model and obtains the health evaluation result of the equipment; The strategy maintenance module determines the corresponding maintenance strategy and maintenance time based on the health assessment result of the equipment, and performs maintenance on the equipment according to the corresponding maintenance strategy and maintenance time; each module is connected by wired and / or wireless means.

2. The equipment predictive maintenance telemetry system based on industrial automation according to claim 1 is characterized in that: The equipment operation data includes vibration data, temperature data, current data and power data.

3. The equipment predictive maintenance telemetry system based on industrial automation according to claim 2 is characterized in that: The method of preprocessing the equipment operation data includes: The equipment operation data is cleaned according to the data type. The data cleaning method is as follows: remove duplicate data and outliers; process noise data; obtain preliminary processed operation data; normalize or standardize the preliminary processed operation data to obtain preprocessed data.

4. The equipment predictive maintenance telemetry system based on industrial automation according to claim 3 is characterized in that: The method of processing noise data includes: The equipment operation data is modeled as k source signals according to the data type. and noise A linear mixture of ;in, is the time index, is the mixing matrix; To observe the signal; The observed signal Perform preliminary processing, which is to subtract its mean to make it have zero mean and obtain the preliminary observation signal ; Calculate each time Initial observation signal The covariance matrix of At every time , using the current estimate of the covariance matrix Perform eigenvalue decomposition to obtain the eigenvector matrix and its diagonal matrix ; Based on the eigenvector matrix and its diagonal matrix Constructing the transformation matrix ;in, for The transpose of , the initial observation signal Left multiply by the transformation matrix , get the middle signal ; The middle signal Perform reverse transformation to obtain the standard original signal ; For the standard original signal Post-processing is performed to obtain preliminary processing operation data.

5. The equipment predictive maintenance telemetry system based on industrial automation according to claim 4 is characterized in that: The covariance matrix is ​​calculated by: Defining the adaptive forgetting factor ( ); initialize a covariance matrix as a diagonal matrix or a unit matrix; and a gain vector as a 0 vector; for the initial observation signal , recursively calculate the gain vector and update the covariance matrix; the formula for calculating the gain vector is: ;in, Indicates at time The estimated value of the covariance matrix when , Indicates at time The calculated gain vector is a column vector; for The transpose of is a positive constant; The formula for updating the covariance matrix is: ;in, is the regularization coefficient, is the unit matrix; For in time The estimated value of the covariance matrix when ; Adaptive forgetting factor ;in, for The kurtosis of is the kurtosis constant of a normal distribution; for The skewness of and is the weight coefficient of the corresponding item, is the index parameter; for The approximate entropy of is a positive adjustment coefficient.

6. The equipment predictive maintenance telemetry system based on industrial automation according to claim 5, characterized in that: The mid-segment signal Ways to reverse the transformation include: The middle signal In an overcomplete dictionary The above transformation is expressed as ;in, is a sparse coefficient vector; Add a transformation mixing matrix based on the transformation representation ,Right now ; Define the optimization objective function FH= ;in, is the square of the L2 norm within it, for The L1 norm of for The mixed norm of Calculate the L2 norm for each row of , and then calculate the L1 norm of the L2 norm of all rows; is the time-varying regularization coefficient; is a fixed regularization coefficient; ;in, is a basic L1 regularization coefficient, and are two positive exponential adjustment coefficients; for The dimension of for The L2 norm of ; By minimizing the function value of the objective function, Normalize each column of to obtain the transformed mixing matrix The specific value of , in this case, QR decomposition or maximum likelihood estimation method is used to decompose , get the inverse matrix W; use the inverse matrix W to correct the mid-segment signal Perform linear transformation to obtain the standard original signal .

7. The equipment predictive maintenance telemetry system based on industrial automation according to claim 6, characterized in that: The method of modeling the preprocessed data includes: Preset a high-dimensional phase space; divide the high-dimensional phase space into grids to obtain a hierarchical lattice model; map the preprocessed data into the hierarchical lattice model to obtain a trajectory sequence, where each time step corresponds to a state point in the hierarchical lattice model; Traverse each state point in the trajectory sequence, and determine the number of the grid to which it belongs according to the coordinates of the state point; maintain a dictionary structure to store the number of visits to each grid, and for each grid to which the state point belongs, add 1 to the value of the corresponding dictionary. After traversing the entire trajectory sequence, the value in the dictionary is the number of visits to each grid; based on the number of visits, calculate its visit probability, that is, the number of visits divided by the length of the trajectory sequence; regard each grid as a discrete state of the Markov chain, and for each grid, count the average residence time of the trajectory sequence in the grid, and regard the average residence time as the duration distribution of the discrete state; Define the state transition count matrix , where the elements Recorded from The grid is transferred to The number of grids, for the grids, traverse the trajectory sequence, and accumulate , and calculate the value of The state transition probability of a grid ;in, is the smoothing parameter; It is from The sum of all transfer times starting from the grid; Indicates the size of the state space; Based on the average residence time, define the self-loop probability ;in, For the trajectory sequence The average residence time of a grid; based on its own cycle probability and state transition probability A state transfer matrix of the Markov chain is constructed. For each row of the state transfer matrix, the value of the state transfer probability is normalized so that the row sum is 1; the Markov chain with the state transfer matrix is ​​the equipment comprehensive prediction model.

8. The equipment predictive maintenance telemetry system based on industrial automation according to claim 7, characterized in that: The method of gridding the high-dimensional phase space includes: Define the number of levels and scales; that is, specify a scale parameter for each level; the scale parameter is the embedding dimension or delay; Starting from level 0, use a uniform grid to construct the initial grid. level( ), based on A hierarchical grid structure, where new grids are constructed by merging adjacent grids; this is done layer by layer until a defined number of levels is reached; during this process, the grids are numbered at the same time; The merging methods include: In the The entropy and the probability of being visited of each grid are counted, and the entropy and the probability of being visited are weighted and summed to obtain the statistical characteristics of the corresponding grid; based on the statistical characteristics, the similarity score between any two grids is calculated; the similarity scores between all grids are constructed into a similarity matrix S; based on the similarity matrix S, the grids are clustered using a hierarchical clustering algorithm to generate a hierarchical clustering tree; for each The Silhouette coefficient of each grid is calculated; on the hierarchical clustering tree, starting from the root node, the cutting height is moved downward layer by layer, and for each cutting height, the average Silhouette coefficient SC of all grids is calculated to obtain a mapping curve between the cutting height and SC; the inflection point in the mapping curve is identified, and the cutting height corresponding to the inflection point is the optimal cutting height; according to the optimal cutting height, the grids belonging to the same category on the hierarchical clustering tree are merged, and the merged grids inherit the statistical characteristics of the grids before the merger.

9. The equipment predictive maintenance telemetry system based on industrial automation according to claim 8, characterized in that: The method for obtaining the health evaluation result of the device includes: According to the current operation data of the equipment, its current state is determined in the hierarchical grid model, and the grid is used as the initial state of the equipment comprehensive prediction model; Using the state transfer matrix, perform n3-step prediction, where n3 is an integer greater than 1; starting from the initial state, after n3 time steps, the short-term prediction distribution is achieved; As n3 tends to infinity, the Markov chain converges to a stable state distribution, which is recorded as the steady-state distribution; Predefine a set of one or more health states , The state in is the state of normal operation of the equipment; the elements in the short-term prediction distribution Indicates that after n3 steps, it is in the The probability of a state, based on which the short-term health is calculated ; Elements in a Steady-State Distribution Indicates that the long-term The probability of a state is calculated to obtain the long-term health ;in, For the The average dwell time of a state, and are two positive function adjustment parameters; the health assessment results include short-term health and long-term health.

10. The equipment predictive maintenance telemetry system based on industrial automation according to claim 9, characterized in that: The maintenance strategy and maintenance time are determined in the following ways: Define a maintenance strategy set, which contains all optional maintenance strategies; define a time window T, which is a discrete time series consisting of possible maintenance times; form a decision space D1 by taking the Cartesian product of the maintenance strategy set and the time window T; define a decision function ; ;in, and is the strategy weight coefficient; is a normal number, It is also a normal number; For maintenance time, is the basic exponential constant; Yes and maintenance strategy Related weight factors, different Corresponding to different value; The decision space D1 is regarded as a discrete space, and each decision in the decision space D1 is a mass point; the function value of each mass point on the decision function is calculated and recorded as the mass of the mass point; Defining the Gravity Field , gravity field The elements in are any two particles and The attraction between ;in is the gravitational constant, There are two particles and The Euclidean distance between For mass point Quality, For mass point Quality, is a characteristic positive real-valued function; ;in, is the underlying positive constant; and are two positive weight parameters; and Particle and The corresponding maintenance time, For measuring point and The similarity function of the corresponding decision; In the gravity field For each particle, calculate the resultant force of all other particles on it, and select the particle with the largest resultant force. , and its corresponding decision is the optimal maintenance strategy and maintenance time.

Images