A mechanical equipment operation and maintenance management system and method

Abstract

The present invention relates to the field of operation and maintenance management technology, specifically to a mechanical equipment operation and maintenance management system and method, including collecting multi-source data through an equipment monitoring unit, a data preprocessing unit cleaning and normalizing the above data, and generating a coordinated temperature, vibration and pressure data packet, and then an analysis and decision unit performing coordinated consistency detection on the temperature, vibration and pressure data in the above data packet, avoiding the disorder of multi-source data of the mechanical equipment operation status, ensuring the reliability of the input data of the subsequent early warning model, and then ensuring the credibility of the model prediction result, and then the analysis and decision unit outputs the operation status level of the mechanical equipment using the trained LSTM early warning model and the mechanical equipment operation status division rule, and the collaborative working unit implements the corresponding operation and maintenance management operation based on the operation status level of the mechanical equipment. The present invention effectively improves the efficiency and reliability of the mechanical equipment operation and maintenance management system.

Description

Technical Field

[0001] The present invention relates to the technical field of operation and maintenance management, and in particular to a mechanical equipment operation and maintenance management system and method. Background Art

[0002] The automation level of industrial production processes has been significantly improved. The extensive application of intelligent equipment and automated production lines has brought about an increase in production efficiency, but it has also put forward higher requirements for the operation and maintenance of equipment. Equipment failure will not only lead to direct economic losses, but may also cause safety accidents, environmental pollution and damage to corporate reputation. Therefore, predicting and preventing equipment failures in advance and reducing the risks caused by failures have become the key to improving the competitiveness of enterprises.

[0003] The prior art was searched and found that: the Chinese invention patent with the announcement number CN116307346B discloses an operation and maintenance management system and method for mechanical equipment. The method calculates the equipment health parameters and the predefined equipment health parameter threshold K 阈 By comparison and judgment, devices with health parameters below the threshold are screened out and early warning information is issued. At the same time, through the inspection task process of the equipment inspection management module, timely processing is achieved to reduce economic losses;

[0004] A Chinese invention patent with publication number CN112580153A discloses a vehicle running gear monitoring component health status management system and method. The method determines the current health status and health score by monitoring the historical abnormal value change trend of the monitoring point, and uses the health score results, failure mode and other maintenance data and operating parameters to predict the remaining service life through the failure mechanism model and neural network mathematical model, and finally gives the operation and maintenance decision suggestions for the monitoring components;

[0005] The above-mentioned patent documents all achieve efficient assessment of equipment health status at the system level, but in the equipment operation and maintenance management stage, how to effectively avoid the problem of multi-source data disorder is still a difficult problem that needs to be solved urgently. Summary of the invention

[0006] The purpose of the present invention is to propose a mechanical equipment operation and maintenance management system and method in response to the problems existing in the background technology.

[0007] The technical solution of the present invention is a method for operation and maintenance management of mechanical equipment, comprising the following specific steps:

[0008] Step 1: The equipment detection unit collects the operating status data of the mechanical equipment, including temperature data, vibration data and pressure data;

[0009] Step 2, the data preprocessing unit generates a coordinated temperature data packet, a coordinated vibration data packet and a coordinated pressure data packet, and transmits the coordinated temperature data packet, the coordinated vibration data packet and the coordinated pressure data packet to the analysis and decision-making unit;

[0010] Step 3, the analysis and decision unit extracts temperature data, vibration data and pressure data from the coordinated temperature data packet, the coordinated vibration data packet and the coordinated pressure data packet, respectively, and detects the coordination consistency of the temperature data, vibration data and pressure data;

[0011] Step 4: The analysis and decision-making unit inputs the real-time monitored temperature data, vibration data, and pressure data into the trained LSTM early warning model to determine in real time whether there is a fault risk, and classifies the fault level based on the output prediction value of the LSTM early warning and the set mechanical equipment status classification rules;

[0012] If the fault level is classified as high risk, the analysis and decision-making unit immediately issues a high-level warning, generates maintenance suggestions, and outputs a device operation status report. The analysis and decision-making unit then transmits the device operation status report to the visualization platform, and transmits the device fault type and maintenance suggestions to the collaborative work unit, which then executes step 5.

[0013] Step 5: The collaborative work unit intelligently dispatches maintenance personnel based on the equipment failure type, maintenance personnel's skills and geographical location, automatically assigns maintenance tasks, and notifies maintenance personnel;

[0014] Maintenance personnel perform equipment maintenance operations based on equipment failure types, maintenance recommendations, and the mechanical equipment maintenance operation manual in the knowledge base, record details of maintenance activities, update maintenance history records, and feed back actual results to the analysis and decision-making unit.

[0015] Preferably, the coordinated temperature data packet is generated as follows:

[0016] Step 2-1, the data preprocessing unit selects a random number α∈[1,q-1] and calculates the coordination code Cc 1i =[α]G;

[0017] Where G is defined in the finite field F p A base point of order q on the elliptic curve E on ;

[0018] Step 2-2, select a random number β∈[1,q-1] and calculate the auxiliary data encapsulation code R 1i =[β]G;

[0019] Step 2-3, calculate the data encapsulation parameter Pe 1i =H(R 1i ,MT~T i ||Ti );

[0020] Among them, || is the string concatenation symbol, H is the hash function, MT~T i is the temperature sensor T i Temperature data collected at all times;

[0021] Step 2-4, calculate the data analysis parameter Pp 1i =(Pe 1i ×α+β)mod q, if Pp 1i =0, return to step 2-2;

[0022] Step 2-5, generate coordinated temperature data packet PMT~T i ={R 1i ,Pe 1i , Pp 1i , Cc 1i ,MT~T i}.

[0023] Preferably, the coordinated vibration data packet is generated as follows:

[0024] Step 3-1, the data preprocessing unit selects a random number γ∈[1,q-1] and calculates the coordination code Cc 2i =[γ]G;

[0025] Step 3-2, select a random number δ∈[1,q-1] and calculate the auxiliary data encapsulation code R 2i =[δ]G;

[0026] Step 3-3, calculate the data encapsulation parameter Pe 2i =H(R 2i , MV~T i ||T i );

[0027] Among them, MV~T i T is the vibration sensor i Vibration data collected at all times;

[0028] Step 3-4, calculate the data analysis parameter Pp 2i =(Pe 2i ×γ+δ)mod q, if Pp 2i =0, then return to step 3-2;

[0029] Step 3-5, generate coordinated temperature data packet PMV~T i ={R 2i ,Pe 2i , Pp 2i , Cc 2i , MV~T i}.

[0030] Preferably, the coordinated pressure data packet is generated as follows:

[0031] Step 4-1: The data preprocessing unit selects a random number ε∈[1, q-1] and calculates the coordination code Cc 3i =[ε]G;

[0032] Step 4-2, select a random number λ∈[1,q-1] and calculate the auxiliary data encapsulation code R 3i =[λ]G;

[0033] Step 4-3, calculate the data encapsulation parameter Pe 3i =H(R 3i , MP~T i ||T i );

[0034] Among them, MP~T i For pressure sensor T i Pressure data collected at all times;

[0035] Step 4-4, calculate the data analysis parameter Pp 3i =(Pe 3i ×ε+λ)mod q, if Pp 3i =0, then return to step 4-2;

[0036] Step 4-5, generate coordinated temperature data packet PMP~T i ={R 3i ,Pe 3i , Pp 3i , Cc 3i , MP~T i}.

[0037] Preferably, the analysis and decision-making unit detects the consistency of the temperature data, vibration data and pressure data in the following steps:

[0038] Step 5-1, the analysis decision unit respectively obtains the coordinated data packets PMT~T i 、PMV~T i 、PMP~T i The following parameters are extracted:

[0039] Auxiliary data encapsulation code R 1i , data encapsulation parameter Pe 1i , Data analysis parameter Pp 1i , coordination code Cc 1i 、Temperature data MT~T i ;

[0040] Auxiliary data encapsulation code R2i , data encapsulation parameter Pe 2i , Data analysis parameter Pp 2i , coordination code Cc 2i 、Vibration data MV~T i ;

[0041] Auxiliary data encapsulation code R 3i , data encapsulation parameter Pe 3i , Data analysis parameter Pp 3i , coordination code Cc 3i , Pressure data MP~T i ;

[0042] Step 5-2, calculate the following auxiliary consistency verification parameters:

[0043] Pcv~Ⅰ~T i =[Pp 1i ]G+[Pp 2i ]G+[Pp 3i ]G;

[0044] Pcv~Ⅱ~T i =([Pe 1i ]Cc 1i +[Pe 2i ]Cc 2i +[Pe 3i ]Cc 3i )+(R 1i +R 2i +R 3i );

[0045] Step 5-3, if Pcv~Ⅰ~T i With Pcv~Ⅱ~T i If they are equal, it means that the temperature data MT~T received by the analysis and decision-making unit i 、Vibration data MV~T i And pressure data MP~T i Have coordination and consistency.

[0046] Preferably, when the early warning model predicts that the mechanical equipment is at low risk or medium risk, the analysis and decision unit outputs an equipment operation status report, which includes temperature data, vibration data, pressure data and the mechanical equipment status level. The analysis and decision unit then transmits the equipment operation status report to the visualization platform. When the mechanical equipment status level is medium risk, the analysis and decision unit issues a medium risk message, and the equipment administrator independently decides on the next mechanical equipment operation and maintenance operation, including but not limited to no intervention, equipment upgrades, formulating a preventive maintenance plan for the equipment, or arranging inspections, maintenance, and replacement of wearing parts.

[0047] The technical solution of the present invention is: a mechanical equipment operation and maintenance management system, which is applicable to the above-mentioned mechanical equipment operation and maintenance management method, including: an equipment monitoring unit, a data preprocessing unit, an analysis and decision-making unit, a collaborative work unit, a knowledge base and a visualization platform;

[0048] The equipment monitoring unit is used to monitor the operating status of the mechanical equipment and collect the operating status data of the mechanical equipment in real time;

[0049] The data preprocessing unit is used to perform cleaning, standardization and normalization operations on the data collected by the equipment monitoring unit to remove abnormal values ​​and noise;

[0050] The knowledge base stores historical maintenance records and mechanical equipment maintenance operation manuals. During the mechanical equipment maintenance process, maintenance personnel can access the knowledge base in the system through handheld mobile devices to obtain professional and compliant maintenance guidance and suggestions;

[0051] The analysis and decision-making unit is responsible for advanced data analysis, AI model training and reasoning, and integration with other systems;

[0052] The collaborative working unit is used to intelligently dispatch maintenance personnel, record operation and maintenance management logs, and optimize the LSTM early warning model based on the actual results fed back by the maintenance personnel;

[0053] The visualization platform is used to intuitively display the operating status data of the mechanical equipment and the operating status level of the mechanical equipment generated by the system.

[0054] Preferably, the analysis and decision-making unit uses the trained LSTM early warning model based on the equipment operation status data processed by the data preprocessing unit to conduct in-depth mining of the equipment operation data, discover potential problems and room for improvement, and output the equipment status level.

[0055] Preferably, the equipment monitoring unit includes a temperature sensor, a vibration sensor and a pressure sensor, and the temperature sensor, vibration sensor and pressure sensor are arranged at corresponding positions of the mechanical equipment according to the system installation manual.

[0056] Compared with the prior art, the above technical solution of the present invention has the following beneficial technical effects:

[0057] The present invention designs a mechanical equipment operation and maintenance management system and method. The method collects multi-source data through sensors arranged on the mechanical equipment, and then cleans and normalizes the data through a data preprocessing unit, and generates a coordinated temperature data packet, a coordinated vibration data packet and a coordinated pressure data packet. Then, an analysis and decision unit performs coordinated consistency detection on the temperature, vibration and pressure data in the coordinated temperature data packet, the coordinated vibration data packet and the coordinated pressure data packet, thereby avoiding the disorder of multi-source data, ensuring the reliability of the input data of the subsequent early warning model, and further ensuring the credibility of the model prediction results. Then, the analysis and decision unit uses the trained LSTM early warning model and the mechanical equipment operation state classification rule to output the operation state level of the mechanical equipment. The collaborative working unit implements corresponding operation and maintenance management operations based on the operation state level of the mechanical equipment. The present invention achieves the beneficial technical effect of improving the efficiency and reliability of the mechanical equipment operation and maintenance management system. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 This is a system architecture diagram of a mechanical equipment operation and maintenance management system proposed by the present invention;

[0059] Figure 2 This is a flow chart of a mechanical equipment operation and maintenance management method proposed by the present invention;

[0060] Figure 3 This is the training flow chart of LSTM early warning model. DETAILED DESCRIPTION

[0061] Embodiment 1, as Figure 1 As shown, a mechanical equipment operation and maintenance management system proposed by the present invention includes: an equipment monitoring unit, a data preprocessing unit, an analysis and decision-making unit, a collaborative work unit, a knowledge base and a visualization platform;

[0062] The equipment monitoring unit is used to monitor the operating status of the mechanical equipment. The equipment monitoring unit includes a temperature sensor, a vibration sensor and a pressure sensor to collect the operating status data of the mechanical equipment in real time;

[0063] The data preprocessing unit is used to perform cleaning, standardization and normalization operations on the data collected by the equipment monitoring unit to remove abnormal values ​​and noise;

[0064] The knowledge base stores historical maintenance records and mechanical equipment maintenance operation manuals. During the mechanical equipment maintenance process, maintenance personnel can access the knowledge base in the system through handheld mobile devices to obtain professional and compliant maintenance guidance and suggestions;

[0065] The analysis and decision-making unit is responsible for advanced data analysis, AI model training and reasoning, and integration with other systems. Based on the equipment monitoring data processed by the data preprocessing unit, the analysis and decision-making unit uses the internal fault warning model to conduct in-depth mining of equipment operation data, discover potential problems and room for improvement, and output the equipment status level.

[0066] The collaborative work unit is used to intelligently dispatch maintenance personnel and record operation and maintenance management logs;

[0067] The visualization platform is used to intuitively display the operating status data of mechanical equipment and the operating status level of mechanical equipment generated by the system.

[0068] Embodiment 2, as Figure 2 As shown, a mechanical equipment operation and maintenance management method proposed by the present invention adopts the mechanical equipment operation and maintenance management system in Example 1 to ensure the coordination and consistency of the monitoring data of the mechanical equipment operation and maintenance management system, and prevent the confusion of mechanical equipment operation status information caused by multi-source data, so as to better monitor and operate the mechanical equipment. The specific implementation steps are as follows:

[0069] Initialization phase:

[0070] (1) The equipment manager places the temperature sensor, vibration sensor and pressure sensor on the mechanical equipment to be monitored according to the system installation manual, and establishes the communication relationship between the temperature sensor, vibration sensor, pressure sensor and the data preprocessing unit respectively;

[0071] (2) The data preprocessing unit sets auxiliary generation parameters, including a, b, p, q, E, and G;

[0072] Where E is defined in the finite field F p The elliptic curve on which the point (x, y) satisfies y 2 ≡(x 3 +ax+b)modp, G=(x G ,y G ) is the base point of order q on the curve;

[0073] (3) The data preprocessing unit discloses the auxiliary generation parameters a, b, p, q, E and G to the analysis and decision-making unit;

[0074] Mechanical equipment operation and maintenance management stage:

[0075] S1, the equipment monitoring unit collects T through temperature sensors, vibration sensors and pressure sensors respectively. i Temperature data of mechanical equipment at the moment MT~T i 、Vibration data MV~T i And pressure data MP~T i, use IoT technology to convert the above temperature data MT~T i 、Vibration data MV~T i And pressure data MP~T i Transmitting to a data preprocessing unit;

[0076] S2, data preprocessing unit cleans, standardizes, normalizes and integrates the collected temperature data MT~T i 、Vibration data MV~T i And pressure data MP~T i , remove abnormal noise, improve data quality, and generate coordinated temperature, vibration and pressure data packets, which are generated as follows:

[0077] (1) How to generate coordinated temperature data packets:

[0078] S2-1, the data preprocessing unit selects a random number α∈[1,q-1] and calculates the coordination code Cc 1i =[α]G;

[0079] S2-2, select a random number β∈[1,q-1] and calculate the auxiliary data encapsulation code R 1i =[β]G;

[0080] S2-3, calculate the data encapsulation parameter Pe 1i =H(R 1i ,MT~T i ||T i );

[0081] Among them, || is the string concatenation symbol, and H is the hash function;

[0082] S2-4, calculate the data analysis parameter Pp 1i =(Pe 1i ×α+β)mod q, if Pp 1i =0, then return to S2-2;

[0083] S2-5, generate coordinated temperature data packet PMT~T i ={R 1i ,Pe 1i , Pp 1i , Cc 1i ,MT~T i}, the coordinated temperature data packet PMT~T i Transmit to analysis and decision-making unit;

[0084] (2) Method for generating coordinated vibration data packets:

[0085] S2-6, the data preprocessing unit selects a random number γ∈[1,q-1] and calculates the coordination code Cc 2i=[γ]G;

[0086] S2-7, select a random number δ∈[1,q-1], and calculate the auxiliary data encapsulation code R 2i =[δ]G;

[0087] S2-8, calculate the data encapsulation parameter Pe 2i =H(R 2i , MV~T i ||T i );

[0088] S2-9, calculate the data analysis parameter Pp 2i =(Pe 2i ×γ+δ)mod q, if Pp 2i =0, then return to S2-7;

[0089] S2-10, generate coordinated temperature data packet PMV~T i ={R 2i ,Pe 2i , Pp 2i , Cc 2i , MV~T i}, and the coordinated temperature data packet PMV~T i Transmit to analysis and decision-making unit;

[0090] (3) Generation method of coordinated pressure data packet:

[0091] S2-11, the data preprocessing unit selects a random number ε∈[1,q-1] and calculates the coordination code Cc 3i =[ε]G;

[0092] S2-12, select a random number λ∈[1,q-1], and calculate the auxiliary data encapsulation code R 3i =[λ]G;

[0093] S2-13, calculate the data encapsulation parameter Pe 3i =H(R 3i , MP~T i ||T i );

[0094] Among them, MP~T i For pressure sensor T i Pressure data collected at all times;

[0095] S2-14, calculate the data analysis parameter Pp 3i =(Pe 3i ×ε+λ)mod q, if Pp 3i =0, then return to S2-12;

[0096] S2-15, generate coordinated temperature data packet PMP~T i ={R 3i ,Pe 3i , Pp 3i , Cc 3i , MP~T i}, and the coordinated temperature data packet PMP~T i Transmit to analysis and decision-making unit;

[0097] S3, the analysis and decision unit respectively obtains the coordinated data packets PMT~T i 、PMV~T i 、PMP~T i The following parameters are extracted:

[0098] Auxiliary data encapsulation code R 1i , data encapsulation parameter Pe 1i , Data analysis parameter Pp 1i , coordination code Cc 1i 、Temperature data MT~T i ;

[0099] Auxiliary data encapsulation code R 2i , data encapsulation parameter Pe 2i , Data analysis parameter Pp 2i , coordination code Cc 2i 、Vibration data MV~T i ;

[0100] Auxiliary data encapsulation code R 3i , data encapsulation parameter Pe 3i , Data analysis parameter Pp 3i , coordination code Cc 3i , Pressure data MP~T i ;

[0101] The analysis decision unit then calculates the following auxiliary consistency verification parameters:

[0102] Pcv~Ⅰ~T i =[Pp 1i ]G+[Pp 2i ]G+[Pp 3i ]G;

[0103] Pcv~Ⅱ~T i =([Pe 1i ]Cc 1i +[Pe 2i ]Cc 2i +[Pe 3i ]Cc 3i )+(R 1i +R 2i +R3i );

[0104] If Pcv~Ⅰ~T i With Pcv~Ⅱ~T i If they are equal, it means that the temperature data MT~T received by the analysis and decision-making unit i 、Vibration data MV~T i And pressure data MP~T i It has coordination consistency, that is, the temperature data MT~T can be reasonably i 、Vibration data MV~T i And pressure data MP~T i Perform analysis and processing, and then the analysis and decision unit executes S4;

[0105] S4, the analysis and decision-making unit uses big data analysis technology to obtain prior knowledge from the knowledge base, conducts in-depth mining of equipment operation data, and then uses the real-time monitored temperature data MT~T i 、Vibration data MV~T i And pressure data MP~T i Input it into the trained LSTM early warning model to perform sliding window prediction, determine in real time whether there is a fault risk, and classify the fault level based on the output prediction value of the LSTM early warning model and the set mechanical equipment status classification rules;

[0106] Among them, Figure 3 As shown in the figure, the LSTM warning model construction and training process is as follows:

[0107] Model training data preprocessing: feature screening is performed on the original multi-sensor monitoring data, and feature data with obvious degradation trends are selected. The screened feature data are then divided into training and test data, respectively, and the data are normalized. The processed data are subjected to principal component analysis to achieve feature noise reduction and dimensionality reduction.

[0108] Model training and prediction: The retained principal components are divided into training sets and test sets. The test set is input into the LSTM network for training. The parameters are iteratively learned multiple times through the AME algorithm until the SMAE loss function value drops to the minimum and converges. The test set is input into the trained LSTM network for performance evaluation, and then the trained model is deployed in the analysis and decision-making unit.

[0109] Among them, PCA stands for principal component analysis, LSTM stands for long short-term memory network, AME stands for affine motion estimation algorithm, and SMAE stands for smoothed mean absolute error loss function (S SMAE ), which is calculated as follows:

[0110] ;

[0111] ;

[0112] In the formula, y i is the true value, is the predicted value, n is the number of samples;

[0113] The mechanical equipment status classification rules are shown in Table 1:

[0114] Table 1 Mechanical equipment status classification rules

[0115] Prediction Value Failure risk level Instruction [0，0.5] Low risk The device status is normal (0.5，0.7) Medium risk There is a certain probability that the device will fail. Further inspection is recommended. [0.7，1] High risk The equipment has a high probability of failure and an emergency warning needs to be issued immediately

[0116] If the model predicts that the status level of the mechanical equipment is high risk, the analysis and decision-making unit will immediately issue a high-level warning, generate maintenance suggestions based on the knowledge base, and output the equipment operation status report, which includes temperature data MT~T i 、Vibration data MV~T i , pressure data MP~T i , equipment failure type and maintenance suggestions, and then the analysis and decision-making unit transmits the equipment operation status report to the visualization platform. The display device on the visualization platform displays the temperature data MT~T of the mechanical equipment i 、Vibration data MV~T i , Pressure data MP~T i , equipment failure type and maintenance suggestions, to provide intuitive decision support information for the management, and on the other hand, transmit the equipment failure type and maintenance suggestions to the collaborative working unit, and then the collaborative working unit executes the following S5;

[0117] If the early warning model predicts that the status level of the mechanical equipment is low risk or medium risk, the analysis and decision-making unit outputs the equipment operation status report, which includes temperature data MT~T i 、Vibration data MV~T i , Pressure data MP~T i and the mechanical equipment status level, and then the analysis and decision-making unit transmits the equipment operation status report to the visualization platform, and the display device on the visualization platform displays the temperature data MT~T of the mechanical equipment i 、Vibration data MV~T i , Pressure data MP~T i and mechanical equipment condition level;

[0118] Among them, when the status level of mechanical equipment is medium risk, the analysis and decision-making unit will issue medium risk information, and the equipment manager will independently decide on the next mechanical equipment operation and maintenance operation, including but not limited to no intervention, equipment upgrade, formulation of equipment preventive maintenance plan or arrangement of inspection, maintenance, replacement of wearing parts;

[0119] S5, the collaborative work unit intelligently dispatches appropriate maintenance personnel based on the equipment failure type, maintenance personnel's skills and geographical location, automatically assigns maintenance tasks, and notifies maintenance personnel;

[0120] Maintenance personnel perform equipment maintenance operations based on equipment failure types, maintenance recommendations, and the mechanical equipment maintenance operation manual in the knowledge base, record the details of maintenance activities, update maintenance history records, and feed back actual results to the analysis and decision-making unit, which optimizes the LSTM early warning model based on the actual results.

[0121] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited thereto, and various changes can be made within the knowledge scope of technicians in the relevant technical field without departing from the purpose of the present invention.

Claims

1. A mechanical equipment operation and maintenance management method, characterized in that: The specific steps include: Step 1: The equipment detection unit collects the operating status data of the mechanical equipment, including temperature data, vibration data and pressure data; Step 2, the data preprocessing unit generates a coordinated temperature data packet, a coordinated vibration data packet and a coordinated pressure data packet, and transmits the coordinated temperature data packet, the coordinated vibration data packet and the coordinated pressure data packet to the analysis and decision-making unit; The coordinated temperature data packet is generated as follows: Step 2-1, the data preprocessing unit selects a random number α∈[1,q-1] and calculates the coordination code Cc 1i =[α]G; Where G is defined in the finite field F p A base point of order q on the elliptic curve E on ; Step 2-2, select a random number β∈[1,q-1] and calculate the auxiliary data encapsulation code R 1i =[β]G; Step 2-3, calculate the data encapsulation parameter Pe 1i =H(R 1i ,MT~T i ||T i ); Among them, || is the string concatenation symbol, H is the hash function, MT~T i is the temperature sensor T i Temperature data collected at all times; Step 2-4, calculate the data analysis parameter Pp 1i =(Pe 1i ×α+β)mod q, if Pp 1i =0, then return to step 2-2; Step 2-5, generate coordinated temperature data packet PMT~T i ={R 1i ,Pe 1i , Pp 1i , Cc 1i ,MT~T i }; The coordinated vibration data packet is generated as follows: Step 3-1, the data preprocessing unit selects a random number γ∈[1,q-1] and calculates the coordination code Cc 2i =[γ]G; Step 3-2, select a random number δ∈[1,q-1] and calculate the auxiliary data encapsulation code R 2i =[δ]G; Step 3-3, calculate the data encapsulation parameter Pe 2i =H(R 2i , MV~T i ||T i ); Among them, MV~T i T is the vibration sensor i Vibration data collected at all times; Step 3-4, calculate the data analysis parameter Pp 2i =(Pe 2i ×γ+δ)mod q, if Pp 2i =0, then return to step 3-2; Step 3-5, generate coordinated temperature data packet PMV~T i ={R 2i ,Pe 2i , Pp 2i , Cc 2i , MV~T i }; The coordinated pressure data packet is generated as follows: Step 4-1: The data preprocessing unit selects a random number ε∈[1, q-1] and calculates the coordination code Cc 3i =[ε]G; Step 4-2, select a random number λ∈[1,q-1] and calculate the auxiliary data encapsulation code R 3i =[λ]G; Step 4-3, calculate the data encapsulation parameter Pe 3i =H(R 3i , MP~T i ||T i ); Among them, MP~T i For pressure sensor T i Pressure data collected at all times; Step 4-4, calculate the data analysis parameter Pp 3i =(Pe 3i ×ε+λ)mod q, if Pp 3i =0, then return to step 4-2; Step 4-5, generate coordinated temperature data packet PMP~T i ={R 3i ,Pe 3i , Pp 3i , Cc 3i , MP~T i }; Step 3, the analysis and decision unit extracts temperature data, vibration data and pressure data from the coordinated temperature data packet, the coordinated vibration data packet and the coordinated pressure data packet, and detects the coordination consistency of the temperature data, the vibration data and the pressure data; The analysis and decision-making unit detects the consistency of the temperature data, vibration data and pressure data in the following steps: Step 5-1, the analysis and decision unit respectively obtains the coordinated temperature data packets PMT~T i , coordinated vibration data package PMV~T i and coordinated pressure data package PMP~T i The following parameters are extracted: Auxiliary data encapsulation code R 1i , data encapsulation parameter Pe 1i , Data analysis parameter Pp 1i , coordination code Cc 1i 、Temperature data MT~T i ; Auxiliary data encapsulation code R 2i , data encapsulation parameter Pe 2i , Data analysis parameter Pp 2i , coordination code Cc 2i 、Vibration data MV~T i ; Auxiliary data encapsulation code R 3i , data encapsulation parameter Pe 3i , Data analysis parameter Pp 3i , coordination code Cc 3i , pressure data MP~T i ; Step 5-2, calculate the following auxiliary consistency verification parameters: Pcv~Ⅰ~T i =[Pp 1i ]G+[Pp 2i ]G+[Pp 3i ]G; Pcv~Ⅱ~T i =([Pe 1i ]Cc 1i +[Pe 2i ]Cc 2i +[Pe 3i ]Cc 3i )+(R 1i +R 2i +R 3i ); Step 5-3, if Pcv~Ⅰ~T i With Pcv~Ⅱ~T i If they are equal, it means that the temperature data MT~T received by the analysis and decision-making unit i 、Vibration data MV~T i And pressure data MP~T i Have coordination and consistency; Step 4: The analysis and decision-making unit inputs the real-time monitored temperature data, vibration data, and pressure data into the trained long short-term memory network LSTM early warning model to determine in real time whether there is a fault risk, and classifies the fault level based on the output prediction value of the LSTM early warning and the set mechanical equipment status classification rules; If the fault level is classified as high risk, the analysis and decision-making unit immediately issues a high-level warning, generates maintenance suggestions, and outputs a device operation status report. The analysis and decision-making unit then transmits the device operation status report to the visualization platform, and transmits the device fault type and maintenance suggestions to the collaborative work unit, which then executes step 5. When the fault level is classified as low risk or medium risk, the analysis and decision unit outputs an equipment operation status report, which includes temperature data, vibration data, pressure data and mechanical equipment status level. The analysis and decision unit then transmits the equipment operation status report to the visualization platform. When the mechanical equipment status level is medium risk, the analysis and decision unit issues a medium risk message, and the equipment manager independently decides on the next mechanical equipment operation and maintenance operation, including no intervention, equipment upgrade, formulation of a preventive maintenance plan for the equipment, or arrangement for inspection, maintenance, and replacement of wearing parts; Step 5: The collaborative work unit intelligently dispatches maintenance personnel based on the equipment failure type, maintenance personnel's skills and geographical location, automatically assigns maintenance tasks, and notifies maintenance personnel; Maintenance personnel perform equipment maintenance operations based on equipment failure types, maintenance recommendations, and the mechanical equipment maintenance operation manual in the knowledge base, record details of maintenance activities, update maintenance history records, and feed back actual results to the analysis and decision-making unit.

2. A mechanical equipment operation and maintenance management system, which is applicable to a mechanical equipment operation and maintenance management method according to claim 1, characterized in that: include: Equipment monitoring unit, data preprocessing unit, analysis and decision-making unit, collaborative work unit, knowledge base and visualization platform; The equipment monitoring unit is used to monitor the operating status of the mechanical equipment and collect the operating status data of the mechanical equipment in real time; The data preprocessing unit is used to perform cleaning, standardization and normalization operations on the data collected by the equipment monitoring unit to remove abnormal values ​​and noise; The knowledge base stores historical maintenance records and mechanical equipment maintenance operation manuals. During the mechanical equipment maintenance process, maintenance personnel access the knowledge base in the system through handheld mobile devices to obtain professional and compliant maintenance guidance and suggestions; The analysis and decision-making unit is responsible for advanced data analysis, AI model training and reasoning, and integration with other systems; The collaborative working unit is used to intelligently dispatch maintenance personnel, record operation and maintenance management logs, and optimize the LSTM early warning model based on the actual results fed back by the maintenance personnel; The visualization platform is used to intuitively display the operating status data of the mechanical equipment and the operating status level of the mechanical equipment generated by the system.

3. A mechanical equipment operation and maintenance management system according to claim 2, characterized in that: The analysis and decision-making unit, based on the equipment operation status data processed by the data preprocessing unit, uses the trained LSTM early warning model to conduct in-depth mining of the equipment operation data, discover potential problems and room for improvement, and output the equipment status level.

4. A mechanical equipment operation and maintenance management system according to claim 2, characterized in that: The equipment monitoring unit includes a temperature sensor, a vibration sensor and a pressure sensor, and the temperature sensor, vibration sensor and pressure sensor are arranged at corresponding positions of the mechanical equipment according to the system installation manual.

Images