Mine car equipment health management system and method based on encryption algorithm

Abstract

The invention discloses a mine car equipment health management system and method based on an encryption algorithm. Comprising the following steps: performing key generation and identity registration by using a trusted mechanism; constructing a mine car dynamic model, a fault prediction model and a mine car control optimization model by using a cloud data center; the remote monitoring device is used for encrypting and signing real-time mine car monitoring data and uploading the real-time mine car monitoring data to the cloud data center; performing identity authentication and decryption by using a cloud data center; generating dynamic data by using the mine car dynamic model; performing fault prediction by using the fault prediction model, and performing mine car control optimization by using the mine car control optimization model; the real-time mine car control optimization strategy is encrypted and returned to the remote monitoring device; and generating a real-time mine car control instruction. According to the method, the problems of low data security, low protection level, low fault prediction efficiency, poor accuracy and low practicability in the prior art are solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of equipment health management and relates to a mine car equipment health management system and method, and in particular relates to a mine car equipment health management system and method based on an encryption algorithm. Background Art

[0002] The mine car equipment health management system is an advanced technology used to monitor the operating status of mine cars, predict potential failures, and determine maintenance time. The system usually integrates a variety of sensors, data acquisition, processing and analysis algorithms, as well as artificial intelligence and machine learning technologies. Its purpose is to maximize the operating efficiency and safety of mine cars, while reducing downtime, extending equipment life, and reducing maintenance costs. It is one of the key technologies for realizing intelligent, networked, and precise maintenance of heavy machinery and equipment such as mine cars. By applying the mine car equipment health management system, the economic benefits and operational safety of mine cars have been significantly improved.

[0003] However, the mine car equipment health management system still has the following defects:

[0004] 1) During the data transmission process of the mine vehicle equipment health management system, the data often exists in plain text, which is easy to be intercepted or disguised by malicious attacks, resulting in data leakage or attacks on the cloud data center, low data security, and low protection level of the cloud data center;

[0005] 2) The artificial intelligence technology used in the mine car equipment health management system is backward, resulting in low efficiency and poor accuracy in fault prediction, and lacks the function of remote control optimization of mine cars. It has low practicality and cannot meet the actual needs of intelligent control of mine cars. Summary of the invention

[0006] In order to solve the problems of low data security, low protection level, low fault prediction efficiency, poor accuracy and low practicality in the prior art, the present invention aims to provide a mine car equipment health management system and method based on encryption algorithm.

[0007] The technical solution adopted by the present invention is:

[0008] 1. A mine car equipment health management system based on encryption algorithm

[0009] The system includes a cloud data center, a trusted institution and several remote monitoring devices.

[0010] The cloud data center and the trusted institution are respectively connected to a plurality of remote monitoring devices in communication, and the cloud data center is connected to the trusted institution in communication, and the plurality of remote monitoring devices are arranged one by one at the corresponding plurality of mining vehicles, and each remote monitoring device is electrically connected to the control system of the corresponding mining vehicle;

[0011] The trusted institution is used to generate keys and register identities for all remote monitoring devices, obtain the public-private key pair and signature information of each remote monitoring device; and send the private key and signature information in the public-private key pair to the corresponding remote monitoring device, and send the public key in the public-private key pair to the cloud data center;

[0012] A remote monitoring device is used to collect real-time mine car monitoring data of the mine car and issue a data accuracy warning based on the mine car monitoring data, and then encrypt the collected real-time mine car monitoring data and upload it to the cloud data center with the signature data; and decrypt the encrypted real-time mine car control optimization strategy issued by the cloud data center to generate a real-time mine car control instruction, and apply the real-time mine car control instruction to the control system of the corresponding mine car;

[0013] The cloud data center is used to decrypt the encrypted real-time mine car monitoring data sent by the remote monitoring device, perform fault prediction and mine car control optimization, obtain the real-time mine car control optimization strategy, and encrypt it and send it to the corresponding remote monitoring device.

[0014] The cloud data center includes an identity authentication unit, a first data decryption unit, a data preprocessing unit, a model building unit, a dynamic data generation unit, a fault prediction unit, a mine car control optimization unit and a first data encryption unit which are connected in sequence. The identity authentication unit is respectively connected to a trusted institution and a plurality of remote monitoring devices in communication, the first data decryption unit is connected to a trusted institution in communication, and the first data encryption unit is respectively connected to a trusted institution and a plurality of remote monitoring devices in communication; the dynamic data generation unit is used to generate different dynamic data of a mine car according to input mine car monitoring data; the fault prediction unit is used to perform fault prediction according to the mine car monitoring data and different dynamic data of the mine car; the mine car control optimization unit is used to generate a real-time mine car control optimization strategy according to the fault prediction result.

[0015] The remote monitoring device includes a monitoring data acquisition unit, a second data encryption unit, a second data decryption unit and a control instruction generation unit. The monitoring data acquisition unit and the control instruction generation unit are both deployed at the mining car. The monitoring data acquisition unit is connected to the second data encryption unit, and the control instruction generation unit is connected to the second data decryption unit. The second data encryption unit and the second data decryption unit are both communicated with the cloud data center and the trusted organization.

[0016] The monitoring data acquisition unit includes a sensor module, a data acquisition unit and a data comparison unit. The sensor module is arranged at the corresponding mine car, and the data acquisition unit and the control instruction generation unit are electrically connected to the control system of the corresponding mine car; the sensor module is used to collect the first real-time mine car monitoring data of the mine car; the data acquisition unit is used to collect the second real-time mine car monitoring data detected by the control system of the mine car itself; the data comparison unit is used to compare and analyze the first real-time mine car monitoring data and the second real-time mine car monitoring data to obtain a data error, and if the data error is greater than a preset error threshold, an alarm signal is issued.

[0017] The sensor module includes a speed sensor, a steering angle sensor, an electrical sensor and a weight sensor.

[0018] 2. A method for health management of mine car equipment based on encryption algorithm

[0019] Deploy corresponding remote monitoring devices on different mining vehicles, use a trusted institution to generate keys and register identities for all remote monitoring devices, obtain the public-private key pair and signature information of each remote monitoring device, then send the private key and signature information in each public-private key pair to the corresponding remote monitoring device, and send the public key in the public-private key pair to the cloud data center;

[0020] The remote monitoring device encrypts the collected real-time mining car monitoring data and sends it to the cloud data center, where it is stored;

[0021] For the stored historical mine car monitoring data, the cloud data center pre-processes the historical mine car monitoring data to obtain the pre-processed historical mine car monitoring data, and then builds the mine car dynamic model, fault prediction model and mine car control optimization model according to the pre-processed historical mine car monitoring data;

[0022] For new real-time mine car monitoring data, the cloud data center calls a trusted organization to authenticate the signature data. After the authentication is passed, the encrypted real-time mine car monitoring data is decrypted according to the public key of the remote monitoring device to obtain the decrypted real-time mine car monitoring data; then, different dynamic data of the mine car, fault prediction and real-time mine car control optimization are generated according to the decrypted real-time mine car monitoring data, and the real-time mine car control optimization strategy is obtained and sent to the remote monitoring device after encryption;

[0023] The remote monitoring device decrypts the encrypted real-time mine car control optimization strategy according to the private key to obtain the decrypted real-time mine car control optimization strategy, and then generates a real-time mine car control instruction according to the decrypted real-time mine car control optimization strategy, and sends the real-time mine car control instruction to the control system of the corresponding mine car.

[0024] The method of generating different dynamic data of the mine car, fault prediction and real-time mine car control optimization according to the decrypted real-time mine car monitoring data is specifically as follows:

[0025] Firstly, the mine car dynamic model is used to generate dynamic data for the decrypted real-time mine car monitoring data to obtain real-time mine car dynamic data, and the real-time mine car dynamic data is associated with the corresponding decrypted real-time mine car monitoring data to obtain real-time comprehensive data;

[0026] The fault prediction model is then used to predict the real-time comprehensive data to obtain the real-time fault prediction results; finally, based on the real-time fault prediction results, the mine car control optimization model is used to optimize the mine car control to obtain the real-time mine car control optimization strategy.

[0027] The method uses a trusted institution to generate keys and register identities for all remote monitoring devices, obtains a public-private key pair and signature information for each remote monitoring device, sends the private key and signature information in the public-private key pair to the corresponding remote monitoring device, and sends the public key in the public-private key pair to the cloud data center, including the following steps:

[0028] Using a cloud data center, collect the communication addresses, attribute information, and device IDs of all remote monitoring devices, and send the communication addresses, attribute information, and device IDs to a trusted institution;

[0029] Use a trusted institution to generate keys and register identities for all remote monitoring devices based on attribute information and device IDs, and obtain public-private key pairs and signature information for each remote monitoring device;

[0030] According to the communication address, the private key and signature information in the public-private key pair are sent to the corresponding remote monitoring device, and the public key in the public-private key pair is sent to the cloud data center.

[0031] For the stored historical mine car monitoring data, the cloud data center pre-processes the historical mine car monitoring data to obtain the pre-processed historical mine car monitoring data, and then constructs the mine car dynamic model, the fault prediction model and the mine car control optimization model according to the pre-processed historical mine car monitoring data, including the following steps:

[0032] In the cloud data center, based on some pre-processed historical mine car monitoring data, a mine car dynamic model is constructed using a state analysis method, and some historical mine car dynamic data are generated;

[0033] The pre-processed historical mine car monitoring data and historical mine car dynamic data are associated, and clustering is performed with fault information as the clustering target to obtain several cluster centers and cluster clusters;

[0034] According to the fault information of each cluster center, a corresponding real fault label is added to each cluster center, and the real fault label is diffused to the corresponding cluster cluster to obtain several fault prediction samples;

[0035] Based on several fault prediction samples, a fault prediction model is constructed using a deep learning algorithm, and several historical fault prediction results are generated;

[0036] According to several historical fault prediction results and preset mine car control optimization strategies, a mine car control optimization model is constructed using reinforcement learning algorithm.

[0037] The mine car dynamic model includes a mine car power dynamic model, a mine car electrical dynamic model, a mine car load performance dynamic model and a mine car energy consumption dynamic model.

[0038] The beneficial effects of the present invention are:

[0039] The present invention discloses a mine car equipment health management system and method based on encryption algorithm. The asymmetric encryption algorithm is adopted to transmit the mine car monitoring data in ciphertext form during data transmission, thereby improving data security and avoiding data leakage. In combination with digital identity authentication technology, the protection level of the cloud data center is strengthened, data security is further improved, and malicious attack invasion is avoided. The mine car dynamic model characterizes the dynamic operation state of the mine car, thereby improving the comprehensiveness of mine car monitoring. The fault prediction model constructed by the deep learning algorithm combines the mine car dynamic data output by the mine car dynamic model and the static mine car monitoring data, thereby improving the efficiency and accuracy of fault prediction. The mine car control optimization model constructed by the reinforcement learning algorithm can generate automatic and adaptive mine car control optimization strategies according to the fault prediction situation, thereby improving the operation condition of the mine car, avoiding and processing faults, thereby improving the practicality and the intelligence of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a structural block diagram of the mining vehicle equipment health management system based on the encryption algorithm in the present invention.

[0041] Figure 2 It is a flowchart of the method of the present invention. DETAILED DESCRIPTION

[0042] The present invention will be further explained below in conjunction with the accompanying drawings and specific embodiments.

[0043] Example 1

[0044] like Figure 1As shown, this embodiment provides a mining car equipment health management system based on an encryption algorithm, including a cloud data center, a trusted institution and a plurality of remote monitoring devices, the cloud data center and the trusted institution are respectively connected to the plurality of remote monitoring devices in communication, and the cloud data center is connected to the trusted institution in communication, the plurality of remote monitoring devices are arranged at a plurality of mining cars in a one-to-one correspondence, and each remote monitoring device is electrically connected to the control system of the corresponding mining car;

[0045] The cloud data center is used to build a mine car dynamic model, a fault prediction model and a mine car control optimization model; perform identity authentication on the signature data, and after the identity authentication is passed, decrypt the encrypted real-time mine car monitoring data to obtain the decrypted real-time mine car monitoring data; use the fault prediction model to perform fault prediction on the decrypted real-time mine car monitoring data to obtain the real-time fault prediction result, and use the mine car control optimization model to perform mine car control optimization according to the real-time fault prediction result to obtain the real-time mine car control optimization strategy; encrypt the real-time mine car control optimization strategy according to the public key of the remote monitoring device to obtain the encrypted real-time mine car control optimization strategy, and return the encrypted real-time mine car control optimization strategy to the corresponding remote monitoring device;

[0046] The trusted institution is used to generate keys and register identities for all remote monitoring devices, obtain the public-private key pair and signature information of each remote monitoring device, send the private key and signature information in the public-private key pair to the corresponding remote monitoring device, and send the public key in the public-private key pair to the cloud data center;

[0047] The remote monitoring device is used to collect real-time mine car monitoring data of the mine car, encrypt and sign the real-time mine car monitoring data according to the private key and signature information, obtain the encrypted real-time mine car monitoring data and signature data, and upload the encrypted real-time mine car monitoring data and signature data to the cloud data center; decrypt the encrypted real-time mine car control optimization strategy according to the private key, obtain the decrypted real-time mine car control optimization strategy, generate real-time mine car control instructions according to the decrypted real-time mine car control optimization strategy, and send the real-time mine car control instructions to the control system of the corresponding mine car.

[0048] Preferably, the cloud data center includes an identity authentication unit, a first data decryption unit, a data preprocessing unit, a model building unit, a dynamic data generation unit, a fault prediction unit, a mine car control optimization unit and a first data encryption unit connected in sequence, the identity authentication unit is respectively connected to the trusted institution and a plurality of remote monitoring devices for communication, the first data decryption unit is connected to the trusted institution for communication, and the first data encryption unit is respectively connected to the trusted institution and a plurality of remote monitoring devices for communication;

[0049] An identity authentication unit is used to call a trusted institution to authenticate the signature data;

[0050] A first data decryption unit is used to decrypt the encrypted real-time mining car monitoring data according to the public key of the remote monitoring device to obtain the decrypted real-time mining car monitoring data;

[0051] A data preprocessing unit, used for preprocessing a number of collected historical mine car monitoring data to obtain a number of preprocessed historical mine car monitoring data;

[0052] A model building unit, used for building a mine car dynamic model, a fault prediction model and a mine car control optimization model according to a number of pre-processed historical mine car monitoring data;

[0053] A dynamic data generating unit is used to generate dynamic data for the decrypted real-time mine car monitoring data using a mine car dynamic model to obtain real-time mine car dynamic data, and associate the real-time mine car dynamic data with the corresponding decrypted real-time mine car monitoring data to obtain real-time comprehensive data;

[0054] A fault prediction unit, used to use a fault prediction model to perform fault prediction on real-time comprehensive data to obtain a real-time fault prediction result;

[0055] A mine car control optimization unit is used to optimize the mine car control according to the real-time fault prediction results and use the mine car control optimization model to obtain a real-time mine car control optimization strategy;

[0056] The first data encryption unit is used to encrypt the real-time mine car control optimization strategy according to the public key of the remote monitoring device, obtain the encrypted real-time mine car control optimization strategy, and return the encrypted real-time mine car control optimization strategy to the corresponding remote monitoring device.

[0057] Preferably, the dynamic data generating unit is provided with a mine car dynamic model, the fault prediction unit is provided with a fault prediction model, and the mine car control optimization unit is provided with a mine car control optimization model.

[0058] The mine car dynamic model includes the mine car power dynamic model, the mine car electrical dynamic model, the mine car load performance dynamic model and the mine car energy consumption dynamic model, which are used to characterize the mine car power dynamic state, electrical dynamic state, load performance dynamic state and energy consumption dynamic state. According to the input mine car monitoring data, the mine car dynamic model is used to dynamically generate corresponding dynamic data. Compared with static data analysis, dynamic model characterization can improve the accuracy of fault analysis;

[0059] The fault prediction model is built based on a deep learning algorithm. The deep learning algorithm uses a deep structure to mine the potential relationship between the mine car monitoring data and the mine car dynamic data and the fault situation, and can discover potential fault risks, make predictions and alarms in advance.

[0060] The mine car control optimization model is built based on the reinforcement learning algorithm. Through the training of intelligent agents, it accumulates mine car control optimization experience and can generate automatic and intelligent mine car control optimization strategies based on real-time fault prediction results to achieve early processing of potential risks.

[0061] Preferably, the remote monitoring device includes a sensor module, a data acquisition unit, a data comparison unit, a second data encryption unit, a second data decryption unit and a control instruction generating unit which are connected in sequence. The sensor module is arranged at the corresponding mine car, the data acquisition unit and the control instruction generating unit are both electrically connected to the control system of the corresponding mine car, and the second data encryption unit and the second data decryption unit are respectively communicated with the cloud data center and the trusted organization.

[0062] A sensor module, used for collecting first real-time mine car monitoring data of the mine car;

[0063] A data acquisition unit, used for acquiring second real-time mine car monitoring data detected by the control system of the mine car itself;

[0064] The data comparison unit is used to compare and analyze the first real-time mine car monitoring data and the second real-time mine car monitoring data to obtain the data error. If the data error is less than the preset error threshold, the real-time mine car monitoring data collection is relatively accurate. If the data error is greater than the preset error threshold, the real-time mine car monitoring data collection is inaccurate, and an alarm signal is issued to notify the staff to perform error calibration, thereby improving the accuracy of real-time mine car monitoring data collection.

[0065] The second data encryption unit is used to encrypt and sign the real-time mine car monitoring data according to the private key and the signature information, obtain the encrypted real-time mine car monitoring data and the signature data, and upload the encrypted real-time mine car monitoring data and the signature data to the cloud data center;

[0066] The second data decryption unit is used to decrypt the encrypted real-time mine car control optimization strategy according to the private key to obtain the decrypted real-time mine car control optimization strategy;

[0067] The control instruction generating unit is used to generate a real-time mine car control instruction according to the decrypted real-time mine car control optimization strategy, and send the real-time mine car control instruction to the control system of the corresponding mine car.

[0068] Preferably, the sensor module includes a speed sensor, a steering angle sensor, an electrical sensor and a weight sensor.

[0069] Example 2

[0070] like Figure 2 As shown, this embodiment provides a mining vehicle equipment health management system method based on an encryption algorithm, and the method includes the following steps:

[0071] S1: Use a trusted institution to generate keys and register identities for all remote monitoring devices, obtain a public-private key pair and signature information for each remote monitoring device, send the private key and signature information in the public-private key pair to the corresponding remote monitoring device, and send the public key in the public-private key pair to the cloud data center, including the following steps:

[0072] S1-1: Use the cloud data center to collect the communication addresses, attribute information and device IDs of all remote monitoring devices, and send the communication addresses, attribute information and device IDs to a trusted institution;

[0073] S1-2: Use a trusted institution to generate keys and register identities for all remote monitoring devices based on attribute information and device IDs, and obtain public-private key pairs and signature information for each remote monitoring device, including the following steps:

[0074] S1-2-1: Initialize the key to generate the public parameter GP, master key MSK and initial key PK. The formula is:

[0075]

[0076] Where GP is the public parameter; MSK is the master key; PK is the initial key; a is the integer domain Z p Random number; H 1 , H 2 , H 3 , H 4 , H 5 , H 6 , H u Both are target hash functions; g, g 1 , g a are all random numbers that are generators of the cyclic group G; e(g,g) a is a bilinear map of random numbers g;

[0077] S1-2-2: Based on the public parameter GP, the master key MSK, the initial key PK and the attribute information V of the remote monitoring device u , generate the corresponding public-private key pair of the remote monitoring device, the formula is:

[0078]

[0079] In the formula, SK u is the private key of the remote monitoring device u; b is the integer domain Z p Random number; L u , K is the private key parameter of the remote monitoring device u; H 3is the target hash function of the public parameter GP; u is the indication of the remote monitoring device; MSK is the master key; PK is the initial key; PK u is the public key of the remote monitoring device u; g b , g a , g ab is the random number of the generator of the cyclic group G; V u is the attribute information of the remote monitoring device u;

[0080] S1-2-3: Perform real-name authentication based on the private key in the public-private key pair and the corresponding device ID to obtain the signature information of the corresponding remote monitoring device. The formula is:

[0081]

[0082] In the formula, k" is a random number; K u is the registration parameter of the remote monitoring device u; KID u KID is the signature ID of the remote monitoring device u; u and the corresponding K u The signature information {K u ,KID u}; H 1 Hash function for the target hash; ID u SK is the device ID of the remote monitoring device u; u is the private key of the remote monitoring device u;

[0083] S1-3: according to the communication address, the private key and signature information in the public-private key pair are sent to the corresponding remote monitoring device, and the public key in the public-private key pair is sent to the cloud data center;

[0084] S2: using the cloud data center, collecting some historical mine car monitoring data, preprocessing some historical mine car monitoring data, obtaining some preprocessed historical mine car monitoring data, and constructing a mine car dynamic model, a fault prediction model and a mine car control optimization model according to some preprocessed historical mine car monitoring data, including the following steps:

[0085] S2-1: using the cloud data center, collecting a number of historical mine car monitoring data within a period of time, preprocessing the number of historical mine car monitoring data, and obtaining a number of preprocessed historical mine car monitoring data;

[0086] S2-2: Based on some pre-processed historical mine car monitoring data, a state analysis method is used to construct a mine car dynamic model and generate some historical mine car dynamic data;

[0087] The mine car dynamic model includes the mine car power dynamic model, the mine car electrical dynamic model, the mine car load performance dynamic model and the mine car energy consumption dynamic model;

[0088] The formula of the mine car dynamic model is:

[0089]

[0090] Where v is the final velocity of the minecart; u is the initial velocity; a' is the acceleration; w is the final angular velocity of the minecart; w 0 is the initial angular velocity; α' is the angular acceleration; t is the time indication;

[0091] The formula of the mine car electrical dynamic model is:

[0092]

[0093] Where, P' is the operating power of the mine car; F 1 (*) is the power calculation function; I is the operating current; V is the operating voltage; R is the operating resistance of the mine car; F 2 (*) is the running current calculation function;

[0094] The formula of the dynamic model of mine car load performance is:

[0095] F eff =m'·g'-f

[0096] In the formula, F eff is the effective force on the mine car; m' is the mass of the mine car; g' is the acceleration of gravity; f is the resultant force on the mine car;

[0097] The formula of the dynamic model of mine car energy consumption is:

[0098] E'=0.5m'v 2 +m'g'h

[0099] Where E' is the total energy of the mine car; v is the final velocity of the mine car; m' is the mass of the mine car; g' is the acceleration due to gravity; h is the height of the mine car;

[0100] S2-3: Correlate the pre-processed historical mine car monitoring data with the historical mine car dynamic data, and perform clustering processing with fault information as the clustering target to obtain several cluster centers and cluster clusters;

[0101] S2-4: According to the fault information of the cluster center, add the corresponding real fault label to each cluster center, and diffuse the real fault label to the corresponding cluster cluster to obtain several fault prediction samples;

[0102] S2-5: Based on several fault prediction samples, a fault prediction model is constructed using the Random Forest (RF)-Multilayer Perceptron (MLP) algorithm, and several historical fault prediction results are generated;

[0103] The RF structure uses the internal Classification And Regression Tree (CART) to screen the key features of the input data and extract the key features related to fault prediction, thereby improving the recognition accuracy and efficiency. The MLP network is a fully connected neural network, including an input layer, a hidden layer, and an output layer. The input layer receives the key features screened by the RF structure, the hidden layer is used to extract the fault information of the features, and the output layer is used to make predictions based on the fault information.

[0104] S2-6: Based on several historical fault prediction results and the preset mine car control optimization strategy, a mine car control optimization model is constructed using a deep Q network (DQN), including the following steps:

[0105] S2-6-1: According to the mine cart control problem, set up the simulation environment for the DQN algorithm to generate the mine cart control optimization strategy, and build the intelligent agent and experience replay pool;

[0106] S2-6-2: Define the state space of the DQN algorithm based on the historical fault prediction results, and define the action space of the DQN algorithm based on the preset mine car control optimization strategy;

[0107] S2-6-3: Define a reward function based on the consequences of several minecart control optimization actions in the action space;

[0108] S2-6-4: Construct the input layer, several hidden layers, and output layer of the deep Q network, connect the input layer to the state space, and connect the output layer to the action space;

[0109] S2-6-5: Based on several historical fault prediction results and preset mine car control optimization strategies, the deep Q network and the intelligent agent are optimized and trained to build a mine car control optimization model, and the generated mine car control optimization strategy generation experience is stored in the experience replay pool;

[0110] S3: Use the remote monitoring device to collect the real-time monitoring data of the mine car, encrypt and sign the real-time monitoring data according to the private key and signature information, obtain the encrypted real-time monitoring data and signature data, and upload the encrypted real-time monitoring data and signature data to the cloud data center;

[0111] The formula is:

[0112] M u =E(SK u ,m u )

[0113] Where M u is the encrypted real-time mining car monitoring data of the remote monitoring device u; E(*) is the asymmetric encryption function; m u Real-time mining car monitoring data from remote monitoring device u; SK u is the private key of the remote monitoring device u; u is the indication quantity of the remote monitoring device;

[0114]

[0115] In the formula, r is a random number; is the prime order; P is the base point of the prime domain; H 2 is the target hash function; K u is the registration parameter of the remote monitoring device u; KID u is the signature ID of the remote monitoring device u; M u It is the encrypted real-time mining car monitoring data of the remote monitoring device u; ID u is the device ID of the remote monitoring device u; the signature information is {ID u ,M u ,γ'={K u ,R u ,B u}}; R u ,B u ,γ' are the signature parameters of the remote monitoring device u;

[0116] S4: Use the cloud data center to call the trusted organization to authenticate the signature data. After the authentication is passed, the encrypted real-time mining car monitoring data is decrypted according to the public key of the remote monitoring device to obtain the decrypted real-time mining car monitoring data;

[0117] The formula is:

[0118] β u B u P=β u H 2 (R u ,M u ,ID u ,K u )R u +β u K u +β u H 1 (ID u ,K u )PK u

[0119] In the formula, β u PK is the identity authentication parameter of the remote monitoring device u; u is the public key of the remote monitoring device u; if the left formula is equal to the right formula, the identity authentication is successful;

[0120] m u =E - (PK u ,M u )

[0121] In the formula, m u The decrypted real-time mining car monitoring data of the remote monitoring device u; E - (*) is an asymmetric decryption function; PK u is the public key of the remote monitoring device u; M u The encrypted real-time mining vehicle monitoring data of the remote monitoring device u;

[0122] S5: using the mine car dynamic model, generating dynamic data for the decrypted real-time mine car monitoring data to obtain real-time mine car dynamic data, and associating the real-time mine car dynamic data with the corresponding decrypted real-time mine car monitoring data to obtain real-time comprehensive data;

[0123] S6: Use the fault prediction model to perform fault prediction on the real-time comprehensive data to obtain real-time fault prediction results. According to the real-time fault prediction results, use the mine car control optimization model to perform mine car control optimization to obtain a real-time mine car control optimization strategy, including the following steps:

[0124] S6-1: Use the trained RF structure in the fault prediction model to extract the feature contribution of several real-time candidate features in the real-time comprehensive data;

[0125] The formula is:

[0126]

[0127] In the formula, is the feature contribution of the jth real-time candidate feature; is the feature contribution of the jth real-time candidate feature in the i-th tree of the random forest; i is the CART tree indicator; j is the real-time candidate feature indicator; n is the total number of CARTs;

[0128]

[0129] In the formula, GI m , GI l , GI r is the Gini index of CART tree node m, node l and node r of random forest; p mkis the proportion of category k in CART tree node m; K is the total number of categories; m, l, r are node indicators; k is the category indicator;

[0130] S6-2: normalizing the feature contributions of the plurality of real-time candidate features to obtain a plurality of corresponding normalized feature contributions;

[0131] The formula is:

[0132]

[0133] Where VIM j is the contribution of the feature after normalization; J is the total number of real-time candidate features;

[0134] S6-3: Generate feature selection standard values ​​for several real-time candidate features according to the normalized feature contribution;

[0135] The formula is:

[0136]

[0137] In the formula, CFC j VIM is the feature selection standard value for the jth real-time candidate feature; j' is the normalized feature contribution of the j'th real-time candidate feature; j' is the indicator of the candidate feature;

[0138] S6-4: sorting the real-time candidate features in descending order according to the feature selection standard value, and selecting the first N real-time candidate features as real-time key features to obtain N real-time key features, where N is the total number of real-time key features;

[0139] S6-5: Perform feature fusion according to the N real-time key features to obtain real-time fusion features, and perform fault prediction according to the real-time fusion features to obtain real-time fault prediction results;

[0140] S6-6: According to the real-time fault prediction results, extract several matching mine car control optimization strategies from the experience playback pool of the mine car control optimization model to generate experience;

[0141] S6-7: Based on the experience generated by several mine car control optimization strategies, the action space of the mine car control optimization model is updated to obtain the updated action space A'=[a' 1 ,...,a' j" ,...,a' I ], where a' j" is the updated j-th "action value", j" is the action indicator;

[0142] S6-8: According to the real-time fault prediction results, the state space of the mine car control optimization model is updated to obtain the updated state space S' = [s' 1 ,...,s' i" ,...,s' I ], where s' i" is the updated i-th state value, i is the state indicator;

[0143] S6-9: Update the state space S' = [s' 1 ,...,s' i' ,...,s' I ] as the input of the minecart control optimization model, using the minecart control optimization model to generate an updated action space A' = [a' 1 ,...,a' j' ,...,a' I ] is the Q value of each possible action;

[0144] S6-10: Use the reward function to obtain the reward value of each possible action in the updated action space, and update the Q value of the possible action according to the reward value to obtain the updated Q value of the possible action;

[0145] The formula is:

[0146] Q(s' p' ,a' p' )=(1-α")·Q(s p' ,a p' )+α"·(R(s p' ,a p' ,s' p' )+γ·Q max (s p' ,a p' ))

[0147] In the formula, Q(s' p' ,a' p' ) is the updated state value s' p' and the updated action value a' p' The corresponding updated Q value; Q(s p' ,a p' ) is the state value s p' and action value a p' The corresponding predicted Q value; α" is the learning rate; Q max (s p' ,a p' ) is the highest predicted Q value;

[0148] S6-11: Repeat the above steps until the iteration number threshold is reached, and use the greedy strategy to take the possible action corresponding to the highest updated Q value as the execution action;

[0149] S6-12: Outputting the execution action as a real-time mine car control optimization strategy;

[0150] S7: Encrypt the real-time mine car control optimization strategy according to the public key of the remote monitoring device to obtain the encrypted real-time mine car control optimization strategy, and return the encrypted real-time mine car control optimization strategy to the corresponding remote monitoring device;

[0151] S8: Using a remote monitoring device, decrypt the encrypted real-time mine car control optimization strategy according to a private key to obtain the decrypted real-time mine car control optimization strategy, generate a real-time mine car control instruction according to the decrypted real-time mine car control optimization strategy, and send the real-time mine car control instruction to the control system of the corresponding mine car.

[0152] The present invention discloses a mine car equipment health management system and method based on encryption algorithm. The asymmetric encryption algorithm is adopted to transmit the mine car monitoring data in ciphertext form during data transmission, thereby improving data security and avoiding data leakage. In combination with digital identity authentication technology, the protection level of the cloud data center is strengthened, data security is further improved, and malicious attack invasion is avoided. The mine car dynamic model characterizes the dynamic operation state of the mine car, thereby improving the comprehensiveness of mine car monitoring. The fault prediction model constructed by the deep learning algorithm combines the mine car dynamic data output by the mine car dynamic model and the static mine car monitoring data, thereby improving the efficiency and accuracy of fault prediction. The mine car control optimization model constructed by the reinforcement learning algorithm can generate automatic and adaptive mine car control optimization strategies according to the fault prediction situation, thereby improving the operation condition of the mine car, avoiding and processing faults, thereby improving the practicality and the intelligence of the system.

[0153] The present invention is not limited to the above optional implementations, and anyone can derive other various forms of products under the enlightenment of the present invention. The above specific implementations should not be understood as limiting the scope of protection of the present invention. The scope of protection of the present invention should be based on the definition in the claims, and the description can be used to interpret the claims.

Claims

1. A mine car equipment health management system based on encryption algorithm, characterized in that: Includes cloud data centers, trusted institutions, and several remote monitoring devices; The cloud data center and the trusted institution are respectively connected to a plurality of remote monitoring devices in communication, and the cloud data center is connected to the trusted institution in communication, and the plurality of remote monitoring devices are arranged one by one at the corresponding plurality of mining vehicles, and each remote monitoring device is electrically connected to the control system of the corresponding mining vehicle; The trusted institution is used to generate keys and register identities for all remote monitoring devices, obtain the public-private key pair and signature information of each remote monitoring device; and send the private key and signature information in the public-private key pair to the corresponding remote monitoring device, and send the public key in the public-private key pair to the cloud data center; A remote monitoring device is used to collect real-time monitoring data of the mine car, and then encrypt the collected real-time monitoring data and upload it to the cloud data center together with the signature data; and decrypting the encrypted real-time mine car control optimization strategy sent by the cloud data center to generate a real-time mine car control instruction, and applying the real-time mine car control instruction to the control system of the mine car; The cloud data center is used to decrypt the encrypted real-time mine car monitoring data sent by the remote monitoring device, perform fault prediction and mine car control optimization, obtain the real-time mine car control optimization strategy, and encrypt it and send it to the remote monitoring device.

2. According to the encryption algorithm-based mining vehicle equipment health management system of claim 1, it is characterized in that: The cloud data center includes an identity authentication unit, a first data decryption unit, a data preprocessing unit, a model building unit, a dynamic data generation unit, a fault prediction unit, a mine car control optimization unit and a first data encryption unit which are connected in sequence, wherein the identity authentication unit is respectively connected to a trusted institution and a plurality of remote monitoring devices in communication, the first data decryption unit is connected to a trusted institution in communication, and the first data encryption unit is respectively connected to a trusted institution and a plurality of remote monitoring devices in communication; the dynamic data generation unit is used to generate different dynamic data of the mine car according to the input mine car monitoring data; The fault prediction unit is used to predict faults based on the mine car monitoring data and different dynamic data of the mine car; The mine car control optimization unit is used to generate a real-time mine car control optimization strategy according to the fault prediction result.

3. According to the encryption algorithm-based mining vehicle equipment health management system of claim 1, it is characterized in that: The remote monitoring device includes a monitoring data acquisition unit, a second data encryption unit, a second data decryption unit and a control instruction generation unit. The monitoring data acquisition unit and the control instruction generation unit are both deployed at the mining car. The monitoring data acquisition unit is connected to the second data encryption unit, and the control instruction generation unit is connected to the second data decryption unit. The second data encryption unit and the second data decryption unit are both communicated with the cloud data center and the trusted organization.

4. A mining vehicle equipment health management system based on encryption algorithm according to claim 3, characterized in that: The monitoring data acquisition unit includes a sensor module, a data acquisition unit and a data comparison unit, wherein the sensor module is arranged at the corresponding mine car, and the data acquisition unit and the control instruction generation unit are both electrically connected to the control system of the corresponding mine car; A sensor module, used for collecting first real-time mine car monitoring data of the mine car; A data acquisition unit, used for acquiring second real-time mine car monitoring data detected by the control system of the mine car itself; The data comparison unit is used to compare and analyze the first real-time mine car monitoring data and the second real-time mine car monitoring data to obtain a data error. If the data error is greater than a preset error threshold, an alarm signal is issued.

5. A mining vehicle equipment health management system based on encryption algorithm according to claim 4, characterized in that: The sensor module includes a speed sensor, a steering angle sensor, an electrical sensor and a weight sensor.

6. A mining vehicle equipment health management method based on encryption algorithm, characterized in that: include: Deploy corresponding remote monitoring devices on different mining vehicles, use a trusted institution to generate keys and register identities for all remote monitoring devices, obtain the public-private key pair and signature information of each remote monitoring device, then send the private key and signature information in each public-private key pair to the corresponding remote monitoring device, and send the public key in the public-private key pair to the cloud data center; The remote monitoring device encrypts the collected real-time mining car monitoring data and sends it to the cloud data center, where it is stored; For the stored historical mine car monitoring data, the cloud data center pre-processes the historical mine car monitoring data to obtain the pre-processed historical mine car monitoring data, and then builds the mine car dynamic model, fault prediction model and mine car control optimization model according to the pre-processed historical mine car monitoring data; For new real-time mine car monitoring data, the cloud data center calls a trusted organization to authenticate the signature data. After the authentication is passed, the encrypted real-time mine car monitoring data is decrypted according to the public key of the remote monitoring device to obtain the decrypted real-time mine car monitoring data; then, different dynamic data of the mine car, fault prediction and real-time mine car control optimization are generated according to the decrypted real-time mine car monitoring data, and the real-time mine car control optimization strategy is obtained and sent to the remote monitoring device after encryption; The remote monitoring device decrypts the encrypted real-time mine car control optimization strategy according to the private key to obtain the decrypted real-time mine car control optimization strategy, and then generates a real-time mine car control instruction according to the decrypted real-time mine car control optimization strategy, and sends the real-time mine car control instruction to the control system of the corresponding mine car.

7. A mining vehicle equipment health management method based on encryption algorithm according to claim 6, characterized in that: The method of generating different dynamic data of the mine car, fault prediction and real-time mine car control optimization according to the decrypted real-time mine car monitoring data is specifically as follows: Firstly, the mine car dynamic model is used to generate dynamic data for the decrypted real-time mine car monitoring data to obtain real-time mine car dynamic data, and the real-time mine car dynamic data is associated with the corresponding decrypted real-time mine car monitoring data to obtain real-time comprehensive data; The fault prediction model is then used to predict the real-time comprehensive data to obtain the real-time fault prediction results; finally, based on the real-time fault prediction results, the mine car control optimization model is used to optimize the mine car control to obtain the real-time mine car control optimization strategy.

8. A mining vehicle equipment health management method based on encryption algorithm according to claim 6, characterized in that: The method uses a trusted institution to generate keys and register identities for all remote monitoring devices, obtains a public-private key pair and signature information for each remote monitoring device, sends the private key and signature information in the public-private key pair to the corresponding remote monitoring device, and sends the public key in the public-private key pair to the cloud data center, including the following steps: Using a cloud data center, collect the communication addresses, attribute information, and device IDs of all remote monitoring devices, and send the communication addresses, attribute information, and device IDs to a trusted institution; Use a trusted institution to generate keys and register identities for all remote monitoring devices based on attribute information and device IDs, and obtain public-private key pairs and signature information for each remote monitoring device; According to the communication address, the private key and signature information in the public-private key pair are sent to the corresponding remote monitoring device, and the public key in the public-private key pair is sent to the cloud data center.

9. A mining vehicle equipment health management method based on encryption algorithm according to claim 6, characterized in that: For the stored historical mine car monitoring data, the cloud data center pre-processes the historical mine car monitoring data to obtain the pre-processed historical mine car monitoring data, and then constructs the mine car dynamic model, the fault prediction model and the mine car control optimization model according to the pre-processed historical mine car monitoring data, including the following steps: In the cloud data center, based on some pre-processed historical mine car monitoring data, a mine car dynamic model is constructed using a state analysis method, and some historical mine car dynamic data are generated; The pre-processed historical mine car monitoring data and historical mine car dynamic data are associated, and clustering is performed with fault information as the clustering target to obtain several cluster centers and cluster clusters; According to the fault information of each cluster center, a corresponding real fault label is added to each cluster center, and the real fault label is diffused to the corresponding cluster cluster to obtain several fault prediction samples; Based on several fault prediction samples, a fault prediction model is constructed using a deep learning algorithm, and several historical fault prediction results are generated; According to several historical fault prediction results and preset mine car control optimization strategies, a mine car control optimization model is constructed using reinforcement learning algorithm.

10. A mining vehicle equipment health management method based on encryption algorithm according to claim 9, characterized in that: The mine car dynamic model includes a mine car power dynamic model, a mine car electrical dynamic model, a mine car load performance dynamic model and a mine car energy consumption dynamic model.

Images