A coal mine flood alarm method based on image and hydrological data monitoring

Abstract

The present invention belongs to the technical field of coal mine flood warning, and discloses a coal mine flood alarm method based on image and hydrological data monitoring. The method uses a non-destructive detector to detect the initial state of groundwater near the coal mine roadway during tunneling on the ground for the tunneling face, coal mining face or working face where water inrush accidents may occur in the coal mine underground, and obtains the initial water level and water temperature data of the groundwater near the coal mine. The change process of the water level and water temperature data during the process is obtained and presented as an image video stream. At the same time, combined with the geological environment factors that may affect the changes in the water level and water temperature data, the change rules of the water level and water temperature data during the future tunneling process are obtained, and a regular trend sequence is formed, and a scatter point set is formed for the abnormal trend points. The credibility score is obtained and visualized. The present invention realizes prior detection, accurately judges the development trend of dangerous information, and has practical significance for preventing problems before they occur and protecting the safety of life and property.

Description

Technical Field

[0001] The invention belongs to the technical field of coal mine flood early warning, and in particular relates to a coal mine flood alarm method based on image and hydrological data monitoring. Background Art

[0002] Mine flood is a serious disaster in coal mines. The alarm of mine flood must be timely and accurate in coal mine production. At present, flood warning is mainly based on hydrological detection and prevention, underground water exploration, and observation of precursor phenomena. Hydrological detection and underground water exploration can prevent underground flood accidents, but due to the possibility of complex hydrological conditions, improper design, ineffective measures, poor management and mental paralysis of people, hydrological detection and underground water exploration cannot completely prevent the occurrence of water inrush, let alone alarm for sudden underground water inrush; the observation of precursor phenomena is mainly based on human experience and judgment, and there are large subjective factors. At present, for on-site water inrush accidents, it mainly relies on the manual alarm of on-site personnel, but when the water inrush occurs at an unattended time or area, or the on-site personnel flee in a hurry and fail to actively alarm, the dispatch room cannot obtain the information of the water inrush in time, and cannot notify the relevant staff in the mine in time, so that emergency measures cannot be taken in time for the water inrush accident, which is easy to cause water damage out of control and casualties. In order to effectively reduce the property losses and casualties caused by floods in mines, a new underground flood alarm method is needed, which can accurately alarm underground water inrush in the first time, and buy precious rescue and escape time for underground personnel in other areas who are not at the scene of the disaster.

[0003] To solve the above problems, the invention patent of coal mine flood alarm method based on image and hydrological data monitoring (publication number CN105569732A, publication date 20160104) discloses that cameras are placed at underground coal mine excavation working faces, coal mining working faces or other working faces where water seepage accidents may occur, and the water level and water temperature data of the ground hydrological observation holes are monitored at the same time; when abnormal water flow is detected in the set area in the camera video image, and the water flow duration exceeds the set time threshold or the water flow increase speed exceeds the set threshold, and the water level or water temperature data of the ground hydrological observation hole is abnormal, a flood alarm signal is issued. This patent takes into account the characteristics of underground coal mine floods, automatically and promptly takes corresponding measures, and can accurately alarm the mine water inrush in the first time, so as to buy precious disaster relief and escape time for underground personnel in other areas who are not at the site of the water inrush.

[0004] Pre - perception technology has been widely applied in network information processing. Combined with existing knowledge bases, it can effectively make intelligent predictions about known and unknown threats, effectively guide the active self - evolution recognition of the system, extract sensitive information during the processing, conduct consistency adjudication to perceive system threats, take measures in advance against the further development of threats, thus achieving prior detection. Applying pre - perception technology to coal mine water disasters and accurately judging the development trend of dangerous information is of practical significance for preventing problems before they occur and protecting life and property safety. Summary of the Invention

[0005] To overcome the problems existing in related technologies, the disclosed embodiments of the present invention provide a coal mine water disaster alarm method based on image and hydrological data monitoring.

[0006] The technical solution is as follows: A coal mine water disaster alarm method based on image and hydrological data monitoring includes:

[0007] S1. Use a non - destructive detector to collect the initial state of groundwater in the driving face, coal mining face and working face where water inrush accidents occur in the coal mine underground, and obtain the initial water level and water temperature data of the mine groundwater.

[0008] S2. During the driving process, obtain the change history of water level and water temperature data and present it as an image video stream; combine the geological environment factors affecting the changes of water level and water temperature data to obtain the change rules of water level and water temperature data in the future driving process, form a regular trend sequence, and form a scatter set for abnormal trend points.

[0009] S3. Conduct simulation comparison based on the historical experience of abnormal coal mine water disaster data monitored by images and hydrological data to obtain a credibility score. The higher the score, the greater the credibility; optimize the water level and water temperature data during the driving process based on the credibility score.

[0010] S4. Apply the optimized regular trend sequence to the coal mine water disaster alarm terminal for visual display.

[0011] In step S2, forming a regular trend sequence includes:

[0012] S201. Initialize the system, allocate the driving process stage, and upload the regular trend evolution data of each water level and water temperature node to be predicted to the regular trend evolution judgment center ECS.

[0013] S202. Notify the regular trend evolution prediction node IA of the water level and water temperature nodes to be predicted, and the regular trend evolution prediction node predicts the updated regular trend evolution data of the water level and water temperature nodes to be predicted.

[0014] S203. Package the regular trend evolution prediction results into a trend sequence set. Inside all regular trend evolution prediction nodes, reach a consensus based on a two-level judgment mechanism combined with clustering verification and upload through the transmission channel.

[0015] In step one, the system initializes and allocates the tunneling process stage, including:

[0016] (1) The tunneling process stage certification center IA generates the main hydrographic data encoding and decoding pair (MPK, MSK) ← Steup(λ), where λ is the mapping parameter. The main hydrographic data encoding MPK of the system is public, and the main hydrographic data decoding MSK is decrypted and saved by the tunneling process stage certification center IA. Steup(λ) is the generation method;

[0017] (2) The node to be predicted EC i Submits an application to join the transmission channel chain AC. After the tunneling process stage certification center IA approves the tunneling process stage, it allocates the tunneling process stage trend sequence evolution set to the node to be predicted EC i where is the globally unique tunneling process stage identifier of the node, and is the hydrographic data encoding and decoding pair of the node;

[0018] (3) The regular trend evolution prediction node RA submits an application to join the transmission channel chain AC. After the tunneling process stage certification center IA approves the qualification, it allocates the tunneling process stage trend sequence evolution set to the regular trend evolution prediction node RA and generates the node attribute main hydrographic data decoding ASK for Ra j ASK = KeyGen(MPK, MSK, A p ), where is the globally unique tunneling process stage identifier of the node, is the hydrographic data encoding and decoding pair of the node, and A p = (a1, a2…a n ) represents the attribute set of the Ra j node; KeyGen() is the node attribute main hydrographic data decoding function;

[0019] (4) The node to be predicted Ec i Combines each hydrographic data trend sequence evolution message CT with the index index to form the M set, attaches the access policy A s in the form of hydrographic data trend evolution, the symmetric hydrographic data encoding and decoding key' m after attribute decoding, and the digest value of M is MD, with the node to be predicted Eci Verification of node pair MD Compose file file j After that, send it to the Regular Trend Evolution Judgment Center Ecs;

[0020] (5) The Regular Trend Evolution Judgment Center Ecs receives the corresponding data, verifies the node to be predicted Ec i , and calculates the hash value of set M to verify MD, and returns the storage path sl of file file i to the node to be predicted Ec j ; After the node to be predicted Ec j receives the storage path sl i , it sends the message of its own data update j to the RA node; is the address of the node to be predicted, is the verification information of the node to be predicted; is the verification information of the node to be predicted;

[0021] (6) The Regular Trend Evolution Prediction Node RA predicts the regular trend evolution data of the water level and water temperature nodes EC to be predicted. According to the number of regional blocks X in different time periods of the tunneling process, calculate the position of each regional block ID in different time periods of the tunneling process on the hash ring, and calculate the position of each RA node on the hash ring through the formula Hash(ID + random); ID is the address, and random is the random position; According to the position of the Regular Trend Evolution Prediction Node RA on the hash ring, search clockwise for the regional block nodes in different time periods of the tunneling process, and the first regional block node in different time periods of the tunneling process found is the regional block in different time periods of the tunneling process to which the RA node belongs;

[0022] (7) Verify whether the number of Regular Trend Evolution Prediction Nodes RA included in each regional block in different time periods of the tunneling process is greater than or equal to four. If not, return to recalculate the position of the RA node by selecting a random number, and re-tunnel the regional block in different time periods; If the verification is passed, determine the regional block in different time periods of the tunneling process, and at the same time all nodes will retain a copy of the list of all nodes and the list of nodes in the regional block in different time periods of the tunneling process;

[0023] (8) Based on the results of the regional block in different time periods of the tunneling process, set the identifier within the regional block in different time periods of the tunneling process for the RA node. According to the hydrological data image identifier v g within the regional block in different time periods of the tunneling process and the number of nodes num g within the regional block in different time periods of the tunneling process, determine the identifier p g of the main node within the regional block in different time periods of the current hydrological data image, p g = vg mod | num g |, where mod || is the positive orientation value determined by the number of nodes in the regional block during different time periods of the tunneling process; is the global identifier set for the main nodes in the regional block during different time periods of each tunneling process. According to the global hydrological data image identifier v a and the number of regional blocks num during different time periods of the tunneling process a , determine the global main node identifier p in the current hydrological data image a , p a = v a mod | num a |;

[0024] (9) Node to be predicted Ec i Send its own update message and the verification sig of this message update message together to the global main node Ra k ; Ra k After receiving the update message, verify the sig of the update message update Verify the signature. If it is illegal, form a scatter point set. If it is legal, determine the relevant data for the regular trend evolution prediction;

[0025] (10) Global main node Ra k After verifying the authenticity and integrity of the relevant data for the regular trend evolution prediction, make a prediction, record it in the update request table Utable0. The global main node Ra k For the node to be predicted Ec i The m regular trend evolution prediction algorithms recently updated are used to make predictions to obtain their respective regular trend evolution values VaR m , and update the Ec i The final regular trend evolution value VaR generates a regular trend evolution value change information tx, which is packed into the trend sequence set; where VaR p is the final regular trend evolution value before the change, VaR a is the updated final regular trend evolution value, ID alg is the identifier of the regular trend evolution algorithm on which the current evaluation result is based, Height is the accurate height of the trend sequence set to which the current tx belongs; index is the index;

[0026] (11) Global main node Ra k Collect the regular trend evolution value change information tx at time t, and form the collected regular trend evolution value change information tx into Blockheader, then Among them, Prehash is a hash pointer pointing to the previous set of trend sequences, and Timestamp represents the block timestamp. represents the main node Ra k Verification of the set of trend sequences. TX Root represents the root of the Merkle tree composed of all txs in the current set of trend sequences. is the main node address;

[0027] (12) Global main node Ra k sends a consensus proposal <Proposal, V a , Height, Blockheader, UtableO) to the main nodes of different time period regional blocks of each tunneling process. After receiving the consensus proposal sent by the global main node Ra k in the tunneling process, append the hydrological data image identifier V g in the different time period regional block of the tunneling process, and then broadcast it in the different time period regional block of the tunneling process. The replica RA nodes in the different time period regional block of the tunneling process perform verification of the set of trend sequences; Proposal is a proposal, and V a is the regular trend evolution value;

[0028] (13) After the verification is completed, send a consensus response message to the main node of the different time period regional block of the tunneling process. Among them, is the identifier of the current replica RA node, is the verification of the current replica RA node for the consensus response message; Respond g is the response value;

[0029] (14) The main node of the different time period regional block of the tunneling process collects the consensus response messages in the different time period regional block of the tunneling process. When it collects more than or equal to 2f2 + 1 legal consensus response messages of the different time period regional block of the tunneling process including the main node itself, cluster the verifications of each replica RA node in the message into and send a global consensus response message to the global main node Among them, f2 is the number of Byzantine nodes in the different time period regional block of the tunneling process, and list g is the ID list of all nodes in the different time period regional block of the tunneling process participating in generating the cluster verification; Respond a is the response value of node a;

[0030] (15) Global main node Ra kCollect the global consensus response messages sent by the regional block master nodes at different time periods of the tunneling process. After collecting more than or equal to 2f2+1 global consensus response messages, recluster the clustering verification in the messages into and transmit a consensus confirmation message where list a is the ID list of all RA nodes participating in generating clustering verification; Commit is the entrusted data;

[0031] (16) After the RA node receives the consensus confirmation message sent by the global master node Ra k and uses list a to verify the hydrological data encoding of the nodes included in it After passing the verification, synchronize the consensus trend sequence set of this round to the transmission channel of this node.

[0032] In step S203, reach a consensus based on a two-level judgment mechanism combined with clustering verification, including:

[0033] Calculate the ID positions of regional blocks at different time periods of the tunneling process, calculate the positions of RA nodes, determine the regional blocks of the nodes belonging to different time periods of the tunneling process, and verify the number of RA nodes included in each regional block of different time periods of the tunneling process;

[0034] Set the identifiers within the regional blocks of different time periods of the tunneling process and the global identifier. Ra k Send a consensus proposal to the master nodes of each regional block of different time periods of the tunneling process. Consensus is reached within the regional blocks of different time periods of the tunneling process, and the master nodes of the regional blocks of different time periods of the tunneling process send global consensus responses to the global master node; Global consensus is reached, thus forming a regular trend sequence. For the nodes that do not reach a consensus, judge them as non-abnormal trend points and form a scatter set.

[0035] In step S4, apply the optimized regular trend sequence to the coal mine flood alarm terminal, including:

[0036] First, Ec i Process the data generated by itself every t h time, update the relevant data m for the evolution prediction of each updated regular trend first, and establish an index index for identifying the specific serial number of the data in the storage path of the regular trend evolution judgment center;

[0037] Secondly, use the symmetric file hydrological data encoding and decoding key randomly selected in the hydrological data encoding and decoding space m to decode m to obtain a hydrological data trend sequence evolution message CT, and according to the access policy A s customized by the current node, use MPK to decode the symmetric file hydrological data encoding and decoding keym Obtain the key m ←Encrypt(MPK, A s , key m ), where Encrypt() is the compilation function.

[0038] In step (6), the regular trend evolution prediction node RA predicts the regular trend evolution data updated by the water level and water temperature nodes EC to be predicted, including:[[]]

[0039] When the value node Ra k receives the update, it uses the hydrological data encoding of Ec i to verify the signature and request to download the file stored in sl from the regular trend evolution judgment center j ; j

[0040] ECS will judge whether Ra k meets the conditions according to the access policy corresponding to the requested file: if the conditions are met, Ra k is allowed to download the file j to obtain M. By comparing the update with the file j and MD in , it is determined whether the data source is authentic and valid and whether the data stored in the regular trend evolution judgment center has been tampered with;

[0041] Decrypt the key' m to obtain the file hydrological data compilation code and use the key m to obtain the hydrological data trend evolution mapping data m, and select a regular trend evolution evaluation algorithm to calculate the regular trend evolution value.

[0042] In step (12), the verification of the trend sequence set is performed, including:[[]]

[0043] Verification of the block-producing node Verify the signature and judge whether v a , v g , Height in the consensus proposal is correct; by calculating the hash of the trend sequence set header of Block n+1 , whether the parent trend sequence set of Block n+1 is Block n ; check whether there are abnormal assignments in the tx of the Block n+1 trend sequence set and verify whether its root hash value is the same as the TX Toot in the trend sequence set header;

[0044] ​When the primary node within the regional block of the global or tunneling process fails to produce a block within the specified time, the next RA node produces a block for replacing the hydrological data image. The RA node initiates a request for replacing the hydrological data image, and the replica RA node verifies the request for replacing the hydrological data image. The RA node collects legal change confirmation messages, and the new RA primary node performs the duties of generating the prediction and trend sequence set.

[0045] Furthermore, the next RA node producing a block for replacing the hydrological data image includes:

[0046] 1) The replica RA node initiates a request for replacing the hydrological data image:

[0047] When the replica RA node discovers a problem with the primary node Ra k it sends a request for changing the hydrological data image to the replica RA node, where v a +1 represents the identifier of the changed hydrological data image, represents the ID of the replica RA node that initiates the request for changing the hydrological data image, represents the verification of the request for changing the hydrological data image by this node, and sig agg-p represents Ra u the clustering verification collected in the previous round of consensus, which is used to prove the correctness of the trend sequence set with a height of Height;

[0048] 2) The replica node verifies the request for replacing the hydrological data image: After receiving the request for changing the hydrological data image, the replica RA node verifies the request. After passing the verification, it broadcasts a change confirmation message where, represents the ID of the current replica RA node, represents the verification of the change confirmation message by the current replica RA node;

[0049] 3) The replica RA node collects legal change confirmation messages: After the replica RA node collects more than or equal to 2f + 1 legal change confirmation messages, for the hydrological data image replacement in the regional block of the tunneling process at different time periods, f = f2, and for the global hydrological data image replacement, f = f1. The identifier of the hydrological data image is updated to v a +1; The new RA primary node performs the duties of generating the prediction and trend sequence set.

[0050] In step S3, based on the historical experience of abnormal coal mine flood data monitored by images and hydrological data, the simulation comparison is carried out, including: placing cameras at the tunneling face, coal mining face and the working face where water inrush accidents occur in the coal mine underground, and drilling hydrological observation holes on the ground for monitoring the state of the mine groundwater, and monitoring the water level and water temperature data in the hydrological observation holes;

[0051] Real-time monitoring is performed on video image data. When abnormal water flow appears in a set area in the camera video image, and the duration of the water flow exceeds the set time threshold or the increasing speed of the water flow exceeds the set threshold, it is determined that the data is abnormal; and when it is found that the water level or water temperature change in the hydrological observation hole exceeds the set threshold, a flood alarm signal is immediately issued.

[0052] Furthermore, based on the formation of a regular trend sequence and the historical experience of abnormal coal mine flood data monitoring based on images and hydrological data, a simulation comparison is carried out to obtain a credibility score.

[0053] Combining all the above technical solutions, the beneficial effects of the present invention are as follows: Based on the acquired monitoring images and hydrological data, and combined with non-destructive detection technology, the present invention uses the pre-perception technology to predict the pre-evolution trend before the possible occurrence of coal mine floods, effectively extracts sensitive information in the process, judges the threats to the consistency adjudication perception system, and takes measures in advance to further develop the threats, so as to achieve prior detection, accurately judge the development trend of dangerous information, and has practical significance for preventing accidents and protecting life and property safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The drawings here are incorporated into the specification and form a part of this specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure;

[0055] Figure 1 is a flow chart of a coal mine flood alarm method based on image and hydrological data monitoring provided by an embodiment of the present invention;

[0056] Figure 2 is a flow chart of forming a regular trend sequence provided by an embodiment of the present invention;

[0057] Figure 3 is a schematic diagram of a coal mine flood alarm system based on image and hydrological data monitoring provided by an embodiment of the present invention;

[0058] Figure 4 is a schematic diagram of the regional block division principle for different time periods of each tunneling process provided by an embodiment of the present invention;

[0059] Figure 5 is a schematic diagram of the regional block transmission principle for different time periods of each tunneling process provided by an embodiment of the present invention;

[0060] In the figure: 1. Initial water level and water temperature data acquisition module; 2. Regular trend sequence acquisition module; 3. Simulation comparison module; 4. Coal mine flood alarm display module. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0061] To make the above objects, features, and advantages of the present invention more apparent and understandable, the following provides a detailed description of the specific embodiments of the present invention in conjunction with the accompanying drawings. Many specific details are set forth in the following description to facilitate a full understanding of the present invention. However, the present invention can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0062] Example 1, as Figure 1 shown, the coal mine flood alarm method based on image and hydrological data monitoring provided by the embodiments of the present invention includes:

[0063] S1, Use a non-destructive detector to collect the initial state of groundwater in the coal mine underground driving face, coal mining face, and the working face where a water inrush accident occurs, and obtain the initial water level and water temperature data of the mine groundwater;

[0064] S2, During the driving process, obtain the change history of the water level and water temperature data and present it as an image video stream; Combine the geological environment factors that affect the changes in the water level and water temperature data to obtain the change laws of the water level and water temperature data in the future driving process, form a regular trend sequence, and form a scatter set of abnormal trend points;

[0065] S3, Based on the historical experience of abnormal coal mine flood data monitored by images and hydrological data, perform simulation and comparison to obtain a credibility score. The higher the score, the greater the credibility; Based on the credibility score, optimize the water level and water temperature data during the driving process;

[0066] S4, Based on the optimized regular trend sequence, apply it to the coal mine flood alarm terminal for visual display.

[0067] As Figure 2 shown, in step S2, forming a regular trend sequence includes:

[0068] S201, System initialization, allocate the driving process stage, and upload the regular trend evolution data of each water level and water temperature node to be predicted to the regular trend evolution judgment center ECS;

[0069] S202, The water level and water temperature nodes to be predicted notify the regular trend evolution prediction node IA, and the regular trend evolution prediction node predicts the updated regular trend evolution data of the water level and water temperature nodes to be predicted;

[0070] S203, Package the regular trend evolution prediction results into a trend sequence set, and within all regular trend evolution prediction nodes, reach a consensus based on a two-level judgment mechanism combined with clustering verification and upload through the transmission channel.

[0071] Exemplarily, in step S203, a consensus is reached based on a two-level judgment mechanism that combines clustering verification, including:

[0072] Calculate the positions of regional block IDs at different time periods of the tunneling process, calculate the positions of RA nodes, determine the regional blocks of different time periods of the tunneling process to which the nodes belong, and verify the number of RA nodes included in each regional block of different time periods of the tunneling process;

[0073] Set markers within the regional blocks of different time periods of the tunneling process and global markers, Ra k Send a consensus proposal to the main nodes of each regional block of different time periods of the tunneling process. Consensus is reached within the regional blocks of different time periods of the tunneling process, and the main nodes of the regional blocks of different time periods of the tunneling process send a global consensus response to the global main node; Global consensus is reached, thus forming a regular trend sequence. For the nodes that do not reach consensus, they are determined as non-abnormal trend points and a scatter point set is formed.

[0074] To ensure that the algorithm resists the influence of abnormal trend point interference, the number X of regional blocks of different time periods of the tunneling process needs to satisfy X≥4, and the number Y of nodes within each regional block of different time periods of the tunneling process also needs to satisfy Y≥4. First, calculate the position of each ID on the hash ring according to the number X. At this time, multiple hash calculations can be performed on each ID of the regional block of different time periods of the tunneling process to generate multiple virtual nodes on the hash ring, thereby reducing the problem of data skew, as Figure 4 shown. The node transmission principle within each regional block of different time periods of the tunneling process is as Figure 5 shown.

[0075] Example 2, Exemplarily, system initialization and tunneling process stage allocation include:

[0076] (1) The tunneling process stage certification center IA generates the main hydrological data encoding and decoding pair (MPK, MSK) ← Steup(λ), where λ is the mapping parameter. The main hydrological data encoding MPK of the system is public, and the main hydrological data decoding MSK is decrypted and saved by the tunneling process stage certification center IA. Steup(λ) is the generation method;

[0077] (2) The node to be predicted EC i Submits an application to join the transmission channel chain AC. After the tunneling process stage certification center IA approves the tunneling process stage, it allocates a tunneling process stage trend sequence evolution set for the node to be predicted EC i where, is the globally unique tunneling process stage identifier of the node, is the hydrological data encoding and decoding pair of the node;

[0078] (3) The regular trend evolution prediction node RA submits an application to join the transmission channel chain AC. After the tunneling process stage certification center IA approves the qualification, the regular trend evolution prediction node RA is assigned a tunneling process stage trend sequence evolution set And for Ra j Generate the node attribute main hydrological data decoding ASK, ASK = KeyGen(MPK, MSK, A p ), where Is the globally unique tunneling process stage identifier for the node, Is the hydrological data encoding / decoding pair for the node, A p =(a1, a2…a n ) represents the attribute set possessed by the Ra j node; KeyGen() is the node attribute main hydrological data interpretation function;

[0079] (4) The node to be predicted, Ec i Combines each hydrological data trend sequence evolution message CT with the index index to form the M set, attaches the access policy A s in the form of hydrological data trend evolution mapping, the symmetric hydrological data encoding / decoding key' m after attribute decoding, and the digest value of M is MD. Using the node of the node to be predicted, Ec i to verify MD to form the file file j and then sends it to the regular trend evolution judgment center Ecs;

[0080] (5) The regular trend evolution judgment center Ecs receives the corresponding data, verifies the node to be predicted, Ec i , and calculates the hash value of the set M to verify MD, and returns the storage path sl i of the file file j to the node to be predicted, Ec j ; After the node to be predicted, Ec i receives the storage path sl j , it sends the message indicating that its own data has been updated to the RA node; Is the address of the node to be predicted, Is the verification information of the node to be predicted;

[0081] (6) The regular trend evolution prediction node RA predicts the water level and water temperature nodes to be predicted, updates the regular trend evolution data of the EC node. According to the number of regional blocks X in different time periods of the tunneling process, calculate the positions of the regional block IDs in different time periods of each tunneling process on the hash ring, and calculate the positions of each RA node on the hash ring through the formula Hash(ID + random); ID is the address and random is the random position; According to the position of the regular trend evolution prediction node RA on the hash ring, search clockwise for the regional block nodes in different time periods of the tunneling process, and the first regional block node found in different time periods of the tunneling process is the regional block in different time periods of the tunneling process to which the RA node belongs;

[0082] (7) Verify whether the number of regular trend evolution prediction nodes RA contained in each regional block in different time periods of the tunneling process is greater than or equal to four. If not, return to reselect a random number to calculate the position of the RA node and re-tunnel the regional block in different time periods; If the verification passes, determine the regional block in different time periods of the tunneling process. At the same time, all nodes will retain a list of all nodes and a list of nodes within the regional block in different time periods of the tunneling process;

[0083] (8) Based on the results of the regional block in different time periods of the tunneling process, set a marker within the regional block in different time periods of the tunneling process for the RA node. According to the hydrological data image marker v within the regional block in different time periods of the tunneling process g and the number of nodes num within the regional block in different time periods of the tunneling process g , determine the marker p of the main node within the regional block in different time periods of the current hydrological data image g , p g = v g mod |num g |, where mod || is the positive orientation value determined by the number of nodes within the regional block in different time periods of the tunneling process; Set a global marker for the main nodes within each regional block in different time periods of the tunneling process. According to the global hydrological data image marker v a and the number of regional blocks num a , determine the global main node marker p in the current hydrological data image a , p a = v a mod |num a |;

[0084] (9) The node to be predicted Ec i Sends its own update message and the verification sig update of this message to the global main node Ra k ; Ra k After receiving the update message, verify the sig of the update messageupdate Verify the signature. If it is illegal, form a scatter point set. If it is legal, determine the relevant data for the regular trend evolution prediction;

[0085] (10) Global master node Ra k After verifying the authenticity and integrity of the relevant data for the regular trend evolution prediction, perform the prediction and record it in the update request table Utable0, global master node Ra k For the node to be predicted Ec i The m regular trend evolution prediction algorithms updated recently are used to perform predictions to obtain their respective regular trend evolution values VaR m and update Ec i Generate a regular trend evolution value change information tx for the final regular trend evolution value VaR of Ec, and package it into the trend sequence set; among them, VaR p is the final regular trend evolution value before the change, VaR a is the updated final regular trend evolution value, ID alg is the identifier of the regular trend evolution algorithm based on which the current evaluation result is obtained, Height is the accurate height of the trend sequence set to which the current tx belongs; index is the index;

[0086] (11) Global master node Ra k Collect the regular trend evolution value change information tx at time t, and form the collected regular trend evolution value change information tx into Blockheader, then Among them, Prehash is the hash pointer pointing to the previous trend sequence set, Timestamp represents the block timestamp, represents the verification of the trend sequence set by the master node Ra k TX Root represents the root of the Merkle tree composed of all txs in the current trend sequence set; is the master node address;

[0087] (12) Global master node Ra k Send the consensus proposal <Proposal, V a , Height, Blockheader, UtableO) to the regional block master nodes of each tunneling process at different time periods. After receiving the consensus proposal sent by the global master node Ra k by the regional block master nodes of each tunneling process at different time periods, attach the hydrological data image identifier V in the regional block of the tunneling process at different time periods gAfter that, broadcast within the regional blocks in different time periods of the tunneling process, and the replica RA nodes in the regional blocks in different time periods of the tunneling process verify the trend sequence set; Proposal is a proposal, V a is the regular trend evolution value;

[0088] (13) After the verification is completed, send a consensus response message within the regional blocks in different time periods of the tunneling process to the master node of the regional blocks in different time periods of the tunneling process, where is the identifier of the current replica RA node, is the verification of the consensus response message by the current replica RA node; Respond g is the response value;

[0089] (14) The master node of the regional blocks in different time periods of the tunneling process collects the consensus response messages within the regional blocks in different time periods of the tunneling process. When it collects more than or equal to 2f2 + 1 legal consensus response messages of the regional blocks in different time periods of the tunneling process including the master node itself, it clusters the verifications of each replica RA node in the message into and sends a global consensus response message to the global master node where f2 is the number of Byzantine nodes within the regional blocks in different time periods of the tunneling process, list g is the ID list of all nodes within the regional blocks in different time periods of the tunneling process participating in generating the clustered verification; Respond a is the response value of node a;

[0090] (15) The global master node Ra k collects the global consensus response messages sent by the master nodes of the regional blocks in different time periods of the tunneling process. When it collects more than or equal to 2f2 + 1 global consensus response messages, it clusters the clustered verifications in the messages again into and transmits a consensus confirmation message where list a is the ID list of all RA nodes participating in generating the clustered verification; Commit is the entrusted data;

[0091] (16) After the RA node receives the consensus confirmation message sent by the global master node Ra k it uses the hydrological data encoding verification of the nodes included in list a After the verification passes, synchronize the consensus trend sequence set of this round to the transmission channel of this node. After the verification passes, synchronize the consensus trend sequence set of this round to the transmission channel of this node.

[0092] Another exemplary one, based on the optimized regular trend sequence, is applied to the coal mine flood alarm terminal, including:

[0093] First, Ec i Every time t h The data that occurs once in a time period is processed, and the update first predicts the relevant data m for each updated regular trend evolution, and establishes an index index used to identify the specific serial number of the data in the regular trend evolution judgment center storage path;

[0094] Secondly, the hydrological data encoding key is randomly selected from the symmetric file in the hydrological data encoding space. m Decode m to get a hydrological data trend sequence evolution message CT, and follow the custom access strategy A of the current node s , use MPK to decode the symmetric file hydrological data encoding key m Get the key m ←Encrypt(MPK,A s ,key m ), Encrypt() is the compilation function.

[0095] In another exemplary embodiment, in step (6), the RA node predicts the regular trend evolution data updated by the EC node, including:

[0096] On-duty node Ra k After receiving the update, use Ec i Hydrological data coding right Verify the signature and request the regularity trend evolution judgment center to download the data stored in sl j File in j ;

[0097] ECS will determine Ra based on the access policy corresponding to the requested file. k Whether the conditions are met: If the conditions are met, Ra is allowed k Download file j Get M by comparing update with file j In and MD, to determine whether the data source is authentic and valid and whether the data stored in the regularity trend evolution judgment center has been tampered with;

[0098] Decryption key m Get file hydrological data encoding and decoding And use key m The hydrological data trend evolution mapping data m is obtained, and a regularity trend evolution evaluation algorithm is selected to calculate the regularity trend evolution value.

[0099] In another exemplary embodiment, in step (12), verifying the trend sequence set includes:

[0100] Verification of block producing nodes Verify the signature and determine the v in the consensus proposal a , v g , whether the Height is correct; by n+1 The trend sequence collection header is hashed, Block n+1 Is the parent trend sequence set of Block n ; Check Block n+1 Check whether there is any abnormal value assignment for tx in the trend sequence set, and check whether its root hash value is the same as the TX Toot in the trend sequence set header;

[0101] When the master node in the regional block of different time periods of the global or excavation process fails to produce a block within the specified time, the next RA node will produce a block to replace the hydrological data image. The RA node initiates a request to replace the hydrological data image, and other replica nodes verify the request. The RA node collects legal change confirmation messages, and the new RA master node performs the responsibility of generating the prediction and trend sequence set.

[0102] The steps for replacing the hydrological data image by the next replica RA node are as follows:

[0103] 1) The replica RA node initiates a request to replace the hydrological data image:

[0104] The replica RA node discovers the master node Ra k Send hydrographic data image change request when there is a problem To other replica RA nodes, where v a +1 indicates the changed hydrological data image marker. Indicates the ID of the replica RA node that initiates the hydrological data image change request. Indicates the node's verification of the hydrological data image change request, sig agg-p Represents Ra u The cluster verification collected in the previous round of consensus is used to prove the correctness of the trend sequence set with height Height;

[0105] 2) Other replica nodes verify the hydrological data image change request: After receiving the hydrological data image change request, other replica RA nodes verify the request and broadcast the change confirmation message after the verification is passed. in, Indicates the ID of the current replica RA node. Indicates the verification of the change confirmation message by the current replica RA node;

[0106] 3) Replica RA nodes collect legal change confirmation messages: After the replica RA nodes collect ≥ 2f + 1 legal change confirmation messages, for the hydrological data images in the regional blocks during different time periods of the tunneling process, f = f2 is replaced, and for the global hydrological data images, f = f1 is replaced. The identifier of the updated hydrological data image is v a +1; The new RA master node performs the duties of generating the prediction and trend sequence set.

[0107] As can be seen from the above embodiments, the present invention uses the hydrological data trend sequence evolution message strategy attribute decoding to ensure the secure storage of privacy data, and at the same time ensures the control right of the data over the regular trend evolution prediction data.

[0108] Combining the idea of network sharding and clustering verification technology, a two-level judgment mechanism is proposed. First, the consistent hashing algorithm is used for the regional blocks of the tunneling process of network nodes during different time periods. PBFT combined with clustering verification is used to reach a consensus within and between the regional blocks of the tunneling process during different time periods. While improving the processing efficiency of the regular trend evolution prediction results and reducing the communication overhead, this consensus mechanism supports the dynamic changes of nodes. Compared with the prior art, the present invention can reduce the number of communication times required for nodes to reach a consensus from square level to linear level, and the throughput is increased by about 2 - 3 times.

[0109] The present invention uses the idea of network sharding and proposes a two-level judgment mechanism combined with clustering verification. First, the consistent hashing algorithm is used for the regional blocks of the tunneling process of network nodes during different time periods, and PBFT combined with clustering verification is used within and between the regional blocks of the tunneling process during different time periods.

[0110] Among them, the tunneling process stage certification center (IA): acts as the trend sequence evolution set institution and attribute institution in this model. Its main responsibilities include global settings, including system main hydrological data encoding and main hydrological data decoding. In addition, it is also necessary to be responsible for reviewing the tunneling process stage of the enterprises whose water levels and water temperatures are to be predicted, reducing the waste of resources caused by the calculation of invalid data by the regular trend evolution prediction institution, and allocating the tunneling process stage and hydrological data encoding / decoding pair for it. At the same time, it is responsible for reviewing the qualifications of the regular trend evolution prediction institution, increasing its cost of doing evil by raising the threshold for the regular trend evolution prediction institution to join the chain, and allocating the tunneling process stage and attribute hydrological data decoding for it;

[0111] Nodes of water levels and water temperatures to be predicted (EC): Heterogeneous members of the tunneling process stage alliance, providing the data required for the regular trend evolution prediction process (with vulnerabilities, regular trend evolution behaviors), and responsible for decoding and uploading the collected data to the regular trend evolution judgment center;

[0112] Regularity Trend Evolution Prediction Node (RA): Responsible for representing the election of the prediction node group and generating a set of data trend sequences for regularity trend evolution prediction;

[0113] Transmission Channel Chain (AC): Responsible for storing the summary values and important parameters of data related to regularity trend evolution prediction;

[0114] Regularity Trend Evolution Judgment Center (ECS): Responsible for storing the decoded data related to regularity trend evolution prediction.

[0115] Example 3. Exemplarily, in step S3, the historical experience of abnormal coal mine flood data monitored based on image and hydrological data includes: placing cameras at locations such as the heading face, coal mining face, or other working faces in the coal mine where water inrush accidents may occur, drilling hydrological observation holes on the ground to monitor the relevant groundwater status near the mine, and monitoring the water level and water temperature data in the hydrological observation holes;

[0116] Performing real-time monitoring on the video image data. When abnormal water flow appears in the set area in the camera video image and the duration of the water flow exceeds the set time threshold or the increasing speed of the water flow exceeds the set threshold, it is determined as data anomaly; and when it is found that the change in the water level or water temperature of the hydrological observation hole exceeds the set threshold, a flood alarm signal is immediately issued.

[0117] In the simulation comparison between the regularity trend sequence formed in step S3 and the historical experience of abnormal coal mine flood data monitored based on image and hydrological data, the principal component analysis method is used for simulation comparison to obtain a credibility score.

[0118] Example 4, as Figure 3 shown, the coal mine flood alarm system based on image and hydrological data provided by the embodiments of the present invention includes:

[0119] Initial water level and water temperature data acquisition module 1, used to collect the initial state of groundwater in the heading face, coal mining face, and working faces where water inrush accidents occur in the coal mine through a non-destructive detector, and obtain the initial water level and water temperature data of the mine groundwater;

[0120] Regularity trend sequence acquisition module 2, used to obtain the change process of water level and water temperature data during the tunneling process and present it in the form of an image video stream; combining the geological environment factors affecting the change of water level and water temperature data, obtaining the change law of water level and water temperature data in the future tunneling process, forming a regularity trend sequence, and forming a scatter set for abnormal trend points;

[0121] The simulation and comparison module 3 is used to perform simulation and comparison based on the abnormal historical experience of coal mine flood data monitored by images and hydrological data, and obtain a credibility score. The higher the score, the greater the credibility. Based on the credibility score, the water level and water temperature data during the tunneling process are optimized;

[0122] The coal mine flood alarm display module 4 is used to apply the optimized regular trend sequence to the coal mine flood alarm terminal for visual display.

[0123] In the above embodiments, the descriptions of the various embodiments have their own focuses. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0124] For the information interaction, execution process, etc. between the above-mentioned devices / units, since they are based on the same concept as the method embodiments of the present invention, their specific functions and the technical effects brought can be specifically referred to the method embodiment part, and will not be elaborated here.

[0125] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of the functional units and modules are only for the convenience of mutual distinction and do not limit the protection scope of the present invention. The specific working process of the units and modules in the above system can refer to the corresponding process in the foregoing method embodiments.

[0126] The embodiment of the present invention also provides a computer device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor. When the processor executes the computer program, the steps in any of the above method embodiments are implemented.

[0127] The embodiment of the present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps in each of the above method embodiments can be implemented.

[0128] An embodiment of the present invention further provides an information data processing terminal, which is used to provide a user input interface to implement the steps in the above method embodiments when executed on an electronic device. The information data processing terminal is not limited to mobile phones, computers, and switches.

[0129] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above method embodiments of this application, a computer program can be used to instruct relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can at least include: any entity or device capable of carrying the computer program code to the photographing device / terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk, or an optical disc, etc.

[0130] The above is only a relatively preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be covered by the protection scope of the present invention.

Claims

1. A coal mine flood alarm method based on image and hydrological data monitoring, characterized in that: The method includes: S1, using non-destructive detectors to collect the initial state of groundwater at the coal mine excavation working face, coal mining working face and working face where water seepage accidents occur, and obtain the initial water level and water temperature data of the mine groundwater; S2, in the process of excavation, obtain the change history of water level and water temperature data and present it in the form of image video stream; combine the geological environment factors that affect the change of water level and water temperature data to obtain the change law of water level and water temperature data in the future excavation process, form a regular trend sequence, and form a scattered point set for abnormal trend points; S3, simulate and compare the historical experience of coal mine flood data anomalies based on image and hydrological data monitoring to obtain a credibility score. The higher the score, the greater the credibility. Based on the credibility score, optimize the water level and water temperature data during the excavation process. S4, based on the optimized regular trend sequence, is applied to the coal mine flood alarm terminal for visualization; In step S2, a regular trend sequence is formed, including: S201, the system is initialized, the excavation process is allocated, and the regular trend evolution data of each water level and water temperature node to be predicted is uploaded to the regular trend evolution judgment center ; S202, the water level and water temperature nodes to be predicted notify the regularity trend evolution prediction node , the regular trend evolution prediction node predicts the regular trend evolution data updated by the water level and water temperature nodes to be predicted; S203, packaging the regular trend evolution prediction results into a trend sequence set, reaching a consensus within all regular trend evolution prediction nodes based on a two-level judgment mechanism combined with clustering verification, and uploading it through a transmission channel.

2. The method for coal mine flood alarm based on image and hydrological data monitoring according to claim 1 is characterized in that: In step 1, the system is initialized and the tunneling process phases are allocated, including: (1) Certification Center for the Tunneling Process Generate the main hydrological data encoding and decoding pair ,in, For mapping parameters, the system's main hydrological data encoding Public, main hydrological data decoding Certification Centre for the Progress of Development Decrypt and save. For the generation method; (2) Nodes to be predicted Submit to join the transmission channel chain Application, Certification Center for the Tunneling Process After the excavation process is reviewed and passed, it will be the node to be predicted. Assigning the evolution set of trend sequence of tunneling process stages , ,in, It is the node's globally unique tunneling process stage identifier. Encode and decode the hydrological data of the node; (3) Regularity trend evolution prediction node Submit to join the transmission channel chain Application, Certification Center for the Tunneling Process After the qualification review is passed, it will be a regular trend evolution prediction node Assigning the evolution set of trend sequence of tunneling process stages , , and Decoding of generated node attributes and main hydrological data , ,in, It is the node's globally unique tunneling process stage identifier. is the node's hydrological data encoding and decoding pair, express The set of attributes that a node has; It is the main hydrological data interpretation function of node attributes; (4) Nodes to be predicted Evolution message of each hydrological data trend sequence With index combination, composition Collection, with access strategy in the form of hydrological data trend evolution mapping , Symmetric hydrological data encoding and decoding after attribute decoding , The summary value is , to be predicted node Node Pair Verification , the composition file Then, it is sent to the regularity trend evolution judgment center ; (5) Regularity Trend Evolution Judgment Center Receive the corresponding data and verify the node to be predicted , and calculate the set Hash value verification , to the node to be predicted Return to File Storage path ; Node to be predicted Storage path to After that, the message of data update will be sent to Send to node; is the address of the node to be predicted, Verification information of the node to be predicted; (6) Regularity trend evolution prediction node Predict the water level and water temperature nodes to be predicted Updated regular trend evolution data, according to the number of regional blocks in different time periods of the excavation process , calculate the area blocks in different time periods of each excavation process The position on the hash ring is calculated by the formula Calculate each The position of the node on the hash ring; For the address, is a random position; predict nodes according to regular trend evolution The position on the hash ring is to search for the regional block nodes of different time periods of the excavation process clockwise. The first regional block node of different time periods of the excavation process found is the The node belongs to the regional blocks of different time periods of the excavation process; (7) Verify that the regional blocks in different time periods of each excavation process contain regular trend evolution prediction nodes Is the number of is greater than or equal to four? If not, return to reselect the random number calculation Node location, re-excavation process different time period area blocks; if the verification is passed, the excavation process different time period area blocks are determined, and all nodes will retain a list of all nodes and the list of nodes in the excavation process different time period area blocks; (8) Based on the regional block results at different time periods during the tunneling process, The node sets the markers in the area blocks at different time periods of the excavation process, and the hydrological data image markers in the area blocks at different time periods of the excavation process The number of nodes in the area block at different time periods and the excavation process , determine the markers of the main nodes in the area blocks of different time periods of the tunneling process in the current hydrological data image ,in, The positive orientation value is determined for the number of nodes in the regional block at different time periods of the excavation process; a global marker is set for the main node in the regional block at different time periods of each excavation process, and the global hydrological data image marker is used to determine the positive orientation value; the global marker is set for the main node in the regional block at different time periods of each excavation process, and the global marker is used to determine the positive orientation value of the node in the regional block at different time periods of the excavation process; the global marker is set for Number of blocks in different time periods of excavation process , determine the global main node marker in the current hydrological data image , ; (9) Nodes to be predicted Put your own Message, and verification of the message The message is sent to the global master node ; Receive After the news, Message Verification Verify the signature. If it is illegal, a scattered point set is formed. If it is legal, the regular trend evolution prediction related data is determined. (10) Global master node After verifying the authenticity and integrity of the regularity trend evolution prediction related data, make a prediction and record it in the update request table , global master node Treating prediction nodes Recently updated Regularity trend evolution prediction algorithms are used to predict the evolution values ​​of their respective regularity trends. , and update The final regular trend evolution value Generate a regular trend evolution value change information , packed into a trend sequence set; among them, , is the final regular trend evolution value before the change, is the final regular trend evolution value after update, It is the identifier of the regularity trend evolution algorithm based on which the current evaluation result is based. For the current The exact height of the trend series set to which it belongs; is the index; (11) Global master node collect Regularity trend evolution value change information over time , collect the regular trend evolution value change information composition ,but ,in, is a hash pointer pointing to the previous trend sequence set, Indicates the block timestamp. Indicates the master node Verification of trend series set, Indicates the current trend sequence set Composition the roots of a tree; Is the master node address; (12) Global Master Node Send consensus proposal To the master node of the regional block in different time periods of each excavation process, the master node of the regional block in different time periods of each excavation process receives the global master node After the consensus proposal is sent, the hydrological data image markers in the area blocks at different time periods of the excavation process are attached. After that, the excavation process is broadcasted in different time periods of the regional blocks, and the copies in different time periods of the regional blocks of the excavation process are The node verifies the trend sequence set; For the proposal, is the regular trend evolution value; (13) After verification is completed, consensus response messages are sent to the blocks in different time periods of the excavation process. Give the master nodes of the regional blocks in different time periods of the excavation process, among which, For the current copy The node's identifier, For the current copy Node verification of consensus response messages; is the response value; (14) The master node of the regional block in different time periods of the excavation process collects the consensus response messages in the regional blocks in different time periods of the excavation process. When the master node collects more than or equal to After the consensus response message of the regional block in different time periods, including the legitimate mining process of the master node itself, is sent to each copy of the message The validation clustering of nodes is , and sends a global consensus response message to the global master node ,in, is the number of Byzantine nodes in the regional block at different time periods of the mining process, The nodes in the regional blocks of all tunneling processes participating in the generation of cluster verification at different time periods are List; For Node The response value of (15) Global master node Collect global consensus response messages sent by regional block master nodes at different time periods during the excavation process. After a global consensus response message, the cluster verification in the message is clustered again into ; and transmit a consensus confirmation message ,in, For all those involved in generating cluster validation Node List; To entrust data; (16) The node receives the global master node After the consensus confirmation message is sent, use Validation of hydrological data encoding in nodes ,After verification, the set of the consensus trend sequence in this round is synchronized to the transmission channel of this node.

3. The coal mine flood alarm method based on image and monitoring according to claim 1 is characterized in that: In step S203, a consensus is reached based on a two-level judgment mechanism combined with cluster verification, including: Calculate the area blocks at different time periods of the tunneling process Location, calculation Node location, determine the area blocks of different time periods of the excavation process to which the node belongs, and verify the area blocks of different time periods of each excavation process. Number of nodes; Set markers in different time periods of the excavation process and global markers. Consensus proposals are sent to the master nodes of the regional blocks in different time periods of each excavation process. Consensus is reached within the regional blocks in different time periods of the excavation process. The master nodes of the regional blocks in different time periods of the excavation process send global consensus responses to the global master node. Global consensus is reached to form a regular trend sequence. For nodes that have not reached consensus, abnormal trend points are determined and a scattered point set is formed.

4. The method for coal mine flood alarm based on image and hydrological data monitoring according to claim 1 is characterized in that: In step S4, based on the optimized regular trend sequence, it is applied to the coal mine flood alarm terminal, including: first, Every time you pass Process the data once it occurs, and update the regular trend evolution prediction related data for each update , establish an index for identifying the specific serial number of the data in the storage path of the regularity trend evolution judgment center ; Secondly, the hydrological data encoding and decoding space is used to randomly select the symmetric file hydrological data encoding and decoding decoding Get a hydrological data trend sequence evolution message , and follow the custom access policy of the current node ,use Decode symmetric files Hydrological data encoding and decoding get , To compile the function.

5. The method for coal mine flood alarm based on image and hydrological data monitoring according to claim 2 is characterized in that: In step (6), the regular trend evolution prediction node Predict the water level and water temperature nodes to be predicted Updated regular trend evolution data, including: On-duty node Upon receiving After that, use Hydrological data coding right Verify the signature and request the regularity trend evolution judgment center to download the data stored in In ; Will be determined based on the access policy corresponding to the requested file Whether the conditions are met: If the conditions are met, it is allowed download get , by comparison and In and , determine whether the data source is authentic and valid and whether the data stored in the regularity trend evolution judgment center has been tampered with; Decryption Get file hydrological data encoding and decoding , and use Obtain hydrological data trend evolution mapping data , select the regularity trend evolution evaluation algorithm to calculate the regularity trend evolution value.

6. The method for coal mine flood alarm based on image and hydrological data monitoring according to claim 2 is characterized in that: In step (12), the trend sequence set is verified, including: Verification of block producing nodes Verify signatures and determine the consensus proposals Is it correct? The trend sequence collection header is hashed. Is the parent trend series set of ;examine Trend series collection Is there any abnormal assignment, and check whether its root hash value is the same as the one in the trend sequence set header? same; When the master node in the global or excavation process in different time periods fails to produce a block within the specified time, the next The node generates blocks to replace the hydrological data image. The node initiates a request to replace the hydrological data image. Node verification hydrological data image replacement request, Click to collect legal change confirmation messages, from the new The master node performs the forecast and trend series set generation duties.

7. The method for coal mine flood alarm based on image and hydrological data monitoring according to claim 6 is characterized in that: By the next The node generates blocks to replace the hydrological data image, including: 1) Copy The node initiates a request to replace the hydrological data image: Instances Node Discovery Master Send hydrographic data image change request when there is a problem Give a copy Node, where Indicates the changed hydrological data image marker, Indicates a copy of the hydrographic data image change request Node , Indicates the node's verification of the hydrological data image change request. express The cluster verification collected in the previous round of consensus is used to prove that the height is The correctness of the trend series set; 2) The replica node verifies the request to replace the hydrological data image: After receiving the hydrological data image change request, the node verifies the request and broadcasts the change confirmation message after the verification is passed. in, Indicates the current copy Node , Indicates the current copy Node verification of change confirmation messages; 3) Copy Nodes collect confirmation messages of legitimate changes: Replica Nodes collected are greater than or equal to After a legal change confirmation message is received, the hydrological data images in the area blocks at different time periods during the excavation process are replaced , global hydrological data image replacement , update the hydrological data image marker to ; by the new The master node performs the forecast and trend series set generation duties.

8. The method for coal mine flood alarm based on image and hydrological data monitoring according to claim 1 is characterized in that: In step S3, a simulation comparison is performed based on the historical experience of abnormal coal mine flood data monitored by images and hydrological data, including: placing cameras at the underground excavation working face, coal mining working face and working face where water seepage accidents occur in the coal mine, drilling hydrological observation holes on the well to monitor the groundwater status of the mine, and monitoring the water level and water temperature data in the hydrological observation holes; The video image data is monitored in real time. When abnormal water flow is detected in the set area in the camera video image, and the water flow duration exceeds the set time threshold or the water flow increase rate exceeds the set threshold, it is judged as data abnormality; and when it is found that the water level or water temperature change of the hydrological observation hole exceeds the set threshold, a flood alarm signal is immediately issued.

9. The method for coal mine flood alarm based on image and hydrological data monitoring according to claim 4, characterized in that: The credibility score is obtained by simulation and comparison based on the formation of regular trend sequences and the historical experience of coal mine flood data anomalies based on image and hydrological data monitoring.

Images