Fault remote analysis system and method for negative pressure station

Abstract

The invention discloses a remote fault analysis system and method for a negative pressure station, and relates to the technical field of big data analysis. Historical normal operation industrial parameters and fault maintenance information of the negative pressure station are collected, and a unique traceability identifier is added; the load working conditions are divided into high, medium and low classes according to a preset threshold value, and normal operation industrial parameter references corresponding to the working conditions are constructed; comparing the historical fault information with a normal industrial standard, generating an abnormal starting feature sequence and an abnormal ending feature sequence, and constructing a first industrial operation and maintenance reference library and a second industrial operation and maintenance reference library; collecting real-time industrial parameters, calling the reference library to calculate a score when the industrial parameters are abnormal, and generating a troubleshooting guide; the system comprises a historical industrial information processing module, a normal industrial standard construction module, an operation and maintenance reference library construction module and a real-time fault processing module which are electrically connected. The method improves the reference accuracy, achieves the quick positioning of a fault, improves the maintenance efficiency, and reduces the shutdown influence of equipment.

Description

Technical Field

[0001] This invention relates to the field of big data analytics, specifically to a remote fault analysis system and method for negative pressure stations. Background Technology

[0002] As a key industrial equipment in industrial production, negative pressure stations play a crucial role in maintaining a specific negative pressure environment and ensuring the safe transport of media. Therefore, negative pressure stations generally have remote fault analysis capabilities, which can monitor faults in negative pressure stations. However, existing technologies can only determine whether a fault has occurred, but cannot perform fault analysis based on the real-time industrial parameters of the negative pressure station. Maintenance personnel still need to go to the site for a comprehensive investigation to locate the fault, resulting in low maintenance efficiency. Summary of the Invention

[0003] The purpose of this invention is to provide a remote fault analysis system and method for negative pressure stations to solve the problems raised in the prior art.

[0004] To achieve the above objectives, the present invention provides the following technical solution: a remote fault analysis method for negative pressure stations, the remote fault analysis method comprising the following steps: Step S1: Collect historical industrial information of the negative pressure station. The historical industrial information includes historical normal operation industrial parameters and historical fault maintenance information, and is accompanied by a unique traceability identifier. Step S2: Extract the industrial parameters of the negative pressure station under different load conditions. The load conditions are divided into high load conditions, medium load conditions, and low load conditions. Based on the load conditions, construct the industrial parameter benchmark for the normal operation of the negative pressure station and use it as the normal industrial benchmark. Step S3: Compare historical fault repair information with normal industrial benchmarks to generate an abnormal feature sequence for each historical fault repair information. The abnormal feature sequence includes an abnormal start feature sequence and an abnormal end feature sequence. Construct a first industrial operation and maintenance reference library and a second industrial operation and maintenance reference library. Step S4: Collect real-time industrial parameters of the negative pressure station and compare them with normal industrial benchmarks. If an anomaly occurs, call the first industrial operation and maintenance reference library and the second industrial operation and maintenance reference library to calculate the reference score and generate a fault troubleshooting guide.

[0005] Furthermore, the specific steps of step S1 are as follows: Step S1-1: Extract historical normal operation information from the operation log and sensor database, and extract historical fault repair information from the maintenance record and alarm system log. The historical normal operation industrial parameters and historical fault repair information both include negative pressure value, fan speed, motor current, and load conditions. The historical fault repair information also includes fault type and fault handling process. Step S1-2: Assign a unique traceability identifier to each piece of historical industrial information. This unique traceability identifier is associated with all data in this piece of historical industrial information. The unique traceability identifier is generated randomly.

[0006] Furthermore, the specific steps of step S2 are as follows: Step S2-1: Divide the normal operation information according to the load conditions. The load conditions are divided according to a preset first threshold and a second threshold. The high load is greater than the second threshold, the medium load is lower than the second threshold but greater than the first threshold, and the low load is less than the first threshold. Step S2-2: Extract all data of a certain parameter under a certain load condition, calculate its average value, take the highest value of this parameter as the upper limit of this parameter, and the lowest value as the lower limit of this parameter, and mark it as the normal operating range. Step S2-3: Collect the normal operating range of all parameters to form the normal operating industrial parameter benchmark, and use it as the normal industrial benchmark.

[0007] Furthermore, the specific steps of step S3 are as follows: Step S3-1: Obtain historical fault repair information and classify it according to load conditions. The load conditions are divided into high load conditions, medium load conditions, and low load conditions. The division of load conditions is based on a preset first threshold and a second threshold. High load is greater than the second threshold, medium load is lower than the second threshold but greater than the first threshold, and low load is less than the first threshold. Step S3-2: Extract a historical fault maintenance information for a certain load condition, align all its parameters in time sequence, plot them as curves, compare them with the normal industrial benchmark for the same load condition, and mark the intersections that exceed the normal industrial benchmark. Step S3-3: The intersection points of curves with slopes greater than 0 and the upper limit, and the intersection points of curves with slopes less than 0 and the lower limit are recorded as abnormal starting nodes. The abnormal starting nodes are associated with the parameter name of the curve they belong to and whether the slope is greater than 0. The abnormal starting nodes are sorted according to time sequence to form an abnormal starting feature sequence. The abnormal starting feature sequence includes the first abnormal starting node, the second abnormal starting node, ..., the nth abnormal starting node. The abnormal starting feature sequence is bound to the unique traceability identifier of historical fault maintenance information to construct the first industrial operation and maintenance reference library. Step S3-4: The intersection points of curves with slopes less than 0 and the upper limit, and the intersection points of curves with slopes greater than 0 and the lower limit, are recorded as abnormal start nodes and abnormal end nodes. The abnormal end node is associated with the parameter name of the curve it belongs to, indicating whether the slope is greater than 0. The abnormal end nodes are sorted according to time sequence to form an abnormal end feature sequence. The abnormal end feature sequence includes the first abnormal end node, the second abnormal end node, ..., the nth abnormal end node. The abnormal end feature sequence is combined with the unique traceability identifier of historical fault maintenance information to construct a second industrial operation and maintenance reference library.

[0008] Furthermore, the specific steps of step S4 are as follows: Step S4-1: Based on the collected real-time industrial parameters and load conditions, match the normal industrial benchmark under the corresponding load conditions constructed in step S2; compare the real-time operating parameters with the normal operating range of each parameter in the corresponding normal industrial benchmark one by one. Step S4-2: If an anomaly occurs, use the method in S3 to generate the anomaly start feature sequence and the anomaly end feature sequence; Step S4-3: Compare the anomaly start feature sequence with the first industrial operation and maintenance reference library, record the number of identical anomaly start nodes, record it as the first score and attach the corresponding unique traceability identifier, compare the anomaly end feature sequence with the second industrial operation and maintenance reference library, record the number of identical anomaly end nodes, record it as the second score and attach the corresponding unique traceability identifier, and add the first score and the second score with the unique traceability identifier to obtain the reference score. Step S4-4: If there are cases with the same reference score, check the fault type based on the unique traceability identifier, count the number of each fault type, sort them in descending order of the number, and generate a fault troubleshooting guide.

[0009] Furthermore, the remote fault analysis system includes a historical industrial information processing module, a normal industrial benchmark construction module, an operation and maintenance reference library construction module, and a real-time fault handling module. The historical industrial information processing module is used to collect historical industrial information of the negative pressure station and assign it a unique traceability identifier; the normal industrial benchmark construction module is used to construct a normal operating industrial parameter benchmark based on the normal operating information of the negative pressure station; the operation and maintenance reference library construction module is used to construct an operation and maintenance reference library for the negative pressure station based on the comparison of historical fault repair information with the normal industrial benchmark; the real-time fault handling module is used to collect real-time industrial parameters of the negative pressure station and compare them with the normal industrial benchmark, and generate a fault troubleshooting guide if an anomaly is found. The output of the historical industrial information processing module is electrically connected to the input of the normal industrial benchmark construction module; the output of the normal industrial benchmark construction module is electrically connected to the input of the operation and maintenance reference library construction module; and the output of the operation and maintenance reference library construction module is electrically connected to the input of the real-time fault handling module.

[0010] Furthermore, the historical industrial information processing module includes a historical industrial information acquisition unit and a traceability identifier allocation unit; The historical industrial information acquisition unit is used to extract historical normal operation information from operation logs and sensor databases, and historical fault maintenance information from maintenance records and alarm system logs; the traceability identifier allocation unit is used to assign a unique traceability identifier to each piece of historical industrial information and associate it with all data in this piece of historical industrial information.

[0011] Furthermore, the normal industrial benchmark construction module includes a load condition division unit and a normal industrial parameter benchmark unit; The load condition classification unit is used to classify load conditions into high load conditions, medium load conditions, and low load conditions according to a preset first threshold and a second threshold. The normal industrial parameter benchmark unit is used to extract parameter data under a certain load condition, calculate the mean, determine the upper and lower limits to form a normal operating range, and then collect all parameter normal operating ranges to form an industrial parameter benchmark.

[0012] Furthermore, the operation and maintenance reference library construction module includes an anomaly feature sequence unit and a reference library generation unit; The abnormal feature sequence unit is used to perform time-series alignment and plotting of historical fault maintenance information parameters under a certain load condition, compare and mark abnormal nodes with normal industrial benchmarks, and then generate an abnormal start feature sequence and an abnormal end feature sequence; the reference library generation unit is used to bind the abnormal start feature sequence and the abnormal end feature sequence to the unique traceability identifier of historical fault maintenance information, respectively, to construct the first industrial operation and maintenance reference library and the second industrial operation and maintenance reference library.

[0013] Furthermore, the real-time fault handling module includes a real-time industrial parameter comparison unit and a fault guide generation unit; The real-time industrial parameter comparison unit is used to match the corresponding normal industrial benchmark according to the load conditions of the real-time industrial parameters, compare the real-time operating parameters with the normal industrial benchmark, and generate an abnormal start feature sequence and an abnormal end feature sequence if there is an anomaly. The fault guide generation unit is used to compare the abnormal feature sequence with the operation and maintenance reference library to calculate the reference score. If the scores are the same, the number of fault types is counted and sorted to generate a fault troubleshooting guide.

[0014] Compared with the prior art, the beneficial effects of the present invention are: 1. This invention divides and constructs corresponding normal industrial benchmarks by different load conditions, rather than using a single benchmark. This makes the normal operating range more consistent with the actual operating status of the negative pressure station under different conditions, effectively reducing abnormal misjudgments caused by differences in operating conditions, improving the accuracy and adaptability of normal industrial benchmarks, making subsequent real-time industrial parameter comparisons more accurate, and avoiding unnecessary shutdowns or equipment risks caused by misjudgments or missed judgments.

[0015] 2. This invention generates anomaly start and end feature sequences by comparing historical fault maintenance information with normal industrial benchmarks and constructs two types of operation and maintenance reference libraries, accurately binding historical faults with features. This allows historical fault experience to be transformed into structured reference data, which can be directly called upon to match features, providing data support for quickly locating fault types.

[0016] 3. This invention compares real-time industrial parameter anomalies with the operation and maintenance reference library and calculates a reference score. It can also generate troubleshooting guidelines by sorting the number of fault types when the scores are the same, providing maintenance personnel with clear fault troubleshooting priorities, greatly shortening fault location time, significantly improving maintenance efficiency, and reducing the impact of equipment downtime. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating a remote fault analysis method for a negative pressure station according to the present invention. Figure 2 This is a schematic diagram of the structure of a remote fault analysis system for a negative pressure station according to the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] Example 1: As Figure 1 As shown, the present invention provides a technical solution, a remote fault analysis method for negative pressure stations, the remote fault analysis method comprising the following steps: Step S1: Collect historical industrial information of the negative pressure station. The historical industrial information includes historical normal operation industrial parameters and historical fault maintenance information, and is accompanied by a unique traceability identifier. The specific steps of step S1 are as follows: Step S1-1: Extract historical normal operation information from the operation log and sensor database, and extract historical fault repair information from the maintenance record and alarm system log. The historical normal operation industrial parameters and historical fault repair information both include negative pressure value, fan speed, motor current, and load conditions. The historical fault repair information also includes fault type and fault handling process. Step S1-2: Assign a unique traceability identifier to each piece of historical industrial information. This unique traceability identifier is associated with all data in this piece of historical industrial information. The unique traceability identifier is generated randomly. Step S2: Extract the industrial parameters of the negative pressure station under different load conditions. The load conditions are divided into high load conditions, medium load conditions, and low load conditions. Based on the load conditions, construct the industrial parameter benchmark for the normal operation of the negative pressure station and use it as the normal industrial benchmark. The specific steps of step S2 are as follows: Step S2-1: Divide the normal operation information according to the load conditions. The load conditions are divided according to a preset first threshold and a second threshold. The high load is greater than the second threshold, the medium load is lower than the second threshold but greater than the first threshold, and the low load is less than the first threshold. Step S2-2: Extract all data of a certain parameter under a certain load condition, calculate its average value, take the highest value of this parameter as the upper limit of this parameter, and the lowest value as the lower limit of this parameter, and mark it as the normal operating range. Step S2-3: Collect the normal operating range of all parameters to form the normal operating industrial parameter benchmark, and use it as the normal industrial benchmark; Step S3: Compare historical fault repair information with normal industrial benchmarks to generate an abnormal feature sequence for each historical fault repair information. The abnormal feature sequence includes an abnormal start feature sequence and an abnormal end feature sequence. Construct a first industrial operation and maintenance reference library and a second industrial operation and maintenance reference library. The specific steps of step S3 are as follows: Step S3-1: Obtain historical fault repair information and classify it according to load conditions. The load conditions are divided into high load conditions, medium load conditions, and low load conditions. The division of load conditions is based on a preset first threshold and a second threshold. High load is greater than the second threshold, medium load is lower than the second threshold but greater than the first threshold, and low load is less than the first threshold. Step S3-2: Extract a historical fault maintenance information for a certain load condition, align all its parameters in time sequence, plot them as curves, compare them with the normal industrial benchmark for the same load condition, and mark the intersections that exceed the normal industrial benchmark. Step S3-3: The intersection points of curves with slopes greater than 0 and the upper limit, and the intersection points of curves with slopes less than 0 and the lower limit are recorded as abnormal starting nodes. The abnormal starting nodes are associated with the parameter name of the curve they belong to and whether the slope is greater than 0. The abnormal starting nodes are sorted according to time sequence to form an abnormal starting feature sequence. The abnormal starting feature sequence includes the first abnormal starting node, the second abnormal starting node, ..., the nth abnormal starting node. The abnormal starting feature sequence is bound to the unique traceability identifier of historical fault maintenance information to construct the first industrial operation and maintenance reference library. Step S3-4: The intersection points of curves with slopes less than 0 and the upper limit, and the intersection points of curves with slopes greater than 0 and the lower limit, are recorded as abnormal start nodes and abnormal end nodes. The abnormal end node is associated with the parameter name of the curve it belongs to, indicating whether the slope is greater than 0. The abnormal end nodes are sorted according to time sequence to form an abnormal end feature sequence. The abnormal end feature sequence includes the first abnormal end node, the second abnormal end node, ..., the nth abnormal end node. The abnormal end feature sequence is combined with the unique traceability identifier of historical fault maintenance information to construct a second industrial operation and maintenance reference library. Step S4: Collect real-time industrial parameters of the negative pressure station and compare them with normal industrial benchmarks. If an anomaly occurs, call the first industrial operation and maintenance reference library and the second industrial operation and maintenance reference library to calculate the reference score and generate a fault troubleshooting guide. The specific steps of step S4 are as follows: Step S4-1: Based on the collected real-time industrial parameters and load conditions, match the normal industrial benchmark under the corresponding load conditions constructed in step S2; compare the real-time operating parameters with the normal operating range of each parameter in the corresponding normal industrial benchmark one by one. Step S4-2: If an anomaly occurs, use the method in S3 to generate the anomaly start feature sequence and the anomaly end feature sequence; Step S4-3: Compare the anomaly start feature sequence with the first industrial operation and maintenance reference library, record the number of identical anomaly start nodes, record it as the first score and attach the corresponding unique traceability identifier, compare the anomaly end feature sequence with the second industrial operation and maintenance reference library, record the number of identical anomaly end nodes, record it as the second score and attach the corresponding unique traceability identifier, and add the first score and the second score with the unique traceability identifier to obtain the reference score. Step S4-4: If there are cases with the same reference score, check the fault type based on the unique traceability identifier, count the number of each fault type, sort them in descending order of the number, and generate a fault troubleshooting guide.

[0020] For example: This embodiment takes the negative pressure station supporting the sewage treatment in the industrial park as the application object. The negative pressure station is used to extract biogas and odorous gases in the sewage tank. The core operating parameters include negative pressure value, fan speed and motor current. There are three load conditions: high, medium and low in daily operation.

[0021] Through the historical industrial information collection unit, historical normal operation information is extracted from the negative pressure station operation log and sensor database, and historical fault maintenance information is extracted from the maintenance records of the maintenance management system and the alarm system log.

[0022] Through the traceability identifier allocation unit, a unique traceability identifier is generated for each piece of historical industrial information using Python's UUID library, and associated with all data such as the load conditions, parameter changes, fault type, and handling process of the fault.

[0023] The load condition division unit of the normal industrial benchmark construction module divides the extracted historical normal operation information into three types of load condition datasets: high, medium, and low, according to the preset first threshold of 40% and the second threshold of 80%, and collects the normal operation range of all parameters under the three types of load conditions.

[0024] The anomaly feature sequence unit of the operation and maintenance reference library construction module divides historical fault maintenance information according to load conditions. The anomaly start nodes are: the intersection of the motor current curve with a slope > 0 at 40 min and the upper limit of 14A; the intersection of the negative pressure curve with a slope < 0 at 60 min and the lower limit of -40kPa; and the intersection of the fan speed curve with a slope < 0 at 65 min and the lower limit of 1500r / min. They are sorted in time sequence as (40 min, motor current, slope > 0), (60 min, negative pressure, slope < 0), (65 min, fan speed, slope < 0)”, and a unique traceability identifier is bound to it and stored in the first industrial operation and maintenance reference library.

[0025] Abnormal termination node: After fault handling, the intersection points of the motor current curve with slope < 0 at 100 min and the upper limit of 14A, the intersection points of the fan speed curve with slope > 0 at 115 min and the lower limit of 1500r / min, and the intersection points of the negative pressure curve with slope > 0 at 120 min and the lower limit of -40kPa are sorted, bound with a unique traceability identifier, and stored in the second industrial operation and maintenance reference library.

[0026] Real-time industrial parameter acquisition and benchmark matching: The real-time industrial parameter comparison unit of the real-time fault handling module detects that the load condition is medium load by acquiring parameters and matches it with the normal industrial benchmark for medium load.

[0027] Anomaly identification and feature sequence generation: Generate the anomaly initial feature sequence according to step S3: 30min, motor current, slope>0), (45min, negative pressure value, slope<0), (50min, fan speed, slope<0).

[0028] Reference score calculation: The fault guide generation unit compares the sequence with the first industrial operation and maintenance reference library. The number of identical starting nodes is 3, so the first score is 3. After comparing the abnormal end sequence, the second score is 2, so the reference score is 3+2=5.

[0029] Troubleshooting guide generation: For faults with no other reference score of 5, directly associate them with the corresponding fault; if there are other faults with a reference score of 5, which have occurred 3 times in the past, and the corresponding fault has occurred 5 times in the past, sort them in descending order of the number of faults and generate a troubleshooting guide.

[0030] Example 2, as Figure 2 As shown, the present invention provides a remote fault analysis system for negative pressure stations. The remote fault analysis system includes a historical industrial information processing module, a normal industrial benchmark construction module, an operation and maintenance reference library construction module, and a real-time fault handling module. The historical industrial information processing module is used to collect historical industrial information of the negative pressure station and assign it a unique traceability identifier; the normal industrial benchmark construction module is used to construct a normal operating industrial parameter benchmark based on the normal operating information of the negative pressure station; the operation and maintenance reference library construction module is used to construct an operation and maintenance reference library for the negative pressure station based on the comparison of historical fault repair information with the normal industrial benchmark; the real-time fault handling module is used to collect real-time industrial parameters of the negative pressure station and compare them with the normal industrial benchmark, and generate a fault troubleshooting guide if an anomaly is found. The output of the historical industrial information processing module is electrically connected to the input of the normal industrial benchmark construction module; the output of the normal industrial benchmark construction module is electrically connected to the input of the operation and maintenance reference library construction module; and the output of the operation and maintenance reference library construction module is electrically connected to the input of the real-time fault handling module.

[0031] The historical industrial information processing module includes a historical industrial information collection unit and a traceability identifier allocation unit. The historical industrial information acquisition unit is used to extract historical normal operation information from operation logs and sensor databases, and historical fault maintenance information from maintenance records and alarm system logs; the traceability identifier allocation unit is used to assign a unique traceability identifier to each piece of historical industrial information and associate it with all data in this piece of historical industrial information.

[0032] The normal industrial benchmark construction module includes a load condition division unit and a normal industrial parameter benchmark unit; The load condition classification unit is used to classify load conditions into high load conditions, medium load conditions, and low load conditions according to a preset first threshold and a second threshold. The normal industrial parameter benchmark unit is used to extract parameter data under a certain load condition, calculate the mean, determine the upper and lower limits to form a normal operating range, and then collect all parameter normal operating ranges to form an industrial parameter benchmark.

[0033] The operation and maintenance reference library construction module includes an anomaly feature sequence unit and a reference library generation unit; The abnormal feature sequence unit is used to perform time-series alignment and plotting of historical fault maintenance information parameters under a certain load condition, compare and mark abnormal nodes with normal industrial benchmarks, and then generate an abnormal start feature sequence and an abnormal end feature sequence; the reference library generation unit is used to bind the abnormal start feature sequence and the abnormal end feature sequence to the unique traceability identifier of historical fault maintenance information, respectively, to construct the first industrial operation and maintenance reference library and the second industrial operation and maintenance reference library.

[0034] The real-time fault handling module includes a real-time industrial parameter comparison unit and a fault guide generation unit. The real-time industrial parameter comparison unit is used to match the corresponding normal industrial benchmark according to the load conditions of the real-time industrial parameters, compare the real-time operating parameters with the normal industrial benchmark, and generate an abnormal start feature sequence and an abnormal end feature sequence if there is an anomaly. The fault guide generation unit is used to compare the abnormal feature sequence with the operation and maintenance reference library to calculate the reference score. If the scores are the same, the number of fault types is counted and sorted to generate a fault troubleshooting guide.

[0035] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A method for remote failure analysis of a negative pressure station, characterized in that: The fault remote analysis method comprises the following steps: Step S1, collecting historical industrial information of the negative pressure station, the historical industrial information comprising historical normal operation industrial parameters and historical fault maintenance information, and adding a unique traceable identifier; Step S2, extracting industrial parameters of the negative pressure station under different load conditions, the load conditions being divided into high load conditions, medium load conditions and low load conditions, and constructing an industrial parameter benchmark for normal operation of the negative pressure station according to the load conditions, which is taken as a normal industrial benchmark; Step S3, comparing the historical fault maintenance information with the normal industrial benchmark to generate an abnormal feature sequence of each piece of historical fault maintenance information, the abnormal feature sequence comprising an abnormal starting feature sequence and an abnormal ending feature sequence, and constructing a first industrial operation and maintenance reference library and a second industrial operation and maintenance reference library; Step S4, collecting real-time industrial parameters of the negative pressure station, comparing them with the normal industrial benchmark, and if an abnormality occurs, calling the first industrial operation and maintenance reference library and the second industrial operation and maintenance reference library to calculate a reference score and generate a fault troubleshooting guide.

2. A method for remote failure analysis of a negative pressure station according to claim 1, characterized in that: The specific steps of step S1 are as follows: Step S1-1, extracting historical normal operation information from operation logs and sensor databases, and extracting historical fault maintenance information from maintenance records and alarm system logs, the historical normal operation industrial parameters and the historical fault maintenance information both comprising negative pressure values, fan speeds and motor currents, and being marked with load conditions; the historical fault maintenance information further comprising fault types and fault handling processes; Step S1-2, assigning a unique traceable identifier to each piece of historical industrial information, the unique traceable identifier being associated with all data in this piece of historical industrial information, and the unique traceable identifier being randomly generated.

3. The method for remote failure analysis of a negative pressure station of claim 1, wherein: The specific steps of step S2 are as follows: Step S2-1, dividing the normal operation information according to load conditions, the division of the load conditions being performed according to preset first and second thresholds, the high load being greater than the second threshold, the medium load being less than the second threshold and greater than the first threshold, and the low load being less than the first threshold; Step S2-2, extracting all data of a parameter under a certain load condition, calculating the average value, taking the maximum value of the parameter as the upper limit of the parameter, and taking the minimum value as the lower limit of the parameter, and marking as a normal operation interval; Step S2-3, collecting normal operation intervals of all parameters to form an industrial parameter benchmark for normal operation, which is taken as a normal industrial benchmark.

4. The method for remote failure analysis of a negative pressure station of claim 1, wherein: The specific steps of step S3 are as follows: Step S3-1, obtaining historical fault maintenance information, dividing it according to load conditions, the division of the load conditions being performed according to preset first and second thresholds, the high load being greater than the second threshold, the medium load being less than the second threshold and greater than the first threshold, and the low load being less than the first threshold; Step S3-2, extracting a piece of historical fault maintenance information under a certain load condition, time-aligning all parameters of the piece of historical fault maintenance information, and respectively drawing curves, and comparing them with a normal industrial benchmark of the same load condition, and marking the intersection points that exceed the normal industrial benchmark; Step S3-3, the intersection point of the curve with a slope greater than 0 and the upper limit and the intersection point of the curve with a slope less than 0 and the lower limit are recorded as abnormal starting nodes, the abnormal starting nodes are additionally provided with the parameter name of the curve and whether the slope is greater than 0, the abnormal starting nodes are sorted in time sequence to form an abnormal starting feature sequence, the abnormal starting feature sequence includes a first abnormal starting node, a second abnormal starting node,..., and an n-th abnormal starting node, the abnormal starting feature sequence is bound to the unique traceability identifier of the historical fault maintenance information, and a first industrial operation and maintenance reference library is constructed; Step S3-4, the intersection point of the curve with a slope less than 0 and the upper limit and the intersection point of the curve with a slope greater than 0 and the lower limit are recorded as abnormal ending nodes, the abnormal ending nodes are additionally provided with the parameter name of the curve and whether the slope is greater than 0, the abnormal ending nodes are sorted in time sequence to form an abnormal ending feature sequence, the abnormal ending feature sequence includes a first abnormal ending node, a second abnormal ending node,..., and an n-th abnormal ending node, the abnormal ending feature sequence is bound to the unique traceability identifier of the historical fault maintenance information, and a second industrial operation and maintenance reference library is constructed.

5. The method for remote failure analysis of a negative pressure station of claim 1, wherein: The specific steps of the step S4 are as follows: Step S4-1, according to the collected real-time industrial parameters and load working conditions, the normal industrial reference corresponding to the load working conditions constructed in step S2 is matched; the real-time operation parameters are compared with each parameter normal operation interval in the corresponding normal industrial reference one by one; Step S4-2, if an abnormality occurs, the abnormal starting feature sequence and the abnormal ending feature sequence are generated by the method of S3; Step S4-3, the abnormal starting feature sequence and the first industrial operation and maintenance reference library are compared, the number of abnormal starting nodes that are the same is recorded, recorded as a first score and additionally provided with the corresponding unique traceability identifier, the abnormal ending feature sequence and the second industrial operation and maintenance reference library are compared, the number of abnormal ending nodes that are the same is recorded, recorded as a second score and additionally provided with the corresponding unique traceability identifier, and the first score and the second score with the unique traceability identifier are added to obtain a reference score; Step S4-4, if there is a case that the reference scores are the same, the fault type is checked according to the unique traceability identifier, the number of each fault type is counted, and the number is sorted in descending order to generate a fault troubleshooting guide.

6. A system for remote analysis of a malfunction of a negative pressure station, applied to the method for remote analysis of a malfunction of a negative pressure station according to any one of claims 1 to 5, characterized in that: The fault remote analysis system comprises a historical industrial information processing module, a normal industrial reference construction module, an operation and maintenance reference library construction module, and a real-time fault disposal module; The historical industrial information processing module is used for collecting historical industrial information of the negative pressure station and assigning a unique traceability identifier to the historical industrial information; the normal industrial reference construction module is used for constructing an industrial parameter reference of normal operation according to normal operation information of the negative pressure station; and the operation and maintenance reference library construction module is used for constructing an operation and maintenance reference library of the negative pressure station according to comparison between historical fault maintenance information and the normal industrial reference; The real-time fault disposal module is used for collecting real-time industrial parameters of the negative pressure station and comparing the real-time industrial parameters with the normal industrial reference, and generating a fault troubleshooting guide if an abnormality occurs. The historical industrial information processing module output is electrically connected to the normal industrial benchmark construction module input; the normal industrial benchmark construction module output is electrically connected to the operation and maintenance reference library construction module input; and the operation and maintenance reference library construction module output is electrically connected to the real-time fault handling module input.

7. The fault remote analysis system for a negative pressure station according to claim 6, characterized in that: The historical industrial information processing module comprises a historical industrial information acquisition unit and a traceability identification allocation unit; The historical industrial information acquisition unit is used to extract historical normal operation information from operation logs and sensor databases, and extract historical fault maintenance information from maintenance records and alarm system logs; and the traceability identification allocation unit is used to allocate a unique traceability identification to each piece of historical industrial information, and associate all data in the piece of historical industrial information.

8. The fault remote analysis system for a negative pressure station according to claim 6, characterized in that: The normal industrial benchmark construction module comprises a load working condition division unit and a normal industrial parameter benchmark unit; The load working condition division unit is used to divide load working conditions into high load working conditions, medium load working conditions and low load working conditions according to preset first and second threshold values; and the normal industrial parameter benchmark unit is used to extract parameter data under a certain load working condition, calculate a mean value, determine upper and lower limits to form a normal operation interval, and then collect all parameter normal operation intervals to form an industrial parameter benchmark.

9. The fault remote analysis system for a negative pressure station according to claim 6, characterized in that: The operation and maintenance reference library construction module comprises an abnormal feature sequence unit and a reference library generation unit; The abnormal feature sequence unit is used to perform time sequence alignment and drawing on historical fault maintenance information parameters of a certain load working condition, mark abnormal nodes by comparing with a normal industrial benchmark, and then generate an abnormal start feature sequence and an abnormal end feature sequence; The reference library generation unit is used to bind the abnormal start feature sequence and the abnormal end feature sequence to the unique traceability identification of the historical fault maintenance information respectively, and construct a first industrial operation and maintenance reference library and a second industrial operation and maintenance reference library.

10. The fault remote analysis system for a negative pressure station according to claim 6, characterized in that: The real-time fault handling module comprises a real-time industrial parameter comparison unit and a fault guide generation unit; The real-time industrial parameter comparison unit is used to match corresponding normal industrial benchmarks according to load working conditions of real-time industrial parameters, compare real-time operation parameters with the normal industrial benchmarks, and generate an abnormal start feature sequence and an abnormal end feature sequence if abnormal; The fault guide generation unit is used to compare abnormal feature sequences with operation and maintenance reference libraries to calculate reference scores, count fault type quantities and sort them if the scores are the same, and generate a fault troubleshooting guide.

Images