Intelligent monitoring system for unattended station geoelectric instrument and terminal equipment

Abstract

The invention relates to the technical field of control management, and discloses an intelligent monitoring system for an unattended station geoelectric instrument and terminal equipment. Comprising the following steps: acquiring basic characteristics of a geoelectric instrument, judging whether a safe operation time period exists or not, dividing a monitoring period into sub-time periods, acquiring comprehensive operation parameters of the geoelectric instrument in the sub-time periods, predicting an operation state value of the next sub-time period, judging whether an abnormal early warning prompt is sent or not, marking control parameters, and judging whether the abnormal early warning prompt is sent or not. Transmitting the control parameters to a user side; compared with the prior art, the method can avoid the additional burden caused by the execution of the subsequent steps by the geoelectric instrument which does not meet the intelligent monitoring requirement, can predict the operation state of the geoelectric instrument in the future in advance, avoids the hysteresis of the real-time monitoring and fault early warning of the geoelectric instrument, and improves the fault early warning efficiency. Therefore, the real-time operation state of the geoelectric instrument can be remotely and intelligently monitored under the condition that the station is unattended.

Description

Technical Field

[0001] The present invention relates to the field of control management technology, and more specifically, to an intelligent monitoring system and terminal equipment for geoelectric instruments at unmanned stations. Background Art

[0002] As an important geophysical measuring instrument, geoelectric meters are widely used in the fields of georesistivity observation, electrical structure of underground media, disaster prevention and control at stations. With the development of Internet of Things technology and artificial intelligence, the intelligent monitoring system of geoelectric meters has gradually become an important means to improve equipment management efficiency and measurement accuracy in stations. It can also play a role in intelligent monitoring and fault prediction of geoelectric meters in unmanned stations, thereby improving the level of remote operation and maintenance technology of stations and reducing the operation and maintenance costs of stations.

[0003] The patent application with reference publication number CN110134053A discloses a monitoring configuration method, device and equipment for rapid response to power outage due to distribution transformer fault, including obtaining power outage logs of power equipment; checking each power outage log in a polling manner, and judging whether the power equipment corresponding to each power outage log is in an abnormal power outage state according to a preset power restoration rule; if so, establishing a power restoration work order for the power equipment with abnormal power outage according to the information of the power equipment with abnormal power outage, so as to restore the power of the power equipment with abnormal power outage; it can effectively save the cost of manual screening and review, and greatly reduce the error rate, optimize the control process of power restoration of power equipment faults, speed up the processing speed of power outage and restoration of power equipment, ensure the timely maintenance of faulty power equipment, and thus ensure the timely repair of faults; Existing intelligent monitoring systems usually use real-time collection and analysis of geoelectric meter operating parameters to determine whether there are any abnormal faults in the real-time operating status of the geoelectric meter, and remotely control the geoelectric meter when an abnormal fault occurs. For example, in the above-mentioned patent application, it polls the power outage log and judges abnormal power outages in combination with preset power restoration rules, thereby monitoring and predicting the operating status of the power equipment in real time. However, since the geoelectric meter needs to be in a continuous and uninterrupted operating state, when real-time data is collected and abnormal fault conditions are analyzed, the geoelectric meter has already experienced abnormal faults. As a result, this method cannot perform advance prediction operations before the geoelectric meter has abnormal faults, resulting in a lag in the intelligent monitoring operation of the geoelectric meter in the station, and it is impossible to make accurate and advance analysis and judgment operations on the future operating status of the geoelectric meter, thereby reducing the intelligent monitoring effect of the geoelectric meter in the unmanned station.

[0004] In view of this, the present invention proposes an unmanned station geoelectric instrument intelligent monitoring system and terminal equipment to solve the above problems. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solutions: an intelligent monitoring system for geoelectric instruments at unmanned stations, applied to a controller, comprising: The feature extraction module is used to obtain the operation events of the geoelectric instrument in the working state, and extract basic features from the operation events, the basic features including the measurement error peak value and the fault triggering peak value; The identification and determination module is used to identify abnormalities of basic features based on abnormality identification criteria, identify the operating attributes of the geoelectric instrument, the operating attributes include reliable attributes and unreliable attributes, and determine whether there is a safe operating period; A parameter acquisition module is used to mark the monitoring period in the safe operation period, divide the monitoring period into sub-periods, and collect the comprehensive operation parameters of the geoelectric instrument in the sub-periods, the comprehensive operation parameters including temperature value, humidity value, measured voltage difference, measured current difference and host power supply voltage; The prediction and judgment module is used to input the collected comprehensive operating parameters into the pre-trained neural network model to predict the operating status value of the next sub-period, which includes normal status and abnormal status, and determine whether to issue an abnormal warning prompt; The parameter reporting module is used to mark the control parameters from the comprehensive operating parameters, transmit the control parameters to the user end, and generate an intelligent monitoring report after summarizing.

[0006] Furthermore, the method for extracting the measurement error peak value and the fault trigger peak value includes: Take the current time as the end point, take the time when the geoelectric instrument was last overhauled as the start point, and record the period from the start point to the end point as the query period; In the working state, all the operation events of the geoelectric instrument within the query period are queried through the database, and the keywords of all the operation events are marked one by one; Record the operation event with the keyword of resistivity as the first event, and record the recording time of the first event as the first moment, to obtain A first moments; A maximum resistivity value and a minimum resistivity value at the first moment are respectively queried, and after subtracting the maximum resistivity value from the minimum resistivity value, A resistance error values ​​are obtained, and the maximum value of the resistance error value is recorded as the measurement error peak value; The operation event with the keyword "failure shutdown" is recorded as the second event, and the number of all second events is counted to obtain the fault trigger peak value.

[0007] Furthermore, the anomaly identification criteria are: no abnormal features exist in the reliable attributes; Methods for identifying reliable and unreliable attributes include: When the measurement error peak is greater than the error peak calibration value, the measurement error peak is recorded as an abnormal feature, and the operation attribute of the geoelectric instrument is recorded as an unreliable attribute; When the measurement error peak value is less than or equal to the error peak calibration value, and the fault trigger peak value is greater than the trigger peak calibration value, the fault trigger peak value is recorded as an abnormal feature, and the operation attribute of the geoelectric instrument is recorded as an unreliable attribute; When the measurement error peak value is less than or equal to the error peak calibration value, and the fault trigger peak value is less than or equal to the trigger peak calibration value, the operation attribute of the geoelectric instrument is recorded as a reliable attribute.

[0008] Furthermore, the method for determining whether there is a safe operation period includes: When the operation attribute of the geometer is unreliable, it is determined that there is no safe operation period; When the operation attribute of the geothermal meter is a reliable attribute, it is determined that there is a safe operation period.

[0009] Furthermore, the method for obtaining the measured voltage difference includes: Using the preset measurement voltage acquisition cycle as the interval standard, mark the B sub-periods respectively. Voltage sampling time; The voltage sensor detects the The supply voltage at the voltage sampling moment is obtained A measured voltage value will The measured voltage values ​​are subtracted from the standard measured voltage values ​​in turn and the absolute values ​​are taken to obtain The voltage difference of each sub-unit; The expression of the sub-voltage difference is: ; In the formula, For the The sub-period The voltage difference of each sub- =1,2...B, =1,2... , For the The sub-period The measured voltage value, is the standard measurement voltage value; After removing the maximum and minimum values ​​of the sub-voltage difference, the remaining The voltage differences of each sub-value are accumulated and averaged to obtain the measured voltage difference; The expression for measuring the voltage difference is: ; In the formula, For the The measured voltage difference of each sub-period is For the The sub-period The voltage difference of each sub-cell.

[0010] Furthermore, the method for obtaining the measured current difference includes: Mark the first moment, the moment in the middle, and the last moment in the B sub-periods respectively, and obtain B first current points, B second current points, and B third current points; Using a current sensor to detect the power supply current of the geoelectric instrument at B first current points, B second current points, and B third current points, respectively, to obtain B first current values, B second current values, and B third current values; Adding the B first current values, the B second current values, and the B third current values ​​accordingly and then averaging them to obtain B average currents; The expression for the average current is: ; In the formula, For the The average current in the sub-period, For the The first current value of the sub-period, For the The second current value of the sub-period, For the A third current value of a sub-period; Subtract the B average currents from the standard measured current value one by one and take the absolute value to obtain B measured current difference values; The expression for measuring the current difference is: ; In the formula, For the The measured current difference of each sub-period is It is the standard measurement current value.

[0011] Furthermore, the training method of the neural network model includes: Pre-collecting multiple groups of comprehensive operating parameters and operating status values ​​corresponding to the comprehensive operating parameters; The comprehensive operation parameters are converted into multiple feature vectors using the sliding window method. The operation state value is converted into a label corresponding to the comprehensive operation parameter according to the sliding step size. The normal state is converted to 0, and the abnormal state is converted to 1. One feature vector corresponds to one label and constitutes a set of training data. Multiple sets of training data constitute a training set. The comprehensive operation parameters are arranged in the order of collection time, and the prediction time step size Q, sliding step size W and sliding window length Y are preset. The feature vector is used as the input of the neural network model, the operating status value of the next sub-period after the predicted time step Q is used as the output, the subsequent operating status value of each training set is used as the prediction target, and the neural network model is trained with the minimized sum of prediction errors as the training target to generate a neural network model that can predict the operating status value of the next sub-period based on the comprehensive operating parameters of the previous sub-period.

[0012] Furthermore, the method for determining whether to issue an abnormal warning prompt includes: When the output of the neural network model is 0, the predicted operation status value of the next sub-period is normal, and it is determined that no abnormal warning prompt will be issued; When the output of the neural network model is 1, the predicted operating state value of the next sub-period is an abnormal state, and it is determined that an abnormal warning prompt is issued.

[0013] Furthermore, the marking method of the control parameters includes: Compare the temperature value with the temperature safety range, and when the temperature value is not within the temperature safety range, record the temperature value as a control parameter; Compare the humidity value with the humidity safety range, and when the humidity value is not within the humidity safety range, record the humidity value as a control parameter; The measured voltage difference is compared with the voltage difference safety value, and when the measured voltage difference is greater than the voltage difference safety value, the measured voltage difference is recorded as a control parameter; The measured current difference is compared with the current difference safety value, and when the measured current difference is greater than the current difference safety value, the measured current difference is recorded as a control parameter; The host power supply voltage is compared with the power supply voltage safety value. When the host power supply voltage is greater than the power supply voltage safety value, the host power supply voltage is recorded as a control parameter.

[0014] A terminal device includes a cabinet, a display, a geoelectric instrument, a host power supply and a controller. The controller is composed of a feature extraction module, an identification and judgment module, a parameter acquisition module, a prediction and judgment module and a parameter reporting module in an unmanned station geoelectric instrument intelligent monitoring system.

[0015] The technical effects and advantages of the unmanned station geoelectric instrument intelligent monitoring system and terminal equipment of the present invention are as follows: The present invention obtains the operation events of the geoelectric instrument in the working state, extracts basic features from the operation events, performs abnormal recognition on the basic features based on the abnormal recognition criteria, recognizes the operation attributes of the geoelectric instrument, and determines whether there is a safe operation period, marks the monitoring period in the safe operation period, divides the monitoring period into sub-periods, collects the comprehensive operation parameters of the geoelectric instrument in the sub-periods, inputs the collected comprehensive operation parameters into a neural network model trained in advance, predicts the operation state value of the next sub-period, determines whether to issue an abnormal warning prompt, marks the control parameters from the comprehensive operation parameters, transmits the control parameters to the user end, and generates an intelligent monitoring report after summarizing; compared with the prior art, the present invention can preliminarily evaluate the basic operation state of the geoelectric instrument in advance through the abnormal recognition of the basic features of the geoelectric instrument. It can estimate whether the geoelectric instrument meets the subsequent intelligent monitoring requirements quickly, avoid the extra burden brought by the execution of subsequent steps by the geoelectric instrument that does not meet the intelligent monitoring requirements, and at the same time combine the multi-dimensional parameters such as the environment in which the geoelectric instrument is located and its own operation, and can predict the operation status of the geoelectric instrument at future moments in advance based on the prediction model, so as to make advance predictions on the abnormal fault phenomena that will occur in the geoelectric instrument in the future, avoid the lag in the real-time monitoring and fault warning of the geoelectric instrument, and at the same time send the abnormal control parameters to the user end for query and display, so as to facilitate the operation and maintenance management personnel to formulate targeted control measures in advance according to the actual operation parameters of the geoelectric instrument, so that the real-time operation status of the geoelectric instrument can be monitored remotely and intelligently when the station is unattended, so as to achieve efficient and accurate intelligent monitoring effect of the geoelectric instrument. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of a module of an unmanned station geoelectric instrument intelligent monitoring system provided in the first embodiment of the present invention; Figure 2 A schematic diagram of the structure of a terminal device provided in Embodiment 2 of the present invention; Figure 3 A schematic diagram of a flow chart of an intelligent monitoring method for geoelectric instruments at unattended stations provided in Embodiment 3 of the present invention; In the figure: 1. Cabinet; 2. Display; 3. Geoelectric meter; 4. Host power supply; 5. Controller. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] Example 1: Please refer to Figure 1 As shown, the unmanned station geoelectric instrument intelligent monitoring system described in this embodiment is applied to a controller, including: The feature extraction module obtains the operation events of the geoelectric instrument in the working state and extracts basic features from the operation events; Operation events are used to comprehensively represent the relevant change data and situations of the geoelectric instrument during its operation in the past time period, so as to provide a basis for evaluating the basic operation status of the geoelectric instrument in the past time period. Basic characteristics refer to the data and parameters that can specifically affect the basic operation status of the geoelectric instrument in the operation events. Since the basic characteristics are used for preliminary evaluation of the basic operating status of the geoelectric meter, it is necessary to ensure that the geoelectric meter is in normal working condition when obtaining the basic characteristics. On the one hand, it can ensure that the current geoelectric meter is in normal operating condition without deviation. On the other hand, it can also directly identify and screen the geoelectric meter in shutdown state such as fault maintenance, thereby avoiding a series of subsequent operations such as intelligent monitoring, reducing the burden on the intelligent monitoring system.

[0019] The basic characteristics include the measurement error peak and the fault trigger peak. The measurement error peak refers to the deviation between the maximum and minimum resistivity values ​​measured by the geoelectric instrument at the same time point in the past time period, thereby indicating the measurement error performance of the geoelectric instrument. The fault trigger value refers to the number of times the geoelectric instrument has experienced fault shutdown in the past time period, thereby indicating the safe operation performance of the geoelectric instrument. The extraction methods of the measurement error peak value and the fault trigger peak value include: The current time is taken as the end point, the time when the last maintenance of the geoelectric instrument is completed is taken as the start point, and the period between the start point and the end point is recorded as the query period; the query period is used to make a preliminary assessment of the basic operating status of the geoelectric instrument, and ensure that the geoelectric instrument within the query period can be within a reasonable time range after maintenance, avoiding the interference caused by the operation failure of the geoelectric instrument that may occur due to long-term non-maintenance; In the working state, all the operation events of the geoelectric instrument within the query period are queried through the database, and the keywords of all the operation events are marked one by one; the keywords are used to indicate the type of specific matters corresponding to the operation events, and different types of matters can be accurately distinguished. For example, the keywords include resistivity, fault shutdown, real-time current, etc. Record the operation event with the keyword of resistivity as the first event, and record the recording time of the first event as the first moment, to obtain A first moments; A maximum resistivity value and a minimum resistivity value at the first moment are respectively queried, and after subtracting the maximum resistivity value from the minimum resistivity value, A resistance error values ​​are obtained, and the maximum value of the resistance error value is recorded as the measurement error peak value; The operation event with the keyword "failure shutdown" is recorded as the second event, and the number of all second events is counted to obtain the fault trigger peak value.

[0020] After the basic characteristics are obtained, they can be used as the basis for preliminary judgment of the basic operating status of the geoelectric instrument. Since the basic characteristics are used as the basis for subsequent comparative evaluation, the measurement error peak and fault trigger peak are both fixed values, ensuring the accuracy of the subsequent evaluation of the basic operating status of the geoelectric instrument.

[0021] The identification and determination module identifies abnormalities of basic features based on abnormality identification criteria, identifies the operating attributes of the geoelectric instrument, and determines whether there is a safe operating period; After the basic features are obtained, the basic features can be identified for anomalies, so that the range of the measurement error peak and the fault trigger peak can be determined, and the operation properties of the geoelectric instrument can be judged based on the results of anomaly identification. The operation properties can indicate whether the basic operation status of the geoelectric instrument in the past time period is safe and reliable; The operation attributes include reliable attributes and unreliable attributes; the reliable attribute means that the measurement error peak value and fault trigger peak value of the geoelectric instrument are both within the normal range, and the basic operation state of the geoelectric instrument is safe and reliable; the unreliable attribute means that the measurement error peak value and fault trigger peak value of the geoelectric instrument are not within the normal range, and the basic operation state of the geoelectric instrument is unsafe; Since the measurement error peak and fault trigger peak represent the basic operating state of the geoelectric instrument from two aspects, when any aspect is abnormal, the basic operating state of the geoelectric instrument will be unsafe. Therefore, it is necessary to define the rules for the abnormal identification of the basic features, that is, the abnormal identification criteria, to ensure that any abnormal phenomenon can be accurately identified; The abnormality identification criteria are: there are no abnormal features in the reliable attributes; it can raise the judgment threshold of the basic operating status of the geoelectric instrument within the reliable normal range, ensuring that the geoelectric instrument involved in the subsequent intelligent monitoring and analysis processing maintains extremely high reliability; Methods for identifying reliable and unreliable attributes include: Compare the measured error peak with the error peak calibration value; the error peak calibration value refers to the maximum value of the resistivity error measured by the geoelectric instrument under normal, safe and reliable operating conditions, which can provide a basis for comparison between normal and abnormal conditions; the error peak calibration value is obtained by collecting a large number of historical maximum values ​​of the error peak measured by the geoelectric instrument under normal, safe and reliable operating conditions, and calculating their average value; When the measurement error peak is greater than the error peak calibration value, the error of the resistivity measured by the geoelectric instrument in the past time period exceeds the maximum value under normal conditions, and the basic operation state of the geoelectric instrument is not good. The measurement error peak is recorded as an abnormal feature, and the operation attribute of the geoelectric instrument is recorded as an unreliable attribute; When the measurement error peak is less than or equal to the error peak calibration value, and the fault trigger peak is greater than the trigger peak calibration value, the number of fault shutdowns of the geoelectric instrument in the past time period exceeds the maximum value under normal conditions, and the basic operating state of the geoelectric instrument is not good. The fault trigger peak is recorded as an abnormal feature, and the operating attribute of the geoelectric instrument is recorded as an unreliable attribute; the trigger peak calibration value refers to the maximum number of fault shutdowns of the geoelectric instrument under normal, safe and reliable operating conditions, which can provide a basis for comparison between normal and abnormal conditions; the trigger peak calibration value is obtained by collecting a large number of historical maximum values ​​of fault trigger peaks of geoelectric instruments under normal, safe and reliable operating conditions, and then calculating their average value; When the measurement error peak is less than or equal to the error peak calibration value, and the fault trigger peak is less than or equal to the trigger peak calibration value, there are no characteristics that cause safety hazards in the parameter characteristics of the geoelectric instrument, and the operation attributes of the geoelectric instrument are recorded as reliable attributes.

[0022] After the operation attributes are identified, it is necessary to analyze whether the geoelectric instrument meets the subsequent intelligent monitoring requirements based on the identified operation attributes, so as to determine whether there is a safe operation period in the geoelectric instrument. The safe operation period at this time refers to a time period with a certain time span in the past time period of the geoelectric instrument that can meet the data collection requirements of the subsequent intelligent monitoring and analysis, and serves as the corresponding time range for data collection in the subsequent intelligent monitoring and analysis; Methods for determining whether there is a safe operating period include: When the operation attribute of the geoelectric meter is unreliable, the geoelectric meter does not have a time period with a certain time span in the past time period and can meet the data collection requirements of subsequent intelligent monitoring and analysis, and it is determined that there is no safe operation time period; When the operation attribute of the geoelectric meter is a reliable attribute, if there is a time period with a certain time span in the past time period and the data collection demand for subsequent intelligent monitoring and analysis is met, it is determined that there is a safe operation time period.

[0023] The parameter acquisition module marks the monitoring period in the safe operation period, divides the monitoring period into sub-periods, and collects the comprehensive operation parameters of the geoelectric instrument in the sub-periods, the comprehensive operation parameters including temperature value, humidity value, measured voltage difference, measured current difference and host power supply voltage; When there is a safe operation period, the monitoring cycle needs to be identified and marked to provide a time limit for the subsequent data collection. In addition, due to the long overall span of the monitoring cycle, the types of data contained in the monitoring cycle are more complex and the amount is larger. In order to classify the overall and massive data, the monitoring cycle needs to be broken down into small pieces to generate sub-periods, and the monitoring cycle is divided into continuous and equal-length segments through sub-periods. In order to divide the monitoring cycle into sub-periods, the monitoring cycle needs to be identified and marked first. Since the monitoring cycle exists within the safe operation period, it is also necessary to consider the time it takes for the geoelectric instrument to take corresponding remedial measures when an abnormal situation occurs. Therefore, the length of the monitoring cycle must be less than the length of the safe operation period, and ensure that the intelligent monitoring can formulate countermeasures in time when abnormal phenomena occur; In summary, the monitoring period can be set according to the time between the occurrence of abnormal phenomena and the making of targeted response and remedial measures in the actual geoelectrical instrument, as long as the geoelectrical instrument can eliminate the abnormal phenomena in time. At the same time, the sub-period is the time during which the geoelectrical instrument can collect at least one complete comprehensive operating parameter collection within the monitoring period, thereby dividing the monitoring period into B consecutive and equal-length sub-periods; for example, when the monitoring period is 2 minutes, the sub-period is 20 seconds, and when the monitoring period is 1 hour, the sub-period is 5 minutes.

[0024] Comprehensive operating parameters refer to data that can represent the comprehensive changes of the geoelectric instrument in each sub-period, and serve as the final data for subsequent evaluation of whether the geoelectric instrument is abnormal, thereby comprehensively representing the environment and operating conditions of the geoelectric instrument; The comprehensive operating parameters include temperature value, humidity value, measured voltage difference value, measured current difference value and host power supply voltage; The temperature value refers to the operating temperature of the geoelectric instrument in each sub-period, which can be used to indicate the operating temperature status of the geoelectric instrument. When the temperature value is higher or lower, the probability of high-temperature failure of components of the geoelectric instrument is higher, and the operating status of the geoelectric instrument is worse. The temperature value is obtained by detecting the temperature sensor.

[0025] The humidity value refers to the humidity of the working environment of the geoelectric meter in each sub-period, which can represent the humidity status of the working environment of the geoelectric meter. When the humidity value is higher or lower, the more or less moisture there is in the working environment of the geoelectric meter, the higher the probability of failure of the geoelectric meter, and the worse the operating status of the geoelectric meter. The humidity value is obtained through the humidity sensor deployed in the cabinet. The host power supply voltage refers to the voltage value of the host power supply of the geoelectric instrument in each sub-time period, which can be used to represent the power supply voltage on the host side of the geoelectric instrument. The closer the host power supply voltage is to the mains voltage, the more stable the power supply voltage of the host power supply of the geoelectric instrument is, the lower the probability of voltage imbalance failure in the geoelectric instrument is, and the better the operating status of the geoelectric instrument is. The host power supply voltage is obtained by detecting the voltage sensor deployed on the host power supply circuit.

[0026] The measured voltage difference refers to the difference between the power supply voltage and the standard measurement voltage value when the geoelectric instrument measures resistivity data in each sub-period, which can indicate the voltage level of the geoelectric instrument parameter resistivity measurement. The larger the measured voltage difference, the larger the difference between the power supply voltage and the standard measurement voltage value when the geoelectric instrument measures resistivity data, the higher the probability of failure of the geoelectric instrument, and the worse the operating status of the geoelectric instrument. The method for obtaining the measured voltage difference includes: Using the preset measurement voltage acquisition cycle as the interval standard, mark the B sub-periods respectively. The preset measurement voltage acquisition period refers to the time span for acquiring two adjacent measurement supply voltages in a sub-period, which can ensure that the acquisition times of two adjacent measurement supply voltages are not too close or even repeated, and also ensure the independence of each measurement supply voltage; The voltage sensor detects the The supply voltage at the voltage sampling moment is obtained A measured voltage value will The measured voltage values ​​are subtracted from the standard measured voltage values ​​in turn and the absolute values ​​are taken to obtain The standard measured voltage value refers to the maximum voltage value collected by the voltage sensor of the geoelectric instrument under normal operating conditions, which can provide a basis for comparison of the voltage value measured by the geoelectric instrument under normal conditions; The expression of the sub-voltage difference is: ; In the formula, For the The sub-period The voltage difference of each sub- =1,2...B, =1,2... , For the The sub-period The measured voltage value, is the standard measurement voltage value; After removing the maximum and minimum values ​​of the sub-voltage difference, the remaining The voltage differences of each sub-value are accumulated and averaged to obtain the measured voltage difference; The expression for measuring the voltage difference is: ; In the formula, For the The measured voltage difference of each sub-period is For the The sub-period The voltage difference of each sub-unit.

[0027] The measured current difference refers to the difference between the power supply current and the standard measured current value when the geoelectric instrument measures resistivity data in each sub-period, which can indicate the current level of the geoelectric instrument parameter resistivity measurement. The larger the measured current difference, the larger the difference between the power supply current and the standard measured current value when the geoelectric instrument measures resistivity data, the higher the probability of failure of the geoelectric instrument, and the worse the operating status of the geoelectric instrument. The method for obtaining the measured current difference includes: Mark the first moment, the moment in the middle, and the last moment in the B sub-periods respectively, and obtain B first current points, B second current points, and B third current points; The power supply current of the geoelectric instrument at B first current points, B second current points and B third current points is detected by the current sensor respectively, and B first current values, B second current values ​​and B third current values ​​are obtained; the detection effect of the current value at the starting position, the middle position and the end position of the sub-time period is adopted, which can not only achieve the effect of comprehensive detection of multiple points in the sub-time period, but also avoid the randomness caused by single-point detection; Adding the B first current values, the B second current values, and the B third current values ​​accordingly and then averaging them to obtain B average currents; The expression for the average current is: ; In the formula, For the The average current in the sub-period, For the The first current value of the sub-period, For the The second current value of the sub-period, For the A third current value of a sub-period; Subtract the B average currents from the standard measured current values ​​one by one and take the absolute value to obtain B measured current difference values; the standard measured current value refers to the maximum value of the current value collected by the current sensor of the geoelectric instrument under normal operating conditions, which can provide a basis for comparison of the current value measured by the geoelectric instrument under normal conditions; The expression for measuring the current difference is: ; In the formula, For the The measured current difference of each sub-period is It is the standard measurement current value.

[0028] The prediction and judgment module inputs the collected comprehensive operating parameters into the pre-trained neural network model to predict the operating status value of the next sub-period and determine whether to issue an abnormal warning prompt; After the comprehensive operating parameters of the geoelectric instrument are collected, the operating status value of the geoelectric instrument in the next sub-period corresponding to the comprehensive operating parameters can be predicted through the pre-trained neural network model, so as to accurately and quickly judge the operating status of the geoelectric instrument in the next sub-period and discover possible abnormal faults of the geoelectric instrument in advance; The operation status value is used to specifically indicate the normal or abnormal situation of the geoelectric instrument during its actual operation. The operation status value includes normal state and abnormal state, and the normal state and abnormal state correspond to the normal operation and abnormal operation of the geoelectric instrument respectively. The operation status value is usually obtained by collecting a large number of temperature values, humidity values, measured voltage difference values, measured current difference values ​​and host power supply voltage corresponding to the normal state and abnormal state; The training methods of neural network models include: Pre-collecting multiple groups of comprehensive operating parameters and operating status values ​​corresponding to the comprehensive operating parameters; The comprehensive operation parameters are converted into multiple feature vectors using the sliding window method. The operation state value is converted into a label corresponding to the comprehensive operation parameter according to the sliding step size. The normal state is converted to 0, and the abnormal state is converted to 1. One feature vector corresponds to one label and constitutes a set of training data. Multiple sets of training data constitute a training set. The comprehensive operation parameters are arranged in the order of collection time, and the prediction time step size Q, sliding step size W and sliding window length Y are preset. The feature vector is used as the input of the neural network model, the operating status value of the next sub-period after the predicted time step Q is used as the output, the subsequent operating status value of each training set is used as the prediction target, and the neural network model is trained with the minimized sum of prediction errors as the training target to generate a neural network model that can predict the operating status value of the next sub-period based on the comprehensive operating parameters of the previous sub-period.

[0029] Exemplarily, the neural network model is any one of CNN or AlexNet; The calculation formula for the prediction error is: ; In the formula, is the prediction error, is the group number of the eigenvector; For the The predicted state value corresponding to the group feature vector, For the The actual state value corresponding to the group training data; In the neural network model, the feature vector is the comprehensive operating parameter and the state value is the operating state value.

[0030] The abnormal warning prompt is a warning prompt issued by the geoelectric instrument when an abnormal fault phenomenon is about to occur in the future, so as to provide accurate information for the early warning of the station's operation and maintenance management platform; The determination method of whether to issue an abnormal warning prompt includes: When the output of the neural network model is 0, it means that the predicted operation state value of the next sub-period is normal, and the probability of abnormal failure of the geoelectric instrument in the future is low, and no early warning is needed, so it is determined that no abnormal early warning will be issued; When the output of the neural network model is 1, it indicates that the predicted operating state value of the next sub-period is abnormal, and the probability of abnormal failure of the geoelectric instrument in the future is high, and an early warning is required, so an abnormal early warning is issued.

[0031] The parameter reporting module marks the control parameters from the comprehensive operating parameters, transmits the control parameters to the user end, and generates an intelligent monitoring report after summarizing; When an abnormal warning is issued, one or more parameters of the geoelectric instrument's comprehensive operating parameters will be too large or too small. These parameters that are too large or too small are control parameters and will be the objects of subsequent remote intelligent monitoring of the geoelectric instrument. The marking methods of control parameters include: Compare the temperature value with the temperature safety range. When the temperature value is not within the temperature safety range, the operating temperature of the geoelectric instrument is too high or too low, and the temperature value is recorded as a control parameter; the temperature safety range refers to the lower and upper limits of the operating temperature of the geoelectric instrument under normal operating conditions, which serves as a basis for determining whether the temperature value is abnormal; Compare the humidity value with the humidity safety range. When the humidity value is not within the humidity safety range, the ambient humidity of the geoelectric instrument is too high, and the humidity value is recorded as a control parameter. The humidity safety range refers to the lower and upper limits of the ambient humidity of the geoelectric instrument under normal operating conditions, which serves as a basis for determining whether the humidity value is abnormal. The measured voltage difference is compared with the voltage difference safety value. When the measured voltage difference is greater than the voltage difference safety value, the measurement power supply voltage of the geoelectric instrument is unstable, and the measured voltage difference is recorded as a control parameter. The voltage difference safety value refers to the maximum value of the measured voltage difference when the geoelectric instrument is in normal operation, which serves as a basis for determining whether the measured voltage difference is abnormal. The measured current difference is compared with the current difference safety value. When the measured current difference is greater than the current difference safety value, the measured power supply current of the geoelectric instrument is unstable, and the measured current difference is recorded as a control parameter. The current difference safety value refers to the maximum value of the measured current difference when the geoelectric instrument is in normal operation, which serves as a basis for determining whether the measured current difference is abnormal. Compare the host power supply voltage with the power supply voltage safety value. When the host power supply voltage is greater than the power supply voltage safety value, the host power supply voltage of the geoelectric instrument is too high, and the host power supply voltage is recorded as a control parameter; the power supply voltage safety value refers to the maximum value of the host voltage of the geoelectric instrument under normal operating conditions, which serves as the basis for determining whether the host power supply voltage is abnormal.

[0032] After the control parameters are obtained, the control parameters can be transmitted to the user end, so that the user end can remotely understand the specific information of the relevant parameters of the geoelectric instrument. The user end here refers to a terminal that can remotely intelligently monitor and control the geoelectric instrument, including but not limited to small programs on mobile phones, programs and web pages on PCs, so that the station operation and maintenance management personnel can remotely monitor the real-time operating status of the geoelectric instrument through the user end, and can query and understand the specific parameters that cause abnormal failures of the geoelectric instrument in the future; After receiving the control parameters at the user end, the control parameters and non-control parameters need to be summarized and displayed, and an intelligent monitoring report needs to be formed so that the operation and maintenance management personnel can accurately and clearly understand the relevant parameters of the geoelectric instrument; When generating an intelligent monitoring report, it is necessary to number each sub-period of the geoelectric meter in chronological order, and summarize the comprehensive operating parameters in each sub-period to form a separate data display position. Then, the comprehensive operating parameters of each sub-period are filled into the data display position one by one, and the control parameters are distinguished from the non-control parameters, so as to facilitate the operation and maintenance management personnel to query and understand the control parameters and non-control parameters, and finally form an intelligent monitoring report for display.

[0033] In this embodiment, by obtaining the operation events of the geoelectric instrument in the working state, and extracting basic features from the operation events, based on the abnormality recognition criteria, the basic features are identified for abnormality, the operation attributes of the geoelectric instrument are identified, and it is determined whether there is a safe operation period, the monitoring period is marked in the safe operation period, the monitoring period is divided into sub-periods, and the comprehensive operation parameters of the geoelectric instrument in the sub-periods are collected, the collected comprehensive operation parameters are input into the neural network model trained in advance, the operation state value of the next sub-period is predicted, and it is determined whether to issue an abnormal warning prompt, the control parameters are marked from the comprehensive operation parameters, the control parameters are transmitted to the user end, and the intelligent monitoring report is generated after summarizing; compared with the prior art, by identifying the abnormalities of the basic features of the geoelectric instrument, the basic operation state of the geoelectric instrument can be preliminarily determined in advance. Evaluation can be performed to quickly determine whether the geoelectric instrument meets the subsequent intelligent monitoring requirements, avoiding the additional burden brought by the execution of subsequent steps by the geoelectric instrument that does not meet the intelligent monitoring requirements. At the same time, combined with multi-dimensional parameters such as the environment in which the geoelectric instrument is located and its own operation, and based on the prediction model, the operation status of the geoelectric instrument at future moments can be predicted in advance, so that the abnormal fault phenomenon that will occur in the geoelectric instrument in the future can be predicted in advance, avoiding the lag in the real-time monitoring and fault warning of the geoelectric instrument. At the same time, the abnormal control parameters can be sent to the user end for query and display, so that the operation and maintenance management personnel can formulate targeted control measures in advance according to the actual operation parameters of the geoelectric instrument, so that the real-time operation status of the geoelectric instrument can be monitored remotely and intelligently when the station is unattended, achieving efficient and accurate intelligent monitoring effect of the geoelectric instrument.

[0034] Example 2: Please refer to Figure 2 As shown, the part not described in detail in this embodiment is described in the first embodiment, and a terminal device is provided, which includes a cabinet 1, a display 2, a geoelectric instrument 3, a host power supply 4 and a controller 5, and the controller 5 is composed of a feature extraction module, an identification and determination module, a parameter acquisition module, a prediction and determination module and a parameter reporting module in the above-mentioned unattended station geoelectric instrument intelligent monitoring system; Among them, the display 2, the geoelectric meter 3, the host power supply 4 and the controller 5 are all arranged in the cabinet 1 and the power supply circuit is turned on. The host power supply 4 is used to power the display 2, the geoelectric meter 3 and the controller 5. The display 2 is used to display the comprehensive operating parameters on the geoelectric meter 3. The controller 5 is used to collect and analyze the comprehensive operating parameters of the geoelectric meter 3, and realize remote intelligent monitoring effect with the user end.

[0035] Example 3: Please refer to Figure 3 As shown, the part not described in detail in this embodiment is described in the first embodiment, which provides an unattended station geoelectric instrument intelligent monitoring method, which is applied to a controller and implemented based on an unattended station geoelectric instrument intelligent monitoring system, including: S1: In the working state, the operation events of the geoelectric instrument are obtained, and basic features are extracted from the operation events. The basic features include the measurement error peak and the fault trigger peak; S2: Based on the anomaly identification criteria, the basic features are identified for anomalies, the operating attributes of the geoelectric instrument are identified, the operating attributes include reliable attributes and unreliable attributes, and whether there is a safe operating period; S3: If there is a safe operation period, mark the monitoring period in the safe operation period, divide the monitoring period into sub-periods, and collect the comprehensive operation parameters of the geoelectric instrument in the sub-periods, the comprehensive operation parameters including temperature value, humidity value, measured voltage difference, measured current difference and host power supply voltage; S4: input the collected comprehensive operation parameters into the neural network model trained in advance, predict the operation status value of the next sub-period, the operation status value includes normal state and abnormal state, and determine whether to issue an abnormal warning prompt; S5: If an abnormal warning prompt is issued, the control parameters are marked from the comprehensive operating parameters, the control parameters are transmitted to the user end, and the intelligent monitoring report is generated after being summarized.

[0036] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. An intelligent monitoring system for geoelectric instruments at unmanned stations, applied to a controller, characterized in that: include: The feature extraction module is used to obtain the operation events of the geoelectric instrument in the working state, and extract basic features from the operation events, the basic features including the measurement error peak value and the fault triggering peak value; The identification and determination module is used to identify abnormalities of basic features based on abnormality identification criteria, identify the operating attributes of the geoelectric instrument, which include reliable attributes and unreliable attributes, and determine whether there is a safe operating period; A parameter acquisition module is used to mark the monitoring period in the safe operation period, divide the monitoring period into sub-periods, and collect the comprehensive operation parameters of the geoelectric instrument in the sub-periods, the comprehensive operation parameters including temperature value, humidity value, measured voltage difference, measured current difference and host power supply voltage; The prediction and judgment module is used to input the collected comprehensive operating parameters into the pre-trained neural network model to predict the operating status value of the next sub-period, which includes normal status and abnormal status, and determine whether to issue an abnormal warning prompt; The parameter reporting module is used to mark the control parameters from the comprehensive operating parameters, transmit the control parameters to the user end, and generate an intelligent monitoring report after summarizing.

2. According to claim 1, the unmanned station geoelectric instrument intelligent monitoring system is characterized in that: The extraction methods of the measurement error peak value and the fault trigger peak value include: Take the current time as the end point, take the time when the geoelectric instrument was last overhauled as the start point, and record the period from the start point to the end point as the query period; In the working state, all the operation events of the geoelectric instrument within the query period are queried through the database, and the keywords of all the operation events are marked one by one; Record the operation event with the keyword of resistivity as the first event, and record the recording time of the first event as the first moment, to obtain A first moments; A maximum resistivity value and a minimum resistivity value at the first moment are respectively queried, and after subtracting the maximum resistivity value from the minimum resistivity value, A resistance error values ​​are obtained, and the maximum value of the resistance error value is recorded as the measurement error peak value; The operation event with the keyword "failure shutdown" is recorded as the second event, and the number of all second events is counted to obtain the fault trigger peak value.

3. The unmanned station geoelectric instrument intelligent monitoring system according to claim 2 is characterized in that: The criteria for anomaly identification are: no abnormal features exist in reliable attributes; Methods for identifying reliable and unreliable attributes include: When the measurement error peak is greater than the error peak calibration value, the measurement error peak is recorded as an abnormal feature, and the operation attribute of the geoelectric instrument is recorded as an unreliable attribute; When the measurement error peak value is less than or equal to the error peak calibration value, and the fault trigger peak value is greater than the trigger peak calibration value, the fault trigger peak value is recorded as an abnormal feature, and the operation attribute of the geoelectric instrument is recorded as an unreliable attribute; When the measurement error peak value is less than or equal to the error peak calibration value, and the fault trigger peak value is less than or equal to the trigger peak calibration value, the operation attribute of the geoelectric instrument is recorded as a reliable attribute.

4. The unmanned station geoelectric instrument intelligent monitoring system according to claim 3 is characterized in that: Methods for determining whether there is a safe operating period include: When the operation attribute of the geometer is unreliable, it is determined that there is no safe operation period; When the operation attribute of the geothermal meter is a reliable attribute, it is determined that there is a safe operation period.

5. The unmanned station geoelectric instrument intelligent monitoring system according to claim 4 is characterized in that: The method for obtaining the measured voltage difference includes: Using the preset measurement voltage acquisition cycle as the interval standard, mark the B sub-periods respectively. Voltage sampling time; The voltage sensor detects the The supply voltage at the voltage sampling moment is obtained A measured voltage value will The measured voltage values ​​are subtracted from the standard measured voltage values ​​in turn and the absolute values ​​are taken to obtain The voltage difference of each sub-unit; The expression of the sub-voltage difference is: ； In the formula, For the The sub-period The voltage difference of each sub- =1,2...B, =1,2... , For the The sub-period The measured voltage value, is the standard measurement voltage value; After removing the maximum and minimum values ​​of the sub-voltage difference, the remaining The voltage differences of each sub-value are accumulated and averaged to obtain the measured voltage difference; The expression for measuring the voltage difference is: ； In the formula, For the The measured voltage difference of each sub-period is For the The sub-period The voltage difference of each sub-cell.

6. The unmanned station geoelectric instrument intelligent monitoring system according to claim 5 is characterized in that: The method for obtaining the measured current difference includes: Mark the first moment, the moment in the middle, and the last moment in the B sub-periods respectively, and obtain B first current points, B second current points, and B third current points; Using a current sensor to detect the power supply current of the geoelectric instrument at B first current points, B second current points, and B third current points, respectively, to obtain B first current values, B second current values, and B third current values; Adding the B first current values, the B second current values, and the B third current values ​​accordingly and then averaging them to obtain B average currents; The expression for the average current is: ； In the formula, For the The average current in the sub-period, For the The first current value of the sub-period, For the The second current value of the sub-period, For the A third current value of a sub-period; Subtract the B average currents from the standard measured current value one by one and take the absolute value to obtain B measured current difference values; The expression for measuring the current difference is: ； In the formula, For the The measured current difference of each sub-period is It is the standard measurement current value.

7. The unmanned station geoelectric instrument intelligent monitoring system according to claim 6 is characterized in that: The training methods of neural network models include: Pre-collecting multiple groups of comprehensive operating parameters and operating status values ​​corresponding to the comprehensive operating parameters; The comprehensive operation parameters are converted into multiple feature vectors using the sliding window method. The operation state value is converted into a label corresponding to the comprehensive operation parameter according to the sliding step size. The normal state is converted to 0, and the abnormal state is converted to 1. One feature vector corresponds to one label and constitutes a set of training data. Multiple sets of training data constitute a training set. The comprehensive operation parameters are arranged in the order of collection time, and the prediction time step size Q, sliding step size W and sliding window length Y are preset. The feature vector is used as the input of the neural network model, the operating status value of the next sub-period after the predicted time step Q is used as the output, the subsequent operating status value of each training set is used as the prediction target, and the neural network model is trained with the minimized sum of prediction errors as the training target to generate a neural network model that can predict the operating status value of the next sub-period based on the comprehensive operating parameters of the previous sub-period.

8. The unmanned station geoelectric instrument intelligent monitoring system according to claim 7 is characterized in that: The determination method of whether to issue an abnormal warning prompt includes: When the output of the neural network model is 0, the predicted operation status value of the next sub-period is normal, and it is determined that no abnormal warning prompt will be issued; When the output of the neural network model is 1, the predicted operating state value of the next sub-period is an abnormal state, and it is determined that an abnormal warning prompt is issued.

9. The unmanned station geoelectric instrument intelligent monitoring system according to claim 8 is characterized in that: The marking methods of control parameters include: Compare the temperature value with the temperature safety range, and when the temperature value is not within the temperature safety range, record the temperature value as a control parameter; Compare the humidity value with the humidity safety range, and when the humidity value is not within the humidity safety range, record the humidity value as a control parameter; The measured voltage difference is compared with the voltage difference safety value, and when the measured voltage difference is greater than the voltage difference safety value, the measured voltage difference is recorded as a control parameter; The measured current difference is compared with the current difference safety value, and when the measured current difference is greater than the current difference safety value, the measured current difference is recorded as a control parameter; The host power supply voltage is compared with the power supply voltage safety value. When the host power supply voltage is greater than the power supply voltage safety value, the host power supply voltage is recorded as a control parameter.

10. A terminal device, comprising a cabinet (1), a display (2), a geoelectric instrument (3), a host power supply (4) and a controller (5), characterized in that: The controller (5) is composed of a feature extraction module, an identification and determination module, a parameter acquisition module, a prediction and determination module, and a parameter reporting module in the intelligent monitoring system of the unmanned station geoelectric instrument according to any one of claims 1 to 9.

Images