Magnetic induction data analysis method and system based on intelligent processing

Abstract

The invention discloses a magnetic induction data analysis method and system based on intelligent processing, and belongs to the technical field of magnetic induction. The system comprises a data acquisition module, an induction analysis module, an intelligent recommendation module and a data storage module. The data acquisition module is used for acquiring travel information and equipment parameters of an object and historical logs and route maps of a train; the induction analysis module is used for analyzing travel information, dividing driving road sections in a route map, splitting the driving road sections into sampling road sections, setting reference maps, establishing measuring points on each reference map, analyzing electromagnetic field intensity, and calculating difference indexes of the sampling road sections so as to set nodes; the intelligent recommendation module draws an electromagnetic field distribution reference diagram for each node, maps all seats in a carriage, analyzes equipment parameters and calculates an influence index of each seat so as to select an optimal seat for recommendation; and the data storage module is used for updating the optimal seat, recommending, collecting train operation information, generating a record and storing the record in a historical log.

Description

Technical Field

[0001] The present invention relates to the field of magnetic induction technology, and in particular to a magnetic induction data analysis method and system based on intelligent processing. Background Art

[0002] With the rapid development of modern transportation technology, EMUs are widely used around the world as efficient public transportation. The electrical equipment and power supply system in the carriages during high-speed operation of the trains create a complex electromagnetic environment, and power frequency electromagnetic fields are ubiquitous. The electromagnetic field changes with the running status of the train and the external environment, and may affect passengers wearing medical devices in the carriages.

[0003] At present, there are usually some problems with the magnetic induction effects on pacemaker wearers when riding high-speed trains. On the one hand, there are large differences in the anti-interference performance of different types of pacemakers to electromagnetic fields, and there are also large differences in the trend of nonlinear influence relationships under different electric field strengths and magnetic field strengths of electromagnetic fields. The existing methods do not conduct detailed analysis and judgment on these two differences to give reasonable suggestions. On the other hand, the electromagnetic field environment of the train compartment is not only affected by the running state of the train itself and the external environment, but also the electric field strength and magnetic field strength at different internal positions will also be different. The existing methods do not make adaptive dynamic position recommendations based on these differences, which is not conducive to the safety protection of pacemaker wearers. Therefore, at this stage, a more intelligent and efficient magnetic induction data analysis technology solution is needed to solve the above problems. Summary of the invention

[0004] The purpose of the present invention is to provide a magnetic induction data analysis method and system based on intelligent processing to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides a magnetic induction data analysis method based on intelligent processing, comprising the following steps:

[0006] S100: When the subject selects a train, the subject's travel information and equipment parameters, as well as historical logs and route maps of all trains are collected.

[0007] S200, analyzing the travel information and dividing the driving sections in the route map, then splitting the driving sections into r sampling sections and setting a reference map for each sampling section, establishing measurement points on each reference map and analyzing the electric field strength and magnetic field strength, thereby calculating the difference index of the sampling sections, and setting nodes according to the difference index.

[0008] S300, calculating the reference speed of each node through historical logs, drawing an electromagnetic field distribution reference map for each node and mapping it to all seats in the train car, analyzing equipment parameters and calculating the magnetic flux density of each seat in each electromagnetic field distribution reference map, thereby obtaining the influence index of each seat, and selecting the best seat for recommendation based on the influence index.

[0009] S400 uses a visual interface to display the electromagnetic field distribution in the train compartment in real time, dynamically updates the best seats and makes recommendations, and collects train operation information through sensors to generate records and store them in historical logs.

[0010] In S100, the object refers to a pacemaker wearer, and the train refers to a high-speed train with a traction transformer. The trip information includes the start point and the end point of the trip.

[0011] The device refers to the pacemaker worn by the subject, and the device parameters include the model of the pacemaker and the magnetic induction influence diagram. The magnetic induction influence diagram includes the magnetic flux density at the heart tissue when the pacemaker works under different electric field strengths and magnetic field strengths.

[0012] The magnetic induction influence diagram in the human body was drawn using the numerical simulation method. The EMU car body model, traction transformer model, human body model and pacemaker model were established using COMSOL Multiphysics simulation software to simulate the influence of the heart tissue and pacemaker electrodes of special passengers on the train exposed to the electromagnetic field generated by the traction transformer.

[0013] By setting up an electromagnetic field environment with different electric field strengths and magnetic field strengths around the pacemaker, the induced electromagnetic field distribution of the patient's heart tissue and pacemaker is simulated to analyze the magnetic flux density.

[0014] The main impact of external electromagnetic fields on pacemakers is the generation of induced voltage at the pacemaker electrode tip, which affects the normal sensing and pacing functions of the pacemaker, thereby threatening the health and safety of the patient.

[0015] The historical log includes a driving log and a sensing log. The driving log includes all driving records of each train, and each driving record includes the train's driving route and driving time period.

[0016] The induction log includes all induction records of each train. Each induction record includes a magnetic induction distribution map of the train at different times. The magnetic induction distribution map refers to the distribution position map of the electric field and magnetic field strength in the train compartment.

[0017] The route map is a map of all routes available for train operation within a specified area, including the tracks and station locations.

[0018] The magnetic induction distribution map is achieved by installing high-precision magnetic induction sensors at different locations in the train carriages and equipping them with data acquisition equipment, and setting appropriate acquisition frequency and time interval.

[0019] During the operation of the train, the timer automatically starts data collection, monitors the magnetic field changes at different locations in the train carriage, and stores the data in real time. The data is regularly analyzed and processed to generate a magnetic induction distribution map.

[0020] In S200, the specific steps are as follows:

[0021] S201, obtaining the starting point and the end point in the travel information, dividing the driving section RT in the route map according to the starting point and the end point, and marking the driving records of all driving routes in the driving log that contain the driving section RT.

[0022] Get the marked driving record REC m Corresponding train TR m , and analyze the driving time period TS occupied by the driving section RT part , the train TR m Corresponding to the driving time period TS in the sensing record part All magnetic induction distribution maps are used as driving records REC m Refer to the figure.

[0023] S202, respectively set a reference map for each marked driving record, analyze the position of the train on the driving section RT as the reference position of CZ1 according to the time corresponding to the reference map CZ1, and respectively analyze the reference position of each reference map.

[0024] Set the sampling number r, evenly split the driving section RT into r sampling sections with the same distance, assign all reference maps to different sampling sections according to the reference positions, and mark the sampling sections with reference maps.

[0025] The number of samples is set in advance by the management personnel, and it is necessary to refer to the collection frequency of the magnetic induction distribution map and the train speed to ensure that the reference maps belonging to the sampling section all belong to different marked driving records.

[0026] S203, set the number of measurement points c, evenly set c measurement points on each reference map, and analyze the electric field strength and magnetic field strength of each measurement point. Obtain the marked sampling section LD m Download all the reference maps, analyze the electric field strength and magnetic field strength of the measuring point cl in these reference maps and calculate the standard deviation respectively, sum the standard deviation of the electric field strength and the standard deviation of the magnetic field strength as the difference coefficient of the measuring point cl, calculate the difference coefficient of each measuring point respectively, and sum the difference coefficients of all measuring points as the marking sampling section LD m difference index.

[0027] The difference index of each marked sampling section is calculated respectively, and the index threshold e is set, and the marked sampling sections with a difference index less than e are regarded as nodes.

[0028] The difference coefficient represents the fluctuation of the electric field strength and magnetic field strength at the corresponding measurement point in the reference figure. The difference index represents the change of the electromagnetic field when each train is running on the marked sampling section. The smaller the difference index, the more similar the electromagnetic field distribution when the trains are running on the marked sampling section.

[0029] In S300, the specific steps are as follows:

[0030] S301, analyzing and marking driving record REC m The duration of the travel time period occupied by node j is time. The length of node j is divided by time to get the train TR m The speed at node j. Calculate the average speed of the trains corresponding to all marked driving records at node j, and use the result as the reference speed of node j. Calculate the reference speed of each node separately.

[0031] S302, obtain the selected train TR d , retrieve the induction log in the train TR d The instantaneous speed ss2 of the train is analyzed according to the time corresponding to the magnetic induction distribution map CZ2, the instantaneous speed ss2 is used as the descriptive speed of the magnetic induction distribution map CZ2, and the descriptive speed corresponding to each magnetic induction distribution map is calculated respectively.

[0032] When a train moves at high speed on a conductive track, the intensity and distribution of the electric and magnetic fields will change due to changes in the speed of the train. The speed change of a high-speed train will cause the intensity of the electric and magnetic fields generated around it to change rapidly, so there are large differences in the magnetic induction distribution diagrams at different speeds.

[0033] S303, obtain the reference speed sp of node j j , filter out train TR d The speed described in is equal to the reference speed sp j For all magnetic induction distribution diagrams, the average electric field strength and the average magnetic field strength of the measuring point c1 in these reference figures are calculated, and they are used as the reference electric field strength and the reference magnetic field strength of the measuring point c1 respectively.

[0034] The reference electric field strength and the reference magnetic field strength of each measuring point are calculated respectively, and the electromagnetic field distribution reference map is drawn for node j according to the reference electric field strength and the reference magnetic field strength of all measuring points.

[0035] S304, draw an electromagnetic field distribution reference map for each node, and dAll seats in the car are mapped to the electromagnetic field distribution reference map of each node.

[0036] Analyze the electric field strength and magnetic field strength at each seat in each electromagnetic field distribution reference map, retrieve the corresponding magnetic flux density in the magnetic induction influence map according to the electric field strength and magnetic field strength, and mark the magnetic flux density of each seat in each electromagnetic field distribution reference map.

[0037] Different types of pacing electrodes are affected differently by external electromagnetic fields. Generally, the unipolar pacing mode is more susceptible to interference than the bipolar pacing mode. When different types of pacemakers work in different electromagnetic field environments, the change in magnetic flux density at the heart tissue is not a linear relationship.

[0038] In practical applications, the electrical properties of cardiac tissue change with physiological conditions, resulting in a nonlinear relationship between electromagnetic field strength and magnetic flux density.

[0039] S305. Count the number of all nodes k, obtain the magnetic flux density of the seat in each electromagnetic field distribution reference map, and calculate the average value. As the average magnetic flux density of the seat, substitute it into the formula to calculate the seat influence index YZ seat .

[0040] Calculate the influence index of each seat respectively, select the seat with the smallest influence index as the best seat, and recommend the best seat to the object. The influence index calculation formula is as follows:

[0041]

[0042] In the formula, α is a constant, T ave is the average value of the average magnetic flux density of all seats, is the magnetic flux density of the seat in the i-th electromagnetic field distribution reference diagram.

[0043] In S400, the subject is riding on a train TR d During the process, the current remaining driving route is analyzed in real time, the nodes are reset according to the remaining driving route, and the best seat is searched again.

[0044] The electromagnetic field distribution map in the train compartment is displayed in real time through a visual interface, and the best seats are dynamically updated and recommended. The train driving conditions and the electromagnetic field distribution in the compartment are collected through sensors, and the driving records and sensing records are generated and stored in the historical log.

[0045] The magnetic induction data analysis system based on intelligent processing includes a data acquisition module, an induction analysis module, an intelligent recommendation module and a data storage module.

[0046] The data acquisition module is used to collect the object's travel information and equipment parameters, as well as the train's historical log and route map.

[0047] The sensing analysis module is used to analyze the travel information and divide the driving sections in the route map, split the driving sections into sampling sections and set reference maps, establish measurement points on each reference map and analyze the electromagnetic field strength, calculate the difference index of each sampling section and set the node.

[0048] The intelligent recommendation module draws an electromagnetic field distribution reference map for each node and maps all seats in the car, analyzes equipment parameters and calculates the influence index of each seat, so as to select the best seat for recommendation.

[0049] The data storage module is used to update the best seats and make recommendations, collect train operation information, generate records and store them in the historical log.

[0050] The data collection module includes a route information collection unit, an object data collection unit and a history log collection unit.

[0051] The route information collection unit is used to collect all route maps available for train travel in a specified area.

[0052] The subject data acquisition unit is used to acquire the subject's travel information and device parameters. The subject refers to the pacemaker wearer, and the device refers to the pacemaker worn by the subject.

[0053] The trip information includes the starting point and the end point of the trip. The device parameters include the model of the pacemaker and the magnetic induction influence diagram, which includes the magnetic flux density at the heart tissue when the pacemaker works under different electric field strengths and magnetic field strengths.

[0054] The historical log collection unit is used to collect driving logs and sensing logs. The driving log includes all driving records of each train, and each driving record includes the train's driving route and driving time period.

[0055] The induction log includes all induction records of each train. Each induction record includes a magnetic induction distribution map of the train at different times. The magnetic induction distribution map refers to the distribution position map of the electric field and magnetic field strength in the train compartment.

[0056] The induction analysis module includes an impact section analysis unit and a difference index calculation unit.

[0057] The impact section analysis unit is used to split the sampling sections and mark them.

[0058] First, the driving section RT is divided in the route map according to the starting point and the end point in the trip information, and the driving record whose driving route includes the driving section RT is marked in the driving log.

[0059] Secondly, obtain the marked driving record REC m Corresponding train TR m , and analyze the driving record REC m The driving time period TS occupied by the driving section RT part , the train TR m Corresponding to the driving time period TS in the sensing record part All magnetic induction distribution maps are used as driving records REC m Refer to the figure.

[0060] Then, a reference map is set for each marked travel record, and the position of the train on the travel section RT is analyzed as the reference position of CZ1 according to the time corresponding to the reference map CZ1, and the reference position of each reference map is analyzed respectively.

[0061] Finally, the sampling number r is set to evenly split the driving section RT into r sampling sections with the same distance. All reference maps are assigned to different sampling sections according to the reference positions, and the sampling sections with reference maps are marked.

[0062] The difference index calculation unit is used to calculate the difference index of each marked sampling road section.

[0063] First, the number of measurement points c is set, and c measurement points are evenly set on each reference map, and the electric field strength and magnetic field strength of each measurement point are analyzed.

[0064] Secondly, obtain the marked sampling section LD m Analyze the electric field strength and magnetic field strength of the measuring point cl in these reference figures, calculate the standard deviation respectively, and sum the standard deviation of the electric field strength and the standard deviation of the magnetic field strength as the coefficient of difference of the measuring point cl.

[0065] Finally, the difference coefficient of each measurement point is calculated separately, and the difference coefficients of all measurement points are summed up as the marked sampling section LD m The difference index of each marked sampling section is calculated respectively, and the index threshold e is set, and the marked sampling sections with a difference index less than e are regarded as nodes.

[0066] The intelligent recommendation module includes an electromagnetic induction prediction unit and an optimal location recommendation unit.

[0067] The electromagnetic induction prediction unit is used to draw an electromagnetic field distribution reference map for each node.

[0068] First, analyze the marked driving record REC m The duration of the travel time period occupied by node j is time. The length of node j is divided by time to get the train TR m The driving speed at node j.

[0069] Calculate the average speed of the trains corresponding to all marked driving records at node j, and use the result as the reference speed of node j. Calculate the reference speed of each node separately.

[0070] Next, get the train TR selected by the object d , retrieve the induction log in the train TR d The instantaneous speed ss2 of the train is analyzed according to the time corresponding to the magnetic induction distribution map CZ2, the instantaneous speed ss2 is used as the descriptive speed of the magnetic induction distribution map CZ2, and the descriptive speed corresponding to each magnetic induction distribution map is calculated respectively.

[0071] Then, obtain the reference speed sp of node j j , filter out train TR d The speed described in is equal to the reference speed sp j For all magnetic induction distribution diagrams, the average electric field strength and the average magnetic field strength of the measuring point c1 in these reference figures are calculated, and they are used as the reference electric field strength and the reference magnetic field strength of the measuring point c1 respectively.

[0072] Finally, the reference electric field strength and reference magnetic field strength of each measuring point are calculated respectively, and an electromagnetic field distribution reference map is drawn for node j according to the reference electric field strength and reference magnetic field strength of all measuring points, and an electromagnetic field distribution reference map is drawn for each node respectively.

[0073] The best seat recommendation unit is used to analyze the best seat and recommend it to the object.

[0074] First, the train TR d All seats in the carriage are mapped to the electromagnetic field distribution reference map of each node, and the electric field strength and magnetic field strength at each seat in each electromagnetic field distribution reference map are analyzed.

[0075] Secondly, the corresponding magnetic flux density is retrieved from the magnetic induction influence diagram according to the electric field strength and magnetic field strength, and the magnetic flux density of each seat is marked in each electromagnetic field distribution reference diagram.

[0076] Then, count the number of all nodes k, obtain the magnetic flux density of the seat in each electromagnetic field distribution reference map, and calculate the average value As the average magnetic flux density of the seat seat.

[0077] Finally, according to the formula Calculate the seat influence index YZ seat . Among them, α is a constant, T ave is the average value of the average magnetic flux density of all seats, is the magnetic flux density of the seat in the i-th electromagnetic field distribution reference diagram.

[0078] The influence index of each seat is calculated respectively, and the seat with the smallest influence index is selected as the best seat, and the best seat is recommended to the object.

[0079] The data storage module resets the nodes according to the remaining route and searches for the best seat for recommendation. The sensors collect the train's running conditions and the electromagnetic field distribution in the carriage, and generate running records and sensing records respectively, which are then stored in the historical log.

[0080] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0081] Accurate node setting: This application divides the driving section by analyzing the travel information, splits the driving section into several sampling sections, and sets several reference maps for each sampling section by analyzing the driving records. The measurement points are established in the reference map, and the difference coefficient of each measurement point is calculated to calculate the difference index of the sampling section and set the node. Compared with the random or fixed setting of nodes in the prior art, it is more accurate, making the subsequent data analysis and processing results more reliable.

[0082] Dynamic location recommendation: This application calculates the reference speed of each node by analyzing historical logs, draws an electromagnetic field distribution reference map for each node, and maps all seats in the train car. The magnetic flux density of each seat in each electromagnetic field distribution reference map and the influence index of each seat are calculated, and the best seat is selected according to the influence index for dynamic recommendation. Compared with the static analysis and recommendation in the prior art, it is more predictive and intelligent.

[0083] In summary, compared with traditional technologies, the present invention has the advantages of accurate node setting and dynamic location recommendation, and can improve the efficiency of magnetic induction data analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0084] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0085] Figure 1 It is a flow chart of the magnetic induction data analysis method based on intelligent processing of the present invention;

[0086] Figure 2 It is a structural schematic diagram of the magnetic induction data analysis system based on intelligent processing of the present invention. DETAILED DESCRIPTION

[0087] 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.

[0088] See also Figure 1 The present invention provides a magnetic induction data analysis method based on intelligent processing, comprising the following steps:

[0089] S100: When the subject selects a train, the subject's travel information and equipment parameters, as well as historical logs and route maps of all trains are collected.

[0090] S200, analyzing the travel information and dividing the driving sections in the route map, then splitting the driving sections into r sampling sections and setting a reference map for each sampling section, establishing measurement points on each reference map and analyzing the electric field strength and magnetic field strength, thereby calculating the difference index of the sampling sections, and setting nodes according to the difference index.

[0091] S300, calculating the reference speed of each node through historical logs, drawing an electromagnetic field distribution reference map for each node and mapping it to all seats in the train car, analyzing equipment parameters and calculating the magnetic flux density of each seat in each electromagnetic field distribution reference map, thereby obtaining the influence index of each seat, and selecting the best seat for recommendation based on the influence index.

[0092] S400 uses a visual interface to display the electromagnetic field distribution in the train compartment in real time, dynamically updates the best seats and makes recommendations, and collects train operation information through sensors to generate records and store them in historical logs.

[0093] In S100, the object refers to a pacemaker wearer, and the train refers to a high-speed train with a traction transformer. The trip information includes the start point and the end point of the trip.

[0094] The device refers to the pacemaker worn by the subject, and the device parameters include the model of the pacemaker and the magnetic induction influence diagram. The magnetic induction influence diagram includes the magnetic flux density at the heart tissue when the pacemaker works under different electric field strengths and magnetic field strengths.

[0095] The magnetic induction influence diagram in the human body was drawn using the numerical simulation method. The EMU car body model, traction transformer model, human body model and pacemaker model were established using COMSOL Multiphysics simulation software to simulate the influence of the heart tissue and pacemaker electrodes of special passengers on the train exposed to the electromagnetic field generated by the traction transformer.

[0096] By setting up an electromagnetic field environment with different electric field strengths and magnetic field strengths around the pacemaker, the induced electromagnetic field distribution of the patient's heart tissue and pacemaker is simulated to analyze the magnetic flux density.

[0097] The main impact of external electromagnetic fields on pacemakers is the generation of induced voltage at the pacemaker electrode tip, which affects the normal sensing and pacing functions of the pacemaker, thereby threatening the health and safety of the patient.

[0098] The historical log includes a driving log and a sensing log. The driving log includes all driving records of each train, and each driving record includes the train's driving route and driving time period.

[0099] The induction log includes all induction records of each train. Each induction record includes a magnetic induction distribution map of the train at different times. The magnetic induction distribution map refers to the distribution position map of the electric field and magnetic field strength in the train compartment.

[0100] The route map is a map of all routes available for train operation within a specified area, including the tracks and station locations.

[0101] The magnetic induction distribution map is achieved by installing high-precision magnetic induction sensors at different locations in the train carriages and equipping them with data acquisition equipment, and setting appropriate acquisition frequency and time interval.

[0102] During the operation of the train, the timer automatically starts data collection, monitors the magnetic field changes at different locations in the train carriage, and stores the data in real time. The data is regularly analyzed and processed to generate a magnetic induction distribution map.

[0103] In S200, the specific steps are as follows:

[0104] S201, obtaining the starting point and the end point in the travel information, dividing the driving section RT in the route map according to the starting point and the end point, and marking the driving records of all driving routes in the driving log that contain the driving section RT.

[0105] Get the marked driving record REC m Corresponding train TR m , and analyze the driving time period TS occupied by the driving section RT part , the train TR m Corresponding to the driving time period TS in the sensing record part All magnetic induction distribution maps are used as driving records REC m Refer to the figure.

[0106] S202, respectively set a reference map for each marked driving record, analyze the position of the train on the driving section RT as the reference position of CZ1 according to the time corresponding to the reference map CZ1, and respectively analyze the reference position of each reference map.

[0107] Set the sampling number r, evenly split the driving section RT into r sampling sections with the same distance, assign all reference maps to different sampling sections according to the reference positions, and mark the sampling sections with reference maps.

[0108] The number of samples is set in advance by the management personnel, and it is necessary to refer to the collection frequency of the magnetic induction distribution map and the train speed to ensure that the reference maps belonging to the sampling section all belong to different marked driving records.

[0109] S203, set the number of measurement points c, evenly set c measurement points on each reference map, and analyze the electric field strength and magnetic field strength of each measurement point. Obtain the marked sampling section LD m Download all the reference maps, analyze the electric field strength and magnetic field strength of the measuring point cl in these reference maps and calculate the standard deviation respectively, sum the standard deviation of the electric field strength and the standard deviation of the magnetic field strength as the difference coefficient of the measuring point cl, calculate the difference coefficient of each measuring point respectively, and sum the difference coefficients of all measuring points as the marking sampling section LD m difference index.

[0110] The difference index of each marked sampling section is calculated respectively, and the index threshold e is set, and the marked sampling sections with a difference index less than e are regarded as nodes.

[0111] The difference coefficient represents the fluctuation of the electric field strength and magnetic field strength at the corresponding measurement point in the reference figure. The difference index represents the change of the electromagnetic field when each train is running on the marked sampling section. The smaller the difference index, the more similar the electromagnetic field distribution when the trains are running on the marked sampling section.

[0112] In S300, the specific steps are as follows:

[0113] S301, analyzing and marking driving record REC m The duration of the travel time period occupied by node j is time. The length of node j is divided by time to get the train TR m The speed at node j. Calculate the average speed of the trains corresponding to all marked driving records at node j, and use the result as the reference speed of node j. Calculate the reference speed of each node separately.

[0114] S302, obtain the selected train TR d , retrieve the induction log in the train TR d The instantaneous speed ss2 of the train is analyzed according to the time corresponding to the magnetic induction distribution map CZ2, the instantaneous speed ss2 is used as the descriptive speed of the magnetic induction distribution map CZ2, and the descriptive speed corresponding to each magnetic induction distribution map is calculated respectively.

[0115] When a train moves at high speed on a conductive track, the intensity and distribution of the electric and magnetic fields will change due to changes in the speed of the train. The speed change of a high-speed train will cause the intensity of the electric and magnetic fields generated around it to change rapidly, so there are large differences in the magnetic induction distribution diagrams at different speeds.

[0116] S303, obtain the reference speed sp of node j j , filter out train TR d The speed described in is equal to the reference speed sp j For all magnetic induction distribution diagrams, the average electric field strength and the average magnetic field strength of the measuring point c1 in these reference figures are calculated, and they are used as the reference electric field strength and the reference magnetic field strength of the measuring point c1 respectively.

[0117] The reference electric field strength and the reference magnetic field strength of each measuring point are calculated respectively, and the electromagnetic field distribution reference map is drawn for node j according to the reference electric field strength and the reference magnetic field strength of all measuring points.

[0118] S304, draw an electromagnetic field distribution reference map for each node, and d All seats in the car are mapped to the electromagnetic field distribution reference map of each node.

[0119] Analyze the electric field strength and magnetic field strength at each seat in each electromagnetic field distribution reference map, retrieve the corresponding magnetic flux density in the magnetic induction influence map according to the electric field strength and magnetic field strength, and mark the magnetic flux density of each seat in each electromagnetic field distribution reference map.

[0120] Different types of pacing electrodes are affected differently by external electromagnetic fields. Generally, the unipolar pacing mode is more susceptible to interference than the bipolar pacing mode. When different types of pacemakers work in different electromagnetic field environments, the change in magnetic flux density at the heart tissue is not a linear relationship.

[0121] In practical applications, the electrical properties of cardiac tissue change with physiological conditions, resulting in a nonlinear relationship between electromagnetic field strength and magnetic flux density.

[0122] S305. Count the number of all nodes k, obtain the magnetic flux density of the seat in each electromagnetic field distribution reference map, and calculate the average value. As the average magnetic flux density of the seat, substitute it into the formula to calculate the seat influence index YZ seat .

[0123] Calculate the influence index of each seat respectively, select the seat with the smallest influence index as the best seat, and recommend the best seat to the object. The influence index calculation formula is as follows:

[0124]

[0125] In the formula, α is a constant, T ave is the average value of the average magnetic flux density of all seats, is the magnetic flux density of the seat in the i-th electromagnetic field distribution reference diagram.

[0126] In S400, the subject is riding on a train TR d During the process, the current remaining driving route is analyzed in real time, the nodes are reset according to the remaining driving route, and the best seat is searched again.

[0127] The electromagnetic field distribution map in the train compartment is displayed in real time through a visual interface, and the best seats are dynamically updated and recommended. The train driving conditions and the electromagnetic field distribution in the compartment are collected through sensors, and the driving records and sensing records are generated and stored in the historical log.

[0128] See also Figure 2 The present invention provides a magnetic induction data analysis system based on intelligent processing, including a data acquisition module, an induction analysis module, an intelligent recommendation module and a data storage module.

[0129] The data acquisition module is used to collect the object's travel information and equipment parameters, as well as the train's historical log and route map.

[0130] The sensing analysis module is used to analyze the travel information and divide the driving sections in the route map, split the driving sections into sampling sections and set reference maps, establish measurement points on each reference map and analyze the electromagnetic field strength, calculate the difference index of each sampling section and set the node.

[0131] The intelligent recommendation module draws an electromagnetic field distribution reference map for each node and maps all seats in the car, analyzes equipment parameters and calculates the influence index of each seat, so as to select the best seat for recommendation.

[0132] The data storage module is used to update the best seats and make recommendations, collect train operation information, generate records and store them in the historical log.

[0133] The data collection module includes a route information collection unit, an object data collection unit and a history log collection unit.

[0134] The route information collection unit is used to collect all route maps available for train travel in a specified area.

[0135] The subject data acquisition unit is used to acquire the subject's travel information and device parameters. The subject refers to the pacemaker wearer, and the device refers to the pacemaker worn by the subject.

[0136] The trip information includes the starting point and the end point of the trip. The device parameters include the model of the pacemaker and the magnetic induction influence diagram, which includes the magnetic flux density at the heart tissue when the pacemaker works under different electric field strengths and magnetic field strengths.

[0137] The historical log collection unit is used to collect driving logs and sensing logs. The driving log includes all driving records of each train, and each driving record includes the train's driving route and driving time period.

[0138] The induction log includes all induction records of each train. Each induction record includes a magnetic induction distribution map of the train at different times. The magnetic induction distribution map refers to the distribution position map of the electric field and magnetic field strength in the train compartment.

[0139] The induction analysis module includes an impact section analysis unit and a difference index calculation unit.

[0140] The impact section analysis unit is used to split the sampling sections and mark them.

[0141] First, the driving section RT is divided in the route map according to the starting point and the end point in the trip information, and the driving record whose driving route includes the driving section RT is marked in the driving log.

[0142] Secondly, obtain the marked driving record REC m Corresponding train TR m , and analyze the driving record REC m The driving time period TS occupied by the driving section RT part , the train TR m Corresponding to the driving time period TS in the sensing record part All magnetic induction distribution maps are used as driving records REC m Refer to the figure.

[0143] Then, a reference map is set for each marked travel record, and the position of the train on the travel section RT is analyzed as the reference position of CZ1 according to the time corresponding to the reference map CZ1, and the reference position of each reference map is analyzed respectively.

[0144] Finally, the sampling number r is set to evenly split the driving section RT into r sampling sections with the same distance. All reference maps are assigned to different sampling sections according to the reference positions, and the sampling sections with reference maps are marked.

[0145] The difference index calculation unit is used to calculate the difference index of each marked sampling road section.

[0146] First, the number of measurement points c is set, and c measurement points are evenly set on each reference map, and the electric field strength and magnetic field strength of each measurement point are analyzed.

[0147] Secondly, obtain the marked sampling section LD m Analyze the electric field strength and magnetic field strength of the measuring point cl in these reference figures, calculate the standard deviation respectively, and sum the standard deviation of the electric field strength and the standard deviation of the magnetic field strength as the coefficient of difference of the measuring point cl.

[0148] Finally, the difference coefficient of each measurement point is calculated separately, and the difference coefficients of all measurement points are summed up as the marked sampling section LD m The difference index of each marked sampling section is calculated respectively, and the index threshold e is set, and the marked sampling sections with a difference index less than e are regarded as nodes.

[0149] The intelligent recommendation module includes an electromagnetic induction prediction unit and an optimal location recommendation unit.

[0150] The electromagnetic induction prediction unit is used to draw an electromagnetic field distribution reference map for each node.

[0151] First, analyze the marked driving record REC m The duration of the travel time period occupied by node j is time. The length of node j is divided by time to get the train TR m The driving speed at node j.

[0152] Calculate the average speed of the trains corresponding to all marked driving records at node j, and use the result as the reference speed of node j. Calculate the reference speed of each node separately.

[0153] Next, get the train TR selected by the object d , retrieve the induction log in the train TR d The instantaneous speed ss2 of the train is analyzed according to the time corresponding to the magnetic induction distribution map CZ2, the instantaneous speed ss2 is used as the descriptive speed of the magnetic induction distribution map CZ2, and the descriptive speed corresponding to each magnetic induction distribution map is calculated respectively.

[0154] Then, get the reference speed sp of node i j , filter out train TR d The speed described in is equal to the reference speed sp j For all magnetic induction distribution diagrams, the average electric field strength and the average magnetic field strength of the measuring point c1 in these reference figures are calculated, and they are used as the reference electric field strength and the reference magnetic field strength of the measuring point c1 respectively.

[0155] Finally, the reference electric field strength and reference magnetic field strength of each measuring point are calculated respectively, and an electromagnetic field distribution reference map is drawn for node j according to the reference electric field strength and reference magnetic field strength of all measuring points, and an electromagnetic field distribution reference map is drawn for each node respectively.

[0156] The best seat recommendation unit is used to analyze the best seat and recommend it to the object.

[0157] First, the train TR d All seats in the carriage are mapped to the electromagnetic field distribution reference map of each node, and the electric field strength and magnetic field strength at each seat in each electromagnetic field distribution reference map are analyzed.

[0158] Secondly, the corresponding magnetic flux density is retrieved from the magnetic induction influence diagram according to the electric field strength and magnetic field strength, and the magnetic flux density of each seat is marked in each electromagnetic field distribution reference diagram.

[0159] Then, count the number of all nodes k, obtain the magnetic flux density of the seat in each electromagnetic field distribution reference map, and calculate the average value As the average magnetic flux density of the seat seat.

[0160] Finally, according to the formula Calculate the seat influence index YZ seat . Among them, α is a constant, T ave is the average value of the average magnetic flux density of all seats, is the magnetic flux density of the seat in the i-th electromagnetic field distribution reference diagram.

[0161] The influence index of each seat is calculated respectively, and the seat with the smallest influence index is selected as the best seat, and the best seat is recommended to the object.

[0162] The data storage module resets the nodes according to the remaining route and searches for the best seat for recommendation. The sensors collect the train's running conditions and the electromagnetic field distribution in the carriage, and generate running records and sensing records respectively, which are then stored in the historical log.

[0163] Embodiment 1:

[0164] Assume that there are three nodes on the driving section, and the magnetic flux density of seat A1 at these three nodes is 2μT, 3μT and 4μT respectively, then the average magnetic flux density is 3μT. When the constant α is 2.1 and the average value of the average magnetic flux density of all seats is 3.5μT, substitute the formula to calculate the influence index of seat A1:

[0165]

[0166] The influence index of seat A1 is 1.19.

[0167] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0168] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A magnetic induction data analysis method based on intelligent processing, characterized in that: The method comprises the following steps: S100, when the subject selects a train, collecting the subject's travel information and equipment parameters, as well as historical logs and route maps of all trains; S200, analyzing the trip information and dividing the driving section in the route map, then splitting the driving section into r sampling sections and setting a reference map for each sampling section, establishing a measurement point on each reference map and analyzing the electric field strength and the magnetic field strength, thereby calculating the difference index of the sampling section, and setting the node according to the difference index; S300, calculating the reference speed of each node through historical logs, drawing an electromagnetic field distribution reference map for each node and mapping it to all seats in the train compartment, analyzing equipment parameters and calculating the magnetic flux density of each seat in each electromagnetic field distribution reference map, thereby obtaining an influence index of each seat, and selecting the best seat for recommendation according to the influence index; S400 uses a visual interface to display the electromagnetic field distribution in the train compartment in real time, dynamically updates the best seats and makes recommendations, and collects train operation information through sensors to generate records and store them in historical logs.

2. The magnetic induction data analysis method based on intelligent processing according to claim 1 is characterized in that: In S100, the subject refers to a pacemaker wearer, the train refers to a high-speed train with a traction transformer, the trip information includes the start point and the end point of the trip, the device refers to the pacemaker worn by the subject, the device parameters include the model of the pacemaker and the magnetic induction influence diagram, and the magnetic induction influence diagram includes the magnetic flux density at the heart tissue when the pacemaker works under different electric field strengths and magnetic field strengths; The historical log includes the driving log and the induction log. The driving log includes all the driving records of each train. Each driving record includes the train's route and driving time period. The induction log includes all the induction records of each train. Each induction record includes the magnetic induction distribution map of the train at different times. The magnetic induction distribution map refers to the distribution position map of the electric field and magnetic field strength in the train car. The route map is a map of all routes available for train travel in the specified area, including the driving tracks and station locations.

3. The magnetic induction data analysis method based on intelligent processing according to claim 2 is characterized in that: In S200, the specific steps are as follows: S201, obtaining the starting point and the end point in the trip information, dividing the driving section RT in the route map according to the starting point and the end point, marking the driving records of all driving routes in the driving log that include the driving section RT; obtaining the marked driving record REC m Corresponding train TR m , and analyze the driving time period TS occupied by the driving section RT part , the train TR m Corresponding to the driving time period TS in the sensing record part All magnetic induction distribution maps are used as driving records REC m Refer to the reference picture; S202, respectively set a reference reference for each marked driving record, analyze the position of the train on the driving section RT as the reference position of CZ1 according to the time corresponding to the reference reference CZ1, and respectively analyze the reference position of each reference reference; set the sampling number r, evenly split the driving section RT into r sampling sections with the same distance, assign all reference references to different sampling sections according to the reference position, and mark the sampling sections where the reference reference exists; S203, set the number of measurement points c, evenly set c measurement points on each reference map, analyze the electric field strength and magnetic field strength of each measurement point; obtain the marked sampling section LD m Download all the reference maps, analyze the electric field strength and magnetic field strength of the measuring point cl in these reference maps and calculate the standard deviation respectively, sum the standard deviation of the electric field strength and the standard deviation of the magnetic field strength as the difference coefficient of the measuring point cl, calculate the difference coefficient of each measuring point respectively, and sum the difference coefficients of all measuring points as the marking sampling section LD m The difference index of The difference index of each marked sampling section is calculated respectively, and the index threshold e is set, and the marked sampling sections with a difference index less than e are regarded as nodes.

4. The magnetic induction data analysis method based on intelligent processing according to claim 3 is characterized in that: In S300, the specific steps are as follows: S301, analyzing and marking driving record REC m The duration of the travel time period occupied by node j is time. The length of node j is divided by time to get the train TR m The speed of the train at node j; calculate the average speed of the trains corresponding to all marked driving records at node j, and use the result as the reference speed of node j, and calculate the reference speed of each node respectively; S302, obtain the selected train TR d , retrieve the induction log in the train TR d all magnetic induction distribution diagrams, analyze the instantaneous speed ss2 of the train according to the time corresponding to the magnetic induction distribution diagram CZ2, use the instantaneous speed ss2 as the descriptive speed of the magnetic induction distribution diagram CZ2, and calculate the descriptive speed corresponding to each magnetic induction distribution diagram respectively; S303, obtain the reference speed sp of node j j , filter out train TR d The speed described in is equal to the reference speed sp j Calculate the average electric field strength and the average magnetic field strength of the measuring point c1 in these reference figures, and use them as the reference electric field strength and the reference magnetic field strength of the measuring point c1 respectively; Calculate the reference electric field strength and reference magnetic field strength of each measuring point respectively, and draw an electromagnetic field distribution reference map for node j according to the reference electric field strength and reference magnetic field strength of all measuring points; S304, draw an electromagnetic field distribution reference map for each node, and d All seats in the carriage are mapped to the electromagnetic field distribution reference map of each node respectively; the electric field strength and magnetic field strength at each seat in each electromagnetic field distribution reference map are analyzed, and the corresponding magnetic flux density is retrieved in the magnetic induction influence map according to the electric field strength and magnetic field strength, and the magnetic flux density of each seat is marked in each electromagnetic field distribution reference map; S305. Count the number of all nodes k, obtain the magnetic flux density of the seat in each electromagnetic field distribution reference map, and calculate the average value. As the average magnetic flux density of the seat, substitute it into the formula to calculate the seat influence index YZ seat ; Calculate the influence index of each seat respectively, select the seat with the smallest influence index as the best seat, and recommend the best seat to the object; The impact index calculation formula is as follows: In the formula, α is a constant, T ave is the average value of the average magnetic flux density of all seats, is the magnetic flux density of the seat in the i-th electromagnetic field distribution reference diagram.

5. The magnetic induction data analysis method based on intelligent processing according to claim 4 is characterized in that: In S400, the subject is riding on a train TR d During the process, the current remaining route is analyzed in real time, nodes are reset according to the remaining route, and the best seat is found again; the electromagnetic field distribution map in the train car is displayed in real time through a visual interface, and the best seat is dynamically updated and recommended; the train driving conditions and the electromagnetic field distribution in the car are collected through sensors, and driving records and sensing records are generated and stored in the historical log.

6. A magnetic induction data analysis system based on intelligent processing, characterized in that: The system includes a data acquisition module, a sensing analysis module, an intelligent recommendation module and a data storage module; The data acquisition module is used to collect the object's travel information and equipment parameters, as well as the train's historical log and route map; The sensing analysis module is used to analyze the travel information and divide the driving sections in the route map, split the driving sections into sampling sections and set reference maps, establish measurement points on each reference map and analyze the electromagnetic field strength, calculate the difference index of each sampling section and set the node; The intelligent recommendation module draws a reference map of electromagnetic field distribution for each node and maps all seats in the carriage, analyzes equipment parameters and calculates the influence index of each seat, so as to select the best seat for recommendation; The data storage module is used to update the best seats and make recommendations, collect train operation information, generate records and store them in the historical log.

7. The magnetic induction data analysis system based on intelligent processing according to claim 6, characterized in that: The data collection module includes a route information collection unit, an object data collection unit and a history log collection unit; The route information collection unit is used to collect all route maps available for train travel in a specified area; The subject data acquisition unit is used to collect the subject's travel information and device parameters; the subject refers to the pacemaker wearer, and the device refers to the pacemaker worn by the subject; the travel information includes the starting point and the end point of the current travel; the device parameters include the model of the pacemaker and the magnetic induction influence diagram, and the magnetic induction influence diagram includes the magnetic flux density at the heart tissue when the pacemaker works under different electric field strengths and magnetic field strengths; The historical log collection unit is used to collect driving logs and induction logs; the driving log includes all driving records of each train, and each driving record includes the train's driving route and driving time period; the induction log includes all induction records of each train, and each induction record includes the magnetic induction distribution map of the train at different times. The magnetic induction distribution map refers to the distribution position map of the electric field and magnetic field intensity in the train car.

8. The magnetic induction data analysis system based on intelligent processing according to claim 7, characterized in that: The sensing analysis module includes an impact section analysis unit and a difference index calculation unit; The impact section analysis unit is used to split the sampling sections and mark them; First, the driving section RT is divided in the route map according to the starting point and the end point in the trip information, and the driving record whose driving route includes the driving section RT is marked in the driving log; Secondly, obtain the marked driving record REC m Corresponding train TR m , and analyze the driving record REC m The driving time period TS occupied by the driving section RT part , the train TR m Corresponding to the driving time period TS in the sensing record part All magnetic induction distribution maps are used as driving records REC m Refer to the reference picture; Then, a reference map is set for each marked driving record, and the position of the train on the driving section RT is analyzed as the reference position of CZ1 according to the time corresponding to the reference map CZ1, and the reference position of each reference map is analyzed respectively; Finally, set the sampling number r, evenly split the driving section RT into r sampling sections with the same distance, assign all references to different sampling sections according to the reference position, and mark the sampling sections with references; The difference index calculation unit is used to calculate the difference index of each marked sampling section; First, set the number of measurement points c, evenly set c measurement points on each reference map, and analyze the electric field strength and magnetic field strength of each measurement point; Secondly, obtain the marked sampling section LD m Refer to all the following references, analyze the electric field strength and magnetic field strength of the measuring point cl in these references and calculate the standard deviation respectively, and sum the standard deviation of the electric field strength and the standard deviation of the magnetic field strength as the difference coefficient of the measuring point cl; Finally, the difference coefficient of each measurement point is calculated separately, and the difference coefficients of all measurement points are summed up as the marked sampling section LD m The difference index of The difference index of each marked sampling section is calculated respectively, and the index threshold e is set, and the marked sampling sections with a difference index less than e are regarded as nodes.

9. The magnetic induction data analysis system based on intelligent processing according to claim 8, characterized in that: The intelligent recommendation module includes an electromagnetic induction prediction unit and an optimal location recommendation unit; The electromagnetic induction prediction unit is used to draw an electromagnetic field distribution reference map for each node; First, analyze the marked driving record REC m The duration of the travel time period occupied by node j is time. The length of node j is divided by time to get the train TR m Travel speed at node j; Calculate the average speed of the trains corresponding to all marked driving records at node j, and use the result as the reference speed of node j. Calculate the reference speed of each node respectively; Next, get the train TR selected by the object d , retrieve the induction log in the train TR d all magnetic induction distribution diagrams, analyze the instantaneous speed ss2 of the train according to the time corresponding to the magnetic induction distribution diagram CZ2, use the instantaneous speed ss2 as the descriptive speed of the magnetic induction distribution diagram CZ2, and calculate the descriptive speed corresponding to each magnetic induction distribution diagram respectively; Then, obtain the reference speed sp of node j j , filter out train TR d The speed described in is equal to the reference speed sp j Calculate the average electric field strength and the average magnetic field strength of the measuring point c1 in these reference figures, and use them as the reference electric field strength and the reference magnetic field strength of the measuring point c1 respectively; Finally, the reference electric field strength and reference magnetic field strength of each measuring point are calculated respectively, and the electromagnetic field distribution reference map is drawn for node j according to the reference electric field strength and reference magnetic field strength of all measuring points, and the electromagnetic field distribution reference map is drawn for each node; The best position recommendation unit is used to analyze the best seat and recommend it to the subject; First, the train TR d All seats in the carriage are mapped to the electromagnetic field distribution reference map of each node, and the electric field strength and magnetic field strength at each seat in each electromagnetic field distribution reference map are analyzed; Secondly, the corresponding magnetic flux density is retrieved in the magnetic induction influence diagram according to the electric field strength and magnetic field strength, and the magnetic flux density of each seat is marked in each electromagnetic field distribution reference diagram; Then, count the number of all nodes k, obtain the magnetic flux density of the seat in each electromagnetic field distribution reference map, and calculate the average value As the average magnetic flux density of the seat; Finally, according to the formula Calculate the seat influence index YZ seat ; where α is a constant, T ave is the average value of the average magnetic flux density of all seats, is the magnetic flux density of the seat in the i-th electromagnetic field distribution reference diagram; The influence index of each seat is calculated respectively, and the seat with the smallest influence index is selected as the best seat, and the best seat is recommended to the object.

10. The magnetic induction data analysis system based on intelligent processing according to claim 9, characterized in that: The data storage module resets the nodes according to the remaining route and searches for the best seats for recommendation again. It collects the train's running conditions and the electromagnetic field distribution in the carriage through sensors, generates running records and sensing records respectively, and stores them in the historical log.

Images