# US 2019/0319835 A1 · Autonomous optimization of intra-train communication network

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2019/0319835 A1
- Document ID: US20190319835A1
- Status: Published application
- Kind: A1
- Application number: 16/387,029
- Filed: 2019-04-17
- Published: 2019-10-17
- Earliest claimed: 2018-04-17
- Assignees: Amsted Rail Company, Inc.
- Applicants: Amsted Rail Company, Inc.
- Inventors: Edward J. Mansfield
- Web page: https://patentgrep.com/patent/US20190319835A1

## CPC

- H04L 67/12: specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
- B61L 15/0027: {Radio-based, e.g. using GSM-R}
- B61L 15/0081: {On-board diagnosis or maintenance}
- B61L 23/042: {Track changes detection}
- B61L 25/025: {Absolute localisation, e.g. providing geodetic coordinates}
- G01W 1/10: Devices for predicting weather conditions (computers per se G06; display devices G09)
- H04L 41/082: the condition being updates or upgrades of network functionality
- H04L 41/0823: characterised by the purposes of a change of settings, e.g. optimising configuration for enhancing reliability (for optimising operational conditions of wireless networks H04W24/02)
- H04L 43/16: Threshold monitoring
- H04L 67/34: {involving the movement of software or configuration parameters (network booting or remote initial program loading [RIPL] G06F9/4416)}
- B61L 2205/00: Communication or navigation systems for railway traffic
- G01W 2203/00: Real-time site-specific personalized weather information, e.g. nowcasting
- H04L 43/08: Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- B61L: GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC (brakes or auxiliary equipment B61H, B61K; point or crossing construction E01B)
- G01W: METEOROLOGY (radar, sonar, lidar or analogous systems, designed for meteorological use G01S13/95, G01S15/88, G01S17/95)

## Abstract

A system for dynamically adjusting a configuration of an intra-train communication network includes an electronic device and a computer-readable storage medium. The computer-readable storage medium has one or more programming instructions that, when executed, cause the electronic device to receive one or more parameters values associated with a train consist, determine whether a potentially adverse condition that would affect intra-train communication for the train consist is anticipated based on at least a portion of the received parameters, in response to determining that the potentially adverse condition is anticipated, identify one or more updated network parameter settings that will assist in maintaining intra-train communication of the train consist during an occurrence of the potentially adverse condition by executing a machine learning model, and implement the identified one or more updated network parameter settings.

## Claims

### Claim 1

A method of dynamically adjusting a configuration of an intra-train communication network, the method comprising:
receiving, by an electronic device, one or more parameter values associated with a train consist;
determining, by the electronic device, whether a potentially adverse condition that would affect intra-train communication for the train consist is anticipated based on at least a portion of the received parameter values;
in response to determining that the potentially adverse condition is anticipated, identifying, by the electronic device, one or more updated network parameter settings that will assist in maintaining intra-train communication of the train consist during an occurrence of the potentially adverse condition by executing a machine learning model; and
implementing, by the electronic device, the identified one or more updated network parameter settings.

### Claim 2 (depends on 1)

The method of claim 1:
further comprising identifying, by the electronic device, one or more historical parameter values associated with a previous navigation of at least a portion of a route being travelled by the train consist or by one or more other train consists,
wherein determining whether a potentially adverse condition that would affect intra-train communication for the train consist is anticipated comprises making such determination based on at least a portion of the historical parameter values.

### Claim 3 (depends on 1)

The method of claim 1, wherein receiving one or more parameters values associated with a train consist comprises receiving at least a portion of the one or more parameter values from a gateway of the train consist, wherein the one or more parameter values are measured by one or more sensors of the train consist, wherein the one or more sensors comprise one or more of the following:
an accelerometer;
a gyroscope;
a magnetometer;
a motion sensor;
a location sensor;
a temperature sensor;
a humidity sensor;
a barometric pressure sensor; or
an atmospheric sensor.

### Claim 4 (depends on 1)

The method of claim 1, wherein:
the potentially adverse condition is a tight turn,
receiving one or more parameter values associated with the train consists comprises receiving:
a centrifugal force measurement or an angular acceleration measurement, and
a duration associated with the centrifugal force measurement or the angular acceleration measurement, executing the machine learning model comprises:
determining whether the duration associated with the centrifugal force measurement or the angular acceleration measurement exceeds a threshold value,
in response to determining that the duration exceeds the threshold value, decreasing a hop distance value associated with the train consist,
determining whether a link margin value associated with the train consist exceeds a link margin threshold value, and
in response to determining that the link margin value does not exceed the link margin threshold value, further decreasing the hop distance value until the link margin value exceeds the link margin threshold value.

### Claim 5 (depends on 4)

The method of claim 4, further comprising:
determining that the train consist has cleared the tight turn; and
restoring the hop distance value to a value in effect prior to encountering the tight turn.

### Claim 6 (depends on 1)

The method of claim 1, wherein:
the potentially adverse condition is a tight turn,
receiving one or more parameter values associated with the train consists comprises receiving:
a centrifugal force measurement or an angular acceleration measurement, and
a duration associated with the centrifugal force measurement or the angular acceleration measurement, executing the machine learning model comprises:
determining whether the duration associated with the centrifugal force measurement or the angular acceleration measurement exceeds a threshold value,
in response to determining that the duration exceeds the threshold value, decreasing a parent-child relationship value associated with the train consist,
determining whether a link margin value associated with the train consist exceeds a link margin threshold value, and
in response to determining that the link margin value does not exceed the link margin threshold value, further decreasing the parent-child relationship value until the link margin value exceeds the link margin threshold value.

### Claim 7 (depends on 6)

The method of claim 6, further comprising:
determining that the train consist has cleared the tight turn; and
restoring the parent/child relationship value to a value in effect prior to encountering the tight turn.

### Claim 8 (depends on 1)

The method of claim 1, wherein:
the potentially adverse condition is rough track, broken track or an area of track subsidence,
receiving one or more parameter values associated with the train consists comprises receiving:
a measurement of an amount of vibration being experienced,
a location associated with where the measurement was obtained, executing the machine learning model comprises:
obtaining historical data comprising vibration information experienced by the train consist or one or more of the other train consists during a previous journey, and
determining whether at least a portion of the received parameter values correlates to at least a portion of the historical data, and, if so, classifying the one or more parameter values as a causation;
the method further comprises:
determining whether a link margin value exceeds a link margin threshold value, and
in response to determining that the link margin value exceeds the link margin threshold value, reducing a hop distance value associated with the train consist and reducing a parent/child relationship value associated with the train consist.

### Claim 9 (depends on 8)

The method of claim 8, further comprising:
in response to determining that the link margin value exceeds the link margin threshold value, restoring each of the hop distance value and the parent/child relationship value to a value in effect prior to encountering the potentially adverse condition.

### Claim 10 (depends on 1)

The method of claim 1, wherein:
the potential adverse condition is a weather-related event,
receiving one or more parameter values associated with the train consists comprises receiving one or more of a temperature measurement or a humidity measurement,
executing the machine learning model comprises:
determining whether a duration associated with the temperature measurement or the humidity measurement exceeds a threshold value,
in response to determining that the duration exceeds the threshold value:
determining whether a link margin value exceeds a link margin threshold value, and
in response to determining that the link margin value does not exceed the link margin threshold value, decreasing a hop distance value associated with the train consist.

### Claim 11 (depends on 10)

The method of claim 10, further comprising:
determining whether the hop distance value exceeds a hop distance threshold value; and
in response to determining that the hop distance value does not exceed the hop distance threshold value, increasing a transmission power value associated with the train consist.

### Claim 12 (depends on 11)

The method of claim 11, further comprising:
determining that the train consist is no longer experiencing the weather-related event; and
performing one or more of the following:
restoring the hop distance value to a value in effect prior to encountering the weather-related event, or
restoring the transmission power value to a value in effect prior to encountering the weather-related event.

### Claim 13 (depends on 1)

The method of claim 1, wherein:
the potential adverse condition is inter-symbol interference,
receiving one or more parameter values associated with the train consists comprises receiving a link margin value associated with the train consist,
executing the machine learning model comprises:
determining whether the link margin value exceeds a link margin threshold value, and
in response to determining that the link margin value does not exceed the link margin threshold value:
decreasing a hop distance value until the hop distance value does not exceed a hop distance threshold value,
determining whether the link margin value exceeds a link margin threshold value,
in response to determining that the link margin value does not exceed the link margin threshold value:
reducing a transmission power value associated with the train consist, and
determining whether the transmission power value is greater than a minimum output value.

### Claim 14 (depends on 13)

The method of claim 13, further comprising:
in response to determining that the transmission power value is greater than the minimum output value:
determining whether the link margin value exceeds the link margin threshold value,
in response to determining that the link margin value does not exceed the link margin threshold value:
further reducing the transmission power value associated with the train consist, and
determining whether the further reduced transmission power value is greater than a minimum output value.

### Claim 15 (depends on 14)

The method of claim 14, further comprising:
determining that the train consist is no longer experiencing inter-symbol interference; and
restoring the transmission power value to a value in effect prior to encountering the inter-symbol interference.

### Claim 16 (depends on 1)

The method of claim 1, wherein:
the potential adverse condition is noise interference,
receiving one or more parameter values associated with the train consists comprises receiving a link margin value associated with the train consist,
executing the machine learning model comprises:
determining whether the link margin value exceeds a link margin threshold value,
in response to determining that the link margin value does not exceed the link margin threshold value:
increasing a transmission power value associated with the train consist, and
determining whether the transmission power value is less than the maximum output value.

### Claim 17 (depends on 16)

The method of claim 16, further comprising:
in response to determining that the transmission power value is less than the maximum output value:
determining whether the link margin value exceeds the link margin threshold value,
in response to determining that the link margin value does not exceed the link margin threshold value:
further increasing the transmission power value associated with the train consist, and
determining whether the further increased transmission power value is greater than the maximum output value.

### Claim 18 (depends on 16)

The method of claim 16, further comprising:
determining that the train consist is no longer experiencing noise interference; and
restoring the transmission power value to a value in effect prior to encountering the noise interference.

### Claim 19

A system for dynamically adjusting a configuration of an intra-train communication network, the system comprising:
an electronic device; and
a computer-readable storage medium comprising one or more programming instructions that, when executed, cause the electronic device to:
receive one or more parameters values associated with a train consist,
determine whether a potentially adverse condition that would affect intra-train communication for the train consist is anticipated based on at least a portion of the received parameters,
in response to determining that the potentially adverse condition is anticipated, identify one or more updated network parameter settings that will assist in maintaining intra-train communication of the train consist during an occurrence of the potentially adverse condition by executing a machine learning model, and
implement the identified one or more updated network parameter settings.

### Claim 20 (depends on 19)

The system of claim 19, wherein:
the computer-readable storage medium further comprises one or more programming instructions that, when executed, cause the electronic device to identify one or more historical parameter values associated with a previous navigation of at least a portion of a route being travelled by the train consist or by one or more other train consists,
the one or more programming instructions that, when executed, cause the electronic device to determine whether a potentially adverse condition that would affect intra-train communication for the train consist is anticipated comprises one or more programming instructions that, when executed, cause the electronic device to make such determination based on at least a portion of the historical parameter values.

### Claim 21 (depends on 19)

The system of claim 19, wherein the one or more programming instructions that, when executed, cause the electronic device to receive one or more parameters values associated with a train consist comprise one or more programming instructions that, when executed, cause the electronic device to receive at least a portion of the one or more parameter values from a gateway of the train consist, wherein the one or more parameter values are measured by one or more sensors of the train consist, wherein the one or more sensors comprise one or more of the following:
an accelerometer;
a gyroscope;
a magnetometer;
a motion sensor;
a location sensor;
a temperature sensor;
a humidity sensor;
a barometric pressure sensor; or
an atmospheric sensor.

### Claim 22 (depends on 19)

The system of claim 19, wherein the one or more programming instructions that, when executed, cause the electronic device to receive one or more parameters values associated with the train consist comprise one or more programming instructions that, when executed, cause the electronic device to receive at least a portion of the one or more parameter values from one or more sensors of the train consist.

### Claim 23 (depends on 19)

The system of claim 19, wherein:
the potentially adverse condition is a tight turn,
the one or more programming instructions that, when executed, cause the electronic device to receive one or more parameter values associated with the train consists comprise one or more programming instructions that, when executed, cause the electronic device to receive:
a centrifugal force measurement or an angular acceleration measurement, and
a duration associated with the centrifugal force measurement or the angular acceleration measurement,
the one or more programming instructions that, when executed, cause the electronic device to execute the machine learning model comprise one or more programming instructions that, when executed, cause the electronic device to:
determine whether the duration associated with the centrifugal force measurement or the angular acceleration measurement exceeds a threshold value,
in response to determining that the duration exceeds the threshold value, decrease a hop distance value associated with the train consist,
determine whether a link margin value associated with the train consist exceeds a link margin threshold value, and
in response to determining that the link margin value does not exceed the link margin threshold value, further decrease the hop distance value until the link margin value exceeds the link margin threshold value.

### Claim 24 (depends on 23)

The system of claim 23, wherein the computer-readable storage medium further comprises one or more programming instructions that, when executed, cause the electronic device to:
determine that the train consist has cleared the tight turn; and
restore the hop distance value to a value in effect prior to encountering the tight turn.

### Claim 25 (depends on 19)

The system of claim 19, wherein:
the potentially adverse condition is a tight turn,
the one or more programming instructions that, when executed, cause the electronic device to receive one or more parameter values associated with the train consists comprise the one or more programming instructions that, when executed, cause the electronic device to receive:
a centrifugal force measurement or an angular acceleration measurement, and
a duration associated with the centrifugal force measurement or the angular acceleration measurement,
the one or more programming instructions that, when executed, cause the electronic device to execute the machine learning model comprise one or more programming instructions that, when executed, cause the electronic device to:
determine whether the duration associated with the centrifugal force measurement or the angular acceleration measurement exceeds a threshold value,
in response to determining that the duration exceeds the threshold value, decrease a parent-child relationship value associated with the train consist,
determine whether a link margin value associated with the train consist exceeds a link margin threshold value, and
in response to determining that the link margin value does not exceed the link margin threshold value, further decrease the parent-child relationship value until the link margin value exceeds the link margin threshold value.

### Claim 26 (depends on 25)

The system of claim 25, wherein the computer-readable storage medium further comprises one or more programming instructions that, when executed, cause the electronic device to:
determine that the train consist has cleared the tight turn; and
restore the parent/child relationship value to a value in effect prior to encountering the tight turn.

### Claim 27 (depends on 19)

The system of claim 19, wherein:
the potentially adverse condition is rough track, broken track or an area of track subsidence,
the one or more programming instructions that, when executed, cause the electronic device to receive one or more parameter values associated with the train consists comprise one or more programming instructions that, when executed, cause the electronic device to receive:
a measurement of an amount of vibration being experienced,
a location associated with where the measurement was obtained,
the one or more programming instructions that, when executed, cause the electronic device to execute the machine learning model comprise one or more programming instructions that, when executed, cause the electronic device to:
obtain historical data comprising vibration information experienced by the train consist or one or more of the other train consists during a previous journey, and
determine whether at least a portion of the received parameter values correlates to at least a portion of the historical data, and, if so, classifying the one or more parameter values as a causation;
the computer-readable storage medium further comprises one or more programming instructions that, when executed, cause the electronic device to:
determine whether a link margin value exceeds a link margin threshold value, and
in response to determining that the link margin value exceeds the link margin threshold value, reduce a hop distance value associated with the train consist and reduce a parent/child relationship value associated with the train consist.

### Claim 28 (depends on 27)

The system of claim 27, wherein the computer-readable storage medium further comprises one or more programming instructions that, when executed, cause the electronic device to, in response to determining that the link margin value exceeds the link margin threshold value, restoring each of the hop distance value and the parent/child relationship value to a value in effect prior to encountering the potentially adverse condition.

### Claim 29 (depends on 19)

The system of claim 19, wherein:
the potential adverse condition is a weather-related event,
the one or more programming instructions that, when executed, cause the electronic device to receive one or more parameter values associated with the train consists comprise one or more programming instructions that, when executed, cause the electronic device to receive one or more of a temperature measurement or a humidity measurement,
the one or more programming instructions that, when executed, cause the electronic device to execute the machine learning model comprise one or more programming instructions that, when executed, cause the electronic device to:
determine whether a duration associated with the temperature measurement or the humidity measurement exceeds a threshold value,
in response to determining that the duration exceeds the threshold value:
determine whether a link margin value exceeds a link margin threshold value, and
in response to determining that the link margin value does not exceed the link margin threshold value, decrease a hop distance value associated with the train consist.

### Claim 30 (depends on 29)

The system of claim 29, wherein the computer-readable storage medium further comprises one or more programming instructions that, when executed, cause the electronic device to:
determine whether the hop distance value is less than a hop distance threshold value;
in response to determining that the hop distance value is less than the hop distance threshold value, increase a transmission power value associated with the train consist.

### Claim 31 (depends on 30)

The system of claim 30, wherein the computer-readable storage medium further comprises one or more programming instructions that, when executed, cause the electronic device to:
determine that the train consist is no longer experiencing the weather-related event; and
perform one or more of the following:
restore the hop distance value to a value in effect prior to encountering the weather-related event, or
restore the transmission power value to a value in effect prior to encountering the weather-related event.

### Claim 32 (depends on 19)

The system of claim 19, wherein:
the potential adverse condition is inter-symbol interference,
the one or more programming instructions that, when executed, cause the electronic device to receive one or more parameter values associated with the train consists comprise the one or more programming instructions that, when executed, cause the electronic device to receive a link margin value associated with the train consist,
the one or more programming instructions that, when executed, cause the electronic device to execute the machine learning model comprise one or more programming instructions that, when executed, cause the electronic device to:
determine whether the link margin value exceeds a link margin threshold value, and
in response to determining that the link margin value does not exceed the link margin threshold value:
decrease a hop distance value until the hop distance value does not exceed a hop distance threshold value,
determine whether the link margin value exceeds a link margin threshold value,
in response to determining that the link margin value does not exceed the link margin threshold value:
reduce a transmission power value associated with the train consist, and
determine whether the transmission power value is greater than a minimum output value.

### Claim 33 (depends on 32)

The system of claim 32, wherein the computer-readable storage medium further comprises one or more programming instructions that, when executed, cause the electronic device to:
in response to determining that the transmission power value is greater than the minimum output value:
determine whether the link margin value exceeds the link margin threshold value,
in response to determining that the link margin value does not exceed the link margin threshold value:
further reduce the transmission power value associated with the train consist, and
determine whether the further reduced transmission power value is greater than a minimum output value.

### Claim 34 (depends on 32)

The system of claim 32, wherein the computer-readable storage medium further comprises one or more programming instructions that, when executed, cause the electronic device to:
determine that the train consist is no longer experiencing inter-symbol interference; and
restore the transmission power value to a value in effect prior to encountering the inter-symbol interference.

### Claim 35 (depends on 19)

The system of claim 19, wherein:
the potential adverse condition is noise interference,
the one or more programming instructions that, when executed, cause the electronic device to receive one or more parameter values associated with the train consists comprise one or more programming instructions that, when executed, cause the electronic device to receive a link margin value associated with the train consist,
the one or more programming instructions that, when executed, cause the electronic device to execute the machine learning model comprise one or more programming instructions that, when executed, cause the electronic device to:
determine whether the link margin value exceeds a link margin threshold value,
in response to determining that the link margin value does not exceed the link margin threshold value:
increase a transmission power value associated with the train consist, and
determine whether the transmission power value is less than the maximum output value.

### Claim 36 (depends on 35)

The system of claim 35, wherein the computer-readable storage medium further comprises one or more programming instructions that, when executed, cause the electronic device to:
in response to determining that the transmission power value is less than the maximum output value:
determine whether the link margin value exceeds the link margin threshold value,
in response to determining that the link margin value does not exceed the link margin threshold value:
further increase the transmission power value associated with the train consist, and
determine whether the further increased transmission power value is greater than the maximum output value.

### Claim 37 (depends on 35)

The system of claim 35, wherein the computer-readable storage medium further comprises one or more programming instructions that, when executed, cause the electronic device to:
determine that the train consist is no longer experiencing noise interference; and
restore the transmission power value to a value in effect prior to encountering the noise interference.

### Claim 38

A system for dynamically adjusting a configuration of an intra-train communication network, the system comprising:
an electronic device; and
a computer-readable storage medium comprising one or more programming instructions that, when executed, cause the electronic device to:
receive one or more parameters values associated with a train consist,
determine whether the train consist is no longer experiencing a potentially adverse condition that affected intra-train communication for the train consist based on at least a portion of the received parameters, and
in response to determining that the train consist is no longer experiencing the potentially adverse condition:
identifying one or more network parameter settings that were updated while the train consist was experiencing the potentially adverse condition in order to maintain intra-train communication of the train consist during the potentially adverse condition, and
restoring the one or more network parameter settings to values that were in existence prior to the train consist experiencing the potentially adverse condition.