# US 2021/0175962 A1 · Decision support method and apparatus for machinery control

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

- Number: US 2021/0175962 A1
- Document ID: US20210175962A1
- Status: Published application
- Kind: A1
- Application number: 16/707,927
- Filed: 2019-12-09
- Published: 2021-06-10
- Earliest claimed: 2019-12-09
- Assignees: Intelligent Fusion Technology, Inc.
- Applicants: Intelligent Fusion Technology, Inc.
- Inventors: Lun LI; Jingyang LU; John NGUYEN; Dan SHEN; Khanh PHAM; Genshe CHEN
- Web page: https://patentgrep.com/patent/US20210175962A1

## CPC

- H04B 7/18519: {Operations control, administration or maintenance}
- G06N 3/006: based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
- G06N 3/08: Learning methods
- G06N 3/092: Reinforcement learning
- G06N 20/00: Machine learning
- H03F 1/3241: {using predistortion circuits (H03F1/3211, H03F1/3217 take precedence)}
- H03F 3/189: High-frequency amplifiers, e.g. radio frequency amplifiers
- H03F 3/24: of transmitter output stages
- H04B 7/18513: {Transmission in a satellite or space-based system}
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- H03F 2200/451: the amplifier being a radio frequency amplifier
- H04B: TRANSMISSION
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- H03F: AMPLIFIERS

## Abstract

The present disclosure provides a high power amplifier (HPA) linearization method, applied to a ground hub which includes a predistorter and a PD controller. The ground hub is arranged in a satellite communication system together with a transmitter and a satellite transponder, and the satellite transponder includes an HPA. The HPA linearization method includes determining an initial correction signal based on a physical model with a plurality of PD parameters to compensate AM-AM and AM-PM characteristics of the HPA; receiving a signal from the satellite transponder; determining a reward function for an action taken by the PD controller; examining an action-value function for actions taken in a preset past period; taking an action to adjust the plurality of PD parameters for the PD to generate an updated correction signal; sending the update correction signal to the transmitter to compensate the AM-AM and AM-PM characteristics of the HPA.

## Claims

### Claim 1

A high power amplifier (HPA) linearization method, applied to a ground hub which includes a predistorter (PD) and a PD controller, wherein the PD controller stores a database including a set of environmental parameters and a set of PD parameters corresponding to the set of environmental parameters, the ground hub is arranged in a satellite communication (SATCOM) system together with a transmitter and a satellite transponder, and the satellite transponder includes an HPA, the method comprising:
determining an initial correction signal including an AM-AM correction signal and an AM-PM correction signal based on a physical model with a plurality of PD parameters, and sending the initial correction signal to the transmitter to compensate AM-AM and AM-PM characteristics of the HPA;
receiving a signal from the satellite transponder;
determining a reward function for an action taken by the PD controller based on the received signal and environmental parameters;
examining an action-value function for actions taken in a preset past period based on reward functions of the actions;
taking an action, based on the environment parameters and the action-value function, to adjust the plurality of PD parameters for the PD to generate an updated correction signal;
sending the update correction signal to the transmitter to compensate the AM-AM and AM-PM characteristics of the HPA; and
updating the database in a real-time manner according to the environment parameters, the plurality of PD parameters, and the action-value function.

### Claim 2 (depends on 1)

The method according to claim 1, wherein determining, by the PD, the initial correction signal based on the physical model with more than four PD parameters includes:
sending a signal to the satellite transponder from the ground hub through the transmitter and receiving a signal sent back from the satellite transponder to the ground hub;
calculating AM-AM and AM-PM characteristics of the HPA according to the signal sent to the satellite transponder and the signal received from the satellite transponder;
simulating the AM-AM and AM-PM characteristics of the HPA using the physical model with the plurality of PD parameters; and
determining the initial correction signal, including the AM-AM correction signal and the AM-PM correction signal, based on obtained values of the plurality of PD parameters.

### Claim 3 (depends on 2)

The method according to claim 2, wherein simulating the AM-AM and AM-PM characteristics of the HPA further includes:
fitting the AM-AM characteristics of the HPA by
α
0

ρ
y

(
t
)
a
0
+
β
0

(
ρ
y

(
t
)
+
b
0
)
2
,
where ρy(t) is an amplitude of an input complex signal, and a0, b0, α0, and β0 are four PD parameters of the plurality of PD parameters; and
fitting the AM-PM characteristics of the HPA by
α
1

ρ
y

(
t
)
2
a
1
+
β
1

(
ρ
y

(
t
)
+
b
1
)
2
,
where a1, b1, α1, and β1 are four PD parameters of the plurality of PD parameters.

### Claim 4 (depends on 3)

The method according to claim 3, wherein:
a least-squares criterion is used to determine fits to the AM-AM and AM-PM characteristics of the HPA.

### Claim 5 (depends on 3)

The method according to claim 3, wherein determining the initial correction signal based on the obtained values of the plurality of PD parameters includes:
determining the AM-AM correction signal as
{
(
α
0
-
2

b
0

β
0

ρ
x

(
t
)
)
-
α
0
2
-
4

β
0

ρ
x

(
t
)

(
a
0

ρ
x

(
t
)
+
b
0

α
0
)
2

β
0

ρ
x

(
t
)
2
ρ
x

(
t
)
≤
1
1
ρ
x

(
t
)
>
1
;
and
determining the AM-PM correction signal as
-
α
1

ρ
y

(
t
)
2
a
1
+
β
1

(
ρ
y

(
t
)
+
b
1
)
2
.

### Claim 6 (depends on 2)

The method according to claim 2, wherein:
the environmental parameters are observable external factors, including equipment imperfections, temperature variation, and interference signals.

### Claim 7 (depends on 1)

The method according to claim 1, further including:
when taking the action to adjust the plurality of PD parameters for the PD to generate the updated correction signal, estimating an output power and an output phase for the HPA, wherein:
the reward function is defined as a distance between estimated and measured output power and phase of the HPA.

### Claim 8 (depends on 2)

The method according to claim 2, wherein:
when examining the action-value function for actions taken in the preset past period based on reward functions of the actions, for every two consecutive actions, a discount factor is used to reduce a weight of the reward function corresponding to a former action between the two consecutive actions.

### Claim 9

A predistorter (PD) disposed in a ground hub for HPA linearization, wherein the ground hub is arranged in a SATCOM system together with a transmitter and a satellite transponder, and the satellite transponder includes an HPA, the PD comprising:
a processor; and
a memory, configured to store computer-executable instructions, wherein when the computer-executable instructions are executed, the processor is configured to:
determine an initial correction signal, including an AM-AM correction signal and an AM-PM correction signal, based on a physical model with a plurality of PD parameters, and send the initial correction signal to the transmitter to compensate AM-AM and AM-PM characteristics of the HPA; and
in respond to the PD controller taking an action to adjust the plurality of PD parameters, generate an updated correction signal, and send the updated correction signal to the transmitter to compensate the AM-AM and AM-PM characteristics of the HPA.

### Claim 10 (depends on 9)

The PD according to claim 9, wherein:
the AM-AM characteristics of the HPA are fitted by
α
0

ρ
y

(
t
)
a
0
+
β
0

(
ρ
y

(
t
)
+
b
0
)
2
,
where ρy(t) is an amplitude of an input complex signal, and a0, b0, α0, and β0 are four PD parameters of the plurality of PD parameters; and
the AM-PM characteristics of the HPA are fitted by
α
1

ρ
y

(
t
)
2
a
1
+
β
1

(
ρ
y

(
t
)
+
b
1
)
2
,
where a1, b1, α1, and β1 are four PD parameters of the plurality of PD parameters.

### Claim 11 (depends on 10)

The PD according to claim 10, wherein:
a least-squares criterion is used to determine fits to the AM-AM and AM-PM characteristics of the HPA.

### Claim 12 (depends on 9)

The PD according to claim 9, wherein:
the AM-AM correction signal is determined as
{
(
α
0
-
2

b
0

β
0

ρ
x

(
t
)
)
-
α
0
2
-
4

β
0

ρ
x

(
t
)

(
a
0

ρ
x

(
t
)
+
b
0

α
0
)
2

β
0

ρ
x

(
t
)
2
ρ
x

(
t
)
≤
1
1
ρ
x

(
t
)
>
1
;
and
the AM-PM correction signal is determined as
-
α
1

ρ
y

(
t
)
2
a
1
+
β
1

(
ρ
y

(
t
)
+
b
1
)
2
.

### Claim 13

A PD controller arranged in a ground hub, wherein the ground hub further includes a PD and is arranged in a SATCOM system together with a transmitter and a satellite transponder, the satellite transponder includes an HPA, and the PD controller receives a signal from the satellite transponder, the PD controller comprising:
a processor;
a memory, configured to store computer-executable instructions; and
a data storage, configured to store a database including a set of environmental parameters and a set of PD parameters corresponding to the set of environmental parameters, wherein when the processor executes the computer-executable instructions, the PD controller is configured to:
determine a reward function for an action taken by the PD controller based on the received signal and environmental parameters;
examine an action-value function for actions taken in a preset past period based on reward functions of the actions;
take an action, based on the measured environment parameters and the action-value function, to adjust a plurality of PD parameters for the PD to generate an updated correction signal; and
update the database, including the set of environmental parameters and the set of PD parameters, in a real-time manner according to the environment parameters, the plurality of PD parameters, and the action-value function.

### Claim 14 (depends on 13)

The PD controller according to claim 13, wherein:
the environmental parameters are observable external factors, including equipment imperfections, temperature variation, and interference signals.

### Claim 15 (depends on 13)

The PD controller according to claim 13, wherein:
when the PD controller takes the action to adjust the plurality of PD parameters for the PD to generate the updated correction signal, an output power and an output phase for the HPA are estimated, wherein:
the reward function is defined as a distance between estimated and measured output power and phase of the HPA.

### Claim 16 (depends on 13)

The PD controller according to claim 13, wherein:
when the PD controller examines the action-value function for actions taken in the preset past period based on reward functions of the actions, for every two consecutive actions, a discount factor is used to reduce a weight of the reward function corresponding to a former action between the two consecutive actions.
