# US 12,009,874 B2 · Handling of impaired antenna branch > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,009,874 B2 - Document ID: US12009874B2 - Status: Granted - Kind: B2 - Application number: 17/415,149 - Filed: 2018-12-18 - Published: 2022-02-24 - Granted: 2024-06-11 - Earliest claimed: 2018-12-18 - Assignees: Telefonaktiebolaget LM Ericsson (publ) - Applicants: Telefonaktiebolaget LM Ericsson (publ) - Inventors: Hao Zhang; Chonghao Yang; Mingshi Li - Web page: https://patentgrep.com/patent/US12009874B2 ## CPC - H04B 17/17: Detection of non-compliance or faulty performance, e.g. response deviations (H04B17/18 takes precedence) - H04B 17/12: of transmit antennas, e.g. of the amplitude or phase - H04B: TRANSMISSION ## Abstract There is provided mechanisms for handling an impaired antenna branch at a radio transceiver device. The radio transceiver device includes a plurality of antenna branches. Channel information is correlated among the respective antenna branches according to a correlation relation. A method is performed by a network node. The method includes obtaining an indication that at least one of the antenna branches at the radio transceiver device is impaired. The method includes, in response thereto obtaining channel information for each of the non-impaired antenna branches at the radio transceiver device. The method includes estimating channel information for each of the at least one impaired antenna branch using the obtained channel information and the correlation relation. ## Claims ### Claim 1 A method for handling an impaired antenna branch at a radio transceiver device comprising a plurality of antenna branches, channel information being correlated among the respective antenna branches according to a correlation relation, the method being performed by a network node, the method comprising: obtaining an indication that at least one of the antenna branches at the radio transceiver device is impaired, the indication specifying that fewer than a threshold number of the antenna branches at the radio transceiver device is impaired, and in response thereto: obtaining channel information for each non-impaired antenna branch of the plurality of antenna branches at the radio transceiver device; estimating channel information for each of the at least one impaired antenna branch using the obtained channel information and the correlation relation; obtaining further channel information for all the antenna branches at the radio transceiver device; and updating the correlation relation by training a machine learning model with the further channel information as input. ### Claim 2 (depends on 1) The method according to claim 1, further comprising: performing downlink beamforming based on the obtained channel information and the estimated channel information. ### Claim 3 (depends on 1) The method according to claim 1, wherein the obtained channel information for each of the non-impaired antenna branches is based on measurements on uplink reference signals. ### Claim 4 (depends on 1) The method according to claim 1, wherein the correlation relation is learned from training performed on the channel information for all the antenna branches when none of the antenna branches are impaired. ### Claim 5 (depends on 1) The method according to claim 1, wherein each of the antenna branches is associated with its own weight in the model, and wherein the weights are updated when training the model. ### Claim 6 (depends on 1) The method according to claim 1, wherein the model is provided as a neural network. ### Claim 7 (depends on 1) The method according to claim 1, further comprising: obtaining a further indication that the estimated channel information for each of the at least one impaired antenna branch is not within a predicted range; and wherein the correlation relation only is updated in response thereto. ### Claim 8 (depends on 1) The method according to claim 1, further comprising: issuing a notification that the at least one of the antenna branches at the radio transceiver device is impaired. ### Claim 9 (depends on 1) The method according to claim 1, wherein the channel information is channel state information, CSI. ### Claim 10 A network node for handling an impaired antenna branch at a radio transceiver device comprising a plurality of antenna branches, channel information being correlated among the respective antenna branches according to a correlation relation, the network node comprising: processing circuitry and; a storage medium for storing software instructions for execution by the processing circuitry, the processing circuitry being configured to cause the network node to: obtain an indication that at least one of the antenna branches at the radio transceiver device is impaired, the indication specifying that fewer than a threshold number of the antenna branches at the radio transceiver device is impaired, and in response thereto: obtain channel information for each non-impaired antenna branch of the plurality of antenna branches at the radio transceiver device; estimate channel information for each of the at least one impaired antenna branch using the obtained channel information and the correlation relation; obtain further channel information for all the antenna branches at the radio transceiver device; and update the correlation relation by training a machine learning model with the further channel information as input. ### Claim 11 (depends on 10) The network node according to claim 10, further configured to: perform downlink beamforming based on the obtained channel information and the estimated channel information. ### Claim 12 (depends on 10) The network node according to claim 10, further configured to: issue a notification that the at least one of the antenna branches at the radio transceiver device is impaired. ### Claim 13 A non-transitory computer storage medium storing a computer program for handling an impaired antenna branch at a radio transceiver device comprising a plurality of antenna branches, channel information being correlated among the respective antenna branches according to a correlation relation, the computer program comprising computer code which, when run on processing circuitry of a network node, causes the network node to: obtain an indication that at least one of the antenna branches at the radio transceiver device is impaired, the indication specifying that fewer than a threshold number of the antenna branches at the radio transceiver device is impaired, and in response thereto: obtain channel information for each non-impaired antenna branch of the plurality of antenna branches at the radio transceiver device; estimate channel information for each of the at least one impaired antenna branch using the obtained channel information and the correlation relation; obtain further channel information for all the antenna branches at the radio transceiver device; and update the correlation relation by training a machine learning model with the further channel information as input.