# US 12,179,480 B2 · Detection of printhead conditions based on isolation scoring

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

- Number: US 12,179,480 B2
- Document ID: US12179480B2
- Status: Granted
- Kind: B2
- Application number: 17/812,520
- Filed: 2022-07-14
- Published: 2024-01-18
- Granted: 2024-12-31
- Earliest claimed: 2022-07-14
- Assignees: Ricoh Company, Ltd.
- Applicants: Ian Wilkins
- Inventors: Ian Wilkins
- Web page: https://patentgrep.com/patent/US12179480B2

## CPC

- B41J 2/0451: {for detecting failure, e.g. clogging, malfunctioning actuator}
- B41J 2/16579: {Detection means therefor, e.g. for nozzle clogging}
- B41J 2/04586: {controlling heads of a type not covered by groups B41J2/04575 - B41J2/04585, or of an undefined type}
- G06K 15/027: {Test patterns and calibration (arrangements for controlling or analysing printing mechanisms of typewriters or selective printing units B41J29/393 takes precedence; colour correction using test pattern analysis in general H04N1/6033)}
- G06K 15/102: {using ink jet print heads}
- G06K 15/408: {Handling exceptions, e.g. faults (computer driven error handling and recovery for a printer G06F3/1234)}
- B41J 2002/1657: {Cleaning of only nozzles or print head parts being selected}
- B41J: TYPEWRITERS; SELECTIVE PRINTING MECHANISMS, i.e. MECHANISMS PRINTING OTHERWISE THAN FROM A FORME; CORRECTION OF TYPOGRAPHICAL ERRORS
- G06K: GRAPHICAL DATA READING (image or video recognition or understanding G06V); PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS

## Abstract

Systems and methods are provided for print quality management. One embodiment is a system for identifying print quality at a printer. The system includes a memory that stores reference data for nozzles of a printer, and a controller. The controller is configured to acquire measurement data after operation of the nozzles, calculate differences between the reference data and the measurement data, apply the differences as an input to an isolation forest, operate the isolation forest to determine isolation values for the nozzles, identify nozzles having more than a threshold amount of deviation from the reference data based on the isolation values, and generate a report flagging the identified nozzles for maintenance.

## Claims

### Claim 1

A system for identifying print quality at a printer, the system comprising:
a memory that stores reference data for a plurality of nozzles of a printer; and
a controller configured to acquire measurement data for each nozzle of the plurality of nozzles after operation of the plurality of nozzles, calculate differences for each nozzle between the reference data and the measurement data, apply the differences as an input to an isolation forest, operate the isolation forest to determine isolation values for each nozzle, identify one or more individual nozzles of the plurality of nozzles having more than a threshold amount of deviation from the reference data based on the isolation values, and generate a report flagging the identified one or more individual nozzles for maintenance.

### Claim 2 (depends on 1)

The system of claim 1 wherein:
the controller is further configured to operate the isolation forest by iteratively selecting a variable provided in the input, assigning a value to the variable, adding a partition at the value for the variable, and subdividing data points of the input into groups separated by partitions.

### Claim 3 (depends on 1)

The system of claim 1 wherein:
the controller is further configured to determine inverse isolation values for the plurality of nozzles based on the isolation values, and to include an aggregation of the inverse isolation values in the report as a print quality metric.

### Claim 4 (depends on 1)

The system of claim 1 wherein:
the isolation forest determines isolation values for printheads of the printer based on the isolation values for each nozzle contained by the printheads.

### Claim 5 (depends on 1)

The system of claim 1 wherein:
the reference data and the measurement data measure a same set of variables, and the variables include X droplet position and Y droplet position.

### Claim 6 (depends on 1)

The system of claim 1 wherein:
the reference data and the measurement data measure a same set of variables, and the variables include color accuracy.

### Claim 7 (depends on 1)

The system of claim 1 wherein:
the reference data and the measurement data measure a same set of variables, and the variables include a number of alignment adjustment actions performed during an alignment sequence.

### Claim 8

A non-transitory computer readable medium embodying programmed instructions which, when executed by a processor, are operable for performing a method of identifying print quality at a printer, the method comprising:
storing reference data for a plurality of nozzles of a printer;
acquiring measurement data for each nozzle of the plurality of nozzles after operation of the plurality of nozzles;
calculating differences for each nozzle between the reference data and the measurement data;
applying the differences as an input to an isolation forest;
operating the isolation forest to determine isolation values for each nozzle;
identifying one or more individual nozzles of the plurality of nozzles having more than a threshold amount of deviation from the reference data based on the isolation values; and
generating a report flagging the identified one or more individual nozzles for maintenance.

### Claim 9 (depends on 8)

The non-transitory computer readable medium of claim 8, wherein:
operating the isolation forest comprises iteratively:
selecting a variable provided in the input;
assigning a value to the variable;
adding a partition at the value for the variable; and
subdividing data points of the input into groups separated by partitions.

### Claim 10 (depends on 8)

The non-transitory computer readable medium of claim 8, wherein the method further comprises:
determining inverse isolation values for each nozzle of the plurality of nozzles based on the isolation values; and
including an aggregation of the inverse isolation values in the report as a print quality metric.

### Claim 11 (depends on 8)

The non-transitory computer readable medium of claim 8, wherein:
operating the isolation forest to determine the isolation values for the plurality of nozzles comprises determining isolation values for printheads of the printer that contain the plurality of nozzles.

### Claim 12 (depends on 8)

The non-transitory computer readable medium of claim 8, wherein:
the reference data and the measurement data measure a same set of variables, and the variables include X droplet position and Y droplet position.

### Claim 13 (depends on 8)

The non-transitory computer readable medium of claim 8, wherein:
the reference data and the measurement data measure a same set of variables, and the variables include color accuracy.

### Claim 14 (depends on 8)

The non-transitory computer readable medium of claim 8, wherein:
the reference data and the measurement data measure a same set of variables, and the variables include a number of alignment adjustment actions performed during an alignment sequence.

### Claim 15

A method for identifying print quality at a printer, the method comprising:
storing reference data for a plurality of nozzles of a printer;
acquiring measurement data for each nozzle of the plurality of nozzles after operation of the plurality of nozzles;
calculating differences for each nozzle between the reference data and the measurement data;
applying the differences as an input to an isolation forest;
operating the isolation forest to determine isolation values for each nozzle;
identifying one or more individual nozzles of the plurality of nozzles having more than a threshold amount of deviation from the reference data based on the isolation values; and
generating a report flagging the identified one or more individual nozzles for maintenance.

### Claim 16 (depends on 15)

The method of claim 15, wherein:
operating the isolation forest comprises iteratively:
selecting a variable provided in the input;
assigning a value to the variable;
adding a partition at the value for the variable; and
subdividing data points of the input into groups separated by partitions.

### Claim 17 (depends on 15)

The method of claim 15, further comprising:
determining inverse isolation values for each nozzle of the plurality of nozzles based on the isolation values; and
including an aggregation of the inverse isolation values in the report as a print quality metric.

### Claim 18 (depends on 15)

The method of claim 15, wherein:
operating the isolation forest to determine the isolation values for the plurality of nozzles comprises determining isolation values for printheads of the printer that contain the plurality of nozzles.

### Claim 19 (depends on 15)

The method of claim 15, wherein:
the reference data and the measurement data measure a same set of variables, and the variables include X droplet position and Y droplet position.

### Claim 20 (depends on 15)

The method of claim 15, wherein:
the reference data and the measurement data measure a same set of variables, and the variables include color accuracy.