US20150168950A1 - Method and apparatus for providing on-board diagnostics - Google Patents
Method and apparatus for providing on-board diagnostics Download PDFInfo
- Publication number
- US20150168950A1 US20150168950A1 US14/629,600 US201514629600A US2015168950A1 US 20150168950 A1 US20150168950 A1 US 20150168950A1 US 201514629600 A US201514629600 A US 201514629600A US 2015168950 A1 US2015168950 A1 US 2015168950A1
- Authority
- US
- United States
- Prior art keywords
- algorithm
- prognostication
- probability
- output
- prdictr
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Abandoned
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0243—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model
- G05B23/0254—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model based on a quantitative model, e.g. mathematical relationships between inputs and outputs; functions: observer, Kalman filter, residual calculation, Neural Networks
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/26—Pc applications
- G05B2219/2637—Vehicle, car, auto, wheelchair
Definitions
- This invention relates to the provision of on-board diagnostics for vehicle fleet maintenance and more particularly to the embedding of a microprocessor programmed with a prognostication algorithm on a vehicle.
- prognostication algorithms have been utilized to predict faults in the operation of vehicles. More importantly the prognostics algorithm, referred to herein as the PRDICTR algorithm, is used to analyze data from vehicles at a central or remote location where the algorithms can be run on relatively complex large fast computers. As originally described, the PRDICTR algorithms are computationally intense and were developed mainly for Class 8 vehicles which are greater than 30,000 pounds gross vehicle weight. Even if the prognostication algorithms are run at a vehicle, they require computational assets that are far in excess of those that can be offered by microprocessors. Thus hosting a prognostication algorithm on a vehicle requires not only a considerable amount of computer power, but also a considerable amount of space.
- the problem therefore becomes is how to embed prognostication in lightweight vehicles where only microprocessors are available for performing any on-board computation. There is therefore a requirement for a stripped down version of the prognostication algorithm to be able to operate on smaller processors such as microprocessors.
- a prognostication algorithm is provided for use in lightweight vehicles that can be run on local microprocessors in which the prognostication algorithms are altered to be able to operate on the smaller processors.
- these algorithms are referred to as PRDICTR Light or on-board diagnostic vehicle OBD2 algorithms.
- a modified algorithm is utilized that reconfigures the failure modes and effects analysis which is the front end of the prognostication algorithm. After providing a stripped down version of the prognostication algorithm, one must then find and apply reasoners that operate faster in this kind of environment.
- PRDICTR algorithm is ordinarily configured by modeling and simulation to create an acceptable probability for a node for a given set of inputs and an observed set of outputs.
- the on-board PRDICTR algorithm runs all inputs each time to change the model and simulation. This is of course computationally intense.
- the PRDICTR algorithm is run at the point of performance for a number of inputs. Then for a given output the input I y and the output O x is assigned a probability, with the PRDICTR algorithm then developed based on an acceptable probability. Once the PRDICTR algorithm has been developed based on the probability of one input and one output, modeling and simulation is utilized to create a modified PRDICTR algorithm, with this algorithm being embedded at the point of performance on a microprocessor. The result is improved fault determination which is faster, more accurate, and requires less infrastructure than the prior instantiation of the prognostication algorithms.
- on-board diagnostics for fleet maintenance is improved by embedding a microprocessor programmed with a prognostication algorithm on a vehicle.
- FIG. 1 is a diagrammatic illustration of a prior art 30,000 plus gross ton vehicle having an onboard PRDICTR algorithm within the cab of the vehicle;
- FIG. 2 is a diagrammatic illustration of a light vehicle in which a microprocessor with a PRDICTR Light algorithm is utilized to permit the use of microprocessors;
- FIG. 3 is a listing of the on-board PRDICTR prior art requirements for modeling and simulation that creates a probability of a node for a given set of inputs, indicating that all inputs must be run each time in order to change the model and simulation used in the prognostication algorithm;
- FIG. 4 is a diagrammatic illustration of a set of inputs and outputs that describe the operation of a system at a point of performance, in which selected inputs and outputs are analyzed as to probability, thereby to be able to develop a stripped down PRDICTR algorithm based on acceptable probability, with the stripped, down PRDICTR algorithm embedded at the point of performance.
- the prior PRDICTR algorithms are utilized on Class 8 vehicles those such as vehicle 10 that are 30,000 plus gross weight vehicles, in which the on-board PRDICTR algorithm 12 is run on an embedded computer 14 within the vehicle.
- computer 14 The size and computational capabilities of computer 14 are not those associated with microprocessors, but rather these computers have massive computational power, unsuitable for use in light vehicles due to size and complexity.
- a light vehicle 20 includes a microprocessor with a light version of the PRDICTR algorithm as illustrated at 22 , with the microprocessor being embedded in the vehicle.
- the algorithm takes inputs from selected vehicle sensors and provides prognostic predications of vehicle failure modes. It is the purpose of the subject invention to provide a PRDICTR Light version of at prognostication algorithm to permit the use of microprocessors by eliminating running massive numbers of inputs each time in order to exercise the prognostication algorithm.
Abstract
On-board diagnostics for fleet maintenance is improved by embedding a microprocessor programmed with a prognostication algorithm on a vehicle.
Description
- This Application is a continuation of U.S. application Ser. No. 12/807,923 filed Sep. 16, 2010 and claims rights under 35 USC §119(e) from U.S. Application Ser. No. 61/342,133 filed Apr. 9, 2010, the contents of which are incorporated herein by reference.
- This invention relates to the provision of on-board diagnostics for vehicle fleet maintenance and more particularly to the embedding of a microprocessor programmed with a prognostication algorithm on a vehicle.
- As discussed in U.S. patent application Ser. No. 12/548,683 by Carolyn Spier filed on Aug. 27, 2009, assigned to the assignee hereof incorporated herein reference, prognostication algorithms have been utilized to predict faults in the operation of vehicles. More importantly the prognostics algorithm, referred to herein as the PRDICTR algorithm, is used to analyze data from vehicles at a central or remote location where the algorithms can be run on relatively complex large fast computers. As originally described, the PRDICTR algorithms are computationally intense and were developed mainly for Class 8 vehicles which are greater than 30,000 pounds gross vehicle weight. Even if the prognostication algorithms are run at a vehicle, they require computational assets that are far in excess of those that can be offered by microprocessors. Thus hosting a prognostication algorithm on a vehicle requires not only a considerable amount of computer power, but also a considerable amount of space.
- The problem therefore becomes is how to embed prognostication in lightweight vehicles where only microprocessors are available for performing any on-board computation. There is therefore a requirement for a stripped down version of the prognostication algorithm to be able to operate on smaller processors such as microprocessors.
- A prognostication algorithm is provided for use in lightweight vehicles that can be run on local microprocessors in which the prognostication algorithms are altered to be able to operate on the smaller processors. In one embodiment these algorithms are referred to as PRDICTR Light or on-board diagnostic vehicle OBD2 algorithms.
- In order to provide a stripped down version of the prognostication algorithm, a modified algorithm is utilized that reconfigures the failure modes and effects analysis which is the front end of the prognostication algorithm. After providing a stripped down version of the prognostication algorithm, one must then find and apply reasoners that operate faster in this kind of environment.
- Once having provided a stripped down PRDICTR algorithm that exhibits appropriate validity, then this algorithm is embedded into the smaller vehicles.
- In order to provide the stripped down version of the PRDICTR algorithm, it is noted that PRDICTR algorithm is ordinarily configured by modeling and simulation to create an acceptable probability for a node for a given set of inputs and an observed set of outputs. In the prior art, the on-board PRDICTR algorithm runs all inputs each time to change the model and simulation. This is of course computationally intense.
- Rather than running all inputs each time one wishes to change a model and simulation, in the subject invention the PRDICTR algorithm is run at the point of performance for a number of inputs. Then for a given output the input Iy and the output Ox is assigned a probability, with the PRDICTR algorithm then developed based on an acceptable probability. Once the PRDICTR algorithm has been developed based on the probability of one input and one output, modeling and simulation is utilized to create a modified PRDICTR algorithm, with this algorithm being embedded at the point of performance on a microprocessor. The result is improved fault determination which is faster, more accurate, and requires less infrastructure than the prior instantiation of the prognostication algorithms.
- In summary, on-board diagnostics for fleet maintenance is improved by embedding a microprocessor programmed with a prognostication algorithm on a vehicle.
- These and other features of the subject invention will be better understood in connection with the Detailed Description, in conjunction with the Drawings, of which:
-
FIG. 1 is a diagrammatic illustration of a prior art 30,000 plus gross ton vehicle having an onboard PRDICTR algorithm within the cab of the vehicle; -
FIG. 2 is a diagrammatic illustration of a light vehicle in which a microprocessor with a PRDICTR Light algorithm is utilized to permit the use of microprocessors; -
FIG. 3 is a listing of the on-board PRDICTR prior art requirements for modeling and simulation that creates a probability of a node for a given set of inputs, indicating that all inputs must be run each time in order to change the model and simulation used in the prognostication algorithm; and, -
FIG. 4 is a diagrammatic illustration of a set of inputs and outputs that describe the operation of a system at a point of performance, in which selected inputs and outputs are analyzed as to probability, thereby to be able to develop a stripped down PRDICTR algorithm based on acceptable probability, with the stripped, down PRDICTR algorithm embedded at the point of performance. - As can be seen from
FIG. 1 , the prior PRDICTR algorithms are utilized on Class 8 vehicles those such as vehicle 10 that are 30,000 plus gross weight vehicles, in which the on-board PRDICTRalgorithm 12 is run on an embeddedcomputer 14 within the vehicle. - The size and computational capabilities of
computer 14 are not those associated with microprocessors, but rather these computers have massive computational power, unsuitable for use in light vehicles due to size and complexity. - Referring to
FIG. 2 , alight vehicle 20 includes a microprocessor with a light version of the PRDICTR algorithm as illustrated at 22, with the microprocessor being embedded in the vehicle. The algorithm takes inputs from selected vehicle sensors and provides prognostic predications of vehicle failure modes. It is the purpose of the subject invention to provide a PRDICTR Light version of at prognostication algorithm to permit the use of microprocessors by eliminating running massive numbers of inputs each time in order to exercise the prognostication algorithm. - As shown in
FIG. 3 , it was the practice hereinbefore when using an on-board PRDICTR to provide modeling and simulation that would describe the probability of a node for a given set of inputs and an observed set of outputs. Thus, for a potential failure mode in a vehicle, it was necessary to run all of the inputs from all of the sensors each time it was necessary to change a model and simulation. This is an incredibly and computationally intense process; and one not readily adapted to light vehicles where only microprocessor processing is available. - Referring to
FIG. 4 , it is possible to develop a stripped down prognostication algorithm by providing a large number of inputs and a large number of outputs, and then ascertaining the probability for a given input and a given output. This involves a reduced data set wherein for instance the interaction of input I1 with input In, for instance at anode 30, and again at anode 32 produces an output 34 having an ascertainable probability. Having ascertained that the probability is sufficiently high, one can develop a PRDICTR algorithm and embed this PRDICTR algorithm at the point of performance on a microprocessor. The result is improved fault predictions and especially fault predictions that can be made at the vehicle and on common microprocessors. The result is improved fault determination which is faster, more accurate and requires less infrastructure. - Thus, what is developed is the ability to slim down the standard PRDICTR algorithm by sensing only a few of the input variables and developing a PRDICTR algorithm based on the result of these particular inputs.
- While the present invention has been described in connection with the preferred embodiments of the various figures, it is to be understood that other similar embodiments may be used or modifications or additions may be made to the described embodiment for performing the same function, of the present invention without deviating therefrom. Therefore, the present invention should not be limited to any single embodiment, but rather construed in breadth and scope in accordance with the recitation of the appended claims.
Claims (7)
1. A method of providing a computationally less intense prognostication algorithm by providing a stripped down version of a standard prognostication algorithm by using selected input sets and a selected output of a monitored system, determining the probability of the output and developing a prognostication algorithm utilizing modeling and simulation based on an acceptable probability.
2. The method of claim 2 , and further including the step of embedding the developed prognostication algorithm at the point of performance.
3. The method of claim 1 , wherein only one selected input and one selected output that describes the operation of the monitored system to determine the acceptable probability.
4. The method of claim 3 , wherein the result of the analysis of the single input and the single output is used to develop the prognostication algorithm.
5. The method of claim 1 , wherein multiple inputs are utilized with at single output for ascertaining acceptable probability.
6. The method of claim 5 , wherein the monitored system has nodes, and wherein when the probability of a node is sufficiently high, the inputs and output are used in he modeling and simulation to develop the prognostication algorithm.
7. The method of claim 3 , wherein the selected input and selected output determine the probability at a predetermined node in the monitored system, whereby a reduced set of inputs is utilized in developing the prognostication algorithm.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US14/629,600 US20150168950A1 (en) | 2010-04-09 | 2015-02-24 | Method and apparatus for providing on-board diagnostics |
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US34213310P | 2010-04-09 | 2010-04-09 | |
US12/807,923 US8977529B2 (en) | 2010-04-09 | 2010-09-16 | Method and apparatus for providing on-board diagnostics |
US14/629,600 US20150168950A1 (en) | 2010-04-09 | 2015-02-24 | Method and apparatus for providing on-board diagnostics |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/807,923 Continuation US8977529B2 (en) | 2010-04-09 | 2010-09-16 | Method and apparatus for providing on-board diagnostics |
Publications (1)
Publication Number | Publication Date |
---|---|
US20150168950A1 true US20150168950A1 (en) | 2015-06-18 |
Family
ID=50100660
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/807,923 Expired - Fee Related US8977529B2 (en) | 2010-04-09 | 2010-09-16 | Method and apparatus for providing on-board diagnostics |
US14/629,600 Abandoned US20150168950A1 (en) | 2010-04-09 | 2015-02-24 | Method and apparatus for providing on-board diagnostics |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/807,923 Expired - Fee Related US8977529B2 (en) | 2010-04-09 | 2010-09-16 | Method and apparatus for providing on-board diagnostics |
Country Status (1)
Country | Link |
---|---|
US (2) | US8977529B2 (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040168100A1 (en) * | 2000-12-04 | 2004-08-26 | Thottan Marina K. | Fault detection and prediction for management of computer networks |
US7260501B2 (en) * | 2004-04-21 | 2007-08-21 | University Of Connecticut | Intelligent model-based diagnostics for system monitoring, diagnosis and maintenance |
-
2010
- 2010-09-16 US US12/807,923 patent/US8977529B2/en not_active Expired - Fee Related
-
2015
- 2015-02-24 US US14/629,600 patent/US20150168950A1/en not_active Abandoned
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040168100A1 (en) * | 2000-12-04 | 2004-08-26 | Thottan Marina K. | Fault detection and prediction for management of computer networks |
US7260501B2 (en) * | 2004-04-21 | 2007-08-21 | University Of Connecticut | Intelligent model-based diagnostics for system monitoring, diagnosis and maintenance |
Also Published As
Publication number | Publication date |
---|---|
US8977529B2 (en) | 2015-03-10 |
US20140052418A1 (en) | 2014-02-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112559315B (en) | Test framework for automation objects | |
Velez et al. | Embedding vision‐based advanced driver assistance systems: a survey | |
CN107066375A (en) | Security critical software automation need-based test case generation system and method | |
CN112558555B (en) | Maintenance and debugging | |
US8103490B2 (en) | Method to aid the design of a system architecture | |
EP4006733A1 (en) | Fuzzy testing a software system | |
CN111046027A (en) | Missing value filling method and device for time series data | |
CN112818966B (en) | Multi-mode remote sensing image data detection method and system | |
CN111145076A (en) | Data parallelization processing method, system, equipment and storage medium | |
CN107220539A (en) | Need-based IMA safety verification analysis methods | |
Aslansefat et al. | Toward improving confidence in autonomous vehicle software: A study on traffic sign recognition systems | |
US8751094B2 (en) | Method for validation of a graphically based executable control specification using model extraction | |
Chen et al. | AI maintenance: a robustness perspective | |
US20110106515A1 (en) | System and method for resource identification | |
Macher et al. | Dependable integration concepts for human-centric ai-based systems | |
US8977529B2 (en) | Method and apparatus for providing on-board diagnostics | |
Soubra et al. | Functional size measurement for processor load estimation in AUTOSAR | |
US8751093B2 (en) | Hierarchical accumulated validation system and method | |
CN115033471A (en) | Method and system for automatically generating integrated test program by using system test program | |
Steimers et al. | Sources of risk and design principles of trustworthy artificial intelligence | |
KR20210023722A (en) | Method for testing a system to a request | |
US20200104234A1 (en) | Event log processing | |
CN114651190A (en) | Method, device and computer program for approving the use of a sensor system for detecting objects in the environment of a vehicle | |
Frisk et al. | A toolbox for design of diagnosis systems | |
US20240045728A1 (en) | Method for processing sensor data |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION |