ISO 13381-1:2025

Condition monitoring and diagnostics of machine systems - Prognostics - Part 1: General guidelines and requirements

This document provides guidance and requirements for the development and application of prognosis processes. It is intended to a) allow developers, providers, users and manufacturers to share common concepts of prognostics, b) enable users to determine the data, characteristics, processes and behaviours necessary for accurate prognosis, c) outline appropriate approaches and processes to prognostics development, and d) introduce prognostics concepts in order to facilitate future systems and training.

Surveillance et diagnostic des systèmes machines — Pronostic — Partie 1: Lignes directrices générales et exigences

L'ISO 13381-1:2015 fournit des lignes directrices relatives au développement des processus de pronostic. Elle est destinée à: ? permettre aux développeurs, aux prestataires, aux utilisateurs et aux fabricants de partager des concepts communs en matière de pronostic; ? permettre aux utilisateurs de déterminer les données, caractéristiques, processus et comportements requis pour pouvoir faire un pronostic précis; ? esquisser des approches et des processus appropriés pour le développement d'un pronostic, et ? introduire des concepts de pronostic afin de faciliter le développement futur de systèmes et de formations. D'autres parties comprendront l'introduction de concepts des formes suivantes d'approches pour le développement d'un pronostic: approches fondées sur les changements de performances (détermination des tendances) (ISO 13381‑2), techniques de durée d'utilisation guidées par les cycles (ISO 13381‑3), et modèles de prévision de la durée de vie restante (ISO 13381‑4).

General Information

• Status: Published
• Publication Date: 01-Sep-2025
• ICS: 17.160 - Vibrations, shock and vibration measurements
• Technical Committee: ISO/TC 108/SC 5 - Condition monitoring and diagnostics of machine systems
• Drafting Committee: ISO/TC 108/SC 5 - Condition monitoring and diagnostics of machine systems
• Current Stage: 6060 - International Standard published
• Start Date: 02-Sep-2025
• Due Date: 18-Oct-2025
• Completion Date: 02-Sep-2025

Relations

• Revises: ISO 13381-1:2015 - Condition monitoring and diagnostics of machines - Prognostics - Part 1: General guidelines
• Effective Date: 21-Oct-2023

Overview

ISO 13381-1:2025 - Condition monitoring and diagnostics of machine systems - Prognostics - Part 1: General guidelines and requirements - provides high-level guidance and mandatory requirements for developing and applying prognosis processes for machine systems. The third edition updates definitions, data requirements, modelling types and failure modelling techniques to help stakeholders produce reliable predictions of remaining useful life (RUL) and estimated time to failure (ETTF). The standard is intended to align terminology and practices so developers, providers, users and manufacturers can share consistent prognostics concepts.

Key topics and technical requirements

• Scope and purpose: Establish common concepts for prognostics and set out requirements for accurate prediction of future machine condition and risk.
• Data requirements: Detailed collection requirements including design specifications, monitored parameters, historical operation and maintenance records, failure investigation data, environmental inputs, and manufacturing configuration. Emphasizes data needed to validate and improve prognosis models.
• Prognosis concepts: Definitions and use of terms such as prognosis, prognostics, confidence level, RUL, predictive horizon, and ETTF.
• Failure and deterioration models: Guidance on modelling failure-mode behavior, modelling types (analytical, statistical, AI/ML), and integration of damage initiation and progression models.
• Generic prognosis process: Lifecycle from preprocessing and existing/future failure-mode prognosis to post-action prognosis and reporting. Includes guidance on confidence level determination and reporting formats.
• Trending and limits: Setting alert, alarm and trip (shutdown) limits and multi-parameter analysis for more robust prognostics.
• Support tools and techniques: Curve fitting, projection, superimposition, FMECA/FMSA, and AI/ML approaches where appropriate.

Practical applications and users

ISO 13381-1:2025 is practical for:

• Reliability, maintenance and condition monitoring engineers implementing predictive maintenance programs.
• Asset managers and operations teams using prognostics to schedule maintenance, reduce downtime and optimize spare parts.
• OEMs and system integrators designing prognostic-enabled equipment or digital twins.
• Data scientists and AI/ML engineers developing models for RUL estimation and failure prediction.
• Training providers and consultants who need standardized terminology and processes for workforce development.

Typical applications include RUL estimation, alarm/threshold setting, prognosis confidence assessment, component life-extension strategies, and integration of prognosis outputs with CMMS/ERP for cost-benefit decisions.

Related standards (normative references)

• ISO 2041 - Mechanical vibration, shock and condition monitoring - Vocabulary
• ISO 13372 - Condition monitoring and diagnostics of machines - Vocabulary
• ISO 13379‑1 - Data interpretation and diagnostics techniques - General guidelines
• ISO 17359 - Condition monitoring and diagnostics - General guidelines
• IEC 60812 (referenced for FMECA procedure)

Keywords: ISO 13381-1:2025, prognostics, condition monitoring, predictive maintenance, RUL, ETTF, failure modes, data requirements, confidence level.

Standards Content (Sample)

International
Standard
ISO 13381-1
Third edition
Condition monitoring and
2025-09
diagnostics of machine systems —
Prognostics —
Part 1:
General guidelines and
requirements
Surveillance et diagnostic des systèmes machines — Pronostic —
Partie 1: Lignes directrices générales et exigences
Reference number
© ISO 2025
All rights reserved. Unless otherwise specified, or required in the context of its implementation, no part of this publication may
be reproduced or utilized otherwise in any form or by any means, electronic or mechanical, including photocopying, or posting on
the internet or an intranet, without prior written permission. Permission can be requested from either ISO at the address below
or ISO’s member body in the country of the requester.
ISO copyright office
CP 401 • Ch. de Blandonnet 8
CH-1214 Vernier, Geneva
Phone: [phone]
Email: [e-mail]
Website: www.iso.org
Published in Switzerland
ii
Contents Page
Foreword .iv
Introduction .v
1 Scope . 1
2 Normative references . 1
3 Terms and definitions . 1
4 Data requirements . 2
5 Prognosis concepts . 4
5.1 Basic concepts .4
5.2 Influence factors .5
5.3 Trending, setting alert, alarm and trip (shutdown) limits .7
5.4 Multiple parameter analysis .9
5.5 Initiation criteria .11
5.6 Prognosis of failure mode initiation . . 12
6 Failure and deterioration models used for prognostics . 14
6.1 Failure mode behaviour modelling concepts .14
6.2 Modelling types .14
6.3 Artifical intelligence (AI) and machine learning (ML) . 15
7 Generic prognosis process .15
7.1 Prognosis confidence levels . 15
7.2 Prognosis process .16
7.2.1 General .16
7.2.2 Pre-processing .16
7.2.3 Existing failure mode prognosis .16
7.2.4 Future failure mode prognosis .16
7.2.5 Post-action prognosis .17
7.3 Prognosis report .17
Annex A (informative) Condition monitoring flow chart . 19
Annex B (informative) Example prognosis confidence level determination .20
Annex C (informative) Failure modelling techniques .21
Bibliography .23

iii
Foreword
ISO (the International Organization for Standardization) is a worldwide federation of national standards
bodies (ISO member bodies). The work of preparing International Standards is normally carried out through
ISO technical committees. Each member body interested in a subject for which a technical committee
has been established has the right to be represented on that committee. International organizations,
governmental and non-governmental, in liaison with ISO, also take part in the work. ISO collaborates closely
with the International Electrotechnical Commission (IEC) on all matters of electrotechnical standardization.
The procedures used to develop this document and those intended for its further maintenance are described
in the ISO/IEC Directives, Part 1. In particular, the different approval criteria needed for the different types
of ISO document should be noted. This document was drafted in accordance with the editorial rules of the
ISO/IEC Directives, Part 2 (see www.iso.org/directives).
ISO draws attention to the possibility that the implementation of this document may involve the use of (a)
patent(s). ISO takes no position concerning the evidence, validity or applicability of any claimed patent
rights in respect thereof. As of the date of publication of this document, ISO had not received notice of (a)
patent(s) which may be required to implement this document. However, implementers are cautioned that
this may not represent the latest information, which may be obtained from the patent database available at
www.iso.org/patents. ISO shall not be held responsible for identifying any or all such patent rights.
Any trade name used in this document is information given for the convenience of users and does not
constitute an endorsement.
For an explanation of the voluntary nature of standards, the meaning of ISO specific terms and expressions
related to conformity assessment, as well as information about ISO's adherence to the World Trade
Organization (WTO) principles in the Technical Barriers to Trade (TBT), see www.iso.org/iso/foreword.html.
This document was prepared by Technical Committee ISO/TC 108, Mechanical vibration, shock and condition
monitoring, Subcommittee SC 5, Condition monitoring and diagnostics of machine systems.
This third edition cancels and replaces the second edition (ISO 13381-1:2015), which has been technically
revised.
The main changes are as follows:
— update of definitions (for clarification purposes);
— revised data requirements;
— revised modelling types;
— revised failure modelling techniques (see Annex C);
— update of Bibliography.
A list of all parts in the ISO 13381 series can be found on the ISO website.
Any feedback or questions on this document should be directed to the user’s national standards body. A
complete listing of these bodies can be found at www.iso.org/members.html.

iv
Introduction
The complete process of machine condition monitoring consists of five distinct phases:
a) detection of problems (deviations from normal conditions);
b) diagnosis of the faults and their causes;
c) prognosis of future fault progression;
d) recommendation of actions;
e) post-mortems.
Machine health prognosis demands prediction of future machine integrity and deterioration so there can be
no exactitude in the process. Instead, prognosis requires statistical or testimonial approaches to be adopted.
Standardization in machine health prognosis therefore embodies guidelines, approaches, and concepts
rather than strict procedures or standard methodologies.
Prognosis of future fault progressions requires foreknowledge of the probable failure modes, future duties
to which the machine will or might be subjected, and a thorough understanding of the relationships between
failure modes and operating conditions. This may require an understanding of the physics underlying
the fault modes and demand the collection of previous duty and cumulative duty parameters, previous
maintenance history, inspection results, run-to-failure data, trajectories and associated operational data,
along with condition and performance parameters prior to extrapolations, projections and forecasts.
Prognosis processes need to be able to accommodate analytical damage models.
As computing power increases, and data storage decreases in cost, multiple-parameter analysis becomes
more complex and modelling becomes more sophisticated. Thus, the ability to predict the progression of
damage accumulation is achievable if the initiation criterion is known (expressed as a set of parameter
values for a given mode) in addition to future behaviour for a given set of conditions.

v
International Standard ISO 13381-1:2025(en)
Condition monitoring and diagnostics of machine systems —
Prognostics —
Part 1:
General guidelines and requirements
1 Scope
This document provides guidance and requirements for the development and application of prognosis
processes. It is intended to
a) allow developers, providers, users and manufacturers to share common concepts of prognostics,
b) enable users to determine the data, characteristics, processes and behaviours necessary for accurate
prognosis,
c) outline appropriate approaches and processes to prognostics development, and
d) introduce prognostics concepts in order to facilitate future systems and training.
2 Normative references
The following documents are referred to in the text in such a way that some or all of their content constitutes
requirements of this document. For dated references, only the edition cited applies. For undated references,
the latest edition of the referenced document (including any amendments) applies.
ISO 2041, Mechanical vibration, shock and condition monitoring — Vocabulary
ISO 13372, Condition monitoring and diagnostics of machines — Vocabulary
ISO 13379-1, Condition monitoring and diagnostics of machines — Data interpretation and diagnostics
techniques — Part 1: General guidelines
ISO 17359, Condition monitoring and diagnostics of machines — General guidelines
3 Terms and definitions
For the purposes of this document, the terms and definitions given in ISO 2041 and ISO 13372 and the
following apply.
3.1
prognosis
estimation of time to failure and risk for one or more incipient failure modes
[SOURCE: ISO 13372:2012, 10.2]
3.2
prognostics
analysis of the symptoms of faults to predict future condition and residual life within design parameters
[SOURCE: ISO 13372:2012, 1.15]
Note 1 to entry: Prognostics refers to the process of prediction whereas prognosis refers to the outcome.

3.3
confidence level
figure of merit (e.g. percentage) that indicates the degree of certainty that the diagnosis and/or prognosis
(3.1) is correct
Note 1 to entry: This figure essentially represents the cumulative effect of error sources on the final certainty or
confidence in the accuracy of the outcome. Such a figure can be determined algorithmically or by a weighted
assessment system.
3.4
root cause
set of conditions or actions that occur at the beginning of a sequence of events that result in the initiation of
a failure mode
[SOURCE: ISO 13372:2012, 8.9]
3.5
failure modes and effects criticality analysis
FMECA
FMEA with a criticality classification process based on the severity of the faults
Note 1 to entry: This is in comparison with the criticality thresholds.
[3]
Note 2 to entry: A FMECA procedure is also outlined in IEC 60812 .
[SOURCE: ISO 13372:2012, 8.3]
3.6
failure mode symptoms analysis
FMSA
process based on the FMECA that documents the symptoms produced by each failure mode and the most
effective detection and monitoring techniques to be used to develop and optimize a monitoring programme
Note 1 to entry: This process shall be in accordance with ISO 13379-1.
3.7
estimated time to failure
ETTF
estimation of the period from the current point in time to the point in time where the monitored machine
will fail
Note 1 to entry: Defined in Figure 2.
3.8
remaining useful life
RUL
remaining time before system health falls below a defined failure threshold
3.9
predictive horizon
threshold for the prediction of time to failure as desired by the user
4 Data requirements
4.1 The data requirements for condition monitoring shall be in accordance with ISO 17359 and shall form
the basis for the prognostic process and its pre-requisites. Prognostics may also require the collection of
documented data covering:
a) the original design specification and final design;

b) the total population of plant, machinery and components under observation along with the original
equipment specifications;
c) all monitored parameters and descriptors;
d) expert knowledge of baseline, commissioning, historical operation, maintenance, inspection and
failure data;
e) current and future operating and maintenance environments, regimes, requirements and schedules;
f) initial diagnosis inclusive of all existing failure modes;
g) failure models including single and multiple failure modes that can include statistics, existing and future
failure mode influence factors, initiation criteria and failure definition set points for all parameters, and
descriptors;
h) curve fitting, projection and superimposition techniques;
i) alarm limits;
j) trip (shut-down) limits;
k) performance thresholds relating to system health;
l) failure investigation results;
m) reliability, availability, maintainability, cost and safety data;
n) damage initiation data;
o) damage progression data;
p) manufacturing configuration state (e.g. lot number, batch number, serial number);
q) environmental data that has an impact on component health.
All this information may not be available in some applications and cases.
4.2 The specific objectives for the collection of reliability data relating to current condition and field
performance of machinery are:
a) survey the actual reliability to enable the predicted reliability characteristics of an item to be made and
compared with field data, and damage models and thereby to improve future predictions;
b) provide data for improving the reliability of both the current item and future developments;
c) provide data for verifying and validating models and algorithms.
4.3 The specific objectives for the collection of data relating to duties of machinery are:
a) survey the relationship between the achieved reliability and the work done to enable the comparison of
damage initiation and progression models with field data;
b) provide data for improving the damage estimation models of both the current item and its future
developments;
c) provide data for extending the range of applications for damage estimation models.
4.4 The specific objectives for the collection of cost data relating to monitored equipment usage,
production losses, damage losses, maintenance activities and inventories of machinery are:
a) survey the benefit-to-cost ratios of various alternative maintenance actions and programmes;

b) improve future maintenance decisions and programmes;
c) provide data for reducing the operating and maintenance costs of both the current item and future
embodiments;
d) provide cost data for the optimal organization and management of any maintenance programme (e.g. on-
condition maintenance, scheduled preventive maintenance, corrective maintenance, service personnel
and spare parts stores).
5 Prognosis concepts
5.1 Basic concepts
Prognosis is an estimation of time to failure and probability for one or more existing and/or future failure
modes. It is based on detailed knowledge and experience of the fault propagation process. The goal of a
prognostics programme is to provide the user with the capability to predict remaining useful life (RUL) with
a satisfactory level of confidence. This information can be used to drive appropriate operators’ decisions to
avert the failure, extend life through appropriate operational changes or simply to allow time to prepare for
the impending failure. The effectiveness of the prognosis is determined by the degree to which faults and
failure modes have known, age-related, performance-related or progressive deterioration characteristics
that are well-understood and supported by models.
A failure defined only in terms of the monitored parameters and descriptors from monitoring data is
insufficient to produce a prognosis.
The general conceptual basics of a prognosis process are to
— define the end point,
— determine or estimate the parameter or descriptor behaviours and the expected rate of deterioration,
— estimate current state of deterioration,
— estimate the expected remaining life or expected time to failure,
— define level of confidence, and
— establish the desired predictive horizon.
It is important to understand that diagnostics is retrospective in nature in that it focuses on existing data at
any given point in time.
Prognostics, however, focuses on the future and shall consider
a) the existing single and multiple failure modes and deterioration rates,
b) the initiation criteria for future failure modes,
c) the role of existing failure modes in the initiation of future failure modes,
d) the influence between existing and future failure modes and their deterioration rates,
e) the sensitivity to detection and change of existing and future failure modes by the current monitoring
techniques being used,
f) the design and variation of monitoring strategies to suit Items a) through e),
g) the effect of maintenance actions and/or operating conditions, and
h) the conditions or assumptions under which prognosis remains valid.

The sub-domains of interest are:
— the performance degradation,
— the cyclic usage, and
— the RUL prediction models.
Figure 1 a) shows the general relationship concepts between prognostics and diagnostics across the failure
progression timeline. Figure 1 b) shows another perspective of the relationship between diagnostic and
prognostic processes.
5.2 Influence factors
Influence factors are parameters that affect the deterioration rate of a failure mode (e.g. temperature,
viscosity, clearance, load, speed, operating conditions). Each influence factor can be considered a
contributing driver of an existing failure mode. Influence factors also affect the progression and initiation of
other existing or future faults.
One example, as shown in Figure 2, is when the initial parameter of vibration, caused by a fault in a lubricating
oil pump bearing (primary failure mode), influences the initiation of a seal failure (secondary failure mode),
which has a faster deterioration rate than the bearing. As this seal fails, the leakage of oil creates a loss of oil
delivery pressure, which influences the initiation of an impeller failure in the pump (tertiary failure mode),
which has a slower deterioration rate.
a) Prognostics and diagnostics across the failure progression timeline

b) Diagnostic and prognostic processes
NOTE Life usage and condition monitoring do not occur in all systems.
Figure 1 — Two perspectives of the diagnostic and prognostic processes

Key
X time
Y severity of parameter
1 PFM: primary failure mode
2 SFM: secondary failure mode
3 TFM: tertiary failure mode
IF influence factor
T estimated time to failure of the PFM
PFM
T estimated time to failure of the SFM
SFM
T estimated time to failure of the TFM
TFM
a
Time of secondary failure mode initiation.
b
Present time.
c
Time of tertiary failure mode initiation.
Figure 2 — Influence factors
5.3 Trending, setting alert, alarm and trip (shutdown) limits
The failure definition set point for a parameter or descriptor is the final value it reaches at the point in time
when the machine or component fails. This value is normally determined historically from failure history.
However, the trip set point is the parameter or descriptor value at which the machine is shut down and is
normally less than its failure set point. This value is normally determined from standards, manufacturers’
guidelines and experience and is the value normally used to define the failed condition. However, this value
is not normally reflective of the fully failed condition due to a lower set point being required to prevent
consequential damage or catastrophic failure.
Alert and alarm limits are normally set at a value less than the trip set point. Typically, this value is
determined based on the maintenance lead time required; however, such alert values should take into
account the following:
a) required confidence level of prognosis;

b) future
...